diff --git a/.github/workflows/image-scan.yml b/.github/workflows/image-scan.yml index 8fb11f40370..e72b8230232 100644 --- a/.github/workflows/image-scan.yml +++ b/.github/workflows/image-scan.yml @@ -16,7 +16,7 @@ on: - backend/Dockerfile - backend/main.py - deploy/lens/** - - litellm/proxy/lens/release.py + - litellm/proxy/lens/** - tests/e2e/migrations/lens_compose_smoke.sh - docker/component_entrypoint.sh - docker/entrypoint.sh @@ -40,6 +40,80 @@ concurrency: cancel-in-progress: true jobs: + lens-worker-image: + name: lens-worker-image (${{ matrix.arch }}) + runs-on: ${{ matrix.runner }} + if: >- + github.event_name != 'pull_request' || + github.event.pull_request.head.repo.full_name == github.repository + timeout-minutes: 15 + permissions: + contents: read + strategy: + fail-fast: false + matrix: + include: + - arch: amd64 + runner: ubuntu-latest + grype_sha256: edda0968d8827daab01d32b3cd7de192ae0915005e7bbfcfef9e68e79bc43343 + - arch: arm64 + runner: ubuntu-24.04-arm + grype_sha256: 553e4c36d9d61349830ba6034d43b8700a7f10576d3e2f4981c0fd2b96086465 + steps: + - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0 + with: + persist-credentials: false + - name: Build the release worker + env: + RELEASE_TAG: sha-${{ github.sha }} + run: docker build --build-arg LITELLM_RELEASE_TAG="${RELEASE_TAG}" -f deploy/lens/Dockerfile -t lens-worker-scan . + - name: Verify the standalone worker on a read-only filesystem + env: + RELEASE_TAG: sha-${{ github.sha }} + run: | + docker run --rm --network none --read-only --cap-drop ALL \ + --tmpfs /tmp:rw,noexec,nosuid,size=1g --security-opt no-new-privileges \ + -e EXPECTED_RELEASE_TAG="${RELEASE_TAG}" --entrypoint python lens-worker-scan -c ' + import os + import lens.worker + from lens.release import release_tag + from lens.trace_store import trace_store + assert os.getuid() == 65532 + assert release_tag() == os.environ["EXPECTED_RELEASE_TAG"] + with trace_store() as store: + assert store.count() == 0 + ' + - name: Reject a dependency whose hash has changed + run: | + docker build --target builder -f deploy/lens/Dockerfile -t lens-worker-deps . + sed -E 's/sha256:[0-9a-f]{64}/sha256:0000000000000000000000000000000000000000000000000000000000000000/g' \ + deploy/lens/requirements.lock > "$RUNNER_TEMP/tampered.lock" + if docker run --rm -v "$RUNNER_TEMP/tampered.lock:/tmp/tampered.lock:ro" \ + --entrypoint uv lens-worker-deps pip sync --python /app/.venv/bin/python \ + --require-hashes --only-binary :all: --reinstall --no-cache /tmp/tampered.lock \ + > "$RUNNER_TEMP/hash-check.log" 2>&1; then + echo "::error::Dependency hash mismatch was accepted" + exit 1 + fi + cat "$RUNNER_TEMP/hash-check.log" + grep -qi 'hash mismatch' "$RUNNER_TEMP/hash-check.log" + - name: Download Grype v0.114.0 + env: + ARCH: ${{ matrix.arch }} + GRYPE_SHA256: ${{ matrix.grype_sha256 }} + run: | + curl -fsSL --retry 3 -o "$RUNNER_TEMP/grype.tar.gz" \ + "https://github.com/anchore/grype/releases/download/v0.114.0/grype_0.114.0_linux_${ARCH}.tar.gz" + echo "${GRYPE_SHA256} $RUNNER_TEMP/grype.tar.gz" | sha256sum -c - + tar xzf "$RUNNER_TEMP/grype.tar.gz" -C "$RUNNER_TEMP" grype + chmod +x "$RUNNER_TEMP/grype" + - name: Scan the worker for fixable HIGH/CRITICAL CVEs + env: + GRYPE_MATCH_PYTHON_USING_CPES: "true" + run: | + "$RUNNER_TEMP/grype" lens-worker-scan \ + --config .grype.yaml --only-fixed --fail-on high --output table + image-scan: name: image-scan runs-on: ubuntu-latest diff --git a/.github/workflows/lens-worker.yml b/.github/workflows/lens-worker.yml index e3c47f35c36..896a598decd 100644 --- a/.github/workflows/lens-worker.yml +++ b/.github/workflows/lens-worker.yml @@ -61,11 +61,11 @@ jobs: -v "$PWD/tests/proxy_behavior/lens/worker_storage_smoke.py:/app/storage_smoke.py:ro" \ --entrypoint python lens-worker:${{ github.sha }} /app/storage_smoke.py - name: Publish versioned Lens worker - if: github.event_name != 'pull_request' && github.repository == 'BerriAI/litellm' + if: github.event_name != 'pull_request' && github.repository == 'BerriAI/litellm' && github.ref == 'refs/heads/main' env: REGISTRY_TOKEN: ${{ secrets.GITHUB_TOKEN }} REGISTRY_USER: ${{ github.actor }} - IMAGE: ghcr.io/berriai/litellm-lens-worker:sha-${{ github.sha }} + IMAGE: ghcr.io/berriai/litellm-lens-worker-dev:sha-${{ github.sha }} run: | printf '%s' "$REGISTRY_TOKEN" | docker login ghcr.io -u "$REGISTRY_USER" --password-stdin docker tag lens-worker:${{ github.sha }} "$IMAGE" diff --git a/Makefile b/Makefile index 40573fb68a3..ad84e2c4014 100644 --- a/Makefile +++ b/Makefile @@ -58,7 +58,7 @@ help: @echo " make test-unit-helm - Run helm unit tests" @echo " make test-rust-extension - Build the Rust extension and run its public Python tests" @echo " make rust-sqlx-prepare - Refresh litellm-rust/crates/db/.sqlx against a migrated Postgres container" - @echo " make lens-dev - Run proxy + Lens worker + hot-reload dashboard (LENS_DEV_PROXY_PORT, LENS_DEV_UI_PORT)" + @echo " make lens-dev - Run proxy + Lens worker + hot-reload dashboard (ARGS=\"--seed large\", LENS_DEV_PROXY_PORT, LENS_DEV_UI_PORT)" @echo "" @echo "Heavy targets (check, lint) queue for LITELLM_GATE_SLOTS machine-wide" @echo "slots (default 2; 0 disables) so parallel sessions don't thrash one machine." @@ -313,7 +313,7 @@ rust-sqlx-prepare: cd litellm-rust && cargo run -p litellm-db-testing --bin sqlx-prepare lens-dev: - ./scripts/lens_dev.sh + ./scripts/lens_dev.sh $(ARGS) test: install-test-deps $(UV_RUN) pytest tests/ diff --git a/deploy/lens/Dockerfile b/deploy/lens/Dockerfile index 3d7ddbe832f..84c45291c42 100644 --- a/deploy/lens/Dockerfile +++ b/deploy/lens/Dockerfile @@ -1,9 +1,27 @@ -FROM python:3.12-slim +ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:1d95114038f76513a9ace6fca107d5582b08c65981f81f61cb56bf7fd2ef216d +ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:1d95114038f76513a9ace6fca107d5582b08c65981f81f61cb56bf7fd2ef216d +ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a + +FROM $UV_IMAGE AS uvbin + +FROM $LITELLM_BUILD_IMAGE AS builder +COPY --from=uvbin /uv /usr/local/bin/uv +RUN apk add --no-cache python-3.13 +ENV UV_PYTHON_DOWNLOADS=0 UV_LINK_MODE=copy +WORKDIR /app +COPY deploy/lens/requirements.lock /tmp/requirements.lock +RUN uv venv --python python3.13 /app/.venv && \ + uv pip sync --python /app/.venv/bin/python --require-hashes --only-binary :all: /tmp/requirements.lock + +FROM $LITELLM_RUNTIME_IMAGE AS runtime ARG LITELLM_RELEASE_TAG="" RUN : "${LITELLM_RELEASE_TAG:?Pass --build-arg LITELLM_RELEASE_TAG matching the gateway}" -ENV LITELLM_RELEASE_TAG=${LITELLM_RELEASE_TAG} +RUN apk add --no-cache python-3.13 +ENV LITELLM_RELEASE_TAG=${LITELLM_RELEASE_TAG} \ + PATH="/app/.venv/bin:${PATH}" \ + PYTHONDONTWRITEBYTECODE=1 WORKDIR /app -RUN pip install --no-cache-dir httpx==0.28.1 pydantic==2.11.7 +COPY --from=builder /app/.venv /app/.venv COPY litellm/proxy/lens/__init__.py litellm/proxy/lens/models.py litellm/proxy/lens/trace_store.py litellm/proxy/lens/analysis.py litellm/proxy/lens/worker.py litellm/proxy/lens/release.py /app/lens/ COPY litellm/proxy/lens/prompts/ /app/lens/prompts/ USER 65532:65532 diff --git a/deploy/lens/Dockerfile.dockerignore b/deploy/lens/Dockerfile.dockerignore index 70fe9c83b6d..801c89d9dfe 100644 --- a/deploy/lens/Dockerfile.dockerignore +++ b/deploy/lens/Dockerfile.dockerignore @@ -1,4 +1,7 @@ ** +!deploy/ +!deploy/lens/ +!deploy/lens/requirements.lock !litellm/ !litellm/proxy/ !litellm/proxy/lens/ @@ -7,5 +10,6 @@ !litellm/proxy/lens/trace_store.py !litellm/proxy/lens/analysis.py !litellm/proxy/lens/worker.py +!litellm/proxy/lens/release.py !litellm/proxy/lens/prompts/ !litellm/proxy/lens/prompts/** diff --git a/deploy/lens/README.md b/deploy/lens/README.md index afd2f409e21..6f8c7d3940e 100644 --- a/deploy/lens/README.md +++ b/deploy/lens/README.md @@ -2,62 +2,74 @@ Lens reviews recorded activity and saves evidence-linked findings in the LiteLLM dashboard under Observability, Lens (`/ui/lens/`) -## Install the release stack +## Install -Each stable, RC, and dev release containing Lens publishes the worker at the same version on GHCR and Docker Hub. Use the [LiteLLM releases page](https://github.com/BerriAI/litellm/releases) to select a version that includes the coordinated worker release +Build LiteLLM and its worker from the same source commit with the same release identity. The worker runs separately and connects to your gateway using a limited worker token -For a new local installation, install Docker with Compose, download the two release files, and create a private environment file. Replace `X.Y.Z` with the release version, without `v` (RCs use `X.Y.Z-rc.N`) +### New local installation + +Install Docker with Compose and Git. This builds LiteLLM and its worker from the same checkout and starts the existing local tracing stack: ```bash -mkdir litellm-lens -cd litellm-lens -LENS_RELEASE=X.Y.Z -curl -fSLo compose.yaml "https://raw.githubusercontent.com/BerriAI/litellm/v${LENS_RELEASE}/deploy/lens/stack.yaml" -curl -fSLo config.yaml "https://raw.githubusercontent.com/BerriAI/litellm/v${LENS_RELEASE}/deploy/lens/config.yaml" -umask 077 -printf 'LITELLM_VERSION=%s\nLITELLM_MASTER_KEY=sk-%s\nLITELLM_SALT_KEY=sk-%s\n' \ - "$LENS_RELEASE" "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env -printf 'POSTGRES_PASSWORD=%s\nCLICKHOUSE_PASSWORD=%s\n' \ - "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" >> .env -docker compose up -d +git clone https://github.com/BerriAI/litellm.git +cd litellm +export LITELLM_RELEASE_TAG="sha-$(git rev-parse HEAD)" +export LENS_WORKER_IMAGE="litellm-lens-worker:${LITELLM_RELEASE_TAG}" +export OPENAI_API_KEY='sk-...' +docker build --build-arg LITELLM_RELEASE_TAG="$LITELLM_RELEASE_TAG" \ + -f deploy/lens/Dockerfile -t "$LENS_WORKER_IMAGE" . +docker compose -f docker/docker-compose.tracing.yml up -d --build ``` -Open `http://localhost:4000/ui/`, log in as `admin` with `LITELLM_MASTER_KEY` from `.env`, and add a model in the dashboard. In Lens, select **Connect worker**, choose that model and a monthly budget, then **Get install command**. Expand **Using Docker Compose or Helm?**, copy the worker token, and add `LENS_WORKER_TOKEN=` to `.env` +Open `http://localhost:4002/ui/` and sign in as `admin` with password `sk-1234`. Go to **Lens > Investigations > Connect worker**, choose a model and monthly budget, then **Get install command**. Expand **Using Docker Compose or Helm?** and copy the worker token. In the same terminal, run: ```bash -docker compose --profile lens up -d +export LITELLM_URL=http://litellm:4000 +export LENS_WORKER_TOKEN='' +docker compose -f docker/docker-compose.tracing.yml -f deploy/lens/compose.yaml up -d ``` -The stack starts LiteLLM, PostgreSQL, ClickHouse, and the worker from published images. The dashboard shows **Worker connected**. The worker has a limited token, no database credentials, and no provider keys. The stack exposes only the dashboard on localhost; use your normal ingress and managed databases for a public production deployment +The worker joins the gateway's Docker network, and the dashboard shows **Worker connected**. Save the token privately for restarts and upgrades -Keep `.env` private and preserve its salt key. Keep both named database volumes. To upgrade, wait for active investigations to finish, stop the worker, change only `LITELLM_VERSION`, then pull and recreate the stack: +This stack is for local evaluation: it binds to localhost and uses development database credentials. For a hosted deployment, keep your normal database, keys, networking, and deployment process. Build both images from one source revision with the same `LITELLM_RELEASE_TAG`, publish the worker to your registry, and set `LENS_WORKER_IMAGE` on LiteLLM to that image + +### Existing LiteLLM installation + +Keep your deployment and PostgreSQL database. A working gateway/worker pair can stay as it is until you upgrade both. For a gateway built from source, use its exact commit and `LITELLM_RELEASE_TAG`; a release version or the latest commit on `main` is not a substitute for that source identity + +The public development package is `ghcr.io/berriai/litellm-lens-worker-dev:sha-`. It publishes amd64 images on Lens-related changes, so an arbitrary source commit may have no image. Check the exact image exists before using it. If it is unavailable, your gateway uses a different release identity, or you need native arm64, build the worker from the gateway's checkout: ```bash -docker compose --profile lens stop lens-worker -# Update LITELLM_VERSION in .env to the new release -docker compose --profile lens pull -docker compose --profile lens up -d +export LITELLM_RELEASE_TAG='' +export LENS_WORKER_IMAGE='/litellm-lens-worker:' +docker build --build-arg LITELLM_RELEASE_TAG="$LITELLM_RELEASE_TAG" \ + -f deploy/lens/Dockerfile -t "$LENS_WORKER_IMAGE" . ``` -This preserves your investigations, findings, model credentials, and worker token. Never use `down -v` during an upgrade. If moving from an existing installation, keep its databases and add the standalone worker instead of creating an empty replacement stack +For a remote worker host, publish that image to a registry the host can pull from. Set the gateway's `LENS_WORKER_IMAGE` to the resulting image reference, restart the gateway using its normal deployment process, then copy its install command. Prefer the published image digest for hosted installations. Do not change the gateway's release identity just to accept another worker + +For Kubernetes or Render, run the standalone worker using `LITELLM_URL` and `LENS_WORKER_TOKEN` from setup. Keep existing databases and secrets. The worker needs no inbound port. ## Helm -The componentized `helm/litellm` chart includes an optional Lens worker. Configure PostgreSQL and ClickHouse as usual, install the chart, then obtain a limited worker token from Lens setup. Store it in a Kubernetes Secret and enable the worker in your values: +The componentized source chart at `helm/litellm` includes an optional Lens worker. Use the chart from the same checkout as your gateway and keep your component image overrides in your values. Configure PostgreSQL and ClickHouse as usual, install the chart, then obtain a limited worker token from Lens setup. Store it in a Kubernetes Secret and enable the worker in your values: ```yaml lensWorker: enabled: true + image: + repository: + digest: sha256: tokenSecret: name: litellm-lens-worker key: token ``` -The worker image defaults to the chart's application version, and the chart connects it to the backend service. Keep these values and the Secret when upgrading the chart so the gateway and worker upgrade together. `lensWorker.replicaCount` controls simultaneous investigations. To use a private registry or external proxy, set `lensWorker.image.repository`, `lensWorker.image.tag`, and `lensWorker.url`. The dashboard uses the chart's worker image for standalone install commands too +Set the worker repository and digest explicitly to an image built from the gateway's source commit and release identity. The chart connects the worker to the backend service. Keep these values and the Secret when upgrading the chart and update the gateway and worker image overrides together. `lensWorker.replicaCount` controls simultaneous investigations. To use a private registry or external proxy, set `lensWorker.image.repository`, `lensWorker.image.digest` (or `tag` for a source build), and `lensWorker.url`. A digest takes precedence over the tag. The dashboard uses the chart's worker image for standalone install commands too ## Standalone worker -Upgrade your existing LiteLLM proxy to a release that includes Lens with PostgreSQL and agent tracing. Configure one ClickHouse URL for trace writes, bounded reads, and Lens queries: +Start with a source deployment that includes Lens, PostgreSQL, and agent tracing, and prepare its matching worker as described above. Configure one ClickHouse URL for trace writes, bounded reads, and Lens queries: ```yaml general_settings: @@ -74,13 +86,13 @@ Retention changes require a proxy restart. ClickHouse removes expired rows durin In **Lens > Investigations**, click **Connect worker**, choose an analysis model and monthly limit, then **Get install command**. Use **Advanced options** to select an existing virtual key or change the proxy URL if the server running Docker needs a different network address. Copy the command and run it on your server. The dashboard shows **Worker connected** when the container checks in -The command already contains the compatible worker image and one worker token. The selected virtual key stays on the proxy; its secret is never sent to the worker. No source checkout, environment file, or second LiteLLM deployment is needed. Keep the command private because it includes the token. The LiteLLM release provides the dashboard and APIs; the container only runs background analysis +The command already contains the compatible worker image and one worker token. The selected virtual key stays on the proxy; its secret is never sent to the worker. Once the matching image is available on the worker host, no second LiteLLM deployment is needed. Keep the command private because it includes the token. The LiteLLM release provides the dashboard and APIs; the container only runs background analysis -The dashboard selects the worker image matching the running gateway release. Release images support Linux amd64 and arm64. CI also publishes `:sha-` development images; use those only with a gateway built from the same commit and release tag +The dashboard uses the gateway's `LENS_WORKER_IMAGE` override when set. Public `:sha-` development images must match both the gateway commit and release identity. Build from source for the worker host's native architecture After upgrading the gateway, update the worker image and redeploy it while keeping its proxy URL and token. Existing containers do not update automatically. If an investigation reports a worker compatibility error, update the image before retrying -For deployments managed with Compose, download `compose.yaml` and provide `LITELLM_URL`, `LENS_WORKER_TOKEN`, and `LITELLM_VERSION` (without `v`) in a private environment file. To use another registry, set `LENS_WORKER_IMAGE` to the compatible image instead of setting a version: +For deployments managed with Compose, download `compose.yaml` and provide `LITELLM_URL`, `LENS_WORKER_TOKEN`, and an explicit `LENS_WORKER_IMAGE` in a private environment file: ```bash docker compose --env-file /path/to/lens.env -f compose.yaml up -d @@ -160,6 +172,38 @@ curl "$LITELLM_URL/lens/$LENS_ID/runs/$BATCH_ID" -H "Authorization: Bearer $LITE Creation queues the first batch. Posting to `/lens/{id}/runs` queues another, or returns the existing active batch. The run response contains its ID under `jobs[0].id`. Poll the batch URL for status, findings and assessments. List responses omit large result payloads; request a batch to retrieve them. Supply an optional complete `settings` object on the runs POST for a one-off override; the saved lens stays unchanged. Selection accepts `team_id`, exact `filters`, and opaque `execution_ids` returned by `/lens/preview/sample`. Preview accepts `offset` and `as_of` to keep the time window fixed while paging. Feedback uses `PATCH /lens/{id}/findings/{finding_id}` with `status` and `reason` +## Local development + +`make lens-dev ARGS=--seed` starts the full dev stack. The live dashboard is at `http://localhost:3000/ui/lens/`, with login at `http://localhost:3000/ui/login/`. Next.js forwards API requests to the proxy on port 4000, so login and navigation stay in the live UI and edits hot-reload + +The default is Next.js dev with no production build (`LENS_DEV_BUILD_UI=0`). Set `LENS_DEV_BUILD_UI=1` when you also want a fresh static dashboard at `http://localhost:4000/ui/`. Build output goes to `.lens-dev/logs/ui-build.log`; a failed build stops startup. Both modes keep the live dashboard on port 3000. Startup checks the live login route before seeding and fails with the UI log path if Next.js exits. `LENS_DEV_STARTUP_TIMEOUT_SECONDS` controls startup readiness retries (default 300; `LENS_DEV_READINESS_REQUEST_TIMEOUT_SECONDS` caps each HTTP probe, default 5) + +For local fixture data, run `make lens-dev ARGS=--seed`. Use `make lens-dev ARGS="--seed large"` for 2,000 fixture copies, over one million spans and linked request logs. To seed a running stack without restarting it, use `make lens-dev ARGS="--seed-only --seed large --copies 100"`. The default profile replays one copy of every checked-in capture through authenticated `/v1/traces`, including failures, retries, streaming and multiple agent frameworks. Large seeds use the same parser and compressed ClickHouse writer in batches of four copies, and write matching request logs to PostgreSQL. The first and last batches verify linked spend totals through the proxy + +Seeds append fresh IDs on every invocation and spread copies over recent timestamps. Restarts without `SEED` do not add data. Lens excludes activity received in the last two minutes, so wait two minutes after seeding before checking investigation previews. `LENS_DEV_SEED_COPIES` overrides total copies, and `LENS_DEV_SEED_BATCH_COPIES` overrides copies per bulk insert (default 4, about 2,000 spans). Start with four or fewer on a constrained machine. Larger batches still respect the existing ClickHouse insert size limit; each capture is decoded separately within the OTLP safety budget. Large seeds test data volume and pagination, rather than concurrent ingestion throughput or review accuracy. They can use substantial disk space; adjust `--copies` for your machine. Seeding expects the generated local tracing configuration. The old `run_tracing_proxy_local.sh --seed` command forwards to Lens dev, using its ports and saved master key + +Local ingestion limits are explicit and configurable. Set OTLP and ClickHouse variables before starting the proxy and seeder so both processes use the same settings. Invalid, zero and negative values fail instead of silently falling back. Changing these limits does not require rebuilding Rust + +| Environment variable | Default | Controls | +| --- | --- | --- | +| `LENS_DEV_SEED_COPIES` | 1 default, 2000 large | Total fixture copies | +| `LENS_DEV_SEED_BATCH_COPIES` | 4 | Copies per bulk insert | +| `LENS_DEV_SEED_TIMEOUT_SECONDS` | 120 | Seeder HTTP timeout | +| `OTLP_MAX_BODY_BYTES` | 16777216 | HTTP body and decompressed payload bytes | +| `OTLP_MAX_CONCURRENT_INGESTS` | 2 | Concurrent proxy ingestion requests | +| `OTLP_MAX_ATTRIBUTE_VALUE_BYTES` | 65536 | Stored attribute/content bytes | +| `OTLP_MAX_DECODE_DEPTH` | 32 | Nested decode depth | +| `OTLP_MAX_DECODE_NODES` | 65536 | JSON values or protobuf fields per export | +| `OTLP_MAX_SPANS` | 4096 | Spans per export | +| `OTLP_MAX_ATTRIBUTES` | 256 | Attributes per resource, scope, span, event or link | +| `OTLP_MAX_EVENTS` | 256 | Events per span | +| `OTLP_MAX_LINKS` | 256 | Links per span | +| `OTLP_MAX_DECODED_SPAN_BYTES` | 16777216 | Decoded span allocation budget | +| `CLICKHOUSE_TRACE_MAX_INSERT_BYTES` | 67108864 | Encoded trace or spend insert bytes | +| `CLICKHOUSE_INSERT_TIMEOUT_SECONDS` | 30 | ClickHouse insert HTTP timeout | + +The wire parsers also enforce their library recursion limits (128 levels for JSON, 100 for protobuf). Raising the configured depth does not remove those parser limits. Bulk seeding parses each capture separately, keeping the per-export limits distinct from the bulk insert limit. Use smaller batches if an insert exceeds its byte budget. For example, `LENS_DEV_SEED_COPIES=100 LENS_DEV_SEED_BATCH_COPIES=2 make lens-dev ARGS="--seed large"` + ## Quality evaluation Run the checked-in cases against a configured real model. Expected labels are used only for scoring, never passed to the model. Dev and held-out cases include missing outcomes, failed tools, recovery, handoffs, unsupported claims, repeated work, long evidence and prompt injection. The background option adds clean arithmetic traces to test rare-issue discovery at scale; those repeated synthetic cases do not establish accuracy on every production workload @@ -187,10 +231,15 @@ Upgrades using `--use_prisma_db_push` stop before schema changes if any legacy L ## Release compatibility -Released gateway and worker images carry `LITELLM_RELEASE_TAG`. A worker announces its release and protocol before claiming an investigation. A mismatch returns HTTP 409 with the required image, leaving queued investigations untouched. During a rolling upgrade, workers wait for a gateway from their release +Gateway and worker builds carry the same `LITELLM_RELEASE_TAG`. A worker announces its release and protocol before claiming an investigation. A mismatch returns HTTP 409 with the required image, leaving queued investigations untouched. During a rolling upgrade, workers wait for a gateway from their release -The dashboard reads its image from the running gateway. `LENS_WORKER_IMAGE` overrides the registry/image for private deployments. Worker-only Compose accepts `LITELLM_VERSION` (without `v`) or an explicit `LENS_WORKER_IMAGE`. Release workers are available as `ghcr.io/berriai/litellm-lens-worker:vX.Y.Z` and `docker.io/litellm/litellm-lens-worker:vX.Y.Z`, including matching RC/dev suffixes, on amd64 and arm64 +The dashboard reads its image from the running gateway. `LENS_WORKER_IMAGE` overrides the registry/image for private deployments. Set an explicit `LENS_WORKER_IMAGE` for worker-only Compose. Verify that the image exists and matches the gateway before deploying it For source development, use `make lens-dev`, which gives the proxy and source worker the same commit identity. For custom containers, build both from the same checkout with `--build-arg LITELLM_RELEASE_TAG=sha-$(git rev-parse HEAD)` and set the proxy's `LENS_WORKER_IMAGE` to the worker image you built. An unlabelled custom build refuses worker setup and claims instead of guessing from the Python package version. Normal package-index installations use their installed release version -The hourly development pipeline pins all component images to the same selected commit and publishes its chart only after every build and worker smoke test succeeds. The public commit-tagged worker workflow publishes on Lens-related changes, so an arbitrary `main` commit may require building your own pair; do not substitute the newest available worker +The hourly development pipeline pins all component images to the same selected commit and publishes its chart only after every build and worker smoke test succeeds. The public commit-tagged worker workflow publishes to `ghcr.io/berriai/litellm-lens-worker-dev` on Lens-related changes, so an arbitrary `main` commit may require building your own pair; do not substitute the newest available worker + + +## Worker dependencies + +The worker uses the same digest-pinned Wolfi base and Python version as the component images. Python dependencies and their hashes are locked in `deploy/lens/requirements.lock`. To update them, edit `deploy/lens/requirements.in`, then run `uv pip compile --universal --python-version 3.13 --generate-hashes --no-emit-index-url deploy/lens/requirements.in -o deploy/lens/requirements.lock`. The image installs only the locked wheels with hash verification. CI builds and scans both native architectures diff --git a/deploy/lens/compose.yaml b/deploy/lens/compose.yaml index 799f0a4fb1e..aa915fef663 100644 --- a/deploy/lens/compose.yaml +++ b/deploy/lens/compose.yaml @@ -1,6 +1,6 @@ services: lens-worker: - image: ${LENS_WORKER_IMAGE:-ghcr.io/berriai/litellm-lens-worker:v${LITELLM_VERSION:?Set LITELLM_VERSION to the gateway release, without the v prefix}} + image: ${LENS_WORKER_IMAGE:-${LITELLM_VERSION:+ghcr.io/berriai/litellm-lens-worker:v}${LITELLM_VERSION:-}} environment: LITELLM_URL: ${LITELLM_URL:?Set the URL reachable from this container} LENS_WORKER_TOKEN: ${LENS_WORKER_TOKEN:?Create a worker credential in the Lens UI} diff --git a/deploy/lens/requirements.in b/deploy/lens/requirements.in new file mode 100644 index 00000000000..3122d7bd6f2 --- /dev/null +++ b/deploy/lens/requirements.in @@ -0,0 +1,2 @@ +httpx==0.28.1 +pydantic==2.13.4 diff --git a/deploy/lens/requirements.lock b/deploy/lens/requirements.lock new file mode 100644 index 00000000000..a895b6d645e --- /dev/null +++ b/deploy/lens/requirements.lock @@ -0,0 +1,172 @@ +# This file was autogenerated by uv via the following command: +# uv pip compile --universal --python-version 3.13 --generate-hashes --no-emit-index-url deploy/lens/requirements.in -o deploy/lens/requirements.lock +annotated-types==0.8.0 \ + --hash=sha256:13b2beaad985e05e2d6407ee4c4f35590b11f8d693a258a561055cac8f64cab7 \ + --hash=sha256:f072f4d804ea359e4eaf198b1af7a8b0943881a87f31bb764f8bf219bb9419e0 + # via pydantic +anyio==4.15.1 \ + --hash=sha256:6152fdbbf9a77fdec97731721bebf7c4c44f7c29b424b0065826173efc7ed101 \ + --hash=sha256:9f28306018cbd6d329e64a36d58256edff76dd996fe423bc957326e578b82a94 + # via httpx +certifi==2026.7.22 \ + --hash=sha256:62f22742b58a1a33014a2b6b706588a8d7e2a88ae7bd1a6ebe8c992928483775 \ + --hash=sha256:741e2c3b351ddf169a738da9f2c048608ff7f2c5cc02f1ebc6b118bb090d5d55 + # via + # httpcore + # httpx +h11==0.16.0 \ + --hash=sha256:4e35b956cf45792e4caa5885e69fba00bdbc6ffafbfa020300e549b208ee5ff1 \ + --hash=sha256:63cf8bbe7522de3bf65932fda1d9c2772064ffb3dae62d55932da54b31cb6c86 + # via httpcore +httpcore==1.0.9 \ + --hash=sha256:2d400746a40668fc9dec9810239072b40b4484b640a8c38fd654a024c7a1bf55 \ + --hash=sha256:6e34463af53fd2ab5d807f399a9b45ea31c3dfa2276f15a2c3f00afff6e176e8 + # via httpx +httpx==0.28.1 \ + --hash=sha256:75e98c5f16b0f35b567856f597f06ff2270a374470a5c2392242528e3e3e42fc \ + --hash=sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad + # via -r deploy/lens/requirements.in +idna==3.20 \ + --hash=sha256:a7db850025b95ded1eae8a46181a1a6c56c92c96f0e2b005d9ff8dc0210cab44 \ + --hash=sha256:ab7ae7122974553370f0bdb919e1a960b2cd1bc1ef0276416d896db81c14582c + # via + # anyio + # httpx +pydantic==2.13.4 \ + --hash=sha256:45a282cde31d808236fd7ea9d919b128653c8b38b393d1c4ab335c62924d9aba \ + --hash=sha256:c40756b57adaa8b1efeeced5c196f3f3b7c435f90e84ea7f443901bec8099ef6 + # via -r deploy/lens/requirements.in +pydantic-core==2.46.4 \ + --hash=sha256:00c603d540afdd6b80eb39f078f33ebd46211f02f33e34a32d9f053bba711de0 \ + --hash=sha256:0186750b482eefa11d7f435892b09c5c606193ef3375bcf94aa00ae6bfb66262 \ + --hash=sha256:041bde0a48fd37cf71cab1c9d56d3e8625a3793fef1f7dd232b3ff37e978ecda \ + --hash=sha256:0c563b08bca408dc7f65f700633d8442fffb2421fc47b8101377e9fd65051ff0 \ + --hash=sha256:0cbe8b01f948de4286c74cdd6c667aceb38f5c1e26f0693b3983d9d74887c65e \ + --hash=sha256:0ce40cd7b21210e99342afafbd4d0f76d784eb5b1d60f3bdc566be4983c6c73b \ + --hash=sha256:0e96592440881c74a213e5ad528e2b24d3d4f940de2766bed9010ab1d9e51594 \ + --hash=sha256:10e17cbb10a330363733efc4d7c4d0dd827ac0909b8f6a6542298fed1ea62f29 \ + --hash=sha256:133878133d271ade3d41d1bfb2a45ec38dbdbda40bc065921c6b04e4630127e2 \ + --hash=sha256:14d4edf427bdcf950a8a02d7cb44a08614388dd6e1bdcbf4f67504fa7887da9c \ + --hash=sha256:14f4c5d6db102bd796a627bbb3a17b4cf4574b9ae861d8b7c9a9661c6dd3362d \ + --hash=sha256:17299feefe090f2caa5b8e37222bb5f663e4935a8bfa6931d4102e5df1a9f398 \ + --hash=sha256:184c081504d17f1c1066e430e117142b2c77d9448a97f7b65c6ac9fd9aee238d \ + --hash=sha256:18e5ceec2ab67e6d5f1a9085e5a24c9c4e2ac4545730bfe668680bca05e555f3 \ + --hash=sha256:19e51f073cd3df251856a8a4189fbdf1de4012c3ebacfb1884f94f1eb406079f \ + --hash=sha256:1a7dd0b3ee80d90150e3495a3a13ac34dbcbfd4f012996a6a1d8900e91b5c0fb \ + --hash=sha256:1d8ba486450b14f3b1d63bc521d410ec7565e52f887b9fb671791886436a42f7 \ + --hash=sha256:2108ba5c1c1eca18030634489dc544844144ee36357f2f9f780b93e7ddbb44b5 \ + --hash=sha256:228ee9bae8bef5b1e97ec58302f80357c37199e0d0a99174e138d28e6957b9d9 \ + --hash=sha256:23ace664830ee0bfe014a0c7bc248b1f7f25ed7ad103852c317624a1083af462 \ + --hash=sha256:2412e734dcb48da14d4e4006b82b46b74f2518b8a26ee7e58c6844a6cd6d03c4 \ + --hash=sha256:29c61fc04a3d840155ff08e475a04809278972fe6aef51e2720554e96367e34b \ + --hash=sha256:2f84c03c8607173d16b5a854ec68a2f9079ae03237a54fb506d13af47e1d018d \ + --hash=sha256:3009f12e4e90b7f88b4f9adb1b0c4a3d58fe7820f3238c190047209d148026df \ + --hash=sha256:3245406455a5d98187ec35530fd772b1d799b26667980872c8d4614991e2c4a2 \ + --hash=sha256:3447661d99f75a3683a4cf5c87da72f2161964611864dbbeac7fbb118bb4bfc0 \ + --hash=sha256:372429a130e469c9cd698925ce5fc50940b7a1336b0d82038e63d5bbc4edc519 \ + --hash=sha256:395aebd9183f9d112f569aeb5b2214d1a10a33bec8456447f7fbdfa51d38d4cd \ + --hash=sha256:3a233125ac121aa3ffba9a2b59edfc4a985a76092dc8279586ab4b71390875e7 \ + --hash=sha256:3be77f45df024d789a672ae34f8b06fb346c4f9f46ea714956660ea4862e89ac \ + --hash=sha256:3bf92c5d0e00fefaab325a4d27828fe6b6e2a21848686b5b60d2d9eeb09d76c6 \ + --hash=sha256:3ecbc122d18468d06ca279dc26a8c2e2d5acb10943bb35e36ae92096dc3b5565 \ + --hash=sha256:3fb702cd90b0446a3a1c5e470bfa0dd23c0233b676a9099ddcc964fa6ca13898 \ + --hash=sha256:428e04521a40150c85216fc8b85e8d39fece235a9cf5e383761238c7fa9b96fb \ + --hash=sha256:432c179df7874eeb73307aad2df0755e1ae0efa61ff0ea89b93e194411ae3928 \ + --hash=sha256:4a05d69cba51d852c5c3e92758653245a50c0b646ced0cf05bd793ed592839d6 \ + --hash=sha256:4c63ebc82684aa89d9a3bcbd13d515b3be44250dc68dd3bd81526c1cb31286c3 \ + --hash=sha256:4fc73cb559bdb54b1134a706a2802a4cddd27a0633f5abb7e53056268751ac6a \ + --hash=sha256:4fcbe087dbc2068af7eda3aa87634eba216dbda64d1ae73c8684b621d33f6596 \ + --hash=sha256:56cb4851bcaf3d117eddcef4fe66afd750a50274b0da8e22be256d10e5611987 \ + --hash=sha256:5855698a4856556d86e8e6cd8434bc3ac0314ee8e12089ae0e143f64c6256e4e \ + --hash=sha256:5a4330cdbc57162e4b3aa303f588ba752257694c9c9be3e7ebb11b4aca659b5d \ + --hash=sha256:5b712b53160b79a5850310b912a5ef8e57e56947c8ad690c227f5c9d7e561712 \ + --hash=sha256:5d5902252db0d3cedf8d4a1bc68f70eeb430f7e4c7104c8c476753519b423008 \ + --hash=sha256:617d7e2ca7dcb8c5cf6bcb8c59b8832c94b36196bbf1cbd1bfb56ed341905edd \ + --hash=sha256:62f875393d7f270851f20523dd2e29f082bcc82292d66db2b64ea71f64b6e1c1 \ + --hash=sha256:633147d34cf4550417f12e2b1a0383973bdf5cdfde212cb09e9a581cf10820be \ + --hash=sha256:66ce7632c22d837c95301830e111ad0128a32b8207533b60896a96c4915192ea \ + --hash=sha256:6b3ace8194b0e5204818c92802dcdca7fc6d88aabbb799d7c795540d9cd6d292 \ + --hash=sha256:6f2eeda33a839975441c86a4119e1383c50b47faf0cbb5176985565c6bb02c33 \ + --hash=sha256:7027560ee92211647d0d34e3f7cd6f50da56399d26a9c8ad0da286d3869a53f3 \ + --hash=sha256:7283d57845ecf5a163403eb0702dfc220cc4fbdd18919cb5ccea4f95ee1cdab4 \ + --hash=sha256:7a5f930472650a82629163023e630d160863fce524c616f4e5186e5de9d9a49b \ + --hash=sha256:7bfb192b3f4b9e8a89b6277b6ce787564f62cfd272055f6e685726b111dc7826 \ + --hash=sha256:811ff8e9c313ab425368bcbb36e5c4ebd7108c2bbf4e4089cfbb0b01eff63fac \ + --hash=sha256:8233f2947cf85404441fd7e0085f53b10c93e0ee78611099b5c7237e36aacbf7 \ + --hash=sha256:82cf5301172168103724d49a1444d3378cb20cdee30b116a1bd6031236298a5d \ + --hash=sha256:8358a950c8909158e3df31538a7e4edc2d7265a7c54b47f0864d9e5bae9dcebf \ + --hash=sha256:85bb3611ff1802f3ee7fdd7dbff26b56f343fb432d57a4728fdd49b6ef35e2f4 \ + --hash=sha256:86e1a4418c6cd97d60c95c71164158eaf7324fae7b0923264016baa993eba6fc \ + --hash=sha256:8b9bab013d1c7a79d3501ff86d0bc9c31bf587db4551677b96bec07df78c6b15 \ + --hash=sha256:8c5dac79fa1614d1e06ca695109c6105923bd9c7d1d6c918d4e637b7e6b32fd3 \ + --hash=sha256:8d0820e8192167f80d88d64038e609c31452eeca865b4e1d9950a27a4609b00b \ + --hash=sha256:8daafc69c93ee8a0204506a3b6b30f586ef54028f52aeeeb5c4cfc5184fd5914 \ + --hash=sha256:9037063db01f09b09e237c282b6792bd4da634b5402c4e7f0c61effed7701a04 \ + --hash=sha256:905a0ed8ea6f2d61c1738835f99b699348d7857379083e5fc497fa0c967a407c \ + --hash=sha256:90884113d8b48f760e9587002789ddd741e76ab9f89518cd1e43b1f1a52ec44b \ + --hash=sha256:91a06d2e259ecfbd8c901d70c3c507900458498142b3026a296b7de4d1322cc9 \ + --hash=sha256:926c9541b14b12b1681dca8a0b75feb510b06c6341b70a8e500c2fdcff837cce \ + --hash=sha256:9401557acd873c3a7f3eb9383edef8ac4968f9510e340f4808d427e75667e7b4 \ + --hash=sha256:9551187363ffc0de2a00b2e47c25aeaeb1020b69b668762966df15fc5659dd5a \ + --hash=sha256:962ccbab7b642487b1d8b7df90ef677e03134cf1fd8880bf698649b22a69371f \ + --hash=sha256:97e7cf2be5c77b7d1a9713a05605d49460d02c6078d38d8bef3cbe323c548424 \ + --hash=sha256:9aa768456404a8bf48a4406685ac2bec8e72b62c69313734fa3b73cf33b3a894 \ + --hash=sha256:9bc519fbf2b7578398853d815009ae5e4d4603d12f4e3f91da8c06852d3da3e9 \ + --hash=sha256:9d56801be94b86a9da183e5f3766e6310752b99ff647e38b09a9500d88e46e76 \ + --hash=sha256:9f444c499b3eefd3a92e348059471ea0c3a6e303d9c1cec09fa748fd9f895201 \ + --hash=sha256:9fa8ae11da9e2b3126c6426f147e0fba88d96d65921799bb30c6abd1cb2c97fb \ + --hash=sha256:a0f62d0a58f4e7da165457e995725421e0064f2255d8eccebc49f41bbc23b109 \ + --hash=sha256:a396dcc17e5a0b164dbe026896245a4fa9ff402edca1dff0be3d53a517f74de4 \ + --hash=sha256:aaa2a54443eff1950ba5ddc6b6ccda0d9c84a364276a62f969bdf2a390650848 \ + --hash=sha256:ad785e92e6dc634c21555edc8bd6b64957ab844541bcb96a1366c202951ae526 \ + --hash=sha256:af8244b2bef6aaad6d92cda81372de7f8c8d36c9f0c3ea36e827c60e7d9467a0 \ + --hash=sha256:b078afbc25f3a1436c7a1d2cd3e322497ee99615ba97c563566fdf46aff1ee01 \ + --hash=sha256:b2f69dec1725e79a012d920df1707de5caf7ed5e08f3be4435e25803efc47458 \ + --hash=sha256:b8458003118a712e66286df6a707db01c52c0f52f7db8e4a38f0da1d3b94fc4e \ + --hash=sha256:bb63e0198ca18aad131c089b9204c23079c3afa95487e561f4c522d519e55aba \ + --hash=sha256:bfec22eab3c8cc2ceec0248aec886624116dc079afa027ecc8ad4a7e62010f8a \ + --hash=sha256:c1747f85cee84c26985853c6f3d9bd3e75da5212912443fa111c113b9c246f39 \ + --hash=sha256:c1b3f518abeca3aa13c712fd202306e145abf59a18b094a6bafb2d2bbf59192c \ + --hash=sha256:c50f2528cf200c5eed56faf3f4e22fcd5f38c157a8b78576e6ba3168ec35f000 \ + --hash=sha256:c68fcd102d71ea85c5b2dfac3f4f8476eff42a9e078fd5faefff6d145063536b \ + --hash=sha256:c7a7bd4e39e8e4c12c39cd480356842b6a8a06e41b23a55a5e3e191718838ddf \ + --hash=sha256:c94f0688e7b8d0a67abf40e57a7eaaecd17cc9586706a31b76c031f63df052b4 \ + --hash=sha256:cbaf13819775b7f769bf4a1f066cb6df7a28d4480081a589828ef190226881cd \ + --hash=sha256:cd2213145bcc2ba85884d0ac63d222fece9209678f77b9b4d76f054c561adb28 \ + --hash=sha256:ce5c1d2a8b27468f433ca974829c44060b8097eedc39933e3c206a90ee49c4a9 \ + --hash=sha256:d396ec2b979760aaf3218e76c24e65bd0aca24983298653b3a9d7a45f9e47b30 \ + --hash=sha256:d51026d73fcfd93610abc7b27789c26b313920fcfb20e27462d74a7f8b06e983 \ + --hash=sha256:d80ee3d731373b24cebbc10d689ca4ee1875caf0d5703a245db18efd4dd37fc1 \ + --hash=sha256:d995260fdf4e1db774581b4900e0f832abe3c7c84996726bbc161b19c8f29e76 \ + --hash=sha256:da4b951fe36dc7c3a1ccb4e3cd1747c3542b8c9ceede8fc86cae054e764485f5 \ + --hash=sha256:daa27d92c36f24388fe3ad306b174781c747627f134452e4f128ea00ce1fe8c4 \ + --hash=sha256:db06ffe51636ffe9ca531fe9023dd64bdd794be8754cb5df57c5498ae5b518a7 \ + --hash=sha256:e0d65b8c354be7fb5f720c3caa8bc940bc2d20ce749c8e06135f07f8ed95dd7c \ + --hash=sha256:e68b7a074f65a2fd746c52a7ce6142ab7006074ac269ace0c25cd8ba171f8066 \ + --hash=sha256:e739fee756ba1010f8bcccb534252e85a35fe45ae92c295a06059ce58b74ccd3 \ + --hash=sha256:e846ae7835bf0703ae43f534ab79a867146dadd59dc9ca5c8b53d5c8f7c9ef02 \ + --hash=sha256:e9c26f834c65f5752f3f06cb08cb86a913ceb7274d0db6e267808a708b46bc89 \ + --hash=sha256:ea793e075b70290d89d8142074262885d3f7da19634845135751bd6344f73b50 \ + --hash=sha256:f027324c56cd5406ca49c124b0db10e56c69064fec039acc571c29020cc87c76 \ + --hash=sha256:f13a646d65d09fbf1bc6b3a9635d30095c8e7e5cc419ff35ecc563c5fd04cd49 \ + --hash=sha256:f47286a97f0bc9b8859519809077b91b2cefe4ae47fcbf5e466a009c1c5d742b \ + --hash=sha256:f747929cf940cddb5b3668a390056ddd5ba2e5010615ea2dcf4f9c4f3ab8791d \ + --hash=sha256:f99626688942fb746e545232e7726926f3be91b5975f8b55327665fafda991c7 \ + --hash=sha256:f9fa868638bf362d3d138ea55829cefb3d5f4b0d7f142234382a15e2485dbec4 \ + --hash=sha256:fbdb89b3e1c94a30cc5edfce477c6e6a5dc4d8f84665b455c27582f211a1c72c \ + --hash=sha256:fc010ab034c8c7452522748bf937df58020d256ccae0874463d1f4d01758af8e \ + --hash=sha256:fc3e9034a63de20e15e8ade85358bc6efc614008cab72898b4b4952bea0509ff \ + --hash=sha256:fd8b3d9fd264be37976686c7f65cd52a83f5e84f4bfd2adf9c1d469676bbb6ae + # via pydantic +typing-extensions==4.16.0 \ + --hash=sha256:481caa481374e813c1b176ada14e97f1f67a4539ce9cfeb3f350d78d6370c2e8 \ + --hash=sha256:dc983d19a509c94dba722ee6abd33940f7c05a89e243c47e907eb4db6f1a43e5 + # via + # anyio + # pydantic + # pydantic-core + # typing-inspection +typing-inspection==0.4.4 \ + --hash=sha256:547274fa6b0a561ccf549cc9524b999a578e737d015d8709d021f9d0d13bea47 \ + --hash=sha256:65b8397ba37ccbce054456aaccddfc91e6e3083c92824df348d96ca832f3f147 + # via pydantic diff --git a/docker/docker-compose.tracing.yml b/docker/docker-compose.tracing.yml index 8f960d50872..c8d90fbc0ae 100644 --- a/docker/docker-compose.tracing.yml +++ b/docker/docker-compose.tracing.yml @@ -5,6 +5,8 @@ services: build: context: .. target: runtime + args: + LITELLM_RELEASE_TAG: ${LITELLM_RELEASE_TAG:-} command: ["--config", "/app/tracing-config.yaml", "--port", "4000"] environment: LITELLM_MASTER_KEY: sk-1234 @@ -15,6 +17,7 @@ services: CLICKHOUSE_URL: http://default:local-tracing@clickhouse:8123 CLICKHOUSE_DATABASE: litellm OPENAI_API_KEY: ${OPENAI_API_KEY:-} + LENS_WORKER_IMAGE: ${LENS_WORKER_IMAGE:-} volumes: - ./tracing-config.yaml:/app/tracing-config.yaml:ro ports: diff --git a/helm/litellm/templates/_helpers.tpl b/helm/litellm/templates/_helpers.tpl index 2b7fdfb5fd7..eb7433c279a 100644 --- a/helm/litellm/templates/_helpers.tpl +++ b/helm/litellm/templates/_helpers.tpl @@ -472,10 +472,21 @@ collector containers through an emptyDir. Empty when the sidecar is off or gateway.collector.address is a tcp://127.0.0.1: address. */}} {{- define "litellm.lensWorker.image" -}} +{{- if .Values.lensWorker.image.digest -}} +{{- if not (regexMatch "^sha256:[0-9a-f]{64}$" .Values.lensWorker.image.digest) -}} +{{- fail "lensWorker.image.digest must be sha256 followed by 64 lowercase hex characters" -}} +{{- end -}} +{{- printf "%s@%s" .Values.lensWorker.image.repository .Values.lensWorker.image.digest -}} +{{- else -}} {{- $backendTag := .Values.backend.image.tag | default .Chart.AppVersion -}} {{- $releaseTag := ternary (printf "v%s" $backendTag) $backendTag (regexMatch "^[0-9]" $backendTag) -}} {{- $tag := .Values.lensWorker.image.tag | default $releaseTag -}} -{{- printf "%s:%s" .Values.lensWorker.image.repository $tag -}} +{{- $repository := .Values.lensWorker.image.repository -}} +{{- if and (hasPrefix "sha-" $tag) (eq $repository "ghcr.io/berriai/litellm-lens-worker") -}} +{{- $repository = "ghcr.io/berriai/litellm-lens-worker-dev" -}} +{{- end -}} +{{- printf "%s:%s" $repository $tag -}} +{{- end -}} {{- end -}} {{- define "litellm.gateway.collectorSocketDir" -}} diff --git a/helm/litellm/tests/lens_worker_tests.yaml b/helm/litellm/tests/lens_worker_tests.yaml index 5230f14efb4..9a83a4af6a4 100644 --- a/helm/litellm/tests/lens_worker_tests.yaml +++ b/helm/litellm/tests/lens_worker_tests.yaml @@ -6,6 +6,66 @@ templates: values: - ./values/required.yaml tests: + - it: installs the development package for a source commit + template: lens/deployment.yaml + set: + backend.image.tag: sha-0123456789abcdef + lensWorker.enabled: true + lensWorker.tokenSecret.name: lens-credential + asserts: + - equal: + path: spec.template.spec.containers[0].image + value: ghcr.io/berriai/litellm-lens-worker-dev:sha-0123456789abcdef + - it: advertises the development package for standalone source workers + template: backend/deployment.yaml + set: + backend.image.tag: sha-0123456789abcdef + asserts: + - contains: + path: spec.template.spec.containers[0].env + content: + name: LENS_WORKER_IMAGE + value: ghcr.io/berriai/litellm-lens-worker-dev:sha-0123456789abcdef + - it: preserves an explicit private source image repository + template: lens/deployment.yaml + set: + backend.image.tag: sha-0123456789abcdef + lensWorker.enabled: true + lensWorker.tokenSecret.name: lens-credential + lensWorker.image.repository: registry.example/lens-worker + asserts: + - equal: + path: spec.template.spec.containers[0].image + value: registry.example/lens-worker:sha-0123456789abcdef + - it: pins the worker to its approved digest even when its tag changes + template: lens/deployment.yaml + set: + lensWorker.enabled: true + lensWorker.tokenSecret.name: lens-credential + lensWorker.image.tag: replaced-release + lensWorker.image.digest: sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + asserts: + - equal: + path: spec.template.spec.containers[0].image + value: ghcr.io/berriai/litellm-lens-worker@sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + - it: advertises the approved digest to standalone installers + template: backend/deployment.yaml + set: + lensWorker.image.tag: replaced-release + lensWorker.image.digest: sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + asserts: + - contains: + path: spec.template.spec.containers[0].env + content: + name: LENS_WORKER_IMAGE + value: ghcr.io/berriai/litellm-lens-worker@sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + - it: refuses a malformed digest instead of falling back to the tag + template: backend/deployment.yaml + set: + lensWorker.image.digest: sha256:invalid + asserts: + - failedTemplate: + errorMessage: lensWorker.image.digest must be sha256 followed by 64 lowercase hex characters - it: keeps the worker opt in template: lens/deployment.yaml asserts: diff --git a/helm/litellm/values.yaml b/helm/litellm/values.yaml index 6964dfd2b6e..cf3334f6156 100644 --- a/helm/litellm/values.yaml +++ b/helm/litellm/values.yaml @@ -636,6 +636,7 @@ lensWorker: image: repository: ghcr.io/berriai/litellm-lens-worker tag: "" + digest: "" pullPolicy: IfNotPresent tokenSecret: name: "" diff --git a/litellm-proxy-extras/litellm_proxy_extras/utils.py b/litellm-proxy-extras/litellm_proxy_extras/utils.py index 245244250ee..1fd292b8137 100644 --- a/litellm-proxy-extras/litellm_proxy_extras/utils.py +++ b/litellm-proxy-extras/litellm_proxy_extras/utils.py @@ -1,3 +1,4 @@ +import functools import glob import os import random @@ -10,7 +11,8 @@ import time from collections.abc import Callable from dataclasses import dataclass, replace from pathlib import Path -from typing import TYPE_CHECKING, Final, Optional +from typing import TYPE_CHECKING, Final, Optional, Union +from urllib.parse import unquote, urlsplit from litellm_proxy_extras import prisma_toolchain from litellm_proxy_extras._logging import logger @@ -202,6 +204,66 @@ def _max_migration_timestamp(names) -> int: return max(_migration_timestamp(n) for n in names) +_REDACTED: Final = "REDACTED" +_PASSWORD_QUERY_KEYS: Final = frozenset(("password", "sslpassword")) + + +@functools.cache +def _secret_shape_redactor() -> Callable[[str], str]: + try: + from litellm._logging import redact_secrets + except ImportError: + return lambda text: text + return redact_secrets + + +def _url_passwords(url: str) -> frozenset[str]: + try: + parts: Final = urlsplit(url) + except ValueError: + return frozenset() + query_pairs: Final = tuple(pair.partition("=") for pair in parts.query.split("&")) + raw_query_passwords: Final = tuple( + value for key, separator, value in query_pairs if separator and key.lower() in _PASSWORD_QUERY_KEYS + ) + raw_passwords: Final = ((parts.password,) if parts.password else ()) + raw_query_passwords + return frozenset(password for password in raw_passwords + tuple(map(unquote, raw_passwords)) if password) + + +def _configured_database_passwords() -> frozenset[str]: + database_url: Final = os.getenv("DATABASE_URL") + direct_url: Final = os.getenv("DIRECT_URL") + database_passwords: Final = _url_passwords(database_url) if database_url else frozenset() + direct_passwords: Final = _url_passwords(direct_url) if direct_url else frozenset() + return database_passwords | direct_passwords + + +def _redact_credentials(text: str) -> str: + """Mask configured database passwords before passing the text to LiteLLM redaction.""" + passwords: Final = sorted(_configured_database_passwords(), key=len, reverse=True) + alternation: Final = "|".join(re.escape(password) for password in passwords) + password_pattern: Final = ( + re.compile(rf"(?P:|password=)(?:{alternation})(?=@|&|$|[\s'\"\]),])", re.IGNORECASE) + if passwords + else None + ) + result: Final = password_pattern.sub(rf"\g{_REDACTED}", text) if password_pattern is not None else text + return _secret_shape_redactor()(result) + + +def _redacted_command(command: object) -> Union[str, tuple[str, ...], list[str]]: + if isinstance(command, tuple): + return tuple(_redact_credentials(str(argument)) for argument in command) + if isinstance(command, list): + return [_redact_credentials(str(argument)) for argument in command] + return _redact_credentials(str(command)) + + +def _redact_command_error(error: subprocess.CalledProcessError) -> str: + redacted_command: Final = _redacted_command(error.cmd) + return str(subprocess.CalledProcessError(error.returncode, redacted_command)) + + def _get_prisma_command() -> str: """Get the Prisma command to use, bypassing Python wrapper in offline mode.""" if str_to_bool(os.getenv("PRISMA_OFFLINE_MODE")): @@ -315,7 +377,8 @@ class ProxyExtrasDBManager: return False except subprocess.CalledProcessError as e: logger.warning( - f"Error creating baseline migration: {e}, {e.stderr}, {e.stdout}" + f"Error creating baseline migration: {_redact_command_error(e)}, " + f"{_redact_credentials(str(e.stderr))}, {_redact_credentials(str(e.stdout))}" ) raise e @@ -1572,6 +1635,11 @@ class ProxyExtrasDBManager: f"Error: {stderr}" ) raise + else: + logger.error( + "prisma migrate deploy failed with an error the resolver does not handle: " + f"{_redact_credentials(stderr)}" + ) else: if ProxyExtrasDBManager.spend_logs_is_partitioned(): raise RuntimeError(PARTITIONED_SPEND_LOGS_PUSH_ERROR) @@ -1586,7 +1654,7 @@ class ProxyExtrasDBManager: ) return True except subprocess.TimeoutExpired: - logger.warning( + logger.error( "Attempt %s timed out. Raise %s if this database needs longer to apply its schema.", attempt + 1, PRISMA_MIGRATE_DEPLOY_TIMEOUT_ENV_VAR if use_migrate else PRISMA_COMMAND_TIMEOUT_ENV_VAR, @@ -1599,7 +1667,12 @@ class ProxyExtrasDBManager: if attempts_left > 0 else "" ) - logger.info(f"The process failed to execute. Details: {e}.{retry_msg}") + stderr_detail: Final = ( + f" stderr: {_redact_credentials(str(e.stderr))}" if e.stderr else "" + ) + logger.error( + f"The process failed to execute. Details: {_redact_command_error(e)}.{stderr_detail}{retry_msg}" + ) time.sleep(random.randrange(5, 15)) finally: os.chdir(original_dir) diff --git a/litellm-rust/crates/python-bridge/src/routes/traces.rs b/litellm-rust/crates/python-bridge/src/routes/traces.rs index 77a98b3980a..dd5c6b9860f 100644 --- a/litellm-rust/crates/python-bridge/src/routes/traces.rs +++ b/litellm-rust/crates/python-bridge/src/routes/traces.rs @@ -39,6 +39,7 @@ fn map_error_ref(error: &Error) -> PyErr { | Error::InsertTooLarge | Error::ReadTooLarge => PyOverflowError::new_err(error.to_string()), Error::InvalidRow + | Error::InvalidLimit(_) | Error::InvalidTable | Error::InvalidCursor(_) | Error::AmbiguousTrace @@ -59,6 +60,7 @@ fn map_error_ref(error: &Error) -> PyErr { Error::Cached(source) => map_error_ref(source), Error::Storage(source) => match source { StorageError::InvalidRow + | StorageError::InvalidLimit(_) | StorageError::InvalidTable | StorageError::InvalidSchema | StorageError::EmptySql @@ -433,6 +435,13 @@ mod tests { #[rstest] #[case::row(Error::InvalidRow, "ValueError")] + #[case::insert_limit(Error::InvalidLimit("CLICKHOUSE_TRACE_MAX_INSERT_BYTES"), "ValueError")] + #[case::insert_timeout( + Error::Storage(litellm_storage_clickhouse::Error::InvalidLimit( + "CLICKHOUSE_INSERT_TIMEOUT_SECONDS" + )), + "ValueError" + )] #[case::insert_budget(Error::InsertTooLarge, "OverflowError")] #[case::scope(Error::InvalidScope, "ValueError")] #[case::schema(Error::SchemaFailed(503), "RuntimeError")] @@ -482,6 +491,10 @@ mod tests { #[rstest] #[case::decode_budget(Error::Decode(litellm_traces::Error::TooLarge), "OverflowError")] #[case::invalid_export(Error::Decode(litellm_traces::Error::InvalidPayload), "ValueError")] + #[case::invalid_decode_limit( + Error::Decode(litellm_traces::Error::InvalidLimit("OTLP_MAX_SPANS")), + "ValueError" + )] #[case::cursor(Error::InvalidCursor("trace"), "ValueError")] #[case::ambiguous(Error::AmbiguousTrace, "ValueError")] #[case::changed_snapshot(Error::TraceChanged, "ValueError")] diff --git a/litellm-rust/crates/storage-clickhouse/src/error.rs b/litellm-rust/crates/storage-clickhouse/src/error.rs index 43202b8fa15..acec9b91675 100644 --- a/litellm-rust/crates/storage-clickhouse/src/error.rs +++ b/litellm-rust/crates/storage-clickhouse/src/error.rs @@ -2,6 +2,8 @@ pub enum Error { #[error("invalid ClickHouse insert row")] InvalidRow, + #[error("{0} must be a positive integer")] + InvalidLimit(&'static str), #[error("invalid ClickHouse insert table")] InvalidTable, #[error("invalid ClickHouse HTTP URL")] diff --git a/litellm-rust/crates/storage-clickhouse/src/insert.rs b/litellm-rust/crates/storage-clickhouse/src/insert.rs index 81528ded907..1cdad1897c1 100644 --- a/litellm-rust/crates/storage-clickhouse/src/insert.rs +++ b/litellm-rust/crates/storage-clickhouse/src/insert.rs @@ -5,7 +5,19 @@ use litellm_http::Client; use crate::{Connection, Error, valid_identifier}; -const INSERT_TIMEOUT: Duration = Duration::from_secs(30); +fn insert_timeout() -> Result { + let name = "CLICKHOUSE_INSERT_TIMEOUT_SECONDS"; + match std::env::var(name) { + Ok(value) => value + .parse::() + .ok() + .filter(|value| *value > 0) + .map(Duration::from_secs) + .ok_or(Error::InvalidLimit(name)), + Err(std::env::VarError::NotPresent) => Ok(Duration::from_secs(30)), + Err(_) => Err(Error::InvalidLimit(name)), + } +} pub async fn insert_encoded_rows( client: &Client, @@ -74,7 +86,7 @@ pub async fn insert_compressed_rows( .append_pair("date_time_input_format", "best_effort"); let response = client .post(url) - .timeout(INSERT_TIMEOUT) + .timeout(insert_timeout()?) .header("Content-Encoding", "gzip") .body(body) .send() diff --git a/litellm-rust/crates/storage-clickhouse/tests/transport.rs b/litellm-rust/crates/storage-clickhouse/tests/transport.rs index 1dab575e21b..f70fe52e1de 100644 --- a/litellm-rust/crates/storage-clickhouse/tests/transport.rs +++ b/litellm-rust/crates/storage-clickhouse/tests/transport.rs @@ -144,3 +144,50 @@ async fn server_result_limits_allow_smaller_pages_without_retrying_other_failure assert!(matches!(error, Error::QueryFailed(500))); } } + +#[test] +fn insert_timeout_environment_controls_transport() { + for value in ["1", "3", "0", "invalid"] { + let result = std::process::Command::new(std::env::current_exe().unwrap()) + .args(["--exact", "insert_timeout_environment_child"]) + .env("LITELLM_TEST_INSERT_TIMEOUT", value) + .env("CLICKHOUSE_INSERT_TIMEOUT_SECONDS", value) + .output() + .unwrap(); + assert!( + result.status.success(), + "{}", + String::from_utf8_lossy(&result.stdout) + ); + } +} + +#[tokio::test] +async fn insert_timeout_environment_child() { + use wiremock::{Mock, MockServer, ResponseTemplate, matchers::method}; + let Ok(value) = std::env::var("LITELLM_TEST_INSERT_TIMEOUT") else { + return; + }; + let server = MockServer::start().await; + Mock::given(method("POST")) + .respond_with(ResponseTemplate::new(200).set_delay(std::time::Duration::from_millis(1500))) + .mount(&server) + .await; + let result = insert_encoded_rows( + &Client::no_redirect_for_test(), + &Connection::parse(&server.uri()).unwrap(), + "traces", + "otel_traces", + "token", + "{}", + ) + .await; + match value.as_str() { + "1" => assert!(matches!(result, Err(Error::Transport))), + "3" => assert!(result.is_ok()), + _ => assert!(matches!( + result, + Err(Error::InvalidLimit("CLICKHOUSE_INSERT_TIMEOUT_SECONDS")) + )), + } +} diff --git a/litellm-rust/crates/traces-clickhouse/query/help/recent_spend.sql b/litellm-rust/crates/traces-clickhouse/query/help/recent_spend.sql index 9b3cbbfe70e..809b1bd44f0 100644 --- a/litellm-rust/crates/traces-clickhouse/query/help/recent_spend.sql +++ b/litellm-rust/crates/traces-clickhouse/query/help/recent_spend.sql @@ -1,7 +1,6 @@ SELECT request_id, response_id, trace_id, span_id, model, spend, - prompt_tokens, completion_tokens, status, - JSONExtractBool(metadata, 'synthetic_spend') AS synthetic_spend + prompt_tokens, completion_tokens, status FROM spend_logs FINAL WHERE start_time >= now() - INTERVAL 1 DAY ORDER BY start_time DESC, request_id diff --git a/litellm-rust/crates/traces-clickhouse/src/error.rs b/litellm-rust/crates/traces-clickhouse/src/error.rs index 909ac5fc60f..78df9a2121c 100644 --- a/litellm-rust/crates/traces-clickhouse/src/error.rs +++ b/litellm-rust/crates/traces-clickhouse/src/error.rs @@ -2,6 +2,8 @@ pub enum Error { #[error("invalid ClickHouse insert row")] InvalidRow, + #[error("{0} must be a positive integer")] + InvalidLimit(&'static str), #[error("invalid ClickHouse insert table")] InvalidTable, #[error("database must be a nonempty SQL identifier and retention must be positive")] diff --git a/litellm-rust/crates/traces-clickhouse/src/insert.rs b/litellm-rust/crates/traces-clickhouse/src/insert.rs index ac9fb474ed0..9e6452844f4 100644 --- a/litellm-rust/crates/traces-clickhouse/src/insert.rs +++ b/litellm-rust/crates/traces-clickhouse/src/insert.rs @@ -15,7 +15,18 @@ use time::{OffsetDateTime, format_description::well_known::Rfc3339}; use super::{Connection, Error}; use litellm_traces::Shared; -const MAX_INSERT_BYTES: usize = 64 * 1024 * 1024; +fn max_insert_bytes() -> Result { + let name = "CLICKHOUSE_TRACE_MAX_INSERT_BYTES"; + match std::env::var(name) { + Ok(value) => value + .parse::() + .ok() + .filter(|value| *value > 0) + .ok_or(Error::InvalidLimit(name)), + Err(std::env::VarError::NotPresent) => Ok(64 * 1024 * 1024), + Err(_) => Err(Error::InvalidLimit(name)), + } +} pub type InsertRow = BTreeMap>; @@ -62,7 +73,7 @@ pub async fn insert_shared_rows( return Ok(()); } let received_ms = (OffsetDateTime::now_utc().unix_timestamp_nanos() / 1_000_000) as u64; - let (token, body) = prepare_insert(&rows, received_ms, MAX_INSERT_BYTES)?; + let (token, body) = prepare_insert(&rows, received_ms, max_insert_bytes()?)?; litellm_storage_clickhouse::insert_compressed_rows( client, connection, diff --git a/litellm-rust/crates/traces-clickhouse/templates/query_help.jinja b/litellm-rust/crates/traces-clickhouse/templates/query_help.jinja index 21cfc134950..a879d3be755 100644 --- a/litellm-rust/crates/traces-clickhouse/templates/query_help.jinja +++ b/litellm-rust/crates/traces-clickhouse/templates/query_help.jinja @@ -184,7 +184,7 @@ Duration is nanoseconds; Timestamp has nanosecond precision, spend start_time ha {%- endblock %} {% block missing_spend -%} -Token usage does not establish billed spend. OTLP exports without companion spend_logs rows have unknown cost; synthetic fixture spend is marked by metadata.synthetic_spend +Token usage does not establish billed spend. OTLP exports without companion spend_logs rows have unknown cost {%- endblock %} {% block partial_spend -%} diff --git a/litellm-rust/crates/traces-clickhouse/tests/fixtures/README.md b/litellm-rust/crates/traces-clickhouse/tests/fixtures/README.md index d47dc84ba5d..c758aa566c3 100644 --- a/litellm-rust/crates/traces-clickhouse/tests/fixtures/README.md +++ b/litellm-rust/crates/traces-clickhouse/tests/fixtures/README.md @@ -4,13 +4,11 @@ Run `cargo test -p litellm-traces-clickhouse --test queries --locked -- --test-t Raw OTLP exports live in `crates/traces/tests/fixtures/query_*.json`. The seeded fixture decodes and normalizes them through `litellm_traces::decode_otlp` at test startup, then projects the decoded fields into ClickHouse columns. Team and key identities come from fixture setup rather than exporter claims. Root and child exports are inserted separately through the public insert API so materialized views process multiple blocks -`crates/traces/tests/fixtures/deeplite_auth_error.json` and `deeplite_swarm.json` were captured from Deeplite runs against the local proxy on 2026-10-02. The first contains a failed model call. The second contains successful model calls, searches, handoff attempts, and virtual filesystem writes. Credentials, workspace identifiers, and local user paths were redacted, and the protobuf exports were converted to OTLP JSON. Their round-trip tests check span identities, parent links, timestamps, durations, token counts, and statuses without pinning the provider's error wording +The ClickHouse round-trip test replays the `google_adk_billed_failure`, `pydantic_ai_retry`, and `deepagents_swarm` exports and checks span identities, parent links, timestamps, durations, token counts, and statuses without pinning the provider's error wording. Exported ERROR and UNSET statuses are diagnostic and do not establish a failed execution, so the test preserves incoming statuses and checks root status separately from the count of error spans, deriving both from the decoded export. Framework-specific interpretation of control-flow exceptions belongs in the instrumentation integration -The swarm capture has handoff spans marked ERROR with `ParentCommand` exception events and a root with UNSET status. These are exported diagnostic statuses, which do not establish a failed execution. The tests preserve incoming statuses and check root status separately from the count of error spans, deriving both from the decoded export. They do not infer an execution outcome from exception text, framework names, successful model calls, or output presence. Framework-specific interpretation of control-flow exceptions belongs in the instrumentation integration +For a local dashboard with linked requests and traces, run `make lens-dev ARGS=--seed` from the repository root and open `http://localhost:3000/ui/lens/`. Log in as `admin` with the master key saved in `.lens-dev/master_key`. The launcher keeps the stack running until Ctrl-C and leaves the database volumes intact -For a local dashboard with linked requests and traces, run `bash scripts/run_tracing_proxy_local.sh --seed` from the repository root and open `http://127.0.0.1:4002/ui/`. Log in as `admin` with password `sk-1234`, matching the UI E2E harness. The launcher keeps the proxy running until Ctrl-C and leaves the database volumes intact - -`deeplite_swarm_spend_logs.jsonl` pairs every LLM span in the swarm export with a ClickHouse spend row. Response IDs, trace and span IDs, token counts, input, output, and timestamps come from the export. Messages and responses use the chat completion format supported by the request viewer. Spend is synthetic, set to $0.01 per request and marked in metadata, because the export does not include actual billed costs. These rows are stored here because `traces-clickhouse` owns the spend row schema +Spend rows are stored here because `traces-clickhouse` owns the spend row schema The simple and swarm exports for all twelve SDK examples were captured on 2026-10-03 against port 4002 using `openai/gpt-6-luna`. Each export has a matching `_spend_logs.jsonl` with actual proxy spend, usage, request and response IDs, messages, and timestamps. Authorization headers, provider cookies, organization and project identifiers, and local paths were redacted. OTLP identifiers and enums use their canonical JSON encodings. `metadata.fixture_capture` identifies the associated export and whether model spans contain sufficient identity to join spend diff --git a/litellm-rust/crates/traces-clickhouse/tests/fixtures/deeplite_swarm_spend_logs.jsonl b/litellm-rust/crates/traces-clickhouse/tests/fixtures/deeplite_swarm_spend_logs.jsonl deleted file mode 100644 index f1fc525093c..00000000000 --- a/litellm-rust/crates/traces-clickhouse/tests/fixtures/deeplite_swarm_spend_logs.jsonl +++ /dev/null @@ -1,7 +0,0 @@ -{"request_id":"msg_011Cfdw9aW9brenPqgybfNwP","response_id":"msg_011Cfdw9aW9brenPqgybfNwP","call_type":"anthropic_messages","api_key":"","key_alias":"local-tracing-fixture","team_id":"","team_alias":"","organization_id":"","user":"","end_user":"","model":"claude-sonnet","model_group":"claude-sonnet","model_id":"","custom_llm_provider":"anthropic","api_base":"","spend":0.01,"prompt_tokens":2845,"completion_tokens":73,"total_tokens":2918,"cache_read_tokens":0,"cache_write_tokens":0,"start_time":1790968013219,"end_time":1790968018769,"completion_start_time":null,"status":"success","error_str":"","cache_hit":false,"session_id":"b2952a96b863250c304cef3376fe4c82","trace_id":"b2952a96b863250c304cef3376fe4c82","span_id":"3baa483880660b3b","request_tags":["local-tracing-fixture"],"metadata":"{\"fixture\": \"deeplite_swarm\", \"synthetic_spend\": true}","messages":"[{\"role\": \"system\", \"content\": \"You are the researcher. Search for evidence and share source URLs. You may read shared virtual files, but only the editor writes them. Send initial findings to the skeptic. If another agent returns with corrections, revise your findings and send them to the verifier. Do not give the final answer.\"}, {\"role\": \"user\", \"content\": \"For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.\"}]","response":"{\"id\": \"msg_011Cfdw9aW9brenPqgybfNwP\", \"model\": \"claude-sonnet\", \"choices\": [{\"index\": 0, \"message\": {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01B2LfHGDjYSFJhmiXNj4CuQ\", \"type\": \"function\", \"function\": {\"name\": \"web_search\", \"arguments\": \"{\\\"query\\\": \\\"docs.python.org tuples immutable sequences lists mutable data structures tutorial\\\"}\"}}]}, \"finish_reason\": \"tool_calls\"}], \"usage\": {\"prompt_tokens\": 2845, \"completion_tokens\": 73, \"total_tokens\": 2918}}"} -{"request_id":"msg_011CfdwA6F4cCN5yhD4Crs9M","response_id":"msg_011CfdwA6F4cCN5yhD4Crs9M","call_type":"anthropic_messages","api_key":"","key_alias":"local-tracing-fixture","team_id":"","team_alias":"","organization_id":"","user":"","end_user":"","model":"claude-sonnet","model_group":"claude-sonnet","model_id":"","custom_llm_provider":"anthropic","api_base":"","spend":0.01,"prompt_tokens":7378,"completion_tokens":33,"total_tokens":7411,"cache_read_tokens":0,"cache_write_tokens":0,"start_time":1790968020184,"end_time":1790968023764,"completion_start_time":null,"status":"success","error_str":"","cache_hit":false,"session_id":"b2952a96b863250c304cef3376fe4c82","trace_id":"b2952a96b863250c304cef3376fe4c82","span_id":"0d31577e2d5562cc","request_tags":["local-tracing-fixture"],"metadata":"{\"fixture\": \"deeplite_swarm\", \"synthetic_spend\": true}","messages":"[{\"role\": \"system\", \"content\": \"You are the researcher. Search for evidence and share source URLs. You may read shared virtual files, but only the editor writes them. Send initial findings to the skeptic. If another agent returns with corrections, revise your findings and send them to the verifier. Do not give the final answer.\"}, {\"role\": \"user\", \"content\": \"For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01B2LfHGDjYSFJhmiXNj4CuQ\", \"type\": \"function\", \"function\": {\"name\": \"web_search\", \"arguments\": \"{\\\"query\\\": \\\"docs.python.org tuples immutable sequences lists mutable data structures tutorial\\\"}\"}}]}, {\"role\": \"tool\", \"content\": \"[{\\\"title\\\": \\\"5. Data Structures \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/tutorial/datastructures.html\\\", \\\"highlights\\\": [\\\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\\\"\\\\\\\", line 1, in \\\\nTypeError: 'tuple' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\\\"]}, {\\\"title\\\": \\\"3. Data model \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/reference/datamodel.html\\\", \\\"highlights\\\": [\\\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\\\"]}, {\\\"title\\\": \\\"Built-in Types \\\\u2014 Python 3.14.7 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/builtins/stdtypes.html\\\", \\\"highlights\\\": [\\\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple('abc')` returns `('a', 'b', 'c')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\\\"]}, {\\\"title\\\": \\\"Built-in Types \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/library/stdtypes.html\\\", \\\"highlights\\\": [\\\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple('abc')` returns `('a', 'b', 'c')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\\\"]}, {\\\"title\\\": \\\"5. Data Structures \\\\u2014 Python 3.10.20 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3.10/tutorial/datastructures.html\\\", \\\"highlights\\\": [\\\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\\\"\\\\\\\", line 1, in \\\\nTypeError: 'tuple' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\\\"]}]\", \"name\": \"web_search\"}]","response":"{\"id\": \"msg_011CfdwA6F4cCN5yhD4Crs9M\", \"model\": \"claude-sonnet\", \"choices\": [{\"index\": 0, \"message\": {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01Xjj3aRdWyhBJfPmTJBxQa9\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_skeptic\", \"arguments\": \"{}\"}}]}, \"finish_reason\": \"tool_calls\"}], \"usage\": {\"prompt_tokens\": 7378, \"completion_tokens\": 33, \"total_tokens\": 7411}}"} -{"request_id":"msg_011CfdwAMRdS21FeJfzQhM3s","response_id":"msg_011CfdwAMRdS21FeJfzQhM3s","call_type":"anthropic_messages","api_key":"","key_alias":"local-tracing-fixture","team_id":"","team_alias":"","organization_id":"","user":"","end_user":"","model":"claude-sonnet","model_group":"claude-sonnet","model_id":"","custom_llm_provider":"anthropic","api_base":"","spend":0.01,"prompt_tokens":7396,"completion_tokens":770,"total_tokens":8166,"cache_read_tokens":0,"cache_write_tokens":0,"start_time":1790968023785,"end_time":1790968030833,"completion_start_time":null,"status":"success","error_str":"","cache_hit":false,"session_id":"b2952a96b863250c304cef3376fe4c82","trace_id":"b2952a96b863250c304cef3376fe4c82","span_id":"f2bbd85b9e41b171","request_tags":["local-tracing-fixture"],"metadata":"{\"fixture\": \"deeplite_swarm\", \"synthetic_spend\": true}","messages":"[{\"role\": \"system\", \"content\": \"You are the skeptic. Challenge the research, name unsupported claims, and send your critique to the verifier. If the editor sends a revision back, ask the researcher to fix concrete gaps or send the result to red_team. Do not give the final answer.\"}, {\"role\": \"user\", \"content\": \"For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01B2LfHGDjYSFJhmiXNj4CuQ\", \"type\": \"function\", \"function\": {\"name\": \"web_search\", \"arguments\": \"{\\\"query\\\": \\\"docs.python.org tuples immutable sequences lists mutable data structures tutorial\\\"}\"}}]}, {\"role\": \"tool\", \"content\": \"[{\\\"title\\\": \\\"5. Data Structures \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/tutorial/datastructures.html\\\", \\\"highlights\\\": [\\\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\\\"\\\\\\\", line 1, in \\\\nTypeError: 'tuple' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\\\"]}, {\\\"title\\\": \\\"3. Data model \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/reference/datamodel.html\\\", \\\"highlights\\\": [\\\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\\\"]}, {\\\"title\\\": \\\"Built-in Types \\\\u2014 Python 3.14.7 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/builtins/stdtypes.html\\\", \\\"highlights\\\": [\\\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple('abc')` returns `('a', 'b', 'c')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\\\"]}, {\\\"title\\\": \\\"Built-in Types \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/library/stdtypes.html\\\", \\\"highlights\\\": [\\\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple('abc')` returns `('a', 'b', 'c')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\\\"]}, {\\\"title\\\": \\\"5. Data Structures \\\\u2014 Python 3.10.20 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3.10/tutorial/datastructures.html\\\", \\\"highlights\\\": [\\\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\\\"\\\\\\\", line 1, in \\\\nTypeError: 'tuple' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\\\"]}]\", \"name\": \"web_search\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01Xjj3aRdWyhBJfPmTJBxQa9\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_skeptic\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to skeptic\", \"name\": \"transfer_to_skeptic\"}]","response":"{\"id\": \"msg_011CfdwAMRdS21FeJfzQhM3s\", \"model\": \"claude-sonnet\", \"choices\": [{\"index\": 0, \"message\": {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01H6fV8JvRJNvXy47eRnd3jH\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_verifier\", \"arguments\": \"{}\"}}]}, \"finish_reason\": \"tool_calls\"}], \"usage\": {\"prompt_tokens\": 7396, \"completion_tokens\": 770, \"total_tokens\": 8166}}"} -{"request_id":"msg_011CfdwAsabDquegHi6YUpCn","response_id":"msg_011CfdwAsabDquegHi6YUpCn","call_type":"anthropic_messages","api_key":"","key_alias":"local-tracing-fixture","team_id":"","team_alias":"","organization_id":"","user":"","end_user":"","model":"claude-sonnet","model_group":"claude-sonnet","model_id":"","custom_llm_provider":"anthropic","api_base":"","spend":0.01,"prompt_tokens":7509,"completion_tokens":88,"total_tokens":7597,"cache_read_tokens":0,"cache_write_tokens":0,"start_time":1790968030850,"end_time":1790968032469,"completion_start_time":null,"status":"success","error_str":"","cache_hit":false,"session_id":"b2952a96b863250c304cef3376fe4c82","trace_id":"b2952a96b863250c304cef3376fe4c82","span_id":"7d9bd24669f22c02","request_tags":["local-tracing-fixture"],"metadata":"{\"fixture\": \"deeplite_swarm\", \"synthetic_spend\": true}","messages":"[{\"role\": \"system\", \"content\": \"You are the verifier. Independently search to check claims and source URLs. If evidence is weak, send the issue to the researcher. Otherwise send your verdict to red_team. Do not give the final answer.\"}, {\"role\": \"user\", \"content\": \"For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01B2LfHGDjYSFJhmiXNj4CuQ\", \"type\": \"function\", \"function\": {\"name\": \"web_search\", \"arguments\": \"{\\\"query\\\": \\\"docs.python.org tuples immutable sequences lists mutable data structures tutorial\\\"}\"}}]}, {\"role\": \"tool\", \"content\": \"[{\\\"title\\\": \\\"5. Data Structures \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/tutorial/datastructures.html\\\", \\\"highlights\\\": [\\\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\\\"\\\\\\\", line 1, in \\\\nTypeError: 'tuple' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\\\"]}, {\\\"title\\\": \\\"3. Data model \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/reference/datamodel.html\\\", \\\"highlights\\\": [\\\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\\\"]}, {\\\"title\\\": \\\"Built-in Types \\\\u2014 Python 3.14.7 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/builtins/stdtypes.html\\\", \\\"highlights\\\": [\\\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple('abc')` returns `('a', 'b', 'c')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\\\"]}, {\\\"title\\\": \\\"Built-in Types \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/library/stdtypes.html\\\", \\\"highlights\\\": [\\\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple('abc')` returns `('a', 'b', 'c')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\\\"]}, {\\\"title\\\": \\\"5. Data Structures \\\\u2014 Python 3.10.20 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3.10/tutorial/datastructures.html\\\", \\\"highlights\\\": [\\\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\\\"\\\\\\\", line 1, in \\\\nTypeError: 'tuple' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\\\"]}]\", \"name\": \"web_search\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01Xjj3aRdWyhBJfPmTJBxQa9\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_skeptic\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to skeptic\", \"name\": \"transfer_to_skeptic\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01H6fV8JvRJNvXy47eRnd3jH\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_verifier\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to verifier\", \"name\": \"transfer_to_verifier\"}]","response":"{\"id\": \"msg_011CfdwAsabDquegHi6YUpCn\", \"model\": \"claude-sonnet\", \"choices\": [{\"index\": 0, \"message\": {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01XEAuhQHCBdyCwtymZwFfDi\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_red_team\", \"arguments\": \"{}\"}}]}, \"finish_reason\": \"tool_calls\"}], \"usage\": {\"prompt_tokens\": 7509, \"completion_tokens\": 88, \"total_tokens\": 7597}}"} -{"request_id":"msg_011CfdwAzfjqUopoEmZLaqm1","response_id":"msg_011CfdwAzfjqUopoEmZLaqm1","call_type":"anthropic_messages","api_key":"","key_alias":"local-tracing-fixture","team_id":"","team_alias":"","organization_id":"","user":"","end_user":"","model":"claude-sonnet","model_group":"claude-sonnet","model_id":"","custom_llm_provider":"anthropic","api_base":"","spend":0.01,"prompt_tokens":7416,"completion_tokens":151,"total_tokens":7567,"cache_read_tokens":0,"cache_write_tokens":0,"start_time":1790968032486,"end_time":1790968035029,"completion_start_time":null,"status":"success","error_str":"","cache_hit":false,"session_id":"b2952a96b863250c304cef3376fe4c82","trace_id":"b2952a96b863250c304cef3376fe4c82","span_id":"28bebc087f4f6678","request_tags":["local-tracing-fixture"],"metadata":"{\"fixture\": \"deeplite_swarm\", \"synthetic_spend\": true}","messages":"[{\"role\": \"system\", \"content\": \"You are red_team. Find the strongest remaining objection to the verified findings. Send unresolved issues to the skeptic, or send your assessment to the editor. Do not give the final answer.\"}, {\"role\": \"user\", \"content\": \"For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01B2LfHGDjYSFJhmiXNj4CuQ\", \"type\": \"function\", \"function\": {\"name\": \"web_search\", \"arguments\": \"{\\\"query\\\": \\\"docs.python.org tuples immutable sequences lists mutable data structures tutorial\\\"}\"}}]}, {\"role\": \"tool\", \"content\": \"[{\\\"title\\\": \\\"5. Data Structures \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/tutorial/datastructures.html\\\", \\\"highlights\\\": [\\\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\\\"\\\\\\\", line 1, in \\\\nTypeError: 'tuple' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\\\"]}, {\\\"title\\\": \\\"3. Data model \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/reference/datamodel.html\\\", \\\"highlights\\\": [\\\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\\\"]}, {\\\"title\\\": \\\"Built-in Types \\\\u2014 Python 3.14.7 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/builtins/stdtypes.html\\\", \\\"highlights\\\": [\\\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple('abc')` returns `('a', 'b', 'c')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\\\"]}, {\\\"title\\\": \\\"Built-in Types \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/library/stdtypes.html\\\", \\\"highlights\\\": [\\\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple('abc')` returns `('a', 'b', 'c')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\\\"]}, {\\\"title\\\": \\\"5. Data Structures \\\\u2014 Python 3.10.20 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3.10/tutorial/datastructures.html\\\", \\\"highlights\\\": [\\\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\\\"\\\\\\\", line 1, in \\\\nTypeError: 'tuple' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\\\"]}]\", \"name\": \"web_search\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01Xjj3aRdWyhBJfPmTJBxQa9\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_skeptic\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to skeptic\", \"name\": \"transfer_to_skeptic\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01H6fV8JvRJNvXy47eRnd3jH\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_verifier\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to verifier\", \"name\": \"transfer_to_verifier\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01XEAuhQHCBdyCwtymZwFfDi\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_red_team\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to red_team\", \"name\": \"transfer_to_red_team\"}]","response":"{\"id\": \"msg_011CfdwAzfjqUopoEmZLaqm1\", \"model\": \"claude-sonnet\", \"choices\": [{\"index\": 0, \"message\": {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01VBrWdWEWYgit4kNYehBMU5\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_editor\", \"arguments\": \"{}\"}}]}, \"finish_reason\": \"tool_calls\"}], \"usage\": {\"prompt_tokens\": 7416, \"completion_tokens\": 151, \"total_tokens\": 7567}}"} -{"request_id":"msg_011CfdwBBaa9gjMCce16TUen","response_id":"msg_011CfdwBBaa9gjMCce16TUen","call_type":"anthropic_messages","api_key":"","key_alias":"local-tracing-fixture","team_id":"","team_alias":"","organization_id":"","user":"","end_user":"","model":"claude-sonnet","model_group":"claude-sonnet","model_id":"","custom_llm_provider":"anthropic","api_base":"","spend":0.01,"prompt_tokens":8127,"completion_tokens":433,"total_tokens":8560,"cache_read_tokens":0,"cache_write_tokens":0,"start_time":1790968035049,"end_time":1790968039090,"completion_start_time":null,"status":"success","error_str":"","cache_hit":false,"session_id":"b2952a96b863250c304cef3376fe4c82","trace_id":"b2952a96b863250c304cef3376fe4c82","span_id":"e90628af060558bc","request_tags":["local-tracing-fixture"],"metadata":"{\"fixture\": \"deeplite_swarm\", \"synthetic_spend\": true}","messages":"[{\"role\": \"system\", \"content\": \"You are the editor. Use the shared conversation to write one concise answer with source URLs. Write the final answer to /answer.md in the shared virtual filesystem before replying. If important issues remain, hand off to the right agent before answering.\"}, {\"role\": \"user\", \"content\": \"For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01B2LfHGDjYSFJhmiXNj4CuQ\", \"type\": \"function\", \"function\": {\"name\": \"web_search\", \"arguments\": \"{\\\"query\\\": \\\"docs.python.org tuples immutable sequences lists mutable data structures tutorial\\\"}\"}}]}, {\"role\": \"tool\", \"content\": \"[{\\\"title\\\": \\\"5. Data Structures \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/tutorial/datastructures.html\\\", \\\"highlights\\\": [\\\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\\\"\\\\\\\", line 1, in \\\\nTypeError: 'tuple' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\\\"]}, {\\\"title\\\": \\\"3. Data model \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/reference/datamodel.html\\\", \\\"highlights\\\": [\\\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\\\"]}, {\\\"title\\\": \\\"Built-in Types \\\\u2014 Python 3.14.7 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/builtins/stdtypes.html\\\", \\\"highlights\\\": [\\\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple('abc')` returns `('a', 'b', 'c')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\\\"]}, {\\\"title\\\": \\\"Built-in Types \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/library/stdtypes.html\\\", \\\"highlights\\\": [\\\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple('abc')` returns `('a', 'b', 'c')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\\\"]}, {\\\"title\\\": \\\"5. Data Structures \\\\u2014 Python 3.10.20 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3.10/tutorial/datastructures.html\\\", \\\"highlights\\\": [\\\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\\\"\\\\\\\", line 1, in \\\\nTypeError: 'tuple' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\\\"]}]\", \"name\": \"web_search\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01Xjj3aRdWyhBJfPmTJBxQa9\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_skeptic\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to skeptic\", \"name\": \"transfer_to_skeptic\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01H6fV8JvRJNvXy47eRnd3jH\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_verifier\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to verifier\", \"name\": \"transfer_to_verifier\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01XEAuhQHCBdyCwtymZwFfDi\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_red_team\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to red_team\", \"name\": \"transfer_to_red_team\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01VBrWdWEWYgit4kNYehBMU5\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_editor\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to editor\", \"name\": \"transfer_to_editor\"}]","response":"{\"id\": \"msg_011CfdwBBaa9gjMCce16TUen\", \"model\": \"claude-sonnet\", \"choices\": [{\"index\": 0, \"message\": {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01Bm8AU9EsQUwqoVLYpxKA77\", \"type\": \"function\", \"function\": {\"name\": \"write_file\", \"arguments\": \"{\\\"file_path\\\": \\\"/answer.md\\\", \\\"content\\\": \\\"**Tuple vs. list immutability (Python)**\\\\n\\\\nA tuple is immutable: once created, you can't assign to its items, and the collection of objects it references can't change. `t[0] = 1` raises `TypeError`. A list is mutable: you can change it in place with index or slice assignment, `append()`, `extend()`, `sort()` and similar methods.\\\\n\\\\nTuple immutability is shallow. If a tuple holds a mutable object, such as a list, that inner object can still change, and so the tuple's value changes. Because of this, a tuple can be a `dict` key or `set` member only if everything inside it is hashable. A list can never be a key.\\\\n\\\\nSources:\\\\n- https://docs.python.org/3/tutorial/datastructures.html\\\\n- https://docs.python.org/3/reference/datamodel.html\\\\n- https://docs.python.org/3/library/stdtypes.html\\\\n\\\"}\"}}]}, \"finish_reason\": \"tool_calls\"}], \"usage\": {\"prompt_tokens\": 8127, \"completion_tokens\": 433, \"total_tokens\": 8560}}"} -{"request_id":"msg_011CfdwBUsNhr19gQNVcFsUe","response_id":"msg_011CfdwBUsNhr19gQNVcFsUe","call_type":"anthropic_messages","api_key":"","key_alias":"local-tracing-fixture","team_id":"","team_alias":"","organization_id":"","user":"","end_user":"","model":"claude-sonnet","model_group":"claude-sonnet","model_id":"","custom_llm_provider":"anthropic","api_base":"","spend":0.01,"prompt_tokens":8494,"completion_tokens":415,"total_tokens":8909,"cache_read_tokens":0,"cache_write_tokens":0,"start_time":1790968039099,"end_time":1790968042916,"completion_start_time":null,"status":"success","error_str":"","cache_hit":false,"session_id":"b2952a96b863250c304cef3376fe4c82","trace_id":"b2952a96b863250c304cef3376fe4c82","span_id":"73aee64af021a907","request_tags":["local-tracing-fixture"],"metadata":"{\"fixture\": \"deeplite_swarm\", \"synthetic_spend\": true}","messages":"[{\"role\": \"system\", \"content\": \"You are the editor. Use the shared conversation to write one concise answer with source URLs. Write the final answer to /answer.md in the shared virtual filesystem before replying. If important issues remain, hand off to the right agent before answering.\"}, {\"role\": \"user\", \"content\": \"For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01B2LfHGDjYSFJhmiXNj4CuQ\", \"type\": \"function\", \"function\": {\"name\": \"web_search\", \"arguments\": \"{\\\"query\\\": \\\"docs.python.org tuples immutable sequences lists mutable data structures tutorial\\\"}\"}}]}, {\"role\": \"tool\", \"content\": \"[{\\\"title\\\": \\\"5. Data Structures \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/tutorial/datastructures.html\\\", \\\"highlights\\\": [\\\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\\\"\\\\\\\", line 1, in \\\\nTypeError: 'tuple' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\\\"]}, {\\\"title\\\": \\\"3. Data model \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/reference/datamodel.html\\\", \\\"highlights\\\": [\\\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\\\"]}, {\\\"title\\\": \\\"Built-in Types \\\\u2014 Python 3.14.7 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/builtins/stdtypes.html\\\", \\\"highlights\\\": [\\\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple('abc')` returns `('a', 'b', 'c')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\\\"]}, {\\\"title\\\": \\\"Built-in Types \\\\u2014 Python 3.14.5 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3/library/stdtypes.html\\\", \\\"highlights\\\": [\\\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple('abc')` returns `('a', 'b', 'c')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\\\"]}, {\\\"title\\\": \\\"5. Data Structures \\\\u2014 Python 3.10.20 documentation\\\", \\\"url\\\": \\\"https://docs.python.org/3.10/tutorial/datastructures.html\\\", \\\"highlights\\\": [\\\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\\\"\\\\\\\", line 1, in \\\\nTypeError: 'tuple' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\\\"]}]\", \"name\": \"web_search\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01Xjj3aRdWyhBJfPmTJBxQa9\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_skeptic\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to skeptic\", \"name\": \"transfer_to_skeptic\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01H6fV8JvRJNvXy47eRnd3jH\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_verifier\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to verifier\", \"name\": \"transfer_to_verifier\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01XEAuhQHCBdyCwtymZwFfDi\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_red_team\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to red_team\", \"name\": \"transfer_to_red_team\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01VBrWdWEWYgit4kNYehBMU5\", \"type\": \"function\", \"function\": {\"name\": \"transfer_to_editor\", \"arguments\": \"{}\"}}]}, {\"role\": \"tool\", \"content\": \"Successfully transferred to editor\", \"name\": \"transfer_to_editor\"}, {\"role\": \"assistant\", \"content\": \"\", \"tool_calls\": [{\"id\": \"toolu_01Bm8AU9EsQUwqoVLYpxKA77\", \"type\": \"function\", \"function\": {\"name\": \"write_file\", \"arguments\": \"{\\\"file_path\\\": \\\"/answer.md\\\", \\\"content\\\": \\\"**Tuple vs. list immutability (Python)**\\\\n\\\\nA tuple is immutable: once created, you can't assign to its items, and the collection of objects it references can't change. `t[0] = 1` raises `TypeError`. A list is mutable: you can change it in place with index or slice assignment, `append()`, `extend()`, `sort()` and similar methods.\\\\n\\\\nTuple immutability is shallow. If a tuple holds a mutable object, such as a list, that inner object can still change, and so the tuple's value changes. Because of this, a tuple can be a `dict` key or `set` member only if everything inside it is hashable. A list can never be a key.\\\\n\\\\nSources:\\\\n- https://docs.python.org/3/tutorial/datastructures.html\\\\n- https://docs.python.org/3/reference/datamodel.html\\\\n- https://docs.python.org/3/library/stdtypes.html\\\\n\\\"}\"}}]}, {\"role\": \"tool\", \"content\": \"Updated file /answer.md\", \"name\": \"write_file\"}]","response":"{\"id\": \"msg_011CfdwBUsNhr19gQNVcFsUe\", \"model\": \"claude-sonnet\", \"choices\": [{\"index\": 0, \"message\": {\"role\": \"assistant\", \"content\": \"I wrote the answer to `/answer.md`. It is about 100 words, under the 120-word limit.\\n\\nI did not get a skeptic or verifier check. I handed off to both, but neither returned any feedback. I also tried to hand off to a `red_team` agent, and that transfer isn't one of the tools I was given. I then wrote the answer myself from the official Python documentation search results. I didn't open the pages directly.\\n\\n**Tuple vs. list immutability (Python)**\\n\\nA tuple is immutable: once created, you can't assign to its items, and the collection of objects it references can't change. `t[0] = 1` raises `TypeError`. A list is mutable: you can change it in place with index or slice assignment, `append()`, `extend()`, `sort()` and similar methods.\\n\\nTuple immutability is shallow. If a tuple holds a mutable object, such as a list, that inner object can still change, and so the tuple's value changes. Because of this, a tuple can be a `dict` key or `set` member only if everything inside it is hashable. A list can never be a key.\\n\\nSources:\\n- https://docs.python.org/3/tutorial/datastructures.html\\n- https://docs.python.org/3/reference/datamodel.html\\n- https://docs.python.org/3/library/stdtypes.html\"}, \"finish_reason\": \"stop\"}], \"usage\": {\"prompt_tokens\": 8494, \"completion_tokens\": 415, \"total_tokens\": 8909}}"} diff --git a/litellm-rust/crates/traces-clickhouse/tests/insert.rs b/litellm-rust/crates/traces-clickhouse/tests/insert.rs index 2d1c98668e2..c552a512713 100644 --- a/litellm-rust/crates/traces-clickhouse/tests/insert.rs +++ b/litellm-rust/crates/traces-clickhouse/tests/insert.rs @@ -138,3 +138,56 @@ fn insert_encoding_preserves_timestamp_precision_and_other_fields( fn insert_encoding_rejects_invalid_span_timestamps(#[case] timestamp: Value) { assert!(encode_rows(vec![BTreeMap::from([("Timestamp".into(), timestamp)])]).is_err()); } + +#[test] +fn insert_byte_limit_environment_controls_transport() { + for value in ["1", "1024", "0", "invalid"] { + let result = std::process::Command::new(std::env::current_exe().unwrap()) + .args(["--exact", "insert_byte_limit_environment_child"]) + .env("LITELLM_TEST_INSERT_LIMIT", value) + .env("CLICKHOUSE_TRACE_MAX_INSERT_BYTES", value) + .output() + .unwrap(); + assert!( + result.status.success(), + "{}", + String::from_utf8_lossy(&result.stdout) + ); + } +} + +#[tokio::test] +async fn insert_byte_limit_environment_child() { + let Ok(value) = std::env::var("LITELLM_TEST_INSERT_LIMIT") else { + return; + }; + let server = MockServer::start().await; + Mock::given(method("POST")) + .respond_with(ResponseTemplate::new(200)) + .mount(&server) + .await; + let connection = Connection::parse(&server.uri()).unwrap(); + let result = insert_shared_rows( + &Client::no_redirect_for_test(), + &connection, + "traces", + InsertTable::OtelTraces, + vec![BTreeMap::from([( + "SpanId".into(), + Shared::new(json!("test")), + )])], + ) + .await; + match value.as_str() { + "1" => assert!(matches!(result, Err(Error::InsertTooLarge))), + "1024" => assert!(result.is_ok()), + _ => assert!(matches!( + result, + Err(Error::InvalidLimit("CLICKHOUSE_TRACE_MAX_INSERT_BYTES")) + )), + } + assert_eq!( + server.received_requests().await.unwrap().len(), + usize::from(value == "1024") + ); +} diff --git a/litellm-rust/crates/traces-clickhouse/tests/queries.rs b/litellm-rust/crates/traces-clickhouse/tests/queries.rs index d973b3a565d..5cb0ee4bfcd 100644 --- a/litellm-rust/crates/traces-clickhouse/tests/queries.rs +++ b/litellm-rust/crates/traces-clickhouse/tests/queries.rs @@ -244,10 +244,11 @@ async fn typed_trace_cursor_returns_the_next_fixture_trace( } #[rstest] -#[case::authentication_error(include_bytes!("../../traces/tests/fixtures/deeplite_auth_error.json"))] -#[case::swarm(include_bytes!("../../traces/tests/fixtures/deeplite_swarm.json"))] +#[case::billed_failure(include_bytes!("../../traces/tests/fixtures/google_adk_billed_failure.json"))] +#[case::retry(include_bytes!("../../traces/tests/fixtures/pydantic_ai_retry.json"))] +#[case::swarm(include_bytes!("../../traces/tests/fixtures/deepagents_swarm.json"))] #[tokio::test] -async fn captured_deeplite_exports_round_trip_through_clickhouse( +async fn captured_sdk_exports_round_trip_through_clickhouse( #[future(awt)] migrated_database: TestResult, admin_access: TestResult, #[case] export: &[u8], diff --git a/litellm-rust/crates/traces/src/error.rs b/litellm-rust/crates/traces/src/error.rs index 4b404782083..ee14abf8b8f 100644 --- a/litellm-rust/crates/traces/src/error.rs +++ b/litellm-rust/crates/traces/src/error.rs @@ -2,6 +2,8 @@ pub enum Error { #[error("invalid OTLP trace payload")] InvalidPayload, + #[error("{0} must be a positive integer")] + InvalidLimit(&'static str), #[error("OTLP trace payload exceeds the decoding budget")] TooLarge, #[error("OTLP token count is outside the storage range")] diff --git a/litellm-rust/crates/traces/src/lib.rs b/litellm-rust/crates/traces/src/lib.rs index 1e2eca3f7cc..a44679a59f3 100644 --- a/litellm-rust/crates/traces/src/lib.rs +++ b/litellm-rust/crates/traces/src/lib.rs @@ -30,7 +30,7 @@ pub use normalize::{ AgentMetadata, AgentType, CallEvidence, CallEvidenceKind, CallKey, Integration, NormalizedSpan, ObservationType, }; -pub use otlp::{DecodedEvent, DecodedSpan, decode_otlp}; +pub use otlp::{DecodeLimits, DecodedEvent, DecodedSpan, decode_otlp, decode_otlp_with_limits}; pub use query::ReadQuery; pub use query_access::QueryScope; pub use resolve::{SpendLookup, iso_time, listed_summary, resolve_trace}; diff --git a/litellm-rust/crates/traces/src/otlp/attributes.rs b/litellm-rust/crates/traces/src/otlp/attributes.rs index fb3f627697a..79239d314bf 100644 --- a/litellm-rust/crates/traces/src/otlp/attributes.rs +++ b/litellm-rust/crates/traces/src/otlp/attributes.rs @@ -8,7 +8,7 @@ use serde::{ ser::{SerializeMap, SerializeSeq}, }; -use super::limits::{Budget, MAX_ATTRIBUTES}; +use super::limits::Budget; use crate::Error; struct AttributeWriter<'a> { @@ -33,7 +33,7 @@ pub(super) fn attributes( values: Vec, budget: &mut Budget, ) -> Result, Error> { - if values.len() > MAX_ATTRIBUTES { + if values.len() > budget.limits.attributes { return Err(Error::TooLarge); } values diff --git a/litellm-rust/crates/traces/src/otlp/limits.rs b/litellm-rust/crates/traces/src/otlp/limits.rs index ca1ac144346..432b863b5af 100644 --- a/litellm-rust/crates/traces/src/otlp/limits.rs +++ b/litellm-rust/crates/traces/src/otlp/limits.rs @@ -5,14 +5,62 @@ use serde::de::{DeserializeSeed, MapAccess, SeqAccess, Visitor}; use crate::{Error, Shared}; -pub(super) const MAX_DEPTH: usize = 32; -pub(super) const MAX_NODES: usize = 65_536; -pub(super) const MAX_SPANS: usize = 4_096; -pub(super) const MAX_ATTRIBUTES: usize = 256; -pub(super) const MAX_EVENTS: usize = 256; -pub(super) const MAX_DECODED_SPAN_BYTES: usize = 16 * 1024 * 1024; +#[derive(Clone, Copy, Debug)] +pub struct DecodeLimits { + pub depth: usize, + pub nodes: usize, + pub spans: usize, + pub attributes: usize, + pub events: usize, + pub links: usize, + pub decoded_span_bytes: usize, +} -pub(super) fn json_preflight(payload: &[u8]) -> Result<(), Error> { +impl Default for DecodeLimits { + fn default() -> Self { + Self { + depth: 32, + nodes: 65_536, + spans: 4_096, + attributes: 256, + events: 256, + links: 256, + decoded_span_bytes: 16 * 1024 * 1024, + } + } +} + +impl DecodeLimits { + pub fn from_env() -> Result { + let defaults = Self::default(); + Ok(Self { + depth: env_limit("OTLP_MAX_DECODE_DEPTH", defaults.depth)?, + nodes: env_limit("OTLP_MAX_DECODE_NODES", defaults.nodes)?, + spans: env_limit("OTLP_MAX_SPANS", defaults.spans)?, + attributes: env_limit("OTLP_MAX_ATTRIBUTES", defaults.attributes)?, + events: env_limit("OTLP_MAX_EVENTS", defaults.events)?, + links: env_limit("OTLP_MAX_LINKS", defaults.links)?, + decoded_span_bytes: env_limit( + "OTLP_MAX_DECODED_SPAN_BYTES", + defaults.decoded_span_bytes, + )?, + }) + } +} + +fn env_limit(name: &'static str, default: usize) -> Result { + match std::env::var(name) { + Ok(value) => value + .parse::() + .ok() + .filter(|value| *value > 0) + .ok_or(Error::InvalidLimit(name)), + Err(std::env::VarError::NotPresent) => Ok(default), + Err(_) => Err(Error::InvalidLimit(name)), + } +} + +pub(super) fn json_preflight(payload: &[u8], limits: &DecodeLimits) -> Result<(), Error> { let mut nodes = 0; let mut exceeded = false; let mut decoder = serde_json::Deserializer::from_slice(payload); @@ -20,6 +68,7 @@ pub(super) fn json_preflight(payload: &[u8]) -> Result<(), Error> { nodes: &mut nodes, exceeded: &mut exceeded, depth: 0, + limits, } .deserialize(&mut decoder) .and_then(|()| decoder.end()); @@ -33,6 +82,7 @@ struct JsonBudget<'a> { nodes: &'a mut usize, exceeded: &'a mut bool, depth: usize, + limits: &'a DecodeLimits, } impl<'de> DeserializeSeed<'de> for JsonBudget<'_> { @@ -40,7 +90,7 @@ impl<'de> DeserializeSeed<'de> for JsonBudget<'_> { fn deserialize>(self, decoder: D) -> Result<(), D::Error> { *self.nodes += 1; - if *self.nodes > MAX_NODES || self.depth > MAX_DEPTH { + if *self.nodes > self.limits.nodes || self.depth > self.limits.depth { *self.exceeded = true; return Err(serde::de::Error::custom("OTLP structure exceeds budget")); } @@ -79,6 +129,7 @@ impl<'de> Visitor<'de> for JsonBudget<'_> { nodes: self.nodes, exceeded: self.exceeded, depth: self.depth + 1, + limits: self.limits, })? .is_some() {} @@ -91,6 +142,7 @@ impl<'de> Visitor<'de> for JsonBudget<'_> { nodes: self.nodes, exceeded: self.exceeded, depth: self.depth + 1, + limits: self.limits, })? .is_some() { @@ -98,6 +150,7 @@ impl<'de> Visitor<'de> for JsonBudget<'_> { nodes: self.nodes, exceeded: self.exceeded, depth: self.depth + 1, + limits: self.limits, })?; } Ok(()) @@ -146,8 +199,8 @@ impl MessageKind { } } -pub(super) fn protobuf_preflight(payload: &[u8]) -> Result<(), Error> { - scan_message(payload, MessageKind::Export, 0, &mut 0) +pub(super) fn protobuf_preflight(payload: &[u8], limits: &DecodeLimits) -> Result<(), Error> { + scan_message(payload, MessageKind::Export, 0, &mut 0, limits) } fn scan_message( @@ -155,13 +208,14 @@ fn scan_message( kind: MessageKind, depth: usize, nodes: &mut usize, + limits: &DecodeLimits, ) -> Result<(), Error> { - if depth > MAX_DEPTH { + if depth > limits.depth { return Err(Error::TooLarge); } while !payload.is_empty() { *nodes += 1; - if *nodes > MAX_NODES { + if *nodes > limits.nodes { return Err(Error::TooLarge); } let (tag, wire) = decode_key(&mut payload).map_err(|_| Error::InvalidPayload)?; @@ -171,7 +225,7 @@ fn scan_message( let (message, rest) = payload .split_at_checked(length) .ok_or(Error::InvalidPayload)?; - scan_message(message, child, depth + 1, nodes)?; + scan_message(message, child, depth + 1, nodes, limits)?; payload = rest; } else { skip_field(wire, tag, &mut payload, DecodeContext::default()) @@ -183,11 +237,15 @@ fn scan_message( pub(super) struct Budget { remaining: usize, + pub(super) limits: DecodeLimits, } impl Budget { - pub(super) fn new(remaining: usize) -> Self { - Self { remaining } + pub(super) fn new(limits: DecodeLimits) -> Self { + Self { + remaining: limits.decoded_span_bytes, + limits, + } } pub(super) fn clone_shared( diff --git a/litellm-rust/crates/traces/src/otlp/mod.rs b/litellm-rust/crates/traces/src/otlp/mod.rs index 1f4da76ca60..2e17d868090 100644 --- a/litellm-rust/crates/traces/src/otlp/mod.rs +++ b/litellm-rust/crates/traces/src/otlp/mod.rs @@ -3,6 +3,8 @@ mod limits; mod span; mod wire; +pub use limits::DecodeLimits; + use serde::Serialize; use std::collections::BTreeMap; @@ -36,6 +38,14 @@ pub struct DecodedSpan { } pub fn decode_otlp(body: &[u8], content_type: Option<&str>) -> Result, Error> { - let request = wire::decode(body, content_type)?; - span::flatten(request) + decode_otlp_with_limits(body, content_type, DecodeLimits::from_env()?) +} + +pub fn decode_otlp_with_limits( + body: &[u8], + content_type: Option<&str>, + limits: DecodeLimits, +) -> Result, Error> { + let request = wire::decode(body, content_type, &limits)?; + span::flatten(request, limits) } diff --git a/litellm-rust/crates/traces/src/otlp/span.rs b/litellm-rust/crates/traces/src/otlp/span.rs index 0261e4aeb07..5ab2392ab04 100644 --- a/litellm-rust/crates/traces/src/otlp/span.rs +++ b/litellm-rust/crates/traces/src/otlp/span.rs @@ -8,15 +8,18 @@ use opentelemetry_proto::tonic::{ use super::{ DecodedEvent, DecodedSpan, attributes::attributes, - limits::{Budget, MAX_ATTRIBUTES, MAX_DECODED_SPAN_BYTES, MAX_EVENTS, MAX_SPANS}, + limits::{Budget, DecodeLimits}, }; use crate::{ Error, Shared, normalize::{SpanContext, normalize}, }; -pub(super) fn flatten(request: ExportTraceServiceRequest) -> Result, Error> { - let mut budget = Budget::new(MAX_DECODED_SPAN_BYTES); +pub(super) fn flatten( + request: ExportTraceServiceRequest, + limits: DecodeLimits, +) -> Result, Error> { + let mut budget = Budget::new(limits); let mut spans = Vec::new(); for resource in request.resource_spans { append_resource(resource, &mut budget, &mut spans)?; @@ -49,17 +52,17 @@ fn append_scope( spans: &mut Vec, ) -> Result<(), Error> { let scope = scope_spans.scope.unwrap_or_default(); - if scope.attributes.len() > MAX_ATTRIBUTES { + if scope.attributes.len() > budget.limits.attributes { return Err(Error::TooLarge); } budget.consume(scope.name.len() + scope.version.len())?; let scope_name: Shared = scope.name.into(); let scope_version: Shared = scope.version.into(); for span in scope_spans.spans { - if spans.len() >= MAX_SPANS { + if spans.len() >= budget.limits.spans { return Err(Error::TooLarge); } - validate_span(&span)?; + validate_span(&span, &budget.limits)?; budget.consume( span.name.len() + span.trace_state.len() @@ -85,7 +88,7 @@ fn valid_id(value: &[u8], length: usize) -> bool { value.len() == length && value.iter().any(|byte| *byte != 0) } -fn validate_span(span: &Span) -> Result<(), Error> { +fn validate_span(span: &Span, limits: &DecodeLimits) -> Result<(), Error> { if !valid_id(&span.trace_id, 16) || !valid_id(&span.span_id, 8) || (!span.parent_span_id.is_empty() && !valid_id(&span.parent_span_id, 8)) @@ -99,17 +102,17 @@ fn validate_span(span: &Span) -> Result<(), Error> { { return Err(Error::InvalidPayload); } - if span.events.len() > MAX_EVENTS - || span.links.len() > MAX_EVENTS - || span.attributes.len() > MAX_ATTRIBUTES + if span.events.len() > limits.events + || span.links.len() > limits.links + || span.attributes.len() > limits.attributes || span .links .iter() - .any(|link| link.attributes.len() > MAX_ATTRIBUTES) + .any(|link| link.attributes.len() > limits.attributes) || span .events .iter() - .any(|event| event.attributes.len() > MAX_ATTRIBUTES) + .any(|event| event.attributes.len() > limits.attributes) { return Err(Error::TooLarge); } diff --git a/litellm-rust/crates/traces/src/otlp/wire.rs b/litellm-rust/crates/traces/src/otlp/wire.rs index 2330ac12be3..d61d4099b96 100644 --- a/litellm-rust/crates/traces/src/otlp/wire.rs +++ b/litellm-rust/crates/traces/src/otlp/wire.rs @@ -1,7 +1,7 @@ use opentelemetry_proto::tonic::collector::trace::v1::ExportTraceServiceRequest; use prost::Message; -use super::limits::{json_preflight, protobuf_preflight}; +use super::limits::{DecodeLimits, json_preflight, protobuf_preflight}; use crate::Error; #[derive(strum::EnumString)] @@ -19,6 +19,7 @@ enum OtlpMediaType { pub(super) fn decode( body: &[u8], content_type: Option<&str>, + limits: &DecodeLimits, ) -> Result { let media_type = content_type .unwrap_or("application/x-protobuf") @@ -31,11 +32,11 @@ pub(super) fn decode( let request = match media_type { OtlpMediaType::Json => { - json_preflight(body)?; + json_preflight(body, limits)?; serde_json::from_slice(body).map_err(|_| Error::InvalidPayload)? } OtlpMediaType::Protobuf => { - protobuf_preflight(body)?; + protobuf_preflight(body, limits)?; ExportTraceServiceRequest::decode(body).map_err(|_| Error::InvalidPayload)? } }; diff --git a/litellm-rust/crates/traces/tests/captures.rs b/litellm-rust/crates/traces/tests/captures.rs index fc3527f6253..ca498fc914a 100644 --- a/litellm-rust/crates/traces/tests/captures.rs +++ b/litellm-rust/crates/traces/tests/captures.rs @@ -330,9 +330,7 @@ fn append_response_id(document: &mut Value, trace_id: &str, span_id: &str, respo #[rstest] fn captured_trace_cost_matches_spend_logs( - #[files("../traces-clickhouse/tests/fixtures/*_spend_logs.jsonl")] - #[exclude("deeplite_swarm")] - spend_logs: PathBuf, + #[files("../traces-clickhouse/tests/fixtures/*_spend_logs.jsonl")] spend_logs: PathBuf, ) { let name = capture_name(&spend_logs); let (_, capture, rows, spends) = fixture(&spend_logs); @@ -347,9 +345,7 @@ fn captured_trace_cost_matches_spend_logs( #[rstest] fn unrelated_sibling_transport_leaves_cost_unchanged( - #[files("../traces-clickhouse/tests/fixtures/*_spend_logs.jsonl")] - #[exclude("deeplite_swarm")] - spend_logs: PathBuf, + #[files("../traces-clickhouse/tests/fixtures/*_spend_logs.jsonl")] spend_logs: PathBuf, ) { let name = capture_name(&spend_logs); let (_, capture, rows, spends) = fixture(&spend_logs); @@ -392,9 +388,7 @@ fn unrelated_sibling_transport_leaves_cost_unchanged( #[rstest] fn redundant_genai_response_id_keeps_call_evidence( - #[files("../traces-clickhouse/tests/fixtures/*_spend_logs.jsonl")] - #[exclude("deeplite_swarm")] - spend_logs: PathBuf, + #[files("../traces-clickhouse/tests/fixtures/*_spend_logs.jsonl")] spend_logs: PathBuf, ) { let (data, capture, _, _) = fixture(&spend_logs); let name = capture.name; diff --git a/litellm-rust/crates/traces/tests/fixtures/deeplite_auth_error.json b/litellm-rust/crates/traces/tests/fixtures/deeplite_auth_error.json deleted file mode 100644 index ef207be9358..00000000000 --- a/litellm-rust/crates/traces/tests/fixtures/deeplite_auth_error.json +++ /dev/null @@ -1,1614 +0,0 @@ -{ - "resourceSpans": [ - { - "resource": { - "attributes": [ - { - "key": "telemetry.sdk.language", - "value": { - "stringValue": "python" - } - }, - { - "key": "telemetry.sdk.name", - "value": { - "stringValue": "opentelemetry" - } - }, - { - "key": "telemetry.sdk.version", - "value": { - "stringValue": "1.45.0" - } - }, - { - "key": "service.instance.id", - "value": { - "stringValue": "cedd2594-abc5-48f2-a9d1-b892921fadfd" - } - }, - { - "key": "service.name", - "value": { - "stringValue": "deeplite" - } - } - ] - }, - "scopeSpans": [ - { - "scope": { - "name": "langsmith" - }, - "spans": [ - { - "traceId": "7b787d5c997d768a725a3a2f0278e857", - "spanId": "93886a81b22f3dab", - "parentSpanId": "11f6195c25249ab1", - "name": "__start__", - "kind": 1, - "startTimeUnixNano": "1790967512073597952", - "endTimeUnixNano": "1790967512075591936", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "__start__" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langgraph" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "0" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "__start__" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__start__\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"__start__\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "__start__:af3b0b0a-9397-3b9d-0717-b11174443ca9" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:0, langsmith:hidden" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJtZXNzYWdlcyI6W3sicm9sZSI6InVzZXIiLCJjb250ZW50IjoiRm9yIGEgc3ludGhldGljIHRyYWNpbmcgZml4dHVyZSwgZXhwbGFpbiBQeXRob24gdHVwbGUgdmVyc3VzIGxpc3QgaW1tdXRhYmlsaXR5IGluIGF0IG1vc3QgMTIwIHdvcmRzLiBVc2Ugb25seSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBpZiB5b3Ugc2VhcmNoLiBIYXZlIHRoZSBza2VwdGljIGFuZCB2ZXJpZmllciBjaGVjayBpdCwgdGhlbiBoYXZlIHRoZSBlZGl0b3Igd3JpdGUgL2Fuc3dlci5tZC4gS2VlcCB0aGUgcnVuIHNob3J0IGFuZCBkbyBub3QgYXNrIGZvbGxvdy11cCBxdWVzdGlvbnMuIn1dfQ==" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJtZXNzYWdlcyI6W3sicm9sZSI6InVzZXIiLCJjb250ZW50IjoiRm9yIGEgc3ludGhldGljIHRyYWNpbmcgZml4dHVyZSwgZXhwbGFpbiBQeXRob24gdHVwbGUgdmVyc3VzIGxpc3QgaW1tdXRhYmlsaXR5IGluIGF0IG1vc3QgMTIwIHdvcmRzLiBVc2Ugb25seSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBpZiB5b3Ugc2VhcmNoLiBIYXZlIHRoZSBza2VwdGljIGFuZCB2ZXJpZmllciBjaGVjayBpdCwgdGhlbiBoYXZlIHRoZSBlZGl0b3Igd3JpdGUgL2Fuc3dlci5tZC4gS2VlcCB0aGUgcnVuIHNob3J0IGFuZCBkbyBub3QgYXNrIGZvbGxvdy11cCBxdWVzdGlvbnMuIn1dfQ==" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "7b787d5c997d768a725a3a2f0278e857", - "spanId": "aa1eaf69717f1df1", - "parentSpanId": "93886a81b22f3dab", - "name": "route_to_active_agent", - "kind": 1, - "startTimeUnixNano": "1790967512074637056", - "endTimeUnixNano": "1790967512075297024", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "route_to_active_agent" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langgraph" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "0" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "__start__" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__start__\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"__start__\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "__start__:af3b0b0a-9397-3b9d-0717-b11174443ca9" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "langsmith:hidden, seq:step:2" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJvdXRwdXQiOiJyZXNlYXJjaGVyIn0=" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "7b787d5c997d768a725a3a2f0278e857", - "spanId": "88d2e1bce2887a89", - "parentSpanId": "b580832fc04b0921", - "name": "ChatAnthropic", - "kind": 1, - "startTimeUnixNano": "1790967512090679808", - "endTimeUnixNano": "1790967512605561856", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chat" - } - }, - { - "key": "gen_ai.serialized.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "llm" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "gen_ai.request.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "gen_ai.tool.definitions", - "value": { - "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"web_search\",\"input_schema\":{\"properties\":{\"query\":{\"type\":\"string\"}},\"required\":[\"query\"],\"type\":\"object\"},\"description\":\"Search the web with Exa for current facts and return excerpts with source URLs\"},{\"name\":\"transfer_to_skeptic\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send findings to the skeptic for critique\"},{\"name\":\"transfer_to_verifier\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send revised findings for source verification\"}]" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_chat_model" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd|model:2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" - } - }, - { - "key": "langsmith.metadata.ls_provider", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "langsmith.metadata.ls_model_name", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.ls_model_type", - "value": { - "stringValue": "chat" - } - }, - { - "key": "langsmith.metadata.ls_max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.lc_versions", - "value": { - "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.model_kwargs", - "value": { - "stringValue": "{}" - } - }, - { - "key": "langsmith.metadata.streaming", - "value": { - "boolValue": false - } - }, - { - "key": "langsmith.metadata.max_retries", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata._type", - "value": { - "stringValue": "anthropic-chat" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "events": [ - { - "timeUnixNano": "1790967512686323000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "7b787d5c997d768a725a3a2f0278e857", - "spanId": "b580832fc04b0921", - "parentSpanId": "382ca31426f8f943", - "name": "UnsupportedContentMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790967512081928960", - "endTimeUnixNano": "1790967512610889984", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "UnsupportedContentMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd|model:2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJvdXRwdXQiOm51bGx9" - } - } - ], - "events": [ - { - "timeUnixNano": "1790967512686465000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "7b787d5c997d768a725a3a2f0278e857", - "spanId": "382ca31426f8f943", - "parentSpanId": "e247cc846cdbc99e", - "name": "FilesystemMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790967512080943104", - "endTimeUnixNano": "1790967512614221056", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd|model:2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJvdXRwdXQiOm51bGx9" - } - } - ], - "events": [ - { - "timeUnixNano": "1790967512686562000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "7b787d5c997d768a725a3a2f0278e857", - "spanId": "e247cc846cdbc99e", - "parentSpanId": "77a5ba07fbe8fb8b", - "name": "model", - "kind": 1, - "startTimeUnixNano": "1790967512077792000", - "endTimeUnixNano": "1790967512617573888", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd|model:2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - } - ], - "events": [ - { - "timeUnixNano": "1790967512686704000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "7b787d5c997d768a725a3a2f0278e857", - "spanId": "77a5ba07fbe8fb8b", - "parentSpanId": "7b77a08f725c2a60", - "name": "researcher", - "kind": 1, - "startTimeUnixNano": "1790967512076764160", - "endTimeUnixNano": "1790967512623192064", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:researcher\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"researcher\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - } - ], - "events": [ - { - "timeUnixNano": "1790967512687171000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "7b787d5c997d768a725a3a2f0278e857", - "spanId": "7b77a08f725c2a60", - "parentSpanId": "11f6195c25249ab1", - "name": "researcher", - "kind": 1, - "startTimeUnixNano": "1790967512076327168", - "endTimeUnixNano": "1790967512626224128", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langgraph" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:researcher\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"researcher\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - } - ], - "events": [ - { - "timeUnixNano": "1790967512687277000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "7b787d5c997d768a725a3a2f0278e857", - "spanId": "11f6195c25249ab1", - "parentSpanId": "9e65698af98970b0", - "name": "LangGraph", - "kind": 1, - "startTimeUnixNano": "1790967512019313152", - "endTimeUnixNano": "1790967512630693888", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "LangGraph" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langgraph" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJtZXNzYWdlcyI6W3sicm9sZSI6InVzZXIiLCJjb250ZW50IjoiRm9yIGEgc3ludGhldGljIHRyYWNpbmcgZml4dHVyZSwgZXhwbGFpbiBQeXRob24gdHVwbGUgdmVyc3VzIGxpc3QgaW1tdXRhYmlsaXR5IGluIGF0IG1vc3QgMTIwIHdvcmRzLiBVc2Ugb25seSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBpZiB5b3Ugc2VhcmNoLiBIYXZlIHRoZSBza2VwdGljIGFuZCB2ZXJpZmllciBjaGVjayBpdCwgdGhlbiBoYXZlIHRoZSBlZGl0b3Igd3JpdGUgL2Fuc3dlci5tZC4gS2VlcCB0aGUgcnVuIHNob3J0IGFuZCBkbyBub3QgYXNrIGZvbGxvdy11cCBxdWVzdGlvbnMuIn1dfQ==" - } - } - ], - "events": [ - { - "timeUnixNano": "1790967512687350000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'\n\n\nDuring task with name 'researcher' and id '816a3f65-9150-0b6d-54aa-920fdcfe25cd'" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'\n\n\nDuring task with name 'researcher' and id '816a3f65-9150-0b6d-54aa-920fdcfe25cd'\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - } - ] - }, - { - "scope": { - "name": "deeplite" - }, - "spans": [ - { - "traceId": "7b787d5c997d768a725a3a2f0278e857", - "spanId": "9e65698af98970b0", - "name": "deeplite.run", - "kind": 1, - "startTimeUnixNano": "1790967512013991000", - "endTimeUnixNano": "1790967512696195000", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "input.value", - "value": { - "stringValue": "For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions." - } - } - ], - "events": [ - { - "timeUnixNano": "1790967512696180000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "langchain_anthropic.chat_models.AnthropicAuthenticationError" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Traceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/opentelemetry/trace/__init__.py\", line 602, in use_span\n yield span\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/opentelemetry/sdk/trace/__init__.py\", line 1136, in start_as_current_span\n yield span\n File \"/workspace/deeplite/src/deeplite/cli.py\", line 22, in run_task\n result: Final = agent.invoke(\n ~~~~~~~~~~~~^\n {\"messages\": [{\"role\": \"user\", \"content\": task}]}, config={\"recursion_limit\": 40}\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'\nDuring task with name 'researcher' and id '816a3f65-9150-0b6d-54aa-920fdcfe25cd'\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "message": "AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}", - "code": 2 - }, - "flags": 256 - } - ] - } - ] - } - ] -} diff --git a/litellm-rust/crates/traces/tests/fixtures/deeplite_swarm.json b/litellm-rust/crates/traces/tests/fixtures/deeplite_swarm.json deleted file mode 100644 index 19351078af8..00000000000 --- a/litellm-rust/crates/traces/tests/fixtures/deeplite_swarm.json +++ /dev/null @@ -1,9812 +0,0 @@ -{ - "resourceSpans": [ - { - "resource": { - "attributes": [ - { - "key": "telemetry.sdk.language", - "value": { - "stringValue": "python" - } - }, - { - "key": "telemetry.sdk.name", - "value": { - "stringValue": "opentelemetry" - } - }, - { - "key": "telemetry.sdk.version", - "value": { - "stringValue": "1.45.0" - } - }, - { - "key": "service.instance.id", - "value": { - "stringValue": "b873df4c-5106-4097-a20b-b9380724f4d9" - } - }, - { - "key": "service.name", - "value": { - "stringValue": "deeplite" - } - } - ] - }, - "scopeSpans": [ - { - "scope": { - "name": "langsmith" - }, - "spans": [ - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "1b73fdc79da730c3", - "parentSpanId": "04ffc0db9ce0f358", - "name": "__start__", - "kind": 1, - "startTimeUnixNano": "1790968013211052032", - "endTimeUnixNano": "1790968013212278016", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "__start__" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langgraph" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "0" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "__start__" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__start__\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"__start__\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "__start__:a08efee1-6b20-6c11-d2f1-f04016499ab0" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "langsmith:hidden, graph:step:0" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJtZXNzYWdlcyI6W3sicm9sZSI6InVzZXIiLCJjb250ZW50IjoiRm9yIGEgc3ludGhldGljIHRyYWNpbmcgZml4dHVyZSwgZXhwbGFpbiBQeXRob24gdHVwbGUgdmVyc3VzIGxpc3QgaW1tdXRhYmlsaXR5IGluIGF0IG1vc3QgMTIwIHdvcmRzLiBVc2Ugb25seSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBpZiB5b3Ugc2VhcmNoLiBIYXZlIHRoZSBza2VwdGljIGFuZCB2ZXJpZmllciBjaGVjayBpdCwgdGhlbiBoYXZlIHRoZSBlZGl0b3Igd3JpdGUgL2Fuc3dlci5tZC4gS2VlcCB0aGUgcnVuIHNob3J0IGFuZCBkbyBub3QgYXNrIGZvbGxvdy11cCBxdWVzdGlvbnMuIn1dfQ==" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJtZXNzYWdlcyI6W3sicm9sZSI6InVzZXIiLCJjb250ZW50IjoiRm9yIGEgc3ludGhldGljIHRyYWNpbmcgZml4dHVyZSwgZXhwbGFpbiBQeXRob24gdHVwbGUgdmVyc3VzIGxpc3QgaW1tdXRhYmlsaXR5IGluIGF0IG1vc3QgMTIwIHdvcmRzLiBVc2Ugb25seSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBpZiB5b3Ugc2VhcmNoLiBIYXZlIHRoZSBza2VwdGljIGFuZCB2ZXJpZmllciBjaGVjayBpdCwgdGhlbiBoYXZlIHRoZSBlZGl0b3Igd3JpdGUgL2Fuc3dlci5tZC4gS2VlcCB0aGUgcnVuIHNob3J0IGFuZCBkbyBub3QgYXNrIGZvbGxvdy11cCBxdWVzdGlvbnMuIn1dfQ==" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "42058e9b69a517f4", - "parentSpanId": "1b73fdc79da730c3", - "name": "route_to_active_agent", - "kind": 1, - "startTimeUnixNano": "1790968013211607808", - "endTimeUnixNano": "1790968013211869952", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "route_to_active_agent" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langgraph" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "0" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "__start__" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__start__\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"__start__\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "__start__:a08efee1-6b20-6c11-d2f1-f04016499ab0" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "langsmith:hidden, seq:step:2" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJvdXRwdXQiOiJyZXNlYXJjaGVyIn0=" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - } - ] - } - ] - }, - { - "resource": { - "attributes": [ - { - "key": "telemetry.sdk.language", - "value": { - "stringValue": "python" - } - }, - { - "key": "telemetry.sdk.name", - "value": { - "stringValue": "opentelemetry" - } - }, - { - "key": "telemetry.sdk.version", - "value": { - "stringValue": "1.45.0" - } - }, - { - "key": "service.instance.id", - "value": { - "stringValue": "b873df4c-5106-4097-a20b-b9380724f4d9" - } - }, - { - "key": "service.name", - "value": { - "stringValue": "deeplite" - } - } - ] - }, - "scopeSpans": [ - { - "scope": { - "name": "langsmith" - }, - "spans": [ - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "57b096e0e89c429f", - "parentSpanId": "08f0feca38b72d47", - "name": "model", - "kind": 1, - "startTimeUnixNano": "1790968013213167872", - "endTimeUnixNano": "1790968018770104832", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:8421bdfe-880b-cb10-d152-84cb9d9551f4" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJtZXNzYWdlcyI6W3siY29udGVudCI6IkZvciBhIHN5bnRoZXRpYyB0cmFjaW5nIGZpeHR1cmUsIGV4cGxhaW4gUHl0aG9uIHR1cGxlIHZlcnN1cyBsaXN0IGltbXV0YWJpbGl0eSBpbiBhdCBtb3N0IDEyMCB3b3Jkcy4gVXNlIG9ubHkgb2ZmaWNpYWwgUHl0aG9uIGRvY3VtZW50YXRpb24gaWYgeW91IHNlYXJjaC4gSGF2ZSB0aGUgc2tlcHRpYyBhbmQgdmVyaWZpZXIgY2hlY2sgaXQsIHRoZW4gaGF2ZSB0aGUgZWRpdG9yIHdyaXRlIC9hbnN3ZXIubWQuIEtlZXAgdGhlIHJ1biBzaG9ydCBhbmQgZG8gbm90IGFzayBmb2xsb3ctdXAgcXVlc3Rpb25zLiIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoiaHVtYW4iLCJpZCI6IjQ2MjA0MzA1LWY4ZWUtNDM4NC05Y2U4LWZjZDgwYmZjZGY3NSJ9XX0=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJvdXRwdXQiOlt7ImdyYXBoIjpudWxsLCJ1cGRhdGUiOnsibWVzc2FnZXMiOlt7ImNvbnRlbnQiOlt7ImlkIjoidG9vbHVfMDFCMkxmSEdEallTRkpobWlYTmo0Q3VRIiwiY2FsbGVyIjp7InR5cGUiOiJkaXJlY3QifSwiaW5wdXQiOnsicXVlcnkiOiJkb2NzLnB5dGhvbi5vcmcgdHVwbGVzIGltbXV0YWJsZSBzZXF1ZW5jZXMgbGlzdHMgbXV0YWJsZSBkYXRhIHN0cnVjdHVyZXMgdHV0b3JpYWwifSwibmFtZSI6IndlYl9zZWFyY2giLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3OWFXOWJyZW5QcWd5YmZOd1AiLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6Mjg0NSwib3V0cHV0X3Rva2VucyI6NzMsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjB9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlc2VhcmNoZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtMjFhMy03MDAwLWEzODEtMjg0YTZhMGMwM2Y3LTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoid2ViX3NlYXJjaCIsImFyZ3MiOnsicXVlcnkiOiJkb2NzLnB5dGhvbi5vcmcgdHVwbGVzIGltbXV0YWJsZSBzZXF1ZW5jZXMgbGlzdHMgbXV0YWJsZSBkYXRhIHN0cnVjdHVyZXMgdHV0b3JpYWwifSwiaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJ0eXBlIjoidG9vbF9jYWxsIn1dLCJpbnZhbGlkX3Rvb2xfY2FsbHMiOltdLCJ1c2FnZV9tZXRhZGF0YSI6eyJpbnB1dF90b2tlbnMiOjI4NDUsIm91dHB1dF90b2tlbnMiOjczLCJ0b3RhbF90b2tlbnMiOjI5MTgsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjB9fX1dfSwicmVzdW1lIjpudWxsLCJnb3RvIjpbXX1dfQ==" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "3535364df77cec3a", - "parentSpanId": "57b096e0e89c429f", - "name": "FilesystemMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968013214705920", - "endTimeUnixNano": "1790968018769807104", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:8421bdfe-880b-cb10-d152-84cb9d9551f4" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "005fac1918b863b6", - "parentSpanId": "3535364df77cec3a", - "name": "UnsupportedContentMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968013215195904", - "endTimeUnixNano": "1790968018769697792", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "UnsupportedContentMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:8421bdfe-880b-cb10-d152-84cb9d9551f4" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJvdXRwdXQiOnsicmVzdWx0IjpbeyJjb250ZW50IjpbeyJpZCI6InRvb2x1XzAxQjJMZkhHRGpZU0ZKaG1pWE5qNEN1USIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7InF1ZXJ5IjoiZG9jcy5weXRob24ub3JnIHR1cGxlcyBpbW11dGFibGUgc2VxdWVuY2VzIGxpc3RzIG11dGFibGUgZGF0YSBzdHJ1Y3R1cmVzIHR1dG9yaWFsIn0sIm5hbWUiOiJ3ZWJfc2VhcmNoIiwidHlwZSI6InRvb2xfdXNlIiwidG9vbHNldF9uYW1lIjpudWxsfV0sImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnsiaWQiOiJtc2dfMDExQ2ZkdzlhVzlicmVuUHFneWJmTndQIiwiY29udGFpbmVyIjpudWxsLCJkaWFnbm9zdGljcyI6bnVsbCwibW9kZWwiOiJjbGF1ZGUtc29ubmV0Iiwic3RvcF9kZXRhaWxzIjpudWxsLCJzdG9wX3JlYXNvbiI6InRvb2xfdXNlIiwic3RvcF9zZXF1ZW5jZSI6bnVsbCwidXNhZ2UiOnsiY2FjaGVfY3JlYXRpb24iOnsiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MH0sImNhY2hlX2NyZWF0aW9uX2lucHV0X3Rva2VucyI6MCwiY2FjaGVfcmVhZF9pbnB1dF90b2tlbnMiOjAsImluZmVyZW5jZV9nZW8iOiJnbG9iYWwiLCJpbnB1dF90b2tlbnMiOjI4NDUsIm91dHB1dF90b2tlbnMiOjczLCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjowfSwic2VydmVyX3Rvb2xfdXNlIjpudWxsLCJzZXJ2aWNlX3RpZXIiOiJzdGFuZGFyZCJ9LCJtb2RlbF9uYW1lIjoiY2xhdWRlLXNvbm5ldCIsIm1vZGVsX3Byb3ZpZGVyIjoiYW50aHJvcGljIn0sInR5cGUiOiJhaSIsIm5hbWUiOiJyZXNlYXJjaGVyIiwiaWQiOiJsY19ydW4tLTAxYTBmZTAzLTIxYTMtNzAwMC1hMzgxLTI4NGE2YTBjMDNmNy0wIiwidG9vbF9jYWxscyI6W3sibmFtZSI6IndlYl9zZWFyY2giLCJhcmdzIjp7InF1ZXJ5IjoiZG9jcy5weXRob24ub3JnIHR1cGxlcyBpbW11dGFibGUgc2VxdWVuY2VzIGxpc3RzIG11dGFibGUgZGF0YSBzdHJ1Y3R1cmVzIHR1dG9yaWFsIn0sImlkIjoidG9vbHVfMDFCMkxmSEdEallTRkpobWlYTmo0Q3VRIiwidHlwZSI6InRvb2xfY2FsbCJ9XSwiaW52YWxpZF90b29sX2NhbGxzIjpbXSwidXNhZ2VfbWV0YWRhdGEiOnsiaW5wdXRfdG9rZW5zIjoyODQ1LCJvdXRwdXRfdG9rZW5zIjo3MywidG90YWxfdG9rZW5zIjoyOTE4LCJpbnB1dF90b2tlbl9kZXRhaWxzIjp7ImNhY2hlX3JlYWQiOjAsImNhY2hlX2NyZWF0aW9uIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowfSwib3V0cHV0X3Rva2VuX2RldGFpbHMiOnsicmVhc29uaW5nIjowfX19XSwic3RydWN0dXJlZF9yZXNwb25zZSI6bnVsbH19" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "3baa483880660b3b", - "parentSpanId": "005fac1918b863b6", - "name": "ChatAnthropic", - "kind": 1, - "startTimeUnixNano": "1790968013219345920", - "endTimeUnixNano": "1790968018769428992", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chat" - } - }, - { - "key": "gen_ai.serialized.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "llm" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "gen_ai.request.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "gen_ai.tool.definitions", - "value": { - "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"web_search\",\"input_schema\":{\"properties\":{\"query\":{\"type\":\"string\"}},\"required\":[\"query\"],\"type\":\"object\"},\"description\":\"Search the web with Exa for current facts and return excerpts with source URLs\"},{\"name\":\"transfer_to_skeptic\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send findings to the skeptic for critique\"},{\"name\":\"transfer_to_verifier\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send revised findings for source verification\"}]" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_chat_model" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:8421bdfe-880b-cb10-d152-84cb9d9551f4" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.ls_provider", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "langsmith.metadata.ls_model_name", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.ls_model_type", - "value": { - "stringValue": "chat" - } - }, - { - "key": "langsmith.metadata.ls_max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.lc_versions", - "value": { - "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.model_kwargs", - "value": { - "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" - } - }, - { - "key": "langsmith.metadata.streaming", - "value": { - "boolValue": false - } - }, - { - "key": "langsmith.metadata.max_retries", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata._type", - "value": { - "stringValue": "anthropic-chat" - } - }, - { - "key": "langsmith.metadata.usage_metadata", - "value": { - "stringValue": "{\"input_tokens\":2845,\"output_tokens\":73,\"total_tokens\":2918,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":0}}" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.usage.input_tokens", - "value": { - "intValue": "2845" - } - }, - { - "key": "gen_ai.usage.output_tokens", - "value": { - "intValue": "73" - } - }, - { - "key": "gen_ai.usage.total_tokens", - "value": { - "intValue": "2918" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "cdef663fc44a4582", - "parentSpanId": "48b7b97682a8fe08", - "name": "FilesystemMiddleware.wrap_tool_call", - "kind": 1, - "startTimeUnixNano": "1790968018771259904", - "endTimeUnixNano": "1790968020179634944", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_tool_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|tools:377cb0ac-b4a5-3ad6-f00b-9afdc4d589a0" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "556c2690603624cc", - "parentSpanId": "cdef663fc44a4582", - "name": "web_search", - "kind": 1, - "startTimeUnixNano": "1790968018771609088", - "endTimeUnixNano": "1790968020179266816", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "execute_tool" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "tool" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "web_search" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "gen_ai.tool.name", - "value": { - "stringValue": "web_search" - } - }, - { - "key": "gen_ai.tool.call.id", - "value": { - "stringValue": "toolu_01B2LfHGDjYSFJhmiXNj4CuQ" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|tools:377cb0ac-b4a5-3ad6-f00b-9afdc4d589a0" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "48b7b97682a8fe08", - "parentSpanId": "08f0feca38b72d47", - "name": "tools", - "kind": 1, - "startTimeUnixNano": "1790968018770586112", - "endTimeUnixNano": "1790968020180293120", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|tools:377cb0ac-b4a5-3ad6-f00b-9afdc4d589a0" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:2" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJpbnB1dCI6W3sibmFtZSI6IndlYl9zZWFyY2giLCJhcmdzIjp7InF1ZXJ5IjoiZG9jcy5weXRob24ub3JnIHR1cGxlcyBpbW11dGFibGUgc2VxdWVuY2VzIGxpc3RzIG11dGFibGUgZGF0YSBzdHJ1Y3R1cmVzIHR1dG9yaWFsIn0sImlkIjoidG9vbHVfMDFCMkxmSEdEallTRkpobWlYTmo0Q3VRIiwidHlwZSI6InRvb2xfY2FsbCJ9XX0=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - } - ] - } - ] - }, - { - "resource": { - "attributes": [ - { - "key": "telemetry.sdk.language", - "value": { - "stringValue": "python" - } - }, - { - "key": "telemetry.sdk.name", - "value": { - "stringValue": "opentelemetry" - } - }, - { - "key": "telemetry.sdk.version", - "value": { - "stringValue": "1.45.0" - } - }, - { - "key": "service.instance.id", - "value": { - "stringValue": "b873df4c-5106-4097-a20b-b9380724f4d9" - } - }, - { - "key": "service.name", - "value": { - "stringValue": "deeplite" - } - } - ] - }, - "scopeSpans": [ - { - "scope": { - "name": "langsmith" - }, - "spans": [ - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "248062b114d67a66", - "parentSpanId": "08f0feca38b72d47", - "name": "tools", - "kind": 1, - "startTimeUnixNano": "1790968023765523968", - "endTimeUnixNano": "1790968023774028032", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "4" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|tools:ed0001c5-0402-bf5e-ceed-69e43e82ae5e" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:4" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJpbnB1dCI6W3sibmFtZSI6InRyYW5zZmVyX3RvX3NrZXB0aWMiLCJhcmdzIjp7fSwiaWQiOiJ0b29sdV8wMVhqajNhUmRXeWhCSmZQbVRKQnhRYTkiLCJ0eXBlIjoidG9vbF9jYWxsIn1dfQ==" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - } - ], - "events": [ - { - "timeUnixNano": "1790968023840499000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic')" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic')\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 2 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "1fd1c862b3a50355", - "parentSpanId": "248062b114d67a66", - "name": "FilesystemMiddleware.wrap_tool_call", - "kind": 1, - "startTimeUnixNano": "1790968023765999104", - "endTimeUnixNano": "1790968023766906112", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_tool_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "4" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|tools:ed0001c5-0402-bf5e-ceed-69e43e82ae5e" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "d92a848281469e5a", - "parentSpanId": "1fd1c862b3a50355", - "name": "transfer_to_skeptic", - "kind": 1, - "startTimeUnixNano": "1790968023766263040", - "endTimeUnixNano": "1790968023766625792", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "tool" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "transfer_to_skeptic" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "execute_tool" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "gen_ai.tool.name", - "value": { - "stringValue": "transfer_to_skeptic" - } - }, - { - "key": "gen_ai.tool.call.id", - "value": { - "stringValue": "toolu_01Xjj3aRdWyhBJfPmTJBxQa9" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "4" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|tools:ed0001c5-0402-bf5e-ceed-69e43e82ae5e" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.__handoff_destination", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "9cc6e8991d091c19", - "parentSpanId": "08f0feca38b72d47", - "name": "model", - "kind": 1, - "startTimeUnixNano": "1790968020180871936", - "endTimeUnixNano": "1790968023765219072", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "3" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:c92c732a-60d5-e72e-21dd-29893acbe69a" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:3" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "95614a9848c5f7d5", - "parentSpanId": "9cc6e8991d091c19", - "name": "FilesystemMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968020181624832", - "endTimeUnixNano": "1790968023765062144", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "3" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:c92c732a-60d5-e72e-21dd-29893acbe69a" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "25a7cd951117a4e0", - "parentSpanId": "95614a9848c5f7d5", - "name": "UnsupportedContentMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968020182045952", - "endTimeUnixNano": "1790968023764993024", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "UnsupportedContentMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "3" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:c92c732a-60d5-e72e-21dd-29893acbe69a" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "0d31577e2d5562cc", - "parentSpanId": "25a7cd951117a4e0", - "name": "ChatAnthropic", - "kind": 1, - "startTimeUnixNano": "1790968020184427008", - "endTimeUnixNano": "1790968023764837120", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chat" - } - }, - { - "key": "gen_ai.serialized.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "llm" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "gen_ai.request.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "gen_ai.tool.definitions", - "value": { - "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"web_search\",\"input_schema\":{\"properties\":{\"query\":{\"type\":\"string\"}},\"required\":[\"query\"],\"type\":\"object\"},\"description\":\"Search the web with Exa for current facts and return excerpts with source URLs\"},{\"name\":\"transfer_to_skeptic\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send findings to the skeptic for critique\"},{\"name\":\"transfer_to_verifier\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send revised findings for source verification\"}]" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_chat_model" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "3" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:c92c732a-60d5-e72e-21dd-29893acbe69a" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.ls_provider", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "langsmith.metadata.ls_model_name", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.ls_model_type", - "value": { - "stringValue": "chat" - } - }, - { - "key": "langsmith.metadata.ls_max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.lc_versions", - "value": { - "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.model_kwargs", - "value": { - "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" - } - }, - { - "key": "langsmith.metadata.streaming", - "value": { - "boolValue": false - } - }, - { - "key": "langsmith.metadata.max_retries", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata._type", - "value": { - "stringValue": "anthropic-chat" - } - }, - { - "key": "langsmith.metadata.usage_metadata", - "value": { - "stringValue": "{\"input_tokens\":7378,\"output_tokens\":33,\"total_tokens\":7411,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":0}}" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.usage.input_tokens", - "value": { - "intValue": "7378" - } - }, - { - "key": "gen_ai.usage.output_tokens", - "value": { - "intValue": "33" - } - }, - { - "key": "gen_ai.usage.total_tokens", - "value": { - "intValue": "7411" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "08f0feca38b72d47", - "parentSpanId": "e2830d2d0406001a", - "name": "researcher", - "kind": 1, - "startTimeUnixNano": "1790968013212771840", - "endTimeUnixNano": "1790968023777713152", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:researcher\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"researcher\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - } - ], - "events": [ - { - "timeUnixNano": "1790968023841631000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "ParentCommand(Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic')" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: ParentCommand(Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic')\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "e2830d2d0406001a", - "parentSpanId": "04ffc0db9ce0f358", - "name": "researcher", - "kind": 1, - "startTimeUnixNano": "1790968013212549888", - "endTimeUnixNano": "1790968023779422976", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langgraph" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "researcher" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:researcher\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"researcher\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - } - ], - "events": [ - { - "timeUnixNano": "1790968023841736000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "ParentCommand(Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic')" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: ParentCommand(Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic')\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - } - ] - } - ] - }, - { - "resource": { - "attributes": [ - { - "key": "telemetry.sdk.language", - "value": { - "stringValue": "python" - } - }, - { - "key": "telemetry.sdk.name", - "value": { - "stringValue": "opentelemetry" - } - }, - { - "key": "telemetry.sdk.version", - "value": { - "stringValue": "1.45.0" - } - }, - { - "key": "service.instance.id", - "value": { - "stringValue": "b873df4c-5106-4097-a20b-b9380724f4d9" - } - }, - { - "key": "service.name", - "value": { - "stringValue": "deeplite" - } - } - ] - }, - "scopeSpans": [ - { - "scope": { - "name": "langsmith" - }, - "spans": [ - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "3049adb48476557c", - "parentSpanId": "419c86d999598365", - "name": "tools", - "kind": 1, - "startTimeUnixNano": "1790968030835418880", - "endTimeUnixNano": "1790968030840750848", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|tools:e52223df-38bd-4e1b-4faf-e72de38488d4" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:2" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJpbnB1dCI6W3sibmFtZSI6InRyYW5zZmVyX3RvX3ZlcmlmaWVyIiwiYXJncyI6e30sImlkIjoidG9vbHVfMDFINmZWOEp2UkpOdlh5NDdlUm5kM2pIIiwidHlwZSI6InRvb2xfY2FsbCJ9XX0=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - } - ], - "events": [ - { - "timeUnixNano": "1790968030907778000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': 'CAQS/REKEQgSGAI4AUIJbmFycmF0aW9uEgwFh3AVJZP3s8y1Hq0aDG76uhHONaScXAGShiIwGgjLXHUx1yZrkLPljjzTOQycpLJiKVwXcxm/EzKJm1s8M5WxuREWEldXcoaN0/msKpkRMT+eLb5ih9rAHULTomUNsUwJeu0jrJe4GLazy7sP5KtjEOEBKQsXUfoQ7fDkZOQUHZi9zzQN4hFNmYJUf3OVqf9TQNdC1+m//HAZPfWmAy6HtDvm7kgBJkCEoiFnm7tn/PX1hXGPRgWc6BTXUMr2WA8aKyqggRUbMH2+JYv5iWZddCc1up1Nbr3sF7WPcot9ZBhyHQXr692zeJk6SJgygIVrASbMly2bBxTWJB623gVgzpCmVSLZFpkKXgPcp8hGyDKOvF6SiQSHqGRxQofr7Vs1aPhfZixROJGD+MlrkggVAnGMyYIDUZpavtCeiU1JmBSz0084bXPtT/tnpsKOnSPYZQo3B0BXKbqA/WsKng8/V3Z8Uuajo6IVZ2hgA1WDduqQOQkExGU6pFuLhebIjuWxSNI/DffvR//LNqCfvdnf0hvoPtDxfx/SawIx4/spq9xbwFzHtLgoHg1F2wFw7clPDlg1PyD/v2yJG3V9T8GL6jGPE6rhfil/u4HNvf7BW0dQzCTTXcqZy4nByy0+p+S7ZxfMl4Kpxa2gOhhSNjfpfuX0QpL4kME8J1nliFN1d8KqEPuDI18BQHUhD/UfY29oA0x510FjM/BsLZ4n5sppkoIi7CFoQq2aAKVNfC1KilhIpRD+1dyDtZQklN8gZpOESHw6ML1TtU0yfAcbmqoxJ6hhjzwH6CMsTQEEy8MbRBM+QKKkIRdRCPHGFW2LkuR50+J0pF/tr6pqVvJeozfiMnrEilB27TZP4nKTJG8rd//vCWen0y7CA/8dBJ9gdp5tx7NVA45k1gdcxER1gYouNX3n1vG3/B1F4+93wXW9Mqo6Us59TQmrb9Nqa7pSQNSrH06w1GxyBAlkFfqAlafk16aMpq416TJYpGy43WCUiCcLWlhiWgz2sgOLAXP9a5weWAKRC8J6jkcUkDeXnW+HFSiPM6+9Bo6kVhLUhN5rc4mHZOZpF7ptPpsQN4XCqLPsqpRH/8o5XpyC6ZneTeF2ExtjhwZVjXDwMbIzVYIbw1y2PPGw8dC7pc4sIVSnI4oQAH0v650ghfhmMevWW4h4Pylbw/DG4fdeT3+8z0f8MOSTtfipx05/QttHlAvODRxa5yDCvOz6n3f1BO0N/4MbGyOM27qW4x8mBVoryUZWfsmhfi0/GfNvB8+ylTGbYNX27OcEF5WZtNqbWEy7V5GbmZUSxspcg7FBZ3j3/3L7muvZXoZi1f5erq4y3lSH+oF7qPFnvieyLOCwubcQy+oyowj4cD0idRecnp+s+52D7+mzF1gpW+f+cJasoxigbxkOloS4yeiKvgM4nWSpGEj12RPx5o80EmziXN9t4zJzW1htA5hXJJeFympMYtyCUCevRWVmrRYktQ7UnCa6tL/AVPi1ni5XCXHfLOuqfK5KLYxjwVtdhhfmCLvpaKVNCEOCf4nNGHqD98wUb0ejWNwDYBnJGkBRw9RVspfwNdoWoVcn2qv8ywGUp7yc/sk2LpI6VziRyvWqbGNG1ZJqVVutRc46+sOE4VSeS2/CTNKNa6NMCf/hxxaUVsYfKdP+S1Lc4ianKp0sUugPpmtoydC0CP2RwjnHLcnzxCnvqxlLQWXMNPTsu2yBcHlWJLtcmdg/McLagy7l5kG6sN7ZxJLD/kAx8E6uqohP+K/jMSrYuQJnhr4tf4biWFY3Jzf/KpAYyVSq+pbfFKXMbL9nHEoZQT15Wyabd6DMAq3QZOthM5pUzdNqUXkcrI1PwjASAg4dVU/2o+98mTXnyhP7VlEkTnddpwyJF+YCCc01pqa6ZX99pnR+YOpIrb5DtPcKq0t5cFCDyQxN1lUuqZcYujvX/GC7+6IpRTz/NkEY/5cntOfZJyd6SkUx/JR5AJIRPCNeib0rcWnnFn0XK8s22x40wLjEtufXDO9+yraf4kHxlBI3SB0meMjepX50CJhAx7NekkRFnwoecLfqIyrjXrgAZsTMPiX94snjdrzisAXtBKanulilSxOfW2HSmfnk0L2GXHJJ3S+vCbgREml9dekfmHhmwEYtv3kfhth7ERIwVT8j69OtIBCmeTIJuA7o73PXc1LJ2whuZK7FZe6NTOs61MP7JVlIc6tbhtOBk3NXU8pBPOCY6Q55d63FtpUU/KCbQ0K2WQ9o5jNGwNNJ6Cw5FDCt+x5YJeP1d2QzDSiq+cSZqwqCZVcNoAftGGzgrRZ4vkpbP0xQZHCtWsUwHVTjrY4NfRDjHdVPRn8J9Xtooc/hIWkqzFaczYTlapu2RCJqe8aEo3jzWZCEJ7AiBzBYraYDgOfeiQyeJUsbbXHdGKiiw22Bdp4M+Yz671MZ0ie9EWRks0Q2DHGUTne9S4tAAJPGbUf4xtCMoJ40Q4QW05QLSZy3wNFAUFYmXE4ECDFB8+IEeNFFF/tgAnfh8GvFh/1xY+LE+ozMminjSRwhq09zQAEkNFyu0IKgvDkyOI+iccF7doWLTUasPxLH1xGPBSKkeWCnSoX/4C2c9du66BbRXamHqae+VCiS6BN953iYKOu8rMkneW+TFjV0CzAf8PNG9LBayUgY5Uw9x0Sap6zI4PpaZKH4d9ktkFU+91yBbN5SRtdd8/EQatJXmBNfw7kRrll+LjwZweWLEb0jT1RpGuDqHLdLTMMgowSczrp2zCsJdQH/seaYrpwkCFR8dRjM7JRUkVa1A0SvdZAX75vuBvvLBzN2c+Rbt5oqy93lqIBIjKb7w2UkRTb4pBWcNKNPUgt3az/PxQxEasaltdmuyvsXYbur3VPNn8JzN/6J5N+QCnz571TccapCmkPvFE+gayXU+UF1VKYyFcUvlev7lsQlmjqzK2QA8X7Q3TzFapqhvJKlt7dzBHraqZBgPgb9N4oKNayi8FZT71+kaYhIhFrESKYRHfHkj5n3kfhgLy+x+jLDbKxMggkgHnJz9RuEHZXBWtkYAQ==', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier')" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier')\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 2 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "3ed306e7faadc279", - "parentSpanId": "3049adb48476557c", - "name": "FilesystemMiddleware.wrap_tool_call", - "kind": 1, - "startTimeUnixNano": "1790968030836527104", - "endTimeUnixNano": "1790968030838146048", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_tool_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|tools:e52223df-38bd-4e1b-4faf-e72de38488d4" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "343bcf62767e113c", - "parentSpanId": "3ed306e7faadc279", - "name": "transfer_to_verifier", - "kind": 1, - "startTimeUnixNano": "1790968030837124096", - "endTimeUnixNano": "1790968030837764096", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "tool" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "transfer_to_verifier" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "execute_tool" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "gen_ai.tool.name", - "value": { - "stringValue": "transfer_to_verifier" - } - }, - { - "key": "gen_ai.tool.call.id", - "value": { - "stringValue": "toolu_01H6fV8JvRJNvXy47eRnd3jH" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|tools:e52223df-38bd-4e1b-4faf-e72de38488d4" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" - } - }, - { - "key": "langsmith.metadata.__handoff_destination", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "709919ff60557ac4", - "parentSpanId": "419c86d999598365", - "name": "model", - "kind": 1, - "startTimeUnixNano": "1790968023780810240", - "endTimeUnixNano": "1790968030834845952", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|model:41713ca4-d95b-3dfd-185e-53f884946d93" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJtZXNzYWdlcyI6W3siY29udGVudCI6IkZvciBhIHN5bnRoZXRpYyB0cmFjaW5nIGZpeHR1cmUsIGV4cGxhaW4gUHl0aG9uIHR1cGxlIHZlcnN1cyBsaXN0IGltbXV0YWJpbGl0eSBpbiBhdCBtb3N0IDEyMCB3b3Jkcy4gVXNlIG9ubHkgb2ZmaWNpYWwgUHl0aG9uIGRvY3VtZW50YXRpb24gaWYgeW91IHNlYXJjaC4gSGF2ZSB0aGUgc2tlcHRpYyBhbmQgdmVyaWZpZXIgY2hlY2sgaXQsIHRoZW4gaGF2ZSB0aGUgZWRpdG9yIHdyaXRlIC9hbnN3ZXIubWQuIEtlZXAgdGhlIHJ1biBzaG9ydCBhbmQgZG8gbm90IGFzayBmb2xsb3ctdXAgcXVlc3Rpb25zLiIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoiaHVtYW4iLCJpZCI6IjQ2MjA0MzA1LWY4ZWUtNDM4NC05Y2U4LWZjZDgwYmZjZGY3NSJ9LHsiY29udGVudCI6W3siaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9LCJuYW1lIjoid2ViX3NlYXJjaCIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHc5YVc5YnJlblBxZ3liZk53UCIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjoyODQ1LCJvdXRwdXRfdG9rZW5zIjo3Mywib3V0cHV0X3Rva2Vuc19kZXRhaWxzIjp7InRoaW5raW5nX3Rva2VucyI6MH0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoicmVzZWFyY2hlciIsImlkIjoibGNfcnVuLS0wMWEwZmUwMy0yMWEzLTcwMDAtYTM4MS0yODRhNmEwYzAzZjctMCIsInRvb2xfY2FsbHMiOlt7Im5hbWUiOiJ3ZWJfc2VhcmNoIiwiYXJncyI6eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9LCJpZCI6InRvb2x1XzAxQjJMZkhHRGpZU0ZKaG1pWE5qNEN1USIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6Mjg0NSwib3V0cHV0X3Rva2VucyI6NzMsInRvdGFsX3Rva2VucyI6MjkxOCwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19fSx7ImNvbnRlbnQiOiJbe1widGl0bGVcIjogXCI1LiBEYXRhIFN0cnVjdHVyZXMgXFx1MjAxNCBQeXRob24gMy4xNC41IGRvY3VtZW50YXRpb25cIiwgXCJ1cmxcIjogXCJodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3R1dG9yaWFsL2RhdGFzdHJ1Y3R1cmVzLmh0bWxcIiwgXCJoaWdobGlnaHRzXCI6IFtcIllvdSBtaWdodCBoYXZlIG5vdGljZWQgdGhhdCBtZXRob2RzIGxpa2VgaW5zZXJ0YCxgcmVtb3ZlYCBvcmBzb3J0YCB0aGF0IG9ubHkgbW9kaWZ5IHRoZSBsaXN0IGhhdmUgbm8gcmV0dXJuIHZhbHVlIHByaW50ZWQgXFx1MjAxMyB0aGV5IHJldHVybiB0aGUgZGVmYXVsdGBOb25lYC4gWzFdIFRoaXMgaXMgYSBkZXNpZ24gcHJpbmNpcGxlIGZvciBhbGwgbXV0YWJsZSBkYXRhIHN0cnVjdHVyZXMgaW4gUHl0aG9uLlxcbi4uLlxcbiMjIDUuMy4gVHVwbGVzIGFuZCBTZXF1ZW5jZXNcXHUwMGI2XFxuXFxuV2Ugc2F3IHRoYXQgbGlzdHMgYW5kIHN0cmluZ3MgaGF2ZSBtYW55IGNvbW1vbiBwcm9wZXJ0aWVzLCBzdWNoIGFzIGluZGV4aW5nIGFuZCBzbGljaW5nIG9wZXJhdGlvbnMuIFRoZXkgYXJlIHR3byBleGFtcGxlcyBvZiBzZXF1ZW5jZSBkYXRhIHR5cGVzIChzZWUgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBsaXN0LCB0dXBsZSwgcmFuZ2UpLiBTaW5jZSBQeXRob24gaXMgYW4gZXZvbHZpbmcgbGFuZ3VhZ2UsIG90aGVyIHNlcXVlbmNlIGRhdGEgdHlwZXMgbWF5IGJlIGFkZGVkLiBUaGVyZSBpcyBhbHNvIGFub3RoZXIgc3RhbmRhcmQgc2VxdWVuY2UgZGF0YSB0eXBlOiB0aGUgdHVwbGUuXFxuXFxuQSB0dXBsZSBjb25zaXN0cyBvZiBhIG51bWJlciBvZiB2YWx1ZXMgc2VwYXJhdGVkIGJ5IGNvbW1hcywgZm9yIGluc3RhbmNlOlxcbi4uLlxcbj4+PiAjIFR1cGxlcyBhcmUgaW1tdXRhYmxlOlxcbj4+PiB0WzBdID0gODg4ODhcXG5UcmFjZWJhY2sgKG1vc3QgcmVjZW50IGNhbGwgbGFzdCk6XFxuICBGaWxlIFxcXCI8c3RkaW4+XFxcIiwgbGluZSAxLCBpbiA8bW9kdWxlPlxcblR5cGVFcnJvcjogJ3R1cGxlJyBvYmplY3QgZG9lcyBub3Qgc3VwcG9ydCBpdGVtIGFzc2lnbm1lbnRcXG4+Pj4gIyBidXQgdGhleSBjYW4gY29udGFpbiBtdXRhYmxlIG9iamVjdHM6XFxuPj4+IHYgPSAoWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuPj4+IHZcXG4oWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuLi4uXFxuQXMgeW91IHNlZSwgb24gb3V0cHV0IHR1cGxlcyBhcmUgYWx3YXlzIGVuY2xvc2VkIGluIHBhcmVudGhlc2VzLCBzbyB0aGF0IG5lc3RlZCB0dXBsZXMgYXJlIGludGVycHJldGVkIGNvcnJlY3RseTsgdGhleSBtYXkgYmUgaW5wdXQgd2l0aCBvciB3aXRob3V0IHN1cnJvdW5kaW5nIHBhcmVudGhlc2VzLCBhbHRob3VnaCBvZnRlbiBwYXJlbnRoZXNlcyBhcmUgbmVjZXNzYXJ5IGFueXdheSAoaWYgdGhlIHR1cGxlIGlzIHBhcnQgb2YgYSBsYXJnZXIgZXhwcmVzc2lvbikuIEl0IGlzIG5vdCBwb3NzaWJsZSB0byBhc3NpZ24gdG8gdGhlIGluZGl2aWR1YWwgaXRlbXMgb2YgYSB0dXBsZSwgaG93ZXZlciBpdCBpcyBwb3NzaWJsZSB0byBjcmVhdGUgdHVwbGVzIHdoaWNoIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzLCBzdWNoIGFzIGxpc3RzLlxcblxcblRob3VnaCB0dXBsZXMgbWF5IHNlZW0gc2ltaWxhciB0byBsaXN0cywgdGhleSBhcmUgb2Z0ZW4gdXNlZCBpbiBkaWZmZXJlbnQgc2l0dWF0aW9ucyBhbmQgZm9yIGRpZmZlcmVudCBwdXJwb3Nlcy4gVHVwbGVzIGFyZSBpbW11dGFibGUsIGFuZCB1c3VhbGx5IGNvbnRhaW4gYSBoZXRlcm9nZW5lb3VzIHNlcXVlbmNlIG9mIGVsZW1lbnRzIHRoYXQgYXJlIGFjY2Vzc2VkIHZpYSB1bnBhY2tpbmcgKHNlZSBsYXRlciBpbiB0aGlzIHNlY3Rpb24pIG9yIGluZGV4aW5nIChvciBldmVuIGJ5IGF0dHJpYnV0ZSBpbiB0aGUgY2FzZSBvZiBuYW1lZHR1cGxlcykuIExpc3RzIGFyZSBtdXRhYmxlLCBhbmQgdGhlaXIgZWxlbWVudHMgYXJlIHVzdWFsbHkgaG9tb2dlbmVvdXMgYW5kIGFyZSBhY2Nlc3NlZCBieSBpdGVyYXRpbmcgb3ZlciB0aGUgbGlzdC5cXG4uLi5cXG5Bbm90aGVyIHVzZWZ1bCBkYXRhIHR5cGUgYnVpbHQgaW50byBQeXRob24gaXMgdGhlIGRpY3Rpb25hcnkgKHNlZSBNYXBwaW5nIFR5cGVzIFxcdTIwMTQgZGljdCkuIERpY3Rpb25hcmllcyBhcmUgc29tZXRpbWVzIGZvdW5kIGluIG90aGVyIGxhbmd1YWdlcyBhcyBcXHUyMDFjYXNzb2NpYXRpdmUgbWVtb3JpZXNcXHUyMDFkIG9yIFxcdTIwMWNhc3NvY2lhdGl2ZSBhcnJheXNcXHUyMDFkLiBVbmxpa2Ugc2VxdWVuY2VzLCB3aGljaCBhcmUgaW5kZXhlZCBieSBhIHJhbmdlIG9mIG51bWJlcnMsIGRpY3Rpb25hcmllcyBhcmUgaW5kZXhlZCBieSBrZXlzLCB3aGljaCBjYW4gYmUgYW55IGltbXV0YWJsZSB0eXBlOyBzdHJpbmdzIGFuZCBudW1iZXJzIGNhbiBhbHdheXMgYmUga2V5cy4gVHVwbGVzIGNhbiBiZSB1c2VkIGFzIGtleXMgaWYgdGhleSBjb250YWluIG9ubHkgc3RyaW5ncywgbnVtYmVycywgb3IgdHVwbGVzOyBpZiBhIHR1cGxlIGNvbnRhaW5zIGFueSBtdXRhYmxlIG9iamVjdCBlaXRoZXIgZGlyZWN0bHkgb3IgaW5kaXJlY3RseSwgaXQgY2Fubm90IGJlIHVzZWQgYXMgYSBrZXkuIFlvdSBjYW5cXHUyMDE5dCB1c2UgbGlzdHMgYXMga2V5cywgc2luY2UgbGlzdHMgY2FuIGJlIG1vZGlmaWVkIGluIHBsYWNlIHVzaW5nIGluZGV4IGFzc2lnbm1lbnRzLCBzbGljZSBhc3NpZ25tZW50cywgb3IgbWV0aG9kcyBsaWtlIGFwcGVuZCgpIGFuZCBleHRlbmQoKS5cIl19LCB7XCJ0aXRsZVwiOiBcIjMuIERhdGEgbW9kZWwgXFx1MjAxNCBQeXRob24gMy4xNC41IGRvY3VtZW50YXRpb25cIiwgXCJ1cmxcIjogXCJodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3JlZmVyZW5jZS9kYXRhbW9kZWwuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiVGhlIHZhbHVlIG9mIHNvbWUgb2JqZWN0cyBjYW4gY2hhbmdlLiBPYmplY3RzIHdob3NlIHZhbHVlIGNhbiBjaGFuZ2UgYXJlIHNhaWQgdG8gYmUgbXV0YWJsZTsgb2JqZWN0cyB3aG9zZSB2YWx1ZSBpcyB1bmNoYW5nZWFibGUgb25jZSB0aGV5IGFyZSBjcmVhdGVkIGFyZSBjYWxsZWQgaW1tdXRhYmxlLiAoVGhlIHZhbHVlIG9mIGFuIGltbXV0YWJsZSBjb250YWluZXIgb2JqZWN0IHRoYXQgY29udGFpbnMgYSByZWZlcmVuY2UgdG8gYSBtdXRhYmxlIG9iamVjdCBjYW4gY2hhbmdlIHdoZW4gdGhlIGxhdHRlclxcdTIwMTlzIHZhbHVlIGlzIGNoYW5nZWQ7IGhvd2V2ZXIgdGhlIGNvbnRhaW5lciBpcyBzdGlsbCBjb25zaWRlcmVkIGltbXV0YWJsZSwgYmVjYXVzZSB0aGUgY29sbGVjdGlvbiBvZiBvYmplY3RzIGl0IGNvbnRhaW5zIGNhbm5vdCBiZSBjaGFuZ2VkLiBTbywgaW1tdXRhYmlsaXR5IGlzIG5vdCBzdHJpY3RseSB0aGUgc2FtZSBhcyBoYXZpbmcgYW4gdW5jaGFuZ2VhYmxlIHZhbHVlLCBpdCBpcyBtb3JlIHN1YnRsZS4pIEFuIG9iamVjdFxcdTIwMTlzIG11dGFiaWxpdHkgaXMgZGV0ZXJtaW5lZCBieSBpdHMgdHlwZTsgZm9yIGluc3RhbmNlLCBudW1iZXJzLCBzdHJpbmdzIGFuZCB0dXBsZXMgYXJlIGltbXV0YWJsZSwgd2hpbGUgZGljdGlvbmFyaWVzIGFuZCBsaXN0cyBhcmUgbXV0YWJsZS5cXG4uLi5cXG5Tb21lIG9iamVjdHMgY29udGFpbiByZWZlcmVuY2VzIHRvIG90aGVyIG9iamVjdHM7IHRoZXNlIGFyZSBjYWxsZWQgY29udGFpbmVycy4gRXhhbXBsZXMgb2YgY29udGFpbmVycyBhcmUgdHVwbGVzLCBsaXN0cyBhbmQgZGljdGlvbmFyaWVzLiBUaGUgcmVmZXJlbmNlcyBhcmUgcGFydCBvZiBhIGNvbnRhaW5lclxcdTIwMTlzIHZhbHVlLiBJbiBtb3N0IGNhc2VzLCB3aGVuIHdlIHRhbGsgYWJvdXQgdGhlIHZhbHVlIG9mIGEgY29udGFpbmVyLCB3ZSBpbXBseSB0aGUgdmFsdWVzLCBub3QgdGhlIGlkZW50aXRpZXMgb2YgdGhlIGNvbnRhaW5lZCBvYmplY3RzOyBob3dldmVyLCB3aGVuIHdlIHRhbGsgYWJvdXQgdGhlIG11dGFiaWxpdHkgb2YgYSBjb250YWluZXIsIG9ubHkgdGhlIGlkZW50aXRpZXMgb2YgdGhlIGltbWVkaWF0ZWx5IGNvbnRhaW5lZCBvYmplY3RzIGFyZSBpbXBsaWVkLiBTbywgaWYgYW4gaW1tdXRhYmxlIGNvbnRhaW5lciAobGlrZSBhIHR1cGxlKSBjb250YWlucyBhIHJlZmVyZW5jZSB0byBhIG11dGFibGUgb2JqZWN0LCBpdHMgdmFsdWUgY2hhbmdlcyBpZiB0aGF0IG11dGFibGUgb2JqZWN0IGlzIGNoYW5nZWQuXFxuLi4uXFxuIyMjIDMuMi41LiBTZXF1ZW5jZXNcXHUwMGI2XFxuLi4uXFxuIyMjIyAzLjIuNS4xLiBJbW11dGFibGUgc2VxdWVuY2VzXFx1MDBiNlxcblxcbkFuIG9iamVjdCBvZiBhbiBpbW11dGFibGUgc2VxdWVuY2UgdHlwZSBjYW5ub3QgY2hhbmdlIG9uY2UgaXQgaXMgY3JlYXRlZC4gKElmIHRoZSBvYmplY3QgY29udGFpbnMgcmVmZXJlbmNlcyB0byBvdGhlciBvYmplY3RzLCB0aGVzZSBvdGhlciBvYmplY3RzIG1heSBiZSBtdXRhYmxlIGFuZCBtYXkgYmUgY2hhbmdlZDsgaG93ZXZlciwgdGhlIGNvbGxlY3Rpb24gb2Ygb2JqZWN0cyBkaXJlY3RseSByZWZlcmVuY2VkIGJ5IGFuIGltbXV0YWJsZSBvYmplY3QgY2Fubm90IGNoYW5nZS4pXFxuXFxuVGhlIGZvbGxvd2luZyB0eXBlcyBhcmUgaW1tdXRhYmxlIHNlcXVlbmNlczpcXG4uLi5cXG5UdXBsZXNcXG46IFRoZSBpdGVtcyBvZiBhIGB0dXBsZWAgYXJlIGFyYml0cmFyeSBQeXRob24gb2JqZWN0cy4gVHVwbGVzIG9mIHR3byBvciBtb3JlIGl0ZW1zIGFyZSBmb3JtZWQgYnkgY29tbWEtc2VwYXJhdGVkIGxpc3RzIG9mIGV4cHJlc3Npb25zLiBBIHR1cGxlIG9mIG9uZSBpdGVtIChhIFxcdTIwMThzaW5nbGV0b25cXHUyMDE5KSBjYW4gYmUgZm9ybWVkIGJ5IGFmZml4aW5nIGEgY29tbWEgdG8gYW4gZXhwcmVzc2lvbiAoYW4gZXhwcmVzc2lvbiBieSBpdHNlbGYgZG9lcyBub3QgY3JlYXRlIGEgdHVwbGUsIHNpbmNlIHBhcmVudGhlc2VzIG11c3QgYmUgdXNhYmxlIGZvciBncm91cGluZyBvZiBleHByZXNzaW9ucykuIEFuIGVtcHR5IHR1cGxlIGNhbiBiZSBmb3JtZWQgYnkgYW4gZW1wdHkgcGFpciBvZiBwYXJlbnRoZXNlcy5cXG4uLi5cXG4jIyMjIDMuMi41LjIuIE11dGFibGUgc2VxdWVuY2VzXFx1MDBiNlxcblxcbk11dGFibGUgc2VxdWVuY2VzIGNhbiBiZSBjaGFuZ2VkIGFmdGVyIHRoZXkgYXJlIGNyZWF0ZWQuIFRoZSBzdWJzY3JpcHRpb24gYW5kIHNsaWNpbmcgbm90YXRpb25zIGNhbiBiZSB1c2VkIGFzIHRoZSB0YXJnZXQgb2YgYXNzaWdubWVudCBhbmQgYGRlbGAgKGRlbGV0ZSkgc3RhdGVtZW50cy5cXG4uLi5cXG5UaGVyZSBhcmUgY3VycmVudGx5IHR3byBpbnRyaW5zaWMgbXV0YWJsZSBzZXF1ZW5jZSB0eXBlczpcXG5cXG5MaXN0c1xcbjogVGhlIGl0ZW1zIG9mIGEgbGlzdCBhcmUgYXJiaXRyYXJ5IFB5dGhvbiBvYmplY3RzLiBMaXN0cyBhcmUgZm9ybWVkIGJ5IHBsYWNpbmcgYSBjb21tYS1zZXBhcmF0ZWQgbGlzdCBvZiBleHByZXNzaW9ucyBpbiBzcXVhcmUgYnJhY2tldHMuIChOb3RlIHRoYXQgdGhlcmUgYXJlIG5vIHNwZWNpYWwgY2FzZXMgbmVlZGVkIHRvIGZvcm0gbGlzdHMgb2YgbGVuZ3RoIDAgb3IgMS4pXCJdfSwge1widGl0bGVcIjogXCJCdWlsdC1pbiBUeXBlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjcgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvYnVpbHRpbnMvc3RkdHlwZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiY29sbGVjdGlvbiBjbGFzc2VzIGFyZSBtdXRhYmxlLiBUaGUgbWV0aG9kcyB0aGF0IGFkZCwgc3VidHJhY3QsIG9yIHJlYXJyYW5nZSB0aGVpciAuLi4gaW4gcGxhY2UsIGFuZCBkb25cXHUyMDE5dCByZXR1cm4gYSAuLi4gLCBuZXZlciByZXR1cm4gdGhlIGNvbGxlY3Rpb24gaW5zdGFuY2UgaXRzZWxmIGJ1dCBgTm9uZWAuXFxuLi4uXFxuIyMgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBgbGlzdGAsIGB0dXBsZWAsIGByYW5nZWBcXHUwMGI2XFxuXFxuVGhlcmUgYXJlIHRocmVlIGJhc2ljIHNlcXVlbmNlIHR5cGVzOiBsaXN0cywgdHVwbGVzLCBhbmQgcmFuZ2Ugb2JqZWN0cy4gQWRkaXRpb25hbCBzZXF1ZW5jZSB0eXBlcyB0YWlsb3JlZCBmb3IgcHJvY2Vzc2luZyBvZiBiaW5hcnkgZGF0YSBhbmQgdGV4dCBzdHJpbmdzIGFyZSBkZXNjcmliZWQgaW4gZGVkaWNhdGVkIHNlY3Rpb25zLlxcbi4uLlxcblRoZSBvcGVyYXRpb25zIGluIHRoZSBmb2xsb3dpbmcgdGFibGUgLi4uIG11dGFibGUgYW5kIGltbXV0YWJsZS4gVGhlIGBjb2xsZWN0aW9ucy4gLi4uIGlzIHByb3ZpZGVkIHRvIG1ha2UgLi4uIGVhc2llciB0byBjb3JyZWN0bHkgaW1wbGVtZW50IHRoZXNlIG9wZXJhdGlvbnMgb24gY3VzdG9tIHNlcXVlbmNlIHR5cGVzXFxuLi4uXFxuIyMjIEltbXV0YWJsZSBTZXF1ZW5jZSBUeXBlc1xcdTAwYjZcXG4uLi5cXG5tdXRhYmxlIHNlcXVlbmNlIHR5cGVzIGlzXFxuLi4uXFxuc3VwcG9ydCBhbGxvd3MgaW1tdXRhYmxlIHNlcXVlbmNlcywgLi4uICwgdG8gYmUgdXNlZCBhcyBgZGljdGAga2V5cyBhbmQgc3RvcmVkIGluIC4uLiBlbnNldGAgaW5zdGFuY2VzXFxuLi4uXFxuIyMjIE11dGFibGUgU2VxdWVuY2UgVHlwZXNcXHUwMGI2XFxuLi4uXFxuIyMjIExpc3RzXFx1MDBiNlxcblxcbkxpc3RzIGFyZSBtdXRhYmxlIHNlcXVlbmNlcywgdHlwaWNhbGx5IHVzZWQgdG8gc3RvcmUgY29sbGVjdGlvbnMgb2YgaG9tb2dlbmVvdXMgaXRlbXMgKHdoZXJlIHRoZSBwcmVjaXNlIGRlZ3JlZSBvZiBzaW1pbGFyaXR5IHdpbGwgdmFyeSBieSBhcHBsaWNhdGlvbikuXFxuLi4uXFxuIyMjIFR1cGxlc1xcdTAwYjZcXG5cXG5UdXBsZXMgYXJlIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhldGVyb2dlbmVvdXMgZGF0YSAoc3VjaCBhcyB0aGUgMi10dXBsZXMgcHJvZHVjZWQgYnkgdGhlIGBlbnVtZXJhdGUoKWAgYnVpbHQtaW4pLiBUdXBsZXMgYXJlIGFsc28gdXNlZCBmb3IgY2FzZXMgd2hlcmUgYW4gaW1tdXRhYmxlIHNlcXVlbmNlIG9mIGhvbW9nZW5lb3VzIGRhdGEgaXMgbmVlZGVkIChzdWNoIGFzIGFsbG93aW5nIHN0b3JhZ2UgaW4gYSBgc2V0YCBvciBgZGljdGAgaW5zdGFuY2UpLlxcbi4uLlxcbnR1cGxlKGl0ZXJhYmxlPVxcbi4uLlxcblRoZSBjb25zdHJ1Y3RvciBidWlsZHMgYSB0dXBsZSB3aG9zZSBpdGVtcyBhcmUgdGhlIHNhbWUgYW5kIGluIHRoZSBzYW1lIG9yZGVyIGFzIGl0ZXJhYmxlXFx1MjAxOXMgaXRlbXMuIGl0ZXJhYmxlIG1heSBiZSBlaXRoZXIgYSBzZXF1ZW5jZSwgYSBjb250YWluZXIgdGhhdCBzdXBwb3J0cyBpdGVyYXRpb24sIG9yIGFuIGl0ZXJhdG9yIG9iamVjdC4gSWYgaXRlcmFibGUgaXMgYWxyZWFkeSBhIHR1cGxlLCBpdCBpcyByZXR1cm5lZCB1bmNoYW5nZWQuIEZvciBleGFtcGxlLCBgdHVwbGUoJ2FiYycpYCByZXR1cm5zIGAoJ2EnLCAnYicsICdjJylgIGFuZCBgdHVwbGUoIFsxLCAyLCAzXSApYCByZXR1cm5zIGAoMSwgMiwgMylgLiBJZiBubyBhcmd1bWVudCBpcyBnaXZlbiwgdGhlIGNvbnN0cnVjdG9yIGNyZWF0ZXMgYSBuZXcgZW1wdHkgdHVwbGUsIGAoKWAuXFxuLi4uXFxuVHVwbGVzIGltcGxlbWVudCBhbGwgb2YgdGhlIGNvbW1vbiBzZXF1ZW5jZSBvcGVyYXRpb25zLlxcbi4uLlxcbkZvciBoZXRlcm9nZW5lb3VzIGNvbGxlY3Rpb25zIG9mIGRhdGEgd2hlcmUgYWNjZXNzIGJ5IG5hbWUgaXMgY2xlYXJlciB0aGFuIGFjY2VzcyBieSBpbmRleCwgYGNvbGxlY3Rpb25zLm5hbWVkdHVwbGUoKWAgbWF5IGJlIGEgbW9yZSBhcHByb3ByaWF0ZSBjaG9pY2UgdGhhbiBhIHNpbXBsZSB0dXBsZSBvYmplY3QuXCJdfSwge1widGl0bGVcIjogXCJCdWlsdC1pbiBUeXBlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjUgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvbGlicmFyeS9zdGR0eXBlcy5odG1sXCIsIFwiaGlnaGxpZ2h0c1wiOiBbXCJTb21lIGNvbGxlY3Rpb24gY2xhc3NlcyBhcmUgbXV0YWJsZS4gVGhlIG1ldGhvZHMgdGhhdCBhZGQsIHN1YnRyYWN0LCBvciByZWFycmFuZ2UgdGhlaXIgLi4uIGluIHBsYWNlLCBhbmQgZG9uXFx1MjAxOXQgcmV0dXJuIGEgLi4uICwgbmV2ZXIgcmV0dXJuIHRoZSBjb2xsZWN0aW9uIGluc3RhbmNlIGl0c2VsZiBidXQgYE5vbmVgLlxcbi4uLlxcbiMjIFNlcXVlbmNlIFR5cGVzIFxcdTIwMTQgYGxpc3RgLCBgdHVwbGVgLCBgcmFuZ2VgXFx1MDBiNlxcblxcblRoZXJlIGFyZSB0aHJlZSBiYXNpYyBzZXF1ZW5jZSB0eXBlczogbGlzdHMsIHR1cGxlcywgYW5kIC4uLiBvYmplY3RzLiBBZGRpdGlvbmFsIHNlcXVlbmNlIHR5cGVzIHRhaWxvcmVkIGZvciBwcm9jZXNzaW5nIG9mIGJpbmFyeSBkYXRhIGFuZCB0ZXh0IHN0cmluZ3MgYXJlIGRlc2NyaWJlZCBpbiBkZWRpY2F0ZWQgc2VjdGlvbnMuXFxuLi4uXFxuVGhlIG9wZXJhdGlvbnMgaW4gdGhlIGZvbGxvd2luZyB0YWJsZSAuLi4gaW1tdXRhYmxlLiBUaGUgYCAuLi4gaXMgcHJvdmlkZWQgdG8gbWFrZSAuLi4gZWFzaWVyIHRvIGNvcnJlY3RseSBpbXBsZW1lbnQgdGhlc2Ugb3BlcmF0aW9ucyBvbiBjdXN0b20gc2VxdWVuY2UgdHlwZXNcXG4uLi5cXG4jIyMgSW1tdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbm9wZXJhdGlvbiB0aGF0IGltbXV0YWJsZSBzZXF1ZW5jZSAuLi4gYnkgbXV0YWJsZSBzZXF1ZW5jZSB0eXBlcyBpcyAuLi4gYGhhc2goKWBcXG4uLi5cXG5UaGlzIHN1cHBvcnQgYWxsb3dzIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHN1Y2ggYXMgYHR1cGxlYCBpbnN0YW5jZXMsIHRvIGJlIHVzZWQgYXMgYGRpY3RgIGtleXMgYW5kIHN0b3JlZCBpbiBgc2V0YCBhbmQgYGZyb3plbnNldGAgaW5zdGFuY2VzLlxcbi4uLlxcbiMjIyBNdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbiMjIyBMaXN0c1xcdTAwYjZcXG5cXG5MaXN0cyBhcmUgbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhvbW9nZW5lb3VzIGl0ZW1zICh3aGVyZSB0aGUgcHJlY2lzZSBkZWdyZWUgb2Ygc2ltaWxhcml0eSB3aWxsIHZhcnkgYnkgYXBwbGljYXRpb24pLlxcbi4uLlxcbiMjIyBUdXBsZXNcXHUwMGI2XFxuXFxuVHVwbGVzIGFyZSBpbW11dGFibGUgc2VxdWVuY2VzLCB0eXBpY2FsbHkgdXNlZCB0byBzdG9yZSBjb2xsZWN0aW9ucyBvZiBoZXRlcm9nZW5lb3VzIGRhdGEgKHN1Y2ggYXMgdGhlIDItdHVwbGVzIHByb2R1Y2VkIGJ5IHRoZSBgZW51bWVyYXRlKClgIGJ1aWx0LWluKS4gVHVwbGVzIGFyZSBhbHNvIHVzZWQgZm9yIGNhc2VzIHdoZXJlIGFuIGltbXV0YWJsZSBzZXF1ZW5jZSBvZiBob21vZ2VuZW91cyBkYXRhIGlzIG5lZWRlZCAoc3VjaCBhcyBhbGxvd2luZyBzdG9yYWdlIGluIGEgYHNldGAgb3IgYGRpY3RgIGluc3RhbmNlKS5cXG4uLi5cXG5UaGUgY29uc3RydWN0b3IgYnVpbGRzIGEgdHVwbGUgd2hvc2UgaXRlbXMgYXJlIHRoZSBzYW1lIGFuZCBpbiB0aGUgc2FtZSBvcmRlciBhcyBpdGVyYWJsZVxcdTIwMTlzIGl0ZW1zLiBpdGVyYWJsZSBtYXkgYmUgZWl0aGVyIGEgc2VxdWVuY2UsIGEgY29udGFpbmVyIHRoYXQgc3VwcG9ydHMgaXRlcmF0aW9uLCBvciBhbiBpdGVyYXRvciBvYmplY3QuIElmIGl0ZXJhYmxlIGlzIGFscmVhZHkgYSB0dXBsZSwgaXQgaXMgcmV0dXJuZWQgdW5jaGFuZ2VkLiBGb3IgZXhhbXBsZSwgYHR1cGxlKCdhYmMnKWAgcmV0dXJucyBgKCdhJywgJ2InLCAnYycpYCBhbmQgYHR1cGxlKCBbMSwgMiwgM10gKWAgcmV0dXJucyBgKDEsIDIsIDMpYC4gSWYgbm8gYXJndW1lbnQgaXMgZ2l2ZW4sIHRoZSBjb25zdHJ1Y3RvciBjcmVhdGVzIGEgbmV3IGVtcHR5IHR1cGxlLCBgKClgLlxcbi4uLlxcblR1cGxlcyBpbXBsZW1lbnQgYWxsIG9mIHRoZSBjb21tb24gc2VxdWVuY2Ugb3BlcmF0aW9ucy5cXG4uLi5cXG5Gb3IgaGV0ZXJvZ2VuZW91cyBjb2xsZWN0aW9ucyBvZiBkYXRhIHdoZXJlIGFjY2VzcyBieSBuYW1lIGlzIGNsZWFyZXIgdGhhbiBhY2Nlc3MgYnkgaW5kZXgsIGBjb2xsZWN0aW9ucy5uYW1lZHR1cGxlKClgIG1heSBiZSBhIG1vcmUgYXBwcm9wcmlhdGUgY2hvaWNlIHRoYW4gYSBzaW1wbGUgdHVwbGUgb2JqZWN0LlwiXX0sIHtcInRpdGxlXCI6IFwiNS4gRGF0YSBTdHJ1Y3R1cmVzIFxcdTIwMTQgUHl0aG9uIDMuMTAuMjAgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMuMTAvdHV0b3JpYWwvZGF0YXN0cnVjdHVyZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiWW91IG1pZ2h0IGhhdmUgbm90aWNlZCB0aGF0IG1ldGhvZHMgbGlrZSBgaW5zZXJ0YCwgYHJlbW92ZWAgb3IgYHNvcnRgIHRoYXQgb25seSBtb2RpZnkgdGhlIGxpc3QgaGF2ZSBubyByZXR1cm4gdmFsdWUgcHJpbnRlZCBcXHUyMDEzIHRoZXkgcmV0dXJuIHRoZSBkZWZhdWx0IGBOb25lYC4gMSBUaGlzIGlzIGEgZGVzaWduIHByaW5jaXBsZSBmb3IgYWxsIG11dGFibGUgZGF0YSBzdHJ1Y3R1cmVzIGluIFB5dGhvbi5cXG4uLi5cXG4jIyA1LjMuIFR1cGxlcyBhbmQgU2VxdWVuY2VzXFx1MDBiNlxcblxcbldlIHNhdyB0aGF0IGxpc3RzIGFuZCBzdHJpbmdzIGhhdmUgbWFueSBjb21tb24gcHJvcGVydGllcywgc3VjaCBhcyBpbmRleGluZyBhbmQgc2xpY2luZyBvcGVyYXRpb25zLiBUaGV5IGFyZSB0d28gZXhhbXBsZXMgb2Ygc2VxdWVuY2UgZGF0YSB0eXBlcyAoc2VlIFNlcXVlbmNlIFR5cGVzIFxcdTIwMTQgbGlzdCwgdHVwbGUsIHJhbmdlKS4gU2luY2UgUHl0aG9uIGlzIGFuIGV2b2x2aW5nIGxhbmd1YWdlLCBvdGhlciBzZXF1ZW5jZSBkYXRhIHR5cGVzIG1heSBiZSBhZGRlZC4gVGhlcmUgaXMgYWxzbyBhbm90aGVyIHN0YW5kYXJkIHNlcXVlbmNlIGRhdGEgdHlwZTogdGhlIHR1cGxlLlxcblxcbkEgdHVwbGUgY29uc2lzdHMgb2YgYSBudW1iZXIgb2YgdmFsdWVzIHNlcGFyYXRlZCBieSBjb21tYXMsIGZvciBpbnN0YW5jZTpcXG4uLi5cXG4+Pj4gIyBUdXBsZXMgYXJlIGltbXV0YWJsZTpcXG4uLi4gdFswXSA9IDg4ODg4XFxuVHJhY2ViYWNrIChtb3N0IHJlY2VudCBjYWxsIGxhc3QpOlxcbiAgRmlsZSBcXFwiPHN0ZGluPlxcXCIsIGxpbmUgMSwgaW4gPG1vZHVsZT5cXG5UeXBlRXJyb3I6ICd0dXBsZScgb2JqZWN0IGRvZXMgbm90IHN1cHBvcnQgaXRlbSBhc3NpZ25tZW50XFxuPj4+ICMgYnV0IHRoZXkgY2FuIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzOlxcbi4uLiB2ID0gKFsxLCAyLCAzXSwgWzMsIDIsIDFdKVxcbj4+PiB2XFxuKFsxLCAyLCAzXSwgWzMsIDIsIDFdKVxcbi4uLlxcbkFzIHlvdSBzZWUsIG9uIG91dHB1dCB0dXBsZXMgYXJlIGFsd2F5cyBlbmNsb3NlZCBpbiBwYXJlbnRoZXNlcywgc28gdGhhdCBuZXN0ZWQgdHVwbGVzIGFyZSBpbnRlcnByZXRlZCBjb3JyZWN0bHk7IHRoZXkgbWF5IGJlIGlucHV0IHdpdGggb3Igd2l0aG91dCBzdXJyb3VuZGluZyBwYXJlbnRoZXNlcywgYWx0aG91Z2ggb2Z0ZW4gcGFyZW50aGVzZXMgYXJlIG5lY2Vzc2FyeSBhbnl3YXkgKGlmIHRoZSB0dXBsZSBpcyBwYXJ0IG9mIGEgbGFyZ2VyIGV4cHJlc3Npb24pLiBJdCBpcyBub3QgcG9zc2libGUgdG8gYXNzaWduIHRvIHRoZSBpbmRpdmlkdWFsIGl0ZW1zIG9mIGEgdHVwbGUsIGhvd2V2ZXIgaXQgaXMgcG9zc2libGUgdG8gY3JlYXRlIHR1cGxlcyB3aGljaCBjb250YWluIG11dGFibGUgb2JqZWN0cywgc3VjaCBhcyBsaXN0cy5cXG5cXG5UaG91Z2ggdHVwbGVzIG1heSBzZWVtIHNpbWlsYXIgdG8gbGlzdHMsIHRoZXkgYXJlIG9mdGVuIHVzZWQgaW4gZGlmZmVyZW50IHNpdHVhdGlvbnMgYW5kIGZvciBkaWZmZXJlbnQgcHVycG9zZXMuIFR1cGxlcyBhcmUgaW1tdXRhYmxlLCBhbmQgdXN1YWxseSBjb250YWluIGEgaGV0ZXJvZ2VuZW91cyBzZXF1ZW5jZSBvZiBlbGVtZW50cyB0aGF0IGFyZSBhY2Nlc3NlZCB2aWEgdW5wYWNraW5nIChzZWUgbGF0ZXIgaW4gdGhpcyBzZWN0aW9uKSBvciBpbmRleGluZyAob3IgZXZlbiBieSBhdHRyaWJ1dGUgaW4gdGhlIGNhc2Ugb2YgYG5hbWVkdHVwbGVzYCkuIExpc3RzIGFyZSBtdXRhYmxlLCBhbmQgdGhlaXIgZWxlbWVudHMgYXJlIHVzdWFsbHkgaG9tb2dlbmVvdXMgYW5kIGFyZSBhY2Nlc3NlZCBieSBpdGVyYXRpbmcgb3ZlciB0aGUgbGlzdC5cXG4uLi5cXG4jIyA1LjQuXFxuLi4uXFxuLiBTZXQgb2JqZWN0c1xcbi4uLlxcbiMjIDUuNS4gRGljdGlvbmFyaWVzXFx1MDBiNlxcblxcbkFub3RoZXIgdXNlZnVsIGRhdGEgdHlwZSBidWlsdCBpbnRvIFB5dGhvbiBpcyB0aGUgZGljdGlvbmFyeSAoc2VlIE1hcHBpbmcgVHlwZXMgXFx1MjAxNCBkaWN0KS4gRGljdGlvbmFyaWVzIGFyZSBzb21ldGltZXMgZm91bmQgaW4gb3RoZXIgbGFuZ3VhZ2VzIGFzIFxcdTIwMWNhc3NvY2lhdGl2ZSBtZW1vcmllc1xcdTIwMWQgb3IgXFx1MjAxY2Fzc29jaWF0aXZlIGFycmF5c1xcdTIwMWQuIFVubGlrZSBzZXF1ZW5jZXMsIHdoaWNoIGFyZSBpbmRleGVkIGJ5IGEgcmFuZ2Ugb2YgbnVtYmVycywgZGljdGlvbmFyaWVzIGFyZSBpbmRleGVkIGJ5IGtleXMsIHdoaWNoIGNhbiBiZSBhbnkgaW1tdXRhYmxlIHR5cGU7IHN0cmluZ3MgYW5kIG51bWJlcnMgY2FuIGFsd2F5cyBiZSBrZXlzLiBUdXBsZXMgY2FuIGJlIHVzZWQgYXMga2V5cyBpZiB0aGV5IGNvbnRhaW4gb25seSBzdHJpbmdzLCBudW1iZXJzLCBvciB0dXBsZXM7IGlmIGEgdHVwbGUgY29udGFpbnMgYW55IG11dGFibGUgb2JqZWN0IGVpdGhlciBkaXJlY3RseSBvciBpbmRpcmVjdGx5LCBpdCBjYW5ub3QgYmUgdXNlZCBhcyBhIGtleS4gWW91IGNhblxcdTIwMTl0IHVzZSBsaXN0cyBhcyBrZXlzLCBzaW5jZSBsaXN0cyBjYW4gYmUgbW9kaWZpZWQgaW4gcGxhY2UgdXNpbmcgaW5kZXggYXNzaWdubWVudHMsIHNsaWNlIGFzc2lnbm1lbnRzLCBvciBtZXRob2RzIGxpa2UgYGFwcGVuZCgpYCBhbmQgYGV4dGVuZCgpYC5cIl19XSIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ3ZWJfc2VhcmNoIiwiaWQiOiI2ZTUxMjVhYy0zMTY0LTRhNzYtOWM1Mi1hYzM0NjBjZTM2ZTQiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJzdGF0dXMiOiJzdWNjZXNzIn0seyJjb250ZW50IjpbeyJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX3NrZXB0aWMiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QTZGNGNDTjV5aEQ0Q3JzOU0iLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjB9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlc2VhcmNoZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtM2NkOC03OWYxLTg4YTEtY2U2Y2VlMjk0ZTc5LTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fc2tlcHRpYyIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsInRvdGFsX3Rva2VucyI6NzQxMSwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19fSx7ImNvbnRlbnQiOiJTdWNjZXNzZnVsbHkgdHJhbnNmZXJyZWQgdG8gc2tlcHRpYyIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ0cmFuc2Zlcl90b19za2VwdGljIiwiaWQiOiIzODkwNThkMS0wODNmLTQ2MzItYmJjNS0wOWJmZDNhMGZmZDIiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMVhqajNhUmRXeWhCSmZQbVRKQnhRYTkiLCJzdGF0dXMiOiJzdWNjZXNzIn1dfQ==" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "87fbd88889f37ec8", - "parentSpanId": "709919ff60557ac4", - "name": "FilesystemMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968023781179904", - "endTimeUnixNano": "1790968030834503936", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|model:41713ca4-d95b-3dfd-185e-53f884946d93" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJvdXRwdXQiOnsicmVzdWx0IjpbeyJjb250ZW50IjpbeyJzaWduYXR1cmUiOiJDQVFTMVFnS0VBZ1NHQUk0QVVJSWRHaHBibXRwYm1jU0RONlRmVTZORE05NzFsRWJ6eG9NdlJVQTFKOW94M2ZKUVlUOUlqQXJDUVFHSEJQNHBSSFBhdlh6UmxiTWJhWUhDNTdZaitHYnhncjBoZWx2ZDJPSUwvbzZSYnQ0UEZBM0ZhSUZVbGdxOGdjN0tRSTlGdEdudlNBa0xCUnpJc1VwLzJkNVJkMnpnRXNma0ZWZVhzbjhXWVlaa2luQVFWVnk2QTdCM0xhRUpXMHhiL3g4OERpNjdmZWR3eDBRK0ZsWnR3Y21UM0RjYWExMUp2ZXlIUnIzZG0rekdTWlA2Q1hlWE5KOG5yVFo3VzFZUlR5c0Q2dzdvN0xwOGgxUndxNGY0bzhqK1FVZlkwdmplK3pKWnN4SFBtUU50M3lrZUtoOTloZ242ZGJpejYvRUhxbWJIalNBdTFNNFNxRURmcUlLVGhIWWVuYW1BWm1jUTRYQU9vNm1kUTYrNzdWZ3BWMWxDMS9rNTJJaVVvSmprR2xRcm5MQ3Z1dGlJN0tOK3NnSzhjMisyS0NKclBSQ3ZWVitCa1N0dlA1aldXcXp5dHBLUStuSHpoTDQ0OE9ySUE5Z2RKQzM5QzhlRHJYZVJuSTd0NEZxbGtYR29NbFpBVjlVTWNyUUhSeE9NaTh0T3lUemk5b3lCRkRUU3NRK0xKcWVyMHR6MUZ0OWdlazZ2emc1MFNwVkFGUWRMRVJ2OFIxWXFNYWVJK3hzdlRBRVc5TVJndlJNa3pMdXpSVDJndXczakQrRmppcDM3eGdLNVFJMFIrQ3NPQW1RUG9UWml6emNJeUFVQXVDSkZDZ3EvZ0QvQ2liTHhveW1pVlVJMWFuOVNudDNLcE5Sb1dkdldJbmUzM1YwcHY4UEhnOXlXMkp1TE9xUUdpbExDc0svUTNvUXIzdXBFTVh4WEdqQ0w3V1VpenZSWkdGRUVWK1ZwbFl0N3Y0dEtaTWo1cGszdmRlTTBNSjVYWmc3UHZVc1J6eWN4Y25yVDNLbm9jM3FNK3R0cVpmVHNiOGQ2VS9wUWlmcTdHdWFoRk9IcnZyb3FnSkxqKy84MVl5MXBaRmtqZkpnWTBYa2x6QW5BNkNGcS9ZVDBneGJWK1RINUlTK1dhWU9VekszNlM4czVxcU13aG5ndjRJekUzY3RYWHFuaElaWE56bnlWQnFiWWEvR3gyYkNqY0VqMm41UnlHWVJTLytNY3VsZ0xCem5ROU1rRzJEN1FQM01xL253SFhLTUlhTFM4Vks4aEczZDByQWpsdm5hdVhTaE5ySnh0a2o0cWt3bnhENExyRWprMXVlK1BMY2JMcVlXd0FyOG4wcys0MWpyc0lQVnl5Szl2RmFFWnJBOUthQnhrSnlpcXg1MEdaTm43Y2t4K21rSTE4Z0g1Mml5VlB0VThGS01YanVnQ2w2bVBMaUhZaURRZCtHNjNMdWRtT0t5czlpdFZuQkRCTk1QMmIvSTcrYklWUmxoZUdhWldyNk1BVEtsODZCM3krMGt1T3JMUk15V2NkaWJjMmlRa1ptKzhmN2RUVXdiS2JCSnNLT0ZZNzMvOG5sTC9KaVlwano2blVJaytJcVNqYUZ5SzZYRmxDY3VrV3BXSHBESm5TdmJFemV5N3FIeUNxSitJK29uOGlQOEdPdGVtcFFhUzAvNGtaR1N3bHJFNnhPajZFd0dwZmpiRFpLSGtQLzJSQWROWVBRcTN6N2JkVkpNSk5uRk16NmUzN216TXBDQmlod1BkU0ZUUkUzU0NZNjZ3dlRnSnpHQ1V5aEhiU2k1aTFhenpPWGQ4dUhDU3BULzZMMW82VlUwcGpvUjhLYWE0d0NXSEdmN1AvV0VkK2F2eXAwMkpudTFjbXBXMCtHcSt2SzloMHRkYjJJQ2xNL2VOZmRvdVFQK2VwOE1KVWpyYURSSUNtQUpRWTVvYlM3MXZuaU9vK3JlYUZ5MHpSZ0IiLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsic2lnbmF0dXJlIjoiQ0FRUy9SRUtFUWdTR0FJNEFVSUpibUZ5Y21GMGFXOXVFZ3dGaDNBVkpaUDNzOHkxSHEwYURHNzZ1aEhPTmFTY1hBR1NoaUl3R2dqTFhIVXgxeVpya0xQbGpqelRPUXljcExKaUtWd1hjeG0vRXpLSm0xczhNNVd4dVJFV0VsZFhjb2FOMC9tc0twa1JNVCtlTGI1aWg5ckFIVUxUb21VTnNVd0pldTBqckplNEdMYXp5N3NQNUt0akVPRUJLUXNYVWZvUTdmRGtaT1FVSFppOXp6UU40aEZObVlKVWYzT1ZxZjlUUU5kQzErbS8vSEFaUGZXbUF5Nkh0RHZtN2tnQkprQ0VvaUZubTd0bi9QWDFoWEdQUmdXYzZCVFhVTXIyV0E4YUt5cWdnUlViTUgyK0pZdjVpV1pkZENjMXVwMU5icjNzRjdXUGNvdDlaQmh5SFFYcjY5MnplSms2U0pneWdJVnJBU2JNbHkyYkJ4VFdKQjYyM2dWZ3pwQ21WU0xaRnBrS1hnUGNwOGhHeURLT3ZGNlNpUVNIcUdSeFFvZnI3VnMxYVBoZlppeFJPSkdEK01scmtnZ1ZBbkdNeVlJRFVacGF2dENlaVUxSm1CU3owMDg0YlhQdFQvdG5wc0tPblNQWVpRbzNCMEJYS2JxQS9Xc0tuZzgvVjNaOFV1YWpvNklWWjJoZ0ExV0RkdXFRT1FrRXhHVTZwRnVMaGViSWp1V3hTTkkvRGZmdlIvL0xOcUNmdmRuZjBodm9QdER4ZngvU2F3SXg0L3NwcTl4YndGekh0TGdvSGcxRjJ3Rnc3Y2xQRGxnMVB5RC92MnlKRzNWOVQ4R0w2akdQRTZyaGZpbC91NEhOdmY3QlcwZFF6Q1RUWGNxWnk0bkJ5eTArcCtTN1p4Zk1sNEtweGEyZ09oaFNOamZwZnVYMFFwTDRrTUU4SjFubGlGTjFkOEtxRVB1REkxOEJRSFVoRC9VZlkyOW9BMHg1MTBGak0vQnNMWjRuNXNwcGtvSWk3Q0ZvUXEyYUFLVk5mQzFLaWxoSXBSRCsxZHlEdFpRa2xOOGdacE9FU0h3Nk1MMVR0VTB5ZkFjYm1xb3hKNmhoanp3SDZDTXNUUUVFeThNYlJCTStRS0trSVJkUkNQSEdGVzJMa3VSNTArSjBwRi90cjZwcVZ2SmVvemZpTW5yRWlsQjI3VFpQNG5LVEpHOHJkLy92Q1dlbjB5N0NBLzhkQko5Z2RwNXR4N05WQTQ1azFnZGN4RVIxZ1lvdU5YM24xdkczL0IxRjQrOTN3WFc5TXFvNlVzNTlUUW1yYjlOcWE3cFNRTlNySDA2dzFHeHlCQWxrRmZxQWxhZmsxNmFNcHE0MTZUSllwR3k0M1dDVWlDY0xXbGhpV2d6MnNnT0xBWFA5YTV3ZVdBS1JDOEo2amtjVWtEZVhuVytIRlNpUE02KzlCbzZrVmhMVWhONXJjNG1IWk9acEY3cHRQcHNRTjRYQ3FMUHNxcFJILzhvNVhweUM2Wm5lVGVGMkV4dGpod1pWalhEd01iSXpWWUlidzF5MlBQR3c4ZEM3cGM0c0lWU25JNG9RQUgwdjY1MGdoZmhtTWV2V1c0aDRQeWxidy9ERzRmZGVUMys4ejBmOE1PU1R0ZmlweDA1L1F0dEhsQXZPRFJ4YTV5REN2T3o2bjNmMUJPME4vNE1iR3lPTTI3cVc0eDhtQlZvcnlVWldmc21oZmkwL0dmTnZCOCt5bFRHYllOWDI3T2NFRjVXWnROcWJXRXk3VjVHYm1aVVN4c3BjZzdGQlozajMvM0w3bXV2WlhvWmkxZjVlcnE0eTNsU0grb0Y3cVBGbnZpZXlMT0N3dWJjUXkrb3lvd2o0Y0QwaWRSZWNucCtzKzUyRDcrbXpGMWdwVytmK2NKYXNveGlnYnhrT2xvUzR5ZWlLdmdNNG5XU3BHRWoxMlJQeDVvODBFbXppWE45dDR6SnpXMWh0QTVoWEpKZUZ5bXBNWXR5Q1VDZXZSV1ZtclJZa3RRN1VuQ2E2dEwvQVZQaTFuaTVYQ1hIZkxPdXFmSzVLTFl4andWdGRoaGZtQ0x2cGFLVk5DRU9DZjRuTkdIcUQ5OHdVYjBlaldOd0RZQm5KR2tCUnc5UlZzcGZ3TmRvV29WY24ycXY4eXdHVXA3eWMvc2syTHBJNlZ6aVJ5dldxYkdORzFaSnFWVnV0UmM0NitzT0U0VlNlUzIvQ1ROS05hNk5NQ2YvaHh4YVVWc1lmS2RQK1MxTGM0aWFuS3Awc1V1Z1BwbXRveWRDMENQMlJ3am5ITGNuenhDbnZxeGxMUVdYTU5QVHN1MnlCY0hsV0pMdGNtZGcvTWNMYWd5N2w1a0c2c043WnhKTEQva0F4OEU2dXFvaFArSy9qTVNyWXVRSm5ocjR0ZjRiaVdGWTNKemYvS3BBWXlWU3ErcGJmRktYTWJMOW5IRW9aUVQxNVd5YWJkNkRNQXEzUVpPdGhNNXBVemROcVVYa2NySTFQd2pBU0FnNGRWVS8ybys5OG1UWG55aFA3VmxFa1RuZGRwd3lKRitZQ0NjMDFwcWE2Wlg5OXBuUitZT3BJcmI1RHRQY0txMHQ1Y0ZDRHlReE4xbFV1cVpjWXVqdlgvR0M3KzZJcFJUei9Oa0VZLzVjbnRPZlpKeWQ2U2tVeC9KUjVBSklSUENOZWliMHJjV25uRm4wWEs4czIyeDQwd0xqRXR1ZlhETzkreXJhZjRrSHhsQkkzU0IwbWVNamVwWDUwQ0poQXg3TmVra1JGbndvZWNMZnFJeXJqWHJnQVpzVE1QaVg5NHNuamRyemlzQVh0QkthbnVsaWxTeE9mVzJIU21mbmswTDJHWEhKSjNTK3ZDYmdSRW1sOWRla2ZtSGhtd0VZdHYza2ZodGg3RVJJd1ZUOGo2OU90SUJDbWVUSUp1QTdvNzNQWGMxTEoyd2h1Wks3RlplNk5UT3M2MU1QN0pWbEljNnRiaHRPQmszTlhVOHBCUE9DWTZRNTVkNjNGdHBVVS9LQ2JRMEsyV1E5bzVqTkd3Tk5KNkN3NUZEQ3QreDVZSmVQMWQyUXpEU2lxK2NTWnF3cUNaVmNOb0FmdEdHemdyUlo0dmtwYlAweFFaSEN0V3NVd0hWVGpyWTROZlJEakhkVlBSbjhKOVh0b29jL2hJV2txekZhY3pZVGxhcHUyUkNKcWU4YUVvM2p6V1pDRUo3QWlCekJZcmFZRGdPZmVpUXllSlVzYmJYSGRHS2lpdzIyQmRwNE0rWXo2NzFNWjBpZTlFV1JrczBRMkRIR1VUbmU5UzR0QUFKUEdiVWY0eHRDTW9KNDBRNFFXMDVRTFNaeTN3TkZBVUZZbVhFNEVDREZCOCtJRWVORkZGL3RnQW5maDhHdkZoLzF4WStMRStvek1taW5qU1J3aHEwOXpRQUVrTkZ5dTBJS2d2RGt5T0kraWNjRjdkb1dMVFVhc1B4TEgxeEdQQlNLa2VXQ25Tb1gvNEMyYzlkdTY2QmJSWGFtSHFhZStWQ2lTNkJOOTUzaVlLT3U4ck1rbmVXK1RGalYwQ3pBZjhQTkc5TEJheVVnWTVVdzl4MFNhcDZ6STRQcGFaS0g0ZDlrdGtGVSs5MXlCYk41U1J0ZGQ4L0VRYXRKWG1CTmZ3N2tScmxsK0xqd1p3ZVdMRWIwalQxUnBHdURxSExkTFRNTWdvd1NjenJwMnpDc0pkUUgvc2VhWXJwd2tDRlI4ZFJqTTdKUlVrVmExQTBTdmRaQVg3NXZ1QnZ2TEJ6TjJjK1JidDVvcXk5M2xxSUJJaktiN3cyVWtSVGI0cEJXY05LTlBVZ3QzYXovUHhReEVhc2FsdGRtdXl2c1hZYnVyM1ZQTm44SnpOLzZKNU4rUUNuejU3MVRjY2FwQ21rUHZGRStnYXlYVStVRjFWS1l5RmNVdmxldjdsc1FsbWpxeksyUUE4WDdRM1R6RmFwcWh2SktsdDdkekJIcmFxWkJnUGdiOU40b0tOYXlpOEZaVDcxK2thWWhJaEZyRVNLWVJIZkhrajVuM2tmaGdMeSt4K2pMRGJLeE1nZ2tnSG5KejlSdUVIWlhCV3RrWUFRPT0iLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsiaWQiOiJ0b29sdV8wMUg2ZlY4SnZSSk52WHk0N2VSbmQzakgiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6e30sIm5hbWUiOiJ0cmFuc2Zlcl90b192ZXJpZmllciIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHdBTVJkUzIxRmVKZnpRaE0zcyIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjo3Mzk2LCJvdXRwdXRfdG9rZW5zIjo3NzAsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjczOX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoic2tlcHRpYyIsImlkIjoibGNfcnVuLS0wMWEwZmUwMy00YWU5LTc2YzAtODlhNi00ZjBiMTE0ZTMwMzAtMCIsInRvb2xfY2FsbHMiOlt7Im5hbWUiOiJ0cmFuc2Zlcl90b192ZXJpZmllciIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxSDZmVjhKdlJKTnZYeTQ3ZVJuZDNqSCIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzM5Niwib3V0cHV0X3Rva2VucyI6NzcwLCJ0b3RhbF90b2tlbnMiOjgxNjYsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjczOX19fV0sInN0cnVjdHVyZWRfcmVzcG9uc2UiOm51bGx9fQ==" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "381fc39d7d99fceb", - "parentSpanId": "87fbd88889f37ec8", - "name": "UnsupportedContentMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968023781553152", - "endTimeUnixNano": "1790968030834259968", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "UnsupportedContentMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|model:41713ca4-d95b-3dfd-185e-53f884946d93" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "f2bbd85b9e41b171", - "parentSpanId": "381fc39d7d99fceb", - "name": "ChatAnthropic", - "kind": 1, - "startTimeUnixNano": "1790968023785360128", - "endTimeUnixNano": "1790968030833796864", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chat" - } - }, - { - "key": "gen_ai.serialized.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "llm" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "gen_ai.request.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "gen_ai.tool.definitions", - "value": { - "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"transfer_to_researcher\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Ask the researcher to address a concrete gap\"},{\"name\":\"transfer_to_verifier\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send critique for independent verification\"},{\"name\":\"transfer_to_red_team\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send checked claims for adversarial review\"}]" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_chat_model" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|model:41713ca4-d95b-3dfd-185e-53f884946d93" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" - } - }, - { - "key": "langsmith.metadata.ls_provider", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "langsmith.metadata.ls_model_name", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.ls_model_type", - "value": { - "stringValue": "chat" - } - }, - { - "key": "langsmith.metadata.ls_max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.lc_versions", - "value": { - "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.model_kwargs", - "value": { - "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" - } - }, - { - "key": "langsmith.metadata.streaming", - "value": { - "boolValue": false - } - }, - { - "key": "langsmith.metadata.max_retries", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata._type", - "value": { - "stringValue": "anthropic-chat" - } - }, - { - "key": "langsmith.metadata.usage_metadata", - "value": { - "stringValue": "{\"input_tokens\":7396,\"output_tokens\":770,\"total_tokens\":8166,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":739}}" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.usage.input_tokens", - "value": { - "intValue": "7396" - } - }, - { - "key": "gen_ai.usage.output_tokens", - "value": { - "intValue": "770" - } - }, - { - "key": "gen_ai.usage.total_tokens", - "value": { - "intValue": "8166" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "419c86d999598365", - "parentSpanId": "0ff4846461350af9", - "name": "skeptic", - "kind": 1, - "startTimeUnixNano": "1790968023780292096", - "endTimeUnixNano": "1790968030843193088", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:skeptic\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"skeptic\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - } - ], - "events": [ - { - "timeUnixNano": "1790968030909441000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "ParentCommand(Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier')" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: ParentCommand(Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier')\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "0ff4846461350af9", - "parentSpanId": "04ffc0db9ce0f358", - "name": "skeptic", - "kind": 1, - "startTimeUnixNano": "1790968023779922944", - "endTimeUnixNano": "1790968030845179136", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langgraph" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "skeptic" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:skeptic\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"skeptic\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:2" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - } - ], - "events": [ - { - "timeUnixNano": "1790968030909679000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "ParentCommand(Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': 'CAQS1QgKEAgSGAI4AUIIdGhpbmtpbmcSDN6TfU6NDM971lEbzxoMvRUA1J9ox3fJQYT9IjArCQQGHBP4pRHPavXzRlbMbaYHC57Yj+Gbxgr0helvd2OIL/o6Rbt4PFA3FaIFUlgq8gc7KQI9FtGnvSAkLBRzIsUp/2d5Rd2zgEsfkFVeXsn8WYYZkinAQVVy6A7B3LaEJW0xb/x88Di67fedwx0Q+FlZtwcmT3Dcaa11JveyHRr3dm+zGSZP6CXeXNJ8nrTZ7W1YRTysD6w7o7Lp8h1Rwq4f4o8j+QUfY0vje+zJZsxHPmQNt3ykeKh99hgn6dbiz6/EHqmbHjSAu1M4SqEDfqIKThHYenamAZmcQ4XAOo6mdQ6+77VgpV1lC1/k52IiUoJjkGlQrnLCvutiI7KN+sgK8c2+2KCJrPRCvVV+BkStvP5jWWqzytpKQ+nHzhL448OrIA9gdJC39C8eDrXeRnI7t4FqlkXGoMlZAV9UMcrQHRxOMi8tOyTzi9oyBFDTSsQ+LJqer0tz1Ft9gek6vzg50SpVAFQdLERv8R1YqMaeI+xsvTAEW9MRgvRMkzLuzRT2guw3jD+Fjip37xgK5QI0R+CsOAmQPoTZizzcIyAUAuCJFCgq/gD/CibLxoymiVUI1an9Snt3KpNRoWdvWIne33V0pv8PHg9yW2JuLOqQGilLCsK/Q3oQr3upEMXxXGjCL7WUizvRZGFEEV+VplYt7v4tKZMj5pk3vdeM0MJ5XZg7PvUsRzycxcnrT3Knoc3qM+ttqZfTsb8d6U/pQifq7GuahFOHrvroqgJLj+/81Yy1pZFkjfJgY0XklzAnA6CFq/YT0gxbV+TH5IS+WaYOUzK36S8s5qqMwhngv4IzE3ctXXqnhIZXNznyVBqbYa/Gx2bCjcEj2n5RyGYRS/+MculgLBznQ9MkG2D7QP3Mq/nwHXKMIaLS8VK8hG3d0rAjlvnauXShNrJxtkj4qkwnxD4LrEjk1ue+PLcbLqYWwAr8n0s+41jrsIPVyyK9vFaEZrA9KaBxkJyiqx50GZNn7ckx+mkI18gH52iyVPtU8FKMXjugCl6mPLiHYiDQd+G63LudmOKys9itVnBDBNMP2b/I7+bIVRlheGaZWr6MATKl86B3y+0kuOrLRMyWcdibc2iQkZm+8f7dTUwbKbBJsKOFY73/8nlL/JiYpjz6nUIk+IqSjaFyK6XFlCcukWpWHpDJnSvbEzey7qHyCqJ+I+on8iP8GOtempQaS0/4kZGSwlrE6xOj6EwGpfjbDZKHkP/2RAdNYPQq3z7bdVJMJNnFMz6e37mzMpCBihwPdSFTRE3SCY66wvTgJzGCUyhHbSi5i1azzOXd8uHCSpT/6L1o6VU0pjoR8Kaa4wCWHGf7P/WEd+avyp02Jnu1cmpW0+Gq+vK9h0tdb2IClM/eNfdouQP+ep8MJUjraDRICmAJQY5obS71vniOo+reaFy0zRgB', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier')" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: ParentCommand(Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier')\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "8e84b2f5d3c9d733", - "parentSpanId": "4862a8dc9e239ae2", - "name": "tools", - "kind": 1, - "startTimeUnixNano": "1790968032471715072", - "endTimeUnixNano": "1790968032476058880", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|tools:74348550-0598-498b-1732-6675e778549b" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:2" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJpbnB1dCI6W3sibmFtZSI6InRyYW5zZmVyX3RvX3JlZF90ZWFtIiwiYXJncyI6e30sImlkIjoidG9vbHVfMDFYRUF1aFFIQ0JkeUN3dHltWndGZkRpIiwidHlwZSI6InRvb2xfY2FsbCJ9XX0=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - } - ], - "events": [ - { - "timeUnixNano": "1790968032542335000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': 'CAQS9gUKEAgSGAI4AUIIdGhpbmtpbmcSDGFyJ1MXoY+Ai6NkbxoMRd2TrUfUU7WrPpA2IjDgy8dUplcZKc7DnJwNLTBfH5UNR+nGnakSPQia8UVIzrjkOnJ2fLrWUsA2oEO8yRsqkwXkkDCsyhB97dwj57RMt91XzgWhL9luNEGO92yW0rNFGoMSUVOxPIrFc5RjyrhKEc3+1RnpxCkylq+LNlQ5NFxLn6v2cF5DzqpvBHNR7XAig+urJIU3gXydCkaGZZDetJtQOUOXgZi9z9100NpdAEkXDo2ICHCGTGpVc0J/pbXxWRBxb6B1/Gl0Yjn68V6HlesH7IoC7GR/3HwRu9NSDBG4ttfQjEWcg+PeAea4Rn7jzx+Tm9H7L1joTKVgDbQg5iKMLfjvPqlnksCLtXOt8jSIS5OYLN7a/7TX6/w5d34vnw8vPDmU1UYi0Q72qUWhUa2vw8OXNpcKL7Bp0lNfBS8rvHY+vBY8/haAoTL3wvLFU1fT+4z/vA3BcsigZDYlfJeDYcxXmRuqxzxEGpXCRe9s1HWtID+41pHu6lpZHkXaghpc6TZHLxNwcVhTb6fMQ7Qo+2L6Pvklh1m32peodxeg2YiPhdpl3w/xkOEu5/JEF7ZBxpdUL+u3wkO5pUlsqfgX7uhzv7HC2WpSWVimrwiQwQOUx0+JPrLtw+lYfq7I3jruo0GW0guWvnuf7JM3YLj84q+JgHomnSSZnnZmrL0UaRvrVyLo877F39ccLS7XoZnnui8J4P58ZTmiLkEJeGcx1Iuag2e33339O7Yew/59tLbQtIGh9VWMwHBnFx39S8/4LEFrK5HldPQhOrloyTtkRs66iQRKtxMKS0VI6QTKZDAbs7a7H1yBv+mJi9Xg4uKmyU6qnn7zEKjjY2bIlCwezx4LLGP5HD3Zr6fZsmdG1UHzDsBvYG2oCI0oqEKM+valsT6hU8MRjbQBD/JJ8JJN/iBGlhBAUHo0UmhhtR2euTVpZWlMnhmpXAdKDXSfPdaPohgB', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team')" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team')\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 2 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "4127f167d1d653d6", - "parentSpanId": "8e84b2f5d3c9d733", - "name": "FilesystemMiddleware.wrap_tool_call", - "kind": 1, - "startTimeUnixNano": "1790968032472590080", - "endTimeUnixNano": "1790968032473856000", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_tool_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|tools:74348550-0598-498b-1732-6675e778549b" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "b2daa1c17359fac2", - "parentSpanId": "4127f167d1d653d6", - "name": "transfer_to_red_team", - "kind": 1, - "startTimeUnixNano": "1790968032472979968", - "endTimeUnixNano": "1790968032473444864", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "tool" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "transfer_to_red_team" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "execute_tool" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "gen_ai.tool.name", - "value": { - "stringValue": "transfer_to_red_team" - } - }, - { - "key": "gen_ai.tool.call.id", - "value": { - "stringValue": "toolu_01XEAuhQHCBdyCwtymZwFfDi" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|tools:74348550-0598-498b-1732-6675e778549b" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" - } - }, - { - "key": "langsmith.metadata.__handoff_destination", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "38a909e757fa3574", - "parentSpanId": "4862a8dc9e239ae2", - "name": "model", - "kind": 1, - "startTimeUnixNano": "1790968030846537984", - "endTimeUnixNano": "1790968032470715136", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|model:6b48cacc-ef10-0459-49d7-052bc435753c" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "0676be444516237c", - "parentSpanId": "38a909e757fa3574", - "name": "FilesystemMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968030846874880", - "endTimeUnixNano": "1790968032470281984", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|model:6b48cacc-ef10-0459-49d7-052bc435753c" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "5846c65e1a0fba02", - "parentSpanId": "0676be444516237c", - "name": "UnsupportedContentMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968030847229952", - "endTimeUnixNano": "1790968032470125056", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "UnsupportedContentMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|model:6b48cacc-ef10-0459-49d7-052bc435753c" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "7d9bd24669f22c02", - "parentSpanId": "5846c65e1a0fba02", - "name": "ChatAnthropic", - "kind": 1, - "startTimeUnixNano": "1790968030850436096", - "endTimeUnixNano": "1790968032469747968", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chat" - } - }, - { - "key": "gen_ai.serialized.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "llm" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "gen_ai.request.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "gen_ai.tool.definitions", - "value": { - "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"web_search\",\"input_schema\":{\"properties\":{\"query\":{\"type\":\"string\"}},\"required\":[\"query\"],\"type\":\"object\"},\"description\":\"Search the web with Exa for current facts and return excerpts with source URLs\"},{\"name\":\"transfer_to_researcher\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request a correction from the researcher\"},{\"name\":\"transfer_to_red_team\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send verified evidence for adversarial review\"},{\"name\":\"transfer_to_editor\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send verified findings to the editor\"}]" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_chat_model" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|model:6b48cacc-ef10-0459-49d7-052bc435753c" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" - } - }, - { - "key": "langsmith.metadata.ls_provider", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "langsmith.metadata.ls_model_name", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.ls_model_type", - "value": { - "stringValue": "chat" - } - }, - { - "key": "langsmith.metadata.ls_max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.lc_versions", - "value": { - "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.model_kwargs", - "value": { - "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" - } - }, - { - "key": "langsmith.metadata.streaming", - "value": { - "boolValue": false - } - }, - { - "key": "langsmith.metadata.max_retries", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata._type", - "value": { - "stringValue": "anthropic-chat" - } - }, - { - "key": "langsmith.metadata.usage_metadata", - "value": { - "stringValue": "{\"input_tokens\":7509,\"output_tokens\":88,\"total_tokens\":7597,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":55}}" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.usage.input_tokens", - "value": { - "intValue": "7509" - } - }, - { - "key": "gen_ai.usage.output_tokens", - "value": { - "intValue": "88" - } - }, - { - "key": "gen_ai.usage.total_tokens", - "value": { - "intValue": "7597" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "4862a8dc9e239ae2", - "parentSpanId": "0b1303d7a7aa229b", - "name": "verifier", - "kind": 1, - "startTimeUnixNano": "1790968030846055936", - "endTimeUnixNano": "1790968032478449152", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "3" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:verifier\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"verifier\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - } - ], - "events": [ - { - "timeUnixNano": "1790968032543667000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "ParentCommand(Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team')" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: ParentCommand(Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': 'CAQS1QgKEAgSGAI4AUIIdGhpbmtpbmcSDN6TfU6NDM971lEbzxoMvRUA1J9ox3fJQYT9IjArCQQGHBP4pRHPavXzRlbMbaYHC57Yj+Gbxgr0helvd2OIL/o6Rbt4PFA3FaIFUlgq8gc7KQI9FtGnvSAkLBRzIsUp/2d5Rd2zgEsfkFVeXsn8WYYZkinAQVVy6A7B3LaEJW0xb/x88Di67fedwx0Q+FlZtwcmT3Dcaa11JveyHRr3dm+zGSZP6CXeXNJ8nrTZ7W1YRTysD6w7o7Lp8h1Rwq4f4o8j+QUfY0vje+zJZsxHPmQNt3ykeKh99hgn6dbiz6/EHqmbHjSAu1M4SqEDfqIKThHYenamAZmcQ4XAOo6mdQ6+77VgpV1lC1/k52IiUoJjkGlQrnLCvutiI7KN+sgK8c2+2KCJrPRCvVV+BkStvP5jWWqzytpKQ+nHzhL448OrIA9gdJC39C8eDrXeRnI7t4FqlkXGoMlZAV9UMcrQHRxOMi8tOyTzi9oyBFDTSsQ+LJqer0tz1Ft9gek6vzg50SpVAFQdLERv8R1YqMaeI+xsvTAEW9MRgvRMkzLuzRT2guw3jD+Fjip37xgK5QI0R+CsOAmQPoTZizzcIyAUAuCJFCgq/gD/CibLxoymiVUI1an9Snt3KpNRoWdvWIne33V0pv8PHg9yW2JuLOqQGilLCsK/Q3oQr3upEMXxXGjCL7WUizvRZGFEEV+VplYt7v4tKZMj5pk3vdeM0MJ5XZg7PvUsRzycxcnrT3Knoc3qM+ttqZfTsb8d6U/pQifq7GuahFOHrvroqgJLj+/81Yy1pZFkjfJgY0XklzAnA6CFq/YT0gxbV+TH5IS+WaYOUzK36S8s5qqMwhngv4IzE3ctXXqnhIZXNznyVBqbYa/Gx2bCjcEj2n5RyGYRS/+MculgLBznQ9MkG2D7QP3Mq/nwHXKMIaLS8VK8hG3d0rAjlvnauXShNrJxtkj4qkwnxD4LrEjk1ue+PLcbLqYWwAr8n0s+41jrsIPVyyK9vFaEZrA9KaBxkJyiqx50GZNn7ckx+mkI18gH52iyVPtU8FKMXjugCl6mPLiHYiDQd+G63LudmOKys9itVnBDBNMP2b/I7+bIVRlheGaZWr6MATKl86B3y+0kuOrLRMyWcdibc2iQkZm+8f7dTUwbKbBJsKOFY73/8nlL/JiYpjz6nUIk+IqSjaFyK6XFlCcukWpWHpDJnSvbEzey7qHyCqJ+I+on8iP8GOtempQaS0/4kZGSwlrE6xOj6EwGpfjbDZKHkP/2RAdNYPQq3z7bdVJMJNnFMz6e37mzMpCBihwPdSFTRE3SCY66wvTgJzGCUyhHbSi5i1azzOXd8uHCSpT/6L1o6VU0pjoR8Kaa4wCWHGf7P/WEd+avyp02Jnu1cmpW0+Gq+vK9h0tdb2IClM/eNfdouQP+ep8MJUjraDRICmAJQY5obS71vniOo+reaFy0zRgB', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team')\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "0b1303d7a7aa229b", - "parentSpanId": "04ffc0db9ce0f358", - "name": "verifier", - "kind": 1, - "startTimeUnixNano": "1790968030845710080", - "endTimeUnixNano": "1790968032481081856", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langgraph" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "3" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "verifier" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:verifier\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"verifier\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:3" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - } - ], - "events": [ - { - "timeUnixNano": "1790968032543832000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "ParentCommand(Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': 'CAQS/REKEQgSGAI4AUIJbmFycmF0aW9uEgwFh3AVJZP3s8y1Hq0aDG76uhHONaScXAGShiIwGgjLXHUx1yZrkLPljjzTOQycpLJiKVwXcxm/EzKJm1s8M5WxuREWEldXcoaN0/msKpkRMT+eLb5ih9rAHULTomUNsUwJeu0jrJe4GLazy7sP5KtjEOEBKQsXUfoQ7fDkZOQUHZi9zzQN4hFNmYJUf3OVqf9TQNdC1+m//HAZPfWmAy6HtDvm7kgBJkCEoiFnm7tn/PX1hXGPRgWc6BTXUMr2WA8aKyqggRUbMH2+JYv5iWZddCc1up1Nbr3sF7WPcot9ZBhyHQXr692zeJk6SJgygIVrASbMly2bBxTWJB623gVgzpCmVSLZFpkKXgPcp8hGyDKOvF6SiQSHqGRxQofr7Vs1aPhfZixROJGD+MlrkggVAnGMyYIDUZpavtCeiU1JmBSz0084bXPtT/tnpsKOnSPYZQo3B0BXKbqA/WsKng8/V3Z8Uuajo6IVZ2hgA1WDduqQOQkExGU6pFuLhebIjuWxSNI/DffvR//LNqCfvdnf0hvoPtDxfx/SawIx4/spq9xbwFzHtLgoHg1F2wFw7clPDlg1PyD/v2yJG3V9T8GL6jGPE6rhfil/u4HNvf7BW0dQzCTTXcqZy4nByy0+p+S7ZxfMl4Kpxa2gOhhSNjfpfuX0QpL4kME8J1nliFN1d8KqEPuDI18BQHUhD/UfY29oA0x510FjM/BsLZ4n5sppkoIi7CFoQq2aAKVNfC1KilhIpRD+1dyDtZQklN8gZpOESHw6ML1TtU0yfAcbmqoxJ6hhjzwH6CMsTQEEy8MbRBM+QKKkIRdRCPHGFW2LkuR50+J0pF/tr6pqVvJeozfiMnrEilB27TZP4nKTJG8rd//vCWen0y7CA/8dBJ9gdp5tx7NVA45k1gdcxER1gYouNX3n1vG3/B1F4+93wXW9Mqo6Us59TQmrb9Nqa7pSQNSrH06w1GxyBAlkFfqAlafk16aMpq416TJYpGy43WCUiCcLWlhiWgz2sgOLAXP9a5weWAKRC8J6jkcUkDeXnW+HFSiPM6+9Bo6kVhLUhN5rc4mHZOZpF7ptPpsQN4XCqLPsqpRH/8o5XpyC6ZneTeF2ExtjhwZVjXDwMbIzVYIbw1y2PPGw8dC7pc4sIVSnI4oQAH0v650ghfhmMevWW4h4Pylbw/DG4fdeT3+8z0f8MOSTtfipx05/QttHlAvODRxa5yDCvOz6n3f1BO0N/4MbGyOM27qW4x8mBVoryUZWfsmhfi0/GfNvB8+ylTGbYNX27OcEF5WZtNqbWEy7V5GbmZUSxspcg7FBZ3j3/3L7muvZXoZi1f5erq4y3lSH+oF7qPFnvieyLOCwubcQy+oyowj4cD0idRecnp+s+52D7+mzF1gpW+f+cJasoxigbxkOloS4yeiKvgM4nWSpGEj12RPx5o80EmziXN9t4zJzW1htA5hXJJeFympMYtyCUCevRWVmrRYktQ7UnCa6tL/AVPi1ni5XCXHfLOuqfK5KLYxjwVtdhhfmCLvpaKVNCEOCf4nNGHqD98wUb0ejWNwDYBnJGkBRw9RVspfwNdoWoVcn2qv8ywGUp7yc/sk2LpI6VziRyvWqbGNG1ZJqVVutRc46+sOE4VSeS2/CTNKNa6NMCf/hxxaUVsYfKdP+S1Lc4ianKp0sUugPpmtoydC0CP2RwjnHLcnzxCnvqxlLQWXMNPTsu2yBcHlWJLtcmdg/McLagy7l5kG6sN7ZxJLD/kAx8E6uqohP+K/jMSrYuQJnhr4tf4biWFY3Jzf/KpAYyVSq+pbfFKXMbL9nHEoZQT15Wyabd6DMAq3QZOthM5pUzdNqUXkcrI1PwjASAg4dVU/2o+98mTXnyhP7VlEkTnddpwyJF+YCCc01pqa6ZX99pnR+YOpIrb5DtPcKq0t5cFCDyQxN1lUuqZcYujvX/GC7+6IpRTz/NkEY/5cntOfZJyd6SkUx/JR5AJIRPCNeib0rcWnnFn0XK8s22x40wLjEtufXDO9+yraf4kHxlBI3SB0meMjepX50CJhAx7NekkRFnwoecLfqIyrjXrgAZsTMPiX94snjdrzisAXtBKanulilSxOfW2HSmfnk0L2GXHJJ3S+vCbgREml9dekfmHhmwEYtv3kfhth7ERIwVT8j69OtIBCmeTIJuA7o73PXc1LJ2whuZK7FZe6NTOs61MP7JVlIc6tbhtOBk3NXU8pBPOCY6Q55d63FtpUU/KCbQ0K2WQ9o5jNGwNNJ6Cw5FDCt+x5YJeP1d2QzDSiq+cSZqwqCZVcNoAftGGzgrRZ4vkpbP0xQZHCtWsUwHVTjrY4NfRDjHdVPRn8J9Xtooc/hIWkqzFaczYTlapu2RCJqe8aEo3jzWZCEJ7AiBzBYraYDgOfeiQyeJUsbbXHdGKiiw22Bdp4M+Yz671MZ0ie9EWRks0Q2DHGUTne9S4tAAJPGbUf4xtCMoJ40Q4QW05QLSZy3wNFAUFYmXE4ECDFB8+IEeNFFF/tgAnfh8GvFh/1xY+LE+ozMminjSRwhq09zQAEkNFyu0IKgvDkyOI+iccF7doWLTUasPxLH1xGPBSKkeWCnSoX/4C2c9du66BbRXamHqae+VCiS6BN953iYKOu8rMkneW+TFjV0CzAf8PNG9LBayUgY5Uw9x0Sap6zI4PpaZKH4d9ktkFU+91yBbN5SRtdd8/EQatJXmBNfw7kRrll+LjwZweWLEb0jT1RpGuDqHLdLTMMgowSczrp2zCsJdQH/seaYrpwkCFR8dRjM7JRUkVa1A0SvdZAX75vuBvvLBzN2c+Rbt5oqy93lqIBIjKb7w2UkRTb4pBWcNKNPUgt3az/PxQxEasaltdmuyvsXYbur3VPNn8JzN/6J5N+QCnz571TccapCmkPvFE+gayXU+UF1VKYyFcUvlev7lsQlmjqzK2QA8X7Q3TzFapqhvJKlt7dzBHraqZBgPgb9N4oKNayi8FZT71+kaYhIhFrESKYRHfHkj5n3kfhgLy+x+jLDbKxMggkgHnJz9RuEHZXBWtkYAQ==', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': 'CAQS/REKEQgSGAI4AUIJbmFycmF0aW9uEgwFh3AVJZP3s8y1Hq0aDG76uhHONaScXAGShiIwGgjLXHUx1yZrkLPljjzTOQycpLJiKVwXcxm/EzKJm1s8M5WxuREWEldXcoaN0/msKpkRMT+eLb5ih9rAHULTomUNsUwJeu0jrJe4GLazy7sP5KtjEOEBKQsXUfoQ7fDkZOQUHZi9zzQN4hFNmYJUf3OVqf9TQNdC1+m//HAZPfWmAy6HtDvm7kgBJkCEoiFnm7tn/PX1hXGPRgWc6BTXUMr2WA8aKyqggRUbMH2+JYv5iWZddCc1up1Nbr3sF7WPcot9ZBhyHQXr692zeJk6SJgygIVrASbMly2bBxTWJB623gVgzpCmVSLZFpkKXgPcp8hGyDKOvF6SiQSHqGRxQofr7Vs1aPhfZixROJGD+MlrkggVAnGMyYIDUZpavtCeiU1JmBSz0084bXPtT/tnpsKOnSPYZQo3B0BXKbqA/WsKng8/V3Z8Uuajo6IVZ2hgA1WDduqQOQkExGU6pFuLhebIjuWxSNI/DffvR//LNqCfvdnf0hvoPtDxfx/SawIx4/spq9xbwFzHtLgoHg1F2wFw7clPDlg1PyD/v2yJG3V9T8GL6jGPE6rhfil/u4HNvf7BW0dQzCTTXcqZy4nByy0+p+S7ZxfMl4Kpxa2gOhhSNjfpfuX0QpL4kME8J1nliFN1d8KqEPuDI18BQHUhD/UfY29oA0x510FjM/BsLZ4n5sppkoIi7CFoQq2aAKVNfC1KilhIpRD+1dyDtZQklN8gZpOESHw6ML1TtU0yfAcbmqoxJ6hhjzwH6CMsTQEEy8MbRBM+QKKkIRdRCPHGFW2LkuR50+J0pF/tr6pqVvJeozfiMnrEilB27TZP4nKTJG8rd//vCWen0y7CA/8dBJ9gdp5tx7NVA45k1gdcxER1gYouNX3n1vG3/B1F4+93wXW9Mqo6Us59TQmrb9Nqa7pSQNSrH06w1GxyBAlkFfqAlafk16aMpq416TJYpGy43WCUiCcLWlhiWgz2sgOLAXP9a5weWAKRC8J6jkcUkDeXnW+HFSiPM6+9Bo6kVhLUhN5rc4mHZOZpF7ptPpsQN4XCqLPsqpRH/8o5XpyC6ZneTeF2ExtjhwZVjXDwMbIzVYIbw1y2PPGw8dC7pc4sIVSnI4oQAH0v650ghfhmMevWW4h4Pylbw/DG4fdeT3+8z0f8MOSTtfipx05/QttHlAvODRxa5yDCvOz6n3f1BO0N/4MbGyOM27qW4x8mBVoryUZWfsmhfi0/GfNvB8+ylTGbYNX27OcEF5WZtNqbWEy7V5GbmZUSxspcg7FBZ3j3/3L7muvZXoZi1f5erq4y3lSH+oF7qPFnvieyLOCwubcQy+oyowj4cD0idRecnp+s+52D7+mzF1gpW+f+cJasoxigbxkOloS4yeiKvgM4nWSpGEj12RPx5o80EmziXN9t4zJzW1htA5hXJJeFympMYtyCUCevRWVmrRYktQ7UnCa6tL/AVPi1ni5XCXHfLOuqfK5KLYxjwVtdhhfmCLvpaKVNCEOCf4nNGHqD98wUb0ejWNwDYBnJGkBRw9RVspfwNdoWoVcn2qv8ywGUp7yc/sk2LpI6VziRyvWqbGNG1ZJqVVutRc46+sOE4VSeS2/CTNKNa6NMCf/hxxaUVsYfKdP+S1Lc4ianKp0sUugPpmtoydC0CP2RwjnHLcnzxCnvqxlLQWXMNPTsu2yBcHlWJLtcmdg/McLagy7l5kG6sN7ZxJLD/kAx8E6uqohP+K/jMSrYuQJnhr4tf4biWFY3Jzf/KpAYyVSq+pbfFKXMbL9nHEoZQT15Wyabd6DMAq3QZOthM5pUzdNqUXkcrI1PwjASAg4dVU/2o+98mTXnyhP7VlEkTnddpwyJF+YCCc01pqa6ZX99pnR+YOpIrb5DtPcKq0t5cFCDyQxN1lUuqZcYujvX/GC7+6IpRTz/NkEY/5cntOfZJyd6SkUx/JR5AJIRPCNeib0rcWnnFn0XK8s22x40wLjEtufXDO9+yraf4kHxlBI3SB0meMjepX50CJhAx7NekkRFnwoecLfqIyrjXrgAZsTMPiX94snjdrzisAXtBKanulilSxOfW2HSmfnk0L2GXHJJ3S+vCbgREml9dekfmHhmwEYtv3kfhth7ERIwVT8j69OtIBCmeTIJuA7o73PXc1LJ2whuZK7FZe6NTOs61MP7JVlIc6tbhtOBk3NXU8pBPOCY6Q55d63FtpUU/KCbQ0K2WQ9o5jNGwNNJ6Cw5FDCt+x5YJeP1d2QzDSiq+cSZqwqCZVcNoAftGGzgrRZ4vkpbP0xQZHCtWsUwHVTjrY4NfRDjHdVPRn8J9Xtooc/hIWkqzFaczYTlapu2RCJqe8aEo3jzWZCEJ7AiBzBYraYDgOfeiQyeJUsbbXHdGKiiw22Bdp4M+Yz671MZ0ie9EWRks0Q2DHGUTne9S4tAAJPGbUf4xtCMoJ40Q4QW05QLSZy3wNFAUFYmXE4ECDFB8+IEeNFFF/tgAnfh8GvFh/1xY+LE+ozMminjSRwhq09zQAEkNFyu0IKgvDkyOI+iccF7doWLTUasPxLH1xGPBSKkeWCnSoX/4C2c9du66BbRXamHqae+VCiS6BN953iYKOu8rMkneW+TFjV0CzAf8PNG9LBayUgY5Uw9x0Sap6zI4PpaZKH4d9ktkFU+91yBbN5SRtdd8/EQatJXmBNfw7kRrll+LjwZweWLEb0jT1RpGuDqHLdLTMMgowSczrp2zCsJdQH/seaYrpwkCFR8dRjM7JRUkVa1A0SvdZAX75vuBvvLBzN2c+Rbt5oqy93lqIBIjKb7w2UkRTb4pBWcNKNPUgt3az/PxQxEasaltdmuyvsXYbur3VPNn8JzN/6J5N+QCnz571TccapCmkPvFE+gayXU+UF1VKYyFcUvlev7lsQlmjqzK2QA8X7Q3TzFapqhvJKlt7dzBHraqZBgPgb9N4oKNayi8FZT71+kaYhIhFrESKYRHfHkj5n3kfhgLy+x+jLDbKxMggkgHnJz9RuEHZXBWtkYAQ==', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team')" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: ParentCommand(Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': 'CAQS9gUKEAgSGAI4AUIIdGhpbmtpbmcSDGFyJ1MXoY+Ai6NkbxoMRd2TrUfUU7WrPpA2IjDgy8dUplcZKc7DnJwNLTBfH5UNR+nGnakSPQia8UVIzrjkOnJ2fLrWUsA2oEO8yRsqkwXkkDCsyhB97dwj57RMt91XzgWhL9luNEGO92yW0rNFGoMSUVOxPIrFc5RjyrhKEc3+1RnpxCkylq+LNlQ5NFxLn6v2cF5DzqpvBHNR7XAig+urJIU3gXydCkaGZZDetJtQOUOXgZi9z9100NpdAEkXDo2ICHCGTGpVc0J/pbXxWRBxb6B1/Gl0Yjn68V6HlesH7IoC7GR/3HwRu9NSDBG4ttfQjEWcg+PeAea4Rn7jzx+Tm9H7L1joTKVgDbQg5iKMLfjvPqlnksCLtXOt8jSIS5OYLN7a/7TX6/w5d34vnw8vPDmU1UYi0Q72qUWhUa2vw8OXNpcKL7Bp0lNfBS8rvHY+vBY8/haAoTL3wvLFU1fT+4z/vA3BcsigZDYlfJeDYcxXmRuqxzxEGpXCRe9s1HWtID+41pHu6lpZHkXaghpc6TZHLxNwcVhTb6fMQ7Qo+2L6Pvklh1m32peodxeg2YiPhdpl3w/xkOEu5/JEF7ZBxpdUL+u3wkO5pUlsqfgX7uhzv7HC2WpSWVimrwiQwQOUx0+JPrLtw+lYfq7I3jruo0GW0guWvnuf7JM3YLj84q+JgHomnSSZnnZmrL0UaRvrVyLo877F39ccLS7XoZnnui8J4P58ZTmiLkEJeGcx1Iuag2e33339O7Yew/59tLbQtIGh9VWMwHBnFx39S8/4LEFrK5HldPQhOrloyTtkRs66iQRKtxMKS0VI6QTKZDAbs7a7H1yBv+mJi9Xg4uKmyU6qnn7zEKjjY2bIlCwezx4LLGP5HD3Zr6fZsmdG1UHzDsBvYG2oCI0oqEKM+valsT6hU8MRjbQBD/JJ8JJN/iBGlhBAUHo0UmhhtR2euTVpZWlMnhmpXAdKDXSfPdaPohgB', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team')\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - } - ] - } - ] - }, - { - "resource": { - "attributes": [ - { - "key": "telemetry.sdk.language", - "value": { - "stringValue": "python" - } - }, - { - "key": "telemetry.sdk.name", - "value": { - "stringValue": "opentelemetry" - } - }, - { - "key": "telemetry.sdk.version", - "value": { - "stringValue": "1.45.0" - } - }, - { - "key": "service.instance.id", - "value": { - "stringValue": "b873df4c-5106-4097-a20b-b9380724f4d9" - } - }, - { - "key": "service.name", - "value": { - "stringValue": "deeplite" - } - } - ] - }, - "scopeSpans": [ - { - "scope": { - "name": "langsmith" - }, - "spans": [ - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "916b875f8575ff2d", - "parentSpanId": "59d91c7c0791b7de", - "name": "tools", - "kind": 1, - "startTimeUnixNano": "1790968035030605056", - "endTimeUnixNano": "1790968035036314112", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|tools:f216a445-733e-fcc8-6fba-de3530aa90b7" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:2" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJpbnB1dCI6W3sibmFtZSI6InRyYW5zZmVyX3RvX2VkaXRvciIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxVkJyV2RXRVdZZ2l0NGtOWWVoQk1VNSIsInR5cGUiOiJ0b29sX2NhbGwifV19" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - } - ], - "events": [ - { - "timeUnixNano": "1790968035107514000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': 'CAQS1QgKEAgSGAI4AUIIdGhpbmtpbmcSDN6TfU6NDM971lEbzxoMvRUA1J9ox3fJQYT9IjArCQQGHBP4pRHPavXzRlbMbaYHC57Yj+Gbxgr0helvd2OIL/o6Rbt4PFA3FaIFUlgq8gc7KQI9FtGnvSAkLBRzIsUp/2d5Rd2zgEsfkFVeXsn8WYYZkinAQVVy6A7B3LaEJW0xb/x88Di67fedwx0Q+FlZtwcmT3Dcaa11JveyHRr3dm+zGSZP6CXeXNJ8nrTZ7W1YRTysD6w7o7Lp8h1Rwq4f4o8j+QUfY0vje+zJZsxHPmQNt3ykeKh99hgn6dbiz6/EHqmbHjSAu1M4SqEDfqIKThHYenamAZmcQ4XAOo6mdQ6+77VgpV1lC1/k52IiUoJjkGlQrnLCvutiI7KN+sgK8c2+2KCJrPRCvVV+BkStvP5jWWqzytpKQ+nHzhL448OrIA9gdJC39C8eDrXeRnI7t4FqlkXGoMlZAV9UMcrQHRxOMi8tOyTzi9oyBFDTSsQ+LJqer0tz1Ft9gek6vzg50SpVAFQdLERv8R1YqMaeI+xsvTAEW9MRgvRMkzLuzRT2guw3jD+Fjip37xgK5QI0R+CsOAmQPoTZizzcIyAUAuCJFCgq/gD/CibLxoymiVUI1an9Snt3KpNRoWdvWIne33V0pv8PHg9yW2JuLOqQGilLCsK/Q3oQr3upEMXxXGjCL7WUizvRZGFEEV+VplYt7v4tKZMj5pk3vdeM0MJ5XZg7PvUsRzycxcnrT3Knoc3qM+ttqZfTsb8d6U/pQifq7GuahFOHrvroqgJLj+/81Yy1pZFkjfJgY0XklzAnA6CFq/YT0gxbV+TH5IS+WaYOUzK36S8s5qqMwhngv4IzE3ctXXqnhIZXNznyVBqbYa/Gx2bCjcEj2n5RyGYRS/+MculgLBznQ9MkG2D7QP3Mq/nwHXKMIaLS8VK8hG3d0rAjlvnauXShNrJxtkj4qkwnxD4LrEjk1ue+PLcbLqYWwAr8n0s+41jrsIPVyyK9vFaEZrA9KaBxkJyiqx50GZNn7ckx+mkI18gH52iyVPtU8FKMXjugCl6mPLiHYiDQd+G63LudmOKys9itVnBDBNMP2b/I7+bIVRlheGaZWr6MATKl86B3y+0kuOrLRMyWcdibc2iQkZm+8f7dTUwbKbBJsKOFY73/8nlL/JiYpjz6nUIk+IqSjaFyK6XFlCcukWpWHpDJnSvbEzey7qHyCqJ+I+on8iP8GOtempQaS0/4kZGSwlrE6xOj6EwGpfjbDZKHkP/2RAdNYPQq3z7bdVJMJNnFMz6e37mzMpCBihwPdSFTRE3SCY66wvTgJzGCUyhHbSi5i1azzOXd8uHCSpT/6L1o6VU0pjoR8Kaa4wCWHGf7P/WEd+avyp02Jnu1cmpW0+Gq+vK9h0tdb2IClM/eNfdouQP+ep8MJUjraDRICmAJQY5obS71vniOo+reaFy0zRgB', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': 'CAQS/REKEQgSGAI4AUIJbmFycmF0aW9uEgwFh3AVJZP3s8y1Hq0aDG76uhHONaScXAGShiIwGgjLXHUx1yZrkLPljjzTOQycpLJiKVwXcxm/EzKJm1s8M5WxuREWEldXcoaN0/msKpkRMT+eLb5ih9rAHULTomUNsUwJeu0jrJe4GLazy7sP5KtjEOEBKQsXUfoQ7fDkZOQUHZi9zzQN4hFNmYJUf3OVqf9TQNdC1+m//HAZPfWmAy6HtDvm7kgBJkCEoiFnm7tn/PX1hXGPRgWc6BTXUMr2WA8aKyqggRUbMH2+JYv5iWZddCc1up1Nbr3sF7WPcot9ZBhyHQXr692zeJk6SJgygIVrASbMly2bBxTWJB623gVgzpCmVSLZFpkKXgPcp8hGyDKOvF6SiQSHqGRxQofr7Vs1aPhfZixROJGD+MlrkggVAnGMyYIDUZpavtCeiU1JmBSz0084bXPtT/tnpsKOnSPYZQo3B0BXKbqA/WsKng8/V3Z8Uuajo6IVZ2hgA1WDduqQOQkExGU6pFuLhebIjuWxSNI/DffvR//LNqCfvdnf0hvoPtDxfx/SawIx4/spq9xbwFzHtLgoHg1F2wFw7clPDlg1PyD/v2yJG3V9T8GL6jGPE6rhfil/u4HNvf7BW0dQzCTTXcqZy4nByy0+p+S7ZxfMl4Kpxa2gOhhSNjfpfuX0QpL4kME8J1nliFN1d8KqEPuDI18BQHUhD/UfY29oA0x510FjM/BsLZ4n5sppkoIi7CFoQq2aAKVNfC1KilhIpRD+1dyDtZQklN8gZpOESHw6ML1TtU0yfAcbmqoxJ6hhjzwH6CMsTQEEy8MbRBM+QKKkIRdRCPHGFW2LkuR50+J0pF/tr6pqVvJeozfiMnrEilB27TZP4nKTJG8rd//vCWen0y7CA/8dBJ9gdp5tx7NVA45k1gdcxER1gYouNX3n1vG3/B1F4+93wXW9Mqo6Us59TQmrb9Nqa7pSQNSrH06w1GxyBAlkFfqAlafk16aMpq416TJYpGy43WCUiCcLWlhiWgz2sgOLAXP9a5weWAKRC8J6jkcUkDeXnW+HFSiPM6+9Bo6kVhLUhN5rc4mHZOZpF7ptPpsQN4XCqLPsqpRH/8o5XpyC6ZneTeF2ExtjhwZVjXDwMbIzVYIbw1y2PPGw8dC7pc4sIVSnI4oQAH0v650ghfhmMevWW4h4Pylbw/DG4fdeT3+8z0f8MOSTtfipx05/QttHlAvODRxa5yDCvOz6n3f1BO0N/4MbGyOM27qW4x8mBVoryUZWfsmhfi0/GfNvB8+ylTGbYNX27OcEF5WZtNqbWEy7V5GbmZUSxspcg7FBZ3j3/3L7muvZXoZi1f5erq4y3lSH+oF7qPFnvieyLOCwubcQy+oyowj4cD0idRecnp+s+52D7+mzF1gpW+f+cJasoxigbxkOloS4yeiKvgM4nWSpGEj12RPx5o80EmziXN9t4zJzW1htA5hXJJeFympMYtyCUCevRWVmrRYktQ7UnCa6tL/AVPi1ni5XCXHfLOuqfK5KLYxjwVtdhhfmCLvpaKVNCEOCf4nNGHqD98wUb0ejWNwDYBnJGkBRw9RVspfwNdoWoVcn2qv8ywGUp7yc/sk2LpI6VziRyvWqbGNG1ZJqVVutRc46+sOE4VSeS2/CTNKNa6NMCf/hxxaUVsYfKdP+S1Lc4ianKp0sUugPpmtoydC0CP2RwjnHLcnzxCnvqxlLQWXMNPTsu2yBcHlWJLtcmdg/McLagy7l5kG6sN7ZxJLD/kAx8E6uqohP+K/jMSrYuQJnhr4tf4biWFY3Jzf/KpAYyVSq+pbfFKXMbL9nHEoZQT15Wyabd6DMAq3QZOthM5pUzdNqUXkcrI1PwjASAg4dVU/2o+98mTXnyhP7VlEkTnddpwyJF+YCCc01pqa6ZX99pnR+YOpIrb5DtPcKq0t5cFCDyQxN1lUuqZcYujvX/GC7+6IpRTz/NkEY/5cntOfZJyd6SkUx/JR5AJIRPCNeib0rcWnnFn0XK8s22x40wLjEtufXDO9+yraf4kHxlBI3SB0meMjepX50CJhAx7NekkRFnwoecLfqIyrjXrgAZsTMPiX94snjdrzisAXtBKanulilSxOfW2HSmfnk0L2GXHJJ3S+vCbgREml9dekfmHhmwEYtv3kfhth7ERIwVT8j69OtIBCmeTIJuA7o73PXc1LJ2whuZK7FZe6NTOs61MP7JVlIc6tbhtOBk3NXU8pBPOCY6Q55d63FtpUU/KCbQ0K2WQ9o5jNGwNNJ6Cw5FDCt+x5YJeP1d2QzDSiq+cSZqwqCZVcNoAftGGzgrRZ4vkpbP0xQZHCtWsUwHVTjrY4NfRDjHdVPRn8J9Xtooc/hIWkqzFaczYTlapu2RCJqe8aEo3jzWZCEJ7AiBzBYraYDgOfeiQyeJUsbbXHdGKiiw22Bdp4M+Yz671MZ0ie9EWRks0Q2DHGUTne9S4tAAJPGbUf4xtCMoJ40Q4QW05QLSZy3wNFAUFYmXE4ECDFB8+IEeNFFF/tgAnfh8GvFh/1xY+LE+ozMminjSRwhq09zQAEkNFyu0IKgvDkyOI+iccF7doWLTUasPxLH1xGPBSKkeWCnSoX/4C2c9du66BbRXamHqae+VCiS6BN953iYKOu8rMkneW+TFjV0CzAf8PNG9LBayUgY5Uw9x0Sap6zI4PpaZKH4d9ktkFU+91yBbN5SRtdd8/EQatJXmBNfw7kRrll+LjwZweWLEb0jT1RpGuDqHLdLTMMgowSczrp2zCsJdQH/seaYrpwkCFR8dRjM7JRUkVa1A0SvdZAX75vuBvvLBzN2c+Rbt5oqy93lqIBIjKb7w2UkRTb4pBWcNKNPUgt3az/PxQxEasaltdmuyvsXYbur3VPNn8JzN/6J5N+QCnz571TccapCmkPvFE+gayXU+UF1VKYyFcUvlev7lsQlmjqzK2QA8X7Q3TzFapqhvJKlt7dzBHraqZBgPgb9N4oKNayi8FZT71+kaYhIhFrESKYRHfHkj5n3kfhgLy+x+jLDbKxMggkgHnJz9RuEHZXBWtkYAQ==', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': 'CAQSwgcKEAgSGAI4AUIIdGhpbmtpbmcSDORXge9uL1832RMQwBoMjQwAwAHb9iP1ojPGIjDDScal486beCJbtG8/D2Y9g9S5xIPfjoHg/dxwX5HypSQEBbjFiTSbPECXSFzV6YIq3wbLcmyPbvusGnDexFgx+3sIXzvqyFV/69xhihMnSpfTCHy0+0zSu1WpYU/WUpIfoaSXTcTa1qkM8x8Ek/y/1jkKMZUfDFa93uhUJxOC4+QgPWBl/+Xy2t82L2x/ebq7QLQTqtR0jXeaURQm3Co6JvOgWmDvMpEdTeTWE3fDh1tzzVKsflum4d89b6CaKtn8nlQd7RhN99vNQMQHG5V4OuVNdrHPZZpFOuhdejsMFWXyB+55slGAd8wEXgFKbI/knOXVGzL/NDF8Gty1tNZlu2fdSCAsYWMsFQP1cbwLeQGszyXzJMVZJ2I9xBPkyz1HOXCPyh5F+j2gRTPikVB3ARC6tfB/lDSUeKBVZPQS8pY/B4eCs+IjjaBNWruLzfqCsc6xL0CuQPSYyQXaYFjYrSRNcC70WQBWT5VVhp0mA9yZDGYbRZt9I5OK9QkQmuJ5zDFaMEOXzSrsC4lteP6MdimiMijvsH3iq+c6WUYolRj3neI88EaHIzLAGRq64BNCLzdAYL2pEU2sb5uG78PKVoUUCbVJL5jpDOhLOTO1bQsTuoUpnRRrLQD/kIzV+ljpVBwwfJcyq75TJA/CtPr/xr2SZ9B1b2sbjG6jD0lhtoCddeDgcqgl/LSSkcuaYY8xPWCy+LtNhcqThfmfvnHLJIpL6gjbjW/OQpRfVUwfw1jOb9bWVwcgHhNYfKYGPtM8oth5xwLYRRVgzqMKOvs7falXRhVzZ2SP6Iw0BMmAAZ6HjfCl9L+tPqJNlnQQOHpoWjum4B+XsYldFEKGQWQqsd59iNPvao9p/sCOt7rGqCozcmgiEm4w66ez/QIDyb46n0+tcNJPUcoBKvQ/jDwE6VwmkQ/nECjFp3UdDT+kWYQSNd8j8VBZOpG8LlqUYrEZCv0q7Bs1vcNrdYiaFoS32osaynWk+Ht3OHuFWbEF8JlsFTQAO05VvYkecf0V/oTHsG5hyOOs7UEaDFq7uaJuzWVhh5pAojIaBcR8fVln2PLRTX7is2nsA+QrdidePcZtFtgxAiKYe1i2sSFi4vm8EOkCbQ63wdQeY4Urr5PuoMEwxUULjgKagiAmsJDq4RrVm7sO4+6YuA9j6l2uylkOEc67vf/5fkXuCsiApNL6keb8c+vL0n4FXGdzj+apSDfFGBgB', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor')" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': 'CAQSwgcKEAgSGAI4AUIIdGhpbmtpbmcSDORXge9uL1832RMQwBoMjQwAwAHb9iP1ojPGIjDDScal486beCJbtG8/D2Y9g9S5xIPfjoHg/dxwX5HypSQEBbjFiTSbPECXSFzV6YIq3wbLcmyPbvusGnDexFgx+3sIXzvqyFV/69xhihMnSpfTCHy0+0zSu1WpYU/WUpIfoaSXTcTa1qkM8x8Ek/y/1jkKMZUfDFa93uhUJxOC4+QgPWBl/+Xy2t82L2x/ebq7QLQTqtR0jXeaURQm3Co6JvOgWmDvMpEdTeTWE3fDh1tzzVKsflum4d89b6CaKtn8nlQd7RhN99vNQMQHG5V4OuVNdrHPZZpFOuhdejsMFWXyB+55slGAd8wEXgFKbI/knOXVGzL/NDF8Gty1tNZlu2fdSCAsYWMsFQP1cbwLeQGszyXzJMVZJ2I9xBPkyz1HOXCPyh5F+j2gRTPikVB3ARC6tfB/lDSUeKBVZPQS8pY/B4eCs+IjjaBNWruLzfqCsc6xL0CuQPSYyQXaYFjYrSRNcC70WQBWT5VVhp0mA9yZDGYbRZt9I5OK9QkQmuJ5zDFaMEOXzSrsC4lteP6MdimiMijvsH3iq+c6WUYolRj3neI88EaHIzLAGRq64BNCLzdAYL2pEU2sb5uG78PKVoUUCbVJL5jpDOhLOTO1bQsTuoUpnRRrLQD/kIzV+ljpVBwwfJcyq75TJA/CtPr/xr2SZ9B1b2sbjG6jD0lhtoCddeDgcqgl/LSSkcuaYY8xPWCy+LtNhcqThfmfvnHLJIpL6gjbjW/OQpRfVUwfw1jOb9bWVwcgHhNYfKYGPtM8oth5xwLYRRVgzqMKOvs7falXRhVzZ2SP6Iw0BMmAAZ6HjfCl9L+tPqJNlnQQOHpoWjum4B+XsYldFEKGQWQqsd59iNPvao9p/sCOt7rGqCozcmgiEm4w66ez/QIDyb46n0+tcNJPUcoBKvQ/jDwE6VwmkQ/nECjFp3UdDT+kWYQSNd8j8VBZOpG8LlqUYrEZCv0q7Bs1vcNrdYiaFoS32osaynWk+Ht3OHuFWbEF8JlsFTQAO05VvYkecf0V/oTHsG5hyOOs7UEaDFq7uaJuzWVhh5pAojIaBcR8fVln2PLRTX7is2nsA+QrdidePcZtFtgxAiKYe1i2sSFi4vm8EOkCbQ63wdQeY4Urr5PuoMEwxUULjgKagiAmsJDq4RrVm7sO4+6YuA9j6l2uylkOEc67vf/5fkXuCsiApNL6keb8c+vL0n4FXGdzj+apSDfFGBgB', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor')\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 2 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "783b8087e857fd50", - "parentSpanId": "916b875f8575ff2d", - "name": "FilesystemMiddleware.wrap_tool_call", - "kind": 1, - "startTimeUnixNano": "1790968035031665920", - "endTimeUnixNano": "1790968035033541888", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_tool_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|tools:f216a445-733e-fcc8-6fba-de3530aa90b7" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "54441d892eb866e9", - "parentSpanId": "783b8087e857fd50", - "name": "transfer_to_editor", - "kind": 1, - "startTimeUnixNano": "1790968035032363008", - "endTimeUnixNano": "1790968035033051904", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "tool" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "transfer_to_editor" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "execute_tool" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "gen_ai.tool.name", - "value": { - "stringValue": "transfer_to_editor" - } - }, - { - "key": "gen_ai.tool.call.id", - "value": { - "stringValue": "toolu_01VBrWdWEWYgit4kNYehBMU5" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|tools:f216a445-733e-fcc8-6fba-de3530aa90b7" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" - } - }, - { - "key": "langsmith.metadata.__handoff_destination", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "1723d5322674ec35", - "parentSpanId": "59d91c7c0791b7de", - "name": "model", - "kind": 1, - "startTimeUnixNano": "1790968032482510080", - "endTimeUnixNano": "1790968035029985792", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|model:04f09f43-f066-c110-818d-1a33d3ba1569" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "028f466e9c7e011c", - "parentSpanId": "1723d5322674ec35", - "name": "FilesystemMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968032482876160", - "endTimeUnixNano": "1790968035029612032", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|model:04f09f43-f066-c110-818d-1a33d3ba1569" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJvdXRwdXQiOnsicmVzdWx0IjpbeyJjb250ZW50IjpbeyJzaWduYXR1cmUiOiJDQVFTd2djS0VBZ1NHQUk0QVVJSWRHaHBibXRwYm1jU0RPUlhnZTl1TDE4MzJSTVF3Qm9NalF3QXdBSGI5aVAxb2pQR0lqRERTY2FsNDg2YmVDSmJ0RzgvRDJZOWc5UzV4SVBmam9IZy9keHdYNUh5cFNRRUJiakZpVFNiUEVDWFNGelY2WUlxM3diTGNteVBidnVzR25EZXhGZ3grM3NJWHp2cXlGVi82OXhoaWhNblNwZlRDSHkwKzB6U3UxV3BZVS9XVXBJZm9hU1hUY1RhMXFrTTh4OEVrL3kvMWprS01aVWZERmE5M3VoVUp4T0M0K1FnUFdCbC8rWHkydDgyTDJ4L2VicTdRTFFUcXRSMGpYZWFVUlFtM0NvNkp2T2dXbUR2TXBFZFRlVFdFM2ZEaDF0enpWS3NmbHVtNGQ4OWI2Q2FLdG44bmxRZDdSaE45OXZOUU1RSEc1VjRPdVZOZHJIUFpacEZPdWhkZWpzTUZXWHlCKzU1c2xHQWQ4d0VYZ0ZLYkkva25PWFZHekwvTkRGOEd0eTF0TlpsdTJmZFNDQXNZV01zRlFQMWNid0xlUUdzenlYekpNVlpKMkk5eEJQa3l6MUhPWENQeWg1RitqMmdSVFBpa1ZCM0FSQzZ0ZkIvbERTVWVLQlZaUFFTOHBZL0I0ZUNzK0lqamFCTldydUx6ZnFDc2M2eEwwQ3VRUFNZeVFYYVlGallyU1JOY0M3MFdRQldUNVZWaHAwbUE5eVpER1liUlp0OUk1T0s5UWtRbXVKNXpERmFNRU9YelNyc0M0bHRlUDZNZGltaU1panZzSDNpcStjNldVWW9sUmozbmVJODhFYUhJekxBR1JxNjRCTkNMemRBWUwycEVVMnNiNXVHNzhQS1ZvVVVDYlZKTDVqcERPaExPVE8xYlFzVHVvVXBuUlJyTFFEL2tJelYrbGpwVkJ3d2ZKY3lxNzVUSkEvQ3RQci94cjJTWjlCMWIyc2JqRzZqRDBsaHRvQ2RkZURnY3FnbC9MU1NrY3VhWVk4eFBXQ3krTHROaGNxVGhmbWZ2bkhMSklwTDZnamJqVy9PUXBSZlZVd2Z3MWpPYjliV1Z3Y2dIaE5ZZktZR1B0TThvdGg1eHdMWVJSVmd6cU1LT3ZzN2ZhbFhSaFZ6WjJTUDZJdzBCTW1BQVo2SGpmQ2w5TCt0UHFKTmxuUVFPSHBvV2p1bTRCK1hzWWxkRkVLR1FXUXFzZDU5aU5QdmFvOXAvc0NPdDdyR3FDb3pjbWdpRW00dzY2ZXovUUlEeWI0Nm4wK3RjTkpQVWNvQkt2US9qRHdFNlZ3bWtRL25FQ2pGcDNVZERUK2tXWVFTTmQ4ajhWQlpPcEc4TGxxVVlyRVpDdjBxN0JzMXZjTnJkWWlhRm9TMzJvc2F5bldrK0h0M09IdUZXYkVGOEpsc0ZUUUFPMDVWdllrZWNmMFYvb1RIc0c1aHlPT3M3VUVhREZxN3VhSnV6V1ZoaDVwQW9qSWFCY1I4ZlZsbjJQTFJUWDdpczJuc0ErUXJkaWRlUGNadEZ0Z3hBaUtZZTFpMnNTRmk0dm04RU9rQ2JRNjN3ZFFlWTRVcnI1UHVvTUV3eFVVTGpnS2FnaUFtc0pEcTRSclZtN3NPNCs2WXVBOWo2bDJ1eWxrT0VjNjd2Zi81ZmtYdUNzaUFwTkw2a2ViOGMrdkwwbjRGWEdkemorYXBTRGZGR0JnQiIsInRoaW5raW5nIjoiIiwidHlwZSI6InRoaW5raW5nIn0seyJpZCI6InRvb2x1XzAxVkJyV2RXRVdZZ2l0NGtOWWVoQk1VNSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX2VkaXRvciIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHdBemZqcVVvcG9FbVpMYXFtMSIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjo3NDE2LCJvdXRwdXRfdG9rZW5zIjoxNTEsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjExOX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoicmVkX3RlYW0iLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtNmNlNi03MjUxLWI3OTYtNGY2NDMzM2Y2N2M2LTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fZWRpdG9yIiwiYXJncyI6e30sImlkIjoidG9vbHVfMDFWQnJXZFdFV1lnaXQ0a05ZZWhCTVU1IiwidHlwZSI6InRvb2xfY2FsbCJ9XSwiaW52YWxpZF90b29sX2NhbGxzIjpbXSwidXNhZ2VfbWV0YWRhdGEiOnsiaW5wdXRfdG9rZW5zIjo3NDE2LCJvdXRwdXRfdG9rZW5zIjoxNTEsInRvdGFsX3Rva2VucyI6NzU2NywiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MTE5fX19XSwic3RydWN0dXJlZF9yZXNwb25zZSI6bnVsbH19" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "ee45871111076e7a", - "parentSpanId": "028f466e9c7e011c", - "name": "UnsupportedContentMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968032483560192", - "endTimeUnixNano": "1790968035029467136", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "UnsupportedContentMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|model:04f09f43-f066-c110-818d-1a33d3ba1569" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "28bebc087f4f6678", - "parentSpanId": "ee45871111076e7a", - "name": "ChatAnthropic", - "kind": 1, - "startTimeUnixNano": "1790968032486740992", - "endTimeUnixNano": "1790968035029083136", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chat" - } - }, - { - "key": "gen_ai.serialized.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "llm" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "gen_ai.request.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "gen_ai.tool.definitions", - "value": { - "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"transfer_to_skeptic\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Return an unresolved objection to the skeptic\"},{\"name\":\"transfer_to_editor\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send adversarial findings to the editor\"}]" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_chat_model" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|model:04f09f43-f066-c110-818d-1a33d3ba1569" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" - } - }, - { - "key": "langsmith.metadata.ls_provider", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "langsmith.metadata.ls_model_name", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.ls_model_type", - "value": { - "stringValue": "chat" - } - }, - { - "key": "langsmith.metadata.ls_max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.lc_versions", - "value": { - "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.model_kwargs", - "value": { - "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" - } - }, - { - "key": "langsmith.metadata.streaming", - "value": { - "boolValue": false - } - }, - { - "key": "langsmith.metadata.max_retries", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata._type", - "value": { - "stringValue": "anthropic-chat" - } - }, - { - "key": "langsmith.metadata.usage_metadata", - "value": { - "stringValue": "{\"input_tokens\":7416,\"output_tokens\":151,\"total_tokens\":7567,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":119}}" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.usage.input_tokens", - "value": { - "intValue": "7416" - } - }, - { - "key": "gen_ai.usage.output_tokens", - "value": { - "intValue": "151" - } - }, - { - "key": "gen_ai.usage.total_tokens", - "value": { - "intValue": "7567" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "59d91c7c0791b7de", - "parentSpanId": "ad48a4e078446202", - "name": "red_team", - "kind": 1, - "startTimeUnixNano": "1790968032481995008", - "endTimeUnixNano": "1790968035039021056", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "4" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:red_team\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"red_team\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - } - ], - "events": [ - { - "timeUnixNano": "1790968035109079000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "ParentCommand(Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor')" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: ParentCommand(Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': 'CAQSwgcKEAgSGAI4AUIIdGhpbmtpbmcSDORXge9uL1832RMQwBoMjQwAwAHb9iP1ojPGIjDDScal486beCJbtG8/D2Y9g9S5xIPfjoHg/dxwX5HypSQEBbjFiTSbPECXSFzV6YIq3wbLcmyPbvusGnDexFgx+3sIXzvqyFV/69xhihMnSpfTCHy0+0zSu1WpYU/WUpIfoaSXTcTa1qkM8x8Ek/y/1jkKMZUfDFa93uhUJxOC4+QgPWBl/+Xy2t82L2x/ebq7QLQTqtR0jXeaURQm3Co6JvOgWmDvMpEdTeTWE3fDh1tzzVKsflum4d89b6CaKtn8nlQd7RhN99vNQMQHG5V4OuVNdrHPZZpFOuhdejsMFWXyB+55slGAd8wEXgFKbI/knOXVGzL/NDF8Gty1tNZlu2fdSCAsYWMsFQP1cbwLeQGszyXzJMVZJ2I9xBPkyz1HOXCPyh5F+j2gRTPikVB3ARC6tfB/lDSUeKBVZPQS8pY/B4eCs+IjjaBNWruLzfqCsc6xL0CuQPSYyQXaYFjYrSRNcC70WQBWT5VVhp0mA9yZDGYbRZt9I5OK9QkQmuJ5zDFaMEOXzSrsC4lteP6MdimiMijvsH3iq+c6WUYolRj3neI88EaHIzLAGRq64BNCLzdAYL2pEU2sb5uG78PKVoUUCbVJL5jpDOhLOTO1bQsTuoUpnRRrLQD/kIzV+ljpVBwwfJcyq75TJA/CtPr/xr2SZ9B1b2sbjG6jD0lhtoCddeDgcqgl/LSSkcuaYY8xPWCy+LtNhcqThfmfvnHLJIpL6gjbjW/OQpRfVUwfw1jOb9bWVwcgHhNYfKYGPtM8oth5xwLYRRVgzqMKOvs7falXRhVzZ2SP6Iw0BMmAAZ6HjfCl9L+tPqJNlnQQOHpoWjum4B+XsYldFEKGQWQqsd59iNPvao9p/sCOt7rGqCozcmgiEm4w66ez/QIDyb46n0+tcNJPUcoBKvQ/jDwE6VwmkQ/nECjFp3UdDT+kWYQSNd8j8VBZOpG8LlqUYrEZCv0q7Bs1vcNrdYiaFoS32osaynWk+Ht3OHuFWbEF8JlsFTQAO05VvYkecf0V/oTHsG5hyOOs7UEaDFq7uaJuzWVhh5pAojIaBcR8fVln2PLRTX7is2nsA+QrdidePcZtFtgxAiKYe1i2sSFi4vm8EOkCbQ63wdQeY4Urr5PuoMEwxUULjgKagiAmsJDq4RrVm7sO4+6YuA9j6l2uylkOEc67vf/5fkXuCsiApNL6keb8c+vL0n4FXGdzj+apSDfFGBgB', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': 'CAQS/REKEQgSGAI4AUIJbmFycmF0aW9uEgwFh3AVJZP3s8y1Hq0aDG76uhHONaScXAGShiIwGgjLXHUx1yZrkLPljjzTOQycpLJiKVwXcxm/EzKJm1s8M5WxuREWEldXcoaN0/msKpkRMT+eLb5ih9rAHULTomUNsUwJeu0jrJe4GLazy7sP5KtjEOEBKQsXUfoQ7fDkZOQUHZi9zzQN4hFNmYJUf3OVqf9TQNdC1+m//HAZPfWmAy6HtDvm7kgBJkCEoiFnm7tn/PX1hXGPRgWc6BTXUMr2WA8aKyqggRUbMH2+JYv5iWZddCc1up1Nbr3sF7WPcot9ZBhyHQXr692zeJk6SJgygIVrASbMly2bBxTWJB623gVgzpCmVSLZFpkKXgPcp8hGyDKOvF6SiQSHqGRxQofr7Vs1aPhfZixROJGD+MlrkggVAnGMyYIDUZpavtCeiU1JmBSz0084bXPtT/tnpsKOnSPYZQo3B0BXKbqA/WsKng8/V3Z8Uuajo6IVZ2hgA1WDduqQOQkExGU6pFuLhebIjuWxSNI/DffvR//LNqCfvdnf0hvoPtDxfx/SawIx4/spq9xbwFzHtLgoHg1F2wFw7clPDlg1PyD/v2yJG3V9T8GL6jGPE6rhfil/u4HNvf7BW0dQzCTTXcqZy4nByy0+p+S7ZxfMl4Kpxa2gOhhSNjfpfuX0QpL4kME8J1nliFN1d8KqEPuDI18BQHUhD/UfY29oA0x510FjM/BsLZ4n5sppkoIi7CFoQq2aAKVNfC1KilhIpRD+1dyDtZQklN8gZpOESHw6ML1TtU0yfAcbmqoxJ6hhjzwH6CMsTQEEy8MbRBM+QKKkIRdRCPHGFW2LkuR50+J0pF/tr6pqVvJeozfiMnrEilB27TZP4nKTJG8rd//vCWen0y7CA/8dBJ9gdp5tx7NVA45k1gdcxER1gYouNX3n1vG3/B1F4+93wXW9Mqo6Us59TQmrb9Nqa7pSQNSrH06w1GxyBAlkFfqAlafk16aMpq416TJYpGy43WCUiCcLWlhiWgz2sgOLAXP9a5weWAKRC8J6jkcUkDeXnW+HFSiPM6+9Bo6kVhLUhN5rc4mHZOZpF7ptPpsQN4XCqLPsqpRH/8o5XpyC6ZneTeF2ExtjhwZVjXDwMbIzVYIbw1y2PPGw8dC7pc4sIVSnI4oQAH0v650ghfhmMevWW4h4Pylbw/DG4fdeT3+8z0f8MOSTtfipx05/QttHlAvODRxa5yDCvOz6n3f1BO0N/4MbGyOM27qW4x8mBVoryUZWfsmhfi0/GfNvB8+ylTGbYNX27OcEF5WZtNqbWEy7V5GbmZUSxspcg7FBZ3j3/3L7muvZXoZi1f5erq4y3lSH+oF7qPFnvieyLOCwubcQy+oyowj4cD0idRecnp+s+52D7+mzF1gpW+f+cJasoxigbxkOloS4yeiKvgM4nWSpGEj12RPx5o80EmziXN9t4zJzW1htA5hXJJeFympMYtyCUCevRWVmrRYktQ7UnCa6tL/AVPi1ni5XCXHfLOuqfK5KLYxjwVtdhhfmCLvpaKVNCEOCf4nNGHqD98wUb0ejWNwDYBnJGkBRw9RVspfwNdoWoVcn2qv8ywGUp7yc/sk2LpI6VziRyvWqbGNG1ZJqVVutRc46+sOE4VSeS2/CTNKNa6NMCf/hxxaUVsYfKdP+S1Lc4ianKp0sUugPpmtoydC0CP2RwjnHLcnzxCnvqxlLQWXMNPTsu2yBcHlWJLtcmdg/McLagy7l5kG6sN7ZxJLD/kAx8E6uqohP+K/jMSrYuQJnhr4tf4biWFY3Jzf/KpAYyVSq+pbfFKXMbL9nHEoZQT15Wyabd6DMAq3QZOthM5pUzdNqUXkcrI1PwjASAg4dVU/2o+98mTXnyhP7VlEkTnddpwyJF+YCCc01pqa6ZX99pnR+YOpIrb5DtPcKq0t5cFCDyQxN1lUuqZcYujvX/GC7+6IpRTz/NkEY/5cntOfZJyd6SkUx/JR5AJIRPCNeib0rcWnnFn0XK8s22x40wLjEtufXDO9+yraf4kHxlBI3SB0meMjepX50CJhAx7NekkRFnwoecLfqIyrjXrgAZsTMPiX94snjdrzisAXtBKanulilSxOfW2HSmfnk0L2GXHJJ3S+vCbgREml9dekfmHhmwEYtv3kfhth7ERIwVT8j69OtIBCmeTIJuA7o73PXc1LJ2whuZK7FZe6NTOs61MP7JVlIc6tbhtOBk3NXU8pBPOCY6Q55d63FtpUU/KCbQ0K2WQ9o5jNGwNNJ6Cw5FDCt+x5YJeP1d2QzDSiq+cSZqwqCZVcNoAftGGzgrRZ4vkpbP0xQZHCtWsUwHVTjrY4NfRDjHdVPRn8J9Xtooc/hIWkqzFaczYTlapu2RCJqe8aEo3jzWZCEJ7AiBzBYraYDgOfeiQyeJUsbbXHdGKiiw22Bdp4M+Yz671MZ0ie9EWRks0Q2DHGUTne9S4tAAJPGbUf4xtCMoJ40Q4QW05QLSZy3wNFAUFYmXE4ECDFB8+IEeNFFF/tgAnfh8GvFh/1xY+LE+ozMminjSRwhq09zQAEkNFyu0IKgvDkyOI+iccF7doWLTUasPxLH1xGPBSKkeWCnSoX/4C2c9du66BbRXamHqae+VCiS6BN953iYKOu8rMkneW+TFjV0CzAf8PNG9LBayUgY5Uw9x0Sap6zI4PpaZKH4d9ktkFU+91yBbN5SRtdd8/EQatJXmBNfw7kRrll+LjwZweWLEb0jT1RpGuDqHLdLTMMgowSczrp2zCsJdQH/seaYrpwkCFR8dRjM7JRUkVa1A0SvdZAX75vuBvvLBzN2c+Rbt5oqy93lqIBIjKb7w2UkRTb4pBWcNKNPUgt3az/PxQxEasaltdmuyvsXYbur3VPNn8JzN/6J5N+QCnz571TccapCmkPvFE+gayXU+UF1VKYyFcUvlev7lsQlmjqzK2QA8X7Q3TzFapqhvJKlt7dzBHraqZBgPgb9N4oKNayi8FZT71+kaYhIhFrESKYRHfHkj5n3kfhgLy+x+jLDbKxMggkgHnJz9RuEHZXBWtkYAQ==', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor')\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "ad48a4e078446202", - "parentSpanId": "04ffc0db9ce0f358", - "name": "red_team", - "kind": 1, - "startTimeUnixNano": "1790968032481682176", - "endTimeUnixNano": "1790968035042222080", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langgraph" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "4" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "red_team" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:red_team\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"red_team\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:4" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - } - ], - "events": [ - { - "timeUnixNano": "1790968035109279000", - "name": "exception", - "attributes": [ - { - "key": "exception.type", - "value": { - "stringValue": "Exception" - } - }, - { - "key": "exception.message", - "value": { - "stringValue": "ParentCommand(Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': 'CAQS1QgKEAgSGAI4AUIIdGhpbmtpbmcSDN6TfU6NDM971lEbzxoMvRUA1J9ox3fJQYT9IjArCQQGHBP4pRHPavXzRlbMbaYHC57Yj+Gbxgr0helvd2OIL/o6Rbt4PFA3FaIFUlgq8gc7KQI9FtGnvSAkLBRzIsUp/2d5Rd2zgEsfkFVeXsn8WYYZkinAQVVy6A7B3LaEJW0xb/x88Di67fedwx0Q+FlZtwcmT3Dcaa11JveyHRr3dm+zGSZP6CXeXNJ8nrTZ7W1YRTysD6w7o7Lp8h1Rwq4f4o8j+QUfY0vje+zJZsxHPmQNt3ykeKh99hgn6dbiz6/EHqmbHjSAu1M4SqEDfqIKThHYenamAZmcQ4XAOo6mdQ6+77VgpV1lC1/k52IiUoJjkGlQrnLCvutiI7KN+sgK8c2+2KCJrPRCvVV+BkStvP5jWWqzytpKQ+nHzhL448OrIA9gdJC39C8eDrXeRnI7t4FqlkXGoMlZAV9UMcrQHRxOMi8tOyTzi9oyBFDTSsQ+LJqer0tz1Ft9gek6vzg50SpVAFQdLERv8R1YqMaeI+xsvTAEW9MRgvRMkzLuzRT2guw3jD+Fjip37xgK5QI0R+CsOAmQPoTZizzcIyAUAuCJFCgq/gD/CibLxoymiVUI1an9Snt3KpNRoWdvWIne33V0pv8PHg9yW2JuLOqQGilLCsK/Q3oQr3upEMXxXGjCL7WUizvRZGFEEV+VplYt7v4tKZMj5pk3vdeM0MJ5XZg7PvUsRzycxcnrT3Knoc3qM+ttqZfTsb8d6U/pQifq7GuahFOHrvroqgJLj+/81Yy1pZFkjfJgY0XklzAnA6CFq/YT0gxbV+TH5IS+WaYOUzK36S8s5qqMwhngv4IzE3ctXXqnhIZXNznyVBqbYa/Gx2bCjcEj2n5RyGYRS/+MculgLBznQ9MkG2D7QP3Mq/nwHXKMIaLS8VK8hG3d0rAjlvnauXShNrJxtkj4qkwnxD4LrEjk1ue+PLcbLqYWwAr8n0s+41jrsIPVyyK9vFaEZrA9KaBxkJyiqx50GZNn7ckx+mkI18gH52iyVPtU8FKMXjugCl6mPLiHYiDQd+G63LudmOKys9itVnBDBNMP2b/I7+bIVRlheGaZWr6MATKl86B3y+0kuOrLRMyWcdibc2iQkZm+8f7dTUwbKbBJsKOFY73/8nlL/JiYpjz6nUIk+IqSjaFyK6XFlCcukWpWHpDJnSvbEzey7qHyCqJ+I+on8iP8GOtempQaS0/4kZGSwlrE6xOj6EwGpfjbDZKHkP/2RAdNYPQq3z7bdVJMJNnFMz6e37mzMpCBihwPdSFTRE3SCY66wvTgJzGCUyhHbSi5i1azzOXd8uHCSpT/6L1o6VU0pjoR8Kaa4wCWHGf7P/WEd+avyp02Jnu1cmpW0+Gq+vK9h0tdb2IClM/eNfdouQP+ep8MJUjraDRICmAJQY5obS71vniOo+reaFy0zRgB', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor')" - } - }, - { - "key": "exception.stacktrace", - "value": { - "stringValue": "Exception: ParentCommand(Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': 'CAQS1QgKEAgSGAI4AUIIdGhpbmtpbmcSDN6TfU6NDM971lEbzxoMvRUA1J9ox3fJQYT9IjArCQQGHBP4pRHPavXzRlbMbaYHC57Yj+Gbxgr0helvd2OIL/o6Rbt4PFA3FaIFUlgq8gc7KQI9FtGnvSAkLBRzIsUp/2d5Rd2zgEsfkFVeXsn8WYYZkinAQVVy6A7B3LaEJW0xb/x88Di67fedwx0Q+FlZtwcmT3Dcaa11JveyHRr3dm+zGSZP6CXeXNJ8nrTZ7W1YRTysD6w7o7Lp8h1Rwq4f4o8j+QUfY0vje+zJZsxHPmQNt3ykeKh99hgn6dbiz6/EHqmbHjSAu1M4SqEDfqIKThHYenamAZmcQ4XAOo6mdQ6+77VgpV1lC1/k52IiUoJjkGlQrnLCvutiI7KN+sgK8c2+2KCJrPRCvVV+BkStvP5jWWqzytpKQ+nHzhL448OrIA9gdJC39C8eDrXeRnI7t4FqlkXGoMlZAV9UMcrQHRxOMi8tOyTzi9oyBFDTSsQ+LJqer0tz1Ft9gek6vzg50SpVAFQdLERv8R1YqMaeI+xsvTAEW9MRgvRMkzLuzRT2guw3jD+Fjip37xgK5QI0R+CsOAmQPoTZizzcIyAUAuCJFCgq/gD/CibLxoymiVUI1an9Snt3KpNRoWdvWIne33V0pv8PHg9yW2JuLOqQGilLCsK/Q3oQr3upEMXxXGjCL7WUizvRZGFEEV+VplYt7v4tKZMj5pk3vdeM0MJ5XZg7PvUsRzycxcnrT3Knoc3qM+ttqZfTsb8d6U/pQifq7GuahFOHrvroqgJLj+/81Yy1pZFkjfJgY0XklzAnA6CFq/YT0gxbV+TH5IS+WaYOUzK36S8s5qqMwhngv4IzE3ctXXqnhIZXNznyVBqbYa/Gx2bCjcEj2n5RyGYRS/+MculgLBznQ9MkG2D7QP3Mq/nwHXKMIaLS8VK8hG3d0rAjlvnauXShNrJxtkj4qkwnxD4LrEjk1ue+PLcbLqYWwAr8n0s+41jrsIPVyyK9vFaEZrA9KaBxkJyiqx50GZNn7ckx+mkI18gH52iyVPtU8FKMXjugCl6mPLiHYiDQd+G63LudmOKys9itVnBDBNMP2b/I7+bIVRlheGaZWr6MATKl86B3y+0kuOrLRMyWcdibc2iQkZm+8f7dTUwbKbBJsKOFY73/8nlL/JiYpjz6nUIk+IqSjaFyK6XFlCcukWpWHpDJnSvbEzey7qHyCqJ+I+on8iP8GOtempQaS0/4kZGSwlrE6xOj6EwGpfjbDZKHkP/2RAdNYPQq3z7bdVJMJNnFMz6e37mzMpCBihwPdSFTRE3SCY66wvTgJzGCUyhHbSi5i1azzOXd8uHCSpT/6L1o6VU0pjoR8Kaa4wCWHGf7P/WEd+avyp02Jnu1cmpW0+Gq+vK9h0tdb2IClM/eNfdouQP+ep8MJUjraDRICmAJQY5obS71vniOo+reaFy0zRgB', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor')\n" - } - }, - { - "key": "exception.escaped", - "value": { - "stringValue": "False" - } - } - ] - } - ], - "status": { - "code": 1 - }, - "flags": 256 - } - ] - } - ] - }, - { - "resource": { - "attributes": [ - { - "key": "telemetry.sdk.language", - "value": { - "stringValue": "python" - } - }, - { - "key": "telemetry.sdk.name", - "value": { - "stringValue": "opentelemetry" - } - }, - { - "key": "telemetry.sdk.version", - "value": { - "stringValue": "1.45.0" - } - }, - { - "key": "service.instance.id", - "value": { - "stringValue": "b873df4c-5106-4097-a20b-b9380724f4d9" - } - }, - { - "key": "service.name", - "value": { - "stringValue": "deeplite" - } - } - ] - }, - "scopeSpans": [ - { - "scope": { - "name": "langsmith" - }, - "spans": [ - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "47f7607ab58c542f", - "parentSpanId": "4809a44f637a7046", - "name": "tools", - "kind": 1, - "startTimeUnixNano": "1790968039092067840", - "endTimeUnixNano": "1790968039095913984", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|tools:4fd8a45a-13d9-1c55-5033-6f6d90c107c0" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:2" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJtZXNzYWdlcyI6W3siY29udGVudCI6IlVwZGF0ZWQgZmlsZSAvYW5zd2VyLm1kIiwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6e30sInR5cGUiOiJ0b29sIiwibmFtZSI6IndyaXRlX2ZpbGUiLCJpZCI6ImUzNDkyZTA4LWM4NjktNDdlYy1hNWY3LWNjNTdlYTVmNjQwMyIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxQm04QVU5RXNRVXdxb1ZMWXB4S0E3NyIsInN0YXR1cyI6InN1Y2Nlc3MifV19" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "848c01c3433c72af", - "parentSpanId": "47f7607ab58c542f", - "name": "FilesystemMiddleware.wrap_tool_call", - "kind": 1, - "startTimeUnixNano": "1790968039093334016", - "endTimeUnixNano": "1790968039095428096", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_tool_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|tools:4fd8a45a-13d9-1c55-5033-6f6d90c107c0" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJjb250ZW50IjoiVXBkYXRlZCBmaWxlIC9hbnN3ZXIubWQiLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7fSwidHlwZSI6InRvb2wiLCJuYW1lIjoid3JpdGVfZmlsZSIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxQm04QVU5RXNRVXdxb1ZMWXB4S0E3NyIsInN0YXR1cyI6InN1Y2Nlc3MifQ==" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "cfb36a1a28ffc485", - "parentSpanId": "848c01c3433c72af", - "name": "write_file", - "kind": 1, - "startTimeUnixNano": "1790968039094265088", - "endTimeUnixNano": "1790968039095307008", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "tool" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "write_file" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "execute_tool" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "gen_ai.tool.name", - "value": { - "stringValue": "write_file" - } - }, - { - "key": "gen_ai.tool.call.id", - "value": { - "stringValue": "toolu_01Bm8AU9EsQUwqoVLYpxKA77" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "tools" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"__pregel_push\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_push\",0,false]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|tools:4fd8a45a-13d9-1c55-5033-6f6d90c107c0" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "eyJvdXRwdXQiOnsiY29udGVudCI6IlVwZGF0ZWQgZmlsZSAvYW5zd2VyLm1kIiwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6e30sInR5cGUiOiJ0b29sIiwibmFtZSI6IndyaXRlX2ZpbGUiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMUJtOEFVOUVzUVV3cW9WTFlweEtBNzciLCJzdGF0dXMiOiJzdWNjZXNzIn19" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "d1e910014914b0a2", - "parentSpanId": "4809a44f637a7046", - "name": "model", - "kind": 1, - "startTimeUnixNano": "1790968035043832064", - "endTimeUnixNano": "1790968039091361024", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:5f0cee1e-bfe5-1171-9153-91c4b775587c" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "fc98979761fe2c4e", - "parentSpanId": "d1e910014914b0a2", - "name": "FilesystemMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968035044310016", - "endTimeUnixNano": "1790968039090991104", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:5f0cee1e-bfe5-1171-9153-91c4b775587c" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "4bd8ddfd6bc728ed", - "parentSpanId": "fc98979761fe2c4e", - "name": "UnsupportedContentMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968035044775936", - "endTimeUnixNano": "1790968039090832896", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "UnsupportedContentMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:5f0cee1e-bfe5-1171-9153-91c4b775587c" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "e90628af060558bc", - "parentSpanId": "4bd8ddfd6bc728ed", - "name": "ChatAnthropic", - "kind": 1, - "startTimeUnixNano": "1790968035049609984", - "endTimeUnixNano": "1790968039090351104", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chat" - } - }, - { - "key": "gen_ai.serialized.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "llm" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "gen_ai.request.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "gen_ai.tool.definitions", - "value": { - "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"write_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path where the file should be written. Must be absolute, not relative.\",\"type\":\"string\"},\"content\":{\"description\":\"The text content to write to the file. This parameter is required.\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"description\":\"Writes content to a file. Creates the file if it does not exist; replaces it entirely if it does.\\n\\nUsage:\\n- Use this tool when you intend to create a new file or replace the whole file. You do not need to read the file first.\\n- Prefer to edit existing files (with the edit_file tool) over creating new ones when possible.\"},{\"name\":\"edit_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to edit. Must be absolute, not relative.\",\"type\":\"string\"},\"old_string\":{\"description\":\"The exact text to find and replace. Must be unique in the file unless replace_all is True.\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace old_string with. Must be different from old_string.\",\"type\":\"string\"},\"replace_all\":{\"default\":false,\"description\":\"If True, replace all occurrences of old_string. If False (default), old_string must be unique.\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"description\":\"Performs exact string replacements in files.\\n\\nUsage:\\n- You must read the file before editing; this tool errors otherwise.\\n- Preserve the exact source indentation from the read output, and never include the read status header in old_string or new_string.\\n- Prefer editing an existing file over creating a new one.\\n- Only use emojis if the user explicitly requests it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"transfer_to_researcher\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request missing evidence from the researcher\"},{\"name\":\"transfer_to_skeptic\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request another critique from the skeptic\"},{\"name\":\"transfer_to_verifier\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request another source check from the verifier\"}]" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_chat_model" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "1" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:5f0cee1e-bfe5-1171-9153-91c4b775587c" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.ls_provider", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "langsmith.metadata.ls_model_name", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.ls_model_type", - "value": { - "stringValue": "chat" - } - }, - { - "key": "langsmith.metadata.ls_max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.lc_versions", - "value": { - "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.model_kwargs", - "value": { - "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" - } - }, - { - "key": "langsmith.metadata.streaming", - "value": { - "boolValue": false - } - }, - { - "key": "langsmith.metadata.max_retries", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata._type", - "value": { - "stringValue": "anthropic-chat" - } - }, - { - "key": "langsmith.metadata.usage_metadata", - "value": { - "stringValue": "{\"input_tokens\":8127,\"output_tokens\":433,\"total_tokens\":8560,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":79}}" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.usage.input_tokens", - "value": { - "intValue": "8127" - } - }, - { - "key": "gen_ai.usage.output_tokens", - "value": { - "intValue": "433" - } - }, - { - "key": "gen_ai.usage.total_tokens", - "value": { - "intValue": "8560" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "04ffc0db9ce0f358", - "parentSpanId": "e8da3a18a9815276", - "name": "LangGraph", - "kind": 1, - "startTimeUnixNano": "1790968013178249984", - "endTimeUnixNano": "1790968042919047168", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "LangGraph" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langgraph" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJtZXNzYWdlcyI6W3sicm9sZSI6InVzZXIiLCJjb250ZW50IjoiRm9yIGEgc3ludGhldGljIHRyYWNpbmcgZml4dHVyZSwgZXhwbGFpbiBQeXRob24gdHVwbGUgdmVyc3VzIGxpc3QgaW1tdXRhYmlsaXR5IGluIGF0IG1vc3QgMTIwIHdvcmRzLiBVc2Ugb25seSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBpZiB5b3Ugc2VhcmNoLiBIYXZlIHRoZSBza2VwdGljIGFuZCB2ZXJpZmllciBjaGVjayBpdCwgdGhlbiBoYXZlIHRoZSBlZGl0b3Igd3JpdGUgL2Fuc3dlci5tZC4gS2VlcCB0aGUgcnVuIHNob3J0IGFuZCBkbyBub3QgYXNrIGZvbGxvdy11cCBxdWVzdGlvbnMuIn1dfQ==" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "41a84418436b8795", - "parentSpanId": "04ffc0db9ce0f358", - "name": "editor", - "kind": 1, - "startTimeUnixNano": "1790968035042877952", - "endTimeUnixNano": "1790968042918639872", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langgraph" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "5" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:editor\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"editor\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:5" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "4809a44f637a7046", - "parentSpanId": "41a84418436b8795", - "name": "editor", - "kind": 1, - "startTimeUnixNano": "1790968035043306240", - "endTimeUnixNano": "1790968042918324992", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "5" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:editor\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"editor\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "5eb6729648b8a8b0", - "parentSpanId": "4809a44f637a7046", - "name": "model", - "kind": 1, - "startTimeUnixNano": "1790968039096445952", - "endTimeUnixNano": "1790968042917764864", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "3" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:d639a607-1d3b-b4dc-823b-564098184f56" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "graph:step:3" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "eyJtZXNzYWdlcyI6W3siY29udGVudCI6IkZvciBhIHN5bnRoZXRpYyB0cmFjaW5nIGZpeHR1cmUsIGV4cGxhaW4gUHl0aG9uIHR1cGxlIHZlcnN1cyBsaXN0IGltbXV0YWJpbGl0eSBpbiBhdCBtb3N0IDEyMCB3b3Jkcy4gVXNlIG9ubHkgb2ZmaWNpYWwgUHl0aG9uIGRvY3VtZW50YXRpb24gaWYgeW91IHNlYXJjaC4gSGF2ZSB0aGUgc2tlcHRpYyBhbmQgdmVyaWZpZXIgY2hlY2sgaXQsIHRoZW4gaGF2ZSB0aGUgZWRpdG9yIHdyaXRlIC9hbnN3ZXIubWQuIEtlZXAgdGhlIHJ1biBzaG9ydCBhbmQgZG8gbm90IGFzayBmb2xsb3ctdXAgcXVlc3Rpb25zLiIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoiaHVtYW4iLCJpZCI6IjQ2MjA0MzA1LWY4ZWUtNDM4NC05Y2U4LWZjZDgwYmZjZGY3NSJ9LHsiY29udGVudCI6W3siaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9LCJuYW1lIjoid2ViX3NlYXJjaCIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHc5YVc5YnJlblBxZ3liZk53UCIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjoyODQ1LCJvdXRwdXRfdG9rZW5zIjo3Mywib3V0cHV0X3Rva2Vuc19kZXRhaWxzIjp7InRoaW5raW5nX3Rva2VucyI6MH0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoicmVzZWFyY2hlciIsImlkIjoibGNfcnVuLS0wMWEwZmUwMy0yMWEzLTcwMDAtYTM4MS0yODRhNmEwYzAzZjctMCIsInRvb2xfY2FsbHMiOlt7Im5hbWUiOiJ3ZWJfc2VhcmNoIiwiYXJncyI6eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9LCJpZCI6InRvb2x1XzAxQjJMZkhHRGpZU0ZKaG1pWE5qNEN1USIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6Mjg0NSwib3V0cHV0X3Rva2VucyI6NzMsInRvdGFsX3Rva2VucyI6MjkxOCwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19fSx7ImNvbnRlbnQiOiJbe1widGl0bGVcIjogXCI1LiBEYXRhIFN0cnVjdHVyZXMgXFx1MjAxNCBQeXRob24gMy4xNC41IGRvY3VtZW50YXRpb25cIiwgXCJ1cmxcIjogXCJodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3R1dG9yaWFsL2RhdGFzdHJ1Y3R1cmVzLmh0bWxcIiwgXCJoaWdobGlnaHRzXCI6IFtcIllvdSBtaWdodCBoYXZlIG5vdGljZWQgdGhhdCBtZXRob2RzIGxpa2VgaW5zZXJ0YCxgcmVtb3ZlYCBvcmBzb3J0YCB0aGF0IG9ubHkgbW9kaWZ5IHRoZSBsaXN0IGhhdmUgbm8gcmV0dXJuIHZhbHVlIHByaW50ZWQgXFx1MjAxMyB0aGV5IHJldHVybiB0aGUgZGVmYXVsdGBOb25lYC4gWzFdIFRoaXMgaXMgYSBkZXNpZ24gcHJpbmNpcGxlIGZvciBhbGwgbXV0YWJsZSBkYXRhIHN0cnVjdHVyZXMgaW4gUHl0aG9uLlxcbi4uLlxcbiMjIDUuMy4gVHVwbGVzIGFuZCBTZXF1ZW5jZXNcXHUwMGI2XFxuXFxuV2Ugc2F3IHRoYXQgbGlzdHMgYW5kIHN0cmluZ3MgaGF2ZSBtYW55IGNvbW1vbiBwcm9wZXJ0aWVzLCBzdWNoIGFzIGluZGV4aW5nIGFuZCBzbGljaW5nIG9wZXJhdGlvbnMuIFRoZXkgYXJlIHR3byBleGFtcGxlcyBvZiBzZXF1ZW5jZSBkYXRhIHR5cGVzIChzZWUgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBsaXN0LCB0dXBsZSwgcmFuZ2UpLiBTaW5jZSBQeXRob24gaXMgYW4gZXZvbHZpbmcgbGFuZ3VhZ2UsIG90aGVyIHNlcXVlbmNlIGRhdGEgdHlwZXMgbWF5IGJlIGFkZGVkLiBUaGVyZSBpcyBhbHNvIGFub3RoZXIgc3RhbmRhcmQgc2VxdWVuY2UgZGF0YSB0eXBlOiB0aGUgdHVwbGUuXFxuXFxuQSB0dXBsZSBjb25zaXN0cyBvZiBhIG51bWJlciBvZiB2YWx1ZXMgc2VwYXJhdGVkIGJ5IGNvbW1hcywgZm9yIGluc3RhbmNlOlxcbi4uLlxcbj4+PiAjIFR1cGxlcyBhcmUgaW1tdXRhYmxlOlxcbj4+PiB0WzBdID0gODg4ODhcXG5UcmFjZWJhY2sgKG1vc3QgcmVjZW50IGNhbGwgbGFzdCk6XFxuICBGaWxlIFxcXCI8c3RkaW4+XFxcIiwgbGluZSAxLCBpbiA8bW9kdWxlPlxcblR5cGVFcnJvcjogJ3R1cGxlJyBvYmplY3QgZG9lcyBub3Qgc3VwcG9ydCBpdGVtIGFzc2lnbm1lbnRcXG4+Pj4gIyBidXQgdGhleSBjYW4gY29udGFpbiBtdXRhYmxlIG9iamVjdHM6XFxuPj4+IHYgPSAoWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuPj4+IHZcXG4oWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuLi4uXFxuQXMgeW91IHNlZSwgb24gb3V0cHV0IHR1cGxlcyBhcmUgYWx3YXlzIGVuY2xvc2VkIGluIHBhcmVudGhlc2VzLCBzbyB0aGF0IG5lc3RlZCB0dXBsZXMgYXJlIGludGVycHJldGVkIGNvcnJlY3RseTsgdGhleSBtYXkgYmUgaW5wdXQgd2l0aCBvciB3aXRob3V0IHN1cnJvdW5kaW5nIHBhcmVudGhlc2VzLCBhbHRob3VnaCBvZnRlbiBwYXJlbnRoZXNlcyBhcmUgbmVjZXNzYXJ5IGFueXdheSAoaWYgdGhlIHR1cGxlIGlzIHBhcnQgb2YgYSBsYXJnZXIgZXhwcmVzc2lvbikuIEl0IGlzIG5vdCBwb3NzaWJsZSB0byBhc3NpZ24gdG8gdGhlIGluZGl2aWR1YWwgaXRlbXMgb2YgYSB0dXBsZSwgaG93ZXZlciBpdCBpcyBwb3NzaWJsZSB0byBjcmVhdGUgdHVwbGVzIHdoaWNoIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzLCBzdWNoIGFzIGxpc3RzLlxcblxcblRob3VnaCB0dXBsZXMgbWF5IHNlZW0gc2ltaWxhciB0byBsaXN0cywgdGhleSBhcmUgb2Z0ZW4gdXNlZCBpbiBkaWZmZXJlbnQgc2l0dWF0aW9ucyBhbmQgZm9yIGRpZmZlcmVudCBwdXJwb3Nlcy4gVHVwbGVzIGFyZSBpbW11dGFibGUsIGFuZCB1c3VhbGx5IGNvbnRhaW4gYSBoZXRlcm9nZW5lb3VzIHNlcXVlbmNlIG9mIGVsZW1lbnRzIHRoYXQgYXJlIGFjY2Vzc2VkIHZpYSB1bnBhY2tpbmcgKHNlZSBsYXRlciBpbiB0aGlzIHNlY3Rpb24pIG9yIGluZGV4aW5nIChvciBldmVuIGJ5IGF0dHJpYnV0ZSBpbiB0aGUgY2FzZSBvZiBuYW1lZHR1cGxlcykuIExpc3RzIGFyZSBtdXRhYmxlLCBhbmQgdGhlaXIgZWxlbWVudHMgYXJlIHVzdWFsbHkgaG9tb2dlbmVvdXMgYW5kIGFyZSBhY2Nlc3NlZCBieSBpdGVyYXRpbmcgb3ZlciB0aGUgbGlzdC5cXG4uLi5cXG5Bbm90aGVyIHVzZWZ1bCBkYXRhIHR5cGUgYnVpbHQgaW50byBQeXRob24gaXMgdGhlIGRpY3Rpb25hcnkgKHNlZSBNYXBwaW5nIFR5cGVzIFxcdTIwMTQgZGljdCkuIERpY3Rpb25hcmllcyBhcmUgc29tZXRpbWVzIGZvdW5kIGluIG90aGVyIGxhbmd1YWdlcyBhcyBcXHUyMDFjYXNzb2NpYXRpdmUgbWVtb3JpZXNcXHUyMDFkIG9yIFxcdTIwMWNhc3NvY2lhdGl2ZSBhcnJheXNcXHUyMDFkLiBVbmxpa2Ugc2VxdWVuY2VzLCB3aGljaCBhcmUgaW5kZXhlZCBieSBhIHJhbmdlIG9mIG51bWJlcnMsIGRpY3Rpb25hcmllcyBhcmUgaW5kZXhlZCBieSBrZXlzLCB3aGljaCBjYW4gYmUgYW55IGltbXV0YWJsZSB0eXBlOyBzdHJpbmdzIGFuZCBudW1iZXJzIGNhbiBhbHdheXMgYmUga2V5cy4gVHVwbGVzIGNhbiBiZSB1c2VkIGFzIGtleXMgaWYgdGhleSBjb250YWluIG9ubHkgc3RyaW5ncywgbnVtYmVycywgb3IgdHVwbGVzOyBpZiBhIHR1cGxlIGNvbnRhaW5zIGFueSBtdXRhYmxlIG9iamVjdCBlaXRoZXIgZGlyZWN0bHkgb3IgaW5kaXJlY3RseSwgaXQgY2Fubm90IGJlIHVzZWQgYXMgYSBrZXkuIFlvdSBjYW5cXHUyMDE5dCB1c2UgbGlzdHMgYXMga2V5cywgc2luY2UgbGlzdHMgY2FuIGJlIG1vZGlmaWVkIGluIHBsYWNlIHVzaW5nIGluZGV4IGFzc2lnbm1lbnRzLCBzbGljZSBhc3NpZ25tZW50cywgb3IgbWV0aG9kcyBsaWtlIGFwcGVuZCgpIGFuZCBleHRlbmQoKS5cIl19LCB7XCJ0aXRsZVwiOiBcIjMuIERhdGEgbW9kZWwgXFx1MjAxNCBQeXRob24gMy4xNC41IGRvY3VtZW50YXRpb25cIiwgXCJ1cmxcIjogXCJodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3JlZmVyZW5jZS9kYXRhbW9kZWwuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiVGhlIHZhbHVlIG9mIHNvbWUgb2JqZWN0cyBjYW4gY2hhbmdlLiBPYmplY3RzIHdob3NlIHZhbHVlIGNhbiBjaGFuZ2UgYXJlIHNhaWQgdG8gYmUgbXV0YWJsZTsgb2JqZWN0cyB3aG9zZSB2YWx1ZSBpcyB1bmNoYW5nZWFibGUgb25jZSB0aGV5IGFyZSBjcmVhdGVkIGFyZSBjYWxsZWQgaW1tdXRhYmxlLiAoVGhlIHZhbHVlIG9mIGFuIGltbXV0YWJsZSBjb250YWluZXIgb2JqZWN0IHRoYXQgY29udGFpbnMgYSByZWZlcmVuY2UgdG8gYSBtdXRhYmxlIG9iamVjdCBjYW4gY2hhbmdlIHdoZW4gdGhlIGxhdHRlclxcdTIwMTlzIHZhbHVlIGlzIGNoYW5nZWQ7IGhvd2V2ZXIgdGhlIGNvbnRhaW5lciBpcyBzdGlsbCBjb25zaWRlcmVkIGltbXV0YWJsZSwgYmVjYXVzZSB0aGUgY29sbGVjdGlvbiBvZiBvYmplY3RzIGl0IGNvbnRhaW5zIGNhbm5vdCBiZSBjaGFuZ2VkLiBTbywgaW1tdXRhYmlsaXR5IGlzIG5vdCBzdHJpY3RseSB0aGUgc2FtZSBhcyBoYXZpbmcgYW4gdW5jaGFuZ2VhYmxlIHZhbHVlLCBpdCBpcyBtb3JlIHN1YnRsZS4pIEFuIG9iamVjdFxcdTIwMTlzIG11dGFiaWxpdHkgaXMgZGV0ZXJtaW5lZCBieSBpdHMgdHlwZTsgZm9yIGluc3RhbmNlLCBudW1iZXJzLCBzdHJpbmdzIGFuZCB0dXBsZXMgYXJlIGltbXV0YWJsZSwgd2hpbGUgZGljdGlvbmFyaWVzIGFuZCBsaXN0cyBhcmUgbXV0YWJsZS5cXG4uLi5cXG5Tb21lIG9iamVjdHMgY29udGFpbiByZWZlcmVuY2VzIHRvIG90aGVyIG9iamVjdHM7IHRoZXNlIGFyZSBjYWxsZWQgY29udGFpbmVycy4gRXhhbXBsZXMgb2YgY29udGFpbmVycyBhcmUgdHVwbGVzLCBsaXN0cyBhbmQgZGljdGlvbmFyaWVzLiBUaGUgcmVmZXJlbmNlcyBhcmUgcGFydCBvZiBhIGNvbnRhaW5lclxcdTIwMTlzIHZhbHVlLiBJbiBtb3N0IGNhc2VzLCB3aGVuIHdlIHRhbGsgYWJvdXQgdGhlIHZhbHVlIG9mIGEgY29udGFpbmVyLCB3ZSBpbXBseSB0aGUgdmFsdWVzLCBub3QgdGhlIGlkZW50aXRpZXMgb2YgdGhlIGNvbnRhaW5lZCBvYmplY3RzOyBob3dldmVyLCB3aGVuIHdlIHRhbGsgYWJvdXQgdGhlIG11dGFiaWxpdHkgb2YgYSBjb250YWluZXIsIG9ubHkgdGhlIGlkZW50aXRpZXMgb2YgdGhlIGltbWVkaWF0ZWx5IGNvbnRhaW5lZCBvYmplY3RzIGFyZSBpbXBsaWVkLiBTbywgaWYgYW4gaW1tdXRhYmxlIGNvbnRhaW5lciAobGlrZSBhIHR1cGxlKSBjb250YWlucyBhIHJlZmVyZW5jZSB0byBhIG11dGFibGUgb2JqZWN0LCBpdHMgdmFsdWUgY2hhbmdlcyBpZiB0aGF0IG11dGFibGUgb2JqZWN0IGlzIGNoYW5nZWQuXFxuLi4uXFxuIyMjIDMuMi41LiBTZXF1ZW5jZXNcXHUwMGI2XFxuLi4uXFxuIyMjIyAzLjIuNS4xLiBJbW11dGFibGUgc2VxdWVuY2VzXFx1MDBiNlxcblxcbkFuIG9iamVjdCBvZiBhbiBpbW11dGFibGUgc2VxdWVuY2UgdHlwZSBjYW5ub3QgY2hhbmdlIG9uY2UgaXQgaXMgY3JlYXRlZC4gKElmIHRoZSBvYmplY3QgY29udGFpbnMgcmVmZXJlbmNlcyB0byBvdGhlciBvYmplY3RzLCB0aGVzZSBvdGhlciBvYmplY3RzIG1heSBiZSBtdXRhYmxlIGFuZCBtYXkgYmUgY2hhbmdlZDsgaG93ZXZlciwgdGhlIGNvbGxlY3Rpb24gb2Ygb2JqZWN0cyBkaXJlY3RseSByZWZlcmVuY2VkIGJ5IGFuIGltbXV0YWJsZSBvYmplY3QgY2Fubm90IGNoYW5nZS4pXFxuXFxuVGhlIGZvbGxvd2luZyB0eXBlcyBhcmUgaW1tdXRhYmxlIHNlcXVlbmNlczpcXG4uLi5cXG5UdXBsZXNcXG46IFRoZSBpdGVtcyBvZiBhIGB0dXBsZWAgYXJlIGFyYml0cmFyeSBQeXRob24gb2JqZWN0cy4gVHVwbGVzIG9mIHR3byBvciBtb3JlIGl0ZW1zIGFyZSBmb3JtZWQgYnkgY29tbWEtc2VwYXJhdGVkIGxpc3RzIG9mIGV4cHJlc3Npb25zLiBBIHR1cGxlIG9mIG9uZSBpdGVtIChhIFxcdTIwMThzaW5nbGV0b25cXHUyMDE5KSBjYW4gYmUgZm9ybWVkIGJ5IGFmZml4aW5nIGEgY29tbWEgdG8gYW4gZXhwcmVzc2lvbiAoYW4gZXhwcmVzc2lvbiBieSBpdHNlbGYgZG9lcyBub3QgY3JlYXRlIGEgdHVwbGUsIHNpbmNlIHBhcmVudGhlc2VzIG11c3QgYmUgdXNhYmxlIGZvciBncm91cGluZyBvZiBleHByZXNzaW9ucykuIEFuIGVtcHR5IHR1cGxlIGNhbiBiZSBmb3JtZWQgYnkgYW4gZW1wdHkgcGFpciBvZiBwYXJlbnRoZXNlcy5cXG4uLi5cXG4jIyMjIDMuMi41LjIuIE11dGFibGUgc2VxdWVuY2VzXFx1MDBiNlxcblxcbk11dGFibGUgc2VxdWVuY2VzIGNhbiBiZSBjaGFuZ2VkIGFmdGVyIHRoZXkgYXJlIGNyZWF0ZWQuIFRoZSBzdWJzY3JpcHRpb24gYW5kIHNsaWNpbmcgbm90YXRpb25zIGNhbiBiZSB1c2VkIGFzIHRoZSB0YXJnZXQgb2YgYXNzaWdubWVudCBhbmQgYGRlbGAgKGRlbGV0ZSkgc3RhdGVtZW50cy5cXG4uLi5cXG5UaGVyZSBhcmUgY3VycmVudGx5IHR3byBpbnRyaW5zaWMgbXV0YWJsZSBzZXF1ZW5jZSB0eXBlczpcXG5cXG5MaXN0c1xcbjogVGhlIGl0ZW1zIG9mIGEgbGlzdCBhcmUgYXJiaXRyYXJ5IFB5dGhvbiBvYmplY3RzLiBMaXN0cyBhcmUgZm9ybWVkIGJ5IHBsYWNpbmcgYSBjb21tYS1zZXBhcmF0ZWQgbGlzdCBvZiBleHByZXNzaW9ucyBpbiBzcXVhcmUgYnJhY2tldHMuIChOb3RlIHRoYXQgdGhlcmUgYXJlIG5vIHNwZWNpYWwgY2FzZXMgbmVlZGVkIHRvIGZvcm0gbGlzdHMgb2YgbGVuZ3RoIDAgb3IgMS4pXCJdfSwge1widGl0bGVcIjogXCJCdWlsdC1pbiBUeXBlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjcgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvYnVpbHRpbnMvc3RkdHlwZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiY29sbGVjdGlvbiBjbGFzc2VzIGFyZSBtdXRhYmxlLiBUaGUgbWV0aG9kcyB0aGF0IGFkZCwgc3VidHJhY3QsIG9yIHJlYXJyYW5nZSB0aGVpciAuLi4gaW4gcGxhY2UsIGFuZCBkb25cXHUyMDE5dCByZXR1cm4gYSAuLi4gLCBuZXZlciByZXR1cm4gdGhlIGNvbGxlY3Rpb24gaW5zdGFuY2UgaXRzZWxmIGJ1dCBgTm9uZWAuXFxuLi4uXFxuIyMgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBgbGlzdGAsIGB0dXBsZWAsIGByYW5nZWBcXHUwMGI2XFxuXFxuVGhlcmUgYXJlIHRocmVlIGJhc2ljIHNlcXVlbmNlIHR5cGVzOiBsaXN0cywgdHVwbGVzLCBhbmQgcmFuZ2Ugb2JqZWN0cy4gQWRkaXRpb25hbCBzZXF1ZW5jZSB0eXBlcyB0YWlsb3JlZCBmb3IgcHJvY2Vzc2luZyBvZiBiaW5hcnkgZGF0YSBhbmQgdGV4dCBzdHJpbmdzIGFyZSBkZXNjcmliZWQgaW4gZGVkaWNhdGVkIHNlY3Rpb25zLlxcbi4uLlxcblRoZSBvcGVyYXRpb25zIGluIHRoZSBmb2xsb3dpbmcgdGFibGUgLi4uIG11dGFibGUgYW5kIGltbXV0YWJsZS4gVGhlIGBjb2xsZWN0aW9ucy4gLi4uIGlzIHByb3ZpZGVkIHRvIG1ha2UgLi4uIGVhc2llciB0byBjb3JyZWN0bHkgaW1wbGVtZW50IHRoZXNlIG9wZXJhdGlvbnMgb24gY3VzdG9tIHNlcXVlbmNlIHR5cGVzXFxuLi4uXFxuIyMjIEltbXV0YWJsZSBTZXF1ZW5jZSBUeXBlc1xcdTAwYjZcXG4uLi5cXG5tdXRhYmxlIHNlcXVlbmNlIHR5cGVzIGlzXFxuLi4uXFxuc3VwcG9ydCBhbGxvd3MgaW1tdXRhYmxlIHNlcXVlbmNlcywgLi4uICwgdG8gYmUgdXNlZCBhcyBgZGljdGAga2V5cyBhbmQgc3RvcmVkIGluIC4uLiBlbnNldGAgaW5zdGFuY2VzXFxuLi4uXFxuIyMjIE11dGFibGUgU2VxdWVuY2UgVHlwZXNcXHUwMGI2XFxuLi4uXFxuIyMjIExpc3RzXFx1MDBiNlxcblxcbkxpc3RzIGFyZSBtdXRhYmxlIHNlcXVlbmNlcywgdHlwaWNhbGx5IHVzZWQgdG8gc3RvcmUgY29sbGVjdGlvbnMgb2YgaG9tb2dlbmVvdXMgaXRlbXMgKHdoZXJlIHRoZSBwcmVjaXNlIGRlZ3JlZSBvZiBzaW1pbGFyaXR5IHdpbGwgdmFyeSBieSBhcHBsaWNhdGlvbikuXFxuLi4uXFxuIyMjIFR1cGxlc1xcdTAwYjZcXG5cXG5UdXBsZXMgYXJlIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhldGVyb2dlbmVvdXMgZGF0YSAoc3VjaCBhcyB0aGUgMi10dXBsZXMgcHJvZHVjZWQgYnkgdGhlIGBlbnVtZXJhdGUoKWAgYnVpbHQtaW4pLiBUdXBsZXMgYXJlIGFsc28gdXNlZCBmb3IgY2FzZXMgd2hlcmUgYW4gaW1tdXRhYmxlIHNlcXVlbmNlIG9mIGhvbW9nZW5lb3VzIGRhdGEgaXMgbmVlZGVkIChzdWNoIGFzIGFsbG93aW5nIHN0b3JhZ2UgaW4gYSBgc2V0YCBvciBgZGljdGAgaW5zdGFuY2UpLlxcbi4uLlxcbnR1cGxlKGl0ZXJhYmxlPVxcbi4uLlxcblRoZSBjb25zdHJ1Y3RvciBidWlsZHMgYSB0dXBsZSB3aG9zZSBpdGVtcyBhcmUgdGhlIHNhbWUgYW5kIGluIHRoZSBzYW1lIG9yZGVyIGFzIGl0ZXJhYmxlXFx1MjAxOXMgaXRlbXMuIGl0ZXJhYmxlIG1heSBiZSBlaXRoZXIgYSBzZXF1ZW5jZSwgYSBjb250YWluZXIgdGhhdCBzdXBwb3J0cyBpdGVyYXRpb24sIG9yIGFuIGl0ZXJhdG9yIG9iamVjdC4gSWYgaXRlcmFibGUgaXMgYWxyZWFkeSBhIHR1cGxlLCBpdCBpcyByZXR1cm5lZCB1bmNoYW5nZWQuIEZvciBleGFtcGxlLCBgdHVwbGUoJ2FiYycpYCByZXR1cm5zIGAoJ2EnLCAnYicsICdjJylgIGFuZCBgdHVwbGUoIFsxLCAyLCAzXSApYCByZXR1cm5zIGAoMSwgMiwgMylgLiBJZiBubyBhcmd1bWVudCBpcyBnaXZlbiwgdGhlIGNvbnN0cnVjdG9yIGNyZWF0ZXMgYSBuZXcgZW1wdHkgdHVwbGUsIGAoKWAuXFxuLi4uXFxuVHVwbGVzIGltcGxlbWVudCBhbGwgb2YgdGhlIGNvbW1vbiBzZXF1ZW5jZSBvcGVyYXRpb25zLlxcbi4uLlxcbkZvciBoZXRlcm9nZW5lb3VzIGNvbGxlY3Rpb25zIG9mIGRhdGEgd2hlcmUgYWNjZXNzIGJ5IG5hbWUgaXMgY2xlYXJlciB0aGFuIGFjY2VzcyBieSBpbmRleCwgYGNvbGxlY3Rpb25zLm5hbWVkdHVwbGUoKWAgbWF5IGJlIGEgbW9yZSBhcHByb3ByaWF0ZSBjaG9pY2UgdGhhbiBhIHNpbXBsZSB0dXBsZSBvYmplY3QuXCJdfSwge1widGl0bGVcIjogXCJCdWlsdC1pbiBUeXBlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjUgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvbGlicmFyeS9zdGR0eXBlcy5odG1sXCIsIFwiaGlnaGxpZ2h0c1wiOiBbXCJTb21lIGNvbGxlY3Rpb24gY2xhc3NlcyBhcmUgbXV0YWJsZS4gVGhlIG1ldGhvZHMgdGhhdCBhZGQsIHN1YnRyYWN0LCBvciByZWFycmFuZ2UgdGhlaXIgLi4uIGluIHBsYWNlLCBhbmQgZG9uXFx1MjAxOXQgcmV0dXJuIGEgLi4uICwgbmV2ZXIgcmV0dXJuIHRoZSBjb2xsZWN0aW9uIGluc3RhbmNlIGl0c2VsZiBidXQgYE5vbmVgLlxcbi4uLlxcbiMjIFNlcXVlbmNlIFR5cGVzIFxcdTIwMTQgYGxpc3RgLCBgdHVwbGVgLCBgcmFuZ2VgXFx1MDBiNlxcblxcblRoZXJlIGFyZSB0aHJlZSBiYXNpYyBzZXF1ZW5jZSB0eXBlczogbGlzdHMsIHR1cGxlcywgYW5kIC4uLiBvYmplY3RzLiBBZGRpdGlvbmFsIHNlcXVlbmNlIHR5cGVzIHRhaWxvcmVkIGZvciBwcm9jZXNzaW5nIG9mIGJpbmFyeSBkYXRhIGFuZCB0ZXh0IHN0cmluZ3MgYXJlIGRlc2NyaWJlZCBpbiBkZWRpY2F0ZWQgc2VjdGlvbnMuXFxuLi4uXFxuVGhlIG9wZXJhdGlvbnMgaW4gdGhlIGZvbGxvd2luZyB0YWJsZSAuLi4gaW1tdXRhYmxlLiBUaGUgYCAuLi4gaXMgcHJvdmlkZWQgdG8gbWFrZSAuLi4gZWFzaWVyIHRvIGNvcnJlY3RseSBpbXBsZW1lbnQgdGhlc2Ugb3BlcmF0aW9ucyBvbiBjdXN0b20gc2VxdWVuY2UgdHlwZXNcXG4uLi5cXG4jIyMgSW1tdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbm9wZXJhdGlvbiB0aGF0IGltbXV0YWJsZSBzZXF1ZW5jZSAuLi4gYnkgbXV0YWJsZSBzZXF1ZW5jZSB0eXBlcyBpcyAuLi4gYGhhc2goKWBcXG4uLi5cXG5UaGlzIHN1cHBvcnQgYWxsb3dzIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHN1Y2ggYXMgYHR1cGxlYCBpbnN0YW5jZXMsIHRvIGJlIHVzZWQgYXMgYGRpY3RgIGtleXMgYW5kIHN0b3JlZCBpbiBgc2V0YCBhbmQgYGZyb3plbnNldGAgaW5zdGFuY2VzLlxcbi4uLlxcbiMjIyBNdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbiMjIyBMaXN0c1xcdTAwYjZcXG5cXG5MaXN0cyBhcmUgbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhvbW9nZW5lb3VzIGl0ZW1zICh3aGVyZSB0aGUgcHJlY2lzZSBkZWdyZWUgb2Ygc2ltaWxhcml0eSB3aWxsIHZhcnkgYnkgYXBwbGljYXRpb24pLlxcbi4uLlxcbiMjIyBUdXBsZXNcXHUwMGI2XFxuXFxuVHVwbGVzIGFyZSBpbW11dGFibGUgc2VxdWVuY2VzLCB0eXBpY2FsbHkgdXNlZCB0byBzdG9yZSBjb2xsZWN0aW9ucyBvZiBoZXRlcm9nZW5lb3VzIGRhdGEgKHN1Y2ggYXMgdGhlIDItdHVwbGVzIHByb2R1Y2VkIGJ5IHRoZSBgZW51bWVyYXRlKClgIGJ1aWx0LWluKS4gVHVwbGVzIGFyZSBhbHNvIHVzZWQgZm9yIGNhc2VzIHdoZXJlIGFuIGltbXV0YWJsZSBzZXF1ZW5jZSBvZiBob21vZ2VuZW91cyBkYXRhIGlzIG5lZWRlZCAoc3VjaCBhcyBhbGxvd2luZyBzdG9yYWdlIGluIGEgYHNldGAgb3IgYGRpY3RgIGluc3RhbmNlKS5cXG4uLi5cXG5UaGUgY29uc3RydWN0b3IgYnVpbGRzIGEgdHVwbGUgd2hvc2UgaXRlbXMgYXJlIHRoZSBzYW1lIGFuZCBpbiB0aGUgc2FtZSBvcmRlciBhcyBpdGVyYWJsZVxcdTIwMTlzIGl0ZW1zLiBpdGVyYWJsZSBtYXkgYmUgZWl0aGVyIGEgc2VxdWVuY2UsIGEgY29udGFpbmVyIHRoYXQgc3VwcG9ydHMgaXRlcmF0aW9uLCBvciBhbiBpdGVyYXRvciBvYmplY3QuIElmIGl0ZXJhYmxlIGlzIGFscmVhZHkgYSB0dXBsZSwgaXQgaXMgcmV0dXJuZWQgdW5jaGFuZ2VkLiBGb3IgZXhhbXBsZSwgYHR1cGxlKCdhYmMnKWAgcmV0dXJucyBgKCdhJywgJ2InLCAnYycpYCBhbmQgYHR1cGxlKCBbMSwgMiwgM10gKWAgcmV0dXJucyBgKDEsIDIsIDMpYC4gSWYgbm8gYXJndW1lbnQgaXMgZ2l2ZW4sIHRoZSBjb25zdHJ1Y3RvciBjcmVhdGVzIGEgbmV3IGVtcHR5IHR1cGxlLCBgKClgLlxcbi4uLlxcblR1cGxlcyBpbXBsZW1lbnQgYWxsIG9mIHRoZSBjb21tb24gc2VxdWVuY2Ugb3BlcmF0aW9ucy5cXG4uLi5cXG5Gb3IgaGV0ZXJvZ2VuZW91cyBjb2xsZWN0aW9ucyBvZiBkYXRhIHdoZXJlIGFjY2VzcyBieSBuYW1lIGlzIGNsZWFyZXIgdGhhbiBhY2Nlc3MgYnkgaW5kZXgsIGBjb2xsZWN0aW9ucy5uYW1lZHR1cGxlKClgIG1heSBiZSBhIG1vcmUgYXBwcm9wcmlhdGUgY2hvaWNlIHRoYW4gYSBzaW1wbGUgdHVwbGUgb2JqZWN0LlwiXX0sIHtcInRpdGxlXCI6IFwiNS4gRGF0YSBTdHJ1Y3R1cmVzIFxcdTIwMTQgUHl0aG9uIDMuMTAuMjAgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMuMTAvdHV0b3JpYWwvZGF0YXN0cnVjdHVyZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiWW91IG1pZ2h0IGhhdmUgbm90aWNlZCB0aGF0IG1ldGhvZHMgbGlrZSBgaW5zZXJ0YCwgYHJlbW92ZWAgb3IgYHNvcnRgIHRoYXQgb25seSBtb2RpZnkgdGhlIGxpc3QgaGF2ZSBubyByZXR1cm4gdmFsdWUgcHJpbnRlZCBcXHUyMDEzIHRoZXkgcmV0dXJuIHRoZSBkZWZhdWx0IGBOb25lYC4gMSBUaGlzIGlzIGEgZGVzaWduIHByaW5jaXBsZSBmb3IgYWxsIG11dGFibGUgZGF0YSBzdHJ1Y3R1cmVzIGluIFB5dGhvbi5cXG4uLi5cXG4jIyA1LjMuIFR1cGxlcyBhbmQgU2VxdWVuY2VzXFx1MDBiNlxcblxcbldlIHNhdyB0aGF0IGxpc3RzIGFuZCBzdHJpbmdzIGhhdmUgbWFueSBjb21tb24gcHJvcGVydGllcywgc3VjaCBhcyBpbmRleGluZyBhbmQgc2xpY2luZyBvcGVyYXRpb25zLiBUaGV5IGFyZSB0d28gZXhhbXBsZXMgb2Ygc2VxdWVuY2UgZGF0YSB0eXBlcyAoc2VlIFNlcXVlbmNlIFR5cGVzIFxcdTIwMTQgbGlzdCwgdHVwbGUsIHJhbmdlKS4gU2luY2UgUHl0aG9uIGlzIGFuIGV2b2x2aW5nIGxhbmd1YWdlLCBvdGhlciBzZXF1ZW5jZSBkYXRhIHR5cGVzIG1heSBiZSBhZGRlZC4gVGhlcmUgaXMgYWxzbyBhbm90aGVyIHN0YW5kYXJkIHNlcXVlbmNlIGRhdGEgdHlwZTogdGhlIHR1cGxlLlxcblxcbkEgdHVwbGUgY29uc2lzdHMgb2YgYSBudW1iZXIgb2YgdmFsdWVzIHNlcGFyYXRlZCBieSBjb21tYXMsIGZvciBpbnN0YW5jZTpcXG4uLi5cXG4+Pj4gIyBUdXBsZXMgYXJlIGltbXV0YWJsZTpcXG4uLi4gdFswXSA9IDg4ODg4XFxuVHJhY2ViYWNrIChtb3N0IHJlY2VudCBjYWxsIGxhc3QpOlxcbiAgRmlsZSBcXFwiPHN0ZGluPlxcXCIsIGxpbmUgMSwgaW4gPG1vZHVsZT5cXG5UeXBlRXJyb3I6ICd0dXBsZScgb2JqZWN0IGRvZXMgbm90IHN1cHBvcnQgaXRlbSBhc3NpZ25tZW50XFxuPj4+ICMgYnV0IHRoZXkgY2FuIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzOlxcbi4uLiB2ID0gKFsxLCAyLCAzXSwgWzMsIDIsIDFdKVxcbj4+PiB2XFxuKFsxLCAyLCAzXSwgWzMsIDIsIDFdKVxcbi4uLlxcbkFzIHlvdSBzZWUsIG9uIG91dHB1dCB0dXBsZXMgYXJlIGFsd2F5cyBlbmNsb3NlZCBpbiBwYXJlbnRoZXNlcywgc28gdGhhdCBuZXN0ZWQgdHVwbGVzIGFyZSBpbnRlcnByZXRlZCBjb3JyZWN0bHk7IHRoZXkgbWF5IGJlIGlucHV0IHdpdGggb3Igd2l0aG91dCBzdXJyb3VuZGluZyBwYXJlbnRoZXNlcywgYWx0aG91Z2ggb2Z0ZW4gcGFyZW50aGVzZXMgYXJlIG5lY2Vzc2FyeSBhbnl3YXkgKGlmIHRoZSB0dXBsZSBpcyBwYXJ0IG9mIGEgbGFyZ2VyIGV4cHJlc3Npb24pLiBJdCBpcyBub3QgcG9zc2libGUgdG8gYXNzaWduIHRvIHRoZSBpbmRpdmlkdWFsIGl0ZW1zIG9mIGEgdHVwbGUsIGhvd2V2ZXIgaXQgaXMgcG9zc2libGUgdG8gY3JlYXRlIHR1cGxlcyB3aGljaCBjb250YWluIG11dGFibGUgb2JqZWN0cywgc3VjaCBhcyBsaXN0cy5cXG5cXG5UaG91Z2ggdHVwbGVzIG1heSBzZWVtIHNpbWlsYXIgdG8gbGlzdHMsIHRoZXkgYXJlIG9mdGVuIHVzZWQgaW4gZGlmZmVyZW50IHNpdHVhdGlvbnMgYW5kIGZvciBkaWZmZXJlbnQgcHVycG9zZXMuIFR1cGxlcyBhcmUgaW1tdXRhYmxlLCBhbmQgdXN1YWxseSBjb250YWluIGEgaGV0ZXJvZ2VuZW91cyBzZXF1ZW5jZSBvZiBlbGVtZW50cyB0aGF0IGFyZSBhY2Nlc3NlZCB2aWEgdW5wYWNraW5nIChzZWUgbGF0ZXIgaW4gdGhpcyBzZWN0aW9uKSBvciBpbmRleGluZyAob3IgZXZlbiBieSBhdHRyaWJ1dGUgaW4gdGhlIGNhc2Ugb2YgYG5hbWVkdHVwbGVzYCkuIExpc3RzIGFyZSBtdXRhYmxlLCBhbmQgdGhlaXIgZWxlbWVudHMgYXJlIHVzdWFsbHkgaG9tb2dlbmVvdXMgYW5kIGFyZSBhY2Nlc3NlZCBieSBpdGVyYXRpbmcgb3ZlciB0aGUgbGlzdC5cXG4uLi5cXG4jIyA1LjQuXFxuLi4uXFxuLiBTZXQgb2JqZWN0c1xcbi4uLlxcbiMjIDUuNS4gRGljdGlvbmFyaWVzXFx1MDBiNlxcblxcbkFub3RoZXIgdXNlZnVsIGRhdGEgdHlwZSBidWlsdCBpbnRvIFB5dGhvbiBpcyB0aGUgZGljdGlvbmFyeSAoc2VlIE1hcHBpbmcgVHlwZXMgXFx1MjAxNCBkaWN0KS4gRGljdGlvbmFyaWVzIGFyZSBzb21ldGltZXMgZm91bmQgaW4gb3RoZXIgbGFuZ3VhZ2VzIGFzIFxcdTIwMWNhc3NvY2lhdGl2ZSBtZW1vcmllc1xcdTIwMWQgb3IgXFx1MjAxY2Fzc29jaWF0aXZlIGFycmF5c1xcdTIwMWQuIFVubGlrZSBzZXF1ZW5jZXMsIHdoaWNoIGFyZSBpbmRleGVkIGJ5IGEgcmFuZ2Ugb2YgbnVtYmVycywgZGljdGlvbmFyaWVzIGFyZSBpbmRleGVkIGJ5IGtleXMsIHdoaWNoIGNhbiBiZSBhbnkgaW1tdXRhYmxlIHR5cGU7IHN0cmluZ3MgYW5kIG51bWJlcnMgY2FuIGFsd2F5cyBiZSBrZXlzLiBUdXBsZXMgY2FuIGJlIHVzZWQgYXMga2V5cyBpZiB0aGV5IGNvbnRhaW4gb25seSBzdHJpbmdzLCBudW1iZXJzLCBvciB0dXBsZXM7IGlmIGEgdHVwbGUgY29udGFpbnMgYW55IG11dGFibGUgb2JqZWN0IGVpdGhlciBkaXJlY3RseSBvciBpbmRpcmVjdGx5LCBpdCBjYW5ub3QgYmUgdXNlZCBhcyBhIGtleS4gWW91IGNhblxcdTIwMTl0IHVzZSBsaXN0cyBhcyBrZXlzLCBzaW5jZSBsaXN0cyBjYW4gYmUgbW9kaWZpZWQgaW4gcGxhY2UgdXNpbmcgaW5kZXggYXNzaWdubWVudHMsIHNsaWNlIGFzc2lnbm1lbnRzLCBvciBtZXRob2RzIGxpa2UgYGFwcGVuZCgpYCBhbmQgYGV4dGVuZCgpYC5cIl19XSIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ3ZWJfc2VhcmNoIiwiaWQiOiI2ZTUxMjVhYy0zMTY0LTRhNzYtOWM1Mi1hYzM0NjBjZTM2ZTQiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJzdGF0dXMiOiJzdWNjZXNzIn0seyJjb250ZW50IjpbeyJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX3NrZXB0aWMiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QTZGNGNDTjV5aEQ0Q3JzOU0iLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjB9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlc2VhcmNoZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtM2NkOC03OWYxLTg4YTEtY2U2Y2VlMjk0ZTc5LTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fc2tlcHRpYyIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsInRvdGFsX3Rva2VucyI6NzQxMSwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19fSx7ImNvbnRlbnQiOiJTdWNjZXNzZnVsbHkgdHJhbnNmZXJyZWQgdG8gc2tlcHRpYyIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ0cmFuc2Zlcl90b19za2VwdGljIiwiaWQiOiIzODkwNThkMS0wODNmLTQ2MzItYmJjNS0wOWJmZDNhMGZmZDIiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMVhqajNhUmRXeWhCSmZQbVRKQnhRYTkiLCJzdGF0dXMiOiJzdWNjZXNzIn0seyJjb250ZW50IjpbeyJzaWduYXR1cmUiOiJDQVFTMVFnS0VBZ1NHQUk0QVVJSWRHaHBibXRwYm1jU0RONlRmVTZORE05NzFsRWJ6eG9NdlJVQTFKOW94M2ZKUVlUOUlqQXJDUVFHSEJQNHBSSFBhdlh6UmxiTWJhWUhDNTdZaitHYnhncjBoZWx2ZDJPSUwvbzZSYnQ0UEZBM0ZhSUZVbGdxOGdjN0tRSTlGdEdudlNBa0xCUnpJc1VwLzJkNVJkMnpnRXNma0ZWZVhzbjhXWVlaa2luQVFWVnk2QTdCM0xhRUpXMHhiL3g4OERpNjdmZWR3eDBRK0ZsWnR3Y21UM0RjYWExMUp2ZXlIUnIzZG0rekdTWlA2Q1hlWE5KOG5yVFo3VzFZUlR5c0Q2dzdvN0xwOGgxUndxNGY0bzhqK1FVZlkwdmplK3pKWnN4SFBtUU50M3lrZUtoOTloZ242ZGJpejYvRUhxbWJIalNBdTFNNFNxRURmcUlLVGhIWWVuYW1BWm1jUTRYQU9vNm1kUTYrNzdWZ3BWMWxDMS9rNTJJaVVvSmprR2xRcm5MQ3Z1dGlJN0tOK3NnSzhjMisyS0NKclBSQ3ZWVitCa1N0dlA1aldXcXp5dHBLUStuSHpoTDQ0OE9ySUE5Z2RKQzM5QzhlRHJYZVJuSTd0NEZxbGtYR29NbFpBVjlVTWNyUUhSeE9NaTh0T3lUemk5b3lCRkRUU3NRK0xKcWVyMHR6MUZ0OWdlazZ2emc1MFNwVkFGUWRMRVJ2OFIxWXFNYWVJK3hzdlRBRVc5TVJndlJNa3pMdXpSVDJndXczakQrRmppcDM3eGdLNVFJMFIrQ3NPQW1RUG9UWml6emNJeUFVQXVDSkZDZ3EvZ0QvQ2liTHhveW1pVlVJMWFuOVNudDNLcE5Sb1dkdldJbmUzM1YwcHY4UEhnOXlXMkp1TE9xUUdpbExDc0svUTNvUXIzdXBFTVh4WEdqQ0w3V1VpenZSWkdGRUVWK1ZwbFl0N3Y0dEtaTWo1cGszdmRlTTBNSjVYWmc3UHZVc1J6eWN4Y25yVDNLbm9jM3FNK3R0cVpmVHNiOGQ2VS9wUWlmcTdHdWFoRk9IcnZyb3FnSkxqKy84MVl5MXBaRmtqZkpnWTBYa2x6QW5BNkNGcS9ZVDBneGJWK1RINUlTK1dhWU9VekszNlM4czVxcU13aG5ndjRJekUzY3RYWHFuaElaWE56bnlWQnFiWWEvR3gyYkNqY0VqMm41UnlHWVJTLytNY3VsZ0xCem5ROU1rRzJEN1FQM01xL253SFhLTUlhTFM4Vks4aEczZDByQWpsdm5hdVhTaE5ySnh0a2o0cWt3bnhENExyRWprMXVlK1BMY2JMcVlXd0FyOG4wcys0MWpyc0lQVnl5Szl2RmFFWnJBOUthQnhrSnlpcXg1MEdaTm43Y2t4K21rSTE4Z0g1Mml5VlB0VThGS01YanVnQ2w2bVBMaUhZaURRZCtHNjNMdWRtT0t5czlpdFZuQkRCTk1QMmIvSTcrYklWUmxoZUdhWldyNk1BVEtsODZCM3krMGt1T3JMUk15V2NkaWJjMmlRa1ptKzhmN2RUVXdiS2JCSnNLT0ZZNzMvOG5sTC9KaVlwano2blVJaytJcVNqYUZ5SzZYRmxDY3VrV3BXSHBESm5TdmJFemV5N3FIeUNxSitJK29uOGlQOEdPdGVtcFFhUzAvNGtaR1N3bHJFNnhPajZFd0dwZmpiRFpLSGtQLzJSQWROWVBRcTN6N2JkVkpNSk5uRk16NmUzN216TXBDQmlod1BkU0ZUUkUzU0NZNjZ3dlRnSnpHQ1V5aEhiU2k1aTFhenpPWGQ4dUhDU3BULzZMMW82VlUwcGpvUjhLYWE0d0NXSEdmN1AvV0VkK2F2eXAwMkpudTFjbXBXMCtHcSt2SzloMHRkYjJJQ2xNL2VOZmRvdVFQK2VwOE1KVWpyYURSSUNtQUpRWTVvYlM3MXZuaU9vK3JlYUZ5MHpSZ0IiLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsic2lnbmF0dXJlIjoiQ0FRUy9SRUtFUWdTR0FJNEFVSUpibUZ5Y21GMGFXOXVFZ3dGaDNBVkpaUDNzOHkxSHEwYURHNzZ1aEhPTmFTY1hBR1NoaUl3R2dqTFhIVXgxeVpya0xQbGpqelRPUXljcExKaUtWd1hjeG0vRXpLSm0xczhNNVd4dVJFV0VsZFhjb2FOMC9tc0twa1JNVCtlTGI1aWg5ckFIVUxUb21VTnNVd0pldTBqckplNEdMYXp5N3NQNUt0akVPRUJLUXNYVWZvUTdmRGtaT1FVSFppOXp6UU40aEZObVlKVWYzT1ZxZjlUUU5kQzErbS8vSEFaUGZXbUF5Nkh0RHZtN2tnQkprQ0VvaUZubTd0bi9QWDFoWEdQUmdXYzZCVFhVTXIyV0E4YUt5cWdnUlViTUgyK0pZdjVpV1pkZENjMXVwMU5icjNzRjdXUGNvdDlaQmh5SFFYcjY5MnplSms2U0pneWdJVnJBU2JNbHkyYkJ4VFdKQjYyM2dWZ3pwQ21WU0xaRnBrS1hnUGNwOGhHeURLT3ZGNlNpUVNIcUdSeFFvZnI3VnMxYVBoZlppeFJPSkdEK01scmtnZ1ZBbkdNeVlJRFVacGF2dENlaVUxSm1CU3owMDg0YlhQdFQvdG5wc0tPblNQWVpRbzNCMEJYS2JxQS9Xc0tuZzgvVjNaOFV1YWpvNklWWjJoZ0ExV0RkdXFRT1FrRXhHVTZwRnVMaGViSWp1V3hTTkkvRGZmdlIvL0xOcUNmdmRuZjBodm9QdER4ZngvU2F3SXg0L3NwcTl4YndGekh0TGdvSGcxRjJ3Rnc3Y2xQRGxnMVB5RC92MnlKRzNWOVQ4R0w2akdQRTZyaGZpbC91NEhOdmY3QlcwZFF6Q1RUWGNxWnk0bkJ5eTArcCtTN1p4Zk1sNEtweGEyZ09oaFNOamZwZnVYMFFwTDRrTUU4SjFubGlGTjFkOEtxRVB1REkxOEJRSFVoRC9VZlkyOW9BMHg1MTBGak0vQnNMWjRuNXNwcGtvSWk3Q0ZvUXEyYUFLVk5mQzFLaWxoSXBSRCsxZHlEdFpRa2xOOGdacE9FU0h3Nk1MMVR0VTB5ZkFjYm1xb3hKNmhoanp3SDZDTXNUUUVFeThNYlJCTStRS0trSVJkUkNQSEdGVzJMa3VSNTArSjBwRi90cjZwcVZ2SmVvemZpTW5yRWlsQjI3VFpQNG5LVEpHOHJkLy92Q1dlbjB5N0NBLzhkQko5Z2RwNXR4N05WQTQ1azFnZGN4RVIxZ1lvdU5YM24xdkczL0IxRjQrOTN3WFc5TXFvNlVzNTlUUW1yYjlOcWE3cFNRTlNySDA2dzFHeHlCQWxrRmZxQWxhZmsxNmFNcHE0MTZUSllwR3k0M1dDVWlDY0xXbGhpV2d6MnNnT0xBWFA5YTV3ZVdBS1JDOEo2amtjVWtEZVhuVytIRlNpUE02KzlCbzZrVmhMVWhONXJjNG1IWk9acEY3cHRQcHNRTjRYQ3FMUHNxcFJILzhvNVhweUM2Wm5lVGVGMkV4dGpod1pWalhEd01iSXpWWUlidzF5MlBQR3c4ZEM3cGM0c0lWU25JNG9RQUgwdjY1MGdoZmhtTWV2V1c0aDRQeWxidy9ERzRmZGVUMys4ejBmOE1PU1R0ZmlweDA1L1F0dEhsQXZPRFJ4YTV5REN2T3o2bjNmMUJPME4vNE1iR3lPTTI3cVc0eDhtQlZvcnlVWldmc21oZmkwL0dmTnZCOCt5bFRHYllOWDI3T2NFRjVXWnROcWJXRXk3VjVHYm1aVVN4c3BjZzdGQlozajMvM0w3bXV2WlhvWmkxZjVlcnE0eTNsU0grb0Y3cVBGbnZpZXlMT0N3dWJjUXkrb3lvd2o0Y0QwaWRSZWNucCtzKzUyRDcrbXpGMWdwVytmK2NKYXNveGlnYnhrT2xvUzR5ZWlLdmdNNG5XU3BHRWoxMlJQeDVvODBFbXppWE45dDR6SnpXMWh0QTVoWEpKZUZ5bXBNWXR5Q1VDZXZSV1ZtclJZa3RRN1VuQ2E2dEwvQVZQaTFuaTVYQ1hIZkxPdXFmSzVLTFl4andWdGRoaGZtQ0x2cGFLVk5DRU9DZjRuTkdIcUQ5OHdVYjBlaldOd0RZQm5KR2tCUnc5UlZzcGZ3TmRvV29WY24ycXY4eXdHVXA3eWMvc2syTHBJNlZ6aVJ5dldxYkdORzFaSnFWVnV0UmM0NitzT0U0VlNlUzIvQ1ROS05hNk5NQ2YvaHh4YVVWc1lmS2RQK1MxTGM0aWFuS3Awc1V1Z1BwbXRveWRDMENQMlJ3am5ITGNuenhDbnZxeGxMUVdYTU5QVHN1MnlCY0hsV0pMdGNtZGcvTWNMYWd5N2w1a0c2c043WnhKTEQva0F4OEU2dXFvaFArSy9qTVNyWXVRSm5ocjR0ZjRiaVdGWTNKemYvS3BBWXlWU3ErcGJmRktYTWJMOW5IRW9aUVQxNVd5YWJkNkRNQXEzUVpPdGhNNXBVemROcVVYa2NySTFQd2pBU0FnNGRWVS8ybys5OG1UWG55aFA3VmxFa1RuZGRwd3lKRitZQ0NjMDFwcWE2Wlg5OXBuUitZT3BJcmI1RHRQY0txMHQ1Y0ZDRHlReE4xbFV1cVpjWXVqdlgvR0M3KzZJcFJUei9Oa0VZLzVjbnRPZlpKeWQ2U2tVeC9KUjVBSklSUENOZWliMHJjV25uRm4wWEs4czIyeDQwd0xqRXR1ZlhETzkreXJhZjRrSHhsQkkzU0IwbWVNamVwWDUwQ0poQXg3TmVra1JGbndvZWNMZnFJeXJqWHJnQVpzVE1QaVg5NHNuamRyemlzQVh0QkthbnVsaWxTeE9mVzJIU21mbmswTDJHWEhKSjNTK3ZDYmdSRW1sOWRla2ZtSGhtd0VZdHYza2ZodGg3RVJJd1ZUOGo2OU90SUJDbWVUSUp1QTdvNzNQWGMxTEoyd2h1Wks3RlplNk5UT3M2MU1QN0pWbEljNnRiaHRPQmszTlhVOHBCUE9DWTZRNTVkNjNGdHBVVS9LQ2JRMEsyV1E5bzVqTkd3Tk5KNkN3NUZEQ3QreDVZSmVQMWQyUXpEU2lxK2NTWnF3cUNaVmNOb0FmdEdHemdyUlo0dmtwYlAweFFaSEN0V3NVd0hWVGpyWTROZlJEakhkVlBSbjhKOVh0b29jL2hJV2txekZhY3pZVGxhcHUyUkNKcWU4YUVvM2p6V1pDRUo3QWlCekJZcmFZRGdPZmVpUXllSlVzYmJYSGRHS2lpdzIyQmRwNE0rWXo2NzFNWjBpZTlFV1JrczBRMkRIR1VUbmU5UzR0QUFKUEdiVWY0eHRDTW9KNDBRNFFXMDVRTFNaeTN3TkZBVUZZbVhFNEVDREZCOCtJRWVORkZGL3RnQW5maDhHdkZoLzF4WStMRStvek1taW5qU1J3aHEwOXpRQUVrTkZ5dTBJS2d2RGt5T0kraWNjRjdkb1dMVFVhc1B4TEgxeEdQQlNLa2VXQ25Tb1gvNEMyYzlkdTY2QmJSWGFtSHFhZStWQ2lTNkJOOTUzaVlLT3U4ck1rbmVXK1RGalYwQ3pBZjhQTkc5TEJheVVnWTVVdzl4MFNhcDZ6STRQcGFaS0g0ZDlrdGtGVSs5MXlCYk41U1J0ZGQ4L0VRYXRKWG1CTmZ3N2tScmxsK0xqd1p3ZVdMRWIwalQxUnBHdURxSExkTFRNTWdvd1NjenJwMnpDc0pkUUgvc2VhWXJwd2tDRlI4ZFJqTTdKUlVrVmExQTBTdmRaQVg3NXZ1QnZ2TEJ6TjJjK1JidDVvcXk5M2xxSUJJaktiN3cyVWtSVGI0cEJXY05LTlBVZ3QzYXovUHhReEVhc2FsdGRtdXl2c1hZYnVyM1ZQTm44SnpOLzZKNU4rUUNuejU3MVRjY2FwQ21rUHZGRStnYXlYVStVRjFWS1l5RmNVdmxldjdsc1FsbWpxeksyUUE4WDdRM1R6RmFwcWh2SktsdDdkekJIcmFxWkJnUGdiOU40b0tOYXlpOEZaVDcxK2thWWhJaEZyRVNLWVJIZkhrajVuM2tmaGdMeSt4K2pMRGJLeE1nZ2tnSG5KejlSdUVIWlhCV3RrWUFRPT0iLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsiaWQiOiJ0b29sdV8wMUg2ZlY4SnZSSk52WHk0N2VSbmQzakgiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6e30sIm5hbWUiOiJ0cmFuc2Zlcl90b192ZXJpZmllciIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHdBTVJkUzIxRmVKZnpRaE0zcyIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjo3Mzk2LCJvdXRwdXRfdG9rZW5zIjo3NzAsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjczOX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoic2tlcHRpYyIsImlkIjoibGNfcnVuLS0wMWEwZmUwMy00YWU5LTc2YzAtODlhNi00ZjBiMTE0ZTMwMzAtMCIsInRvb2xfY2FsbHMiOlt7Im5hbWUiOiJ0cmFuc2Zlcl90b192ZXJpZmllciIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxSDZmVjhKdlJKTnZYeTQ3ZVJuZDNqSCIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzM5Niwib3V0cHV0X3Rva2VucyI6NzcwLCJ0b3RhbF90b2tlbnMiOjgxNjYsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjczOX19fSx7ImNvbnRlbnQiOiJTdWNjZXNzZnVsbHkgdHJhbnNmZXJyZWQgdG8gdmVyaWZpZXIiLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7fSwidHlwZSI6InRvb2wiLCJuYW1lIjoidHJhbnNmZXJfdG9fdmVyaWZpZXIiLCJpZCI6ImMwNjQ1NjNhLTk3NGYtNGYwZi1hYjRhLTA4MGU2M2MwMWNmNSIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxSDZmVjhKdlJKTnZYeTQ3ZVJuZDNqSCIsInN0YXR1cyI6InN1Y2Nlc3MifSx7ImNvbnRlbnQiOlt7InNpZ25hdHVyZSI6IkNBUVM5Z1VLRUFnU0dBSTRBVUlJZEdocGJtdHBibWNTREdGeUoxTVhvWStBaTZOa2J4b01SZDJUclVmVVU3V3JQcEEySWpEZ3k4ZFVwbGNaS2M3RG5Kd05MVEJmSDVVTlIrbkduYWtTUFFpYThVVkl6cmprT25KMmZMcldVc0Eyb0VPOHlSc3Frd1hra0RDc3loQjk3ZHdqNTdSTXQ5MVh6Z1doTDlsdU5FR085MnlXMHJORkdvTVNVVk94UElyRmM1Ump5cmhLRWMzKzFSbnB4Q2t5bHErTE5sUTVORnhMbjZ2MmNGNUR6cXB2QkhOUjdYQWlnK3VySklVM2dYeWRDa2FHWlpEZXRKdFFPVU9YZ1ppOXo5MTAwTnBkQUVrWERvMklDSENHVEdwVmMwSi9wYlh4V1JCeGI2QjEvR2wwWWpuNjhWNkhsZXNIN0lvQzdHUi8zSHdSdTlOU0RCRzR0dGZRakVXY2crUGVBZWE0Um43anp4K1RtOUg3TDFqb1RLVmdEYlFnNWlLTUxmanZQcWxua3NDTHRYT3Q4alNJUzVPWUxON2EvN1RYNi93NWQzNHZudzh2UERtVTFVWWkwUTcycVVXaFVhMnZ3OE9YTnBjS0w3QnAwbE5mQlM4cnZIWSt2Qlk4L2hhQW9UTDN3dkxGVTFmVCs0ei92QTNCY3NpZ1pEWWxmSmVEWWN4WG1SdXF4enhFR3BYQ1JlOXMxSFd0SUQrNDFwSHU2bHBaSGtYYWdocGM2VFpITHhOd2NWaFRiNmZNUTdRbysyTDZQdmtsaDFtMzJwZW9keGVnMllpUGhkcGwzdy94a09FdTUvSkVGN1pCeHBkVUwrdTN3a081cFVsc3FmZ1g3dWh6djdIQzJXcFNXVmltcndpUXdRT1V4MCtKUHJMdHcrbFlmcTdJM2pydW8wR1cwZ3VXdm51ZjdKTTNZTGo4NHErSmdIb21uU1Nabm5abXJMMFVhUnZyVnlMbzg3N0YzOWNjTFM3WG9abm51aThKNFA1OFpUbWlMa0VKZUdjeDFJdWFnMmUzMzMzOU83WWV3LzU5dExiUXRJR2g5VldNd0hCbkZ4MzlTOC80TEVGcks1SGxkUFFoT3Jsb3lUdGtSczY2aVFSS3R4TUtTMFZJNlFUS1pEQWJzN2E3SDF5QnYrbUppOVhnNHVLbXlVNnFubjd6RUtqalkyYklsQ3dleng0TExHUDVIRDNacjZmWnNtZEcxVUh6RHNCdllHMm9DSTBvcUVLTSt2YWxzVDZoVThNUmpiUUJEL0pKOEpKTi9pQkdsaEJBVUhvMFVtaGh0UjJldVRWcFpXbE1uaG1wWEFkS0RYU2ZQZGFQb2hnQiIsInRoaW5raW5nIjoiIiwidHlwZSI6InRoaW5raW5nIn0seyJpZCI6InRvb2x1XzAxWEVBdWhRSENCZHlDd3R5bVp3RmZEaSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX3JlZF90ZWFtIiwidHlwZSI6InRvb2xfdXNlIiwidG9vbHNldF9uYW1lIjpudWxsfV0sImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnsiaWQiOiJtc2dfMDExQ2Zkd0FzYWJEcXVlZ0hpNllVcENuIiwiY29udGFpbmVyIjpudWxsLCJkaWFnbm9zdGljcyI6bnVsbCwibW9kZWwiOiJjbGF1ZGUtc29ubmV0Iiwic3RvcF9kZXRhaWxzIjpudWxsLCJzdG9wX3JlYXNvbiI6InRvb2xfdXNlIiwic3RvcF9zZXF1ZW5jZSI6bnVsbCwidXNhZ2UiOnsiY2FjaGVfY3JlYXRpb24iOnsiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MH0sImNhY2hlX2NyZWF0aW9uX2lucHV0X3Rva2VucyI6MCwiY2FjaGVfcmVhZF9pbnB1dF90b2tlbnMiOjAsImluZmVyZW5jZV9nZW8iOiJnbG9iYWwiLCJpbnB1dF90b2tlbnMiOjc1MDksIm91dHB1dF90b2tlbnMiOjg4LCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjo1NX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoidmVyaWZpZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtNjY4Mi03ZDIxLThjMTUtZmZiY2U5NDIyYzlmLTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fcmVkX3RlYW0iLCJhcmdzIjp7fSwiaWQiOiJ0b29sdV8wMVhFQXVoUUhDQmR5Q3d0eW1ad0ZmRGkiLCJ0eXBlIjoidG9vbF9jYWxsIn1dLCJpbnZhbGlkX3Rvb2xfY2FsbHMiOltdLCJ1c2FnZV9tZXRhZGF0YSI6eyJpbnB1dF90b2tlbnMiOjc1MDksIm91dHB1dF90b2tlbnMiOjg4LCJ0b3RhbF90b2tlbnMiOjc1OTcsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjU1fX19LHsiY29udGVudCI6IlN1Y2Nlc3NmdWxseSB0cmFuc2ZlcnJlZCB0byByZWRfdGVhbSIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ0cmFuc2Zlcl90b19yZWRfdGVhbSIsImlkIjoiOTgyYzAxMjYtZTZhYi00NThhLTkyMmUtN2IyNjZlODNjMmIyIiwidG9vbF9jYWxsX2lkIjoidG9vbHVfMDFYRUF1aFFIQ0JkeUN3dHltWndGZkRpIiwic3RhdHVzIjoic3VjY2VzcyJ9LHsiY29udGVudCI6W3sic2lnbmF0dXJlIjoiQ0FRU3dnY0tFQWdTR0FJNEFVSUlkR2hwYm10cGJtY1NET1JYZ2U5dUwxODMyUk1Rd0JvTWpRd0F3QUhiOWlQMW9qUEdJakREU2NhbDQ4NmJlQ0pidEc4L0QyWTlnOVM1eElQZmpvSGcvZHh3WDVIeXBTUUVCYmpGaVRTYlBFQ1hTRnpWNllJcTN3YkxjbXlQYnZ1c0duRGV4Rmd4KzNzSVh6dnF5RlYvNjl4aGloTW5TcGZUQ0h5MCswelN1MVdwWVUvV1VwSWZvYVNYVGNUYTFxa004eDhFay95LzFqa0tNWlVmREZhOTN1aFVKeE9DNCtRZ1BXQmwvK1h5MnQ4MkwyeC9lYnE3UUxRVHF0UjBqWGVhVVJRbTNDbzZKdk9nV21Edk1wRWRUZVRXRTNmRGgxdHp6VktzZmx1bTRkODliNkNhS3RuOG5sUWQ3UmhOOTl2TlFNUUhHNVY0T3VWTmRySFBaWnBGT3VoZGVqc01GV1h5Qis1NXNsR0FkOHdFWGdGS2JJL2tuT1hWR3pML05ERjhHdHkxdE5abHUyZmRTQ0FzWVdNc0ZRUDFjYndMZVFHc3p5WHpKTVZaSjJJOXhCUGt5ejFIT1hDUHloNUYrajJnUlRQaWtWQjNBUkM2dGZCL2xEU1VlS0JWWlBRUzhwWS9CNGVDcytJamphQk5XcnVMemZxQ3NjNnhMMEN1UVBTWXlRWGFZRmpZclNSTmNDNzBXUUJXVDVWVmhwMG1BOXlaREdZYlJadDlJNU9LOVFrUW11SjV6REZhTUVPWHpTcnNDNGx0ZVA2TWRpbWlNaWp2c0gzaXErYzZXVVlvbFJqM25lSTg4RWFISXpMQUdScTY0Qk5DTHpkQVlMMnBFVTJzYjV1Rzc4UEtWb1VVQ2JWSkw1anBET2hMT1RPMWJRc1R1b1VwblJSckxRRC9rSXpWK2xqcFZCd3dmSmN5cTc1VEpBL0N0UHIveHIyU1o5QjFiMnNiakc2akQwbGh0b0NkZGVEZ2NxZ2wvTFNTa2N1YVlZOHhQV0N5K0x0TmhjcVRoZm1mdm5ITEpJcEw2Z2pialcvT1FwUmZWVXdmdzFqT2I5YldWd2NnSGhOWWZLWUdQdE04b3RoNXh3TFlSUlZnenFNS092czdmYWxYUmhWeloyU1A2SXcwQk1tQUFaNkhqZkNsOUwrdFBxSk5sblFRT0hwb1dqdW00QitYc1lsZEZFS0dRV1Fxc2Q1OWlOUHZhbzlwL3NDT3Q3ckdxQ296Y21naUVtNHc2NmV6L1FJRHliNDZuMCt0Y05KUFVjb0JLdlEvakR3RTZWd21rUS9uRUNqRnAzVWREVCtrV1lRU05kOGo4VkJaT3BHOExscVVZckVaQ3YwcTdCczF2Y05yZFlpYUZvUzMyb3NheW5XaytIdDNPSHVGV2JFRjhKbHNGVFFBTzA1VnZZa2VjZjBWL29USHNHNWh5T09zN1VFYURGcTd1YUp1eldWaGg1cEFvaklhQmNSOGZWbG4yUExSVFg3aXMybnNBK1FyZGlkZVBjWnRGdGd4QWlLWWUxaTJzU0ZpNHZtOEVPa0NiUTYzd2RRZVk0VXJyNVB1b01Fd3hVVUxqZ0thZ2lBbXNKRHE0UnJWbTdzTzQrNll1QTlqNmwydXlsa09FYzY3dmYvNWZrWHVDc2lBcE5MNmtlYjhjK3ZMMG40RlhHZHpqK2FwU0RmRkdCZ0IiLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsiaWQiOiJ0b29sdV8wMVZCcldkV0VXWWdpdDRrTlllaEJNVTUiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6e30sIm5hbWUiOiJ0cmFuc2Zlcl90b19lZGl0b3IiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QXpmanFVb3BvRW1aTGFxbTEiLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6NzQxNiwib3V0cHV0X3Rva2VucyI6MTUxLCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjoxMTl9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlZF90ZWFtIiwiaWQiOiJsY19ydW4tLTAxYTBmZTAzLTZjZTYtNzI1MS1iNzk2LTRmNjQzMzNmNjdjNi0wIiwidG9vbF9jYWxscyI6W3sibmFtZSI6InRyYW5zZmVyX3RvX2VkaXRvciIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxVkJyV2RXRVdZZ2l0NGtOWWVoQk1VNSIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzQxNiwib3V0cHV0X3Rva2VucyI6MTUxLCJ0b3RhbF90b2tlbnMiOjc1NjcsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjExOX19fSx7ImNvbnRlbnQiOiJTdWNjZXNzZnVsbHkgdHJhbnNmZXJyZWQgdG8gZWRpdG9yIiwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6e30sInR5cGUiOiJ0b29sIiwibmFtZSI6InRyYW5zZmVyX3RvX2VkaXRvciIsImlkIjoiNWQzOWUzNmItYzViNS00NDI2LWE5YWEtYmUyZjdkMzgxNmQ2IiwidG9vbF9jYWxsX2lkIjoidG9vbHVfMDFWQnJXZFdFV1lnaXQ0a05ZZWhCTVU1Iiwic3RhdHVzIjoic3VjY2VzcyJ9LHsiY29udGVudCI6W3sic2lnbmF0dXJlIjoiQ0FRUzVnWUtFQWdTR0FJNEFVSUlkR2hwYm10cGJtY1NESTRRSWI3TDJ3NWFXM2NNL1JvTUxpMndFeERrcWh1eEpEaVlJakFxR3hNNFdVd2lxNHVaSHJpQ2J1QzRrVndhN2lnZFVMb29jWmJpNWZldktiZndxSFNickxOVDUxTkdYNFhzTHRzcWd3WS90YWJIamxsenF1N25SV3Y4K0Z6NFI2bjlqYTdDcGoyNFp1eEZ1S2trUU9CbUE0VGYxYXBrM1JQcWNFUStqK3dlZHUwbE8rcmRFQ3lkM2xYaGZnRVJGRnFjTTZhdWN4ZWw0UmJ3NW9BSFh1OStYZVR0emwrTjh0QWVaOWlHWjJYVHRVNU9iOGFQVDFLdVgrdXA4a1E0VlVYa0JUZmQyZjVKUDlSeFpFcTl3U1lhWnN5SGR2MG4rMVU0NkFPc3ZLWm1wOVFYQndvMmY0TzkwalA4ZWdpcmVtOUViWmJtYVlPSjhXSzdDdEtSVmJZMnk0Kzl4UlVKMDRuc2RJejVGNUZGS0V4eE5PckI0bWMvTkU4M2FiM1o2NGlXek93cW9VR0FHUVNrYUgwZDVjRXVtWm80ZlpaQWhQeXVKZVFEeHVsTUNld243RUdDbnBKdy9uemkwd295RWFRTDRZN2g5OVA3YVh4RnIyOHA1S0N5SkVKVERlZmVJcFZsQXdNQ0Fqeit4QzY5QUFMbXd5VFErY0ZFTStLQWdlSVNwaExWeThBUHIyRlNoYXhCTnJYUWd6MXM5czJkaExaUU9CaXd6aHhtRWdkSzcrOEphcWhCMGVFRWQvMVJWQXVJWWRlekE1SEJyd0U5RHlRaUNsM1VPc2JTbk5FVmUrZ3JIcDVwM3RtTUJxNjhnTFY4Mm9BekZZWmwrQ2V3eDcxdjVkUEZPdktQRUhVenBRWU9WTHJuQjFFWlJZclp6NzJuMndmU1Z4Qk96cFRjbkJ4VjZIZWRDUHlJektYWk05K3lFZVRKaThRdHZWZ1oxdyt2MGhtQ0ZHcG5tWk43bVhsZ3FMMXM2TVhWeWRwUE9LUGxNM05hN0NkSG5QRllpd3Iyekx2a2tjSU03Q3NrL0MzK1pNQVdUSytDOUIxdmJHeFBsdEUzT3Y4a085OFBnU1htMUFKdUViWHkrcjNhM0QzUWxaSjNkRUtlMkxOZEFCeXJQTWhTY0tVOEdsZkgvOU50Z3JodGFrZ2xsRC9NZkFsVHNiTndORHJVdFdSeG1EdUovMForaGtrL1lOd0VEWUFaYThUbXdWb1dPZEJIcFJQSHZaOUU5dXNldWx0bWErSmsxZ1JMRHR2RVprcVhVRVNrTWNxVXRWd1lNNWFqSkE1TjUyY05pWjE1QlRmOFhqR2hLV2RPVjQwKzhIMFBPU3hNMkppZndDTzBDNXhGVzVCbzNJaUlOdjBVT3RZNWY4a3ZQZE0zUGpraGFPcksxeVRBOGVFRTQ0dnVuTDlQa29HZWNiWW0rWEU1S3pMM1FzRW4yWTFJSndPOXcweEhYUVpFZWlQNSswdTNZbkRjOHE5ZEJMaEdXM0Z5MzBnWUFRPT0iLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsiaWQiOiJ0b29sdV8wMUJtOEFVOUVzUVV3cW9WTFlweEtBNzciLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6eyJmaWxlX3BhdGgiOiIvYW5zd2VyLm1kIiwiY29udGVudCI6IioqVHVwbGUgdnMuIGxpc3QgaW1tdXRhYmlsaXR5IChQeXRob24pKipcblxuQSB0dXBsZSBpcyBpbW11dGFibGU6IG9uY2UgY3JlYXRlZCwgeW91IGNhbid0IGFzc2lnbiB0byBpdHMgaXRlbXMsIGFuZCB0aGUgY29sbGVjdGlvbiBvZiBvYmplY3RzIGl0IHJlZmVyZW5jZXMgY2FuJ3QgY2hhbmdlLiBgdFswXSA9IDFgIHJhaXNlcyBgVHlwZUVycm9yYC4gQSBsaXN0IGlzIG11dGFibGU6IHlvdSBjYW4gY2hhbmdlIGl0IGluIHBsYWNlIHdpdGggaW5kZXggb3Igc2xpY2UgYXNzaWdubWVudCwgYGFwcGVuZCgpYCwgYGV4dGVuZCgpYCwgYHNvcnQoKWAgYW5kIHNpbWlsYXIgbWV0aG9kcy5cblxuVHVwbGUgaW1tdXRhYmlsaXR5IGlzIHNoYWxsb3cuIElmIGEgdHVwbGUgaG9sZHMgYSBtdXRhYmxlIG9iamVjdCwgc3VjaCBhcyBhIGxpc3QsIHRoYXQgaW5uZXIgb2JqZWN0IGNhbiBzdGlsbCBjaGFuZ2UsIGFuZCBzbyB0aGUgdHVwbGUncyB2YWx1ZSBjaGFuZ2VzLiBCZWNhdXNlIG9mIHRoaXMsIGEgdHVwbGUgY2FuIGJlIGEgYGRpY3RgIGtleSBvciBgc2V0YCBtZW1iZXIgb25seSBpZiBldmVyeXRoaW5nIGluc2lkZSBpdCBpcyBoYXNoYWJsZS4gQSBsaXN0IGNhbiBuZXZlciBiZSBhIGtleS5cblxuU291cmNlczpcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy90dXRvcmlhbC9kYXRhc3RydWN0dXJlcy5odG1sXG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvcmVmZXJlbmNlL2RhdGFtb2RlbC5odG1sXG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvbGlicmFyeS9zdGR0eXBlcy5odG1sXG4ifSwibmFtZSI6IndyaXRlX2ZpbGUiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QkJhYTlnak1DY2UxNlRVZW4iLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6ODEyNywib3V0cHV0X3Rva2VucyI6NDMzLCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjo3OX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoiZWRpdG9yIiwiaWQiOiJsY19ydW4tLTAxYTBmZTAzLTc2ZTktN2NhMy1hNWZmLTYzZGU2NmRkOGRkMS0wIiwidG9vbF9jYWxscyI6W3sibmFtZSI6IndyaXRlX2ZpbGUiLCJhcmdzIjp7ImZpbGVfcGF0aCI6Ii9hbnN3ZXIubWQiLCJjb250ZW50IjoiKipUdXBsZSB2cy4gbGlzdCBpbW11dGFiaWxpdHkgKFB5dGhvbikqKlxuXG5BIHR1cGxlIGlzIGltbXV0YWJsZTogb25jZSBjcmVhdGVkLCB5b3UgY2FuJ3QgYXNzaWduIHRvIGl0cyBpdGVtcywgYW5kIHRoZSBjb2xsZWN0aW9uIG9mIG9iamVjdHMgaXQgcmVmZXJlbmNlcyBjYW4ndCBjaGFuZ2UuIGB0WzBdID0gMWAgcmFpc2VzIGBUeXBlRXJyb3JgLiBBIGxpc3QgaXMgbXV0YWJsZTogeW91IGNhbiBjaGFuZ2UgaXQgaW4gcGxhY2Ugd2l0aCBpbmRleCBvciBzbGljZSBhc3NpZ25tZW50LCBgYXBwZW5kKClgLCBgZXh0ZW5kKClgLCBgc29ydCgpYCBhbmQgc2ltaWxhciBtZXRob2RzLlxuXG5UdXBsZSBpbW11dGFiaWxpdHkgaXMgc2hhbGxvdy4gSWYgYSB0dXBsZSBob2xkcyBhIG11dGFibGUgb2JqZWN0LCBzdWNoIGFzIGEgbGlzdCwgdGhhdCBpbm5lciBvYmplY3QgY2FuIHN0aWxsIGNoYW5nZSwgYW5kIHNvIHRoZSB0dXBsZSdzIHZhbHVlIGNoYW5nZXMuIEJlY2F1c2Ugb2YgdGhpcywgYSB0dXBsZSBjYW4gYmUgYSBgZGljdGAga2V5IG9yIGBzZXRgIG1lbWJlciBvbmx5IGlmIGV2ZXJ5dGhpbmcgaW5zaWRlIGl0IGlzIGhhc2hhYmxlLiBBIGxpc3QgY2FuIG5ldmVyIGJlIGEga2V5LlxuXG5Tb3VyY2VzOlxuLSBodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3R1dG9yaWFsL2RhdGFzdHJ1Y3R1cmVzLmh0bWxcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy9yZWZlcmVuY2UvZGF0YW1vZGVsLmh0bWxcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy9saWJyYXJ5L3N0ZHR5cGVzLmh0bWxcbiJ9LCJpZCI6InRvb2x1XzAxQm04QVU5RXNRVXdxb1ZMWXB4S0E3NyIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6ODEyNywib3V0cHV0X3Rva2VucyI6NDMzLCJ0b3RhbF90b2tlbnMiOjg1NjAsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjc5fX19LHsiY29udGVudCI6IlVwZGF0ZWQgZmlsZSAvYW5zd2VyLm1kIiwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6e30sInR5cGUiOiJ0b29sIiwibmFtZSI6IndyaXRlX2ZpbGUiLCJpZCI6ImUzNDkyZTA4LWM4NjktNDdlYy1hNWY3LWNjNTdlYTVmNjQwMyIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxQm04QVU5RXNRVXdxb1ZMWXB4S0E3NyIsInN0YXR1cyI6InN1Y2Nlc3MifV19" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "17535b52f19759b3", - "parentSpanId": "5eb6729648b8a8b0", - "name": "FilesystemMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968039097378048", - "endTimeUnixNano": "1790968042917388032", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "FilesystemMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "3" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:d639a607-1d3b-b4dc-823b-564098184f56" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "6ad99925c2a25881", - "parentSpanId": "17535b52f19759b3", - "name": "UnsupportedContentMiddleware.wrap_model_call", - "kind": 1, - "startTimeUnixNano": "1790968039097809152", - "endTimeUnixNano": "1790968042917225984", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chain" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "e30=" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "UnsupportedContentMiddleware.wrap_model_call" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "langchain" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_create_agent" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "3" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:d639a607-1d3b-b4dc-823b-564098184f56" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - }, - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "73aee64af021a907", - "parentSpanId": "6ad99925c2a25881", - "name": "ChatAnthropic", - "kind": 1, - "startTimeUnixNano": "1790968039099990016", - "endTimeUnixNano": "1790968042916750848", - "attributes": [ - { - "key": "gen_ai.operation.name", - "value": { - "stringValue": "chat" - } - }, - { - "key": "gen_ai.serialized.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "llm" - } - }, - { - "key": "langsmith.trace.name", - "value": { - "stringValue": "ChatAnthropic" - } - }, - { - "key": "langsmith.trace.session_name", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "gen_ai.system", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "gen_ai.request.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "gen_ai.tool.definitions", - "value": { - "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"write_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path where the file should be written. Must be absolute, not relative.\",\"type\":\"string\"},\"content\":{\"description\":\"The text content to write to the file. This parameter is required.\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"description\":\"Writes content to a file. Creates the file if it does not exist; replaces it entirely if it does.\\n\\nUsage:\\n- Use this tool when you intend to create a new file or replace the whole file. You do not need to read the file first.\\n- Prefer to edit existing files (with the edit_file tool) over creating new ones when possible.\"},{\"name\":\"edit_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to edit. Must be absolute, not relative.\",\"type\":\"string\"},\"old_string\":{\"description\":\"The exact text to find and replace. Must be unique in the file unless replace_all is True.\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace old_string with. Must be different from old_string.\",\"type\":\"string\"},\"replace_all\":{\"default\":false,\"description\":\"If True, replace all occurrences of old_string. If False (default), old_string must be unique.\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"description\":\"Performs exact string replacements in files.\\n\\nUsage:\\n- You must read the file before editing; this tool errors otherwise.\\n- Preserve the exact source indentation from the read output, and never include the read status header in old_string or new_string.\\n- Prefer editing an existing file over creating a new one.\\n- Only use emojis if the user explicitly requests it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"transfer_to_researcher\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request missing evidence from the researcher\"},{\"name\":\"transfer_to_skeptic\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request another critique from the skeptic\"},{\"name\":\"transfer_to_verifier\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request another source check from the verifier\"}]" - } - }, - { - "key": "langsmith.metadata.ls_integration", - "value": { - "stringValue": "langchain_chat_model" - } - }, - { - "key": "langsmith.metadata.langgraph_step", - "value": { - "intValue": "3" - } - }, - { - "key": "langsmith.metadata.langgraph_node", - "value": { - "stringValue": "model" - } - }, - { - "key": "langsmith.metadata.langgraph_triggers", - "value": { - "stringValue": "[\"branch:to:model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_path", - "value": { - "stringValue": "[\"__pregel_pull\",\"model\"]" - } - }, - { - "key": "langsmith.metadata.langgraph_checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:d639a607-1d3b-b4dc-823b-564098184f56" - } - }, - { - "key": "langsmith.metadata.lc_agent_name", - "value": { - "stringValue": "editor" - } - }, - { - "key": "langsmith.metadata.checkpoint_ns", - "value": { - "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" - } - }, - { - "key": "langsmith.metadata.ls_provider", - "value": { - "stringValue": "anthropic" - } - }, - { - "key": "langsmith.metadata.ls_model_name", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.ls_model_type", - "value": { - "stringValue": "chat" - } - }, - { - "key": "langsmith.metadata.ls_max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.lc_versions", - "value": { - "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" - } - }, - { - "key": "langsmith.metadata.ls_method", - "value": { - "stringValue": "traceable" - } - }, - { - "key": "langsmith.metadata.model", - "value": { - "stringValue": "claude-sonnet" - } - }, - { - "key": "langsmith.metadata.max_tokens", - "value": { - "intValue": "4096" - } - }, - { - "key": "langsmith.metadata.model_kwargs", - "value": { - "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" - } - }, - { - "key": "langsmith.metadata.streaming", - "value": { - "boolValue": false - } - }, - { - "key": "langsmith.metadata.max_retries", - "value": { - "intValue": "2" - } - }, - { - "key": "langsmith.metadata._type", - "value": { - "stringValue": "anthropic-chat" - } - }, - { - "key": "langsmith.metadata.usage_metadata", - "value": { - "stringValue": "{\"input_tokens\":8494,\"output_tokens\":415,\"total_tokens\":8909,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":0}}" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", - "value": { - "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_PROJECT", - "value": { - "stringValue": "litellm-fixture" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING", - "value": { - "stringValue": "true" - } - }, - { - "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", - "value": { - "stringValue": "otel" - } - }, - { - "key": "langsmith.metadata.revision_id", - "value": { - "stringValue": "abd4db9" - } - }, - { - "key": "langsmith.span.tags", - "value": { - "stringValue": "seq:step:1" - } - }, - { - "key": "gen_ai.prompt", - "value": { - "bytesValue": "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" - } - }, - { - "key": "gen_ai.usage.input_tokens", - "value": { - "intValue": "8494" - } - }, - { - "key": "gen_ai.usage.output_tokens", - "value": { - "intValue": "415" - } - }, - { - "key": "gen_ai.usage.total_tokens", - "value": { - "intValue": "8909" - } - }, - { - "key": "gen_ai.completion", - "value": { - "bytesValue": "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" - } - } - ], - "status": { - "code": 1 - }, - "flags": 256 - } - ] - }, - { - "scope": { - "name": "deeplite" - }, - "spans": [ - { - "traceId": "b2952a96b863250c304cef3376fe4c82", - "spanId": "e8da3a18a9815276", - "name": "deeplite.run", - "kind": 1, - "startTimeUnixNano": "1790968013175004000", - "endTimeUnixNano": "1790968042976537000", - "attributes": [ - { - "key": "langsmith.span.kind", - "value": { - "stringValue": "chain" - } - }, - { - "key": "input.value", - "value": { - "stringValue": "For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions." - } - }, - { - "key": "output.value", - "value": { - "stringValue": "I wrote the answer to `/answer.md`. It is about 100 words, under the 120-word limit.\n\nI did not get a skeptic or verifier check. I handed off to both, but neither returned any feedback. I also tried to hand off to a `red_team` agent, and that transfer isn't one of the tools I was given. I then wrote the answer myself from the official Python documentation search results. I didn't open the pages directly.\n\n**Tuple vs. list immutability (Python)**\n\nA tuple is immutable: once created, you can't assign to its items, and the collection of objects it references can't change. `t[0] = 1` raises `TypeError`. A list is mutable: you can change it in place with index or slice assignment, `append()`, `extend()`, `sort()` and similar methods.\n\nTuple immutability is shallow. If a tuple holds a mutable object, such as a list, that inner object can still change, and so the tuple's value changes. Because of this, a tuple can be a `dict` key or `set` member only if everything inside it is hashable. A list can never be a key.\n\nSources:\n- https://docs.python.org/3/tutorial/datastructures.html\n- https://docs.python.org/3/reference/datamodel.html\n- https://docs.python.org/3/library/stdtypes.html" - } - } - ], - "status": {}, - "flags": 256 - } - ] - } - ] - } - ] -} diff --git a/litellm-rust/crates/traces/tests/normalize.rs b/litellm-rust/crates/traces/tests/normalize.rs index 244b814cdd6..ccc0c3bb224 100644 --- a/litellm-rust/crates/traces/tests/normalize.rs +++ b/litellm-rust/crates/traces/tests/normalize.rs @@ -120,8 +120,6 @@ fn array<'a>(value: &'a Value, key: &str) -> &'a [Value] { #[case::crewai_swarm(include_bytes!("fixtures/crewai_swarm.json"))] #[case::deepagents_simple(include_bytes!("fixtures/deepagents_simple.json"))] #[case::deepagents_swarm(include_bytes!("fixtures/deepagents_swarm.json"))] -#[case::deeplite_auth_error(include_bytes!("fixtures/deeplite_auth_error.json"))] -#[case::deeplite_swarm(include_bytes!("fixtures/deeplite_swarm.json"))] #[case::google_adk_simple(include_bytes!("fixtures/google_adk_simple.json"))] #[case::google_adk_swarm(include_bytes!("fixtures/google_adk_swarm.json"))] #[case::langchain_simple(include_bytes!("fixtures/langchain_simple.json"))] diff --git a/litellm-rust/crates/traces/tests/otlp.rs b/litellm-rust/crates/traces/tests/otlp.rs index 1a38bd15ffd..eb17bdc374b 100644 --- a/litellm-rust/crates/traces/tests/otlp.rs +++ b/litellm-rust/crates/traces/tests/otlp.rs @@ -1333,3 +1333,98 @@ fn resource_identity_preserves_explicit_names_and_sdk_fallbacks( expected ); } + +#[rstest] +#[case::depth(litellm_traces::DecodeLimits { depth: 1, ..Default::default() })] +#[case::nodes(litellm_traces::DecodeLimits { nodes: 1, ..Default::default() })] +#[case::spans(litellm_traces::DecodeLimits { spans: 1, ..Default::default() })] +#[case::attributes(litellm_traces::DecodeLimits { attributes: 1, ..Default::default() })] +#[case::events(litellm_traces::DecodeLimits { events: 1, ..Default::default() })] +#[case::links(litellm_traces::DecodeLimits { links: 1, ..Default::default() })] +#[case::decoded_bytes(litellm_traces::DecodeLimits { decoded_span_bytes: 1, ..Default::default() })] +fn configurable_decode_limits_apply_to_both_wire_formats( + mut span: Span, + #[case] limits: litellm_traces::DecodeLimits, +) { + use opentelemetry_proto::tonic::{ + common::v1::KeyValue, + trace::v1::span::{Event, Link}, + }; + use prost::Message; + span.attributes = vec![ + KeyValue { + key: "a".into(), + ..Default::default() + }, + KeyValue { + key: "b".into(), + ..Default::default() + }, + ]; + span.events = vec![Event::default(), Event::default()]; + span.links = vec![ + Link { + trace_id: vec![1; 16], + span_id: vec![2; 8], + ..Default::default() + }; + 2 + ]; + let mut request = request_with(span.clone()); + request.resource_spans[0].scope_spans[0].spans.push(span); + for (body, content_type) in [ + (serde_json::to_vec(&request).unwrap(), "application/json"), + (request.encode_to_vec(), "application/x-protobuf"), + ] { + assert!(matches!( + litellm_traces::decode_otlp_with_limits(&body, Some(content_type), limits), + Err(litellm_traces::Error::TooLarge) + )); + assert_eq!( + litellm_traces::decode_otlp_with_limits( + &body, + Some(content_type), + litellm_traces::DecodeLimits::default() + ) + .unwrap() + .len(), + 2 + ); + } +} + +#[test] +fn environment_decode_limits_are_used_and_invalid_values_fail() { + for value in ["2", "4", "0", "invalid"] { + let result = std::process::Command::new(std::env::current_exe().unwrap()) + .args(["--exact", "environment_decode_limits_child"]) + .env("LITELLM_TEST_DECODE_LIMIT", value) + .env("OTLP_MAX_SPANS", value) + .output() + .unwrap(); + assert!( + result.status.success(), + "{}", + String::from_utf8_lossy(&result.stdout) + ); + } +} + +#[test] +fn environment_decode_limits_child() { + let Ok(value) = std::env::var("LITELLM_TEST_DECODE_LIMIT") else { + return; + }; + let result = decode_otlp( + include_bytes!("fixtures/opentelemetry_simple.json"), + Some("application/json"), + ); + match value.as_str() { + "2" => assert!(matches!(result, Err(litellm_traces::Error::TooLarge))), + "4" => assert_eq!(result.unwrap().len(), 3), + _ => assert!(matches!( + result, + Err(litellm_traces::Error::InvalidLimit("OTLP_MAX_SPANS")) + )), + } +} diff --git a/litellm/__init__.py b/litellm/__init__.py index b6428b51bfb..fea7a27a5fb 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -1474,6 +1474,7 @@ from .rust_bridge import rust from .rag.main import * from .sandbox.main import * from .decisions.main import * +from .tool_loop import ToolLoopMaxRoundsExceeded, arun_tool_loop, run_tool_loop from .search.main import * from .realtime_api.main import ( _arealtime, diff --git a/litellm/constants.py b/litellm/constants.py index 49514fc4d0e..d58fc8a6318 100644 --- a/litellm/constants.py +++ b/litellm/constants.py @@ -2234,3 +2234,5 @@ HARNESS_SNAPSHOT_SKIP_DIRS: Final = frozenset( ".ruff_cache", } ) + +DEFAULT_TOOL_LOOP_MAX_ROUNDS: Final = 20 diff --git a/litellm/decisions/main.py b/litellm/decisions/main.py index da037f1d8cb..4864fcaa0e4 100644 --- a/litellm/decisions/main.py +++ b/litellm/decisions/main.py @@ -59,7 +59,7 @@ def _resolve_provider_model(model: str, custom_llm_provider: str | None) -> tupl model=model, llm_provider=provider, ) - upstream_model: Final = model.removeprefix(f"{provider}/") if model.startswith(f"{provider}/") else model + upstream_model: Final = model.removeprefix(f"{provider}/") if not upstream_model: raise litellm.BadRequestError( message="A model name is required for the Decisions API", diff --git a/litellm/harness/handlers/tool_loop_handler.py b/litellm/harness/handlers/tool_loop_handler.py index 33efcba4ff7..d3acb50eadb 100644 --- a/litellm/harness/handlers/tool_loop_handler.py +++ b/litellm/harness/handlers/tool_loop_handler.py @@ -267,11 +267,8 @@ class ToolLoopHandler(BaseHarnessHandler): tool_specs: list[ChatCompletionToolParam] = copy.deepcopy( # mutable-ok: acompletion takes tool list list(self._tool_specs) ) - request_kwargs: dict[str, object] = { # mutable-ok: acompletion takes keyword arguments - key: value for key, value in self._completion_kwargs.items() if key not in {"messages", "tools"} - } kwargs: dict[str, object] = { # mutable-ok: acompletion takes keyword arguments - **request_kwargs, + **{key: value for key, value in self._completion_kwargs.items() if key not in {"messages", "tools"}}, "messages": messages, **({"tools": tool_specs} if tool_specs else {}), } @@ -287,8 +284,7 @@ class ToolLoopHandler(BaseHarnessHandler): yield Text(content) tool_calls = message.tool_calls or () if not tool_calls: - final_text = content or "" - ctx.final_text = final_text # rebind-ok: SessionContext is the runtime's per-turn result sink + ctx.final_text = content or "" # rebind-ok: SessionContext is the runtime's per-turn result sink ctx.output_json = content if ctx.output is not None else None # rebind-ok: per-turn output sink final_message: ChatCompletionMessageParam = { "role": "assistant", diff --git a/litellm/harness/options.py b/litellm/harness/options.py index b0014fea393..18865359ba8 100644 --- a/litellm/harness/options.py +++ b/litellm/harness/options.py @@ -36,7 +36,7 @@ class DeepAgentsOptions: @dataclass(frozen=True) class ToolLoopOptions: - completion_kwargs: Mapping[str, Any] = field(default_factory=dict) + completion_kwargs: Mapping[str, object] = field(default_factory=dict) HarnessOptions = ClaudeCodeOptions | CodexOptions | OpenCodeOptions | DeepAgentsOptions | ToolLoopOptions diff --git a/litellm/llms/anthropic/files/transformation.py b/litellm/llms/anthropic/files/transformation.py index 04d057ed3e9..da21f130f1a 100644 --- a/litellm/llms/anthropic/files/transformation.py +++ b/litellm/llms/anthropic/files/transformation.py @@ -125,13 +125,12 @@ class AnthropicFilesConfig(BaseFilesConfig): return self._finalize_headers(headers, auth_header) @staticmethod - def _resolve_params( - litellm_params: dict, api_base: str | None - ) -> tuple[dict | None, str | None]: # mutable-ok: mirrors the sync validate_environment contract this overrides + def _resolve_params(litellm_params: dict, api_base: str | None) -> tuple[Mapping[str, object] | None, str | None]: params_mapping: Final = litellm_params if isinstance(litellm_params, dict) else None - if api_base is None and params_mapping is not None: - api_base = params_mapping.get("api_base") - return params_mapping, api_base + resolved_api_base: Final = ( + api_base if api_base is not None or params_mapping is None else params_mapping.get("api_base") + ) + return params_mapping, resolved_api_base @staticmethod def _finalize_headers(headers: dict, auth_header: Mapping[str, str] | None) -> dict: # mutable-ok: out-param diff --git a/litellm/llms/anthropic/pass_through/messages/mcp_handler.py b/litellm/llms/anthropic/pass_through/messages/mcp_handler.py index ab722a60ca5..7961a38dedf 100644 --- a/litellm/llms/anthropic/pass_through/messages/mcp_handler.py +++ b/litellm/llms/anthropic/pass_through/messages/mcp_handler.py @@ -147,6 +147,7 @@ async def anthropic_messages_with_mcp( tool_results = await LiteLLM_Proxy_MCP_Handler._execute_tool_calls( tool_server_map=tool_server_map, + served_tools=deduplicated_mcp_tools, tool_calls=list(tool_use_blocks), user_api_key_auth=context.user_api_key_auth, mcp_auth_header=context.mcp_auth_header, diff --git a/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py b/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py index a776470e2ab..49cd8cf6fb9 100644 --- a/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py +++ b/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py @@ -28,7 +28,7 @@ from contextlib import asynccontextmanager from dataclasses import dataclass, replace from functools import lru_cache from itertools import chain, groupby -from types import MappingProxyType +from types import EllipsisType, MappingProxyType from typing import TYPE_CHECKING, Any, Final, Generic, Literal, TypeAlias, TypedDict, TypeVar, cast from urllib.parse import ParseResult, urlparse @@ -259,6 +259,20 @@ _user_env_vars_cache: Final[dict[tuple[str, str], tuple[dict[str, str], float]]] _USER_ENV_VARS_CACHE_TTL: Final = 60 # seconds _USER_ENV_VARS_CACHE_MAX_SIZE: Final = 4096 # cap to prevent unbounded growth +_ListedToolsByCaller: TypeAlias = Mapping[str | None, Mapping[str, MCPTool]] +_LISTED_TOOLS_CALLERS_PER_SERVER: Final = 256 + + +@dataclass(frozen=True, slots=True) +class ListedToolsCaller: + """Request inputs that select which upstream catalog a caller was shown by tools/list.""" + + user_api_key_auth: UserAPIKeyAuth | None = None + mcp_auth_header: str | dict[str, str] | None = None + raw_headers: Mapping[str, str] | None = None + oauth2_headers: Mapping[str, str] | None = None + + # Auth types whose upstream OAuth endpoints (protected-resource + authorization-server metadata) the # gateway discovers from the upstream itself: interactive oauth2 and the two client-forwarded modes. # OBO/M2M endpoint discovery is decided separately via _obo_needs_endpoint_discovery. Shared by the @@ -1172,6 +1186,57 @@ def _authorization_is_litellm_admission_credential( return bool(user_api_key_auth and user_api_key_auth.api_key and not admission_header) +def _server_auth_header_for( + server: MCPServer, + mcp_server_auth_headers: Mapping[str, str | dict[str, str]] | None, + mcp_auth_header: str | dict[str, str] | None, +) -> str | dict[str, str] | None: + """Server-specific ``x-mcp--authorization`` header, else the deprecated global one.""" + server_specific: Final = ( + lookup_mcp_server_auth_in_headers( + mcp_server_auth_headers, + alias=server.alias, + server_name=server.server_name, + access_groups=server.access_groups, + ) + if mcp_server_auth_headers + else None + ) + return mcp_auth_header if server_specific is None else server_specific + + +def listed_tools_caller_for( + server: MCPServer, + user_api_key_auth: UserAPIKeyAuth | None, + mcp_auth_header: str | dict[str, str] | None, + mcp_server_auth_headers: Mapping[str, str | dict[str, str]] | None, + raw_headers: Mapping[str, str] | None, + oauth2_headers: Mapping[str, str] | None, +) -> ListedToolsCaller: + """The caller a tools/call must look its listed entry up under: the same inputs tools/list keyed by.""" + return ListedToolsCaller( + user_api_key_auth=user_api_key_auth, + mcp_auth_header=_server_auth_header_for(server, mcp_server_auth_headers, mcp_auth_header), + raw_headers=raw_headers, + oauth2_headers=oauth2_headers, + ) + + +def _admission_identity( + auth: UserAPIKeyAuth, raw_headers: Mapping[str, str] | None +) -> tuple[str | None, str | None, str | None, str | None, str | None]: + """The admission identity the served catalog is shaped for: the hashed key, user, team and + organization, plus the admission credential (``x-litellm-api-key``, else ``Authorization``) of a + caller admitted with neither a key nor a user.""" + keyless: Final = auth.api_key is None and auth.user_id is None + credential: Final = ( + _raw_header_value(raw_headers, "x-litellm-api-key") or _raw_header_value(raw_headers, "authorization") + if keyless + else None + ) + return auth.api_key, auth.user_id, auth.team_id, auth.org_id, credential + + def _format_byok_openapi_auth_header(mcp_server: MCPServer, mcp_auth_header: str) -> str: """Format a raw BYOK credential for OpenAPI tool ``Authorization`` injection. @@ -1297,6 +1362,16 @@ async def _resolve_byok_mcp_auth_header( return mcp_auth_header +def _catalog_auth_header( + mcp_auth_header: str | dict[str, str] | None, + catalog_auth_header: str | dict[str, str] | None | EllipsisType, +) -> str | dict[str, str] | None: + """The header the client supplied, which keys the caller's catalog slot on both tools/list and + tools/call. A caller that already swapped a stored BYOK credential into ``mcp_auth_header`` passes + the client's value explicitly, since the stored credential must never be read to find the slot.""" + return mcp_auth_header if catalog_auth_header is ... else catalog_auth_header + + def _client_forwarded_authorization_headers( mcp_server: MCPServer, oauth2_headers: dict[str, str] | None, @@ -1925,6 +2000,8 @@ class MCPServerManager: "gmail_send_email": "zapier_mcp_server", } """ + self._listed_tools_by_server_id: dict[str, _ListedToolsByCaller] = {} # mutable-ok: refreshed per tools/list + self._listed_tools_generations: dict[str, int] = {} # mutable-ok: bumped per server save self._upstream_initialize_instructions_by_server_id: dict[str, str] = {} # Per-server monotonic timestamp of last upstream prefetch attempt (success, # empty result, or failure). Used to throttle re-probes for servers that do @@ -3242,6 +3319,8 @@ class MCPServerManager: self._invalidate_server_definition_caches(mcp_server.server_id) self.registry[mcp_server.server_id] = new_server await self._maybe_register_openapi_tools(new_server) + if new_server.spec_path: + self._drop_listed_tools(mcp_server.server_id) self.prime_oauth_metadata_discovery(new_server) verbose_logger.debug("Added MCP Server: %s", new_server.name) @@ -3279,6 +3358,8 @@ class MCPServerManager: self._invalidate_server_definition_caches(mcp_server.server_id) self.registry[mcp_server.server_id] = new_server await self._maybe_register_openapi_tools(new_server) + if new_server.spec_path: + self._drop_listed_tools(mcp_server.server_id) self.prime_oauth_metadata_discovery(new_server) verbose_logger.debug("Updated MCP Server: %s", new_server.name) @@ -3754,25 +3835,14 @@ class MCPServerManager: verbose_logger.warning("MCP Server %s not found", server_id) return [] - # Get server-specific auth header if available - server_auth_header: str | dict[str, str] | None = None - if mcp_server_auth_headers: - server_auth_header = lookup_mcp_server_auth_in_headers( - mcp_server_auth_headers, - alias=server.alias, - server_name=server.server_name, - access_groups=server.access_groups, - ) - - # Fall back to deprecated mcp_auth_header if no server-specific header found - if server_auth_header is None: - server_auth_header = mcp_auth_header + server_auth_header: Final = _server_auth_header_for(server, mcp_server_auth_headers, mcp_auth_header) try: tools: Final = await self._get_tools_from_server( server=server, mcp_auth_header=server_auth_header, user_api_key_auth=user_api_key_auth, + record_listing=True, ) return tools except Exception as e: @@ -3852,7 +3922,7 @@ class MCPServerManager: def _build_stdio_env( self, server: MCPServer, - raw_headers: dict[str, str] | None = None, + raw_headers: Mapping[str, str] | None = None, ) -> dict[str, str] | None: """Resolve stdio env values, supporting header-driven placeholders.""" @@ -4147,13 +4217,20 @@ class MCPServerManager: oauth2_headers: dict[str, str] | None = None, client_ip: str | None = None, proxy_logging_obj: ProxyLogging | None = None, - ) -> list[MCPTool]: + *, + catalog_auth_header: str | dict[str, str] | None | EllipsisType = ..., + record_listing: bool = False, + ) -> Sequence[MCPTool]: """ Helper method to get tools from a single MCP server with prefixed names. Args: server (MCPServer): The server to query tools from mcp_auth_header: Optional auth header for MCP server + catalog_auth_header: The header the client supplied, keying the caller's catalog slot; + defaults to ``mcp_auth_header`` + record_listing: Record the served catalog into the caller's listed-tools slot; only a + listing actually served to the caller sets it Returns: List[MCPTool]: List of tools available on the server with prefixed names @@ -4169,6 +4246,13 @@ class MCPServerManager: verbose_logger.info("_get_tools_from_server for %s...", server.name) client = None + listed_caller: Final = ListedToolsCaller( + user_api_key_auth=user_api_key_auth, + mcp_auth_header=_catalog_auth_header(mcp_auth_header, catalog_auth_header), + raw_headers=raw_headers, + oauth2_headers=oauth2_headers, + ) + listed_generation: Final = self._listed_tools_generations.get(server.server_id, 0) try: # Tool *listing* must not be blocked by missing per-user env vars — @@ -4266,8 +4350,12 @@ class MCPServerManager: # applied (e.g. "test_petstore-getinventory"). Do NOT pass them # through _create_prefixed_tools — that would add the prefix a second # time producing "test_petstore-test_petstore-getinventory". + unprefixed_tools: Final = guarded_openapi + self._record_listed_tools( + server, unprefixed_tools, listed_caller, listed_generation, record_listing=record_listing + ) if not add_prefix: - return list(guarded_openapi) + return unprefixed_tools return [t.model_copy(update={"name": registered_names[t.name]}) for t in guarded_openapi] else: tools = await self._fetch_tools_with_timeout(client, server.name) @@ -4281,7 +4369,10 @@ class MCPServerManager: raw_headers=raw_headers, ) prefixed_or_original_tools: Final = self._create_prefixed_tools( - list(guarded_tools), server, add_prefix=add_prefix + guarded_tools, server, add_prefix=add_prefix + ) + self._record_listed_tools( + server, guarded_tools, listed_caller, listed_generation, record_listing=record_listing ) return prefixed_or_original_tools @@ -4332,8 +4423,99 @@ class MCPServerManager: ) self._invalidate_discovery_lists(server_id) + self._drop_listed_tools(server_id) invalidate_oauth_metadata_cache(server_id) + def _drop_listed_tools(self, server_id: str) -> None: + self._listed_tools_by_server_id.pop(server_id, None) + self._listed_tools_generations[server_id] = self._listed_tools_generations.get(server_id, 0) + 1 + + def _listed_tools_identity(self, server: MCPServer, caller: ListedToolsCaller | None) -> str | None: + """Key the listed-tool cache by every request input that can change the served catalog. + + The catalog is guardrail-shaped for the caller's admission identity (default-on guardrails, + key or team selections and opt-outs), so every admitted caller gets its own slot, keyed by + ``_admission_identity``: the hashed key, user, team and organization, plus the admission + credential of a caller admitted with neither a key nor a user (a team-only JWT). Forwarded + headers, header-driven stdio env, the caller bearer on every server whose egress forwards it + (``_consumes_caller_authorization``) or exchanges it as the OBO subject, and the + server-specific auth header also reach upstream and split the slot further. Only unkeyed + listings with none of those share the ``None`` slot. + """ + if caller is None: + return None + auth: Final = caller.user_api_key_auth + forwarded: Final = self._forwarded_header_values(server, caller.raw_headers) or None + header_env: Final = self._build_stdio_env(server, caller.raw_headers) + stdio_env: Final = None if header_env == self._build_stdio_env(server) else header_env + caller_bearer: Final = ( + self._extract_subject_token(caller.oauth2_headers, caller.raw_headers, auth) + if _consumes_caller_authorization(server) or server.auth_type == MCPAuth.oauth2_token_exchange + else None + ) + identity: Final = None if auth is None else _admission_identity(auth, caller.raw_headers) + if not (identity or caller.mcp_auth_header or forwarded or stdio_env or caller_bearer): + return None + material: Final = json.dumps( + (identity, caller.mcp_auth_header, forwarded, stdio_env, caller_bearer), + sort_keys=True, + separators=(",", ":"), + ) + return hashlib.sha256(material.encode()).hexdigest() + + @staticmethod + def _forwarded_header_values( + server: MCPServer, raw_headers: Mapping[str, str] | None + ) -> tuple[tuple[str, str], ...]: + if not raw_headers or not server.extra_headers: + return () + forwarded_names: Final = frozenset(name.lower() for name in server.extra_headers) + return tuple( + sorted((name.lower(), value) for name, value in raw_headers.items() if name.lower() in forwarded_names) + ) + + def listed_tools_generation(self, server_id: str) -> int: + return self._listed_tools_generations.get(server_id, 0) + + def record_listed_tools( + self, + server: MCPServer, + tools: Sequence[MCPTool], + caller: ListedToolsCaller | None, + generation: int, + *, + record_listing: bool = True, + ) -> None: + self._record_listed_tools(server, tools, caller, generation, record_listing=record_listing) + + def _record_listed_tools( + self, + server: MCPServer, + tools: Sequence[MCPTool], + caller: ListedToolsCaller | None, + generation: int | None = None, + *, + record_listing: bool = True, + ) -> None: + """Store the catalog served to ``caller``. ``generation`` is the server's listed-tools generation + read before the listing's upstream fetch; the record is skipped when it no longer matches.""" + if not record_listing: + return + if generation is not None and generation != self._listed_tools_generations.get(server.server_id, 0): + return + identity: Final = self._listed_tools_identity(server, caller) + listing: Final = MappingProxyType({tool.name: tool for tool in tools}) + existing: Final = self._listed_tools_by_server_id.get(server.server_id, MappingProxyType({})) + shared: Final = existing.get(None) + callers: Final = tuple((key, value) for key, value in existing.items() if key not in (None, identity)) + evicted: Final = 0 if identity is None else max(len(callers) + 1 - _LISTED_TOOLS_CALLERS_PER_SERVER, 0) + entries: Final = ( + *(() if shared is None else ((None, shared),)), + *callers[evicted:], + (identity, listing), + ) + self._listed_tools_by_server_id[server.server_id] = MappingProxyType(dict(entries)) + def _discovery_key( self, server: MCPServer, @@ -4343,9 +4525,11 @@ class MCPServerManager: stdio_env: dict[str, str] | None, subject_token: str | None, credential_fingerprint: str | None = None, + per_caller: bool = False, ) -> _DiscoveryKey: per_user: Final = ( - server.requires_per_user_auth + per_caller + or server.requires_per_user_auth or self._references_per_user_env_var(server) or server.delegate_auth_to_upstream or server.auth_type in (MCPAuth.oauth2_token_exchange, MCPAuth.oauth2_id_jag) @@ -5253,7 +5437,12 @@ class MCPServerManager: {seen: kept for seen, kept in self._catalog_alert_signatures.items() if seen != key} ) - def _create_prefixed_tools(self, tools: list[MCPTool], server: MCPServer, add_prefix: bool = True) -> list[MCPTool]: + def _create_prefixed_tools( + self, + tools: Sequence[MCPTool], + server: MCPServer, + add_prefix: bool = True, + ) -> list[MCPTool]: """ Create prefixed tools and update tool mapping. @@ -5281,6 +5470,13 @@ class MCPServerManager: verbose_logger.info("Successfully fetched %s tools from server %s", len(prefixed_tools), server.name) return prefixed_tools + def get_listed_tool(self, server: MCPServer, name: str, caller: ListedToolsCaller | None = None) -> MCPTool | None: + identity: Final = self._listed_tools_identity(server, caller) + listed: Final = self._listed_tools_by_server_id.get(server.server_id, MappingProxyType({})).get(identity) + if not listed: + return None + return listed.get(name) + def _create_prefixed_prompts( self, prompts: Sequence[Prompt], server: MCPServer, add_prefix: bool = True ) -> list[Prompt]: @@ -5514,6 +5710,7 @@ class MCPServerManager: raw_headers: dict[str, str] | None = None, litellm_logging_obj: "LiteLLMLoggingObj | None" = None, guardrail_context: Mapping[str, object] | None = None, + tool: MCPTool | None = None, ) -> dict[str, Any]: """ Run pre-call checks and guardrail hooks for an MCP tool call. @@ -5527,6 +5724,9 @@ class MCPServerManager: ``pre_mcp_call`` evaluation (or a block) on the spend-log row the Guardrails Monitor counts. It stays optional so callers that do no logging are unchanged. + ``tool`` is the upstream tool definition when one was listed, so guardrails + can see its description and input schema, not just the name and arguments. + Returns a dict that may contain: - "arguments": hook-modified tool arguments (only if changed) - "extra_headers": headers injected by pre_mcp_call guardrail hooks @@ -5590,6 +5790,8 @@ class MCPServerManager: "user_api_key_hash": (getattr(user_api_key_auth, "api_key_hash", None) if user_api_key_auth else None), "incoming_bearer_token": incoming_bearer_token, "headers": logging_safe_mcp_headers(raw_headers), + "tool_description": tool.description if tool is not None else None, + "tool_input_schema": tool.input_schema if tool is not None else None, } # Create MCP request object for processing @@ -5805,21 +6007,7 @@ class MCPServerManager: GuardrailRaisedException: If guardrails block the call HTTPException: If an HTTP error occurs """ - # Get server-specific auth header if available (case-insensitive) - # FIX: Added case-insensitive matching to handle auth header keys that may not match - # the exact case of server alias/name (e.g., '1litellmagcgateway' vs '1LiteLLMAGCGateway') - server_auth_header: dict[str, str] | str | None = None - if mcp_server_auth_headers: - server_auth_header = lookup_mcp_server_auth_in_headers( - mcp_server_auth_headers, - alias=mcp_server.alias, - server_name=mcp_server.server_name, - access_groups=mcp_server.access_groups, - ) - - # Fall back to deprecated mcp_auth_header if no server-specific header found - if server_auth_header is None: - server_auth_header = mcp_auth_header + server_auth_header: Final = _server_auth_header_for(mcp_server, mcp_server_auth_headers, mcp_auth_header) # Extract subject token for OAuth2 Token Exchange (OBO) and ID-JAG flows subject_token: str | None = None @@ -6242,6 +6430,9 @@ class MCPServerManager: guardrail_context: Mapping[str, object] | None = None, client_ip: str | None = None, wire_compat: WireCompat = WireCompat.LEGACY, + *, + catalog_auth_header: str | None | EllipsisType = ..., + listed_tool: MCPTool | None | EllipsisType = ..., ) -> CallToolResult | InputRequiredResult: """ Call a tool with the given name and arguments @@ -6253,6 +6444,8 @@ class MCPServerManager: user_api_key_auth: User authentication mcp_auth_header: MCP auth header (deprecated) mcp_server_auth_headers: Optional dict of server-specific auth headers {server_alias: auth_value} + catalog_auth_header: The header the client supplied, keying the caller's catalog slot; + defaults to ``mcp_auth_header`` as received, before BYOK resolution proxy_logging_obj: Optional ProxyLogging object for hook integration litellm_logging_obj: Optional request logger the guardrail hooks record their evaluations onto, so MCP guardrail activity reaches the @@ -6264,6 +6457,7 @@ class MCPServerManager: """ start_time: Final = datetime.datetime.now() mcp_server: Final = self._resolve_mcp_server_for_tool_call(server_name, name) + client_auth_header: Final = _catalog_auth_header(mcp_auth_header, catalog_auth_header) # Resolved before any hook runs so a missing BYOK credential (401) never # leaves during-hook side effects (audit logging, rate-limit bookkeeping) @@ -6273,6 +6467,9 @@ class MCPServerManager: user_api_key_auth, mcp_auth_header, ) + listed_caller: Final = listed_tools_caller_for( + mcp_server, user_api_key_auth, client_auth_header, mcp_server_auth_headers, raw_headers, oauth2_headers + ) ######################################################### # Pre MCP Tool Call Hook @@ -6289,6 +6486,7 @@ class MCPServerManager: raw_headers=raw_headers, litellm_logging_obj=litellm_logging_obj, guardrail_context=guardrail_context, + tool=self.get_listed_tool(mcp_server, name, listed_caller) if listed_tool is ... else listed_tool, ) if "arguments" in hook_result: arguments = hook_result["arguments"] diff --git a/litellm/proxy/_experimental/mcp_server/operations.py b/litellm/proxy/_experimental/mcp_server/operations.py index f98a8c0ea5a..d83a4a72e2f 100644 --- a/litellm/proxy/_experimental/mcp_server/operations.py +++ b/litellm/proxy/_experimental/mcp_server/operations.py @@ -81,12 +81,14 @@ from litellm.proxy._experimental.mcp_server.faults.list_outcomes import ( outcome_wire_value, ) from litellm.proxy._experimental.mcp_server.mcp_server_manager import ( + ListedToolsCaller, MCPServerManager, _caller_authorization_fans_out, _client_forwarded_authorization_headers, _resolve_openapi_tool_auth, _should_strip_caller_authorization, global_mcp_server_manager, + listed_tools_caller_for, ) from litellm.proxy._experimental.mcp_server.oauth_utils import ( _redact_mcp_resource_url, @@ -954,6 +956,8 @@ async def _get_tools_from_mcp_servers( request_tags: list[str] | None = None, client_ip: str | None = None, mcp_proxy_mode: bool = False, + *, + record_listing: bool = False, ) -> AggregateToolListing: """ Helper method to fetch tools from MCP servers based on server filtering criteria. @@ -964,6 +968,8 @@ async def _get_tools_from_mcp_servers( mcp_servers: Optional list of server names/aliases to filter by mcp_server_auth_headers: Optional dict of server-specific auth headers oauth2_headers: Optional dict of oauth2 headers + record_listing: Record each served catalog into the caller's listed-tools slot; only a + listing actually served to the caller sets it Returns: AggregateToolListing: Combined tools from filtered servers plus each server's @@ -1111,12 +1117,14 @@ async def _get_tools_from_mcp_servers( prefetched_creds=_prefetched_oauth_creds, ) + catalog_auth_header: Final = server_auth_header if server.is_byok and server.auth_type != MCPAuth.oauth2 and server_auth_header is None: server_auth_header = await _get_byok_credential(server, user_api_key_auth) try: from litellm.proxy.proxy_server import proxy_logging_obj + listed_generation: Final = global_mcp_server_manager.listed_tools_generation(server.server_id) tools: Final = await global_mcp_server_manager._get_tools_from_server( server=server, mcp_auth_header=server_auth_header, @@ -1127,6 +1135,8 @@ async def _get_tools_from_mcp_servers( user_api_key_auth=user_api_key_auth, oauth2_headers=oauth2_headers, proxy_logging_obj=proxy_logging_obj, + catalog_auth_header=catalog_auth_header, + record_listing=False, ) filtered_tools = filter_tools_by_allowed_tools(tools, server) @@ -1135,6 +1145,21 @@ async def _get_tools_from_mcp_servers( server_id=server.server_id, user_api_key_auth=user_api_key_auth, ) + global_mcp_server_manager.record_listed_tools( + server, + [ + tool.model_copy(update={"name": strip_known_server_prefix(tool.name, server)}) + for tool in filtered_tools + ], + ListedToolsCaller( + user_api_key_auth=user_api_key_auth, + mcp_auth_header=catalog_auth_header, + raw_headers=raw_headers, + oauth2_headers=oauth2_headers, + ), + listed_generation, + record_listing=record_listing, + ) if mcp_proxy_mode: from litellm.proxy._experimental.mcp_server.tool_search import with_mcp_proxy_identity @@ -1458,6 +1483,8 @@ async def _list_mcp_tools( list_tools_log_source: str | None = None, client_ip: str | None = None, mcp_proxy_mode: bool = False, + *, + record_listing: bool = False, ) -> AggregateToolListing: """ List all available MCP tools. @@ -1468,6 +1495,8 @@ async def _list_mcp_tools( mcp_servers: Optional list of server names/aliases to filter by mcp_server_auth_headers: Optional dict of server-specific auth headers {server_alias: auth_value} client_ip: Client IP for IP-based server access control + record_listing: Record each served catalog into the caller's listed-tools slot; only a + listing actually served to the caller sets it Returns: AggregateToolListing: Combined tools from all accessible servers plus each server's @@ -1486,6 +1515,7 @@ async def _list_mcp_tools( list_tools_log_source=list_tools_log_source, client_ip=client_ip, mcp_proxy_mode=mcp_proxy_mode, + record_listing=record_listing, ) verbose_logger.debug("Successfully fetched %s tools from managed MCP servers", len(listing.tools)) return listing @@ -1798,6 +1828,7 @@ async def _list_tools_before_first_call( oauth2_headers=oauth2_headers, raw_headers=raw_headers, client_ip=client_ip, + record_listing=False, ) except Exception as e: # noqa: BLE001 # best effort: resolution below answers as it did before verbose_logger.debug("MCP tools/call: listing %s before its first call failed: %s", server.name, e) @@ -2001,6 +2032,7 @@ async def _execute_mcp_tool( if mcp_server is None: mcp_server = global_mcp_server_manager._get_mcp_server_from_tool_name(name) + client_auth_header: Final = mcp_auth_header if mcp_server: standard_logging_mcp_tool_call["mcp_server_cost_info"] = (mcp_server.mcp_info or {}).get("mcp_server_cost_info") if litellm_logging_obj: @@ -2071,6 +2103,18 @@ async def _execute_mcp_tool( raw_headers=raw_headers, litellm_logging_obj=litellm_logging_obj, guardrail_context=guardrail_context, + tool=global_mcp_server_manager.get_listed_tool( + mcp_server, + original_tool_name, + listed_tools_caller_for( + mcp_server, + user_api_key_auth, + client_auth_header, + mcp_server_auth_headers, + raw_headers, + oauth2_headers, + ), + ), ) # `pre_call_tool_check` may return guardrail-modified # arguments; honor them on the local path too. @@ -2120,6 +2164,7 @@ async def _execute_mcp_tool( arguments=arguments, user_api_key_auth=user_api_key_auth, mcp_auth_header=mcp_auth_header, + catalog_auth_header=client_auth_header, mcp_server_auth_headers=mcp_server_auth_headers, oauth2_headers=oauth2_headers, raw_headers=raw_headers, @@ -2139,7 +2184,8 @@ async def _execute_mcp_tool( # not in the registry either, `_handle_local_mcp_tool` below reports # 404 and nothing runs, so demanding a server here would turn every # unknown tool name into a misleading 503. - if global_mcp_tool_registry.get_tool(original_tool_name) is not None: + registered_local_tool: Final = global_mcp_tool_registry.get_tool(original_tool_name) + if registered_local_tool is not None: # `mcp_server` is None here because the tool name is not in the # tool -> server mapping, but the name still carries a prefix # that the server-level check above compared against the @@ -2181,6 +2227,18 @@ async def _execute_mcp_tool( raw_headers=raw_headers, litellm_logging_obj=litellm_logging_obj, guardrail_context=guardrail_context, + tool=global_mcp_server_manager.get_listed_tool( + prefix_server, + original_tool_name, + listed_tools_caller_for( + prefix_server, + user_api_key_auth, + client_auth_header, + mcp_server_auth_headers, + raw_headers, + oauth2_headers, + ), + ), ) if "arguments" in hook_result: arguments = hook_result["arguments"] # pyright: ignore[reportAny] # hook returns untyped args @@ -2583,8 +2641,12 @@ async def _handle_managed_mcp_tool( guardrail_context: Mapping[str, object] | None = None, client_ip: str | None = None, wire_compat: WireCompat = WireCompat.LEGACY, + *, + catalog_auth_header: str | None, ) -> CallToolResult | InputRequiredResult: - """Handle tool execution for managed server tools""" + """Handle tool execution for managed server tools. ``catalog_auth_header`` is the header the client + supplied, which keys the caller's catalog slot; ``mcp_auth_header`` may already be the resolved + BYOK credential.""" # Import here to avoid circular import from litellm.proxy.proxy_server import proxy_logging_obj @@ -2594,6 +2656,7 @@ async def _handle_managed_mcp_tool( arguments=arguments, user_api_key_auth=user_api_key_auth, mcp_auth_header=mcp_auth_header, + catalog_auth_header=catalog_auth_header, mcp_server_auth_headers=mcp_server_auth_headers, oauth2_headers=oauth2_headers, raw_headers=raw_headers, @@ -2712,6 +2775,7 @@ async def _execute_handle_list_tools( log_list_tools_to_spendlogs=log_list_tools_to_spendlogs, list_tools_log_source="mcp_protocol", client_ip=_client_ip, + record_listing=True, ) verbose_logger.info("MCP list_tools - Successfully returned %s tools", len(listing.tools)) if not listing.outcomes: diff --git a/litellm/proxy/_experimental/mcp_server/rest_endpoints.py b/litellm/proxy/_experimental/mcp_server/rest_endpoints.py index 7f936ec9269..845dcaa1f16 100644 --- a/litellm/proxy/_experimental/mcp_server/rest_endpoints.py +++ b/litellm/proxy/_experimental/mcp_server/rest_endpoints.py @@ -223,6 +223,7 @@ if MCP_AVAILABLE: ) from litellm.proxy._experimental.mcp_server.mcp_server_manager import ( _UPSTREAM_OAUTH_DISCOVERY_AUTH_TYPES, + ListedToolsCaller, global_mcp_server_manager, ) from litellm.proxy._experimental.mcp_server.oauth_utils import ( @@ -701,6 +702,8 @@ if MCP_AVAILABLE: extra_headers: dict[str, str] | None, client_ip: str | None, proxy_logging_obj: "ProxyLogging | None", + *, + record_listing: bool, ) -> list[MCPTool]: return await global_mcp_server_manager._get_tools_from_server( server=server, @@ -711,11 +714,12 @@ if MCP_AVAILABLE: client_ip=client_ip, user_api_key_auth=user_api_key_auth, proxy_logging_obj=proxy_logging_obj, + record_listing=record_listing, ) async def _get_tools_for_single_server( - server, - server_auth_header, + server: MCPServer, + server_auth_header: dict[str, str] | str | None, raw_headers: dict[str, str] | None = None, user_api_key_auth: UserAPIKeyAuth | None = None, extra_headers: dict[str, str] | None = None, @@ -731,31 +735,44 @@ if MCP_AVAILABLE: """ from litellm.proxy.proxy_server import proxy_logging_obj - tools = await _list_server_tools( - server, server_auth_header, raw_headers, user_api_key_auth, extra_headers, client_ip, proxy_logging_obj + listed_generation: Final = global_mcp_server_manager.listed_tools_generation(server.server_id) + tools: Final = await _list_server_tools( + server, + server_auth_header, + raw_headers, + user_api_key_auth, + extra_headers, + client_ip, + proxy_logging_obj, + record_listing=False, ) - if not apply_tool_filters: - return _create_tool_response_objects(tools, server) - - # Always apply allowed_tools/disallowed_tools so the blacklist is - # enforced even when no allowlist is set (matches the SSE/HTTP path). - tools = filter_tools_by_allowed_tools(tools, server) - - # Filter by the key's effective tool permissions through the same - # function the MCP protocol path uses (direct grants, toolset grants, - # and team/agent/org ceilings), so REST listing cannot drift from it. - # Entries here are tool names on one server, written bare by every - # writer, and dispatch compares them bare; matching a wider set of - # spellings would advertise a tool that tools/call then refuses - if user_api_key_auth: - tools = await filter_tools_by_key_team_permissions( - tools=tools, + server_filtered: Final = filter_tools_by_allowed_tools(tools, server) if apply_tool_filters else tools + served_tools: Final = ( + await filter_tools_by_key_team_permissions( + tools=server_filtered, server_id=server.server_id, user_api_key_auth=user_api_key_auth, ) + if apply_tool_filters and user_api_key_auth + else server_filtered + ) + if apply_tool_filters: + # Only a listing shaped for the caller's runtime view may set their + # listed-tools slot; the admin-only unfiltered configuration view + # must not warm it. + global_mcp_server_manager.record_listed_tools( + server, + served_tools, + ListedToolsCaller( + user_api_key_auth=user_api_key_auth, + mcp_auth_header=server_auth_header, + raw_headers=raw_headers, + ), + listed_generation, + ) - return _create_tool_response_objects(tools, server) + return _create_tool_response_objects(served_tools, server) async def fetch_pinnable_tool_catalog( server: MCPServer, request: Request, user_api_key_dict: UserAPIKeyAuth @@ -774,6 +791,7 @@ if MCP_AVAILABLE: await _get_user_oauth_extra_headers(server, user_api_key_dict), IPAddressUtils.get_mcp_client_ip(request), None, + record_listing=False, ) scan: Final = await scan_tool_descriptions( apply_description_overrides(upstream, server), server, proxy_logging_obj, user_api_key_dict, raw_headers diff --git a/litellm/proxy/guardrails/guardrail_hooks/agent_365/agent_365.py b/litellm/proxy/guardrails/guardrail_hooks/agent_365/agent_365.py index 6621d94ed96..c683e1f2c5d 100644 --- a/litellm/proxy/guardrails/guardrail_hooks/agent_365/agent_365.py +++ b/litellm/proxy/guardrails/guardrail_hooks/agent_365/agent_365.py @@ -19,7 +19,7 @@ from typing import TYPE_CHECKING, ClassVar, Final, Literal, NoReturn import httpx from fastapi import HTTPException -from pydantic import TypeAdapter, ValidationError +from pydantic import BaseModel, ConfigDict, Field, TypeAdapter, ValidationError from typing_extensions import ReadOnly, TypedDict from litellm._logging import verbose_proxy_logger @@ -61,6 +61,7 @@ _GATEWAY_OWNED_TOKEN_ERRORS: Final = frozenset( _INVALID_ASSERTION_AADSTS_PREFIX: Final = "50027" _AADSTS_CODES_ADAPTER: Final = TypeAdapter(tuple[int, ...]) _MCP_CALL_TYPES: Final[tuple[str, ...]] = ("mcp_call", "call_mcp_tool") +_TOOL_INPUT_SCHEMA_ADAPTER: Final = TypeAdapter(dict[str, object]) _OBO_CACHE_MAX_ENTRIES: Final = 1000 _DEFAULT_TOKEN_TTL_SECONDS: Final = 3599.0 _TOKEN_EXPIRY_SLACK_SECONDS: Final = 60.0 @@ -82,6 +83,13 @@ def _parse_aadsts_codes(raw: object) -> tuple[int, ...]: return () +def _parse_tool_input_schema(raw: object) -> Mapping[str, object] | None: + try: + return _TOOL_INPUT_SCHEMA_ADAPTER.validate_python(raw) + except ValidationError: + return None + + def entra_assertion(value: object) -> str | None: """``value`` when it is a compact JWS, the only bearer shape the OBO exchange accepts as its assertion. A LiteLLM virtual key, session bearer, or opaque upstream token in ``Authorization`` yields ``None``.""" @@ -100,6 +108,14 @@ class _EvaluateResponse(TypedDict, total=False): correlationId: ReadOnly[str] +class _ToolReference(BaseModel): + model_config = ConfigDict(frozen=True) + + name: str + description: str | None = None + input_schema: Mapping[str, object] | None = Field(default=None, serialization_alias="inputSchema") + + class _UnavailableDetail(TypedDict): error: ReadOnly[str] message: ReadOnly[str] @@ -392,8 +408,14 @@ class Agent365Guardrail(CustomGuardrail): arguments: Final = data.get("mcp_arguments") server_name: Final = str(data.get("mcp_server_name") or "litellm") agent_id: Final = user_api_key_dict.key_alias + description: Final = data.get("mcp_tool_description") + tool_reference: Final = _ToolReference( + name=tool_name, + description=description if isinstance(description, str) and description else None, + input_schema=_parse_tool_input_schema(data.get("mcp_input_schema")), + ) payload: Final[dict[str, object]] = { # mutable-ok: JSON body with optional fields added below - "tool": {"name": tool_name}, + "tool": tool_reference.model_dump(by_alias=True, exclude_none=True), "serverName": server_name, "conversationId": self._resolve_conversation_id(data), } diff --git a/litellm/proxy/lens/release.py b/litellm/proxy/lens/release.py index 0338858a6a5..c5256e3ed4e 100644 --- a/litellm/proxy/lens/release.py +++ b/litellm/proxy/lens/release.py @@ -32,4 +32,5 @@ def worker_image() -> str: override: Final = os.environ.get("LENS_WORKER_IMAGE", "") if override: return override - return f"ghcr.io/berriai/litellm-lens-worker:{tag}" + package: Final = "litellm-lens-worker-dev" if tag.startswith("sha-") else "litellm-lens-worker" + return f"ghcr.io/berriai/{package}:{tag}" diff --git a/litellm/proxy/management_endpoints/mcp_management_endpoints.py b/litellm/proxy/management_endpoints/mcp_management_endpoints.py index be4e46f247e..e1504172d9e 100644 --- a/litellm/proxy/management_endpoints/mcp_management_endpoints.py +++ b/litellm/proxy/management_endpoints/mcp_management_endpoints.py @@ -1018,6 +1018,7 @@ if MCP_AVAILABLE: mcp_auth_header=None, mcp_servers=None, mcp_server_auth_headers=None, + record_listing=True, ) tools: Final = listing.tools dumped_tools: Final = [tool.model_dump(by_alias=True) for tool in tools] diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py index 8af90e19ecb..1c738aefb97 100644 --- a/litellm/proxy/utils.py +++ b/litellm/proxy/utils.py @@ -1151,6 +1151,8 @@ def _overrides_moderation_hook(callback: CustomLogger) -> bool: _LISTED_MODEL_NAMES: Final = TypeAdapter(tuple[str, ...]) +_MCP_TOOL_DESCRIPTION: Final[TypeAdapter[str | None]] = TypeAdapter(str | None) +_MCP_TOOL_INPUT_SCHEMA: Final[TypeAdapter[Mapping[str, object] | None]] = TypeAdapter(Mapping[str, object] | None) @dataclass(frozen=True, slots=True) @@ -1475,9 +1477,14 @@ class ProxyLogging: TypeAdapter(dict[str, object]).validate_python(guardrail_context.get("metadata") or MappingProxyType({})) ) - mcp_tool_description: Final = kwargs.get("mcp_tool_description") - mcp_input_schema: Final = kwargs.get("mcp_input_schema") - description_line: Final = f"\nDescription: {mcp_tool_description}" if mcp_tool_description else "" + mcp_tool_description: Final = request_obj.tool_description or kwargs.get("mcp_tool_description") + mcp_input_schema: Final = ( + request_obj.tool_input_schema + if request_obj.tool_input_schema is not None + else kwargs.get("mcp_input_schema") + ) + listing_description: Final = kwargs.get("mcp_tool_description") + description_line: Final = f"\nDescription: {listing_description}" if listing_description else "" tool_call_content: Final = ( f"Tool: {request_obj.tool_name}{description_line}\nArguments: {request_obj.arguments}" ) @@ -1735,6 +1742,8 @@ class ProxyLogging: tool_name=kwargs.get("name", ""), arguments=kwargs.get("arguments", {}), server_name=kwargs.get("server_name"), + tool_description=_MCP_TOOL_DESCRIPTION.validate_python(kwargs.get("tool_description")), + tool_input_schema=_MCP_TOOL_INPUT_SCHEMA.validate_python(kwargs.get("tool_input_schema")), user_api_key_auth=user_api_key_auth_dict, hidden_params=HiddenParams(), ) diff --git a/litellm/responses/main.py b/litellm/responses/main.py index 14c12fc571d..5e2793ed40d 100644 --- a/litellm/responses/main.py +++ b/litellm/responses/main.py @@ -286,6 +286,7 @@ async def aresponses_api_with_mcp( call_params=call_params, previous_response_id=previous_response_id, tool_server_map=tool_server_map, + served_tools=original_mcp_tools, **kwargs, ) await mcp_streaming_response._create_initial_response_iterator() @@ -339,6 +340,7 @@ async def aresponses_api_with_mcp( tool_results: Final = await LiteLLM_Proxy_MCP_Handler._execute_tool_calls( tool_server_map=tool_server_map, + served_tools=original_mcp_tools, tool_calls=tool_calls, user_api_key_auth=user_api_key_auth, mcp_auth_header=mcp_auth_header, @@ -395,6 +397,7 @@ async def aresponses_api_with_mcp( final_response = MCPEnhancedStreamingIterator( tool_server_map=tool_server_map, + served_tools=original_mcp_tools, base_iterator=final_response, mcp_events=tool_execution_events, user_api_key_auth=user_api_key_auth, diff --git a/litellm/responses/mcp/chat_completions_handler.py b/litellm/responses/mcp/chat_completions_handler.py index b17e0befba6..8aa4181cc8a 100644 --- a/litellm/responses/mcp/chat_completions_handler.py +++ b/litellm/responses/mcp/chat_completions_handler.py @@ -435,6 +435,7 @@ async def acompletion_with_mcp( # Execute tool calls self.tool_results = await LiteLLM_Proxy_MCP_Handler._execute_tool_calls( tool_server_map=self.tool_server_map, + served_tools=deduplicated_mcp_tools, tool_calls=self.tool_calls, user_api_key_auth=self.user_api_key_auth, mcp_auth_header=self.mcp_auth_header, @@ -609,6 +610,7 @@ async def acompletion_with_mcp( tool_results: Final = await LiteLLM_Proxy_MCP_Handler._execute_tool_calls( tool_server_map=tool_server_map, tool_calls=tool_calls, + served_tools=deduplicated_mcp_tools, user_api_key_auth=user_api_key_auth, mcp_auth_header=mcp_auth_header, mcp_server_auth_headers=mcp_server_auth_headers, diff --git a/litellm/responses/mcp/litellm_proxy_mcp_handler.py b/litellm/responses/mcp/litellm_proxy_mcp_handler.py index fb7882adcb4..1d6c0695621 100644 --- a/litellm/responses/mcp/litellm_proxy_mcp_handler.py +++ b/litellm/responses/mcp/litellm_proxy_mcp_handler.py @@ -696,6 +696,7 @@ class LiteLLM_Proxy_MCP_Handler: litellm_trace_id: str | None = None, request_tags: list[str] | None = None, guardrail_context: Mapping[str, object] | None = None, + served_tools: Sequence[MCPTool] | None = None, ) -> list[MCPToolResult]: """Execute tool calls and return results.""" from fastapi import HTTPException @@ -860,6 +861,11 @@ class LiteLLM_Proxy_MCP_Handler: proxy_logging_obj=proxy_logging_obj, litellm_logging_obj=litellm_logging_obj, guardrail_context=guardrail_context, + listed_tool=( + next((tool for tool in served_tools if tool.name == tool_name), None) + if served_tools is not None + else ... + ), ) if proxy_logging_obj: @@ -1152,6 +1158,7 @@ class LiteLLM_Proxy_MCP_Handler: call_params: Mapping[str, object], previous_response_id: str | None, tool_server_map: dict[str, str], + served_tools: Sequence[MCPTool] | None = None, **kwargs, ) -> Any: """ @@ -1181,6 +1188,7 @@ class LiteLLM_Proxy_MCP_Handler: base_iterator=None, # Will be created internally mcp_events=mcp_discovery_events, # Pre-generated MCP discovery events tool_server_map=tool_server_map, + served_tools=served_tools, mcp_tools_with_litellm_proxy=mcp_tools_with_litellm_proxy, user_api_key_auth=kwargs.get("user_api_key_auth") or kwargs.get("litellm_metadata", {}).get("user_api_key_auth"), diff --git a/litellm/responses/mcp/mcp_streaming_iterator.py b/litellm/responses/mcp/mcp_streaming_iterator.py index c0bb92cfb2a..b1f12233f33 100644 --- a/litellm/responses/mcp/mcp_streaming_iterator.py +++ b/litellm/responses/mcp/mcp_streaming_iterator.py @@ -281,6 +281,7 @@ class MCPEnhancedStreamingIterator(BaseResponsesAPIStreamingIterator): mcp_tools_with_litellm_proxy: Sequence[Mapping[str, object]] | None = None, user_api_key_auth: "UserAPIKeyAuth | None" = None, original_request_params: dict[str, Any] | None = None, + served_tools: Sequence[MCPTool] | None = None, ): # MCP setup self.mcp_tools_with_litellm_proxy = mcp_tools_with_litellm_proxy or [] @@ -300,6 +301,7 @@ class MCPEnhancedStreamingIterator(BaseResponsesAPIStreamingIterator): self.mcp_discovery_generated = True # Events are already generated self.mcp_events = mcp_events # Store the initial MCP events for backward compatibility self.tool_server_map = tool_server_map + self.served_tools = tuple(served_tools) if served_tools is not None else None # Iterator references self.base_iterator: BaseResponsesAPIStreamingIterator | ResponsesAPIResponse | None = ( @@ -796,6 +798,7 @@ class MCPEnhancedStreamingIterator(BaseResponsesAPIStreamingIterator): # Execute the tools tool_results: Final = await LiteLLM_Proxy_MCP_Handler._execute_tool_calls( tool_server_map=self.tool_server_map, + served_tools=self.served_tools, tool_calls=tool_calls, user_api_key_auth=self.user_api_key_auth, mcp_auth_header=self.mcp_auth_header, diff --git a/litellm/tool_loop.py b/litellm/tool_loop.py new file mode 100644 index 00000000000..64d6de51818 --- /dev/null +++ b/litellm/tool_loop.py @@ -0,0 +1,172 @@ +"""Client-side tool-calling loop helpers for litellm.completion.""" + +from collections.abc import Awaitable, Callable, Sequence +from typing import TypeAlias, cast + +from typing_extensions import TypedDict, Unpack + +from litellm.constants import DEFAULT_TOOL_LOOP_MAX_ROUNDS +from litellm.types.llms.openai import ( + AllMessageValues, + ChatCompletionAssistantMessage, + ChatCompletionAssistantToolCall, + ChatCompletionToolCallFunctionChunk, + ChatCompletionToolMessage, + ChatCompletionToolParam, +) +from litellm.types.utils import ChatCompletionMessageToolCall, Message, ModelResponse + +ToolExecutor: TypeAlias = Callable[[ChatCompletionMessageToolCall], ChatCompletionToolMessage] +AsyncToolExecutor: TypeAlias = Callable[[ChatCompletionMessageToolCall], Awaitable[ChatCompletionToolMessage]] + + +class _ToolLoopCompletionKwargs(TypedDict, total=False, extra_items=object): + """Extra keywords forwarded verbatim to ``litellm.completion``, which owns their contract.""" + + +class ToolLoopMaxRoundsExceeded(RuntimeError): + max_rounds: int + + def __init__(self, max_rounds: int) -> None: + self.max_rounds = max_rounds + super().__init__(f"model still requested tool calls on round {max_rounds} of {max_rounds}") + + +def _validate_tool_loop_args(max_rounds: int, completion_kwargs: _ToolLoopCompletionKwargs) -> None: + if max_rounds < 1: + raise ValueError(f"max_rounds must be >= 1, got {max_rounds}") + if completion_kwargs.get("stream"): + raise ValueError("run_tool_loop requires whole responses; stream=True is not supported") + + +def _expect_model_response(response: object) -> ModelResponse: + if not isinstance(response, ModelResponse): + raise TypeError(f"run_tool_loop requires completion to return a ModelResponse, got {type(response).__name__}") + return response + + +def _assistant_tool_call(tool_call: ChatCompletionMessageToolCall) -> ChatCompletionAssistantToolCall: + return ChatCompletionAssistantToolCall( + id=tool_call.id, + type="function", + function=ChatCompletionToolCallFunctionChunk( + name=tool_call.function.name, arguments=tool_call.function.arguments + ), + ) + + +def _assistant_message( + message: Message, tool_calls: tuple[ChatCompletionMessageToolCall, ...] +) -> ChatCompletionAssistantMessage: + return cast( # cast-ok: dict literal with thinking_blocks and reasoning_items spread in only when set + "ChatCompletionAssistantMessage", + { + "role": "assistant", + "content": message.content, + "tool_calls": [_assistant_tool_call(tc) for tc in tool_calls], + **{ + key: value + for key, value in ( + ("thinking_blocks", getattr(message, "thinking_blocks", None)), + ("reasoning_items", getattr(message, "reasoning_items", None)), + ) + if value is not None + }, + }, + ) + + +def _function_tool_call(tool_call: object) -> ChatCompletionMessageToolCall: + if not isinstance(tool_call, ChatCompletionMessageToolCall): + raise TypeError( + f"run_tool_loop only executes function tool calls, got custom tool call {getattr(tool_call, 'id', None)}" + ) + return tool_call + + +def _function_tool_calls(message: Message) -> tuple[ChatCompletionMessageToolCall, ...]: + return tuple(_function_tool_call(tool_call) for tool_call in message.tool_calls or ()) + + +def run_tool_loop( + *, + model: str, + messages: Sequence[AllMessageValues], + tools: Sequence[ChatCompletionToolParam], + execute_tool: ToolExecutor, + max_rounds: int = DEFAULT_TOOL_LOOP_MAX_ROUNDS, + **completion_kwargs: Unpack[_ToolLoopCompletionKwargs], # kwargs-ok: forwarded verbatim to litellm.completion +) -> str | None: + """Call completion, execute each requested tool, and repeat until the model answers. + + Returns the final assistant message content. Raises ToolLoopMaxRoundsExceeded when the + model is still requesting tools after max_rounds completions. + + Example: + execute = functools.partial(run_repo_tool, repository="litellm", revision="main") + answer = litellm.run_tool_loop( + model="anthropic/claude-sonnet-5-5", messages=messages, tools=tools, execute_tool=execute + ) + """ + import litellm + + _validate_tool_loop_args(max_rounds, completion_kwargs) + history: tuple[AllMessageValues, ...] = tuple(messages) # rebind-ok: rounds append new turns + for round_number in range(1, max_rounds + 1): + message = ( + _expect_model_response( + litellm.completion(model=model, messages=list(history), tools=list(tools), **completion_kwargs) + ) + .choices[0] + .message + ) + if not message.tool_calls: + return message.content + tool_calls = _function_tool_calls(message) + if round_number == max_rounds: + break + tool_results = tuple(execute_tool(tool_call) for tool_call in tool_calls) + history = (*history, _assistant_message(message, tool_calls), *tool_results) + raise ToolLoopMaxRoundsExceeded(max_rounds) + + +async def arun_tool_loop( + *, + model: str, + messages: Sequence[AllMessageValues], + tools: Sequence[ChatCompletionToolParam], + execute_tool: AsyncToolExecutor, + max_rounds: int = DEFAULT_TOOL_LOOP_MAX_ROUNDS, + **completion_kwargs: Unpack[_ToolLoopCompletionKwargs], # kwargs-ok: forwarded verbatim to litellm.acompletion +) -> str | None: + """Async version of run_tool_loop, awaiting each execute_tool call in order. + + Returns the final assistant message content. Raises ToolLoopMaxRoundsExceeded when the + model is still requesting tools after max_rounds completions. + + Example: + execute = functools.partial(arun_repo_tool, repository="litellm", revision="main") + answer = await litellm.arun_tool_loop( + model="anthropic/claude-sonnet-5-5", messages=messages, tools=tools, execute_tool=execute + ) + """ + import litellm + + _validate_tool_loop_args(max_rounds, completion_kwargs) + history: tuple[AllMessageValues, ...] = tuple(messages) # rebind-ok: rounds append new turns + for round_number in range(1, max_rounds + 1): + message = ( + _expect_model_response( + await litellm.acompletion(model=model, messages=list(history), tools=list(tools), **completion_kwargs) + ) + .choices[0] + .message + ) + if not message.tool_calls: + return message.content + tool_calls = _function_tool_calls(message) + if round_number == max_rounds: + break + tool_results = tuple([await execute_tool(tool_call) for tool_call in tool_calls]) + history = (*history, _assistant_message(message, tool_calls), *tool_results) + raise ToolLoopMaxRoundsExceeded(max_rounds) diff --git a/litellm/types/mcp.py b/litellm/types/mcp.py index da7401e2a2e..ce86e79a6f0 100644 --- a/litellm/types/mcp.py +++ b/litellm/types/mcp.py @@ -429,6 +429,8 @@ class MCPPreCallRequestObject(BaseModel): tool_name: str arguments: dict[str, Any] server_name: str | None = None + tool_description: str | None = None + tool_input_schema: Mapping[str, object] | None = None user_api_key_auth: dict[str, Any] | None = None hidden_params: HiddenParams = HiddenParams() @@ -452,6 +454,8 @@ class MCPDuringCallRequestObject(BaseModel): tool_name: str arguments: dict[str, Any] server_name: str | None = None + tool_description: str | None = None + tool_input_schema: Mapping[str, object] | None = None start_time: float | None = None hidden_params: HiddenParams = HiddenParams() diff --git a/pyproject.toml b/pyproject.toml index d765bccb552..f04e66a04eb 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -34,6 +34,7 @@ dependencies = [ "pydantic-settings>=2.14.1,<3.0", "jsonschema>=4.0.0,<5.0", "boto3>=1.43.1,<2.0", + "typing-extensions>=4.13.0,<5.0", ] [project.urls] diff --git a/scripts/lens_dev.sh b/scripts/lens_dev.sh index 46408fdaf19..d8918f02fc5 100755 --- a/scripts/lens_dev.sh +++ b/scripts/lens_dev.sh @@ -25,6 +25,8 @@ py="${LENS_DEV_PYTHON:-$repo_root/.venv/bin/python}" database_url="${LENS_DEV_DATABASE_URL:-postgresql://litellm:litellm@127.0.0.1:15432/litellm}" clickhouse_url=http://default:local-tracing@127.0.0.1:18123 master_key="" +startup_timeout="${LENS_DEV_STARTUP_TIMEOUT_SECONDS:-300}" +readiness_request_timeout="${LENS_DEV_READINESS_REQUEST_TIMEOUT_SECONDS:-5}" pids=() die() { echo "lens-dev: $*" >&2; exit 1; } @@ -121,6 +123,7 @@ proxy_env() { export CLICKHOUSE_DATABASE=litellm export LITELLM_LOCAL_MODEL_COST_MAP=True export PROXY_BASE_URL="$proxy_url" + export LITELLM_UI_PATH="$repo_root/ui/litellm-dashboard/out" export UI_USERNAME=admin export UI_PASSWORD="$master_key" } @@ -161,12 +164,26 @@ ensure_worker_token() { wait_for_proxy() { local proxy_pid="$1" echo "lens-dev: waiting for the proxy (log: $log_dir/proxy.log)" - for _ in $(seq 1 300); do + for _ in $(seq 1 "$startup_timeout"); do kill -0 "$proxy_pid" 2>/dev/null || die "proxy exited; see $log_dir/proxy.log" - curl -fsS "$proxy_url/health/readiness" -H "Authorization: Bearer $master_key" >/dev/null 2>&1 && return + curl -fsS --max-time "$readiness_request_timeout" "$proxy_url/health/readiness" -H "Authorization: Bearer $master_key" >/dev/null 2>&1 && return sleep 1 done - die "proxy not ready after 300s; see $log_dir/proxy.log" + die "proxy not ready after ${startup_timeout}s; see $log_dir/proxy.log" +} + +wait_for_ui() { + local ui_pid="$1" + echo "lens-dev: waiting for the UI (log: $log_dir/ui.log)" + for _ in $(seq 1 "$startup_timeout"); do + kill -0 "$ui_pid" 2>/dev/null || die "UI exited; see $log_dir/ui.log" + if curl -fsS --max-time "$readiness_request_timeout" "http://localhost:$ui_port/ui/login/" >/dev/null 2>&1; then + kill -0 "$ui_pid" 2>/dev/null || die "UI exited; see $log_dir/ui.log" + return + fi + sleep 1 + done + die "UI not ready after ${startup_timeout}s; see $log_dir/ui.log" } # Children run in their own process groups (set -m), so killing -pid takes their trees too. @@ -185,14 +202,71 @@ cleanup() { for pid in "${pids[@]}"; do kill -KILL -- "-$pid" 2>/dev/null || true; done } +build_dashboard() { + local dashboard_dir="$repo_root/ui/litellm-dashboard" + case "${LENS_DEV_BUILD_UI:-0}" in + 0) return ;; + 1) ;; + *) die "LENS_DEV_BUILD_UI must be 0 or 1" ;; + esac + echo "lens-dev: building the proxy dashboard (log: $log_dir/ui-build.log)" + ( + cd "$dashboard_dir" + NEXT_PUBLIC_BASE_URL="" LENS_DEV_PROXY_URL="" "$repo_root/scripts/with_dashboard_node.sh" npm run build + ) > "$log_dir/ui-build.log" 2>&1 || die "UI build failed; see $log_dir/ui-build.log" +} + +seed_data() { + ( + proxy_env "" + "$py" -m scripts.seed_tracing_fixtures --profile "$seed_profile" ${seed_options[@]+"${seed_options[@]}"} + ) +} + +parse_args() { + seed_profile="${LENS_DEV_SEED:-}" + seed_only=0 + seed_options=() + while [ "$#" -gt 0 ]; do + case "$1" in + --seed) + seed_profile=default + if [ "${2:-}" = default ] || [ "${2:-}" = large ]; then seed_profile="$2"; shift; fi + ;; + --copies) + [ "$#" -ge 2 ] && [[ "$2" =~ ^[1-9][0-9]*$ ]] || die "--copies requires a positive integer" + seed_options=(--copies "$2"); shift ;; + --seed-only) seed_only=1 ;; + --help) + echo "Usage: $0 [--seed [default|large]] [--copies N] [--seed-only]" + exit 0 ;; + *) die "unknown argument: $1 (use --help)" ;; + esac + shift + done + if [ "$seed_only" = 1 ] && [ -z "$seed_profile" ]; then seed_profile=default; fi + case "$seed_profile" in ""|default|large) ;; *) die "seed profile must be default or large" ;; esac + [ "${#seed_options[@]}" = 0 ] || [ -n "$seed_profile" ] || die "--copies requires --seed" +} + main() { - local config_file exports proxy_pid pid key_hint + local config_file exports proxy_pid ui_pid pid key_hint + parse_args "$@" if [ -n "${LENS_DEV_CONFIG:-}" ]; then [ -f "$LENS_DEV_CONFIG" ] || die "LENS_DEV_CONFIG not found: $LENS_DEV_CONFIG" config_file="$(cd "$(dirname "$LENS_DEV_CONFIG")" && pwd)/$(basename "$LENS_DEV_CONFIG")" fi cd "$repo_root" + if [ "$seed_only" = 1 ]; then + [ -s "$key_file" ] || [ -n "${LENS_DEV_MASTER_KEY:-}" ] || die "start make lens-dev before --seed-only" + load_master_key + seed_data + return + fi + + [[ "$startup_timeout" =~ ^[1-9][0-9]*$ ]] || die "LENS_DEV_STARTUP_TIMEOUT_SECONDS must be a positive integer" + [[ "$readiness_request_timeout" =~ ^[1-9][0-9]*$ ]] || die "LENS_DEV_READINESS_REQUEST_TIMEOUT_SECONDS must be a positive integer" listening "$proxy_port" && die "port $proxy_port is in use; set LENS_DEV_PROXY_PORT" listening "$ui_port" && die "port $ui_port is in use; set LENS_DEV_UI_PORT" [ "$proxy_port" != "$ui_port" ] || die "proxy and UI ports must differ" @@ -213,6 +287,8 @@ main() { (cd ui/litellm-dashboard && "$repo_root/scripts/with_dashboard_node.sh" npm ci) fi + build_dashboard + if [ -z "${config_file:-}" ]; then config_file="$state_dir/config.yaml" write_default_config "$config_file" @@ -225,6 +301,7 @@ main() { ( proxy_env "$exports" + export PROXY_BASE_URL="http://localhost:$ui_port" exec "$py" litellm/proxy/proxy_cli.py --config "$config_file" --host 127.0.0.1 --port "$proxy_port" ) < /dev/null > "$log_dir/proxy.log" 2>&1 & proxy_pid=$! @@ -232,12 +309,15 @@ main() { ( cd ui/litellm-dashboard - NEXT_PUBLIC_BASE_URL="$proxy_url" exec "$repo_root/scripts/with_dashboard_node.sh" npx next dev -p "$ui_port" + NEXT_PUBLIC_BASE_URL="" LENS_DEV_PROXY_URL="$proxy_url" exec "$repo_root/scripts/with_dashboard_node.sh" npx next dev -p "$ui_port" ) < /dev/null > "$log_dir/ui.log" 2>&1 & - pids+=("$!") + ui_pid=$! + pids+=("$ui_pid") + wait_for_ui "$ui_pid" wait_for_proxy "$proxy_pid" ensure_worker_token + if [ -n "$seed_profile" ]; then seed_data; fi LITELLM_RELEASE_TAG="$source_release_tag" \ LITELLM_MODE=PRODUCTION LITELLM_URL="$proxy_url" LENS_WORKER_TOKEN="$(cat "$token_file")" \ @@ -250,12 +330,13 @@ main() { cat <&2; exit 2 ;; -esac - -if lsof -nP -iTCP:4002 -sTCP:LISTEN >/dev/null 2>&1; then - echo "Port 4002 is already in use. Stop the existing proxy before starting this stack" >&2 - exit 1 -fi - -docker compose -f docker/docker-compose.tracing.yml up -d --wait db clickhouse -uv sync --inexact --frozen --extra proxy --group proxy-dev --no-install-project -"$repo_root/.venv/bin/python" scripts/prisma_generate_if_needed.py -VIRTUAL_ENV="$repo_root/.venv" uvx --from maturin==1.15.0 maturin develop \ - --release --manifest-path litellm-rust/crates/python-bridge/Cargo.toml --features extension-module - -config_file="$(mktemp "${TMPDIR:-/tmp}/litellm-tracing-local.XXXXXX")" -proxy_pid="" -cleanup() { - if [ -n "$proxy_pid" ]; then - kill "$proxy_pid" 2>/dev/null || true - wait "$proxy_pid" 2>/dev/null || true - fi - rm -f "$config_file" -} -trap cleanup EXIT -trap 'exit 130' INT TERM -cat > "$config_file" <<'EOF' -model_list: - - model_name: openai/gpt-6-luna - litellm_params: - model: openai/gpt-6-luna - api_key: os.environ/OPENAI_API_KEY -general_settings: - master_key: os.environ/LITELLM_MASTER_KEY - store_prompts_in_spend_logs: true - tracing: - store: - type: clickhouse - url: os.environ/CLICKHOUSE_URL - retention_days: 14 -EOF - -export LITELLM_MASTER_KEY=sk-1234 -export LITELLM_DANGEROUSLY_PERMIT_WEAK_OR_UNSET_MASTER_KEY=true -export LITELLM_SALT_KEY=sk-local-tracing-salt-key -export DATABASE_URL=postgresql://litellm:litellm@127.0.0.1:15432/litellm -export STORE_MODEL_IN_DB=True -export CLICKHOUSE_URL=http://default:local-tracing@127.0.0.1:18123 -export CLICKHOUSE_DATABASE=litellm -export LITELLM_LOCAL_MODEL_COST_MAP=True -export PROXY_BASE_URL=http://127.0.0.1:4002 - -( - cd "$repo_root/ui/litellm-dashboard" - "$repo_root/scripts/with_dashboard_node.sh" npm ci - NEXT_PUBLIC_BASE_URL= "$repo_root/scripts/with_dashboard_node.sh" npm run build -) -export LITELLM_UI_PATH="$repo_root/ui/litellm-dashboard/out" - -printf 'Dashboard: http://127.0.0.1:4002/ui/\nProxy: http://127.0.0.1:4002\nMaster key: %s\n' "$LITELLM_MASTER_KEY" -"$repo_root/.venv/bin/python" litellm/proxy/proxy_cli.py \ - --config "$config_file" --host 127.0.0.1 --port 4002 & -proxy_pid=$! - -if [ "$seed_fixtures" = "1" ]; then - ready=0 - for attempt in $(seq 1 180); do - kill -0 "$proxy_pid" 2>/dev/null || { echo "Proxy exited before seeding" >&2; exit 1; } - if curl --fail --silent "$PROXY_BASE_URL/health/readiness" \ - -H "Authorization: Bearer $LITELLM_MASTER_KEY" >/dev/null; then - ready=1 - break - fi - sleep 1 - done - [ "$ready" = "1" ] || { echo "Proxy did not become ready within 180 seconds" >&2; exit 1; } - "$repo_root/.venv/bin/python" -m scripts.seed_tracing_fixtures -fi - -wait "$proxy_pid" +echo "run_tracing_proxy_local.sh is deprecated; use make lens-dev" >&2 +exec "$repo_root/scripts/lens_dev.sh" "$@" diff --git a/scripts/seed_tracing_fixtures.py b/scripts/seed_tracing_fixtures.py index d482b265784..3febe49c451 100644 --- a/scripts/seed_tracing_fixtures.py +++ b/scripts/seed_tracing_fixtures.py @@ -1,5 +1,6 @@ from __future__ import annotations +import argparse import asyncio import base64 import binascii @@ -10,32 +11,31 @@ import os import re import sys import time -from collections.abc import Iterator +from collections.abc import Iterator, Mapping, Sequence from dataclasses import dataclass from datetime import datetime, timezone +from functools import cache from itertools import chain from pathlib import Path from types import MappingProxyType -from typing import TYPE_CHECKING, Final +from typing import TYPE_CHECKING, Final, Literal from uuid import uuid4 import httpx from pydantic import BaseModel, ConfigDict, JsonValue, TypeAdapter from litellm.rust_bridge.trace.generated.types import AllQueryScope, Trace -from litellm.rust_bridge.trace.storage import ClickHouseStorage +from litellm.rust_bridge.trace.storage import ClickHouseStorage, Tenant, span_rows from litellm.tracing.config import trace_storage_config from litellm.tracing.types import SpendLogRecord if TYPE_CHECKING: + from prisma import Prisma from prisma.types import LiteLLM_SpendLogsCreateWithoutRelationsInput REPO_ROOT: Final = Path(__file__).resolve().parents[1] TRACE_FIXTURES: Final = REPO_ROOT / "litellm-rust/crates/traces/tests/fixtures" -SPEND_FIXTURE: Final = ( - REPO_ROOT / "litellm-rust/crates/traces-clickhouse/tests/fixtures/deeplite_swarm_spend_logs.jsonl" -) -SPEND_FIXTURES: Final = SPEND_FIXTURE.parent +SPEND_FIXTURES: Final = REPO_ROOT / "litellm-rust/crates/traces-clickhouse/tests/fixtures" JSON: Final[TypeAdapter[JsonValue]] = TypeAdapter(JsonValue) JSON_OBJECT: Final = TypeAdapter(dict[str, JsonValue]) SPEND_ROWS: Final = TypeAdapter(tuple[SpendLogRecord, ...]) @@ -103,7 +103,9 @@ def response_ids(rows: tuple[SpendLogRecord, ...]) -> Iterator[str]: def response_pattern(rows: tuple[SpendLogRecord, ...]) -> re.Pattern[str]: identities: Final = sorted( - frozenset(filter(None, chain(response_ids(rows), (row["litellm_call_id"] for row in rows)))), + frozenset( + identity for identity in chain(response_ids(rows), (row["litellm_call_id"] for row in rows)) if identity + ), key=len, reverse=True, ) @@ -118,12 +120,15 @@ def rebased_response(value: str, namespace: str, pattern: re.Pattern[str]) -> st return "resp_" + base64.b64encode(payload.encode()).decode() +@cache +def fixture_exports(directory: Path) -> tuple[tuple[str, JsonValue], ...]: + return tuple((path.stem, JSON.validate_json(path.read_bytes())) for path in sorted(directory.glob("*.json"))) + + def fixture_replays( directory: Path, now_ms: int, namespace: str, response_pattern: re.Pattern[str] ) -> tuple[FixtureReplay, ...]: - exports: Final = tuple( - (path.stem, JSON.validate_json(path.read_bytes())) for path in sorted(directory.glob("*.json")) - ) + exports: Final = fixture_exports(directory) query_latest: Final = max( (max(timestamps(export)) for name, export in exports if name.startswith("query_")), default=0 ) @@ -236,15 +241,51 @@ def postgres_row(row: SpendLogRecord) -> LiteLLM_SpendLogsCreateWithoutRelations ) -async def seed() -> int: - from prisma import Prisma +class SeedOptions(BaseModel): + model_config = ConfigDict(frozen=True) + profile: Literal["default", "large"] + copies: int | None + batch_copies: int = 4 + timeout_seconds: float = 120 - fixtures: Final = spend_fixtures() - spends: Final = tuple(chain.from_iterable(rows for _, rows in fixtures)) + +def seed_arguments(argv: Sequence[str] | None = None) -> SeedOptions: + parser: Final = argparse.ArgumentParser(description="Replay tracing fixtures into a running local Lens stack") + parser.add_argument("--profile", choices=("default", "large"), default="default") + parser.add_argument( + "--copies", + type=int, + default=os.environ.get("LENS_DEV_SEED_COPIES"), + help="Override fixture copies (default: 1, large: 2000; env: LENS_DEV_SEED_COPIES)", + ) + parser.add_argument( + "--batch-copies", + type=int, + default=os.environ.get("LENS_DEV_SEED_BATCH_COPIES", "4"), + help="Copies per bulk insert (default: 4; env: LENS_DEV_SEED_BATCH_COPIES)", + ) + parser.add_argument("--timeout-seconds", type=float, default=os.environ.get("LENS_DEV_SEED_TIMEOUT_SECONDS", "120")) + arguments: Final = SeedOptions.model_validate(vars(parser.parse_args(argv))) + if arguments.copies is not None and arguments.copies < 1: + parser.error("--copies must be positive") + if arguments.batch_copies < 1: + parser.error("--batch-copies must be positive") + if not math.isfinite(arguments.timeout_seconds) or arguments.timeout_seconds <= 0: + parser.error("--timeout-seconds must be finite and positive") + return arguments + + +async def seed_batch( + client: httpx.AsyncClient, + storage: ClickHouseStorage, + database: Prisma, + replays: tuple[FixtureReplay, ...], + fixtures: tuple[tuple[str, tuple[SpendLogRecord, ...]], ...], + pattern: re.Pattern[str], + tenant: TenantIdentity | None, + verify: bool, +) -> TenantIdentity: by_name: Final = MappingProxyType(dict(fixtures)) - namespace: Final = uuid4().hex - pattern: Final = response_pattern(spends) - replays: Final = fixture_replays(TRACE_FIXTURES, time.time_ns() // 1_000_000, namespace, pattern) paired: Final = tuple( ( replay.name, @@ -254,45 +295,108 @@ async def seed() -> int: if replay.name in by_name ) rebased_spends: Final = tuple(chain.from_iterable(rows for _, rows in paired)) - master_key: Final = os.environ["LITELLM_MASTER_KEY"] - proxy_url: Final = os.environ.get("PROXY_BASE_URL", "http://127.0.0.1:4002") - async with httpx.AsyncClient( - base_url=proxy_url, headers={"Authorization": f"Bearer {master_key}"}, timeout=60 - ) as client: - for replay in replays: - ( - await client.post( - "/v1/traces", content=json.dumps(replay.export), headers={"Content-Type": "application/json"} - ) - ).raise_for_status() - storage: Final = ClickHouseStorage(trace_storage_config({})) - trace_id: Final = next(row["trace_id"] for row in rebased_spends if row["trace_id"]) - identity: Final = await storage.query_sql( - "SELECT DISTINCT TeamId AS team_id, ApiKeyHash AS api_key, UserId AS user " - f"FROM otel_traces WHERE TraceId = '{trace_id}'", - AllQueryScope(kind="all"), - master_key, - ) - tenant: Final = TenantIdentity.model_validate(identity.data[0]) - stamped_spends: Final[tuple[SpendLogRecord, ...]] = tuple( - {**row, "team_id": tenant.team_id, "api_key": tenant.api_key, "user": tenant.user} for row in rebased_spends - ) - await storage.insert_rows("spend_logs", stamped_spends) - async with Prisma() as database: - await database.litellm_spendlogs.create_many(data=[postgres_row(row) for row in stamped_spends]) + resolved_tenant: Final = await ingest_replays( + client, storage, replays, fixture_capture(*next((name, rows[0]) for name, rows in paired)).trace_id, tenant + ) + stamped_spends: Final[tuple[SpendLogRecord, ...]] = tuple( + {**row, "team_id": resolved_tenant.team_id, "api_key": resolved_tenant.api_key, "user": resolved_tenant.user} + for row in rebased_spends + ) + await storage.insert_rows("spend_logs", stamped_spends) + await database.litellm_spendlogs.create_many(data=[postgres_row(row) for row in stamped_spends]) + if verify: verified: Final = tuple(await asyncio.gather(*(verify_capture(client, name, rows) for name, rows in paired))) - sys.stdout.write( - json.dumps( - { - "trace_fixtures": tuple(replay.name for replay in replays), - "spend_rows": len(stamped_spends), - "captures": verified, - }, - indent=2, - ) - + "\n" + sys.stdout.write(json.dumps({"spend_rows": len(stamped_spends), "captures": verified}, indent=2) + "\n") + if not all(capture["verified"] for capture in verified): + raise RuntimeError("Seed spend verification failed") + return resolved_tenant + + +async def ingest_replays( + client: httpx.AsyncClient, + storage: ClickHouseStorage, + replays: tuple[FixtureReplay, ...], + trace_id: str, + tenant: TenantIdentity | None, +) -> TenantIdentity: + if tenant is not None: + await storage.insert_rows( + "otel_traces", bulk_span_rows(replays, Tenant(tenant.team_id, tenant.api_key, user_id=tenant.user)) ) - return 0 if all(capture["verified"] for capture in verified) else 1 + return tenant + for replay in replays: + ( + await client.post( + "/v1/traces", content=json.dumps(replay.export), headers={"Content-Type": "application/json"} + ) + ).raise_for_status() + identity: Final = await storage.query_sql( + "SELECT DISTINCT TeamId AS team_id, ApiKeyHash AS api_key, UserId AS user " + f"FROM otel_traces WHERE TraceId = '{trace_id}'", + AllQueryScope(kind="all"), + os.environ["LITELLM_MASTER_KEY"], + ) + return TenantIdentity.model_validate(identity.data[0]) + + +def bulk_span_rows(replays: tuple[FixtureReplay, ...], tenant: Tenant) -> tuple[Mapping[str, JsonValue], ...]: + return tuple( + chain.from_iterable( + span_rows(json.dumps(replay.export).encode(), "application/json", tenant) for replay in replays + ) + ) + + +def replay_batches( + count: int, now_ms: int, namespace: str, pattern: re.Pattern[str], batch_copies: int = 4 +) -> Iterator[tuple[int, tuple[FixtureReplay, ...]]]: + for start, stop in ((start, min(start + batch_copies, count)) for start in range(1, count, batch_copies)): + yield ( + stop, + tuple( + chain.from_iterable( + fixture_replays(TRACE_FIXTURES, now_ms - index * 1000, f"{namespace}-{index}", pattern) + for index in range(start, stop) + ) + ), + ) + + +async def seed( + profile: str = "default", copies: int | None = None, batch_copies: int = 4, timeout_seconds: float = 120 +) -> int: + from prisma import Prisma + + fixtures: Final = spend_fixtures() + pattern: Final = response_pattern(tuple(chain.from_iterable(rows for _, rows in fixtures))) + count: Final = copies if copies is not None else (2000 if profile == "large" else 1) + namespace: Final = uuid4().hex + now_ms: Final = time.time_ns() // 1_000_000 + storage: Final = ClickHouseStorage(trace_storage_config({})) + async with ( + httpx.AsyncClient( + base_url=os.environ.get("PROXY_BASE_URL", "http://127.0.0.1:4002"), + headers={"Authorization": f"Bearer {os.environ['LITELLM_MASTER_KEY']}"}, + timeout=timeout_seconds, + ) as client, + Prisma() as database, + ): + tenant: Final = await seed_batch( + client, + storage, + database, + fixture_replays(TRACE_FIXTURES, now_ms, namespace + "-0", pattern), + fixtures, + pattern, + None, + True, + ) + for stop, replays in replay_batches(count, now_ms, namespace, pattern, batch_copies): + await seed_batch(client, storage, database, replays, fixtures, pattern, tenant, stop == count) + sys.stdout.write(f"Seeded {stop}/{count} fixture copies\n") + sys.stdout.flush() + sys.stdout.write(f"Seed complete: profile={profile}, copies={count}, namespace={namespace}\n") + return 0 def fixture_capture(name: str, row: SpendLogRecord) -> FixtureCapture: @@ -307,7 +411,7 @@ def fixture_capture(name: str, row: SpendLogRecord) -> FixtureCapture: async def verify_capture( client: httpx.AsyncClient, name: str, rows: tuple[SpendLogRecord, ...] -) -> dict[str, JsonValue]: +) -> Mapping[str, JsonValue]: capture: Final = fixture_capture(name, rows[0]) detail: Final = await client.get(f"/v1/traces/{capture.trace_id}") detail.raise_for_status() @@ -320,9 +424,14 @@ async def verify_capture( "spend_rows": len(rows), "recorded_spend": expected, "trace_spend": actual, - "verified": math.isclose(actual, expected) if actual is not None else not (capture.spend_linked and capture.spend_complete), + "verified": math.isclose(actual, expected) + if actual is not None + else not (capture.spend_linked and capture.spend_complete), } if __name__ == "__main__": - raise SystemExit(asyncio.run(seed())) + arguments: Final = seed_arguments() + raise SystemExit( + asyncio.run(seed(arguments.profile, arguments.copies, arguments.batch_copies, arguments.timeout_seconds)) + ) diff --git a/tests/code_coverage_tests/liccheck.ini b/tests/code_coverage_tests/liccheck.ini index 70c49c5c256..a62af1b3725 100644 --- a/tests/code_coverage_tests/liccheck.ini +++ b/tests/code_coverage_tests/liccheck.ini @@ -177,3 +177,4 @@ hypothesis: >=6.165.10 # MPL 2.0 license pytest-rerunfailures: >=15.1 # MPL 2.0 license pytest-recording: >=0.13.4 # MIT license expression: >=5.6.0 # MIT License - https://github.com/cognitedata/Expression/blob/main/LICENSE +typing-extensions: >=4.13.0 # PSF-2.0 license - https://github.com/python/typing_extensions/blob/main/LICENSE diff --git a/tests/e2e/migrations/lens_compose_smoke.sh b/tests/e2e/migrations/lens_compose_smoke.sh index 69a13b58d88..6a57926895b 100644 --- a/tests/e2e/migrations/lens_compose_smoke.sh +++ b/tests/e2e/migrations/lens_compose_smoke.sh @@ -1,6 +1,19 @@ #!/usr/bin/env bash set -euo pipefail +worker_image() { + env -u LENS_WORKER_IMAGE -u LITELLM_VERSION \ + LITELLM_URL=http://litellm:4000 LENS_WORKER_TOKEN=config-test "$@" \ + docker compose --env-file /dev/null -f deploy/lens/compose.yaml config --images +} +[[ "$(worker_image LENS_WORKER_IMAGE=registry.example/lens:source)" == registry.example/lens:source ]] +[[ "$(worker_image LITELLM_VERSION=1.2.3)" == ghcr.io/berriai/litellm-lens-worker:v1.2.3 ]] +[[ "$(worker_image LENS_WORKER_IMAGE=registry.example/lens:source LITELLM_VERSION=1.2.3)" == registry.example/lens:source ]] +if worker_image > /dev/null 2>&1; then + printf 'Worker Compose accepted neither an image nor a release version\n' >&2 + exit 1 +fi + qa_dir=$(mktemp -d) master_key="sk-$(openssl rand -hex 32)" compose=(docker compose -p lens-compose-ci --env-file "$qa_dir/env" -f deploy/lens/stack.yaml) diff --git a/tests/e2e/ui/fixtures/migratedPages.ts b/tests/e2e/ui/fixtures/migratedPages.ts index bce09b49e10..d44dfc625aa 100644 --- a/tests/e2e/ui/fixtures/migratedPages.ts +++ b/tests/e2e/ui/fixtures/migratedPages.ts @@ -99,7 +99,7 @@ export const MIGRATED_E2E_PAGES: Readonly> = { group: "Settings", content: { role: "heading", name: "UI Theme Customization" }, }, - logs: { segment: "logs", linkName: "Logs", content: { role: "heading", name: "Request Logs" } }, + logs: { segment: "logs", linkName: "Logs", content: { role: "tab", name: "Request Logs" } }, "admin-panel": { segment: "admin-panel", linkName: "Admin Settings", diff --git a/tests/integration/_support/bedrock_runtime_peer.py b/tests/integration/_support/bedrock_runtime_peer.py index 3a547260590..64115d9eaa0 100644 --- a/tests/integration/_support/bedrock_runtime_peer.py +++ b/tests/integration/_support/bedrock_runtime_peer.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import json import re import threading diff --git a/tests/integration/_support/mcp.py b/tests/integration/_support/mcp.py index a3693433de4..d39d7e4029e 100644 --- a/tests/integration/_support/mcp.py +++ b/tests/integration/_support/mcp.py @@ -216,6 +216,16 @@ JsonRpc = Mapping[str, object] class ScriptedTool: name: str respond: Callable[[JsonRpc], Reply | JsonRpc] + description: str | Callable[[Mapping[str, str]], str] | None = None + input_schema: JsonRpc = field(default_factory=lambda: {"type": "object"}) + + def listing(self, headers: Mapping[str, str]) -> JsonRpc: + described: Final = self.description(headers) if callable(self.description) else self.description + return { + "name": self.name, + "inputSchema": self.input_schema, + **({} if described is None else {"description": described}), + } def jsonrpc_reply(identity: object, result: JsonRpc) -> Reply: @@ -253,9 +263,7 @@ def scripted_peer(*tools: ScriptedTool) -> Iterator[McpPeer]: }, ) if method == "tools/list": - return jsonrpc_reply( - identity, {"tools": [{"name": name, "inputSchema": {"type": "object"}} for name in by_name]} - ) + return jsonrpc_reply(identity, {"tools": [tool.listing(request.headers) for tool in by_name.values()]}) if method != "tools/call": return jsonrpc_error(identity, -32601, f"unsupported method {method}") tool: Final = by_name.get(body["params"]["name"]) diff --git a/tests/integration/_support/wire.py b/tests/integration/_support/wire.py index c807852ef6b..10bb7787cc9 100644 --- a/tests/integration/_support/wire.py +++ b/tests/integration/_support/wire.py @@ -133,6 +133,7 @@ def wire_server( class OwnedHTTPServer(ThreadingHTTPServer): daemon_threads = False + request_queue_size = 128 def server_bind(self) -> None: super().server_bind() diff --git a/tests/integration/database/test_v1_migration_error_logging.py b/tests/integration/database/test_v1_migration_error_logging.py new file mode 100644 index 00000000000..c3a3d8c43d6 --- /dev/null +++ b/tests/integration/database/test_v1_migration_error_logging.py @@ -0,0 +1,558 @@ +from __future__ import annotations + +import json +import os +import re +import signal +import socket +import socketserver +import subprocess +import sys +import threading +import uuid +from collections.abc import Callable, Iterator, Mapping +from contextlib import contextmanager, suppress +from dataclasses import dataclass +from pathlib import Path +from typing import Final, Literal, cast +from urllib.parse import quote, urlsplit, urlunsplit + +import psycopg +import pytest +from psycopg import sql +from psycopg.types.json import Jsonb + +from tests.integration._support.client import eventually +from tests.integration._support.process import _free_port as free_port + +REPO_ROOT: Final = Path(__file__).resolve().parents[3] +MIGRATIONS_DIR: Final = REPO_ROOT / "litellm-proxy-extras" / "litellm_proxy_extras" / "migrations" +MIGRATION_NAME: Final = "20260921190000_agent_identity" +pytestmark: Final = pytest.mark.timeout(300) +PASSWORD: Final = "wr ong'pw9" +FRAGMENTS: Final = ("wr ong", "wr+ong", "ong'pw9", "wr%20ong", "ong%27pw9", "pw9") +SHIPPED_MIGRATIONS: Final = tuple( + sorted(path.name for path in MIGRATIONS_DIR.iterdir() if path.is_dir() and path.name != "0_init") +) +LOG_PREFIX: Final = r"^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2},\d{3} - [^\n]+ - " +LOG_RECORD_START: Final = rf"{LOG_PREFIX}(?:DEBUG|INFO|WARNING|ERROR|CRITICAL) - " +ERROR_RECORD: Final = re.compile(rf"(?ms)^({LOG_PREFIX}ERROR - .*?)(?={LOG_RECORD_START}|\Z)") +RETRY_COUNT: Final = re.compile(r"Retrying\.\.\. \((\d+) attempts left\)") +FRAGMENT_PATTERN: Final = re.compile( + "|".join(re.escape(fragment) for fragment in sorted(FRAGMENTS, key=len, reverse=True)) +) + + +@dataclass(frozen=True, slots=True) +class MigrationResult: + returncode: int + output: str + + +def _migration_log_path(test_name: str, tmp_path: Path) -> Path: + log_directory: Final = ( + Path(os.environ["INTEGRATION_RESULTS_DIR"]) if "INTEGRATION_RESULTS_DIR" in os.environ else tmp_path + ) + log_path: Final = log_directory / f"v1-migration-{test_name}-{uuid.uuid4().hex[:8]}.log" + log_path.parent.mkdir(parents=True, exist_ok=True) + return log_path + + +def _database_url( + admin_url: str, + role: str, + password: str, + database: str, + *, + encode_password: bool = True, +) -> str: + parsed: Final = urlsplit(admin_url) + authority: Final = parsed.netloc.rsplit("@", 1)[-1] + encoded_password: Final = quote(password, safe="") if encode_password else password + netloc: Final = f"{quote(role, safe='')}:{encoded_password}@{authority}" + return urlunsplit(parsed._replace(netloc=netloc, path=f"/{database}")) + + +def _replace_port(database_url: str, port: int, hostname: str | None = None) -> str: + parsed: Final = urlsplit(database_url) + target_host: Final = hostname or parsed.hostname + assert target_host is not None + host: Final = f"[{target_host}]" if ":" in target_host else target_host + userinfo: Final = parsed.netloc.rsplit("@", 1)[0] + return urlunsplit(parsed._replace(netloc=f"{userinfo}@{host}:{port}")) + + +def _unreachable_database_url(database_url: str) -> str: + parsed: Final = urlsplit(database_url) + url: Final = _database_url( + database_url, + parsed.username or "", + PASSWORD, + parsed.path.lstrip("/"), + encode_password=False, + ) + return _replace_port(url, free_port()) + + +@contextmanager +def owned_database(password: str) -> Iterator[str]: + admin_url: Final = os.environ["DATABASE_URL"] + role: Final = f"v1_migration_{uuid.uuid4().hex}" + database: Final = f"v1_migration_{uuid.uuid4().hex}" + database_url: Final = _database_url(admin_url, role, password, database) + try: + with psycopg.connect(admin_url, autocommit=True) as admin: + admin.execute( + sql.SQL("CREATE ROLE {} WITH LOGIN PASSWORD {}").format(sql.Identifier(role), sql.Literal(password)) + ) + admin.execute(sql.SQL("CREATE DATABASE {} OWNER {}").format(sql.Identifier(database), sql.Identifier(role))) + yield database_url + finally: + with psycopg.connect(admin_url, autocommit=True) as admin: + admin.execute(sql.SQL("DROP DATABASE IF EXISTS {} WITH (FORCE)").format(sql.Identifier(database))) + admin.execute(sql.SQL("DROP ROLE IF EXISTS {}").format(sql.Identifier(role))) + + +def _migration_environment(database_url: str | None, extra_env: Mapping[str, str]) -> dict[str, str]: + excluded_variables: Final = ( + ("DIRECT_URL", "USE_V2_MIGRATION_RESOLVER") + if database_url is not None + else ("DATABASE_URL", "DIRECT_URL", "USE_V2_MIGRATION_RESOLVER") + ) + inherited_environment: Final = {key: value for key, value in os.environ.items() if key not in excluded_variables} + database_environment: Final = {"DATABASE_URL": database_url} if database_url is not None else {} + return { + **inherited_environment, + **database_environment, + "LITELLM_LOG": "ERROR", + **extra_env, + } + + +def _migration_invocation( + database_url: str | None, + tmp_path: Path, + extra_env: Mapping[str, str], + resolver: Literal["legacy", "v2"] = "legacy", +) -> tuple[tuple[str, ...], dict[str, str]]: + config_path: Final = tmp_path / "config.yaml" + config_path.write_text( + "model_list:\n - model_name: integration-fake\n litellm_params:\n model: openai/integration-fake\n" + ) + resolver_flag: Final = "--use_legacy_migration_resolver" if resolver == "legacy" else "--use_v2_migration_resolver" + command: Final = ( + sys.executable, + "-I", + "-m", + "litellm.proxy.proxy_cli", + "--config", + str(config_path), + resolver_flag, + "--skip_server_startup", + ) + environment: Final = _migration_environment(database_url, extra_env) + return command, environment + + +def run_v1_migrations( + database_url: str | None, + tmp_path: Path, + extra_env: Mapping[str, str], + test_name: str, + resolver: Literal["legacy", "v2"] = "legacy", +) -> MigrationResult: + command, environment = _migration_invocation(database_url, tmp_path, extra_env, resolver) + output_path: Final = _migration_log_path(test_name, tmp_path) + with output_path.open("w") as output_file: + completed: Final = subprocess.run( + command, + cwd=REPO_ROOT, + env=environment, + stdout=output_file, + stderr=subprocess.STDOUT, + text=True, + timeout=240, + ) + output: Final = output_path.read_text() + return MigrationResult(completed.returncode, output) + + +def error_lines(output: str) -> tuple[str, ...]: + return tuple(match.group(1) for match in ERROR_RECORD.finditer(output)) + + +def _json_error_records(output: str) -> tuple[dict[str, object], ...]: + records: Final = tuple(_parse_json_record(line, output) for line in output.splitlines() if line.startswith("{")) + return tuple(record for record in records if record.get("level") == "ERROR") + + +def _parse_json_record(line: str, output: str) -> dict[str, object]: + try: + record: Final = json.loads(line) + except json.JSONDecodeError: + pytest.fail(_safe_output(output)) + assert isinstance(record, dict), _safe_output(output) + return cast(dict[str, object], record) + + +def _retry_count_texts(lines: tuple[str, ...]) -> tuple[str, ...]: + return tuple(value for value in (_retry_count_text(line) for line in lines) if value is not None) + + +def _retry_count_text(line: str) -> str | None: + match: Final = RETRY_COUNT.search(line) + return match.group(1) if match is not None else None + + +def _safe_output(output: str) -> str: + return FRAGMENT_PATTERN.sub("[REDACTED]", output) + + +def _assert_no_password_fragments(output: str) -> None: + assert [fragment for fragment in FRAGMENTS if fragment in output] == [], _safe_output(output) + + +def _applied_migrations(database_url: str) -> tuple[str, ...]: + with psycopg.connect(database_url) as connection: + rows: Final = connection.execute( + 'SELECT migration_name FROM "_prisma_migrations" ' + "WHERE finished_at IS NOT NULL AND rolled_back_at IS NULL ORDER BY migration_name" + ).fetchall() + return tuple(str(row[0]) for row in rows) + + +def _duplicate_migrations(database_url: str) -> tuple[tuple[str, int], ...]: + with psycopg.connect(database_url) as connection: + rows: Final = connection.execute( + 'SELECT migration_name, COUNT(*) FROM "_prisma_migrations" ' + "GROUP BY migration_name HAVING COUNT(*) > 1 ORDER BY migration_name" + ).fetchall() + return tuple((str(row[0]), int(row[1])) for row in rows) + + +def _retry_p3018_migration(database_url: str) -> None: + agent_ids: Final = (uuid.uuid4().hex, uuid.uuid4().hex) + with psycopg.connect(database_url) as connection: + connection.execute('DROP INDEX "LiteLLM_AgentIdentity_provider_tenant_id_client_id_key"') + for agent_id in agent_ids: + connection.execute( + 'INSERT INTO "LiteLLM_AgentsTable" ' + '("agent_id", "agent_name", "agent_card_params", "created_by", "updated_by") ' + "VALUES (%s, %s, %s, %s, %s)", + (agent_id, f"audit-agent-{agent_id}", Jsonb({}), "integration", "integration"), + ) + connection.execute( + 'INSERT INTO "LiteLLM_AgentIdentity" ' + '("agent_id", "provider", "issuer", "tenant_id", "client_id", "revision") ' + "VALUES (%s, %s, %s, %s, %s, %s)", + (agent_id, "entra", f"https://audit.invalid/{agent_id}", "tenant-1", "client-1", uuid.uuid4().hex), + ) + connection.execute('DELETE FROM "_prisma_migrations" WHERE migration_name = %s', (MIGRATION_NAME,)) + + +def _relay(source: socket.socket, destination: socket.socket) -> None: + try: + while data := source.recv(65536): + destination.sendall(data) + except (BrokenPipeError, ConnectionAbortedError, ConnectionResetError): + return + + +class _PostgresForwardingServer(socketserver.ThreadingTCPServer): + allow_reuse_address = True + daemon_threads = True + request_queue_size = 64 + target: tuple[str, int] + + def __init__(self, port: int, target: tuple[str, int]) -> None: + self.target = target + super().__init__(("127.0.0.1", port), _PostgresForwardingHandler) + + +class _PostgresForwardingHandler(socketserver.BaseRequestHandler): + def handle(self) -> None: + server: Final = cast(_PostgresForwardingServer, self.server) + with socket.create_connection(server.target, timeout=10) as upstream: + reply: Final = threading.Thread(target=_relay, args=(upstream, self.request), daemon=True) + reply.start() + try: + _relay(self.request, upstream) + finally: + with suppress(OSError): + self.request.shutdown(socket.SHUT_WR) + with suppress(OSError): + upstream.shutdown(socket.SHUT_WR) + reply.join(timeout=10) + + +@contextmanager +def _gated_postgres_forwarder(port: int, target: tuple[str, int]) -> Iterator[Callable[[], None]]: + server: Final = _PostgresForwardingServer(port, target) + thread: Final = threading.Thread(target=server.serve_forever, daemon=True) + try: + yield thread.start + finally: + if thread.is_alive(): + server.shutdown() + server.server_close() + if thread.ident is not None: + thread.join(timeout=10) + + +def _stop_process(process: subprocess.Popen[str]) -> None: + if process.poll() is None: + with suppress(ProcessLookupError): + os.killpg(process.pid, signal.SIGTERM) + try: + process.wait(timeout=30) + except subprocess.TimeoutExpired: + with suppress(ProcessLookupError): + os.killpg(process.pid, signal.SIGKILL) + process.wait(timeout=30) + + +def _migration_log_has_p1001_or_process_exited(output_path: Path, process: subprocess.Popen[str]) -> tuple[bool, bool]: + p1001_logged: Final = any("P1001" in line for line in error_lines(output_path.read_text())) + process_exited: Final = process.poll() is not None + return p1001_logged, process_exited + + +def test_unreachable_database_emits_four_p1001_errors_without_password_fragments( + tmp_path: Path, request: pytest.FixtureRequest +) -> None: + with owned_database(PASSWORD) as database_url: + unreachable_url: Final = _unreachable_database_url(database_url) + completed: Final = run_v1_migrations(unreachable_url, tmp_path, {}, request.node.name) + output: Final = completed.output + errors: Final = error_lines(output) + p1001_errors: Final = tuple(line for line in errors if "P1001" in line) + assert completed.returncode == 1, _safe_output(output) + assert len(errors) == 4, _safe_output(output) + assert len(p1001_errors) == 4, _safe_output(output) + assert _retry_count_texts(errors) == (), _safe_output(output) + _assert_no_password_fragments(output) + + +def test_wrong_password_emits_four_p1000_errors_without_password_fragments( + tmp_path: Path, request: pytest.FixtureRequest +) -> None: + with owned_database(f"correct-{uuid.uuid4().hex}") as database_url: + parsed: Final = urlsplit(database_url) + wrong_url: Final = _database_url( + database_url, + parsed.username or "", + PASSWORD, + parsed.path.lstrip("/"), + ) + completed: Final = run_v1_migrations(wrong_url, tmp_path, {}, request.node.name) + output: Final = completed.output + errors: Final = error_lines(output) + p1000_errors: Final = tuple(line for line in errors if "P1000" in line) + assert completed.returncode == 1, _safe_output(output) + assert len(errors) == 4, _safe_output(output) + assert len(p1000_errors) == 4, _safe_output(output) + assert _retry_count_texts(errors) == (), _safe_output(output) + _assert_no_password_fragments(output) + + +def test_duplicate_agent_identity_logs_the_p3018_migration_error( + tmp_path: Path, request: pytest.FixtureRequest +) -> None: + with owned_database(PASSWORD) as database_url: + setup: Final = run_v1_migrations(database_url, tmp_path, {}, request.node.name) + setup_output: Final = setup.output + assert setup.returncode == 0, _safe_output(setup_output) + _retry_p3018_migration(database_url) + completed: Final = run_v1_migrations(database_url, tmp_path, {}, request.node.name) + output: Final = completed.output + errors: Final = error_lines(output) + p3018_errors: Final = tuple(line for line in errors if "P3018" in line) + expected_markers: Final = ((True, True), (True, True)) + assert completed.returncode == 1, _safe_output(output) + assert len(errors) == 2, _safe_output(output) + assert tuple((MIGRATION_NAME in line, "P3018" in line) for line in p3018_errors) == expected_markers, ( + _safe_output(output) + ) + assert _retry_count_texts(errors) == ("3", "1"), _safe_output(output) + _assert_no_password_fragments(output) + + +def test_clean_database_applies_exactly_the_shipped_migrations(tmp_path: Path, request: pytest.FixtureRequest) -> None: + with owned_database(PASSWORD) as database_url: + completed: Final = run_v1_migrations(database_url, tmp_path, {}, request.node.name) + output: Final = completed.output + assert completed.returncode == 0, _safe_output(output) + assert error_lines(output) == (), _safe_output(output) + assert _applied_migrations(database_url) == SHIPPED_MIGRATIONS, _safe_output(output) + _assert_no_password_fragments(output) + + +def test_unreachable_database_recovers_after_postgres_forwarder_starts( + tmp_path: Path, request: pytest.FixtureRequest +) -> None: + with owned_database(PASSWORD) as database_url: + admin_url: Final = os.environ["DATABASE_URL"] + admin: Final = urlsplit(admin_url) + hostname: Final = admin.hostname + port: Final = admin.port + assert hostname is not None and port is not None + target_host: Final = "127.0.0.1" if hostname == "localhost" else hostname + forwarding_port: Final = free_port() + forwarded_url: Final = _replace_port(database_url, forwarding_port, "127.0.0.1") + command, environment = _migration_invocation(forwarded_url, tmp_path, {}) + output_path: Final = _migration_log_path(request.node.name, tmp_path) + with _gated_postgres_forwarder(forwarding_port, (target_host, port)) as open_forwarder: + with output_path.open("w") as output_file: + process: Final = subprocess.Popen( + command, + cwd=REPO_ROOT, + env=environment, + stdout=output_file, + stderr=subprocess.STDOUT, + text=True, + start_new_session=True, + ) + try: + observation: Final = eventually( + lambda: _migration_log_has_p1001_or_process_exited(output_path, process), + lambda state: state[0] or state[1], + seconds=240, + ) + assert observation[0], _safe_output(output_path.read_text()) + open_forwarder() + completed_returncode: Final = process.wait(timeout=240) + finally: + _stop_process(process) + output: Final = output_path.read_text() + errors: Final = error_lines(output) + p1001_errors: Final = tuple(line for line in errors if "P1001" in line) + assert completed_returncode == 0, _safe_output(output) + assert len(p1001_errors) == 1, _safe_output(output) + assert _retry_count_texts(errors) == (), _safe_output(output) + assert _duplicate_migrations(database_url) == (), _safe_output(output) + assert _applied_migrations(database_url) == SHIPPED_MIGRATIONS, _safe_output(output) + _assert_no_password_fragments(output) + + +def test_unreachable_database_keeps_password_masked_when_shape_redaction_is_disabled( + tmp_path: Path, request: pytest.FixtureRequest +) -> None: + with owned_database(PASSWORD) as database_url: + unreachable_url: Final = _unreachable_database_url(database_url) + completed: Final = run_v1_migrations( + unreachable_url, + tmp_path, + {"LITELLM_DISABLE_REDACT_SECRETS": "true"}, + request.node.name, + ) + output: Final = completed.output + errors: Final = error_lines(output) + p1001_errors: Final = tuple(line for line in errors if "P1001" in line) + assert completed.returncode == 1, _safe_output(output) + assert len(errors) == 4, _safe_output(output) + assert len(p1001_errors) == 4, _safe_output(output) + assert _retry_count_texts(errors) == (), _safe_output(output) + _assert_no_password_fragments(output) + + +def test_component_database_env_vars_with_wrong_password_emit_four_p1000_errors_without_password_fragments( + tmp_path: Path, request: pytest.FixtureRequest +) -> None: + correct_password: Final = f"correct-{uuid.uuid4().hex}" + with owned_database(correct_password) as database_url: + parsed: Final = urlsplit(database_url) + host: Final = parsed.hostname + port: Final = parsed.port + username: Final = parsed.username + assert host is not None and port is not None and username is not None + extra_env: Final = { + "DATABASE_HOST": f"{host}:{port}", + "DATABASE_USERNAME": username, + "DATABASE_PASSWORD": PASSWORD, + "DATABASE_NAME": parsed.path.lstrip("/"), + } + completed: Final = run_v1_migrations(None, tmp_path, extra_env, request.node.name) + output: Final = completed.output + errors: Final = error_lines(output) + p1000_errors: Final = tuple(line for line in errors if "P1000" in line) + assert completed.returncode == 1, _safe_output(output) + assert len(errors) == 4, _safe_output(output) + assert len(p1000_errors) == 4, _safe_output(output) + assert _retry_count_texts(errors) == (), _safe_output(output) + _assert_no_password_fragments(output) + + +def test_json_logs_emit_four_valid_json_p1001_error_records_without_password_fragments( + tmp_path: Path, request: pytest.FixtureRequest +) -> None: + with owned_database(PASSWORD) as database_url: + unreachable_url: Final = _unreachable_database_url(database_url) + completed: Final = run_v1_migrations(unreachable_url, tmp_path, {"JSON_LOGS": "true"}, request.node.name) + output: Final = completed.output + errors: Final = _json_error_records(output) + messages: Final = tuple(record.get("message") for record in errors) + assert completed.returncode == 1, _safe_output(output) + assert len(errors) == 4, _safe_output(output) + assert tuple(isinstance(message, str) and "P1001" in message for message in messages) == ( + True, + True, + True, + True, + ), _safe_output(output) + assert error_lines(output) == (), _safe_output(output) + _assert_no_password_fragments(output) + + +def test_migration_job_entrypoint_emits_four_p1001_errors_without_password_fragments( + tmp_path: Path, request: pytest.FixtureRequest +) -> None: + with owned_database(PASSWORD) as database_url: + unreachable_url: Final = _unreachable_database_url(database_url) + command: Final = (sys.executable, "-I", "-m", "litellm.proxy.prisma_migration") + environment: Final = _migration_environment( + unreachable_url, + {"USE_V2_MIGRATION_RESOLVER": "false"}, + ) + output_path: Final = _migration_log_path(request.node.name, tmp_path) + with output_path.open("w") as output_file: + completed: Final = subprocess.run( + command, + cwd=REPO_ROOT, + env=environment, + stdout=output_file, + stderr=subprocess.STDOUT, + text=True, + timeout=240, + ) + output: Final = output_path.read_text() + errors: Final = error_lines(output) + p1001_errors: Final = tuple(line for line in errors if "P1001" in line) + assert completed.returncode == 1, _safe_output(output) + assert len(errors) == 4, _safe_output(output) + assert len(p1001_errors) == 4, _safe_output(output) + _assert_no_password_fragments(output) + + +def test_v2_resolver_unreachable_database_exits_2_and_names_p1001( + tmp_path: Path, request: pytest.FixtureRequest +) -> None: + with owned_database(PASSWORD) as database_url: + unreachable_url: Final = _unreachable_database_url(database_url) + completed: Final = run_v1_migrations(unreachable_url, tmp_path, {}, request.node.name, resolver="v2") + output: Final = completed.output + assert completed.returncode == 2, _safe_output(output) + assert "P1001" in output, _safe_output(output) + assert error_lines(output) == (), _safe_output(output) + _assert_no_password_fragments(output) + + +def test_v2_resolver_clean_database_applies_exactly_the_shipped_migrations( + tmp_path: Path, request: pytest.FixtureRequest +) -> None: + with owned_database(PASSWORD) as database_url: + completed: Final = run_v1_migrations(database_url, tmp_path, {}, request.node.name, resolver="v2") + output: Final = completed.output + assert completed.returncode == 0, _safe_output(output) + assert error_lines(output) == (), _safe_output(output) + assert _applied_migrations(database_url) == SHIPPED_MIGRATIONS, _safe_output(output) + _assert_no_password_fragments(output) diff --git a/tests/integration/mcp/test_mcp_access_matrix.py b/tests/integration/mcp/test_mcp_access_matrix.py index e458911cc68..bf8adbc7cd7 100644 --- a/tests/integration/mcp/test_mcp_access_matrix.py +++ b/tests/integration/mcp/test_mcp_access_matrix.py @@ -1,20 +1,29 @@ +import re +import textwrap import uuid +from collections.abc import Iterator +from pathlib import Path from typing import Final import pytest -from integration._support.client import Gateway +from integration._support.client import Gateway, gateway_from_environment from integration._support.database import read_rows from integration._support.mcp import ( ENTRY_POINTS, EntryPoint, McpCaller, McpPeer, + Outcome, PeerKind, + ScriptedTool, peer_of, register_mcp, + scripted_peer, + text_result, tool_calls, ) from integration._support.mcp_grants import SUBJECTS, Subject, grant +from integration._support.process import owned_proxy CALLABLE: Final = {"add": {"a": 1, "b": 2}, "multiply": {"a": 2, "b": 3}} RESULTS: Final = {"add": "3", "multiply": "6"} @@ -135,3 +144,87 @@ def test_same_tool_name_on_two_servers_routes_by_prefix(gateway: Gateway) -> Non assert outcome.ok and outcome.text == "10", outcome.raw assert tool_calls(first.drain()) == () assert [call["body"]["params"]["name"] for call in tool_calls(second.drain())] == ["add"] + + +_PROBE: Final = "catalog-probe" +_ECHO: Final = "catalog-echo" +_UNLISTED: Final = "" +_GUARDRAIL_CODE: Final = ( + "def apply_guardrail(inputs, request_data, input_type):\n" + f' if "{_PROBE}" not in list(inputs.get("texts") or []):\n' + " return allow()\n" + ' function = inputs.get("tools", [{}])[0].get("function", {})\n' + f' return block("{_ECHO}[" + function.get("description") + "]")\n' +) + + +_ECHO_GUARDRAIL_YAML: Final = ( + "guardrails:\n" + " - guardrail_name: catalog-echo\n" + " litellm_params:\n" + " guardrail: custom_code\n" + " mode: pre_mcp_call\n" + " default_on: true\n" + " custom_code: |\n" + textwrap.indent(_GUARDRAIL_CODE, 8 * " ") +) + + +@pytest.fixture(scope="module") +def echo_rig(tmp_path_factory: pytest.TempPathFactory) -> Iterator[Gateway]: + directory: Final = tmp_path_factory.mktemp("catalog-echo") + path: Final = directory / "catalog_echo.yaml" + path.write_text((Path(__file__).resolve().parents[1] / "proxy_config.yaml").read_text() + _ECHO_GUARDRAIL_YAML) + with gateway_from_environment() as gateway, owned_proxy(gateway, directory, {}, config=path, workers=2) as rig: + yield rig + + +def _echoed_description(outcome: Outcome) -> str: + found: Final = re.search(rf"{_ECHO}\[(.*?)\]", outcome.raw) + assert found is not None, outcome.raw + return found.group(1) + + +@pytest.mark.parametrize("subject", SUBJECTS) +def test_each_subjects_call_is_evaluated_only_against_the_catalog_its_own_listing_served( + echo_rig: Gateway, subject: Subject +) -> None: + described: Final = "Adds under grant " + uuid.uuid4().hex[:8] + tool: Final = ScriptedTool("add", lambda _: text_result("3"), description=described) + with scripted_peer(tool) as peer, echo_rig.scenario() as scenario: + group: Final = "grp" + uuid.uuid4().hex[:8] + alias: Final = "cat" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias, mcp_access_groups=[group]) + caller: Final = grant( + scenario, subject, (identity,), (identity,), access_group=group, allowed_tools={identity: ("add",)} + ) + reach: Final = McpCaller(echo_rig, caller.key, "mcp", alias, caller.headers) + assert reach.initialize().ok + cold: Final = _echoed_description(reach.call(f"{alias}-add", {"probe": _PROBE})) + listed: Final = reach.list_tools() + assert listed.ok and f"{alias}-add" in listed.tools, listed.raw + warm: Final = _echoed_description(reach.call(f"{alias}-add", {"probe": _PROBE})) + assert (cold, warm) == (_UNLISTED, described), (cold, warm) + assert tool_calls(peer.drain()) == (), "a blocked probe reached the peer" + + +def test_end_users_of_one_key_share_its_catalog_slot_because_the_identity_excludes_the_end_user( + echo_rig: Gateway, +) -> None: + described: Final = "Adds for end users " + uuid.uuid4().hex[:8] + tool: Final = ScriptedTool("add", lambda _: text_result("3"), description=described) + with scripted_peer(tool) as peer, echo_rig.scenario() as scenario: + alias: Final = "eu" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias) + granted: Final = grant(scenario, "end_user", (identity,), (identity,)) + first: Final = McpCaller(echo_rig, granted.key, "mcp", alias, granted.headers) + second: Final = McpCaller( + echo_rig, granted.key, "mcp", alias, {"x-litellm-end-user-id": "integration-" + uuid.uuid4().hex[:10]} + ) + assert second.initialize().ok + assert _echoed_description(second.call(f"{alias}-add", {"probe": _PROBE})) == _UNLISTED + listed: Final = first.list_tools() + assert listed.ok and f"{alias}-add" in listed.tools, listed.raw + assert _echoed_description(second.call(f"{alias}-add", {"probe": _PROBE})) == described, ( + "the end-user header is intentionally not part of the catalog identity: one key, one slot" + ) + assert tool_calls(peer.drain()) == (), "a blocked probe reached the peer" diff --git a/tests/integration/mcp/test_mcp_accounting_guardrails.py b/tests/integration/mcp/test_mcp_accounting_guardrails.py index 323afad40db..a276718c280 100644 --- a/tests/integration/mcp/test_mcp_accounting_guardrails.py +++ b/tests/integration/mcp/test_mcp_accounting_guardrails.py @@ -1,11 +1,23 @@ +import json import uuid -from collections.abc import Iterator +from collections.abc import Generator, Iterator, Mapping from contextlib import contextmanager +from dataclasses import dataclass from hashlib import sha256 +from pathlib import Path from typing import Final +import httpx import pytest -from integration._support.client import Gateway, JsonValue, Scenario, eventually +import yaml +from integration._support.client import ( + JSON_OBJECT, + Gateway, + Scenario, + eventually, + gateway_from_environment, + object_value, +) from integration._support.database import read_rows from integration._support.mcp import ( ENTRY_POINTS, @@ -13,10 +25,16 @@ from integration._support.mcp import ( McpCaller, McpPeer, Outcome, + ScriptedTool, mcp_peer, register_mcp, + scripted_peer, + text_result, tool_calls, ) +from integration._support.process import owned_proxy +from integration._support.wire import Reply, Request, Wire, wire_server +from pydantic import JsonValue DEFAULT_COST: Final = 0.25 ADD_COST: Final = 0.5 @@ -191,3 +209,472 @@ def test_guardrail_removal_stops_blocking_without_restart(gateway: Gateway) -> N lambda calls: len(calls) >= 1, seconds=40, ) + + +MASK_ME: Final = "mask-integration-secret" +MASKED: Final = "[MASKED]" +COUNT_MISMATCH: Final = "count-mismatch-marker" +LOOKUP_DESCRIPTION: Final = "Look up one record" +LOOKUP_SCHEMA: Final = { + "type": "object", + "properties": {"record": {"type": "string", "description": "record identifier"}}, +} +SPEND_ROW: Final = 'SELECT status, metadata FROM "LiteLLM_SpendLogs" WHERE request_id = %s' +_RECORDER_CODE: Final = """\ +import os + +import httpx +from litellm.integrations.custom_guardrail import CustomGuardrail +from litellm.integrations.custom_logger import CustomLogger + +SINK = "{sink}/native" + + +def _record(stage, data, call_type): + logging_obj = data.get("litellm_logging_obj") + return {{ + "stage": stage, + "pid": os.getpid(), + "call_type": call_type, + "litellm_call_id": None if logging_obj is None else logging_obj.litellm_call_id, + "messages": data.get("messages"), + "mcp_tool_name": data.get("mcp_tool_name"), + "mcp_arguments": data.get("mcp_arguments"), + "mcp_tool_description": data.get("mcp_tool_description"), + "mcp_input_schema": data.get("mcp_input_schema"), + }} + + +async def _post(record): + async with httpx.AsyncClient(timeout=5) as client: + await client.post(SINK, json=record) + + +class HookRecorder(CustomLogger): + async def async_pre_call_hook(self, user_api_key_dict, cache, data, call_type): + await _post(_record("pre", data, call_type)) + + async def async_moderation_hook(self, data, user_api_key_dict, call_type): + await _post(_record("during", data, call_type)) + + async def async_post_mcp_tool_call_hook(self, kwargs, response_obj, start_time, end_time): + await _post( + {{ + "stage": "post", + "pid": os.getpid(), + "litellm_call_id": kwargs.get("litellm_call_id"), + "tool": kwargs.get("mcp_tool_call_metadata"), + "content": [item.model_dump() for item in response_obj.mcp_tool_call_response], + }} + ) + + +class SinkGuardrail(CustomGuardrail): + def __init__(self, api_base, **kwargs): + super().__init__(**kwargs) + self.api_base = api_base + + async def apply_guardrail(self, inputs, request_data, input_type, logging_obj=None): + payload = {{ + "pid": os.getpid(), + "input_type": input_type, + "litellm_call_id": None if logging_obj is None else logging_obj.litellm_call_id, + "texts": inputs.get("texts"), + "tools": inputs.get("tools"), + "structured_messages": inputs.get("structured_messages"), + "mcp_tool_name": request_data.get("mcp_tool_name"), + }} + async with httpx.AsyncClient(timeout=5) as client: + verdict = (await client.post(self.api_base, json=payload)).json() + return {{**inputs, "texts": verdict["texts"]}} + + +recorder = HookRecorder() +""" + + +@dataclass(frozen=True, slots=True) +class Sunk: + target: str + body: dict[str, JsonValue] + + +@dataclass(frozen=True, slots=True) +class HooksRig: + gateway: Gateway + sibling: Gateway + sink: Wire + guardrail: str + + def sunk(self) -> tuple[Sunk, ...]: + return tuple(Sunk(request.target, JSON_OBJECT.validate_json(request.body)) for request in self.sink.drain()) + + +def _guardrail_sink(request: Request) -> Reply: + if not request.target.startswith("/guardrail"): + return Reply() + texts: Final = JSON_OBJECT.validate_json(request.body).get("texts") + assert isinstance(texts, list), texts + masked: Final = [str(text).replace(MASK_ME, MASKED) for text in texts] + extra: Final = ["extra"] if any(COUNT_MISMATCH in text for text in masked) else [] + return Reply(body=json.dumps({"texts": [*masked, *extra]}).encode()) + + +@pytest.fixture(scope="module") +def hooks_rig(tmp_path_factory: pytest.TempPathFactory) -> Iterator[HooksRig]: + directory: Final = tmp_path_factory.mktemp("guardrail-payloads") + guardrail: Final = "sink" + uuid.uuid4().hex[:8] + with wire_server(_guardrail_sink) as sink: + (directory / "hook_recorder.py").write_text(_RECORDER_CODE.format(sink=sink.url)) + config: Final = JSON_OBJECT.validate_python( + yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text()) + ) + config["guardrails"] = [ + { + "guardrail_name": guardrail, + "litellm_params": { + "guardrail": "hook_recorder.SinkGuardrail", + "mode": ["pre_mcp_call", "post_mcp_call"], + "default_on": True, + "api_base": f"{sink.url}/guardrail", + }, + } + ] + config["litellm_settings"] = { + **object_value(config["litellm_settings"]), + "callbacks": ["hook_recorder.recorder"], + } + path: Final = directory / "config.yaml" + path.write_text(yaml.safe_dump(config)) + with ( + gateway_from_environment() as gateway, + owned_proxy(gateway, directory, {"KEEPALIVE_TIMEOUT": "120"}, config=path, workers=2) as candidate, + owned_proxy(gateway, directory, {}, config=path) as sibling, + ): + yield HooksRig(candidate, sibling, sink, guardrail) + + +def _worker(gateway: Gateway) -> int: + response: Final = gateway.client.get("/debug/memory/summary", headers={"x-litellm-api-key": gateway.key}) + assert response.status_code == 200, response.text + worker: Final = JSON_OBJECT.validate_json(response.content)["worker_pid"] + assert isinstance(worker, int), response.text + return worker + + +@contextmanager +def _pinned(gateway: Gateway) -> Generator[tuple[Gateway, int], None, None]: + limits: Final = httpx.Limits(max_connections=1, max_keepalive_connections=1, keepalive_expiry=120) + with httpx.Client(base_url=gateway.client.base_url, timeout=15, trust_env=False, limits=limits) as client: + pinned: Final = Gateway(client, gateway.key, gateway.upstream_url) + yield pinned, _worker(pinned) + + +def _lookup_tool(result: str = "found") -> ScriptedTool: + return ScriptedTool( + "lookup", lambda _: text_result(result), description=LOOKUP_DESCRIPTION, input_schema=LOOKUP_SCHEMA + ) + + +def _generic(sunk: tuple[Sunk, ...], input_type: str) -> tuple[dict[str, JsonValue], ...]: + return tuple(item.body for item in sunk if item.target == "/guardrail" and item.body["input_type"] == input_type) + + +def _native(sunk: tuple[Sunk, ...], stage: str) -> tuple[dict[str, JsonValue], ...]: + return tuple(item.body for item in sunk if item.target == "/native" and item.body["stage"] == stage) + + +def _only(records: tuple[dict[str, JsonValue], ...]) -> dict[str, JsonValue]: + assert len(records) == 1, records + return records[0] + + +def _scan(sunk: tuple[Sunk, ...], call_id: JsonValue) -> dict[str, JsonValue]: + return _only(tuple(record for record in _generic(sunk, "request") if record["litellm_call_id"] == call_id)) + + +def _texts(content: JsonValue) -> list[JsonValue]: + assert isinstance(content, list), content + return [object_value(item)["text"] for item in content] + + +def _has_lookup(listing: Outcome) -> bool: + return any(tool.endswith("lookup") for tool in listing.tools) + + +def _spend_row(call_id: JsonValue) -> dict[str, JsonValue]: + assert isinstance(call_id, str), call_id + rows: Final = eventually(lambda: read_rows(SPEND_ROW, (call_id,)), lambda found: len(found) == 1, seconds=70) + return rows[0] + + +def _synthetic_message(name: str, arguments: Mapping[str, str]) -> list[dict[str, str]]: + return [{"role": "user", "content": f"Tool: {name}\nArguments: {dict(arguments)}"}] + + +def test_generic_sink_and_native_hooks_receive_listed_metadata_on_typed_keys_with_the_message_bytes_unchanged( + hooks_rig: HooksRig, +) -> None: + with ( + scripted_peer(_lookup_tool()) as peer, + _pinned(hooks_rig.gateway) as (pinned, worker), + pinned.scenario() as scenario, + ): + alias: Final = "payload" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + caller: Final = McpCaller(pinned, key, "mcp", headers={"x-mcp-servers": alias}) + assert eventually(caller.initialize, lambda outcome: outcome.ok, seconds=30).ok + hooks_rig.sunk() + listed: Final = eventually(caller.list_tools, _has_lookup, seconds=30) + name: Final = next(tool for tool in listed.tools if tool.endswith("lookup")) + scans: Final = _generic(hooks_rig.sunk(), "request") + assert scans and all(scan["texts"] == [LOOKUP_DESCRIPTION, "record identifier"] for scan in scans), scans + arguments: Final = {"record": "r-1"} + outcome: Final = caller.call(name, arguments) + assert outcome.text == "found", outcome.raw + assert _worker(pinned) == worker + sunk: Final = hooks_rig.sunk() + pre: Final = _only(_native(sunk, "pre")) + call_id: Final = pre["litellm_call_id"] + generic: Final = _scan(sunk, call_id) + assert generic["texts"] == [LOOKUP_DESCRIPTION, "record identifier", "r-1"], generic + assert generic["tools"] == [ + { + "type": "function", + "function": { + "name": "lookup", + "description": LOOKUP_DESCRIPTION, + "parameters": {**LOOKUP_SCHEMA, "additionalProperties": False}, + "strict": False, + }, + } + ], generic + response: Final = _only(_generic(sunk, "response")) + assert (response["texts"], response["pid"]) == (["found"], worker), response + during: Final = _only(_native(sunk, "during")) + post: Final = _only(_native(sunk, "post")) + assert all(record["pid"] == worker for record in (pre, during, post)), sunk + assert all(record["litellm_call_id"] == call_id for record in (pre, during, post)), sunk + assert pre["call_type"] == "call_mcp_tool" and during["call_type"] == "call_mcp_tool", sunk + assert pre["messages"] == _synthetic_message("lookup", arguments), pre + assert during["messages"] == _synthetic_message("lookup", arguments), during + assert (pre["mcp_tool_name"], pre["mcp_arguments"]) == ("lookup", arguments), pre + assert pre["mcp_tool_description"] == LOOKUP_DESCRIPTION, pre + assert pre["mcp_input_schema"] == LOOKUP_SCHEMA, pre + assert (during["mcp_tool_description"], during["mcp_input_schema"]) == (None, None), during + assert _texts(post["content"]) == ["found"], post + row: Final = _spend_row(call_id) + assert row["status"] == "success", row + assert _tool_metadata(row)["name"] == "lookup", row + metadata: Final = row["metadata"] + assert isinstance(metadata, dict) and metadata["applied_guardrails"] == [hooks_rig.guardrail], metadata + + +def test_pre_call_mask_reaches_the_peer_and_post_call_mask_reaches_the_caller_on_one_call_id( + hooks_rig: HooksRig, +) -> None: + with ( + scripted_peer(_lookup_tool(f"found {MASK_ME}")) as peer, + _pinned(hooks_rig.gateway) as (pinned, worker), + pinned.scenario() as scenario, + ): + alias: Final = "mask" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + caller: Final = McpCaller(pinned, key, "mcp", headers={"x-mcp-servers": alias}) + assert eventually(caller.initialize, lambda outcome: outcome.ok, seconds=30).ok + name: Final = next( + tool for tool in eventually(caller.list_tools, _has_lookup, seconds=30).tools if "lookup" in tool + ) + peer.drain() + hooks_rig.sunk() + outcome: Final = caller.call(name, {"record": MASK_ME}) + assert outcome.text == f"found {MASKED}", outcome.raw + assert _worker(pinned) == worker + reached: Final = tool_calls(peer.drain()) + assert len(reached) == 1, reached + params: Final = object_value(JSON_OBJECT.validate_python(reached[0]["body"])["params"]) + assert params["arguments"] == {"record": MASKED}, params + sunk: Final = hooks_rig.sunk() + generic: Final = _scan(sunk, _only(_native(sunk, "pre"))["litellm_call_id"]) + scanned: Final = generic["texts"] + assert isinstance(scanned, list) and scanned[-1] == MASK_ME and MASKED not in scanned, generic + assert _only(_generic(sunk, "response"))["texts"] == [f"found {MASK_ME}"], sunk + during: Final = _only(_native(sunk, "during")) + assert during["mcp_arguments"] == {"record": MASKED}, during + assert during["messages"] == _synthetic_message("lookup", {"record": MASKED}), during + assert _only(_native(sunk, "post"))["litellm_call_id"] == generic["litellm_call_id"], sunk + assert _spend_row(generic["litellm_call_id"])["status"] == "success" + + +def test_call_time_description_and_schema_come_from_the_catalog_of_the_worker_that_served_the_listing( + hooks_rig: HooksRig, +) -> None: + with ( + scripted_peer(_lookup_tool()) as peer, + hooks_rig.gateway.scenario() as scenario, + _pinned(hooks_rig.sibling) as (second, second_worker), + ): + alias: Final = "local" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + other: Final = McpCaller(second, key, "mcp", headers={"x-mcp-servers": alias}) + assert eventually(other.initialize, lambda outcome: outcome.ok, seconds=60).ok + with _pinned(hooks_rig.gateway) as (first, first_worker): + assert first_worker != second_worker + lister: Final = McpCaller(first, key, "mcp", headers={"x-mcp-servers": alias}) + assert eventually(lister.initialize, lambda outcome: outcome.ok, seconds=30).ok + name: Final = next( + tool for tool in eventually(lister.list_tools, _has_lookup, seconds=30).tools if "lookup" in tool + ) + hooks_rig.sunk() + assert other.call(name, {"record": "r-2"}).text == "found" + assert _worker(second) == second_worker + elsewhere: Final = hooks_rig.sunk() + unlisted: Final = _only(_native(elsewhere, "pre")) + assert unlisted["pid"] == second_worker, unlisted + assert (unlisted["mcp_tool_description"], unlisted["mcp_input_schema"]) == (None, None), unlisted + assert _scan(elsewhere, unlisted["litellm_call_id"])["texts"] == ["r-2"], elsewhere + assert lister.call(name, {"record": "r-3"}).text == "found" + assert _worker(first) == first_worker + at_lister: Final = hooks_rig.sunk() + listed: Final = _only(_native(at_lister, "pre")) + assert listed["pid"] == first_worker, listed + assert (listed["mcp_tool_description"], listed["mcp_input_schema"]) == (LOOKUP_DESCRIPTION, LOOKUP_SCHEMA) + assert _scan(at_lister, listed["litellm_call_id"])["texts"] == [ + LOOKUP_DESCRIPTION, + "record identifier", + "r-3", + ] + assert _has_lookup(other.list_tools()) + hooks_rig.sunk() + assert other.call(name, {"record": "r-4"}).text == "found" + assert _worker(second) == second_worker + populated: Final = _only(_native(hooks_rig.sunk(), "pre")) + assert populated["pid"] == second_worker, populated + assert populated["mcp_tool_description"] == LOOKUP_DESCRIPTION, populated + + +@pytest.mark.parametrize("entry", ("mcp", "rest")) +@pytest.mark.parametrize("listed", (False, True)) +@pytest.mark.parametrize("record", ("r-1", MASK_ME)) +def test_long_descriptions_do_not_refuse_small_tpm_calls_or_change_masked_message_bytes( + hooks_rig: HooksRig, entry: EntryPoint, listed: bool, record: str +) -> None: + description: Final = "Gateway tool metadata. " * 300 + tool: Final = ScriptedTool( + "lookup", lambda _: text_result("found"), description=description, input_schema=LOOKUP_SCHEMA + ) + with ( + scripted_peer(tool) as peer, + _pinned(hooks_rig.gateway) as (pinned, worker), + pinned.scenario() as scenario, + ): + alias: Final = "quota" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}, tpm_limit=64) + caller: Final = McpCaller(pinned, key, entry, headers={"x-mcp-servers": alias}) + assert eventually(caller.initialize, lambda outcome: outcome.ok, seconds=30).ok + if listed: + listing: Final = eventually(lambda: caller.list_tools(identity), _has_lookup, seconds=30) + assert _has_lookup(listing), listing.raw + hooks_rig.sunk() + peer.drain() + arguments: Final = {"record": record} + outcome: Final = caller.call(f"{alias}-lookup", arguments, identity) + assert outcome.ok and outcome.text == "found", outcome.raw + assert _worker(pinned) == worker + reached: Final = tool_calls(peer.drain()) + assert len(reached) == 1, reached + params: Final = object_value(JSON_OBJECT.validate_python(reached[0]["body"])["params"]) + masked_arguments: Final = {"record": record.replace(MASK_ME, MASKED)} + assert params["arguments"] == masked_arguments, params + sunk: Final = hooks_rig.sunk() + pre: Final = _only(tuple(hook for hook in _native(sunk, "pre") if hook["mcp_tool_name"] == "lookup")) + during: Final = _only(tuple(hook for hook in _native(sunk, "during") if hook["mcp_tool_name"] == "lookup")) + assert pre["messages"] == _synthetic_message("lookup", arguments), pre + assert during["messages"] == _synthetic_message("lookup", masked_arguments), during + assert _spend_row(pre["litellm_call_id"])["status"] == "success" + + +def _nested_schema(levels: int) -> dict[str, object]: + if levels == 0: + return {"type": "string", "description": "deepest leaf"} + return {"type": "object", "properties": {"a": _nested_schema(levels - 1)}} + + +def test_a_schema_past_the_scan_depth_is_not_published_while_one_at_the_limit_is_scanned_on_the_call( + hooks_rig: HooksRig, +) -> None: + shallow: Final = ScriptedTool("shallow", lambda _: text_result("found"), input_schema=_nested_schema(49)) + deep: Final = ScriptedTool("deep", lambda _: text_result("found"), input_schema=_nested_schema(50)) + with ( + scripted_peer(shallow, deep) as peer, + _pinned(hooks_rig.gateway) as (pinned, worker), + pinned.scenario() as scenario, + ): + alias: Final = "depth" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + caller: Final = McpCaller(pinned, key, "mcp", headers={"x-mcp-servers": alias}) + assert eventually(caller.initialize, lambda outcome: outcome.ok, seconds=30).ok + listing: Final = eventually(caller.list_tools, lambda outcome: len(outcome.tools) > 0, seconds=30) + assert listing.tools == (f"{alias}-shallow",), listing.raw + assert _worker(pinned) == worker + hooks_rig.sunk() + assert caller.call(f"{alias}-shallow", {"record": "r-1"}).text == "found" + scanned: Final = _only(_generic(hooks_rig.sunk(), "request")) + assert scanned["texts"] == ["deepest leaf", "r-1"], scanned + unpublished: Final = caller.call(f"{alias}-deep", {"record": "r-2"}) + assert _worker(pinned) == worker + assert unpublished.error is not None and "Tool 'deep' not found" in unpublished.raw, unpublished.raw + reached: Final = tool_calls(peer.drain()) + assert [object_value(JSON_OBJECT.validate_python(call["body"])["params"])["name"] for call in reached] == [ + "shallow" + ] + relisted: Final = _generic(hooks_rig.sunk(), "request") + assert all((scan["mcp_tool_name"], scan["litellm_call_id"]) == ("shallow", None) for scan in relisted), relisted + rows: Final = _rows(key, 3) + assert [(row["call_type"], row["status"]) for row in rows] == [ + ("list_mcp_tools", "success"), + ("call_mcp_tool", "success"), + ("call_mcp_tool", "failure"), + ], rows + assert [_tool_metadata(row)["name"] for row in rows[1:]] == ["shallow", "deep"], rows + failed: Final = object_value(JSON_OBJECT.validate_python(rows[2]["metadata"])["error_information"]) + assert failed["error_message"] == "404: Tool 'deep' not found", failed + + +def test_an_adapter_returning_the_wrong_number_of_texts_fails_closed_before_the_peer(hooks_rig: HooksRig) -> None: + with ( + scripted_peer(_lookup_tool()) as peer, + _pinned(hooks_rig.gateway) as (pinned, worker), + pinned.scenario() as scenario, + ): + alias: Final = "count" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + caller: Final = McpCaller(pinned, key, "mcp", headers={"x-mcp-servers": alias}) + assert eventually(caller.initialize, lambda outcome: outcome.ok, seconds=30).ok + name: Final = next( + tool for tool in eventually(caller.list_tools, _has_lookup, seconds=30).tools if "lookup" in tool + ) + assert _worker(pinned) == worker + hooks_rig.sunk() + blocked: Final = caller.call(name, {"record": COUNT_MISMATCH}) + assert _worker(pinned) == worker + assert blocked.error is not None, blocked.raw + assert ( + "guardrail returned 4 texts for 3 MCP tool strings, so the redaction cannot be mapped back" in blocked.raw + ) + assert tool_calls(peer.drain()) == (), "the blocked call reached the peer" + sunk: Final = hooks_rig.sunk() + assert _only(_generic(sunk, "request"))["texts"] == [LOOKUP_DESCRIPTION, "record identifier", COUNT_MISMATCH] + assert _native(sunk, "post") == (), sunk + rows: Final = _rows(key, 2) + assert [(row["call_type"], row["status"]) for row in rows] == [ + ("list_mcp_tools", "success"), + ("call_mcp_tool", "failure"), + ], rows + assert _tool_metadata(rows[1])["arguments"] == {"record": COUNT_MISMATCH}, rows[1] diff --git a/tests/integration/mcp/test_mcp_credentials.py b/tests/integration/mcp/test_mcp_credentials.py index 95a5e46646b..16dcaab274a 100644 --- a/tests/integration/mcp/test_mcp_credentials.py +++ b/tests/integration/mcp/test_mcp_credentials.py @@ -1,21 +1,32 @@ import base64 +import re +import textwrap import uuid +from collections.abc import Iterator +from pathlib import Path from typing import Final import pytest -from integration._support.client import Gateway, eventually +from integration._support.client import Gateway, Scenario, eventually, gateway_from_environment from integration._support.database import read_rows from integration._support.mcp import ( ENTRY_POINTS, EntryPoint, McpCaller, McpPeer, + Outcome, + ScriptedTool, call_tool, mcp_peer, register_mcp, + scripted_peer, + text_result, tool_calls, tool_names, ) +from integration._support.oauth_server import oauth_server +from integration._support.process import owned_proxy +from pydantic import TypeAdapter ADD: Final = {"a": 2, "b": 3} STATIC_MODES: Final = ( @@ -192,3 +203,288 @@ def test_byok_server_uses_the_calling_users_stored_credential_and_fails_closed_w assert removed.status_code in (200, 204), removed.text eventually(lambda: call_tool(gateway, owner_key, identity, name, ADD), lambda value: value.status_code == 401) assert tool_calls(peer.drain()) == () + + +def _listings(peer: McpPeer) -> tuple[dict[str, object], ...]: + return tuple( + item + for item in peer.drain() + if isinstance(item.get("body"), dict) and item["body"].get("method") == "tools/list" + ) + + +def test_oauth2_byok_listing_sends_the_minted_token_not_the_users_stored_secret(gateway: Gateway) -> None: + with mcp_peer() as peer, oauth_server() as auth, gateway.scenario() as scenario: + alias: Final = "cc" + uuid.uuid4().hex[:8] + identity: Final = register_mcp( + scenario, + peer, + alias, + auth_type="oauth2", + oauth2_flow="client_credentials", + is_byok=True, + token_url=auth.issuer + "/token", + credentials={"client_id": "cc-client", "client_secret": "cc-secret-" + uuid.uuid4().hex}, + ) + owner: Final = scenario.user() + owner_key: Final = scenario.key(user_id=owner, object_permission={"mcp_servers": [identity]}) + secret: Final = "byok-" + uuid.uuid4().hex + stored: Final = gateway.client.post( + f"/v1/mcp/server/{identity}/user-credential", + json={"credential": secret}, + headers={"x-litellm-api-key": owner_key}, + ) + assert stored.status_code in (200, 201), stored.text + scenario.cleanups.callback( + gateway.client.delete, + f"/v1/mcp/server/{identity}/user-credential", + headers={"x-litellm-api-key": owner_key}, + ) + peer.drain() + auth.drain() + response: Final = gateway.client.get( + "/mcp-rest/tools/list", params={"server_id": identity}, headers={"x-litellm-api-key": owner_key} + ) + assert response.status_code == 200, response.text + assert "add" in {tool["name"] for tool in response.json()["tools"]}, response.text + assert [request["grant_type"] for request in auth.token_requests()] == ["client_credentials"] + listings: Final = _listings(peer) + assert len(listings) == 1, listings + sent: Final = _header(listings[0], b"authorization") + assert sent is not None and auth.is_live(sent.decode().removeprefix("Bearer ")), sent + assert secret.encode() not in sent, "stored BYOK secret replaced the minted token on tools/list" + + +@pytest.mark.parametrize(("auth_type", "header", "shape"), STATIC_MODES[:2]) +def test_byok_rest_listing_sends_the_servers_static_credential_not_the_users_stored_secret( + gateway: Gateway, auth_type: str, header: bytes, shape: str +) -> None: + with mcp_peer() as peer, gateway.scenario() as scenario: + alias: Final = "byok" + uuid.uuid4().hex[:8] + static: Final = "static-" + uuid.uuid4().hex + identity: Final = register_mcp( + scenario, peer, alias, auth_type=auth_type, is_byok=True, credentials={"auth_value": static} + ) + owner: Final = scenario.user() + owner_key: Final = scenario.key(user_id=owner, object_permission={"mcp_servers": [identity]}) + secret: Final = "byok-" + uuid.uuid4().hex + stored: Final = gateway.client.post( + f"/v1/mcp/server/{identity}/user-credential", + json={"credential": secret}, + headers={"x-litellm-api-key": owner_key}, + ) + assert stored.status_code in (200, 201), stored.text + scenario.cleanups.callback( + gateway.client.delete, + f"/v1/mcp/server/{identity}/user-credential", + headers={"x-litellm-api-key": owner_key}, + ) + peer.drain() + response: Final = gateway.client.get( + "/mcp-rest/tools/list", params={"server_id": identity}, headers={"x-litellm-api-key": owner_key} + ) + assert response.status_code == 200, response.text + assert "add" in {tool["name"] for tool in response.json()["tools"]}, response.text + listings: Final = _listings(peer) + assert len(listings) == 1, listings + assert _header(listings[0], header) == shape.format(secret=static, basic="").encode(), listings[0]["headers"] + peer.drain() + called: Final = call_tool(gateway, owner_key, identity, f"{alias}-add", ADD) + assert called.status_code == 200, called.text + assert _header(_one_call(peer), header) == shape.format(secret=secret, basic="").encode() + + +def test_deprecated_string_x_mcp_auth_lists_a_byok_server_for_a_key_without_a_user(gateway: Gateway) -> None: + with mcp_peer() as peer, gateway.scenario() as scenario: + alias: Final = "byok" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias, auth_type="bearer_token", is_byok=True) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + peer.drain() + response: Final = gateway.client.get( + "/mcp-rest/tools/list", + params={"server_id": identity}, + headers={"x-litellm-api-key": key, "x-mcp-auth": "Bearer hdr"}, + ) + assert response.status_code == 200, response.text + names: Final = {tool["name"] for tool in response.json()["tools"]} + assert "add" in names, names + listings: Final = _listings(peer) + assert len(listings) == 1, listings + assert listings[0]["headers"].get(b"authorization") == b"Bearer hdr" + + +_PROBE: Final = "catalog-probe" +_ECHO: Final = "catalog-echo" +_UNLISTED: Final = "" +_GUARDRAIL_CODE: Final = ( + "def apply_guardrail(inputs, request_data, input_type):\n" + f' if "{_PROBE}" not in list(inputs.get("texts") or []):\n' + " return allow()\n" + ' function = inputs.get("tools", [{}])[0].get("function", {})\n' + f' return block("{_ECHO}[" + function.get("description") + "]")\n' +) + + +_ECHO_GUARDRAIL_YAML: Final = ( + "guardrails:\n" + " - guardrail_name: catalog-echo\n" + " litellm_params:\n" + " guardrail: custom_code\n" + " mode: pre_mcp_call\n" + " default_on: true\n" + " custom_code: |\n" + textwrap.indent(_GUARDRAIL_CODE, 8 * " ") +) + + +@pytest.fixture(scope="module") +def echo_rig(tmp_path_factory: pytest.TempPathFactory) -> Iterator[Gateway]: + directory: Final = tmp_path_factory.mktemp("catalog-echo") + path: Final = directory / "catalog_echo.yaml" + path.write_text((Path(__file__).resolve().parents[1] / "proxy_config.yaml").read_text() + _ECHO_GUARDRAIL_YAML) + with gateway_from_environment() as gateway, owned_proxy(gateway, directory, {}, config=path, workers=2) as rig: + yield rig + + +def _echoed_description(outcome: Outcome) -> str: + found: Final = re.search(rf"{_ECHO}\[(.*?)\]", outcome.raw) + assert found is not None, outcome.raw + return found.group(1) + + +_PROBE_ARGUMENTS: Final = {"probe": _PROBE} +_HEADERS: Final = TypeAdapter(dict[str, str]) + + +def _store_byok_credential(scenario: Scenario, identity: str, key: str, secret: str) -> None: + stored: Final = scenario.gateway.client.post( + f"/v1/mcp/server/{identity}/user-credential", json={"credential": secret}, headers={"x-litellm-api-key": key} + ) + assert stored.status_code in (200, 201), stored.text + scenario.cleanups.callback( + scenario.gateway.client.delete, f"/v1/mcp/server/{identity}/user-credential", headers={"x-litellm-api-key": key} + ) + + +def test_rotating_the_credential_drops_the_callers_listing_until_it_lists_again(echo_rig: Gateway) -> None: + with mcp_peer() as peer, echo_rig.scenario() as scenario: + first: Final = "cred-" + uuid.uuid4().hex + second: Final = "cred-" + uuid.uuid4().hex + alias: Final = "rot" + uuid.uuid4().hex[:8] + identity: Final = register_mcp( + scenario, peer, alias, auth_type="bearer_token", credentials={"auth_value": first} + ) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + caller: Final = McpCaller(echo_rig, key, "mcp", alias) + assert caller.list_tools().ok + assert _echoed_description(caller.call(f"{alias}-add", _PROBE_ARGUMENTS)) == "Add two integers" + rotated: Final = echo_rig.request( + "PUT", "/v1/mcp/server", {"server_id": identity, "credentials": {"auth_value": second}} + ) + assert rotated.status_code == 202, rotated.text + eventually( + lambda: _echoed_description(caller.call(f"{alias}-add", _PROBE_ARGUMENTS)), lambda seen: seen == _UNLISTED + ) + peer.drain() + assert caller.list_tools().ok + assert _echoed_description(caller.call(f"{alias}-add", _PROBE_ARGUMENTS)) == "Add two integers" + relisted: Final = _listings(peer) + assert len(relisted) == 1, relisted + assert _header(relisted[0], b"authorization") == f"Bearer {second}".encode(), relisted[0]["headers"] + + +def test_byok_callers_are_evaluated_against_their_own_listing_and_the_stored_secret_never_keys_the_slot( + echo_rig: Gateway, +) -> None: + with mcp_peer() as peer, echo_rig.scenario() as scenario: + alias: Final = "byok" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias, auth_type="api_key", is_byok=True) + owner_key: Final = scenario.key(user_id=scenario.user(), object_permission={"mcp_servers": [identity]}) + stranger_key: Final = scenario.key(user_id=scenario.user(), object_permission={"mcp_servers": [identity]}) + owner_secret: Final = "byok-" + uuid.uuid4().hex + replacement: Final = "byok-" + uuid.uuid4().hex + _store_byok_credential(scenario, identity, owner_key, owner_secret) + _store_byok_credential(scenario, identity, stranger_key, "byok-" + uuid.uuid4().hex) + owner: Final = McpCaller(echo_rig, owner_key, "mcp", alias) + stranger: Final = McpCaller(echo_rig, stranger_key, "mcp", alias) + peer.drain() + assert owner.list_tools().ok + listings: Final = _listings(peer) + assert [_header(item, b"x-api-key") for item in listings] == [owner_secret.encode()], listings + own: Final = _echoed_description(owner.call(f"{alias}-add", _PROBE_ARGUMENTS)) + other: Final = _echoed_description(stranger.call(f"{alias}-add", _PROBE_ARGUMENTS)) + assert (own, other) == ("Add two integers", _UNLISTED), (own, other) + _store_byok_credential(scenario, identity, owner_key, replacement) + assert _echoed_description(owner.call(f"{alias}-add", _PROBE_ARGUMENTS)) == "Add two integers", ( + "the slot is keyed by the client-supplied header, never by the stored credential" + ) + sent: Final = eventually( + lambda: (owner.call(f"{alias}-add", ADD).ok, tool_calls(peer.drain())), + lambda value: any(_header(call, b"x-api-key") == replacement.encode() for call in value[1]), + ) + assert sent[0], sent + + +def test_callers_with_different_server_scoped_auth_headers_are_evaluated_against_their_own_listings( + echo_rig: Gateway, +) -> None: + tool: Final = ScriptedTool( + "add", + lambda _: text_result("3"), + description=lambda headers: "Adds for " + headers.get("authorization", "nobody"), + ) + with scripted_peer(tool) as peer, echo_rig.scenario() as scenario: + alias: Final = "scoped" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + acme_token: Final = "acme-" + uuid.uuid4().hex + globex_token: Final = "globex-" + uuid.uuid4().hex + acme: Final = McpCaller(echo_rig, key, "mcp", alias, {f"x-mcp-{alias}-authorization": f"Bearer {acme_token}"}) + globex: Final = McpCaller( + echo_rig, key, "mcp", alias, {f"x-mcp-{alias}-authorization": f"Bearer {globex_token}"} + ) + assert acme.list_tools().ok and globex.list_tools().ok + seen: Final = ( + _echoed_description(acme.call(f"{alias}-add", _PROBE_ARGUMENTS)), + _echoed_description(globex.call(f"{alias}-add", _PROBE_ARGUMENTS)), + ) + assert seen == (f"Adds for Bearer {acme_token}", f"Adds for Bearer {globex_token}"), seen + assert tool_calls(peer.drain()) == (), "a blocked probe reached the peer" + + +def test_deprecated_string_x_mcp_auth_callers_on_a_user_less_key_own_separate_listings(echo_rig: Gateway) -> None: + tool: Final = ScriptedTool( + "add", + lambda _: text_result("3"), + description=lambda headers: "Adds for " + headers.get("authorization", "nobody"), + ) + with scripted_peer(tool) as peer, echo_rig.scenario() as scenario: + alias: Final = "legacy" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias, auth_type="bearer_token") + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + first_token: Final = "first-" + uuid.uuid4().hex + second_token: Final = "second-" + uuid.uuid4().hex + first: Final = McpCaller(echo_rig, key, "mcp", alias, {"x-mcp-auth": f"Bearer {first_token}"}) + second: Final = McpCaller(echo_rig, key, "mcp", alias, {"x-mcp-auth": f"Bearer {second_token}"}) + assert _echoed_description(first.call(f"{alias}-add", _PROBE_ARGUMENTS)) == _UNLISTED + peer.drain() + assert first.list_tools().ok + listings: Final = _listings(peer) + assert len(listings) == 1, listings + listed_with: Final = _HEADERS.validate_python(listings[0]["headers"]) + assert listed_with.get("authorization") == f"Bearer {first_token}", listed_with + warm: Final = eventually( + lambda: _echoed_description(first.call(f"{alias}-add", _PROBE_ARGUMENTS)), + lambda seen: seen != _UNLISTED, + ) + assert warm == f"Adds for Bearer {first_token}", warm + assert _echoed_description(second.call(f"{alias}-add", _PROBE_ARGUMENTS)) == _UNLISTED + assert second.list_tools().ok + seen: Final = eventually( + lambda: ( + _echoed_description(first.call(f"{alias}-add", _PROBE_ARGUMENTS)), + _echoed_description(second.call(f"{alias}-add", _PROBE_ARGUMENTS)), + ), + lambda pair: _UNLISTED not in pair, + ) + assert seen == (f"Adds for Bearer {first_token}", f"Adds for Bearer {second_token}"), seen + assert tool_calls(peer.drain()) == (), "a blocked probe reached the peer" diff --git a/tests/integration/mcp/test_mcp_lifecycle.py b/tests/integration/mcp/test_mcp_lifecycle.py index fa253f03520..eed3cbf658e 100644 --- a/tests/integration/mcp/test_mcp_lifecycle.py +++ b/tests/integration/mcp/test_mcp_lifecycle.py @@ -1,7 +1,9 @@ import functools import json import uuid +from collections.abc import Mapping from contextlib import ExitStack +from hashlib import sha256 from pathlib import Path from typing import Final @@ -14,15 +16,27 @@ from integration._support.client import Gateway, eventually from integration._support.database import read_rows from integration._support.generation import LIFECYCLE_SETTINGS, bounded_http_requests from integration._support.mcp import ( + JsonRpc, McpCaller, Outcome, + ScriptedTool, call_tool, mcp_peer, register_mcp, + scripted_peer, + text_result, tool_calls, tool_names, ) from integration._support.process import owned_proxy +from pydantic import TypeAdapter + +_SPEND_NONCES: Final = ( + "SELECT status, metadata->'mcp_tool_call_metadata'->'arguments'->>'nonce' AS nonce" + ' FROM "LiteLLM_SpendLogs" WHERE api_key = %s AND call_type = %s' +) +_OBJECTS: Final = TypeAdapter(Mapping[str, object]) +_STRINGS: Final = TypeAdapter(Mapping[str, str]) @pytest.mark.covers("mcp.call_tool.saved_headers.reach_actual_transport") @@ -463,9 +477,7 @@ def _update_tool_permissions( assert updated.status_code == 200, updated.text -def _listing_on_both( - gateway: Gateway, peer: Gateway, key: str, expected: set[str] -) -> None: +def _listing_on_both(gateway: Gateway, peer: Gateway, key: str, expected: set[str]) -> None: for worker in (gateway, peer): listing: Final = eventually( functools.partial(_granted_view, worker, key), @@ -525,3 +537,56 @@ def test_key_update_tool_permission_widen_narrow_and_clear_apply_on_both_workers _listing_on_both(gateway, peer, key, all_tools) nulled: Final = _multiply_outcome_on_both(gateway, peer, key, alias) assert [call.text for call in nulled] == ["6", "6"], [call.raw for call in nulled] + + +def _nonce_echo(params: JsonRpc) -> JsonRpc: + return text_result(_STRINGS.validate_python(params["arguments"])["nonce"]) + + +def _call_params(call: Mapping[str, object]) -> Mapping[str, object]: + return _OBJECTS.validate_python(_OBJECTS.validate_python(call["body"])["params"]) + + +def _listed(caller: McpCaller, name: str) -> None: + listing: Final = eventually(caller.list_tools, lambda outcome: name in outcome.tools, seconds=45) + assert listing.error is None, (caller.gateway.client.base_url, listing.raw) + + +def test_tool_calls_on_both_workers_stay_base_compatible_after_each_worker_lists( + gateway: Gateway, peer: Gateway +) -> None: + schema: Final = {"type": "object", "properties": {"nonce": {"type": "string"}}} + tool: Final = ScriptedTool("echo", _nonce_echo, description="Echo the nonce back", input_schema=schema) + with scripted_peer(tool) as upstream, gateway.scenario() as scenario: + alias: Final = "compat" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, upstream, alias) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + name: Final = f"{alias}-echo" + first: Final = McpCaller(gateway, key, "mcp", alias) + second: Final = McpCaller(peer, key, "mcp", alias) + _listed(first, name) + _listed(second, name) + upstream.drain() + nonces: Final = (uuid.uuid4().hex, uuid.uuid4().hex) + outcomes: Final = ( + first.call(name, {"nonce": nonces[0]}), + second.call(name, {"nonce": nonces[1]}), + first.call(name, {"nonce": nonces[0]}), + ) + assert [outcome.text for outcome in outcomes] == [nonces[0], nonces[1], nonces[0]], [o.raw for o in outcomes] + params: Final = [_call_params(call) for call in tool_calls(upstream.drain())] + assert [set(entry) - {"_meta"} for entry in params] == [{"name", "arguments"}] * 3, params + assert [entry["name"] for entry in params] == ["echo"] * 3, params + assert [entry["arguments"] for entry in params] == [ + {"nonce": nonces[0]}, + {"nonce": nonces[1]}, + {"nonce": nonces[0]}, + ], params + rows: Final = eventually( + lambda: read_rows(_SPEND_NONCES, (sha256(key.encode()).hexdigest(), "call_mcp_tool")), + lambda found: len(found) >= 3, + seconds=70, + ) + assert sorted((str(row["status"]), str(row["nonce"])) for row in rows) == sorted( + ("success", nonce) for nonce in (nonces[0], nonces[1], nonces[0]) + ), rows diff --git a/tests/integration/mcp/test_mcp_listed_tool_metadata.py b/tests/integration/mcp/test_mcp_listed_tool_metadata.py new file mode 100644 index 00000000000..d09864da4b1 --- /dev/null +++ b/tests/integration/mcp/test_mcp_listed_tool_metadata.py @@ -0,0 +1,531 @@ +"""pre_mcp_call guardrails are handed the tool entry ``tools/list`` served to the caller. + +One owned proxy carries a default-on ``custom_code`` pre_mcp_call guardrail. At listing time it masks +``SECRET`` out of every scanned text. At call time, when an argument carries the probe marker, it +blocks and echoes the description and parameters it was handed, which is the only way to observe from outside +what metadata the gateway attached to the hook +""" + +import json +import threading +import uuid +from collections.abc import Callable, Generator, Iterator, Mapping +from concurrent.futures import ThreadPoolExecutor +from contextlib import ExitStack, contextmanager +from pathlib import Path +from typing import Final + +import httpx +import pytest +import yaml +from integration._support.client import Gateway, eventually, gateway_from_environment +from integration._support.mcp import ( + EntryPoint, + JsonRpc, + McpCaller, + ScriptedTool, + listed_tools, + openapi_peer, + register_mcp, + scripted_peer, + text_result, + tool_calls, +) +from integration._support.process import owned_proxy +from pydantic import TypeAdapter + +_ECHO: Final = "catalog-echo:" +_PROBE: Final = "catalog-probe" +_CALLERS_PER_SERVER: Final = 256 +_PIN_SECONDS: Final = 120 +_COLD: Final[tuple[str, JsonRpc]] = ("", {"type": "object", "properties": {}, "additionalProperties": False}) +_PID: Final = TypeAdapter(int) +_HEADERS: Final = TypeAdapter(dict[bytes, bytes]) +_SCHEMA: Final = TypeAdapter(dict[str, object]) +_LOOKUP_SCHEMA: Final = { + "type": "object", + "properties": {"probe": {"type": "string", "description": "a probe marker"}}, + "additionalProperties": False, +} +_GUARDRAIL_CODE: Final = ( + "def apply_guardrail(inputs, request_data, input_type):\n" + ' texts = list(inputs.get("texts") or [])\n' + ' function = inputs.get("tools", [{}])[0].get("function", {})\n' + f' if "{_PROBE}" in texts:\n' + f' return block("{_ECHO}" + json_stringify(' + '{"description": function.get("description"), "parameters": function.get("parameters")}))\n' + ' masked = [text.replace("SECRET", "[MASKED]") for text in texts]\n' + " if masked != texts:\n" + " return modify(texts=masked)\n" + " return allow()\n" +) + + +@pytest.fixture(scope="module") +def rig(tmp_path_factory: pytest.TempPathFactory) -> Iterator[Gateway]: + directory: Final = tmp_path_factory.mktemp("listed-tool-metadata") + config: Final = yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text()) + config["guardrails"] = [ + { + "guardrail_name": "catalog-echo-" + uuid.uuid4().hex[:8], + "litellm_params": { + "guardrail": "custom_code", + "mode": "pre_mcp_call", + "default_on": True, + "custom_code": _GUARDRAIL_CODE, + }, + } + ] + config["general_settings"] = {**config["general_settings"], "proxy_config_reload_interval_seconds": 1} + path: Final = directory / "config.yaml" + path.write_text(yaml.safe_dump(config)) + with ( + gateway_from_environment() as gateway, + owned_proxy(gateway, directory, {"KEEPALIVE_TIMEOUT": "120"}, config=path, workers=2) as candidate, + ExitStack() as stack, + ): + _two_workers(stack, candidate) + yield candidate + + +def _strings(value: object) -> Iterator[str]: + if isinstance(value, str): + yield value + return + children: Final = value.values() if isinstance(value, Mapping) else value if isinstance(value, list) else () + for child in children: + yield from _strings(child) + + +def _decoded(raw: str) -> object: + data: Final = tuple(line[5:].strip() for line in raw.splitlines() if line.startswith("data:")) + return json.loads(data[-1] if data else raw) + + +def _echoed(raw: str) -> tuple[str | None, Mapping[str, object] | None]: + """The (description, parameters) the guardrail was handed, recovered from its block reason.""" + carrier: Final = next((text for text in _strings(_decoded(raw)) if _ECHO in text), None) + assert carrier is not None, raw + echoed, _ = json.JSONDecoder().raw_decode(carrier.split(_ECHO, 1)[1]) + assert isinstance(echoed, dict), carrier + return echoed.get("description"), echoed.get("parameters") + + +def _probe(caller: McpCaller, name: str, server_id: str) -> tuple[str | None, Mapping[str, object] | None]: + outcome: Final = caller.call(name, {"probe": _PROBE}, server_id=server_id) + assert outcome.error is not None, outcome.raw + return _echoed(outcome.raw) + + +def _worker(gateway: Gateway) -> int: + response: Final = gateway.request("GET", "/debug/memory/summary") + assert response.status_code == 200, response.text + return _PID.validate_python(response.json()["worker_pid"]) + + +@contextmanager +def _pinned(rig: Gateway) -> Generator[Gateway, None, None]: + """A single keep-alive connection, so every request on it is served by the worker that accepted it.""" + limits: Final = httpx.Limits(max_connections=1, max_keepalive_connections=1) + with httpx.Client(base_url=rig.client.base_url, timeout=15, trust_env=False, limits=limits) as client: + yield Gateway(client, rig.key, rig.upstream_url) + + +def _connection(stack: ExitStack, rig: Gateway, wanted: Callable[[int], bool]) -> tuple[Gateway, int]: + """A pinned connection to a worker ``wanted`` accepts; a worker still starting up accepts nothing yet.""" + + def attempt() -> tuple[Gateway, int] | None: + with ExitStack() as candidate: + gateway: Final = candidate.enter_context(_pinned(rig)) + pid: Final = _worker(gateway) + if not wanted(pid): + return None + stack.enter_context(candidate.pop_all()) + return gateway, pid + + found: Final = eventually(attempt, lambda pair: pair is not None, seconds=_PIN_SECONDS) + assert found is not None + return found + + +def _two_workers(stack: ExitStack, rig: Gateway) -> tuple[tuple[Gateway, int], tuple[Gateway, int]]: + """Connects while the first worker is busy answering, so the idle worker wins the accept race.""" + first: Final = _connection(stack, rig, lambda _: True) + stop: Final = threading.Event() + + def keep_busy() -> None: + while not stop.is_set(): + _worker(first[0]) + + with ThreadPoolExecutor(max_workers=1) as pool: + busy: Final = pool.submit(keep_busy) + try: + other: Final = _connection(stack, rig, lambda pid: pid != first[1]) + finally: + stop.set() + busy.result() + return first, other + + +def _served_name(gateway: Gateway, key: str, identity: str, tool: str) -> str: + """The prefixed name this worker lists for ``tool`` once its registry reload carries the server.""" + listing: Final = eventually( + lambda: McpCaller(gateway, key, "rest").list_tools(server_id=identity), + lambda value: value.ok and any(full.endswith(tool) for full in value.tools), + ) + return next(full for full in listing.tools if full.endswith(tool)) + + +def _settled_probe( + gateway: Gateway, key: str, name: str, identity: str +) -> tuple[str | None, Mapping[str, object] | None]: + """The hook echo for a direct call, once this worker's registry reload carries the server.""" + outcome: Final = eventually( + lambda: McpCaller(gateway, key, "rest").call(name, {"probe": _PROBE}, server_id=identity), + lambda value: value.error is not None and _ECHO in value.raw, + ) + return _echoed(outcome.raw) + + +def _forwarded_tenants(observed: tuple[dict[str, object], ...]) -> frozenset[bytes]: + return frozenset(_HEADERS.validate_python(item["headers"]).get(b"x-tenant", b"") for item in observed) - {b""} + + +def _lookup_tool(description: str | Callable[[Mapping[str, str]], str] = "Look up one record") -> ScriptedTool: + return ScriptedTool("lookup", lambda _: text_result("found"), description=description, input_schema=_LOOKUP_SCHEMA) + + +@pytest.mark.parametrize("entry", ["rest", "mcp"]) +def test_pre_call_hook_receives_the_description_and_input_schema_the_caller_was_listed( + rig: Gateway, entry: EntryPoint +) -> None: + schema: Final = {"type": "object", "properties": {"probe": {"type": "string", "description": "a probe marker"}}} + tool: Final = ScriptedTool( + "lookup", lambda _: text_result("found"), description="Look up one record", input_schema=schema + ) + with scripted_peer(tool) as peer, rig.scenario() as scenario: + alias: Final = "meta" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + caller: Final = McpCaller(rig, key, entry, headers={"x-mcp-servers": alias}) + assert caller.initialize().ok + listed: Final = caller.list_tools(server_id=identity) + assert listed.ok, listed.raw + name: Final = next(full for full in listed.tools if full.endswith("lookup")) + description, parameters = _probe(caller, name, identity) + assert description == "Look up one record", (description, parameters) + assert parameters is not None and parameters.get("properties") == schema["properties"], parameters + + +def test_each_caller_is_evaluated_against_the_catalog_its_own_forwarded_headers_produced(rig: Gateway) -> None: + tool: Final = ScriptedTool( + "report", + lambda _: text_result("ok"), + description=lambda headers: f"Report for tenant {headers.get('x-tenant', 'nobody')}", + ) + with scripted_peer(tool) as peer, rig.scenario() as scenario: + alias: Final = "tenant" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias, extra_headers=["x-tenant"]) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + acme: Final = McpCaller(rig, key, "server_mcp", alias, headers={"x-tenant": "acme"}) + globex: Final = McpCaller(rig, key, "server_mcp", alias, headers={"x-tenant": "globex"}) + acme_listing: Final = acme.list_tools() + globex_listing: Final = globex.list_tools() + assert acme_listing.ok and globex_listing.ok, (acme_listing.raw, globex_listing.raw) + name: Final = next(full for full in acme_listing.tools if full.endswith("report")) + acme_seen, _ = _probe(acme, name, identity) + globex_seen, _ = _probe(globex, name, identity) + assert (acme_seen, globex_seen) == ("Report for tenant acme", "Report for tenant globex"), ( + "each caller's tools/call must be evaluated against the catalog its own headers listed" + ) + + +def test_call_is_evaluated_against_the_masked_description_the_listing_served(rig: Gateway) -> None: + tool: Final = ScriptedTool("read_note", lambda _: text_result("note"), description="Read a note") + with scripted_peer(tool) as peer, rig.scenario() as scenario: + alias: Final = "note" + uuid.uuid4().hex[:8] + identity: Final = register_mcp( + scenario, peer, alias, tool_name_to_description={"read_note": "Read a SECRET note"} + ) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + served: Final = listed_tools(rig, key, identity) + name: Final = next(full for full in served if full.endswith("read_note")) + assert served[name]["description"] == "Read a [MASKED] note", served[name] + seen, _ = _probe(McpCaller(rig, key, "rest"), name, identity) + assert seen == "Read a [MASKED] note", "the admin override must not restore wording the listing masked" + + +def test_openapi_call_is_evaluated_against_the_masked_override_the_listing_served(rig: Gateway) -> None: + with openapi_peer() as peer, rig.scenario() as scenario: + alias: Final = "pets" + uuid.uuid4().hex[:8] + identity: Final = register_mcp( + scenario, peer, alias, tool_name_to_description={"getpet": "Fetch one SECRET pet"} + ) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + served: Final = listed_tools(rig, key, identity) + name: Final = next(full for full in served if full.endswith("getpet")) + assert served[name]["description"] == "Fetch one [MASKED] pet", served[name] + seen, parameters = _probe(McpCaller(rig, key, "rest"), name, identity) + assert seen == "Fetch one [MASKED] pet", "the OpenAPI call path must hand hooks the entry the listing served" + assert parameters is not None and "petId" in parameters.get("properties", {}), parameters + assert not [call for call in peer.drain() if call["path"].startswith("/pets")], "blocked before upstream" + + +def test_openapi_call_is_evaluated_against_the_entry_this_key_was_listed_not_the_last_listing( + rig: Gateway, +) -> None: + with openapi_peer() as peer, rig.scenario() as scenario: + alias: Final = "pets" + uuid.uuid4().hex[:8] + identity: Final = register_mcp( + scenario, peer, alias, tool_name_to_description={"getpet": "Fetch one SECRET pet"} + ) + guarded: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + opted_out: Final = scenario.key( + object_permission={"mcp_servers": [identity]}, metadata={"disable_global_guardrails": True} + ) + guarded_served: Final = listed_tools(rig, guarded, identity) + opted_out_served: Final = listed_tools(rig, opted_out, identity) + name: Final = next(full for full in guarded_served if full.endswith("getpet")) + assert (guarded_served[name]["description"], opted_out_served[name]["description"]) == ( + "Fetch one [MASKED] pet", + "Fetch one SECRET pet", + ), (guarded_served[name], opted_out_served[name]) + seen, _ = _probe(McpCaller(rig, guarded, "rest"), name, identity) + assert seen == "Fetch one [MASKED] pet", ( + "the guarded key must be evaluated against its own listing, not the opted-out key's later one" + ) + + +def test_direct_call_without_a_listing_hands_the_hook_no_metadata_on_either_worker(rig: Gateway) -> None: + with scripted_peer(_lookup_tool()) as peer, ExitStack() as stack: + (first, first_pid), (other, other_pid) = _two_workers(stack, rig) + with first.scenario() as scenario: + identity: Final = register_mcp(scenario, peer, "cold" + uuid.uuid4().hex[:8]) + observer: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + name: Final = _served_name(first, observer, identity, "lookup") + seen: Final = tuple(_settled_probe(gateway, key, name, identity) for gateway in (first, other)) + assert seen == (_COLD, _COLD), (seen, first_pid, other_pid) + assert (_worker(first), _worker(other)) == (first_pid, other_pid) + assert tool_calls(peer.drain()) == (), "the probe is blocked at the hook, before the upstream" + + +def test_warm_metadata_is_local_to_the_worker_that_served_the_listing(rig: Gateway) -> None: + with scripted_peer(_lookup_tool()) as peer, ExitStack() as stack: + (first, first_pid), (other, other_pid) = _two_workers(stack, rig) + with first.scenario() as scenario: + identity: Final = register_mcp(scenario, peer, "local" + uuid.uuid4().hex[:8]) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + name: Final = _served_name(first, key, identity, "lookup") + warm: Final = ("Look up one record", _LOOKUP_SCHEMA) + assert _probe(McpCaller(first, key, "rest"), name, identity) == warm, first_pid + assert _settled_probe(other, key, name, identity) == _COLD, ( + "a worker that never served this caller a listing has no catalog for it", + other_pid, + ) + assert _served_name(other, key, identity, "lookup") == name + assert _probe(McpCaller(other, key, "rest"), name, identity) == warm, other_pid + assert (_worker(first), _worker(other)) == (first_pid, other_pid) + assert tool_calls(peer.drain()) == () + + +def test_listed_tools_without_a_description_still_hand_the_hook_the_schema_the_listing_served(rig: Gateway) -> None: + open_schema: Final[JsonRpc] = {"type": "object", "properties": {}, "additionalProperties": True} + undescribed: Final = ScriptedTool("undescribed", lambda _: text_result("ok"), input_schema=open_schema) + blank: Final = ScriptedTool("blank", lambda _: text_result("ok"), description="", input_schema=open_schema) + with scripted_peer(undescribed, blank) as peer, _pinned(rig) as worker, worker.scenario() as scenario: + pid: Final = _worker(worker) + identity: Final = register_mcp(scenario, peer, "bare" + uuid.uuid4().hex[:8]) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + served: Final = listed_tools(worker, key, identity) + names: Final = tuple(next(full for full in served if full.endswith(tool)) for tool in ("undescribed", "blank")) + assert tuple((served[name].get("description") or "", served[name]["inputSchema"]) for name in names) == ( + ("", open_schema), + ("", open_schema), + ), served + seen: Final = tuple(_probe(McpCaller(worker, key, "rest"), name, identity) for name in names) + assert seen == (("", open_schema), ("", open_schema)), (seen, _COLD) + assert _worker(worker) == pid + assert tool_calls(peer.drain()) == () + + +def test_hook_receives_the_nested_schema_with_the_leaves_the_listing_masked(rig: Gateway) -> None: + schema: Final = { + "type": "object", + "required": ["filter"], + "additionalProperties": False, + "properties": { + "filter": { + "type": "object", + "properties": { + "path": {"type": "string", "description": "SECRET path"}, + "tags": {"type": "array", "items": {"type": "string", "description": "one SECRET tag"}}, + }, + } + }, + } + masked: Final = _SCHEMA.validate_python(json.loads(json.dumps(schema).replace("SECRET", "[MASKED]"))) + tool: Final = ScriptedTool( + "search", lambda _: text_result("hit"), description="Search SECRET records", input_schema=schema + ) + with scripted_peer(tool) as peer, _pinned(rig) as worker, worker.scenario() as scenario: + pid: Final = _worker(worker) + identity: Final = register_mcp(scenario, peer, "nested" + uuid.uuid4().hex[:8]) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + served: Final = listed_tools(worker, key, identity) + name: Final = next(full for full in served if full.endswith("search")) + assert (served[name]["description"], served[name]["inputSchema"]) == ("Search [MASKED] records", masked), served + assert _probe(McpCaller(worker, key, "rest"), name, identity) == ("Search [MASKED] records", masked), ( + "the hook must be handed the nested schema exactly as the listing served it" + ) + assert _worker(worker) == pid + assert tool_calls(peer.drain()) == () + + +def test_a_server_definition_update_drops_the_catalog_on_every_worker_until_the_caller_lists_again( + rig: Gateway, +) -> None: + with scripted_peer(_lookup_tool()) as peer, ExitStack() as stack: + (first, first_pid), (other, other_pid) = _two_workers(stack, rig) + with first.scenario() as scenario: + identity: Final = register_mcp(scenario, peer, "upd" + uuid.uuid4().hex[:8]) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + name: Final = _served_name(first, key, identity, "lookup") + assert _served_name(other, key, identity, "lookup") == name + before: Final = tuple(_probe(McpCaller(gateway, key, "rest"), name, identity) for gateway in (first, other)) + assert before == (("Look up one record", _LOOKUP_SCHEMA),) * 2, before + updated: Final = first.request( + "PUT", + "/v1/mcp/server", + {"server_id": identity, "tool_name_to_description": {"lookup": "Audited lookup"}}, + ) + assert updated.status_code == 202, updated.text + assert _probe(McpCaller(first, key, "rest"), name, identity) == _COLD, ( + "the worker that applied the update must drop its catalog at once", + first_pid, + ) + assert ( + eventually(lambda: _probe(McpCaller(other, key, "rest"), name, identity), lambda seen: seen == _COLD) + == _COLD + ), other_pid + relisted: Final = tuple( + listed_tools(gateway, key, identity)[name]["description"] for gateway in (first, other) + ) + assert relisted == ("Audited lookup", "Audited lookup"), relisted + after: Final = tuple(_probe(McpCaller(gateway, key, "rest"), name, identity) for gateway in (first, other)) + assert after == (("Audited lookup", _LOOKUP_SCHEMA),) * 2, after + assert (_worker(first), _worker(other)) == (first_pid, other_pid) + assert tool_calls(peer.drain()) == () + + +def test_a_listing_in_flight_across_a_server_update_does_not_resurrect_the_old_catalog(rig: Gateway) -> None: + started: Final = threading.Event() + release: Final = threading.Event() + + def describe(_: Mapping[str, str]) -> str: + started.set() + assert release.wait(20), "the listing was never released" + return "Look up one record" + + with ( + scripted_peer(_lookup_tool(describe)) as peer, + ExitStack() as stack, + ThreadPoolExecutor(max_workers=1) as pool, + ): + worker, pid = _connection(stack, rig, lambda _: True) + sibling, _ = _connection(stack, rig, lambda candidate: candidate == pid) + with worker.scenario() as scenario: + identity: Final = register_mcp(scenario, peer, "stale" + uuid.uuid4().hex[:8]) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + release.set() + name: Final = _served_name(worker, key, identity, "lookup") + assert _probe(McpCaller(worker, key, "rest"), name, identity) == ("Look up one record", _LOOKUP_SCHEMA) + started.clear() + release.clear() + pending: Final = pool.submit(McpCaller(worker, key, "rest").list_tools, identity) + assert started.wait(10), "the upstream never saw the in-flight listing" + updated: Final = sibling.request( + "PUT", + "/v1/mcp/server", + {"server_id": identity, "tool_name_to_description": {"lookup": "Audited lookup"}}, + ) + assert updated.status_code == 202, updated.text + release.set() + stale: Final = pending.result(timeout=20) + assert stale.ok, stale.raw + assert _probe(McpCaller(worker, key, "rest"), name, identity) == _COLD, ( + "a listing fetched before the update must not be recorded after it" + ) + assert listed_tools(worker, key, identity)[name]["description"] == "Audited lookup" + assert _probe(McpCaller(worker, key, "rest"), name, identity) == ("Audited lookup", _LOOKUP_SCHEMA) + assert (_worker(worker), _worker(sibling)) == (pid, pid) + assert tool_calls(peer.drain()) == () + + +def test_a_server_keeps_the_newest_256_caller_catalogs_and_evicts_the_oldest(rig: Gateway) -> None: + tool: Final = _lookup_tool(lambda headers: f"Lookup for tenant {headers.get('x-tenant', 'nobody')}") + with scripted_peer(tool) as peer, _pinned(rig) as worker, worker.scenario() as scenario: + pid: Final = _worker(worker) + alias: Final = "cap" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias, extra_headers=["x-tenant"]) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + tenants: Final = tuple(f"t{index}" for index in range(_CALLERS_PER_SERVER + 1)) + callers: Final = { + tenant: McpCaller(worker, key, "server_mcp", alias, headers={"x-tenant": tenant}) for tenant in tenants + } + listings: Final = tuple(callers[tenant].list_tools() for tenant in tenants) + assert all(listing.ok for listing in listings), [listing.raw for listing in listings if not listing.ok] + name: Final = next(full for full in listings[0].tools if full.endswith("lookup")) + + def seen(tenant: str) -> str | None: + return _probe(callers[tenant], name, identity)[0] + + assert (seen("t0"), seen("t1"), seen(tenants[-1])) == ( + "", + "Lookup for tenant t1", + f"Lookup for tenant {tenants[-1]}", + ), "the oldest of 257 callers is evicted, the newest 256 keep their own catalog" + assert callers["t0"].list_tools().ok + assert (seen("t0"), seen("t1")) == ("Lookup for tenant t0", ""), "relisting makes t0 newest and evicts t1" + assert _worker(worker) == pid + observed: Final = peer.drain() + assert _forwarded_tenants(observed) == frozenset(tenant.encode() for tenant in tenants), len(observed) + assert tool_calls(observed) == () + + +def test_an_admin_include_disabled_tools_listing_does_not_warm_the_runtime_catalog(rig: Gateway) -> None: + """``include_disabled_tools=true`` is the admin-only configuration view, not a listing the caller + runs against: recording it would warm tools/call metadata no runtime listing ever served.""" + tool: Final = _lookup_tool() + with scripted_peer(tool) as peer, rig.scenario() as scenario: + alias: Final = "adminview" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias) + admin: Final = rig.key + caller: Final = McpCaller(rig, admin, "rest") + name: Final = eventually( + lambda: caller.call(f"{alias}-lookup", {"probe": _PROBE}, server_id=identity), + lambda value: value.error is not None and _ECHO in value.raw, + ) + assert _echoed(name.raw) == _COLD, "before any listing the call is cold" + + view: Final = eventually( + lambda: rig.client.get( + "/mcp-rest/tools/list", + params={"server_id": identity, "include_disabled_tools": "true"}, + headers={"x-litellm-api-key": admin}, + ), + lambda response: response.status_code == 200 + and any(entry["name"].endswith("lookup") for entry in response.json()["tools"]), + ) + assert view.status_code == 200, view.text + + after_view: Final = _probe(caller, f"{alias}-lookup", identity) + assert after_view == _COLD, ( + "the admin-only include_disabled_tools view must not record the caller's listed-tools slot" + ) + + runtime: Final = caller.list_tools(server_id=identity) + assert runtime.ok, runtime.raw + assert _probe(caller, f"{alias}-lookup", identity)[0] == "Look up one record", ( + "a genuine runtime listing still warms the slot" + ) diff --git a/tests/integration/mcp/test_mcp_llm_endpoints.py b/tests/integration/mcp/test_mcp_llm_endpoints.py index 01bf006a03e..af3bff1fd8b 100644 --- a/tests/integration/mcp/test_mcp_llm_endpoints.py +++ b/tests/integration/mcp/test_mcp_llm_endpoints.py @@ -1,16 +1,35 @@ +import asyncio import json import uuid -from collections.abc import Callable, Iterator, Mapping, Sequence +from collections.abc import Callable, Generator, Iterator, Mapping, Sequence +from concurrent.futures import ThreadPoolExecutor from contextlib import contextmanager from dataclasses import dataclass -from typing import Final, Literal +from hashlib import sha256 +from pathlib import Path +from typing import Final, Literal, TypeVar import httpx import pytest -from integration._support.client import Gateway, Scenario -from integration._support.mcp import McpPeer, mcp_peer, register_mcp, tool_calls +import yaml +from integration._support.client import Gateway, Scenario, eventually, gateway_from_environment, object_value +from integration._support.database import read_rows +from integration._support.mcp import ( + McpPeer, + ScriptedTool, + mcp_peer, + register_mcp, + scripted_peer, + text_result, + tool_calls, +) from integration._support.mcp_grants import create_toolset +from integration._support.process import owned_proxy from integration._support.wire import Reply, Request, Wire, wire_server +from openai import AsyncOpenAI, OpenAI +from openai.types.chat import ChatCompletionMessageParam +from openai.types.responses.tool_param import Mcp +from pydantic import JsonValue, TypeAdapter Surface = Literal["chat", "responses", "messages", "messages_bridge"] SURFACES: Final[tuple[Surface, ...]] = ("chat", "responses", "messages", "messages_bridge") @@ -18,6 +37,9 @@ ADD: Final = {"a": 2, "b": 3} ANSWER: Final = "the sum is 5" GATEWAY_REF: Final = {"type": "mcp", "server_url": "litellm_proxy", "server_label": "litellm"} AUTO: Final = {**GATEWAY_REF, "require_approval": "never"} +OUTAGE: Final = "bridge-outage" +JSON_OBJECT: Final = TypeAdapter(dict[str, JsonValue]) +JSON_VALUE: Final[TypeAdapter[JsonValue]] = TypeAdapter(JsonValue) def _json(body: Mapping[str, object]) -> Reply: @@ -44,25 +66,94 @@ def _has_tool_result(body: Mapping[str, object]) -> bool: return False -def _model_double(tool: str) -> Callable[[Request], Reply]: - arguments: Final = json.dumps(ADD) +@dataclass(frozen=True, slots=True) +class Turn: + tool: str + arguments: str + answer: str + +def _fixed_turn(tool: str) -> Callable[[Mapping[str, JsonValue]], Turn]: + return lambda _: Turn(tool, json.dumps(ADD), ANSWER) + + +def _echoing_turn(body: Mapping[str, JsonValue]) -> Turn: + names: Final = _tool_names(body) + return Turn(names[0] if names else "", json.dumps({"query": _prompt(body)}), _tool_result_text(body) or "") + + +def _prompt(body: Mapping[str, JsonValue]) -> str: + inputs: Final = body.get("input") + if isinstance(inputs, str): + return inputs + items: Final = inputs if isinstance(inputs, list) else body.get("messages") + first: Final = items[0] if isinstance(items, list) and items else None + return str(first["content"]) if isinstance(first, dict) and isinstance(first.get("content"), str) else "" + + +def _tool_result_text(body: Mapping[str, JsonValue]) -> str | None: + inputs: Final = body.get("input") + messages: Final = body.get("messages") + items: Final = inputs if isinstance(inputs, list) else messages if isinstance(messages, list) else () + for item in items: + if not isinstance(item, dict): + continue + if item.get("type") == "function_call_output": + return str(item["output"]) + if item.get("role") == "tool": + return str(item["content"]) + if (block := _tool_result_block(item)) is not None: + return block + return None + + +def _tool_result_block(item: Mapping[str, JsonValue]) -> str | None: + content: Final = item.get("content") + for block in content if isinstance(content, list) else (): + if isinstance(block, dict) and block.get("type") == "tool_result": + return str(block["content"]) + return None + + +def _responses_stream(response: Mapping[str, JsonValue], item: Mapping[str, JsonValue]) -> Reply: + events: Final = ( + {"type": "response.created", "sequence_number": 0, "response": {**response, "status": "in_progress"}}, + {"type": "response.in_progress", "sequence_number": 1, "response": {**response, "status": "in_progress"}}, + {"type": "response.output_item.added", "sequence_number": 2, "output_index": 0, "item": item}, + {"type": "response.output_item.done", "sequence_number": 3, "output_index": 0, "item": item}, + {"type": "response.completed", "sequence_number": 4, "response": response}, + ) + return Reply( + content_type="text/event-stream", + chunks=tuple(f"event: {event['type']}\ndata: {json.dumps(event)}\n\n".encode() for event in events), + ) + + +def _model_double(plan: Callable[[Mapping[str, JsonValue]], Turn]) -> Callable[[Request], Reply]: def respond(request: Request) -> Reply: if request.method == "GET" and request.target.endswith("/models"): return _json({"object": "list", "data": []}) - body: Final = json.loads(request.body) - assert isinstance(body, dict), request.body + body: Final = JSON_OBJECT.validate_json(request.body) + if OUTAGE in _prompt(body): + outage: Final = {"error": {"message": "scripted provider outage", "type": "server_error", "code": None}} + return Reply(status=500, body=json.dumps(outage).encode()) + turn: Final = plan(body) done: Final = _has_tool_result(body) + identity: Final = uuid.uuid4().hex[:12] usage: Final = {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15} if request.target.endswith("/chat/completions"): message: Final = ( - {"role": "assistant", "content": ANSWER} + {"role": "assistant", "content": turn.answer} if done else { "role": "assistant", "content": None, "tool_calls": [ - {"id": "call_1", "type": "function", "function": {"name": tool, "arguments": arguments}} + { + "id": "call_1", + "type": "function", + "function": {"name": turn.tool, "arguments": turn.arguments}, + } ], } ) @@ -74,7 +165,7 @@ def _model_double(tool: str) -> Callable[[Request], Reply]: else message ) chunk: Final = { - "id": "chatcmpl-1", + "id": f"chatcmpl-{identity}", "object": "chat.completion.chunk", "created": 1, "model": "gpt-4o-mini", @@ -89,7 +180,7 @@ def _model_double(tool: str) -> Callable[[Request], Reply]: ) return _json( { - "id": "chatcmpl-1", + "id": f"chatcmpl-{identity}", "object": "chat.completion", "created": 1, "model": "gpt-4o-mini", @@ -99,13 +190,13 @@ def _model_double(tool: str) -> Callable[[Request], Reply]: ) if request.target.endswith("/messages"): content: Final = ( - [{"type": "text", "text": ANSWER}] + [{"type": "text", "text": turn.answer}] if done - else [{"type": "tool_use", "id": "toolu_1", "name": tool, "input": ADD}] + else [{"type": "tool_use", "id": "toolu_1", "name": turn.tool, "input": json.loads(turn.arguments)}] ) return _json( { - "id": "msg_1", + "id": f"msg_{identity}", "type": "message", "role": "assistant", "model": "claude", @@ -116,39 +207,34 @@ def _model_double(tool: str) -> Callable[[Request], Reply]: } ) assert request.target.endswith("/responses"), request.target - output: Final = ( - [ - { - "type": "message", - "id": "msg_1", - "role": "assistant", - "status": "completed", - "content": [{"type": "output_text", "text": ANSWER, "annotations": []}], - } - ] - if done - else [ - { - "type": "function_call", - "id": "fc_1", - "call_id": "call_1", - "name": tool, - "arguments": arguments, - "status": "completed", - } - ] - ) - return _json( + item: Final[dict[str, JsonValue]] = ( { - "id": "resp_1", - "object": "response", - "created_at": 1, + "type": "message", + "id": f"msg_{identity}", + "role": "assistant", + "status": "completed", + "content": [{"type": "output_text", "text": turn.answer, "annotations": []}], + } + if done + else { + "type": "function_call", + "id": f"fc_{identity}", + "call_id": f"call_{identity}", + "name": turn.tool, + "arguments": turn.arguments, "status": "completed", - "model": "gpt-4o-mini", - "output": output, - "usage": {"input_tokens": 10, "output_tokens": 5, "total_tokens": 15}, } ) + response: Final[dict[str, JsonValue]] = { + "id": f"resp_{identity}", + "object": "response", + "created_at": 1, + "status": "completed", + "model": "gpt-4o-mini", + "output": [item], + "usage": {"input_tokens": 10, "output_tokens": 5, "total_tokens": 15}, + } + return _responses_stream(response, item) if body.get("stream") is True else _json(response) return respond @@ -240,7 +326,7 @@ def _rig(gateway: Gateway, surface: Surface) -> Iterator[Rig]: alias: Final = "llm" + uuid.uuid4().hex[:8] with ( mcp_peer() as peer, - wire_server(_model_double(f"{alias}-add")) as wire, + wire_server(_model_double(_fixed_turn(f"{alias}-add"))) as wire, gateway.scenario() as scenario, ): server_id: Final = register_mcp(scenario, peer, alias) @@ -403,3 +489,460 @@ def test_toolset_gateway_url_gives_a_key_of_an_ungranted_team_no_tools_and_never assert _peer_add_calls(rig.peer) == (), "denied caller reached the peer" assert all(rig.tool not in names for names in rig.upstream_tools()), rig.upstream_tools() assert response.status_code in (200, 400, 401, 403), response.text + + +Bridge = Literal["chat", "responses", "messages"] +BRIDGES: Final[tuple[Bridge, ...]] = ("chat", "responses") +Client = Literal["sync", "async"] +HOOK_ECHO: Final = "bridge-echo:" +HOOK_PROBE: Final = "bridge-probe" +HOOK_CODE: Final = ( + "def apply_guardrail(inputs, request_data, input_type):\n" + ' texts = list(inputs.get("texts") or [])\n' + ' function = inputs.get("tools", [{}])[0].get("function", {})\n' + " for text in texts:\n" + f' if "{HOOK_PROBE}" in text:\n' + f' return block("{HOOK_ECHO}" + json_stringify(' + '{"description": function.get("description"), "parameters": function.get("parameters")}))\n' + " return allow()\n" +) +LOOKUP: Final[tuple[str, dict[str, JsonValue]]] = ( + "Look up one record", + {"type": "object", "properties": {"query": {"type": "string"}}}, +) +REPORT: Final[tuple[str, dict[str, JsonValue]]] = ( + "Write one report", + {"type": "object", "properties": {"query": {"type": "string"}, "format": {}}}, +) +COLD: Final[tuple[str, dict[str, JsonValue]]] = ( + "", + {"type": "object", "properties": {}, "additionalProperties": False}, +) +RELOAD_FAST: Final = {"PROXY_CONFIG_RELOAD_INTERVAL_SECONDS": "5"} +CALL_ID: Final = "x-litellm-call-id" +T = TypeVar("T") +Definition = tuple[str, str, JsonValue] +Echo = tuple[JsonValue, JsonValue] + + +def _served(listing: tuple[str, Mapping[str, JsonValue]]) -> Echo: + return listing[0], {**listing[1], "additionalProperties": False} + + +@dataclass(frozen=True, slots=True) +class Hooked: + proxy: Gateway + sink: Wire + + +@pytest.fixture(scope="module") +def hooked(tmp_path_factory: pytest.TempPathFactory) -> Iterator[Hooked]: + directory: Final = tmp_path_factory.mktemp("bridge-hooks") + base: Final = JSON_OBJECT.validate_python(yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text())) + with wire_server(lambda _: _json({"flagged": False, "session_id": "scripted"})) as sink: + echo: Final = {"guardrail": "custom_code", "mode": "pre_mcp_call", "default_on": True, "custom_code": HOOK_CODE} + pillar: Final = { + "guardrail": "pillar", + "mode": ["pre_call", "pre_mcp_call"], + "default_on": True, + "api_key": "sk-pillar-" + uuid.uuid4().hex, + "api_base": sink.url, + "on_flagged_action": "monitor", + } + guardrails: Final = [ + {"guardrail_name": "bridge-echo-" + uuid.uuid4().hex[:8], "litellm_params": echo}, + {"guardrail_name": "bridge-sink-" + uuid.uuid4().hex[:8], "litellm_params": pillar}, + ] + path: Final = directory / "config.yaml" + path.write_text(yaml.safe_dump({**base, "guardrails": guardrails})) + with ( + gateway_from_environment() as gateway, + owned_proxy(gateway, directory, RELOAD_FAST, config=path, workers=2) as proxy, + ): + yield Hooked(proxy, sink) + + +@dataclass(frozen=True, slots=True) +class BridgeRig: + hooked: Hooked + scenario: Scenario + peer: McpPeer + wire: Wire + alias: str + server_id: str + model: str + bridge: Bridge + + def tool(self, name: str) -> str: + return f"{self.alias}-{name}" + + def names(self) -> frozenset[str]: + return frozenset(("lookup", "report")) + + def mcp(self, name: str) -> Mcp: + return {**AUTO_MCP, "allowed_tools": [self.tool(name)]} + + def url(self, path: str) -> str: + return str(self.hooked.proxy.client.base_url).rstrip("/") + path + + def post(self, key: str, prompt: str, tools: Sequence[Mcp], **extra: object) -> httpx.Response: + headers: Final = {"Authorization": f"Bearer {key}"} + if self.bridge == "chat": + body: Final = {"model": self.model, "messages": [{"role": "user", "content": prompt}], "tools": list(tools)} + return httpx.post(self.url("/v1/chat/completions"), headers=headers, json={**body, **extra}, timeout=90) + if self.bridge == "responses": + body_r: Final = {"model": self.model, "input": prompt, "tools": list(tools), **extra} + return httpx.post(self.url("/v1/responses"), headers=headers, json=body_r, timeout=90) + body_m: Final = { + "model": self.model, + "max_tokens": 64, + "messages": [{"role": "user", "content": prompt}], + "tools": list(tools), + **extra, + } + return httpx.post(self.url("/v1/messages"), headers=headers, json=body_m, timeout=90) + + def upstream_by_prompt(self) -> Mapping[str, tuple[tuple[Definition, ...], ...]]: + bodies: Final = tuple( + JSON_OBJECT.validate_json(request.body) for request in self.wire.drain() if request.method == "POST" + ) + prompts: Final = frozenset(_prompt(body) for body in bodies) + return {prompt: tuple(_definitions(body) for body in bodies if _prompt(body) == prompt) for prompt in prompts} + + def peer_calls(self) -> tuple[tuple[str, JsonValue], ...]: + return tuple(_peer_call(call) for call in tool_calls(self.peer.drain())) + + def hook_messages(self, marker: str) -> tuple[str, ...]: + posted: Final = tuple( + JSON_OBJECT.validate_json(request.body) for request in self.hooked.sink.drain() if request.method == "POST" + ) + contents: Final = tuple(content for payload in posted for content in _contents(payload)) + return tuple(content for content in contents if _synthetic(content, marker)) + + +AUTO_MCP: Final[Mcp] = { + "type": "mcp", + "server_label": "litellm", + "server_url": "litellm_proxy", + "require_approval": "never", +} + + +def _peer_call(call: Mapping[str, object]) -> tuple[str, JsonValue]: + params: Final = object_value(object_value(JSON_VALUE.validate_python(call["body"]))["params"]) + return str(params["name"]), params["arguments"] + + +def _contents(payload: Mapping[str, JsonValue]) -> Iterator[str]: + messages: Final = payload.get("messages") + for message in messages if isinstance(messages, list) else (): + if isinstance(message, dict): + yield str(message.get("content")) + + +def _function(tool: JsonValue) -> dict[str, JsonValue] | None: + if not isinstance(tool, dict): + return None + function: Final = tool.get("function", tool) + return function if isinstance(function, dict) else None + + +def _definitions(body: Mapping[str, JsonValue]) -> tuple[Definition, ...]: + tools: Final = body.get("tools") + functions: Final = tuple(_function(tool) for tool in tools) if isinstance(tools, list) else () + return tuple( + (str(function["name"]), str(function.get("description", "")), function.get("parameters")) + for function in functions + if function is not None + ) + + +def _uniform(upstream: Mapping[str, tuple[tuple[Definition, ...], ...]]) -> Mapping[str, tuple[Definition, ...] | None]: + return { + prompt: rounds[0] if all(definitions == rounds[0] for definitions in rounds) else None + for prompt, rounds in upstream.items() + } + + +def _strings(value: JsonValue) -> Iterator[str]: + if isinstance(value, str): + yield value + return + children: Final = value.values() if isinstance(value, dict) else value if isinstance(value, list) else () + for child in children: + yield from _strings(child) + + +def _echoed(value: JsonValue) -> Echo: + carrier: Final = next((text for text in _strings(value) if HOOK_ECHO in text), None) + assert carrier is not None, value + payload: Final = carrier.split(HOOK_ECHO, 1)[1] + end: Final = json.JSONDecoder().raw_decode(payload)[1] + echoed: Final = JSON_OBJECT.validate_json(payload[:end]) + return echoed.get("description"), echoed.get("parameters") + + +@contextmanager +def _bridge_rig(hooked: Hooked, bridge: Bridge) -> Generator[BridgeRig, None, None]: + alias: Final = "brg" + uuid.uuid4().hex[:8] + lookup: Final = ScriptedTool( + "lookup", + lambda params: text_result("found:" + json.dumps(JSON_OBJECT.validate_python(params)["arguments"])), + description=LOOKUP[0], + input_schema=LOOKUP[1], + ) + report: Final = ScriptedTool( + "report", lambda _: text_result("reported"), description=REPORT[0], input_schema=REPORT[1] + ) + with ( + scripted_peer(lookup, report) as peer, + wire_server(_model_double(_echoing_turn)) as wire, + hooked.proxy.scenario() as scenario, + ): + server_id: Final = register_mcp(scenario, peer, alias) + model: Final = scenario.model(model=_upstream_model(bridge), api_base=wire.url + "/v1") + rig: Final = BridgeRig(hooked, scenario, peer, wire, alias, server_id, model, bridge) + eventually( + lambda: tuple(_on_worker(hooked.proxy, lambda client: _master_listing(rig, client)) for _ in range(6)), + lambda seen: len({pid for pid, _ in seen}) >= 2 and all(names == rig.names() for _, names in seen), + seconds=45, + ) + peer.drain() + hooked.sink.drain() + yield rig + + +def _bridge_key(rig: BridgeRig) -> str: + return rig.scenario.key(object_permission={"mcp_servers": [rig.server_id]}) + + +@dataclass(frozen=True, slots=True) +class Seen: + response_id: str + call_id: str + text: str + + +def _ask_sync(rig: BridgeRig, key: str, prompt: str, tools: Sequence[Mcp], stream: bool) -> Seen: + sdk: Final = OpenAI(base_url=rig.url("/v1"), api_key=key, max_retries=0, timeout=90) + if rig.bridge == "responses": + if stream: + raw_events: Final = sdk.responses.with_raw_response.create( + model=rig.model, input=prompt, tools=tools, stream=True + ) + completed: Final = next( + event.response for event in raw_events.parse() if event.type == "response.completed" + ) + return Seen(completed.id, raw_events.headers[CALL_ID], completed.output_text) + raw_response: Final = sdk.responses.with_raw_response.create(model=rig.model, input=prompt, tools=tools) + response: Final = raw_response.parse() + return Seen(response.id, raw_response.headers[CALL_ID], response.output_text) + messages: Final[list[ChatCompletionMessageParam]] = [{"role": "user", "content": prompt}] + extra: Final = {"tools": list(tools)} + if stream: + raw_chunks: Final = sdk.chat.completions.with_raw_response.create( + model=rig.model, messages=messages, stream=True, extra_body=extra + ) + parts: Final = tuple( + (chunk.id, chunk.choices[0].delta.content or "") for chunk in raw_chunks.parse() if chunk.choices + ) + return Seen(parts[0][0], raw_chunks.headers[CALL_ID], "".join(text for _, text in parts)) + raw_completion: Final = sdk.chat.completions.with_raw_response.create( + model=rig.model, messages=messages, extra_body=extra + ) + completion: Final = raw_completion.parse() + return Seen(completion.id, raw_completion.headers[CALL_ID], completion.choices[0].message.content or "") + + +async def _ask_async(rig: BridgeRig, key: str, prompt: str, tools: Sequence[Mcp], stream: bool) -> Seen: + sdk: Final = AsyncOpenAI(base_url=rig.url("/v1"), api_key=key, max_retries=0, timeout=90) + if rig.bridge == "responses": + if stream: + raw_events: Final = await sdk.responses.with_raw_response.create( + model=rig.model, input=prompt, tools=tools, stream=True + ) + completed: Final = [ + event.response async for event in raw_events.parse() if event.type == "response.completed" + ] + return Seen(completed[0].id, raw_events.headers[CALL_ID], completed[0].output_text) + raw_response: Final = await sdk.responses.with_raw_response.create(model=rig.model, input=prompt, tools=tools) + response: Final = raw_response.parse() + return Seen(response.id, raw_response.headers[CALL_ID], response.output_text) + messages: Final[list[ChatCompletionMessageParam]] = [{"role": "user", "content": prompt}] + extra: Final = {"tools": list(tools)} + if stream: + raw_chunks: Final = await sdk.chat.completions.with_raw_response.create( + model=rig.model, messages=messages, stream=True, extra_body=extra + ) + parts: Final = [ + (chunk.id, chunk.choices[0].delta.content or "") async for chunk in raw_chunks.parse() if chunk.choices + ] + return Seen(parts[0][0], raw_chunks.headers[CALL_ID], "".join(text for _, text in parts)) + raw_completion: Final = await sdk.chat.completions.with_raw_response.create( + model=rig.model, messages=messages, extra_body=extra + ) + completion: Final = raw_completion.parse() + return Seen(completion.id, raw_completion.headers[CALL_ID], completion.choices[0].message.content or "") + + +def _ask(rig: BridgeRig, key: str, prompt: str, tools: Sequence[Mcp], stream: bool, client: Client) -> Seen: + if client == "async": + return asyncio.run(_ask_async(rig, key, prompt, tools, stream)) + return _ask_sync(rig, key, prompt, tools, stream) + + +def _synthetic(content: str, marker: str) -> bool: + return content.startswith("Tool: lookup\n") and marker in content + + +def _on_worker(gateway: Gateway, act: Callable[[httpx.Client], T]) -> tuple[int, T]: + with httpx.Client(base_url=str(gateway.client.base_url), timeout=30) as client: + summary: Final = client.get("/debug/memory/summary", headers={"Authorization": f"Bearer {gateway.key}"}) + assert summary.status_code == 200, summary.text + pid: Final = JSON_OBJECT.validate_json(summary.content)["worker_pid"] + assert isinstance(pid, int), summary.text + return pid, act(client) + + +def _both_workers(gateway: Gateway) -> frozenset[int]: + return eventually( + lambda: frozenset(_on_worker(gateway, lambda _: None)[0] for _ in range(6)), lambda pids: len(pids) >= 2 + ) + + +def _master_listing(rig: BridgeRig, client: httpx.Client) -> frozenset[str]: + headers: Final = {"x-litellm-api-key": rig.hooked.proxy.key} + response: Final = client.get("/mcp-rest/tools/list", headers=headers, params={"server_id": rig.server_id}) + tools: Final = JSON_OBJECT.validate_json(response.content).get("tools") if response.status_code == 200 else None + return frozenset(str(object_value(tool)["name"]) for tool in tools) if isinstance(tools, list) else frozenset() + + +def _direct_probe(rig: BridgeRig, key: str, name: str, client: httpx.Client) -> Echo: + body: Final = {"server_id": rig.server_id, "name": rig.tool(name), "arguments": {"query": HOOK_PROBE}} + response: Final = client.post("/mcp-rest/tools/call", headers={"x-litellm-api-key": key}, json=body) + return _echoed(JSON_VALUE.validate_json(response.content)) + + +def _spend_row(key: str, call_id: str) -> dict[str, JsonValue]: + rows: Final = eventually( + lambda: read_rows( + 'SELECT api_key, call_type, status, cache_hit FROM "LiteLLM_SpendLogs" WHERE litellm_call_id=%s', (call_id,) + ), + lambda found: len(found) >= 1, + seconds=70, + ) + assert rows[0]["api_key"] == sha256(key.encode()).hexdigest(), rows + return rows[0] + + +@pytest.mark.parametrize("client", ("sync", "async")) +@pytest.mark.parametrize("stream", (False, True), ids=("plain", "stream")) +@pytest.mark.parametrize("bridge", BRIDGES) +def test_bridge_hook_sees_the_definition_of_the_tool_filtered_for_that_request( + hooked: Hooked, bridge: Bridge, stream: bool, client: Client +) -> None: + with _bridge_rig(hooked, bridge) as rig: + key: Final = _bridge_key(rig) + marker: Final = "m" + uuid.uuid4().hex + probe: Final = f"{marker} {HOOK_PROBE}" + found: Final = _ask(rig, key, marker, [rig.mcp("lookup")], stream, client) + assert found.text == "found:" + json.dumps({"query": marker}), found + blocked: Final = _ask(rig, key, probe, [rig.mcp("lookup")], stream, client) + assert _echoed(blocked.text) == _served(LOOKUP), blocked + expected: Final = ((rig.tool("lookup"), *_served(LOOKUP)),) + upstream: Final = rig.upstream_by_prompt() + assert set(upstream) == {marker, probe} and all( + definitions == expected for definitions in upstream[marker] + upstream[probe] + ), upstream + assert rig.peer_calls() == (("lookup", {"query": marker}),) + assert rig.hook_messages(marker) == (f"Tool: lookup\nArguments: {dict(query=marker)}",) + assert _spend_row(key, found.call_id)["status"] == "success" + + +@pytest.mark.parametrize("bridge", BRIDGES) +def test_direct_call_after_bridge_only_discovery_stays_cold(hooked: Hooked, bridge: Bridge) -> None: + with _bridge_rig(hooked, bridge) as rig: + key: Final = _bridge_key(rig) + workers: Final = _both_workers(rig.hooked.proxy) + bridged: Final = _ask(rig, key, HOOK_PROBE, [rig.mcp("lookup")], False, "sync") + assert _echoed(bridged.text) == _served(LOOKUP), bridged + direct: Final = eventually( + lambda: tuple( + _on_worker(rig.hooked.proxy, lambda client: _direct_probe(rig, key, "lookup", client)) for _ in range(6) + ), + lambda seen: frozenset(pid for pid, _ in seen) == workers, + ) + assert all(echo == COLD for _, echo in direct) and frozenset(pid for pid, _ in direct) == workers, ( + direct, + workers, + ) + assert rig.peer_calls() == () + + +@pytest.mark.parametrize("bridge", BRIDGES) +def test_concurrent_requests_of_one_key_with_different_allowed_tools_each_see_their_own_definition( + hooked: Hooked, bridge: Bridge +) -> None: + with _bridge_rig(hooked, bridge) as rig: + key: Final = _bridge_key(rig) + prompts: Final = {name: f"{name} {uuid.uuid4().hex} {HOOK_PROBE}" for name in ("lookup", "report")} + + def ask(name: str) -> Seen: + return _ask(rig, key, prompts[name], [rig.mcp(name)], False, "sync") + + with ThreadPoolExecutor(2) as pool: + lookup, report = pool.map(ask, ("lookup", "report")) + assert (_echoed(lookup.text), _echoed(report.text)) == (_served(LOOKUP), _served(REPORT)), (lookup, report) + upstream: Final = rig.upstream_by_prompt() + assert _uniform(upstream) == { + prompts["lookup"]: ((rig.tool("lookup"), *_served(LOOKUP)),), + prompts["report"]: ((rig.tool("report"), *_served(REPORT)),), + }, upstream + assert rig.peer_calls() == () + + +@pytest.mark.parametrize("bridge", BRIDGES) +def test_provider_outage_reaches_the_caller_and_never_the_peer_or_the_hooks(hooked: Hooked, bridge: Bridge) -> None: + with _bridge_rig(hooked, bridge) as rig: + key: Final = _bridge_key(rig) + prompt: Final = f"{OUTAGE} {uuid.uuid4().hex}" + response: Final = rig.post(key, prompt, [rig.mcp("lookup")]) + assert response.status_code == 500, response.text + upstream: Final = rig.upstream_by_prompt() + assert set(upstream) == {prompt} and all( + definitions == ((rig.tool("lookup"), *_served(LOOKUP)),) for definitions in upstream[prompt] + ), upstream + assert rig.peer_calls() == () + assert rig.hook_messages(prompt) == () + + +@pytest.mark.parametrize("bridge", BRIDGES) +def test_identical_nonstream_repeat_is_a_cache_hit_without_new_model_peer_or_hook_traffic( + hooked: Hooked, bridge: Bridge +) -> None: + with _bridge_rig(hooked, bridge) as rig: + key: Final = _bridge_key(rig) + marker: Final = "m" + uuid.uuid4().hex + first: Final = _ask(rig, key, marker, [rig.mcp("lookup")], False, "sync") + assert first.text == "found:" + json.dumps({"query": marker}), first + assert set(rig.upstream_by_prompt()) == {marker} and rig.peer_calls() == (("lookup", {"query": marker}),) + assert rig.hook_messages(marker) == (f"Tool: lookup\nArguments: {dict(query=marker)}",) + assert _spend_row(key, first.call_id)["cache_hit"] != "True" + repeat: Final = _ask(rig, key, marker, [rig.mcp("lookup")], False, "sync") + assert repeat.text == first.text, (first, repeat) + assert (rig.upstream_by_prompt(), rig.peer_calls(), rig.hook_messages(marker)) == ({}, (), ()), repeat + assert _spend_row(key, repeat.call_id)["cache_hit"] == "True" + + +def test_messages_bridge_hook_keeps_the_base_shape_without_request_local_metadata(hooked: Hooked) -> None: + with _bridge_rig(hooked, "messages") as rig: + key: Final = _bridge_key(rig) + marker: Final = "m" + uuid.uuid4().hex + probe: Final = f"{marker} {HOOK_PROBE}" + found: Final = rig.post(key, marker, [rig.mcp("lookup")]) + assert found.status_code == 200, found.text + blocked: Final = rig.post(key, probe, [rig.mcp("lookup")]) + assert blocked.status_code == 200, blocked.text + assert _echoed(JSON_VALUE.validate_json(blocked.content)) == COLD, blocked.text + assert rig.peer_calls() == (("lookup", {"query": marker}),) + assert rig.hook_messages(marker) == (f"Tool: lookup\nArguments: {dict(query=marker)}",) diff --git a/tests/integration/mcp/test_mcp_oauth_flows.py b/tests/integration/mcp/test_mcp_oauth_flows.py index 60563e7aacd..e95cdb902e8 100644 --- a/tests/integration/mcp/test_mcp_oauth_flows.py +++ b/tests/integration/mcp/test_mcp_oauth_flows.py @@ -1,16 +1,20 @@ import base64 import hashlib +import re import secrets +import textwrap import time import uuid +from collections.abc import Iterator from dataclasses import dataclass +from pathlib import Path from typing import Final from urllib.parse import parse_qs, urlsplit import httpx import jwt import pytest -from integration._support.client import Gateway, eventually +from integration._support.client import Gateway, eventually, gateway_from_environment from integration._support.database import read_rows from integration._support.mcp import ( ENTRY_POINTS, @@ -27,6 +31,7 @@ from integration._support.mcp import ( ) from integration._support.mcp_grants import create_toolset from integration._support.oauth_server import AuthorizationServer, oauth_server +from integration._support.process import owned_proxy ADD: Final = {"a": 2, "b": 3} CLIENT_REDIRECT: Final = "http://127.0.0.1:9/cb" @@ -503,3 +508,70 @@ def test_resource_scoped_session_bearer_opens_a_team_toolset_inside_its_server_a refused: Final = _toolset_rpc(gateway, bearer, outside_name, "tools/list", {}) assert refused.status == 403, refused.raw assert tool_calls(peer.drain()) == () + + +_PROBE: Final = "catalog-probe" +_ECHO: Final = "catalog-echo" +_UNLISTED: Final = "" +_GUARDRAIL_CODE: Final = ( + "def apply_guardrail(inputs, request_data, input_type):\n" + f' if "{_PROBE}" not in list(inputs.get("texts") or []):\n' + " return allow()\n" + ' function = inputs.get("tools", [{}])[0].get("function", {})\n' + f' return block("{_ECHO}[" + function.get("description") + "]")\n' +) + + +_ECHO_GUARDRAIL_YAML: Final = ( + "guardrails:\n" + " - guardrail_name: catalog-echo\n" + " litellm_params:\n" + " guardrail: custom_code\n" + " mode: pre_mcp_call\n" + " default_on: true\n" + " custom_code: |\n" + textwrap.indent(_GUARDRAIL_CODE, 8 * " ") +) + + +@pytest.fixture(scope="module") +def echo_rig(tmp_path_factory: pytest.TempPathFactory) -> Iterator[Gateway]: + directory: Final = tmp_path_factory.mktemp("catalog-echo") + path: Final = directory / "catalog_echo.yaml" + path.write_text((Path(__file__).resolve().parents[1] / "proxy_config.yaml").read_text() + _ECHO_GUARDRAIL_YAML) + with gateway_from_environment() as gateway, owned_proxy(gateway, directory, {}, config=path, workers=2) as rig: + yield rig + + +def _echoed_description(outcome: Outcome) -> str: + found: Final = re.search(rf"{_ECHO}\[(.*?)\]", outcome.raw) + assert found is not None, outcome.raw + return found.group(1) + + +def test_token_exchange_callers_with_different_subject_tokens_own_separate_listings(echo_rig: Gateway) -> None: + with mcp_peer() as peer, oauth_server() as auth, echo_rig.scenario() as scenario: + alias: Final = "te" + uuid.uuid4().hex[:8] + identity: Final = register_mcp( + scenario, + peer, + alias, + auth_type="oauth2_token_exchange", + token_exchange_endpoint=auth.issuer + "/token", + credentials={"client_id": "te-client", "client_secret": "te-secret"}, + ) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + first_subject: Final = "subject-" + uuid.uuid4().hex + first: Final = McpCaller(echo_rig, key, "mcp", alias, {"Authorization": f"Bearer {first_subject}"}) + second: Final = McpCaller(echo_rig, key, "mcp", alias, {"Authorization": "Bearer subject-" + uuid.uuid4().hex}) + auth.drain() + assert first.list_tools().ok + assert [request["subject_token"] for request in auth.token_requests()] == [first_subject] + probe: Final = {"probe": _PROBE} + own: Final = _echoed_description(first.call(f"{alias}-add", probe)) + other: Final = _echoed_description(second.call(f"{alias}-add", probe)) + assert (own, other) == ("Add two integers", _UNLISTED), ( + "the caller bearer is part of the identity on a token-exchange server: one subject, one slot" + ) + assert second.list_tools().ok + assert _echoed_description(second.call(f"{alias}-add", probe)) == "Add two integers" + assert tool_calls(peer.drain()) == (), "a blocked probe reached the peer" diff --git a/tests/integration/mcp/test_mcp_resilience.py b/tests/integration/mcp/test_mcp_resilience.py index 8efb54a18fd..d821181962f 100644 --- a/tests/integration/mcp/test_mcp_resilience.py +++ b/tests/integration/mcp/test_mcp_resilience.py @@ -1,13 +1,23 @@ +import itertools import uuid +from collections.abc import Mapping +from concurrent.futures import ThreadPoolExecutor +from dataclasses import dataclass +from hashlib import sha256 +from pathlib import Path from typing import Final import pytest +import yaml from integration._support.client import Gateway, eventually +from integration._support.database import read_rows from integration._support.mcp import ( ENTRY_POINTS, EntryPoint, + JsonRpc, McpCaller, Outcome, + ScriptedTool, disconnecting_tool, echo_tool, listed_tools, @@ -15,8 +25,67 @@ from integration._support.mcp import ( register_mcp, scripted_peer, slow_tool, + text_result, tool_calls, ) +from integration._support.process import owned_proxy_process +from integration._support.wire import Reply +from pydantic import BaseModel, TypeAdapter + +_ECHO: Final = "catalog-echo:" +_PROBE: Final = "catalog-probe" +_DESCRIPTION: Final = "Look up one record" +_GUARDRAIL_CODE: Final = ( + "def apply_guardrail(inputs, request_data, input_type):\n" + ' texts = list(inputs.get("texts") or [])\n' + ' function = inputs.get("tools", [{}])[0].get("function", {})\n' + f' if "{_PROBE}" in texts:\n' + f' return block("{_ECHO}" + json_stringify({{"description": function.get("description")}}))\n' + " return allow()\n" +) +_BURST: Final = 20 +_OUTAGE: Final = 6 +_SPEND_NONCES: Final = ( + "SELECT status, metadata->'mcp_tool_call_metadata'->'arguments'->>'nonce' AS nonce" + ' FROM "LiteLLM_SpendLogs" WHERE api_key = %s AND call_type = %s' +) +_OBJECTS: Final = TypeAdapter(Mapping[str, object]) +_STRINGS: Final = TypeAdapter(Mapping[str, str]) +_ECHOED: Final = TypeAdapter(Mapping[str, str | None]) + + +class _Content(BaseModel): + text: str + + +class _Result(BaseModel): + content: tuple[_Content, ...] + + +class _RpcReply(BaseModel): + id: int + result: _Result + + +class _SessionsReport(BaseModel): + worker_pid: int + + +@pytest.fixture(scope="module") +def echo_config(tmp_path_factory: pytest.TempPathFactory) -> Path: + base: Final = _OBJECTS.validate_python(yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text())) + guardrail: Final = { + "guardrail_name": "catalog-echo-" + uuid.uuid4().hex[:8], + "litellm_params": { + "guardrail": "custom_code", + "mode": "pre_mcp_call", + "default_on": True, + "custom_code": _GUARDRAIL_CODE, + }, + } + path: Final = tmp_path_factory.mktemp("failure-recovery") / "config.yaml" + path.write_text(yaml.safe_dump({**base, "guardrails": [guardrail]})) + return path def _call(caller: McpCaller, name: str, arguments: dict[str, object], entry: EntryPoint, identity: str) -> Outcome: @@ -134,3 +203,151 @@ def test_peer_restart_on_the_same_url_is_picked_up_without_gateway_restart(gatew ) assert back.text == '{"a": 1, "b": 1}', back.raw assert len(tool_calls(replacement.drain())) >= 1 + + +def _rpc_reply(raw: str) -> _RpcReply: + data: Final = tuple(line[5:].strip() for line in raw.splitlines() if line.startswith("data:")) + return _RpcReply.model_validate_json(data[-1] if data else raw) + + +def _call_params(call: Mapping[str, object]) -> Mapping[str, object]: + return _OBJECTS.validate_python(_OBJECTS.validate_python(call["body"])["params"]) + + +def _call_nonce(call: Mapping[str, object]) -> str: + return _STRINGS.validate_python(_call_params(call)["arguments"])["nonce"] + + +def _listed(caller: McpCaller, name: str) -> None: + listing: Final = eventually(caller.list_tools, lambda outcome: name in outcome.tools, seconds=45) + assert listing.error is None, (caller.gateway.client.base_url, listing.raw) + + +@dataclass(frozen=True, slots=True) +class _Worker: + caller: McpCaller + pid: int + + +def _worker(proxy: Gateway, key: str, alias: str) -> _Worker: + sessions: Final = proxy.client.get("/v1/mcp/sessions", headers={"x-litellm-api-key": proxy.key}) + assert sessions.status_code == 200, sessions.text + return _Worker(McpCaller(proxy, key, "mcp", alias), _SessionsReport.model_validate_json(sessions.text).worker_pid) + + +def _served(worker: _Worker, name: str, nonce: str) -> None: + served: Final = worker.caller.call(name, {"nonce": nonce}) + assert served.text == "found", (worker.pid, served.raw) + + +def _probed_description(worker: _Worker, name: str) -> str | None: + """The description the pre_mcp_call guardrail on that worker was handed, recovered from its block reason.""" + blocked: Final = worker.caller.call(name, {"nonce": _PROBE}) + assert blocked.error is not None, (worker.pid, blocked.raw) + carrier: Final = next((item.text for item in _rpc_reply(blocked.raw).result.content if _ECHO in item.text), None) + assert carrier is not None, (worker.pid, blocked.raw) + return _ECHOED.validate_json(carrier.split(_ECHO, 1)[1])["description"] + + +def _catalog_is_cold(worker: _Worker, name: str) -> bool: + return not _probed_description(worker, name) + + +@pytest.mark.timeout(600) +def test_worker_restart_cools_its_listed_catalog_while_the_sibling_worker_keeps_serving( + gateway: Gateway, echo_config: Path, tmp_path: Path +) -> None: + tool: Final = ScriptedTool("lookup", lambda _: text_result("found"), description=_DESCRIPTION) + with scripted_peer(tool) as peer, gateway.scenario() as scenario: + alias: Final = "cold" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, peer, alias) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + name: Final = f"{alias}-lookup" + with owned_proxy_process(gateway, tmp_path / "sibling", {}, config=echo_config) as sibling_proxy: + sibling: Final = _worker(sibling_proxy.gateway, key, alias) + with owned_proxy_process(gateway, tmp_path / "first", {}, config=echo_config) as first_proxy: + first: Final = _worker(first_proxy.gateway, key, alias) + assert first.pid != sibling.pid + _served(first, name, "first-unlisted") + _served(sibling, name, "sibling-unlisted") + assert _catalog_is_cold(first, name) and _catalog_is_cold(sibling, name) + _listed(first.caller, name) + assert _probed_description(first, name) == _DESCRIPTION + assert _catalog_is_cold(sibling, name), "a listing on one worker warmed its sibling" + _listed(sibling.caller, name) + assert _probed_description(sibling, name) == _DESCRIPTION + _served(sibling, name, "sibling-alone") + with owned_proxy_process(gateway, tmp_path / "restarted", {}, config=echo_config) as restarted_proxy: + restarted: Final = _worker(restarted_proxy.gateway, key, alias) + assert restarted.pid not in (first.pid, sibling.pid) + assert _catalog_is_cold(restarted, name), "a restarted worker kept the old process's catalog" + assert _probed_description(sibling, name) == _DESCRIPTION + _served(restarted, name, "restarted-unlisted") + _listed(restarted.caller, name) + assert _probed_description(restarted, name) == _DESCRIPTION + calls: Final = tool_calls(peer.drain()) + assert [_call_nonce(call) for call in calls] == [ + "first-unlisted", + "sibling-unlisted", + "sibling-alone", + "restarted-unlisted", + ], calls + assert all(set(_call_params(call)) - {"_meta"} == {"name", "arguments"} for call in calls), calls + + +def _outage_echo(name: str, failures: int) -> ScriptedTool: + attempts: Final = itertools.count(1) + + def respond(params: JsonRpc) -> Reply | JsonRpc: + if next(attempts) <= failures: + return Reply(status=503, body=b'{"error": "scripted outage"}') + return text_result(_STRINGS.validate_python(params["arguments"])["nonce"]) + + return ScriptedTool(name, respond) + + +def _echo_call(caller: McpCaller, name: str, nonce: str) -> Outcome: + return caller.call(name, {"nonce": nonce}) + + +def _logged_nonces(key: str, count: int) -> tuple[tuple[str, str], ...]: + rows: Final = eventually( + lambda: read_rows(_SPEND_NONCES, (sha256(key.encode()).hexdigest(), "call_mcp_tool")), + lambda found: len(found) >= count, + seconds=70, + ) + return tuple(sorted((str(row["status"]), str(row["nonce"])) for row in rows)) + + +def test_peer_outage_during_a_bounded_burst_fails_exactly_the_outage_calls_and_lands_each_call_once( + gateway: Gateway, peer: Gateway +) -> None: + with scripted_peer(_outage_echo("echo", _OUTAGE)) as upstream, gateway.scenario() as scenario: + alias: Final = "burst" + uuid.uuid4().hex[:8] + identity: Final = register_mcp(scenario, upstream, alias) + key: Final = scenario.key(object_permission={"mcp_servers": [identity]}) + name: Final = f"{alias}-echo" + callers: Final = (McpCaller(gateway, key, "mcp", alias), McpCaller(peer, key, "mcp", alias)) + for caller in callers: + _listed(caller, name) + upstream.drain() + nonces: Final = tuple(uuid.uuid4().hex for _ in range(_BURST)) + with ThreadPoolExecutor(max_workers=_BURST) as pool: + outcomes: Final = tuple(pool.map(_echo_call, itertools.cycle(callers), itertools.repeat(name), nonces)) + raws: Final = [outcome.raw for outcome in outcomes] + failed: Final = tuple(nonce for nonce, outcome in zip(nonces, outcomes) if outcome.error is not None) + assert len(failed) == _OUTAGE, raws + assert all(outcome.error is not None or outcome.text == nonce for nonce, outcome in zip(nonces, outcomes)), raws + assert all(_rpc_reply(outcome.raw).id == 1 for outcome in outcomes), raws + burst_calls: Final = tool_calls(upstream.drain()) + assert sorted(_call_nonce(call) for call in burst_calls) == sorted(nonces), burst_calls + assert all(_call_params(call)["arguments"] == {"nonce": _call_nonce(call)} for call in burst_calls), burst_calls + assert all(set(_call_params(call)) - {"_meta"} == {"name", "arguments"} for call in burst_calls), burst_calls + recovered: Final = tuple( + _echo_call(caller, name, nonce) for caller, nonce in zip(itertools.cycle(callers), failed) + ) + assert [outcome.text for outcome in recovered] == list(failed), [outcome.raw for outcome in recovered] + assert sorted(_call_nonce(call) for call in tool_calls(upstream.drain())) == sorted(failed) + assert _logged_nonces(key, _BURST + len(failed)) == tuple( + sorted([("success", nonce) for nonce in nonces] + [("failure", nonce) for nonce in failed]) + ) diff --git a/tests/integration/mcp/test_mcp_toolsets.py b/tests/integration/mcp/test_mcp_toolsets.py index 3dd309db665..b97fa6e72cb 100644 --- a/tests/integration/mcp/test_mcp_toolsets.py +++ b/tests/integration/mcp/test_mcp_toolsets.py @@ -1,5 +1,8 @@ +import re import secrets +import textwrap import uuid +from collections.abc import Iterator from datetime import datetime, timedelta, timezone from pathlib import Path from typing import Final @@ -7,14 +10,17 @@ from typing import Final import httpx import pytest import yaml -from integration._support.client import Gateway, Scenario, object_value +from integration._support.client import Gateway, Scenario, gateway_from_environment, object_value from integration._support.mcp import ( INITIALIZE, Outcome, + ScriptedTool, _outcome_from_rest, _outcome_from_rpc, mcp_peer, register_mcp, + scripted_peer, + text_result, tool_calls, ) from integration._support.mcp_grants import create_toolset @@ -507,3 +513,63 @@ def test_a_member_of_two_teams_sees_the_union_and_each_route_stays_narrowed_to_i crossed: Final = _route_call(gateway, headers, first_name, f"{alias}-multiply") assert not crossed.ok, crossed.raw assert tool_calls(peer.drain()) == () + + +_PROBE: Final = "catalog-probe" +_ECHO: Final = "catalog-echo" +_UNLISTED: Final = "" +_GUARDRAIL_CODE: Final = ( + "def apply_guardrail(inputs, request_data, input_type):\n" + f' if "{_PROBE}" not in list(inputs.get("texts") or []):\n' + " return allow()\n" + ' function = inputs.get("tools", [{}])[0].get("function", {})\n' + f' return block("{_ECHO}[" + function.get("description") + "]")\n' +) + + +_ECHO_GUARDRAIL_YAML: Final = ( + "guardrails:\n" + " - guardrail_name: catalog-echo\n" + " litellm_params:\n" + " guardrail: custom_code\n" + " mode: pre_mcp_call\n" + " default_on: true\n" + " custom_code: |\n" + textwrap.indent(_GUARDRAIL_CODE, 8 * " ") +) + + +@pytest.fixture(scope="module") +def echo_rig(tmp_path_factory: pytest.TempPathFactory) -> Iterator[Gateway]: + directory: Final = tmp_path_factory.mktemp("catalog-echo") + path: Final = directory / "catalog_echo.yaml" + path.write_text((Path(__file__).resolve().parents[1] / "proxy_config.yaml").read_text() + _ECHO_GUARDRAIL_YAML) + with gateway_from_environment() as gateway, owned_proxy(gateway, directory, {}, config=path, workers=2) as rig: + yield rig + + +def _echoed_description(outcome: Outcome) -> str: + found: Final = re.search(rf"{_ECHO}\[(.*?)\]", outcome.raw) + assert found is not None, outcome.raw + return found.group(1) + + +def test_a_team_keys_toolset_route_listing_feeds_its_own_calls_but_not_a_team_mates(echo_rig: Gateway) -> None: + described: Final = "Adds for the team " + uuid.uuid4().hex[:8] + tool: Final = ScriptedTool("add", lambda _: text_result("9"), description=described) + with scripted_peer(tool) as peer, echo_rig.scenario() as scenario: + alias: Final = "lit6029echo" + uuid.uuid4().hex[:6] + server_id: Final = register_mcp(scenario, peer, alias) + granted_id, granted_name = _toolset(scenario, server_id, "add") + team_id: Final = scenario.team(object_permission={"mcp_toolsets": [granted_id]}) + key: Final = scenario.key(team_id=team_id) + team_mate: Final = scenario.key(team_id=team_id) + _assert_team_grants_only(echo_rig, team_id, key, granted_id) + listed: Final = _toolset_rpc(echo_rig, _bearer(key), granted_name, "tools/list", {}) + assert listed.ok and listed.tools == (f"{alias}-add",), listed.raw + probe: Final[dict[str, object]] = {"name": f"{alias}-add", "arguments": {"probe": _PROBE}} + own: Final = _echoed_description(_toolset_rpc(echo_rig, _bearer(key), granted_name, "tools/call", probe)) + mate: Final = _echoed_description(_toolset_rpc(echo_rig, _bearer(team_mate), granted_name, "tools/call", probe)) + assert (own, mate) == (described, _UNLISTED), ( + "the slot is keyed by the hashed key, so a team-mate that never listed is handed nothing" + ) + assert tool_calls(peer.drain()) == (), "a blocked probe reached the peer" diff --git a/tests/integration/providers/test_bedrock_runtime_chat_completions_chaos.py b/tests/integration/providers/test_bedrock_runtime_chat_completions_chaos.py index 5f59fa883ce..820d033135f 100644 --- a/tests/integration/providers/test_bedrock_runtime_chat_completions_chaos.py +++ b/tests/integration/providers/test_bedrock_runtime_chat_completions_chaos.py @@ -1,3 +1,5 @@ +from __future__ import annotations + import asyncio import base64 import binascii diff --git a/tests/store_model_in_db_tests/test_mcp_servers.py b/tests/store_model_in_db_tests/test_mcp_servers.py index 94e14798c54..5c1a996b276 100644 --- a/tests/store_model_in_db_tests/test_mcp_servers.py +++ b/tests/store_model_in_db_tests/test_mcp_servers.py @@ -1,6 +1,6 @@ import sys from datetime import datetime -from typing import List, Optional +from typing import Final, List, Optional import pytest from litellm._uuid import uuid import os @@ -391,6 +391,7 @@ async def test_create_mcp_server_invalid_alias(): @_SKIP_NO_MCP @pytest.mark.asyncio async def test_edit_mcp_server_redacts_credentials(): + mock_get_server: Final = mock.AsyncMock() with ( mock.patch( "litellm.proxy.management_endpoints.mcp_management_endpoints.MCP_AVAILABLE", @@ -399,6 +400,10 @@ async def test_edit_mcp_server_redacts_credentials(): mock.patch( "litellm.proxy.management_endpoints.mcp_management_endpoints.get_prisma_client_or_throw" ) as mock_get_prisma, + mock.patch( + "litellm.proxy.management_endpoints.mcp_management_endpoints.get_mcp_server", + new=mock_get_server, + ), mock.patch( "litellm.proxy.management_endpoints.mcp_management_endpoints.update_mcp_server", new_callable=mock.AsyncMock, @@ -422,6 +427,18 @@ async def test_edit_mcp_server_redacts_credentials(): mock_manager.reload_servers_from_database = mock.AsyncMock() server_id = str(uuid.uuid4()) + stored_server: Final = LiteLLM_MCPServerTable( + server_id=server_id, + alias="Updated Server", + url="https://updated.example.com/mcp", + transport=MCPTransport.http, + created_at=datetime.now(), + updated_at=datetime.now(), + credentials={"auth_value": "secret"}, + teams=[], + ) + mock_get_server.return_value = stored_server + updated_server = LiteLLM_MCPServerTable( server_id=server_id, alias="Updated Server", @@ -458,6 +475,7 @@ async def test_edit_mcp_server_redacts_credentials(): mock_update.assert_awaited_once() mock_manager.update_server.assert_called_once_with(updated_server) mock_manager.reload_servers_from_database.assert_awaited_once() + mock_get_server.assert_awaited_once_with(mock_prisma, server_id) def test_validate_mcp_server_name_direct(): diff --git a/tests/test_litellm_rust/test_traces.py b/tests/test_litellm_rust/test_traces.py index da1cd0af77a..c1847a52760 100644 --- a/tests/test_litellm_rust/test_traces.py +++ b/tests/test_litellm_rust/test_traces.py @@ -490,10 +490,10 @@ def seeded_trace_api(clickhouse_url: str) -> Iterator[SeededTraceAPI]: rebase_spend, ) - spends: Final = dict(spend_fixtures())["deeplite_swarm"] + spends: Final = dict(spend_fixtures())["openai_agents_swarm"] pattern: Final = re.compile("|".join(re.escape(row["response_id"]) for row in spends)) replays: Final = fixture_replays(TRACE_FIXTURES, time.time_ns() // 1_000_000, "query-api", pattern) - swarm: Final = next(replay for replay in replays if replay.name == "deeplite_swarm") + swarm: Final = next(replay for replay in replays if replay.name == "openai_agents_swarm") rebased: Final = rebase_spend(spends, swarm.offset_ms, swarm.namespace, pattern) stamped: Final[tuple[SpendLogRecord, ...]] = tuple( {**row, "team_id": "team-a", "api_key": "fixture-key", "user": "fixture-user"} for row in rebased @@ -533,12 +533,11 @@ def test_fixture_backed_help_examples_execute_through_query_api(seeded_trace_api assert {table.name for table in api.help.tables} == {"otel_traces", "spend_logs", "agent_traces_by_key"} assert api.help.metadata.error is None assert api.help.metadata.sampled_rows == len(api.spends) - assert any(field.path == ("synthetic_spend",) for field in api.help.metadata.fields) + assert any(field.path == ("fixture_capture", "name") for field in api.help.metadata.fields) for example in api.help.examples: api.query_example(example.name) records: Final = api.query_example("Recent spend records") assert {str(row["request_id"]) for row in records} == {row["request_id"] for row in api.spends} - assert all(bool(row["synthetic_spend"]) for row in records) total: Final = sum(row["spend"] or 0 for row in api.spends) recorded: Final = api.query_example("Recorded spend by trace") assert len(recorded) == 1 @@ -616,7 +615,7 @@ def captured_trace_api() -> Iterator[SeededTraceAPI]: yield from _fixture_trace_api(url, replays, stamped) -@pytest.mark.parametrize("name", tuple(name for name, _ in spend_fixtures() if name != "deeplite_swarm")) +@pytest.mark.parametrize("name", tuple(name for name, _ in spend_fixtures())) def test_captured_sdk_cost_survives_seeding_and_is_queryable(name: str, captured_trace_api: SeededTraceAPI) -> None: api: Final = captured_trace_api rows: Final = tuple(row for row in api.spends if fixture_capture("", row).name == name) diff --git a/tests/unit/gateway/test_launch.py b/tests/unit/gateway/test_launch.py index a783ce6ac7e..f76aea030fe 100644 --- a/tests/unit/gateway/test_launch.py +++ b/tests/unit/gateway/test_launch.py @@ -1,3 +1,4 @@ +import importlib import os import socket import sys @@ -12,10 +13,10 @@ import pytest from uvicorn.importer import import_from_string from uvicorn.main import main as uvicorn_main -import gateway.main from gateway.launch import GATEWAY_APP, main, pool_database_url, uvicorn_argv from litellm.proxy.db.db_url_settings import DatabaseURLSettings from litellm.proxy.db.pgbouncer import PGBOUNCER_POOLED_ENV_VAR, PgBouncerError, PgBouncerSettings +from litellm.proxy.proxy_server import app as proxy_app DB_ENV: Final = { "DATABASE_HOST": "db.internal", @@ -107,8 +108,22 @@ class TestUvicornArgv: argv: Final = uvicorn_argv(("--timeout-keep-alive", "30"), {"KEEPALIVE_TIMEOUT": "75"}) assert _uvicorn_params(argv)["timeout_keep_alive"] == 30 - def test_the_app_uvicorn_is_told_to_serve_is_the_trimmed_gateway(self): - assert import_from_string(cast(str, _uvicorn_params(uvicorn_argv((), {}))["app"])) is gateway.main.app + def test_the_app_uvicorn_is_told_to_serve_is_the_trimmed_gateway(self, monkeypatch: pytest.MonkeyPatch) -> None: + monkeypatch.setattr(proxy_app.router, "lifespan_context", proxy_app.router.lifespan_context) + for key in ( + "DATABASE_URL", + "DIRECT_URL", + "DATABASE_URL_READ_REPLICA", + "DATABASE_HOST", + "DATABASE_HOST_READ_REPLICA", + "DATABASE_PASSWORD", + "IAM_TOKEN_DB_AUTH", + "AZURE_POSTGRESQL_AUTH", + ): + monkeypatch.delenv(key, raising=False) + + served: Final = import_from_string(cast(str, _uvicorn_params(uvicorn_argv((), {}))["app"])) + assert served is importlib.import_module("gateway.main").app class TestPoolDatabaseUrl: diff --git a/tests/unit/litellm_proxy_extras/test_litellm_proxy_extras_utils.py b/tests/unit/litellm_proxy_extras/test_litellm_proxy_extras_utils.py index ea4a25283a1..70c6ec44790 100644 --- a/tests/unit/litellm_proxy_extras/test_litellm_proxy_extras_utils.py +++ b/tests/unit/litellm_proxy_extras/test_litellm_proxy_extras_utils.py @@ -1,11 +1,13 @@ import glob +import logging import os import re +import subprocess import sys import threading from dataclasses import dataclass from pathlib import Path -from typing import Final +from typing import Final, NoReturn, Optional import pytest @@ -19,6 +21,8 @@ sys.path.insert( from litellm_proxy_extras.utils import ( PARTITIONED_SPEND_LOGS_PUSH_ERROR, ProxyExtrasDBManager, + _redact_command_error, + _redact_credentials, filter_partitioned_spend_logs_diff, ) @@ -1412,3 +1416,411 @@ class TestMigrationJobOwnedDrift: assert 'PRIMARY KEY ("request_id")' not in filtered assert "LiteLLM_SpendLogs_legacy" not in filtered assert 'ALTER TABLE "LiteLLM_BudgetTable" ADD COLUMN "updated_by" TEXT;' in filtered + + +_P3018_UNCLASSIFIED_STDERR: Final = ( + "Error: P3018\n\n" + "A migration failed to apply. New migrations cannot be applied before the error is " + "recovered from.\n\n" + "Migration name: 20260921190000_agent_identity\n\n" + "Database error code: 23505\n\n" + "Database error:\n" + 'ERROR: could not create unique index "agent_identity_key"\n' + "DETAIL: Key (agent_id)=(agent-1) is duplicated.\n" +) + + +_FAKE_PRISMA_PID: Final = 424242 + + +class TestV1MigrationFailuresLogAtError: + @staticmethod + def _run_v1_migrations( + monkeypatch: pytest.MonkeyPatch, + tmp_path: Path, + *, + deploy_stderr: Optional[str] = None, + deploy_timeout: bool = False, + diff_stderr: Optional[str] = None, + database_url: Optional[str] = None, + ) -> tuple[bool, list[list[str]], list[int]]: + import litellm_proxy_extras.utils as utils_module + + calls: Final[list[list[str]]] = [] + killed_pids: Final[list[int]] = [] + + class _FakePrismaPopen: + def __init__( + self, + argv: tuple[str, ...], + *, + env: Optional[dict[str, str]] = None, + stdout: object = None, + stderr: object = None, + text: object = None, + start_new_session: object = None, + ) -> None: + self.args: Final = argv + self.argv: Final = argv + self.pid: Final = _FAKE_PRISMA_PID + self.returncode: Optional[int] = None + calls.append(list(argv)) + + def __enter__(self) -> "_FakePrismaPopen": + return self + + def __exit__(self, *args: object) -> None: + return None + + def _subcommand(self) -> tuple[str, str]: + known: Final = ( + ("migrate", "deploy"), + ("migrate", "diff"), + ("migrate", "resolve"), + ("db", "execute"), + ) + for index in range(len(self.argv) - 1): + pair: Final = tuple(self.argv[index : index + 2]) + if pair in known: + return pair + return ("", "") + + def communicate(self, timeout: Optional[float] = None) -> tuple[str, str]: + subcommand: Final = self._subcommand() + if subcommand == ("migrate", "deploy"): + if deploy_timeout: + raise subprocess.TimeoutExpired(self.argv, timeout) + if deploy_stderr is not None: + self.returncode = 1 + return "", deploy_stderr + self.returncode = 0 + return "No pending migrations to apply", "" + if subcommand == ("migrate", "diff") and diff_stderr is not None: + self.returncode = 1 + return "", diff_stderr + self.returncode = 0 + return "", "" + + migration_dir: Final = tmp_path / "migration_dir" + migration_dir.mkdir() + if database_url is None: + monkeypatch.delenv("DATABASE_URL", raising=False) + else: + monkeypatch.setenv("DATABASE_URL", database_url) + monkeypatch.setenv("LITELLM_MIGRATION_DIR", str(migration_dir)) + monkeypatch.setattr( + utils_module.prisma_toolchain.subprocess, "Popen", _FakePrismaPopen + ) + monkeypatch.setattr( + utils_module.prisma_toolchain.os, "killpg", lambda pid, sig: killed_pids.append(pid) + ) + monkeypatch.setattr(utils_module.time, "sleep", lambda seconds: None) + + succeeded: Final = ProxyExtrasDBManager._run_migrations(use_migrate=True, use_v2_resolver=False) + return succeeded, calls, killed_pids + + @staticmethod + def _deploy_call_count(calls: list[list[str]]) -> int: + return sum(1 for call in calls if tuple(call[-2:]) == ("migrate", "deploy")) + + @staticmethod + def _error_messages(caplog: pytest.LogCaptureFixture) -> list[str]: + return [ + record.getMessage() + for record in caplog.records + if record.levelno >= logging.ERROR and record.name.startswith("litellm_proxy_extras") + ] + + def test_an_unrecognized_prisma_error_logs_its_stderr_at_error( + self, monkeypatch: pytest.MonkeyPatch, tmp_path: Path, caplog: pytest.LogCaptureFixture + ) -> None: + stderr: Final = "Error: P1001: Can't reach database server at db:5432" + with caplog.at_level(logging.ERROR, logger="litellm_proxy_extras"): + succeeded, calls, _ = self._run_v1_migrations( + monkeypatch, tmp_path, deploy_stderr=stderr + ) + + assert succeeded is False + assert self._deploy_call_count(calls) == 4 + assert any(stderr in message for message in self._error_messages(caplog)) + + def test_an_unclassified_p3018_logs_its_stderr_and_retry_failure_at_error( + self, monkeypatch: pytest.MonkeyPatch, tmp_path: Path, caplog: pytest.LogCaptureFixture + ) -> None: + with caplog.at_level(logging.ERROR, logger="litellm_proxy_extras"): + succeeded, calls, _ = self._run_v1_migrations( + monkeypatch, tmp_path, deploy_stderr=_P3018_UNCLASSIFIED_STDERR + ) + + assert succeeded is False + assert self._deploy_call_count(calls) == 4 + messages: Final = self._error_messages(caplog) + assert any( + "20260921190000_agent_identity" in message and "is duplicated" in message + for message in messages + ) + assert any( + "The process failed to execute" in message and "Retrying... (3 attempts left)" in message + for message in messages + ) + + def test_called_process_error_with_no_command_retries_all_v1_attempts( + self, monkeypatch: pytest.MonkeyPatch, tmp_path: Path + ) -> None: + import litellm_proxy_extras.utils as utils_module + + migration_dir: Final = tmp_path / "migration_dir" + migration_dir.mkdir() + monkeypatch.setenv("LITELLM_MIGRATION_DIR", str(migration_dir)) + monkeypatch.delenv("DATABASE_URL", raising=False) + monkeypatch.delenv("DIRECT_URL", raising=False) + monkeypatch.setenv("PRISMA_OFFLINE_MODE", "true") + monkeypatch.setenv("PRISMA_CLI_PATH", sys.executable) + monkeypatch.setattr(utils_module.time, "sleep", lambda seconds: None) + calls: Final[list[None]] = [] + + class _FakePrismaPopen: + def __init__( + self, + argv: tuple[str, ...], + *, + env: Optional[dict[str, str]] = None, + stdout: object = None, + stderr: object = None, + text: object = None, + start_new_session: object = None, + ) -> None: + self.args: Final = None + self.returncode: Final = 1 + calls.append(None) + + def __enter__(self) -> "_FakePrismaPopen": + return self + + def __exit__(self, *args: object) -> None: + return None + + def communicate(self, timeout: Optional[float] = None) -> tuple[str, str]: + return "", "Error: P3018 unclassified" + + monkeypatch.setattr( + utils_module.prisma_toolchain.subprocess, "Popen", _FakePrismaPopen + ) + + try: + succeeded: Final = ProxyExtrasDBManager._run_migrations( + use_migrate=True, use_v2_resolver=False + ) + except TypeError as error: + pytest.fail( + f"_run_migrations raised TypeError after {len(calls)} Popen calls: {error}", + pytrace=False, + ) + + assert succeeded is False + assert len(calls) == 4 + + def test_a_timeout_logs_at_error_naming_the_migrate_deploy_timeout_env_var( + self, monkeypatch: pytest.MonkeyPatch, tmp_path: Path, caplog: pytest.LogCaptureFixture + ) -> None: + from litellm_proxy_extras.prisma_toolchain import PRISMA_MIGRATE_DEPLOY_TIMEOUT_ENV_VAR + + with caplog.at_level(logging.ERROR, logger="litellm_proxy_extras"): + succeeded, calls, killed_pids = self._run_v1_migrations( + monkeypatch, tmp_path, deploy_timeout=True + ) + + assert succeeded is False + assert self._deploy_call_count(calls) == 4 + assert killed_pids == [_FAKE_PRISMA_PID] * 4 + assert any( + "timed out" in message and PRISMA_MIGRATE_DEPLOY_TIMEOUT_ENV_VAR in message + for message in self._error_messages(caplog) + ) + + def test_a_recovered_baseline_logs_nothing_at_error( + self, monkeypatch: pytest.MonkeyPatch, tmp_path: Path, caplog: pytest.LogCaptureFixture + ) -> None: + with caplog.at_level(logging.ERROR, logger="litellm_proxy_extras"): + succeeded, calls, _ = self._run_v1_migrations( + monkeypatch, + tmp_path, + deploy_stderr=_P3005_STDERR, + database_url="postgresql://user:pass@db:5432/litellm", + ) + + assert succeeded is True + assert tuple(calls[0][-2:]) == ("migrate", "deploy") + assert self._error_messages(caplog) == [] + + def test_a_failed_baseline_recovery_logs_its_stderr_at_error( + self, monkeypatch: pytest.MonkeyPatch, tmp_path: Path, caplog: pytest.LogCaptureFixture + ) -> None: + database_url: Final = "postgresql://llmproxy:s3cr3t 'p\"w@db:5432/litellm" + monkeypatch.delenv("DIRECT_URL", raising=False) + with caplog.at_level(logging.DEBUG, logger="litellm_proxy_extras"): + succeeded, calls, _ = self._run_v1_migrations( + monkeypatch, + tmp_path, + deploy_stderr=_P3005_STDERR, + diff_stderr=f"baseline diff failed: XYZ-7731 for {database_url}", + database_url=database_url, + ) + + assert succeeded is False + assert self._deploy_call_count(calls) == 4 + assert [ + record.getMessage() + for record in caplog.records + if "s3cr3t" in record.getMessage() or 'p"w' in record.getMessage() + ] == [] + messages: Final = self._error_messages(caplog) + assert any("postgresql://REDACTED@db:5432/litellm" in message for message in messages) + assert any("XYZ-7731" in message for message in messages) + + +@pytest.mark.parametrize( + "database_url,direct_url,text,expected", + ( + ( + "postgresql://u:pa ss@db:5432/litellm", + None, + 'Error: P1000: Authentication failed against database server at "postgresql://u:pa ss@db:5432/litellm"', + 'Error: P1000: Authentication failed against database server at "postgresql://REDACTED@db:5432/litellm"', + ), + ( + "postgresql://u:pa'ss@db:5432/litellm", + None, + "postgresql://u:pa'ss@db:5432/litellm", + "postgresql://REDACTED@db:5432/litellm", + ), + ( + 'postgresql://u:pa"ss@db:5432/litellm', + None, + 'postgresql://u:pa"ss@db:5432/litellm', + "postgresql://REDACTED@db:5432/litellm", + ), + ( + "postgresql://u:p@ss@db:5432/litellm", + None, + "postgresql://u:p@ss@db:5432/litellm", + "postgresql://REDACTED@db:5432/litellm", + ), + ( + "postgresql://u:p%20ss@db:5432/litellm", + None, + "postgresql://u:p ss@db:5432/litellm", + "postgresql://REDACTED@db:5432/litellm", + ), + ( + "postgresql://db/litellm?password=a b&sslmode=require", + None, + "postgresql://db/litellm?password=a b&sslmode=require", + "postgresql://db/litellm?REDACTED&sslmode=require", + ), + ( + "postgresql://db/litellm?sslpassword=zq'7x", + None, + "postgresql://db/litellm?sslpassword=zq'7x", + "postgresql://db/litellm?REDACTED", + ), + ( + None, + "postgresql://u:pa ss@db:5432/litellm", + "postgresql://u:pa ss@db:5432/litellm", + "postgresql://REDACTED@db:5432/litellm", + ), + ( + None, + None, + "postgresql://u:pw@db/x", + "postgresql://REDACTED@db/x", + ), + ( + "postgresql://u:p@db:5432/litellm", + None, + "Error: P1001: Can't reach database server at db:5432", + "Error: P1001: Can't reach database server at db:5432", + ), + ( + "postgresql://u:p@db:5432/litellm", + None, + "Error:P1001: Can't reach database server at db:5432", + "Error:P1001: Can't reach database server at db:5432", + ), + ( + None, + None, + "plain text with no URL", + "plain text with no URL", + ), + ), +) +def test_redact_credentials_masks_passwords_in_embedded_urls( + database_url: str | None, + direct_url: str | None, + text: str, + expected: str, + monkeypatch: pytest.MonkeyPatch, +) -> None: + if database_url is None: + monkeypatch.delenv("DATABASE_URL", raising=False) + else: + monkeypatch.setenv("DATABASE_URL", database_url) + if direct_url is None: + monkeypatch.delenv("DIRECT_URL", raising=False) + else: + monkeypatch.setenv("DIRECT_URL", direct_url) + assert _redact_credentials(text) == expected + + +@pytest.mark.parametrize("password", ("zq'7x", 'zq"7x', "zq'\"7x", "zq 7x", "zq@7x")) +def test_redact_command_error_masks_url_arguments(password: str, monkeypatch: pytest.MonkeyPatch) -> None: + database_url: Final = f"postgresql://u:{password}@db:5432/litellm" + monkeypatch.setenv("DATABASE_URL", database_url) + monkeypatch.delenv("DIRECT_URL", raising=False) + error: Final = subprocess.CalledProcessError(1, ["prisma", "migrate", "diff", "--to-url", database_url]) + + message: Final = _redact_command_error(error) + + assert "zq" not in message + assert "7x" not in message + assert "postgresql://REDACTED@db:5432/litellm" in message + assert "returned non-zero exit status 1" in message + + +@pytest.mark.parametrize( + "command", + ( + None, + Path("/usr/bin/prisma"), + 7, + ("prisma", "migrate", "deploy"), + ["prisma", "migrate", "deploy"], + "prisma migrate deploy", + ), +) +def test_redact_command_error_preserves_unredacted_command_format( + command: object, monkeypatch: pytest.MonkeyPatch +) -> None: + monkeypatch.delenv("DATABASE_URL", raising=False) + monkeypatch.delenv("DIRECT_URL", raising=False) + error: Final = subprocess.CalledProcessError(1, command) + + assert _redact_command_error(error) == str(error) + + +def test_redact_command_error_masks_password_in_tuple_url_argument( + monkeypatch: pytest.MonkeyPatch, +) -> None: + password: Final = "zq 7x" + database_url: Final = f"postgresql://u:{password}@db:5432/litellm" + monkeypatch.setenv("DATABASE_URL", database_url) + monkeypatch.delenv("DIRECT_URL", raising=False) + error: Final = subprocess.CalledProcessError(1, ("prisma", "migrate", "deploy", "--to-url", database_url)) + + message: Final = _redact_command_error(error) + + assert message.startswith("Command '('") + assert password not in message + assert "postgresql://REDACTED@db:5432/litellm" in message diff --git a/tests/unit/llms/anthropic/pass_through/messages/test_mcp_handler.py b/tests/unit/llms/anthropic/pass_through/messages/test_mcp_handler.py index 37db61031c9..fc9d77a10a2 100644 --- a/tests/unit/llms/anthropic/pass_through/messages/test_mcp_handler.py +++ b/tests/unit/llms/anthropic/pass_through/messages/test_mcp_handler.py @@ -226,6 +226,76 @@ async def test_anthropic_messages_with_mcp_forwards_the_callers_mcp_credentials( assert execution["guardrail_context"] == {"metadata": {"guardrails": ("block-all",)}} +@pytest.mark.asyncio +async def test_anthropic_messages_with_mcp_hands_execution_the_requests_served_tools(): + """ + Regression test: /v1/messages auto-execution must carry this request's + resolved tool definitions into execution, matching the Responses and chat + completions bridges. + + Given: A request whose MCP reference resolves to a definition carrying a + description and input schema + When: The model asks for that tool and the gateway executes it + Then: _execute_tool_calls receives the definition under served_tools, so + pre_mcp_call hooks can judge the call on what the model was shown + + Dropping it does not fail loudly; the call still runs, but the hook sees + only the name and arguments, leaving /v1/messages permanently colder than + the other two bridges even though all three resolve the same definitions. + """ + from mcp.types import Tool + + from litellm.llms.anthropic.pass_through.messages import mcp_handler + from litellm.responses.mcp.request_context import MCPRequestContext + + served = [ + Tool( + name="read_wiki_structure", + description="Read the structure of a wiki", + inputSchema={"type": "object", "properties": {"repoName": {"type": "string"}}}, + ) + ] + + process = AsyncMock(return_value=(served, {"read_wiki_structure": "deepwiki"})) + execute = AsyncMock( + return_value=[{"tool_call_id": "toolu_1", "result": "ok", "name": "read_wiki_structure"}] + ) + responses = [ + { + "stop_reason": "tool_use", + "content": [{"type": "tool_use", "id": "toolu_1", "name": "read_wiki_structure", "input": {}}], + }, + {"stop_reason": "end_turn", "content": [{"type": "text", "text": "done"}]}, + ] + + with ( + patch.object(MCPRequestContext, "resolve", return_value=MCPRequestContext(user_api_key_auth="auth")), + patch.object( + import_module("litellm.responses.mcp.litellm_proxy_mcp_handler").LiteLLM_Proxy_MCP_Handler, + "_process_mcp_tools_without_openai_transform", + new=process, + ), + patch.object( + import_module("litellm.responses.mcp.litellm_proxy_mcp_handler").LiteLLM_Proxy_MCP_Handler, + "_execute_tool_calls", + new=execute, + ), + patch("litellm.anthropic_messages", new=AsyncMock(side_effect=responses)), + ): + await mcp_handler.anthropic_messages_with_mcp( + max_tokens=100, + messages=[{"role": "user", "content": "hi"}], + model="claude-sonnet-4-5", + tools=[MCP_REFERENCE], + ) + + execution = execute.call_args.kwargs + assert execution.get("served_tools") == served, ( + "The request's resolved tool definitions must reach execution so pre_mcp_call " + "hooks see the listed description and input schema" + ) + + @pytest.mark.asyncio async def test_anthropic_messages_with_mcp_stops_when_every_tool_call_is_skipped(): """ diff --git a/tests/unit/proxy/_experimental/mcp_server/test_mcp_guardrail_usage_monitor.py b/tests/unit/proxy/_experimental/mcp_server/test_mcp_guardrail_usage_monitor.py index e1e4cd3d161..8e87837611a 100644 --- a/tests/unit/proxy/_experimental/mcp_server/test_mcp_guardrail_usage_monitor.py +++ b/tests/unit/proxy/_experimental/mcp_server/test_mcp_guardrail_usage_monitor.py @@ -48,6 +48,7 @@ def _bare_manager() -> MOD.MCPServerManager: reaches the guardrail hooks; they have their own coverage elsewhere. """ mgr = MOD.MCPServerManager.__new__(MOD.MCPServerManager) + mgr._listed_tools_by_server_id = {} mgr.check_allowed_or_banned_tools = lambda name, server: True mgr.validate_allowed_params = lambda tool_name, arguments, server: None diff --git a/tests/unit/proxy/_experimental/mcp_server/test_mcp_proxy_mode.py b/tests/unit/proxy/_experimental/mcp_server/test_mcp_proxy_mode.py index ed5d67164bd..e52a86d76af 100644 --- a/tests/unit/proxy/_experimental/mcp_server/test_mcp_proxy_mode.py +++ b/tests/unit/proxy/_experimental/mcp_server/test_mcp_proxy_mode.py @@ -1,17 +1,29 @@ from litellm.proxy._experimental.mcp_server import operations as mcp_operations +import asyncio import json from datetime import datetime +from unittest.mock import AsyncMock, patch import pytest from fastapi import HTTPException from mcp.shared.exceptions import MCPError +from mcp.types import CallToolResult, TextContent +from mcp.types import Tool as MCPTool from pydantic import AnyUrl import litellm from litellm.integrations.custom_logger import CustomLogger from litellm.proxy._experimental.mcp_server import server from litellm.proxy._experimental.mcp_server.mcp_context import _mcp_proxy_mode +from litellm.proxy._experimental.mcp_server.mcp_server_manager import ListedToolsCaller +from litellm.proxy._experimental.mcp_server.tool_search import ( + handle_mcp_proxy_tool, + mcp_proxy_tool_id, + with_mcp_proxy_identity, +) from litellm.proxy._types import LiteLLM_ObjectPermissionTable, UserAPIKeyAuth +from litellm.types.mcp import MCPTransport +from litellm.types.mcp_server.mcp_server_manager import MCPServer AUTH = UserAPIKeyAuth(api_key="key") @@ -130,3 +142,46 @@ async def test_proxy_scope_exception_emits_failure_log(monkeypatch: pytest.Monke assert hook_payload["arguments"] == arguments assert "raw_headers" not in hook_payload assert "raw-scope-secret" not in recorder.events[1][1] + + +@pytest.mark.asyncio +async def test_proxy_call_tool_on_a_never_listed_tool_hands_the_pre_hook_no_listed_tool() -> None: + """/mcp/proxy tools/list serves only the meta-tools, so the catalog call_tool reads to resolve its + tool_id was never served: it must not fill the caller's listed-tools slot, and the pre-call hook + must see no listed tool for the call.""" + manager = mcp_operations.global_mcp_server_manager + server = MCPServer(server_id="proxy-meta", name="proxy-meta", transport=MCPTransport.http, url="http://meta") + auth = UserAPIKeyAuth(api_key="sk-proxy-meta", user_id="proxy-caller") + upstream = [MCPTool(name="echo", description="Echo text back", inputSchema={"type": "object"})] + served_as = with_mcp_proxy_identity(MCPTool(name="proxy-meta-echo", inputSchema={}), server.server_id) + pre_call_tool_check = AsyncMock(return_value={}) + + async def call_regular_mcp_tool(*, tasks: list[asyncio.Task[object]], **_: object) -> CallToolResult: + await asyncio.gather(*tasks) + return CallToolResult(content=[TextContent(type="text", text="echoed")]) + + with ( + patch.dict(manager.registry, {server.server_id: server}), + patch.dict(manager.tool_name_to_mcp_server_name_mapping), + patch.object(mcp_operations, "_get_allowed_mcp_servers", AsyncMock(return_value=[server])), + patch.object(manager, "_create_mcp_client", AsyncMock(return_value=object())), + patch.object(manager, "_fetch_tools_with_timeout", AsyncMock(return_value=upstream)), + patch.object(manager, "pre_call_tool_check", pre_call_tool_check), + patch.object(manager, "_call_regular_mcp_tool", call_regular_mcp_tool), + ): + try: + result = await handle_mcp_proxy_tool( + name="call_tool", + arguments={"tool_id": mcp_proxy_tool_id(served_as), "arguments": {}}, + user_api_key_dict=auth, + ) + listed = manager.get_listed_tool(server, "echo", ListedToolsCaller(user_api_key_auth=auth)) + finally: + manager._drop_listed_tools(server.server_id) + + assert result.is_error is False + assert result.content[0].text == "echoed" + pre_call_tool_check.assert_awaited_once() + assert pre_call_tool_check.await_args.kwargs["name"] == "echo" + assert pre_call_tool_check.await_args.kwargs["tool"] is None + assert listed is None diff --git a/tests/unit/proxy/_experimental/mcp_server/test_mcp_server.py b/tests/unit/proxy/_experimental/mcp_server/test_mcp_server.py index d3679506a2f..316988ef175 100644 --- a/tests/unit/proxy/_experimental/mcp_server/test_mcp_server.py +++ b/tests/unit/proxy/_experimental/mcp_server/test_mcp_server.py @@ -963,6 +963,8 @@ async def test_get_tools_from_mcp_servers(): user_api_key_auth=None, oauth2_headers=None, proxy_logging_obj=None, + catalog_auth_header=None, + record_listing=True, ): if server.server_id == "server1_id": return [mock_tool_1] @@ -1998,6 +2000,7 @@ async def test_get_tools_for_single_server(): client_ip=None, user_api_key_auth=None, proxy_logging_obj=ANY, + record_listing=False, ) # Verify the result diff --git a/tests/unit/proxy/_experimental/mcp_server/test_mcp_server_manager.py b/tests/unit/proxy/_experimental/mcp_server/test_mcp_server_manager.py index cf6cf93f35b..cb017afbea5 100644 --- a/tests/unit/proxy/_experimental/mcp_server/test_mcp_server_manager.py +++ b/tests/unit/proxy/_experimental/mcp_server/test_mcp_server_manager.py @@ -6,6 +6,7 @@ import json import logging import os import sys +import time from collections.abc import AsyncIterator from datetime import datetime from pathlib import Path @@ -41,8 +42,10 @@ from mcp.types import Tool as MCPTool from pydantic import AnyUrl, TypeAdapter from litellm.constants import MCP_METADATA_TIMEOUT +from litellm.proxy._experimental.mcp_server import discoverable_endpoints from litellm.proxy._experimental.mcp_server.tool_outcome import TextResult from litellm.proxy._experimental.mcp_server.mcp_server_manager import ( + ListedToolsCaller, MCPServerManager, _deserialize_json_dict, _flow_endpoints_missing, @@ -53,6 +56,7 @@ from litellm.proxy._experimental.mcp_server.mcp_server_manager import ( _obo_retry_applies, _resolve_openapi_tool_auth, _should_strip_caller_authorization, + listed_tools_caller_for, ) from litellm.proxy._types import ( LiteLLM_MCPServerTable, @@ -116,7 +120,6 @@ async def test_manager_sampling_preserves_explicit_headers_without_ambient_conte assert sampling.await_args.kwargs["raw_headers"] == {"x-test-caller": "sampling-caller"} - @pytest.mark.asyncio async def test_sampling_callback_keeps_creation_context_after_caller_switch(): from mcp.server.auth.middleware.auth_context import auth_context_var @@ -218,8 +221,6 @@ def _reload_mcp_manager_module(): return reloaded - - @pytest.fixture(autouse=True) def enable_eager_mcp_oauth_discovery(monkeypatch): monkeypatch.setenv("LITELLM_MCP_OAUTH_DISCOVERY_ON_STARTUP", "1") @@ -1576,7 +1577,9 @@ class TestMCPServerManager: assert not any("oauth2_id_jag" in message for message in caplog.messages) @pytest.mark.asyncio - async def test_load_servers_from_config_does_not_warn_for_api_key_with_google_sso(self, config_only_mcp_manager_factory, monkeypatch, caplog): + async def test_load_servers_from_config_does_not_warn_for_api_key_with_google_sso( + self, config_only_mcp_manager_factory, monkeypatch, caplog + ): self._clear_sso_env(monkeypatch) monkeypatch.setenv("GOOGLE_CLIENT_ID", "google-cid") manager = config_only_mcp_manager_factory() @@ -4862,7 +4865,9 @@ class TestMCPServerManager: @pytest.mark.parametrize("auth_type", [MCPAuth.none, MCPAuth.bearer_token, MCPAuth.api_key, MCPAuth.oauth2]) @pytest.mark.parametrize("is_byok", [False, True]) @pytest.mark.parametrize("scheme", ["http", "https"]) - async def test_openapi_health_loads_spec_without_mcp_handshake(self, respx_mock, monkeypatch, auth_type, is_byok, scheme): + async def test_openapi_health_loads_spec_without_mcp_handshake( + self, respx_mock, monkeypatch, auth_type, is_byok, scheme + ): monkeypatch.setenv("DISABLE_AIOHTTP_TRANSPORT", "True") manager = MCPServerManager() server = MCPServer( @@ -4912,14 +4917,28 @@ class TestMCPServerManager: @pytest.mark.parametrize( ("failure", "expected_status", "expected_error"), [ - (httpx.Response(401, text="secret response content"), "unhealthy", "OpenAPI specification request failed (HTTP 401)"), + ( + httpx.Response(401, text="secret response content"), + "unhealthy", + "OpenAPI specification request failed (HTTP 401)", + ), (httpx.Response(404), "unhealthy", "OpenAPI specification request failed (HTTP 404)"), (httpx.Response(500), "unhealthy", "OpenAPI specification request failed (HTTP 500)"), - (httpx.ConnectError("secret network details"), "unhealthy", "OpenAPI specification could not be loaded (ConnectError)"), - (httpx.Response(200, text="secret invalid JSON body"), "unhealthy", "OpenAPI specification could not be loaded (JSONDecodeError)"), + ( + httpx.ConnectError("secret network details"), + "unhealthy", + "OpenAPI specification could not be loaded (ConnectError)", + ), + ( + httpx.Response(200, text="secret invalid JSON body"), + "unhealthy", + "OpenAPI specification could not be loaded (JSONDecodeError)", + ), ], ) - async def test_openapi_health_reports_safe_failures(self, respx_mock, monkeypatch, failure, expected_status, expected_error): + async def test_openapi_health_reports_safe_failures( + self, respx_mock, monkeypatch, failure, expected_status, expected_error + ): monkeypatch.setenv("DISABLE_AIOHTTP_TRANSPORT", "True") manager = MCPServerManager() server = MCPServer( @@ -5077,7 +5096,10 @@ class TestMCPServerManager: @pytest.mark.asyncio @pytest.mark.parametrize("oauth2_flow", [None, "authorization_code", "client_credentials"]) async def test_health_check_server_oauth2_reports_reachability( - self, monkeypatch: pytest.MonkeyPatch, respx_mock: MockRouter, oauth2_flow: Literal["authorization_code", "client_credentials"] | None + self, + monkeypatch: pytest.MonkeyPatch, + respx_mock: MockRouter, + oauth2_flow: Literal["authorization_code", "client_credentials"] | None, ) -> None: monkeypatch.setenv("DISABLE_AIOHTTP_TRANSPORT", "True") manager: Final = MCPServerManager() @@ -5106,14 +5128,28 @@ class TestMCPServerManager: assert not {"authorization", "x-api-key", "cookie"}.intersection(route.calls[0].request.headers) @pytest.mark.asyncio - @pytest.mark.parametrize("auth_type", [ - MCPAuth.bearer_token, MCPAuth.api_key, MCPAuth.basic, MCPAuth.authorization, MCPAuth.token, - MCPAuth.oauth2_token_exchange, MCPAuth.oauth2_id_jag, MCPAuth.true_passthrough, MCPAuth.oauth_delegate, - ]) + @pytest.mark.parametrize( + "auth_type", + [ + MCPAuth.bearer_token, + MCPAuth.api_key, + MCPAuth.basic, + MCPAuth.authorization, + MCPAuth.token, + MCPAuth.oauth2_token_exchange, + MCPAuth.oauth2_id_jag, + MCPAuth.true_passthrough, + MCPAuth.oauth_delegate, + ], + ) @pytest.mark.parametrize("transport", [MCPTransport.http, MCPTransport.sse]) @pytest.mark.parametrize("response_code", [200, 204, 302, 401, 403, 405, 503]) async def test_health_check_without_credentials_accepts_any_http_response( - self, monkeypatch: pytest.MonkeyPatch, respx_mock: MockRouter, auth_type: MCPAuthType, transport: Literal[MCPTransport.http, MCPTransport.sse], + self, + monkeypatch: pytest.MonkeyPatch, + respx_mock: MockRouter, + auth_type: MCPAuthType, + transport: Literal[MCPTransport.http, MCPTransport.sse], response_code: int, ) -> None: monkeypatch.setenv("DISABLE_AIOHTTP_TRANSPORT", "True") @@ -5144,6 +5180,7 @@ class TestMCPServerManager: self, monkeypatch: pytest.MonkeyPatch, respx_mock: MockRouter, response_code: int ) -> None: monkeypatch.setenv("DISABLE_AIOHTTP_TRANSPORT", "True") + class UnreadBody(httpx.AsyncByteStream): def __init__(self) -> None: self.read = False @@ -5158,17 +5195,28 @@ class TestMCPServerManager: manager: Final = MCPServerManager() server: Final = MCPServer( - server_id="streaming-health", name="streaming-health", transport=MCPTransport.sse, - auth_type=MCPAuth.oauth2, url="https://mcp.example.test/events", + server_id="streaming-health", + name="streaming-health", + transport=MCPTransport.sse, + auth_type=MCPAuth.oauth2, + url="https://mcp.example.test/events", ) manager.registry[server.server_id] = server bodies: Final = (UnreadBody(), UnreadBody()) - route: Final = respx_mock.get(server.url).mock(side_effect=[ - httpx.Response(response_code, stream=body, headers={ - "Content-Type": "text/event-stream", "Set-Cookie": "health=secret; Path=/", - "Location": "http://127.0.0.1/private", - }) for body in bodies - ]) + route: Final = respx_mock.get(server.url).mock( + side_effect=[ + httpx.Response( + response_code, + stream=body, + headers={ + "Content-Type": "text/event-stream", + "Set-Cookie": "health=secret; Path=/", + "Location": "http://127.0.0.1/private", + }, + ) + for body in bodies + ] + ) first: Final = await manager.health_check_server(server.server_id) second: Final = await manager.health_check_server(server.server_id) @@ -5179,19 +5227,28 @@ class TestMCPServerManager: assert all("cookie" not in call.request.headers for call in route.calls) @pytest.mark.asyncio - @pytest.mark.parametrize(("transport", "url"), [ - (MCPTransport.stdio, "https://mcp.example.test"), - (MCPTransport.http, None), (MCPTransport.http, ""), (MCPTransport.http, "not-a-url"), - (MCPTransport.http, "ftp://mcp.example.test"), - (MCPTransport.http, "https://user:secret@mcp.example.test"), - (MCPTransport.http, "https://mcp.example.test:bad/mcp"), - ]) + @pytest.mark.parametrize( + ("transport", "url"), + [ + (MCPTransport.stdio, "https://mcp.example.test"), + (MCPTransport.http, None), + (MCPTransport.http, ""), + (MCPTransport.http, "not-a-url"), + (MCPTransport.http, "ftp://mcp.example.test"), + (MCPTransport.http, "https://user:secret@mcp.example.test"), + (MCPTransport.http, "https://mcp.example.test:bad/mcp"), + ], + ) async def test_health_reachability_rejects_unprobeable_urls_without_requests( self, respx_mock: MockRouter, transport: Literal[MCPTransport.http, MCPTransport.stdio], url: str | None ) -> None: manager: Final = MCPServerManager() server: Final = MCPServer( - server_id="unprobeable", name="unprobeable", transport=transport, auth_type=MCPAuth.oauth2, url=url, + server_id="unprobeable", + name="unprobeable", + transport=transport, + auth_type=MCPAuth.oauth2, + url=url, ) manager.registry[server.server_id] = server @@ -5202,19 +5259,26 @@ class TestMCPServerManager: assert not respx_mock.calls @pytest.mark.asyncio - @pytest.mark.parametrize("failure", [ - httpx.ConnectError("TLS/connection failure with secret details"), - httpx.ReadTimeout("secret timeout details"), - httpx.RemoteProtocolError("secret malformed response"), - ]) + @pytest.mark.parametrize( + "failure", + [ + httpx.ConnectError("TLS/connection failure with secret details"), + httpx.ReadTimeout("secret timeout details"), + httpx.RemoteProtocolError("secret malformed response"), + ], + ) async def test_health_reachability_reports_no_response_without_secret_details( self, monkeypatch: pytest.MonkeyPatch, respx_mock: MockRouter, failure: httpx.RequestError ) -> None: monkeypatch.setenv("DISABLE_AIOHTTP_TRANSPORT", "True") manager: Final = MCPServerManager() server: Final = MCPServer( - server_id="failed-health", name="failed-health", transport=MCPTransport.http, - auth_type=MCPAuth.bearer_token, is_byok=True, url="https://mcp.example.test/secret?token=secret", + server_id="failed-health", + name="failed-health", + transport=MCPTransport.http, + auth_type=MCPAuth.bearer_token, + is_byok=True, + url="https://mcp.example.test/secret?token=secret", ) manager.registry[server.server_id] = server route: Final = respx_mock.get(server.url).mock(side_effect=failure) @@ -5230,8 +5294,11 @@ class TestMCPServerManager: monkeypatch.setenv("SSL_SECURITY_LEVEL", "invalid-secret-cipher") manager: Final = MCPServerManager() server: Final = MCPServer( - server_id="bad-tls", name="bad-tls", transport=MCPTransport.http, - auth_type=MCPAuth.oauth2, url="https://mcp.example.test", + server_id="bad-tls", + name="bad-tls", + transport=MCPTransport.http, + auth_type=MCPAuth.oauth2, + url="https://mcp.example.test", ) manager.registry[server.server_id] = server @@ -5249,8 +5316,11 @@ class TestMCPServerManager: monkeypatch.setattr("litellm.proxy._experimental.mcp_server.mcp_server_manager.MCP_HEALTH_CHECK_TIMEOUT", 0.1) manager: Final = MCPServerManager() server: Final = MCPServer( - server_id="slow-health", name="slow-health", transport=MCPTransport.http, - auth_type=MCPAuth.oauth2, url="https://mcp.example.test/slow", + server_id="slow-health", + name="slow-health", + transport=MCPTransport.http, + auth_type=MCPAuth.oauth2, + url="https://mcp.example.test/slow", ) manager.registry[server.server_id] = server started: Final = asyncio.Event() @@ -5303,8 +5373,11 @@ class TestMCPServerManager: server_ids: Final = [f"health-{index}" for index in range(server_count)] manager.registry = { server_id: MCPServer( - server_id=server_id, name=server_id, transport=MCPTransport.http, - auth_type=MCPAuth.oauth2, url=f"https://health.example.test/{server_id}", + server_id=server_id, + name=server_id, + transport=MCPTransport.http, + auth_type=MCPAuth.oauth2, + url=f"https://health.example.test/{server_id}", ) for server_id in server_ids } @@ -5631,8 +5704,15 @@ class TestMCPServerManager: captured: dict = {} def fake_create_tool_function( - path, method, operation, base_url, headers=None, server_label=None, relays_upstream_auth=False, - auth_type=None, upstream_token_header=None, + path, + method, + operation, + base_url, + headers=None, + server_label=None, + relays_upstream_auth=False, + auth_type=None, + upstream_token_header=None, ): captured["headers"] = headers captured["server_label"] = server_label @@ -5717,8 +5797,15 @@ class TestMCPServerManager: captured: dict = {} def fake_create_tool_function( - path, method, operation, base_url, headers=None, server_label=None, relays_upstream_auth=False, - auth_type=None, upstream_token_header=None, + path, + method, + operation, + base_url, + headers=None, + server_label=None, + relays_upstream_auth=False, + auth_type=None, + upstream_token_header=None, ): captured["headers"] = headers @@ -7067,8 +7154,7 @@ class TestMCPServerManager: # Mock _create_mcp_client to return our mock client manager._create_mcp_client = AsyncMock(return_value=mock_client) - # Mock user auth with no restrictions - user_api_key_auth: Final = UserAPIKeyAuth() + user_api_key_auth: Final = UserAPIKeyAuth(api_key="sk-test") # Mock proxy logging proxy_logging_obj = MagicMock() @@ -7094,6 +7180,1051 @@ class TestMCPServerManager: # Verify the MCP client call was awaited exactly once assert mock_client.call_tool.await_count == 1 + @staticmethod + def _manager_ready_for_call_tool( + listed_tools: list[MCPTool], caller: ListedToolsCaller | None = None + ) -> tuple[MCPServerManager, MagicMock]: + from mcp.types import CallToolResult + + manager = MCPServerManager() + server = MCPServer( + server_id="test-server", + name="test-server", + transport=MCPTransport.http, + url="http://test-server.com", + ) + manager.registry = {"test-server": server} + manager.tool_name_to_mcp_server_name_mapping["test_tool"] = "test-server" + manager.tool_name_to_mcp_server_name_mapping["test-server-test_tool"] = "test-server" + manager._create_prefixed_tools(listed_tools, server) + manager._record_listed_tools(server, listed_tools, caller) + + mock_client = AsyncMock() + mock_client.call_tool.return_value = MagicMock(spec=CallToolResult, content=[], isError=False) + manager._create_mcp_client = AsyncMock(return_value=mock_client) + + proxy_logging_obj = MagicMock() + proxy_logging_obj._create_mcp_request_object_from_kwargs = MagicMock(return_value={}) + proxy_logging_obj._convert_mcp_to_llm_format = MagicMock(return_value={}) + proxy_logging_obj.pre_call_hook = AsyncMock(return_value={}) + proxy_logging_obj.during_call_hook = AsyncMock(return_value=None) + return manager, proxy_logging_obj + + @staticmethod + def _unrestricted_auth() -> UserAPIKeyAuth: + return UserAPIKeyAuth(api_key="sk-test") + + @pytest.mark.asyncio + async def test_call_tool_hands_listed_tool_description_and_schema_to_pre_call_hooks(self): + schema = {"type": "object", "properties": {"param": {"type": "string"}}, "required": ["param"]} + listed = [MCPTool(name="test_tool", description="Runs the test tool", inputSchema=schema)] + auth = self._unrestricted_auth() + manager, proxy_logging_obj = self._manager_ready_for_call_tool( + listed, caller=ListedToolsCaller(user_api_key_auth=auth) + ) + + await manager.call_tool( + server_name="test-server", + name="test_tool", + arguments={"param": "value"}, + user_api_key_auth=auth, + proxy_logging_obj=proxy_logging_obj, + ) + + hook_kwargs = proxy_logging_obj._create_mcp_request_object_from_kwargs.call_args.args[0] + assert (hook_kwargs["tool_description"], hook_kwargs["tool_input_schema"]) == ("Runs the test tool", schema) + + @pytest.mark.asyncio + async def test_call_tool_hands_during_call_hooks_name_and_arguments_only_even_for_a_listed_tool(self): + """A during_mcp_call guardrail evaluates the call in flight, so it keeps seeing only the name and + arguments it always did; the listed description and schema go to the pre-call hooks alone.""" + schema = {"type": "object", "properties": {"param": {"type": "string"}}} + listed = [MCPTool(name="test_tool", description="Runs the test tool", inputSchema=schema)] + auth = UserAPIKeyAuth(api_key="sk-test") + manager, _ = self._manager_ready_for_call_tool(listed, caller=ListedToolsCaller(user_api_key_auth=auth)) + proxy_logging_obj = ProxyLogging(user_api_key_cache=DualCache()) + proxy_logging_obj.pre_call_hook = AsyncMock(return_value={}) + proxy_logging_obj.during_call_hook = AsyncMock(return_value=None) + + await manager.call_tool( + server_name="test-server", + name="test_tool", + arguments={"param": "value"}, + user_api_key_auth=auth, + proxy_logging_obj=proxy_logging_obj, + ) + + during_data = proxy_logging_obj.during_call_hook.call_args.kwargs["data"] + assert during_data["mcp_arguments"] == {"param": "value"} + assert (during_data.get("mcp_tool_description"), during_data.get("mcp_input_schema")) == (None, None) + assert "Description:" not in during_data["messages"][0]["content"] + + @pytest.mark.asyncio + async def test_call_tool_passes_no_tool_metadata_when_tool_was_never_listed(self): + auth = self._unrestricted_auth() + manager, proxy_logging_obj = self._manager_ready_for_call_tool( + [MCPTool(name="other_tool", description="Unrelated", inputSchema={"type": "object"})], + caller=ListedToolsCaller(user_api_key_auth=auth), + ) + + await manager.call_tool( + server_name="test-server", + name="test_tool", + arguments={"param": "value"}, + user_api_key_auth=auth, + proxy_logging_obj=proxy_logging_obj, + ) + + hook_kwargs = proxy_logging_obj._create_mcp_request_object_from_kwargs.call_args.args[0] + assert (hook_kwargs["tool_description"], hook_kwargs["tool_input_schema"]) == (None, None) + + def test_get_listed_tool_resolves_the_bare_name_from_the_latest_listing(self): + manager = MCPServerManager() + server = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + manager._record_listed_tools(server, [MCPTool(name="echo", description="v1", inputSchema={})], None) + manager._record_listed_tools(server, [MCPTool(name="echo", description="v2", inputSchema={})], None) + + latest = manager.get_listed_tool(server, "echo") + assert latest is not None and latest.description == "v2" + assert manager.get_listed_tool(server, "missing") is None + + def test_get_listed_tool_never_strips_the_bare_name_it_is_given(self): + """The lookup is exact: a never-listed tool whose bare name starts with the server prefix is not the + listed sibling that stripping the prefix again would name.""" + manager = MCPServerManager() + server = MCPServer(server_id="srv-id", name="srv", alias="srv", transport=MCPTransport.http, url="http://srv") + caller = ListedToolsCaller(user_api_key_auth=UserAPIKeyAuth(api_key="sk-user", user_id="alice")) + manager._record_listed_tools( + server, + [ + MCPTool(name="foo", description="Fetches foo records", inputSchema={"type": "object"}), + MCPTool(name="bar", description="Fetches bar records", inputSchema={"type": "object"}), + ], + caller, + ) + + assert manager.get_listed_tool(server, "srv-foo", caller) is None + listed = manager.get_listed_tool(server, "foo", caller) + assert listed is not None and listed.description == "Fetches foo records" + + @pytest.mark.asyncio + async def test_get_listed_tool_uses_admin_description_override_clients_saw(self): + schema = {"type": "object", "properties": {"text": {"type": "string"}}} + manager = _catalog_manager( + MCPTool(name="echo", description="Upstream wording", inputSchema=schema), + MCPTool(name="ping", description="Untouched", inputSchema={}), + ) + server = MCPServer( + server_id="srv", + name="srv", + transport=MCPTransport.http, + url="http://srv", + tool_name_to_description={"echo": "Admin wording"}, + ) + await manager._get_tools_from_server(server, add_prefix=True, record_listing=True) + + overridden = manager.get_listed_tool(server, "echo") + assert overridden is not None + assert (overridden.name, overridden.description, overridden.input_schema) == ("echo", "Admin wording", schema) + untouched = manager.get_listed_tool(server, "ping") + assert untouched is not None and untouched.description == "Untouched" + + @pytest.mark.asyncio + async def test_get_listed_tool_keeps_the_masked_description_over_the_admin_override(self, catalog_guardrail): + """A discovery guardrail masked the admin override in tools/list, so the tool-call hooks must see + the masked wording, not the original override the caller never saw.""" + _, proxy_logging_obj = catalog_guardrail + manager = _catalog_manager(MCPTool(name="read_note", description="Read a note", inputSchema={"type": "object"})) + server = MCPServer( + server_id="notes", + name="notes", + transport=MCPTransport.http, + tool_name_to_description={"read_note": "Read a SECRET note"}, + ) + served = await manager._get_tools_from_server( + server, add_prefix=True, proxy_logging_obj=proxy_logging_obj, record_listing=True + ) + assert [tool.description for tool in served] == ["Read a [MASKED] note"] + + listed = manager.get_listed_tool(server, "read_note") + assert listed is not None and listed.description == "Read a [MASKED] note", ( + "tools/call must be evaluated against the description tools/list served" + ) + + def test_server_definition_change_drops_listed_tools(self): + manager = MCPServerManager() + server = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + other = MCPServer(server_id="other", name="other", transport=MCPTransport.http, url="http://other") + manager._record_listed_tools(server, [MCPTool(name="echo", description="old", inputSchema={})], None) + manager._record_listed_tools(other, [MCPTool(name="ping", description="kept", inputSchema={})], None) + + manager._invalidate_server_definition_caches(server.server_id) + + assert manager.get_listed_tool(server, "echo") is None + kept = manager.get_listed_tool(other, "ping") + assert kept is not None and kept.description == "kept" + + @pytest.mark.asyncio + async def test_server_save_during_an_in_flight_listing_is_not_undone_by_the_stale_record(self): + """A PUT /v1/mcp/server that lands while a listing awaits its upstream fetch drops the server's + catalog; the fetch completing afterwards must not write the pre-save catalog back, or hooks see + the old description next to the new definition until the next listing.""" + manager = MCPServerManager() + server = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + user = UserAPIKeyAuth(api_key="sk-litellm", user_id="saver") + fetch_started = asyncio.Event() + release_fetch = asyncio.Event() + + async def fetch(client, name): + fetch_started.set() + await release_fetch.wait() + return [MCPTool(name="turn", description="before save", inputSchema={})] + + manager._create_mcp_client = AsyncMock(return_value=AsyncMock()) + manager._fetch_tools_with_timeout = fetch + caller = ListedToolsCaller(user_api_key_auth=user) + + async def list_tools() -> None: + await manager._get_tools_from_server(server=server, user_api_key_auth=user, record_listing=True) + + listing = asyncio.create_task(list_tools()) + await fetch_started.wait() + manager._invalidate_server_definition_caches(server.server_id) + release_fetch.set() + await listing + + assert manager.get_listed_tool(server, "turn", caller) is None + + manager._fetch_tools_with_timeout = AsyncMock( + return_value=[MCPTool(name="turn", description="after save", inputSchema={})] + ) + await manager._get_tools_from_server(server=server, user_api_key_auth=user, record_listing=True) + listed = manager.get_listed_tool(server, "turn", caller) + assert listed is not None and listed.description == "after save" + + @pytest.mark.asyncio + async def test_update_server_refreshing_openapi_tools_drops_a_listing_recorded_during_the_spec_fetch(self): + """An OpenAPI server's registry entries are rebuilt after the save is published, so a listing that + records while the spec is fetched holds the pre-save entries; the catalog is dropped again once the + registry is current.""" + manager = MCPServerManager() + old = MCPServer( + server_id="srv", name="srv", transport=MCPTransport.http, url="http://old", spec_path="/old.json" + ) + manager.registry[old.server_id] = old + new = MCPServer( + server_id="srv", name="srv", transport=MCPTransport.http, url="http://new", spec_path="/new.json" + ) + caller = ListedToolsCaller(user_api_key_auth=UserAPIKeyAuth(api_key="sk-litellm", user_id="lister")) + + async def register_while_a_listing_records(server: MCPServer, *, initialize_mapping: bool = True) -> None: + manager._record_listed_tools( + server, + [MCPTool(name="search", description="pre-save", inputSchema={})], + caller, + manager._listed_tools_generations.get(server.server_id, 0), + ) + + manager.build_mcp_server_from_table = AsyncMock(return_value=new) + manager._maybe_register_openapi_tools = register_while_a_listing_records + manager.prime_oauth_metadata_discovery = MagicMock() + record = LiteLLM_MCPServerTable( + server_id="srv", server_name="srv", url="http://new", transport=MCPTransport.http + ) + + await manager.update_server(record) + + assert manager.registry["srv"] is new + assert manager.get_listed_tool(new, "search", caller) is None + + @pytest.mark.asyncio + @pytest.mark.parametrize("already_registered", [False, True], ids=["add_server", "update_server"]) + async def test_openapi_spec_re_read_keeps_discovery_and_oauth_metadata_filled_during_the_fetch( + self, already_registered: bool + ): + """The listed-tool catalog recorded during the spec fetch holds pre-save entries, but a prompts + discovery or OAuth protected-resource fetch answered in that window already saw the published + definition; dropping those too sends the next request upstream again.""" + manager = MCPServerManager() + if already_registered: + manager.registry["srv"] = MCPServer( + server_id="srv", name="srv", transport=MCPTransport.http, url="http://old", spec_path="/old.json" + ) + new = MCPServer( + server_id="srv", name="srv", transport=MCPTransport.http, url="http://new", spec_path="/new.json" + ) + caller = ListedToolsCaller(user_api_key_auth=UserAPIKeyAuth(api_key="sk-litellm", user_id="lister")) + metadata_key: Final = (new.server_id, new.url) + prompt_fetches = 0 + + async def fetch_prompts() -> list[Prompt]: + nonlocal prompt_fetches + prompt_fetches += 1 + return [Prompt(name="greet")] + + async def register_while_discovery_fills(server: MCPServer, *, initialize_mapping: bool = True) -> None: + manager._record_listed_tools( + server, + [MCPTool(name="search", description="pre-save", inputSchema={})], + caller, + manager._listed_tools_generations.get(server.server_id, 0), + ) + await manager._prompt_discovery_cache.get((server.server_id, None), fetch_prompts) + discoverable_endpoints._OAUTH_METADATA_CACHE[metadata_key] = (time.time() + 300, {"resource": new.url}) + + manager.build_mcp_server_from_table = AsyncMock(return_value=new) + manager._maybe_register_openapi_tools = register_while_discovery_fills + manager.prime_oauth_metadata_discovery = MagicMock() + record = LiteLLM_MCPServerTable( + server_id="srv", server_name="srv", url="http://new", transport=MCPTransport.http + ) + save = manager.update_server if already_registered else manager.add_server + + try: + await save(record) + + assert manager.registry["srv"] is new + assert manager.get_listed_tool(new, "search", caller) is None + prompts = await manager._prompt_discovery_cache.get((new.server_id, None), fetch_prompts) + assert [prompt.name for prompt in prompts] == ["greet"] + assert prompt_fetches == 1, "the prompts list filled after the save was published went upstream again" + cached_metadata = discoverable_endpoints._OAUTH_METADATA_CACHE.get(metadata_key) + assert cached_metadata is not None and cached_metadata[1] == {"resource": new.url} + finally: + discoverable_endpoints._OAUTH_METADATA_CACHE.pop(metadata_key, None) + + @pytest.mark.asyncio + async def test_user_oauth_refresh_keeps_listed_tools(self): + manager = MCPServerManager() + server = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + manager._record_listed_tools(server, [MCPTool(name="echo", description="shared", inputSchema={})], None) + + await manager.invalidate_user_oauth_token_cache("alice", server.server_id) + + listed = manager.get_listed_tool(server, "echo") + assert listed is not None and listed.description == "shared" + + def test_per_caller_server_keeps_listed_tools_per_identity(self): + manager = MCPServerManager() + server = MCPServer( + server_id="srv", + name="srv", + transport=MCPTransport.http, + url="http://srv", + auth_type=MCPAuth.oauth2_token_exchange, + ) + alice = UserAPIKeyAuth(user_id="alice", token="hashed-alice") + bob = UserAPIKeyAuth(user_id="bob", token="hashed-bob") + alice_schema = {"type": "object", "properties": {"path": {"type": "string"}}} + bob_schema = {"type": "object", "properties": {"path": {"type": "string"}, "site": {"type": "string"}}} + manager._record_listed_tools( + server, + [MCPTool(name="read", description="alice view", inputSchema=alice_schema)], + ListedToolsCaller(user_api_key_auth=alice), + ) + manager._record_listed_tools( + server, + [MCPTool(name="read", description="bob view", inputSchema=bob_schema)], + ListedToolsCaller(user_api_key_auth=bob), + ) + + alice_tool = manager.get_listed_tool(server, "read", ListedToolsCaller(user_api_key_auth=alice)) + bob_tool = manager.get_listed_tool(server, "read", ListedToolsCaller(user_api_key_auth=bob)) + assert alice_tool is not None and (alice_tool.description, alice_tool.input_schema) == ( + "alice view", + alice_schema, + ) + assert bob_tool is not None and (bob_tool.description, bob_tool.input_schema) == ("bob view", bob_schema) + carol = ListedToolsCaller(user_api_key_auth=UserAPIKeyAuth(user_id="carol", token="k")) + assert manager.get_listed_tool(server, "read", carol) is None + + shared = MCPServer(server_id="shared", name="shared", transport=MCPTransport.http, url="http://shared") + manager._record_listed_tools( + shared, + [MCPTool(name="echo", description="everyone", inputSchema={})], + ListedToolsCaller(user_api_key_auth=alice), + ) + for_bob = manager.get_listed_tool(shared, "echo", ListedToolsCaller(user_api_key_auth=bob)) + assert for_bob is None, "keyed callers get their own slot even on servers without upstream per-user auth" + anonymous = manager.get_listed_tool(shared, "echo") + assert anonymous is None + + @pytest.mark.parametrize( + ("server_kwargs", "caller_a", "caller_b"), + [ + pytest.param( + {"extra_headers": ["X-Workspace"]}, + ListedToolsCaller(raw_headers={"x-workspace": "A"}), + ListedToolsCaller(raw_headers={"X-Workspace": "B"}), + id="forwarded-header", + ), + pytest.param( + {"auth_type": MCPAuth.true_passthrough}, + ListedToolsCaller(raw_headers={"authorization": "Bearer upstream-a"}), + ListedToolsCaller(raw_headers={"authorization": "Bearer upstream-b"}), + id="anonymous-passthrough-bearer", + ), + pytest.param( + {"auth_type": MCPAuth.bearer_token}, + ListedToolsCaller(mcp_auth_header="byok-a"), + ListedToolsCaller(mcp_auth_header="byok-b"), + id="per-server-auth-header", + ), + pytest.param( + {"auth_type": MCPAuth.oauth2_token_exchange}, + ListedToolsCaller( + user_api_key_auth=UserAPIKeyAuth(user_id="team-bot", token="hashed-shared"), + raw_headers={"x-litellm-api-key": "sk-shared", "authorization": "Bearer entra-alice"}, + ), + ListedToolsCaller( + user_api_key_auth=UserAPIKeyAuth(user_id="team-bot", token="hashed-shared"), + raw_headers={"x-litellm-api-key": "sk-shared", "authorization": "Bearer entra-bob"}, + ), + id="shared-key-different-obo-subjects", + ), + pytest.param( + {"transport": MCPTransport.stdio, "command": "srv", "env": {"WS": "${X-WS}"}}, + ListedToolsCaller(raw_headers={"X-WS": "A"}), + ListedToolsCaller(raw_headers={"X-WS": "B"}), + id="header-driven-stdio-env", + ), + ], + ) + def test_upstream_identity_inputs_keep_listed_tools_apart(self, server_kwargs, caller_a, caller_b): + manager = MCPServerManager() + server = MCPServer( + **{"server_id": "srv", "name": "srv", "transport": MCPTransport.http, "url": "http://srv", **server_kwargs} + ) + manager._record_listed_tools(server, [MCPTool(name="turn", description="Catalog A", inputSchema={})], caller_a) + manager._record_listed_tools(server, [MCPTool(name="turn", description="Catalog B", inputSchema={})], caller_b) + + for_a = manager.get_listed_tool(server, "turn", caller_a) + for_b = manager.get_listed_tool(server, "turn", caller_b) + assert for_a is not None and for_a.description == "Catalog A" + assert for_b is not None and for_b.description == "Catalog B" + assert manager.get_listed_tool(server, "turn", ListedToolsCaller()) is None + + def test_shared_server_ignores_headers_it_never_forwards(self): + manager = MCPServerManager() + server = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + manager._record_listed_tools( + server, + [MCPTool(name="turn", description="everyone", inputSchema={})], + ListedToolsCaller(raw_headers={"authorization": "Bearer sk-litellm", "x-workspace": "A"}), + ) + + other = ListedToolsCaller(raw_headers={"authorization": "Bearer sk-other", "x-workspace": "B"}) + listed = manager.get_listed_tool(server, "turn", other) + assert listed is not None and listed.description == "everyone" + + @pytest.mark.asyncio + async def test_byok_listing_never_reads_the_credential_store(self): + """tools/list keys the caller's catalog slot by what the client supplied plus the caller's key. + Resolving the stored BYOK credential for that would fail every REST listing while the DB is + down and would seed a per-worker cache the next tools/call trusts over the store.""" + manager = MCPServerManager() + server = MCPServer( + server_id="byok-cold", + name="byok_cold", + transport=MCPTransport.http, + url="http://byok-cold", + is_byok=True, + auth_type=MCPAuth.api_key, + ) + user = UserAPIKeyAuth(api_key="sk-litellm", user_id="byok-cold-user") + manager._create_mcp_client = AsyncMock(return_value=AsyncMock()) + manager._fetch_tools_with_timeout = AsyncMock( + return_value=[MCPTool(name="turn", description="listed while db down", inputSchema={})] + ) + + with ( + patch("litellm.proxy.proxy_server.prisma_client", MagicMock()), + patch( + "litellm.proxy._experimental.mcp_server.db.get_user_credential", + AsyncMock(side_effect=RuntimeError("DB DOWN")), + ), + ): + await manager._get_tools_from_server(server=server, user_api_key_auth=user, record_listing=True) + + listed = manager.get_listed_tool(server, "turn", listed_tools_caller_for(server, user, None, None, None, None)) + assert listed is not None and listed.description == "listed while db down" + + @pytest.mark.parametrize( + ("list_header", "call_kwargs"), + [ + pytest.param( + None, {"mcp_auth_header": "stored-secret", "catalog_auth_header": None}, id="execute-mcp-tool" + ), + pytest.param(None, {"mcp_auth_header": None}, id="responses-api"), + pytest.param("Bearer hdr", {"mcp_auth_header": "Bearer hdr"}, id="client-supplied-header"), + ], + ) + @pytest.mark.asyncio + async def test_byok_tools_call_reads_the_slot_the_clients_own_header_listed( + self, list_header: str | None, call_kwargs: dict[str, str | None] + ): + """A REST listing records under the header the client sent (none here). tools/call then swaps the + stored credential in, either before reaching ``call_tool`` (``execute_mcp_tool``) or inside it (the + Responses API), and must still read that slot rather than one keyed by the credential.""" + from litellm.proxy._experimental.mcp_server.byok_credential_cache import ( + byok_credential_cache_key, + cache_byok_credential, + ) + from litellm.proxy._experimental.mcp_server.operations import byok_credential_cache + + manager = MCPServerManager() + server = MCPServer( + server_id="byok-catalog", + name="byok_catalog", + transport=MCPTransport.http, + url="http://byok-catalog", + is_byok=True, + ) + manager.registry = {"byok-catalog": server} + user = UserAPIKeyAuth(api_key="sk-litellm", user_id="byok-user") + mock_client = AsyncMock() + mock_client.call_tool.return_value = MagicMock(spec=CallToolResult, content=[], isError=False) + manager._create_mcp_client = AsyncMock(return_value=mock_client) + manager._fetch_tools_with_timeout = AsyncMock( + return_value=[MCPTool(name="turn", description="stored cred catalog", inputSchema={})] + ) + proxy_logging_obj = MagicMock() + proxy_logging_obj._create_mcp_request_object_from_kwargs = MagicMock(return_value={}) + proxy_logging_obj._convert_mcp_to_llm_format = MagicMock(return_value={}) + proxy_logging_obj.pre_call_hook = AsyncMock(return_value={}) + proxy_logging_obj.during_call_hook = AsyncMock(return_value=None) + cache_byok_credential("byok-user", "byok-catalog", "stored-secret") + try: + await manager._get_tools_from_server( + server=server, mcp_auth_header=list_header, user_api_key_auth=user, record_listing=True + ) + listed = manager.get_listed_tool( + server, "turn", listed_tools_caller_for(server, user, list_header, None, None, None) + ) + assert listed is not None and listed.description == "stored cred catalog" + + await manager.call_tool( + server_name="byok_catalog", + name="turn", + arguments={}, + user_api_key_auth=user, + proxy_logging_obj=proxy_logging_obj, + **call_kwargs, + ) + finally: + byok_credential_cache.delete_cache(byok_credential_cache_key("byok-user", "byok-catalog")) + + hook_kwargs = proxy_logging_obj._create_mcp_request_object_from_kwargs.call_args.args[0] + assert hook_kwargs["tool_description"] == "stored cred catalog" + + @pytest.mark.asyncio + async def test_byok_supplied_header_lists_without_credential_validation(self): + manager = MCPServerManager() + server = MCPServer( + server_id="byok-catalog", + name="byok_catalog", + transport=MCPTransport.http, + url="http://byok-catalog", + is_byok=True, + ) + manager._create_mcp_client = AsyncMock(return_value=AsyncMock()) + manager._fetch_tools_with_timeout = AsyncMock( + return_value=[MCPTool(name="turn", description="t", inputSchema={})] + ) + + with patch("litellm.proxy.proxy_server.prisma_client", None): + await manager._get_tools_from_server( + server=server, + mcp_auth_header="Bearer hdr", + user_api_key_auth=UserAPIKeyAuth(api_key="sk-litellm"), + record_listing=True, + ) + + caller: Final = ListedToolsCaller( + user_api_key_auth=UserAPIKeyAuth(api_key="sk-litellm"), mcp_auth_header="Bearer hdr" + ) + listed = manager.get_listed_tool(server, "turn", caller) + assert listed is not None and listed.description == "t" + assert manager._create_mcp_client.await_args.kwargs["mcp_auth_header"] == "Bearer hdr" + + @pytest.mark.parametrize( + "server_auth", + [ + pytest.param( + { + "auth_type": MCPAuth.oauth2, + "client_id": "cid", + "client_secret": "csec", + "token_url": "http://cc1/token", + }, + id="oauth2", + ), + pytest.param({"auth_type": MCPAuth.api_key, "authentication_token": "STATIC-ADMIN-TOKEN"}, id="api_key"), + pytest.param( + {"auth_type": MCPAuth.bearer_token, "authentication_token": "STATIC-ADMIN-TOKEN"}, id="bearer_token" + ), + pytest.param({"auth_type": MCPAuth.none}, id="none"), + ], + ) + @pytest.mark.asyncio + async def test_byok_listing_keys_the_catalog_by_the_caller_and_never_touches_the_stored_secret( + self, server_auth: dict[str, object] + ): + """The caller's key plus what the caller supplied (nothing here) keys the catalog slot tools/call + reads, even with the stored BYOK secret at hand in the cache, and tools/list sends upstream exactly + what the caller supplied, so the static token, the M2M mint and MCPJWTSigner all behave as they + did before the catalog existed, whatever the auth_type.""" + from litellm.proxy._experimental.mcp_server.byok_credential_cache import ( + byok_credential_cache_key, + cache_byok_credential, + ) + from litellm.proxy._experimental.mcp_server.operations import byok_credential_cache + + manager = MCPServerManager() + server = MCPServer( + server_id="cc1", + name="cc1", + transport=MCPTransport.http, + url="http://cc1", + is_byok=True, + **server_auth, + ) + alice = UserAPIKeyAuth(api_key="sk-alice", user_id="alice") + manager._create_mcp_client = AsyncMock(return_value=AsyncMock()) + manager._fetch_tools_with_timeout = AsyncMock( + return_value=[MCPTool(name="echo", description="listed catalog", inputSchema={})] + ) + signer_headers = AsyncMock(return_value={"Authorization": "Bearer signed-jwt"}) + cache_byok_credential("alice", "cc1", "BYOK-ALICE-SECRET") + try: + with ( + patch( # test-quality-ok: the signer is a process-wide singleton the manager reads, no injection seam + "litellm.proxy.guardrails.guardrail_hooks.mcp_jwt_signer.mcp_jwt_signer.get_mcp_jwt_signer", + return_value=MagicMock(), + ), + patch( # test-quality-ok: same singleton's header injection, asserted on by call + "litellm.proxy.guardrails.guardrail_hooks.mcp_jwt_signer.mcp_jwt_signer.inject_mcp_jwt_headers_for_upstream", + signer_headers, + ), + ): + await manager._get_tools_from_server(server=server, user_api_key_auth=alice, record_listing=True) + finally: + byok_credential_cache.delete_cache(byok_credential_cache_key("alice", "cc1")) + + client_kwargs = manager._create_mcp_client.await_args.kwargs + assert client_kwargs["mcp_auth_header"] is None, client_kwargs + assert client_kwargs["extra_headers"] == {"Authorization": "Bearer signed-jwt"} + signer_headers.assert_awaited_once() + listed = manager.get_listed_tool(server, "echo", ListedToolsCaller(user_api_key_auth=alice)) + assert listed is not None and listed.description == "listed catalog" + + @pytest.mark.parametrize( + ("signer", "static_headers"), + [ + pytest.param(MagicMock(), None, id="signer"), + pytest.param(MagicMock(), {"Authorization": "Bearer admin-token"}, id="static-authorization"), + pytest.param(None, None, id="no-signer"), + ], + ) + def test_keyed_callers_always_list_into_their_own_slot(self, signer, static_headers): + """The catalog is guardrail-shaped per key, so a keyed caller never reads another caller's + listing regardless of the signer or static authorization configuration.""" + manager = MCPServerManager() + server = MCPServer( + server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv", static_headers=static_headers + ) + alice = ListedToolsCaller(user_api_key_auth=UserAPIKeyAuth(user_id="alice", token="hashed-alice")) + bob = ListedToolsCaller(user_api_key_auth=UserAPIKeyAuth(user_id="bob", token="hashed-bob")) + + with patch( # test-quality-ok: the signer is a process-wide singleton the manager reads, no injection seam + "litellm.proxy.guardrails.guardrail_hooks.mcp_jwt_signer.mcp_jwt_signer.get_mcp_jwt_signer", + return_value=signer, + ): + manager._record_listed_tools( + server, [MCPTool(name="turn", description="alice view", inputSchema={})], alice + ) + assert manager.get_listed_tool(server, "turn", bob) is None + + for_alice = manager.get_listed_tool(server, "turn", alice) + assert for_alice is not None and for_alice.description == "alice view" + + def test_signed_server_slot_splits_on_the_callers_key_not_only_the_user(self): + """Two keys sharing a user_id get different signed JWTs, so they split; the same key + presented again lands on its own slot.""" + manager = MCPServerManager() + server = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + alice = ListedToolsCaller(user_api_key_auth=UserAPIKeyAuth(user_id="same-user", api_key="sk-alpha")) + bob = ListedToolsCaller(user_api_key_auth=UserAPIKeyAuth(user_id="same-user", api_key="sk-beta")) + + with patch( # test-quality-ok: the signer is a process-wide singleton the manager reads, no injection seam + "litellm.proxy.guardrails.guardrail_hooks.mcp_jwt_signer.mcp_jwt_signer.get_mcp_jwt_signer", + return_value=MagicMock(), + ): + manager._record_listed_tools(server, [MCPTool(name="turn", description="slot a", inputSchema={})], alice) + assert manager.get_listed_tool(server, "turn", bob) is None + + same_key = ListedToolsCaller(user_api_key_auth=UserAPIKeyAuth(user_id="same-user", api_key="sk-alpha")) + listed = manager.get_listed_tool(server, "turn", same_key) + + assert listed is not None and listed.description == "slot a" + + def test_listed_tools_slot_is_split_per_team_for_keyless_callers(self): + """A team-only JWT admits a caller with neither a key nor a user, so the team keys the slot.""" + manager: Final = MCPServerManager() + server: Final = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + team_one: Final = ListedToolsCaller( + user_api_key_auth=UserAPIKeyAuth(api_key=None, user_id=None, team_id="team-one") + ) + team_two: Final = ListedToolsCaller( + user_api_key_auth=UserAPIKeyAuth(api_key=None, user_id=None, team_id="team-two") + ) + manager._record_listed_tools( + server, [MCPTool(name="foo", description="Fetch rows FLAGWORD", inputSchema={})], team_one + ) + + assert manager.get_listed_tool(server, "foo", team_two) is None + listed: Final = manager.get_listed_tool(server, "foo", team_one) + assert listed is not None and listed.description == "Fetch rows FLAGWORD" + + def test_listed_tools_slot_is_split_per_team_for_the_same_keyless_user(self): + """One JWT user acting in two teams is served two team-shaped catalogs, so each team is a slot.""" + manager: Final = MCPServerManager() + server: Final = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + alice_in_one: Final = ListedToolsCaller( + user_api_key_auth=UserAPIKeyAuth(api_key=None, user_id="alice", team_id="team-one") + ) + alice_in_two: Final = ListedToolsCaller( + user_api_key_auth=UserAPIKeyAuth(api_key=None, user_id="alice", team_id="team-two") + ) + manager._record_listed_tools( + server, [MCPTool(name="foo", description="Fetch rows FLAGWORD", inputSchema={})], alice_in_one + ) + + assert manager.get_listed_tool(server, "foo", alice_in_two) is None + listed: Final = manager.get_listed_tool(server, "foo", alice_in_one) + assert listed is not None and listed.description == "Fetch rows FLAGWORD" + + def test_listed_tools_slot_is_split_by_the_admission_bearer_of_keyless_callers_without_a_user(self): + """Two team-only JWT callers of one team differ only in the JWT they were admitted with, so that + credential keys the slot, on a server that never forwards it.""" + manager: Final = MCPServerManager() + server: Final = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + alice: Final = ListedToolsCaller( + user_api_key_auth=UserAPIKeyAuth(api_key=None, user_id=None, team_id="team-one"), + raw_headers={"authorization": "Bearer jwt-alice"}, + ) + bob: Final = ListedToolsCaller( + user_api_key_auth=UserAPIKeyAuth(api_key=None, user_id=None, team_id="team-one"), + raw_headers={"authorization": "Bearer jwt-bob"}, + ) + manager._record_listed_tools(server, [MCPTool(name="foo", description="alice view", inputSchema={})], alice) + + assert manager.get_listed_tool(server, "foo", bob) is None + listed: Final = manager.get_listed_tool(server, "foo", alice) + assert listed is not None and listed.description == "alice view" + + @pytest.mark.parametrize( + ("server_kwargs", "forwards_bearer"), + [ + pytest.param( + {"auth_type": MCPAuth.oauth2, "delegate_auth_to_upstream": True, "oauth2_flow": "authorization_code"}, + True, + id="oauth2-delegated-to-upstream", + ), + pytest.param({"auth_type": MCPAuth.oauth_delegate}, True, id="oauth-delegate"), + pytest.param({"auth_type": MCPAuth.true_passthrough}, True, id="true-passthrough"), + pytest.param({"auth_type": MCPAuth.oauth2_token_exchange}, True, id="token-exchange"), + pytest.param( + {"auth_type": MCPAuth.none, "extra_headers": ["Authorization"], "oauth_passthrough": True}, + True, + id="oauth-passthrough", + ), + pytest.param({}, False, id="plain"), + pytest.param( + {"auth_type": MCPAuth.oauth2, "oauth2_flow": "authorization_code"}, + False, + id="oauth2-gateway-managed", + ), + pytest.param( + { + "auth_type": MCPAuth.oauth2, + "oauth2_flow": "client_credentials", + "delegate_auth_to_upstream": True, + "client_id": "gateway", + "client_secret": "secret", + "token_url": "http://idp/token", + }, + False, + id="oauth2-client-credentials", + ), + ], + ) + def test_listed_tools_slot_is_split_by_the_forwarded_bearer_on_servers_that_forward_it( + self, server_kwargs: dict[str, object], forwards_bearer: bool + ): + """Two callers sharing one key but carrying different upstream bearers are served two upstream + catalogs exactly on the servers whose egress forwards or exchanges that bearer.""" + manager: Final = MCPServerManager() + server: Final = MCPServer( + **{"server_id": "dg", "name": "dg", "transport": MCPTransport.http, "url": "http://dg", **server_kwargs} + ) + caller_a: Final = ListedToolsCaller( + user_api_key_auth=UserAPIKeyAuth(api_key="sk-master"), + raw_headers={"x-litellm-api-key": "Bearer sk-master", "authorization": "Bearer UP-A"}, + ) + caller_b: Final = ListedToolsCaller( + user_api_key_auth=UserAPIKeyAuth(api_key="sk-master"), + raw_headers={"x-litellm-api-key": "Bearer sk-master", "authorization": "Bearer UP-B"}, + ) + manager._record_listed_tools( + server, [MCPTool(name="lookup", description="Workspace A lookup FLAGWORD", inputSchema={})], caller_a + ) + + for_b: Final = manager.get_listed_tool(server, "lookup", caller_b) + assert (for_b is None) is forwards_bearer + for_a: Final = manager.get_listed_tool(server, "lookup", caller_a) + assert for_a is not None and for_a.description == "Workspace A lookup FLAGWORD" + + @pytest.mark.asyncio + async def test_call_tool_hands_hooks_the_catalog_the_same_forwarded_headers_listed(self): + manager = MCPServerManager() + server = MCPServer( + server_id="catalog", + name="catalog", + transport=MCPTransport.http, + url="http://catalog", + extra_headers=["X-Workspace"], + ) + manager.registry = {"catalog": server} + catalogs = { + "A": [ + MCPTool( + name="turn", description="Catalog A", inputSchema={"properties": {"turn": {"description": "A"}}} + ) + ], + "B": [ + MCPTool( + name="turn", description="Catalog B", inputSchema={"properties": {"turn": {"description": "B"}}} + ) + ], + } + mock_client = AsyncMock() + mock_client.call_tool.return_value = MagicMock(spec=CallToolResult, content=[], isError=False) + manager._create_mcp_client = AsyncMock(return_value=mock_client) + manager._fetch_tools_with_timeout = AsyncMock(side_effect=lambda client, name: catalogs[client.workspace]) + for workspace in ("A", "B"): + manager._create_mcp_client.return_value.workspace = workspace + await manager._get_tools_from_server( + server=server, + extra_headers={"X-Workspace": workspace}, + raw_headers={"x-workspace": workspace, "authorization": "Bearer sk-litellm"}, + user_api_key_auth=UserAPIKeyAuth(api_key="sk-litellm", user_id="shared-key"), + record_listing=True, + ) + + proxy_logging_obj = MagicMock() + proxy_logging_obj._create_mcp_request_object_from_kwargs = MagicMock(return_value={}) + proxy_logging_obj._convert_mcp_to_llm_format = MagicMock(return_value={}) + proxy_logging_obj.pre_call_hook = AsyncMock(return_value={}) + proxy_logging_obj.during_call_hook = AsyncMock(return_value=None) + await manager.call_tool( + server_name="catalog", + name="turn", + arguments={"turn": "A-1"}, + user_api_key_auth=UserAPIKeyAuth(api_key="sk-litellm", user_id="shared-key"), + proxy_logging_obj=proxy_logging_obj, + raw_headers={"x-workspace": "A", "authorization": "Bearer sk-litellm"}, + ) + + hook_kwargs = proxy_logging_obj._create_mcp_request_object_from_kwargs.call_args.args[0] + assert (hook_kwargs["tool_description"], hook_kwargs["tool_input_schema"]) == ( + "Catalog A", + {"properties": {"turn": {"description": "A"}}}, + ) + + def test_per_caller_listed_tools_evict_oldest_caller_and_keep_shared(self): + from litellm.proxy._experimental.mcp_server.mcp_server_manager import _LISTED_TOOLS_CALLERS_PER_SERVER + + manager = MCPServerManager() + server = MCPServer( + server_id="srv", + name="srv", + transport=MCPTransport.http, + url="http://srv", + auth_type=MCPAuth.oauth2_token_exchange, + ) + manager._record_listed_tools(server, [MCPTool(name="read", description="shared", inputSchema={})], None) + callers = [ + ListedToolsCaller(user_api_key_auth=UserAPIKeyAuth(user_id=f"u{i}", api_key=f"k{i}")) + for i in range(_LISTED_TOOLS_CALLERS_PER_SERVER + 1) + ] + for caller in callers: + manager._record_listed_tools( + server, + [MCPTool(name="read", description=caller.user_api_key_auth.user_id, inputSchema={})], + caller, + ) + manager._record_listed_tools(server, [MCPTool(name="read", description="u1 again", inputSchema={})], callers[1]) + + assert manager.get_listed_tool(server, "read", callers[0]) is None + second = manager.get_listed_tool(server, "read", callers[1]) + assert second is not None and second.description == "u1 again" + newest = manager.get_listed_tool(server, "read", callers[-1]) + assert newest is not None and newest.description == callers[-1].user_api_key_auth.user_id + assert len(manager._listed_tools_by_server_id[server.server_id]) == _LISTED_TOOLS_CALLERS_PER_SERVER + 1 + shared = manager.get_listed_tool(server, "read") + assert shared is not None and shared.description == "shared" + + @pytest.mark.asyncio + @pytest.mark.parametrize("add_prefix", [True, False]) + async def test_openapi_listing_records_listed_tools(self, add_prefix): + from litellm.proxy._experimental.mcp_server.tool_registry import global_mcp_tool_registry + + server = MCPServer( + server_id="petstore-id", + name="petstore", + alias="petstore", + transport=MCPTransport.http, + url=None, + spec_path="/spec.yaml", + ) + manager = MCPServerManager() + manager._create_mcp_client = AsyncMock(return_value=AsyncMock()) + + async def _handler(**kwargs): + return None + + global_mcp_tool_registry.unregister_tools_with_prefix("petstore-") + global_mcp_tool_registry.register_tool( + name="petstore-list_pets", + description="List pets", + input_schema={"type": "object", "properties": {"limit": {"type": "integer"}}}, + handler=_handler, + ) + try: + listed = await manager._get_tools_from_server(server=server, add_prefix=add_prefix, record_listing=True) + finally: + global_mcp_tool_registry.unregister_tools_with_prefix("petstore-") + + assert [t.name for t in listed] == ["petstore-list_pets" if add_prefix else "list_pets"] + tool = manager.get_listed_tool(server, "list_pets") + assert tool is not None and tool.description == "List pets" + assert tool.input_schema["properties"] == {"limit": {"type": "integer"}} + + @pytest.mark.asyncio + async def test_openapi_listing_ignores_overlapping_server_prefix(self): + from litellm.proxy._experimental.mcp_server.tool_registry import global_mcp_tool_registry + + server = MCPServer( + server_id="pet-id", + name="pet", + alias="pet", + transport=MCPTransport.http, + url=None, + spec_path="/spec.yaml", + ) + manager = MCPServerManager() + manager._create_mcp_client = AsyncMock(return_value=AsyncMock()) + + async def _handler(**kwargs): + return None + + for prefix in ("pet-", "petstore-"): + global_mcp_tool_registry.unregister_tools_with_prefix(prefix) + global_mcp_tool_registry.register_tool( + name="pet-petstore-list", + description="Local pet tool", + input_schema={"type": "object", "properties": {"limit": {"type": "integer"}}}, + handler=_handler, + ) + global_mcp_tool_registry.register_tool( + name="petstore-list", + description="Foreign petstore tool", + input_schema={"type": "object", "properties": {"status": {"type": "string"}}}, + handler=_handler, + ) + try: + listed = await manager._get_tools_from_server(server=server, add_prefix=True, record_listing=True) + finally: + for prefix in ("pet-", "petstore-"): + global_mcp_tool_registry.unregister_tools_with_prefix(prefix) + + assert [t.name for t in listed] == ["pet-petstore-list"] + tool = manager.get_listed_tool(server, "petstore-list") + assert tool is not None and tool.description == "Local pet tool" + assert tool.input_schema["properties"] == {"limit": {"type": "integer"}} + + @pytest.mark.asyncio + @pytest.mark.parametrize("openapi", [False, True], ids=["remote", "openapi"]) + async def test_get_tools_from_server_records_the_catalog_only_when_asked_to(self, openapi): + """The startup fill, the implicit pre-call listing and the pin snapshot reuse this fetch without + serving its result, so only a listing that asks to be recorded sets what tools/call hooks see.""" + from litellm.proxy._experimental.mcp_server.tool_registry import global_mcp_tool_registry + + if openapi: + server = MCPServer( + server_id="srv", name="srv", alias="srv", transport=MCPTransport.http, url=None, spec_path="/spec.yaml" + ) + manager = MCPServerManager() + manager._create_mcp_client = AsyncMock(return_value=AsyncMock()) + global_mcp_tool_registry.unregister_tools_with_prefix("srv-") + global_mcp_tool_registry.register_tool( + name="srv-echo", description="Echoes", input_schema={"type": "object"}, handler=lambda **kwargs: None + ) + else: + server = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + manager = _catalog_manager(MCPTool(name="echo", description="Echoes", inputSchema={"type": "object"})) + user = UserAPIKeyAuth(api_key="sk-litellm", user_id="lister") + + try: + listed = await manager._get_tools_from_server(server=server, user_api_key_auth=user) + assert [t.name for t in listed] == ["srv-echo"] + assert server.server_id not in manager._listed_tools_by_server_id + + await manager._get_tools_from_server(server=server, user_api_key_auth=user, record_listing=True) + finally: + global_mcp_tool_registry.unregister_tools_with_prefix("srv-") + + recorded = manager.get_listed_tool(server, "echo", ListedToolsCaller(user_api_key_auth=user)) + assert recorded is not None and recorded.description == "Echoes" + + @pytest.mark.asyncio + async def test_list_tools_records_the_served_catalog(self): + manager = _catalog_manager(MCPTool(name="echo", description="Echoes", inputSchema={"type": "object"})) + server = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + manager.registry = {"srv": server} + manager.get_allowed_mcp_servers = AsyncMock(return_value=["srv"]) + user = UserAPIKeyAuth(api_key="sk-litellm", user_id="lister") + + listed = await manager.list_tools(user_api_key_auth=user) + + assert [t.name for t in listed] == ["srv-echo"] + recorded = manager.get_listed_tool(server, "echo", ListedToolsCaller(user_api_key_auth=user)) + assert recorded is not None and recorded.description == "Echoes" + + @pytest.mark.asyncio + async def test_startup_tool_name_mapping_records_no_listed_catalog(self): + manager = _catalog_manager(MCPTool(name="echo", description="Echoes", inputSchema={"type": "object"})) + server = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + manager.registry = {"srv": server} + + await manager._initialize_tool_name_to_mcp_server_name_mapping() + + assert manager.server_exposes_tool(server, "echo") is True + assert server.server_id not in manager._listed_tools_by_server_id + assert manager.get_listed_tool(server, "echo") is None + + @pytest.mark.asyncio + async def test_get_tools_for_server_records_no_listed_catalog(self): + manager = _catalog_manager(MCPTool(name="echo", description="Echoes", inputSchema={"type": "object"})) + server = MCPServer(server_id="srv", name="srv", transport=MCPTransport.http, url="http://srv") + manager.registry = {"srv": server} + + listed = await manager.get_tools_for_server("srv") + + assert [t.name for t in listed] == ["srv-echo"] + assert server.server_id not in manager._listed_tools_by_server_id + @pytest.mark.asyncio async def test_get_allowed_mcp_servers_with_user_api_key_auth(self): """ @@ -9739,15 +10870,11 @@ class TestGetPublicMCPServers: if registered_in == "both" else server ) - manager.config_mcp_servers = ( - {server.server_id: config_server} if registered_in in ("config", "both") else {} - ) + manager.config_mcp_servers = {server.server_id: config_server} if registered_in in ("config", "both") else {} manager.registry = {server.server_id: server} if registered_in in ("database", "both") else {} original_server: Final = server.model_dump() original_config_server: Final = config_server.model_dump() - expected_public: Final = registered_in != "neither" and ( - public_ids == [server.server_id] or implicitly_public - ) + expected_public: Final = registered_in != "neither" and (public_ids == [server.server_id] or implicitly_public) with ( patch("litellm.public_mcp_servers", public_ids), @@ -9755,9 +10882,7 @@ class TestGetPublicMCPServers: ): public_servers: Final = manager.get_public_mcp_servers() assert manager.is_mcp_server_public(server.server_id) is expected_public - assert [item.server_id for item in public_servers] == ( - [server.server_id] if expected_public else [] - ) + assert [item.server_id for item in public_servers] == ([server.server_id] if expected_public else []) assert manager.is_mcp_server_public("server-alias") is False assert manager.is_mcp_server_public("missing-server") is False assert manager.is_mcp_server_public(server.server_id, public_ids=frozenset()) is ( @@ -10657,7 +11782,9 @@ class TestOBOConcurrencyLimit: inflight = {"current": 0, "peak": 0} class _ConcurrencyRecordingClient: - async def call_tool(self, params, host_progress_callback=None, raise_on_error=False, allow_input_required=False): + async def call_tool( + self, params, host_progress_callback=None, raise_on_error=False, allow_input_required=False + ): inflight["current"] += 1 inflight["peak"] = max(inflight["peak"], inflight["current"]) try: @@ -12992,7 +14119,9 @@ class TestConfigServerIdPinning: @pytest.mark.asyncio @pytest.mark.parametrize("aliasing_entry_first", [True, False]) - async def test_pinning_own_name_that_is_another_entrys_alias_is_rejected(self, config_only_mcp_manager_factory, aliasing_entry_first: bool): + async def test_pinning_own_name_that_is_another_entrys_alias_is_rejected( + self, config_only_mcp_manager_factory, aliasing_entry_first: bool + ): """A grant naming 'docs_server' reaches both servers unpinned; the pin would narrow it to one.""" manager = config_only_mcp_manager_factory() wiki = ( @@ -13008,7 +14137,9 @@ class TestConfigServerIdPinning: await manager.load_servers_from_config(dict((wiki, docs) if aliasing_entry_first else (docs, wiki))) @pytest.mark.asyncio - async def test_pinning_own_name_that_is_another_entrys_mapped_alias_is_rejected(self, config_only_mcp_manager_factory): + async def test_pinning_own_name_that_is_another_entrys_mapped_alias_is_rejected( + self, config_only_mcp_manager_factory + ): manager = config_only_mcp_manager_factory() with pytest.raises(ValueError, match="server_name or alias of MCP server 'wiki_server'"): @@ -13096,7 +14227,9 @@ class TestConfigServerIdPinning: assert second_round == first_round @pytest.mark.asyncio - async def test_shadow_warning_fires_again_when_the_shadowed_set_changes(self, config_only_mcp_manager_factory, caplog): + async def test_shadow_warning_fires_again_when_the_shadowed_set_changes( + self, config_only_mcp_manager_factory, caplog + ): manager = config_only_mcp_manager_factory() await manager.load_servers_from_config(self._config(server_id="docs-prod-1")) @@ -13267,7 +14400,9 @@ class TestConfigServerIdPinning: assert manager.config_mcp_servers["wiki"].url == "https://example.com/mcp" @pytest.mark.asyncio - async def test_a_row_that_shadows_one_id_still_reports_capturing_another(self, config_only_mcp_manager_factory, caplog): + async def test_a_row_that_shadows_one_id_still_reports_capturing_another( + self, config_only_mcp_manager_factory, caplog + ): """Skipping is per identifier, not per row, so the second collision is not lost.""" manager = config_only_mcp_manager_factory() await manager.load_servers_from_config( @@ -13639,7 +14774,8 @@ async def test_pre_call_tool_check_honors_guardrail_attached_to_key(monkeypatch, ("none", {"Authorization": "Bearer injected"}, "extra-headers", "Bearer injected"), ], ) -async def test_debug_resolution_matches_final_header_conflict_winner(_mcp_request_ctx, +async def test_debug_resolution_matches_final_header_conflict_winner( + _mcp_request_ctx, config: Literal["stored", "static", "none"], extra_headers: dict[str, str] | None, expected_source: str, @@ -13758,12 +14894,16 @@ async def test_debug_reports_legacy_signing_and_non_http_transport( async def test_temporary_server_discovery_reuses_resolved_metadata_without_publishing() -> None: manager: Final = MCPServerManager() server: Final = MCPServer( - server_id="temporary-oauth-discovery", name="temporary", url="https://idp.example.com/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.true_passthrough, + server_id="temporary-oauth-discovery", + name="temporary", + url="https://idp.example.com/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.true_passthrough, ) manager._set_oauth_discovery_deferred(server.server_id, True) metadata: Final = MCPOAuthMetadata( - authorization_url="https://idp.example.com/authorize", token_url="https://idp.example.com/token", + authorization_url="https://idp.example.com/authorize", + token_url="https://idp.example.com/token", registration_url="https://idp.example.com/register", ) with patch.object(manager, "_discover_oauth_metadata_for_server", AsyncMock(return_value=metadata)) as discovery: @@ -13783,13 +14923,18 @@ async def test_temporary_server_discovery_reuses_resolved_metadata_without_publi async def test_repeated_stale_oauth_discovery_is_bounded(auth_type: MCPAuth) -> None: manager: Final = MCPServerManager() server: Final = MCPServer( - server_id="repeated-stale", name="stale", url="https://idp.example.com/mcp", - transport=MCPTransport.http, auth_type=auth_type, oauth2_flow="authorization_code", + server_id="repeated-stale", + name="stale", + url="https://idp.example.com/mcp", + transport=MCPTransport.http, + auth_type=auth_type, + oauth2_flow="authorization_code", ) manager.registry[server.server_id] = server manager._set_oauth_discovery_deferred(server.server_id, True) metadata: Final = MCPOAuthMetadata( - authorization_url="https://idp.example.com/authorize", token_url="https://idp.example.com/token", + authorization_url="https://idp.example.com/authorize", + token_url="https://idp.example.com/token", ) with ( patch.object(manager, "_discover_oauth_metadata_for_server", AsyncMock(return_value=metadata)) as discovery, @@ -13809,13 +14954,20 @@ async def test_repeated_stale_oauth_discovery_is_bounded(auth_type: MCPAuth) -> async def test_stale_discovery_falls_back_to_resolved_registered_server() -> None: manager: Final = MCPServerManager() original: Final = MCPServer( - server_id="resolved-replacement", name="replacement", url="https://old.example.com/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.oauth2, oauth2_flow="authorization_code", + server_id="resolved-replacement", + name="replacement", + url="https://old.example.com/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.oauth2, + oauth2_flow="authorization_code", + ) + replacement: Final = original.model_copy( + update={ + "url": "https://new.example.com/mcp", + "authorization_url": "https://new.example.com/authorize", + "token_url": "https://new.example.com/token", + } ) - replacement: Final = original.model_copy(update={ - "url": "https://new.example.com/mcp", "authorization_url": "https://new.example.com/authorize", - "token_url": "https://new.example.com/token", - }) manager.registry[original.server_id] = replacement assert await manager._rejoin_oauth_metadata_discovery(original, retry_stale=False) is replacement @@ -13823,8 +14975,11 @@ async def test_stale_discovery_falls_back_to_resolved_registered_server() -> Non def test_stale_discovery_cannot_overwrite_new_registered_server() -> None: manager: Final = MCPServerManager() original: Final = MCPServer( - server_id="stale-publication", name="publication", url="https://old.example.com/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.oauth2, + server_id="stale-publication", + name="publication", + url="https://old.example.com/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.oauth2, ) manager._set_oauth_discovery_deferred(original.server_id, True) original_slot: Final = manager._oauth_discovery_slot(original.server_id) @@ -13840,9 +14995,13 @@ def test_stale_discovery_cannot_overwrite_new_registered_server() -> None: async def test_temporary_oauth_discovery_expires_without_more_requests() -> None: manager: Final = MCPServerManager() server: Final = MCPServer( - server_id="expiring-session", name="temporary", url="https://idp.example.com/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.true_passthrough, - authorization_url="https://idp.example.com/authorize", token_url="https://idp.example.com/token", + server_id="expiring-session", + name="temporary", + url="https://idp.example.com/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.true_passthrough, + authorization_url="https://idp.example.com/authorize", + token_url="https://idp.example.com/token", ) manager._set_oauth_discovery_deferred(server.server_id, True) resolved: Final = await manager.ensure_oauth_metadata_discovered(server) @@ -13943,7 +15102,9 @@ async def test_openapi_health_reports_size_limit_as_unknown_and_caches_failure(r result = await manager.health_check_server(server.server_id) cached = await manager.health_check_server(server.server_id) assert result.status == "unknown" - assert result.health_check_error == "OpenAPI specification probe refused: Response exceeds the configured size limit" + assert ( + result.health_check_error == "OpenAPI specification probe refused: Response exceeds the configured size limit" + ) assert cached.health_check_error == result.health_check_error assert cached.last_health_check == result.last_health_check assert route.call_count == 1 @@ -13955,8 +15116,11 @@ async def test_openapi_health_cancellation_does_not_poison_cache(respx_mock, mon monkeypatch.setenv("DISABLE_AIOHTTP_TRANSPORT", "True") manager = MCPServerManager() server = MCPServer( - server_id="cancelled-cache", name="cancelled-cache", transport=MCPTransport.http, - spec_path="https://93.184.216.34/cancelled-cache.json", auth_type=MCPAuth.none, + server_id="cancelled-cache", + name="cancelled-cache", + transport=MCPTransport.http, + spec_path="https://93.184.216.34/cancelled-cache.json", + auth_type=MCPAuth.none, ) manager.registry = {server.server_id: server} started = asyncio.Event() @@ -14085,7 +15249,9 @@ class _DiscoveryUpstream: def _discovery_server() -> MCPServer: - return MCPServer(server_id="discovery", name="discovery", url="https://discovery.example/mcp", transport=MCPTransport.http) + return MCPServer( + server_id="discovery", name="discovery", url="https://discovery.example/mcp", transport=MCPTransport.http + ) @pytest.mark.asyncio @@ -14253,7 +15419,9 @@ async def test_discovery_cache_can_be_disabled(monkeypatch: pytest.MonkeyPatch) assert upstream.initializes == 2 -@pytest.mark.parametrize("value,expected", (("invalid", 60.0), ("nan", 60.0), ("inf", 60.0), ("-1", 60.0), ("12.5", 12.5))) +@pytest.mark.parametrize( + "value,expected", (("invalid", 60.0), ("nan", 60.0), ("inf", 60.0), ("-1", 60.0), ("12.5", 12.5)) +) def test_discovery_cache_ttl_validation(value: str, expected: float, monkeypatch: pytest.MonkeyPatch) -> None: from litellm.proxy._experimental.mcp_server.mcp_server_manager import _mcp_discovery_cache_ttl @@ -14570,26 +15738,45 @@ async def test_discovery_cache_returns_oversized_results_without_retaining_them( class TestProtectedCredentialPreparation: @pytest.mark.asyncio - @pytest.mark.parametrize("auth_type,credential", [ - (MCPAuth.bearer_token, None), - (MCPAuth.bearer_token, "Bearer"), - (MCPAuth.api_key, None), - (MCPAuth.basic, "Basic"), - ]) + @pytest.mark.parametrize( + "auth_type,credential", + [ + (MCPAuth.bearer_token, None), + (MCPAuth.bearer_token, "Bearer"), + (MCPAuth.api_key, None), + (MCPAuth.basic, "Basic"), + ], + ) @pytest.mark.parametrize("dispatch", ["managed", "local"]) async def test_openapi_dispatch_rejects_unusable_effective_credentials( - self, tmp_path: Path, respx_mock: MockRouter, monkeypatch: pytest.MonkeyPatch, - auth_type: MCPAuthType, credential: str | None, dispatch: str, + self, + tmp_path: Path, + respx_mock: MockRouter, + monkeypatch: pytest.MonkeyPatch, + auth_type: MCPAuthType, + credential: str | None, + dispatch: str, ) -> None: from litellm.proxy._experimental.mcp_server.server import _handle_local_mcp_tool from litellm.proxy._experimental.mcp_server.utils import add_server_prefix_to_name, get_server_prefix spec_path: Final = tmp_path / "openapi.json" - spec_path.write_text(json.dumps({"openapi": "3.0.0", "info": {"title": "Auth", "version": "1"}, - "paths": {"/echo": {"get": {"operationId": "echo"}}}})) + spec_path.write_text( + json.dumps( + { + "openapi": "3.0.0", + "info": {"title": "Auth", "version": "1"}, + "paths": {"/echo": {"get": {"operationId": "echo"}}}, + } + ) + ) server: Final = MCPServer( - server_id="dispatch-auth", name="dispatch-auth", url="https://upstream.example", - transport=MCPTransport.http, auth_type=auth_type, authentication_token=credential, + server_id="dispatch-auth", + name="dispatch-auth", + url="https://upstream.example", + transport=MCPTransport.http, + auth_type=auth_type, + authentication_token=credential, ) manager: Final = MCPServerManager() await manager._register_openapi_tools(str(spec_path), server, server.url) @@ -14612,14 +15799,21 @@ class TestProtectedCredentialPreparation: self, transport: MCPTransport, client_secret: str | None, subject: str | None ) -> None: server = MCPServer( - server_id="incomplete-obo", name="incomplete-obo", url="https://upstream.example/mcp", - transport=transport, auth_type=MCPAuth.oauth2_token_exchange, - client_id="gateway", client_secret=client_secret, - token_exchange_endpoint="https://idp.example/token", authentication_token="static-fallback", + server_id="incomplete-obo", + name="incomplete-obo", + url="https://upstream.example/mcp", + transport=transport, + auth_type=MCPAuth.oauth2_token_exchange, + client_id="gateway", + client_secret=client_secret, + token_exchange_endpoint="https://idp.example/token", + authentication_token="static-fallback", ) with pytest.raises(HTTPException) as exc: await MCPServerManager()._create_mcp_client( - server, mcp_auth_header="Bearer override", subject_token=subject, + server, + mcp_auth_header="Bearer override", + subject_token=subject, ) assert exc.value.status_code == (401 if subject is None else 500) assert "static-fallback" not in str(exc.value.detail) @@ -14632,8 +15826,11 @@ class TestProtectedCredentialPreparation: self, auth_type: MCPAuthType, credential: str | dict[str, str] | None ) -> None: server = MCPServer( - server_id="empty-static", name="empty-static", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=auth_type, + server_id="empty-static", + name="empty-static", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=auth_type, ) with pytest.raises(HTTPException) as exc: await MCPServerManager()._create_mcp_client(server, mcp_auth_header=credential) @@ -14641,16 +15838,22 @@ class TestProtectedCredentialPreparation: assert "credential" in str(exc.value.detail).lower() @pytest.mark.asyncio - @pytest.mark.parametrize("auth_type,headers", [ - (MCPAuth.api_key, {"X-API-Key": "key"}), - (MCPAuth.bearer_token, {"Authorization": "Bearer token"}), - ]) + @pytest.mark.parametrize( + "auth_type,headers", + [ + (MCPAuth.api_key, {"X-API-Key": "key"}), + (MCPAuth.bearer_token, {"Authorization": "Bearer token"}), + ], + ) async def test_static_auth_accepts_actual_forwarded_credential( self, auth_type: MCPAuthType, headers: dict[str, str] ) -> None: server = MCPServer( - server_id="header-static", name="header-static", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=auth_type, + server_id="header-static", + name="header-static", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=auth_type, ) client = await MCPServerManager()._create_mcp_client(server, extra_headers=headers) assert client._get_auth_headers() == headers @@ -14659,29 +15862,48 @@ class TestProtectedCredentialPreparation: @pytest.mark.parametrize("auth_type", [MCPAuth.oauth2_token_exchange]) async def test_openapi_protected_auth_rejects_missing_credentials(self, auth_type: MCPAuthType) -> None: server = MCPServer( - server_id="openapi-empty", name="openapi-empty", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=auth_type, + server_id="openapi-empty", + name="openapi-empty", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=auth_type, token_exchange_endpoint="https://idp.example/token", ) with pytest.raises(HTTPException) as exc: await MCPServerManager().resolve_openapi_upstream_auth( - mcp_server=server, oauth2_headers=None, raw_headers=None, mcp_auth_header=None, - user_api_key_auth=None, forwarded_headers=None, + mcp_server=server, + oauth2_headers=None, + raw_headers=None, + mcp_auth_header=None, + user_api_key_auth=None, + forwarded_headers=None, ) assert exc.value.status_code in (401, 500) @pytest.mark.asyncio - @pytest.mark.parametrize("auth_type,slot,value", [ - (MCPAuth.api_key, "X-API-Key", "token"), - (MCPAuth.authorization, "Authorization", "opaque-secret-value"), - (MCPAuth.authorization, "Authorization", "Bearer abc"), - (MCPAuth.authorization, "Authorization", "Custom abc"), - ]) + @pytest.mark.parametrize( + "auth_type,slot,value", + [ + (MCPAuth.api_key, "X-API-Key", "token"), + (MCPAuth.authorization, "Authorization", "opaque-secret-value"), + (MCPAuth.authorization, "Authorization", "Bearer abc"), + (MCPAuth.authorization, "Authorization", "Custom abc"), + ], + ) async def test_raw_static_credentials_are_forwarded_unchanged( - self, auth_type: MCPAuthType, slot: str, value: str, + self, + auth_type: MCPAuthType, + slot: str, + value: str, ) -> None: - server = MCPServer(server_id="raw-key", name="raw-key", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=auth_type, authentication_token=value) + server = MCPServer( + server_id="raw-key", + name="raw-key", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=auth_type, + authentication_token=value, + ) client = await MCPServerManager()._create_mcp_client(server) assert client._resolved_auth is not None request = httpx.Request("GET", server.url) @@ -14695,17 +15917,24 @@ class TestProtectedCredentialPreparation: @pytest.mark.parametrize("value", ["Bearer", "basic", "token", "ApiKey", " bEaReR ", "\tTOKEN\t"]) @pytest.mark.parametrize("source", ["configured", "caller", "forwarded"]) async def test_raw_authorization_rejects_bare_schemes_before_dispatch( - self, respx_mock: MockRouter, value: str, source: str, + self, + respx_mock: MockRouter, + value: str, + source: str, ) -> None: server: Final = MCPServer( - server_id="raw-empty", name="raw-empty", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.authorization, + server_id="raw-empty", + name="raw-empty", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.authorization, authentication_token=value if source == "configured" else None, ) destination: Final = respx_mock.route().respond(200) with pytest.raises(HTTPException, match="requires a usable upstream credential") as exc: await MCPServerManager()._create_mcp_client( - server, mcp_auth_header=value if source == "caller" else None, + server, + mcp_auth_header=value if source == "caller" else None, extra_headers={"Authorization": value} if source == "forwarded" else None, ) assert exc.value.status_code == 500 @@ -14713,9 +15942,15 @@ class TestProtectedCredentialPreparation: @pytest.mark.asyncio async def test_byok_flag_cannot_bypass_incomplete_obo(self) -> None: - server = MCPServer(server_id="obo-byok", name="obo-byok", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.oauth2_token_exchange, is_byok=True, - token_exchange_endpoint="https://idp.example/token") + server = MCPServer( + server_id="obo-byok", + name="obo-byok", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.oauth2_token_exchange, + is_byok=True, + token_exchange_endpoint="https://idp.example/token", + ) with pytest.raises(HTTPException) as exc: await MCPServerManager()._create_mcp_client(server, mcp_auth_header="Bearer override") assert exc.value.status_code == 401 @@ -14723,41 +15958,66 @@ class TestProtectedCredentialPreparation: @pytest.mark.asyncio @pytest.mark.parametrize("configured,override", [(None, "Bearer usable"), ("shared", "Bearer usable")]) async def test_bearer_override_remains_usable(self, configured: str | None, override: str) -> None: - server = MCPServer(server_id="override", name="override", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.bearer_token, authentication_token=configured) + server = MCPServer( + server_id="override", + name="override", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.bearer_token, + authentication_token=configured, + ) client = await MCPServerManager()._create_mcp_client(server, mcp_auth_header=override) assert client._get_auth_headers()["Authorization"] == override @pytest.mark.asyncio @pytest.mark.parametrize("token", [None, "shared"]) async def test_empty_injected_header_cannot_satisfy_protected_auth(self, token: str | None) -> None: - server = MCPServer(server_id="empty-header", name="empty-header", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.bearer_token, authentication_token=token) + server = MCPServer( + server_id="empty-header", + name="empty-header", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.bearer_token, + authentication_token=token, + ) with pytest.raises(HTTPException) as exc: await MCPServerManager()._create_mcp_client(server, extra_headers={"authorization": " "}) assert exc.value.status_code == 500 @pytest.mark.asyncio async def test_custom_slot_uses_its_actual_credential(self) -> None: - server = MCPServer(server_id="custom", name="custom", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.api_key, - upstream_token_header="X-Custom", authentication_token="key") + server = MCPServer( + server_id="custom", + name="custom", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.api_key, + upstream_token_header="X-Custom", + authentication_token="key", + ) client = await MCPServerManager()._create_mcp_client(server, extra_headers={"X-Trace": "trace"}) assert client._credential_slot == "X-Custom" assert await client.discovery_auth_fingerprint() @pytest.mark.asyncio - @pytest.mark.parametrize("static_headers,accepted", [ - ({"apikey": "static-key"}, True), - ({"apikey": ""}, False), - ({"X-Tenant": "tenant"}, True), - ]) + @pytest.mark.parametrize( + "static_headers,accepted", + [ + ({"apikey": "static-key"}, True), + ({"apikey": ""}, False), + ({"X-Tenant": "tenant"}, True), + ], + ) async def test_api_key_carried_by_static_header_passes_fail_closed_check( self, static_headers: dict[str, str], accepted: bool ) -> None: server: Final = MCPServer( - server_id="static-slot", name="static-slot", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.api_key, static_headers=static_headers, + server_id="static-slot", + name="static-slot", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.api_key, + static_headers=static_headers, ) if not accepted: with pytest.raises(HTTPException) as exc: @@ -14769,21 +16029,36 @@ class TestProtectedCredentialPreparation: assert all(request.headers[name] == value for name, value in static_headers.items()) @pytest.mark.asyncio - @pytest.mark.parametrize("static,forwarded,caller", [ - ({"X-API-Key": "static"}, {"x-api-key": "forwarded"}, None), - ({}, {"X-API-Key": "forwarded"}, None), - ({}, None, "ApiKey caller"), - ({"X-API-Key": "static"}, {"Authorization": ""}, None), - ]) + @pytest.mark.parametrize( + "static,forwarded,caller", + [ + ({"X-API-Key": "static"}, {"x-api-key": "forwarded"}, None), + ({}, {"X-API-Key": "forwarded"}, None), + ({}, None, "ApiKey caller"), + ({"X-API-Key": "static"}, {"Authorization": ""}, None), + ], + ) async def test_openapi_static_credentials_remain_supported( - self, respx_mock: MockRouter, monkeypatch: pytest.MonkeyPatch, - static: dict[str, str], forwarded: dict[str, str] | None, caller: str | None + self, + respx_mock: MockRouter, + monkeypatch: pytest.MonkeyPatch, + static: dict[str, str], + forwarded: dict[str, str] | None, + caller: str | None, ) -> None: from litellm.proxy._experimental.mcp_server.openapi_to_mcp_generator import ( - _request_auth_header, _request_extra_headers, create_tool_function, + _request_auth_header, + _request_extra_headers, + create_tool_function, ) + tool: Final = create_tool_function( - "/echo", "get", {}, "https://upstream.example", headers=static, auth_type=MCPAuth.api_key, + "/echo", + "get", + {}, + "https://upstream.example", + headers=static, + auth_type=MCPAuth.api_key, ) monkeypatch.setenv("DISABLE_AIOHTTP_TRANSPORT", "True") destination: Final = respx_mock.get("https://upstream.example/echo").respond(200, text="authenticated") @@ -14817,8 +16092,13 @@ class TestProtectedCredentialPreparation: self.closed = True auth = CancelledAuth() - server = MCPServer(server_id="cancel", name="cancel", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.api_key) + server = MCPServer( + server_id="cancel", + name="cancel", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.api_key, + ) client = MCPClient(server_url=server.url, auth_type=MCPAuth.api_key, resolved_auth=auth) with pytest.raises(asyncio.CancelledError): await prepare_mcp_client(server, client) @@ -14827,8 +16107,14 @@ class TestProtectedCredentialPreparation: @pytest.mark.asyncio @pytest.mark.parametrize("auth_type", [MCPAuth.basic, MCPAuth.token, MCPAuth.authorization]) async def test_other_static_schemes_reject_whitespace_credentials(self, auth_type: MCPAuthType) -> None: - server = MCPServer(server_id="blank-static", name="blank-static", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=auth_type, authentication_token=" ") + server = MCPServer( + server_id="blank-static", + name="blank-static", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=auth_type, + authentication_token=" ", + ) with pytest.raises(HTTPException) as exc: await MCPServerManager()._create_mcp_client(server) assert exc.value.status_code == 500 @@ -14836,8 +16122,13 @@ class TestProtectedCredentialPreparation: @pytest.mark.asyncio @pytest.mark.parametrize("header", ["Basic", "Basic @@@", "Other abc", "Basic QmFzaWM=", "Basic bm8tY29sb24="]) async def test_basic_headers_without_usable_credentials_reject(self, header: str) -> None: - server = MCPServer(server_id="bad-basic", name="bad-basic", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.basic) + server = MCPServer( + server_id="bad-basic", + name="bad-basic", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.basic, + ) with pytest.raises(HTTPException) as exc: await MCPServerManager()._create_mcp_client(server, extra_headers={"Authorization": header}) assert exc.value.status_code == 500 @@ -14846,34 +16137,48 @@ class TestProtectedCredentialPreparation: @pytest.mark.parametrize("value", ["Basic", "Basic ", "basic"]) @pytest.mark.parametrize("source", ["configured", "caller"]) async def test_basic_scheme_alone_is_not_a_credential(self, value: str, source: str) -> None: - server = MCPServer(server_id="basic-scheme", name="basic-scheme", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.basic, - authentication_token=value if source == "configured" else None) + server = MCPServer( + server_id="basic-scheme", + name="basic-scheme", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.basic, + authentication_token=value if source == "configured" else None, + ) with pytest.raises(HTTPException) as exc: await MCPServerManager()._create_mcp_client(server, mcp_auth_header=value if source == "caller" else None) assert exc.value.status_code == 500 @pytest.mark.asyncio - @pytest.mark.parametrize("auth_type,value,default_slot", [ - (MCPAuth.api_key, "fixture-key", "X-API-Key"), - (MCPAuth.bearer_token, "fixture-key", "Authorization"), - (MCPAuth.basic, "user:pass", "Authorization"), - (MCPAuth.token, "fixture-key", "Authorization"), - (MCPAuth.authorization, "fixture-key", "Authorization"), - ]) + @pytest.mark.parametrize( + "auth_type,value,default_slot", + [ + (MCPAuth.api_key, "fixture-key", "X-API-Key"), + (MCPAuth.bearer_token, "fixture-key", "Authorization"), + (MCPAuth.basic, "user:pass", "Authorization"), + (MCPAuth.token, "fixture-key", "Authorization"), + (MCPAuth.authorization, "fixture-key", "Authorization"), + ], + ) @pytest.mark.parametrize("source", ["configured", "caller"]) async def test_usable_credential_survives_an_empty_alternate_header( self, auth_type: MCPAuthType, value: str, default_slot: str, source: str ) -> None: server: Final = MCPServer( - server_id="alternate", name="alternate", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=auth_type, upstream_token_header="X-Custom", + server_id="alternate", + name="alternate", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=auth_type, + upstream_token_header="X-Custom", authentication_token=value if source == "configured" else None, ) empty_slot: Final = default_slot if source == "configured" else "X-Custom" selected_slot: Final = "X-Custom" if source == "configured" else default_slot client: Final = await MCPServerManager()._create_mcp_client( - server, mcp_auth_header=value if source == "caller" else None, extra_headers={empty_slot: ""}, + server, + mcp_auth_header=value if source == "caller" else None, + extra_headers={empty_slot: ""}, ) request: Final = await client.prepare_request_auth() assert request.headers[selected_slot] @@ -14882,8 +16187,12 @@ class TestProtectedCredentialPreparation: @pytest.mark.asyncio async def test_empty_custom_and_default_headers_do_not_satisfy_auth(self) -> None: server: Final = MCPServer( - server_id="both-empty", name="both-empty", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.api_key, upstream_token_header="X-Custom", + server_id="both-empty", + name="both-empty", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.api_key, + upstream_token_header="X-Custom", ) with pytest.raises(HTTPException) as exc: await MCPServerManager()._create_mcp_client(server, extra_headers={"X-Custom": "", "X-API-Key": ""}) @@ -14896,12 +16205,17 @@ class TestProtectedCredentialPreparation: self, custom_slot: str | None, source: str ) -> None: server: Final = MCPServer( - server_id="caller-auth", name="caller-auth", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.api_key, upstream_token_header=custom_slot, + server_id="caller-auth", + name="caller-auth", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.api_key, + upstream_token_header=custom_slot, ) headers: Final = {"Authorization": "Bearer caller-credential", "X-API-Key": ""} client: Final = await MCPServerManager()._create_mcp_client( - server, mcp_auth_header=headers if source == "caller" else None, + server, + mcp_auth_header=headers if source == "caller" else None, extra_headers=headers if source == "forwarded" else None, ) request: Final = await client.prepare_request_auth() @@ -14910,14 +16224,29 @@ class TestProtectedCredentialPreparation: assert custom_slot is None or custom_slot not in request.headers @pytest.mark.asyncio - @pytest.mark.parametrize("value", [ - "", " ", "Bearer", "Basic", "token", "ApiKey", - "Bearer Bearer", "ApiKey ApiKey", "token token", "bEaReR BEARER", "aPiKeY\tAPIKEY", - ]) + @pytest.mark.parametrize( + "value", + [ + "", + " ", + "Bearer", + "Basic", + "token", + "ApiKey", + "Bearer Bearer", + "ApiKey ApiKey", + "token token", + "bEaReR BEARER", + "aPiKeY\tAPIKEY", + ], + ) async def test_api_key_rejects_authorization_without_a_credential(self, value: str) -> None: server: Final = MCPServer( - server_id="caller-empty", name="caller-empty", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.api_key, + server_id="caller-empty", + name="caller-empty", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.api_key, ) with pytest.raises(HTTPException) as exc: await MCPServerManager()._create_mcp_client(server, mcp_auth_header={"Authorization": value}) @@ -14928,8 +16257,11 @@ class TestProtectedCredentialPreparation: @pytest.mark.parametrize("source", ["configured", "caller"]) async def test_basic_requires_a_username_password_separator(self, value: str, source: str) -> None: server: Final = MCPServer( - server_id="basic-pair", name="basic-pair", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.basic, + server_id="basic-pair", + name="basic-pair", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.basic, authentication_token=value if source == "configured" else None, ) with pytest.raises(HTTPException) as exc: @@ -14942,8 +16274,12 @@ class TestProtectedCredentialPreparation: import base64 server: Final = MCPServer( - server_id="basic-valid", name="basic-valid", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=MCPAuth.basic, authentication_token=value, + server_id="basic-valid", + name="basic-valid", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=MCPAuth.basic, + authentication_token=value, ) client: Final = await MCPServerManager()._create_mcp_client(server) request: Final = await client.prepare_request_auth() @@ -14952,17 +16288,27 @@ class TestProtectedCredentialPreparation: assert base64.b64decode(encoded) == value.encode() @pytest.mark.asyncio - @pytest.mark.parametrize("auth_type,value", [ - (MCPAuth.bearer_token, "Bearer"), (MCPAuth.bearer_token, "Bearer "), (MCPAuth.bearer_token, "bearer"), - (MCPAuth.token, "token"), (MCPAuth.token, "token "), (MCPAuth.token, "TOKEN"), - ]) + @pytest.mark.parametrize( + "auth_type,value", + [ + (MCPAuth.bearer_token, "Bearer"), + (MCPAuth.bearer_token, "Bearer "), + (MCPAuth.bearer_token, "bearer"), + (MCPAuth.token, "token"), + (MCPAuth.token, "token "), + (MCPAuth.token, "TOKEN"), + ], + ) @pytest.mark.parametrize("source", ["configured", "caller"]) async def test_static_scheme_only_input_cannot_hide_behind_rendered_prefix( self, auth_type: MCPAuthType, value: str, source: str ) -> None: server: Final = MCPServer( - server_id="empty-scheme", name="empty-scheme", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=auth_type, + server_id="empty-scheme", + name="empty-scheme", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=auth_type, authentication_token=value if source == "configured" else None, ) with pytest.raises(HTTPException) as exc: @@ -14970,17 +16316,24 @@ class TestProtectedCredentialPreparation: assert exc.value.status_code == 500 @pytest.mark.asyncio - @pytest.mark.parametrize("auth_type,value,expected", [ - (MCPAuth.bearer_token, "token", "Bearer token"), - (MCPAuth.bearer_token, "Bearertoken", "Bearer Bearertoken"), - (MCPAuth.token, "tokenish", "token tokenish"), - ]) + @pytest.mark.parametrize( + "auth_type,value,expected", + [ + (MCPAuth.bearer_token, "token", "Bearer token"), + (MCPAuth.bearer_token, "Bearertoken", "Bearer Bearertoken"), + (MCPAuth.token, "tokenish", "token tokenish"), + ], + ) async def test_static_credentials_that_resemble_schemes_remain_usable( self, auth_type: MCPAuthType, value: str, expected: str ) -> None: server: Final = MCPServer( - server_id="real-token", name="real-token", url="https://upstream.example/mcp", - transport=MCPTransport.http, auth_type=auth_type, authentication_token=value, + server_id="real-token", + name="real-token", + url="https://upstream.example/mcp", + transport=MCPTransport.http, + auth_type=auth_type, + authentication_token=value, ) client: Final = await MCPServerManager()._create_mcp_client(server) request: Final = await client.prepare_request_auth() @@ -15019,16 +16372,31 @@ async def test_request_selected_during_guardrail_runs_concurrently_with_tool(mon registry.register_tool("observer-execute", "Execute", {"type": "object"}, upstream) monkeypatch.setattr(tool_registry, "global_mcp_tool_registry", registry) manager = MCPServerManager() - manager.registry = {"observer": MCPServer( - server_id="observer", name="observer", server_name="observer", transport="http", - url="https://observer.example/mcp", spec_path="observer.json", auth_type="none", - )} + manager.registry = { + "observer": MCPServer( + server_id="observer", + name="observer", + server_name="observer", + transport="http", + url="https://observer.example/mcp", + spec_path="observer.json", + auth_type="none", + ) + } manager.tool_name_to_mcp_server_name_mapping = {"observer-execute": "observer"} - result = await asyncio.wait_for(manager.call_tool( - server_name="observer", name="execute", arguments={"text": "hello"}, - user_api_key_auth=UserAPIKeyAuth(), proxy_logging_obj=ProxyLogging(user_api_key_cache=DualCache()), - guardrail_context=MCPRequestContext.resolve_guardrail_context({"metadata": {"guardrails": ["observe"] if selected else []}}), - ), timeout=5) + result = await asyncio.wait_for( + manager.call_tool( + server_name="observer", + name="execute", + arguments={"text": "hello"}, + user_api_key_auth=UserAPIKeyAuth(), + proxy_logging_obj=ProxyLogging(user_api_key_cache=DualCache()), + guardrail_context=MCPRequestContext.resolve_guardrail_context( + {"metadata": {"guardrails": ["observe"] if selected else []}} + ), + ), + timeout=5, + ) assert tool_started.is_set() assert guardrail_started.is_set() is selected assert result.is_error is False @@ -15057,11 +16425,21 @@ async def test_client_sampling_does_not_fill_explicit_context_from_another_ambie from litellm.proxy._experimental.mcp_server import server as legacy_server from litellm.proxy._experimental.mcp_server.mcp_server_manager import _create_sampling_callback - upstream = MCPServer(server_id="explicit-empty", name="explicit_empty", url="https://example.invalid/mcp", transport=MCPTransport.http, allow_sampling=True) + upstream = MCPServer( + server_id="explicit-empty", + name="explicit_empty", + url="https://example.invalid/mcp", + transport=MCPTransport.http, + allow_sampling=True, + ) token = auth_context_var.set(None) sampling = AsyncMock() try: - legacy_server.set_auth_context(UserAPIKeyAuth(user_id="unrelated"), raw_headers={"authorization": "unrelated-credential"}, client_ip="192.0.2.99") + legacy_server.set_auth_context( + UserAPIKeyAuth(user_id="unrelated"), + raw_headers={"authorization": "unrelated-credential"}, + client_ip="192.0.2.99", + ) with ( patch("litellm.proxy._experimental.mcp_server.upstream.MCPClient") as factory, patch("litellm.proxy._experimental.mcp_server.sampling_handler.handle_sampling_create_message", sampling), @@ -15069,7 +16447,9 @@ async def test_client_sampling_does_not_fill_explicit_context_from_another_ambie if legacy_factory: callback = _create_sampling_callback(user_api_key_auth=UserAPIKeyAuth(user_id="explicit")) else: - await MCPServerManager()._create_mcp_client(upstream, user_api_key_auth=UserAPIKeyAuth(user_id="explicit") if with_caller else None) + await MCPServerManager()._create_mcp_client( + upstream, user_api_key_auth=UserAPIKeyAuth(user_id="explicit") if with_caller else None + ) callback = factory.call_args.kwargs["sampling_callback"] await callback(None, None) captured = sampling.await_args.kwargs @@ -15092,16 +16472,28 @@ class TestSharedIdentifierPrefixWarning: manager = MCPServerManager() rows = [ LiteLLM_MCPServerTable( - server_id="srv-a", server_name="alpha", alias="shared", url="https://a.example.com/mcp", - transport=MCPTransport.http, updated_at=datetime.now(), + server_id="srv-a", + server_name="alpha", + alias="shared", + url="https://a.example.com/mcp", + transport=MCPTransport.http, + updated_at=datetime.now(), ), LiteLLM_MCPServerTable( - server_id="srv-b", server_name="beta", alias="Shared", url="https://b.example.com/mcp", - transport=MCPTransport.http, updated_at=datetime.now(), + server_id="srv-b", + server_name="beta", + alias="Shared", + url="https://b.example.com/mcp", + transport=MCPTransport.http, + updated_at=datetime.now(), ), LiteLLM_MCPServerTable( - server_id="srv-c", server_name="gamma", alias="lonely", url="https://c.example.com/mcp", - transport=MCPTransport.http, updated_at=datetime.now(), + server_id="srv-c", + server_name="gamma", + alias="lonely", + url="https://c.example.com/mcp", + transport=MCPTransport.http, + updated_at=datetime.now(), ), ] raw_rows = [MagicMock(model_dump=lambda row=row: row.model_dump()) for row in rows] @@ -15193,7 +16585,9 @@ async def test_reload_warns_once_about_a_blocked_stdio_row_that_is_rebuilt_every @pytest.mark.parametrize("revision", ["auto", "2024-11-05", "2025-03-26", "2025-06-18", "2025-11-25"]) async def test_configured_protocol_reaches_the_upstream_client(config_only_mcp_manager_factory, revision): manager = config_only_mcp_manager_factory() - await manager.load_servers_from_config({"versions": {"url": "http://127.0.0.1:9/mcp", "transport": "http", "protocol_version": revision}}) + await manager.load_servers_from_config( + {"versions": {"url": "http://127.0.0.1:9/mcp", "transport": "http", "protocol_version": revision}} + ) server = next(iter(manager.config_mcp_servers.values())) client = await manager._create_mcp_client(server) assert server.protocol_version == revision @@ -15205,11 +16599,15 @@ async def test_configured_protocol_reaches_the_upstream_client(config_only_mcp_m def test_runtime_protocol_metadata_preserves_explicit_precedence( revision: MCPUpstreamProtocol, explicit: MCPUpstreamProtocol | None ) -> None: - server: Final = MCPServer.model_validate({ - "server_id": "preview", "name": "preview", "transport": "http", - "mcp_info": {"protocol_version": revision}, - **({"protocol_version": explicit} if explicit is not None else {}), - }) + server: Final = MCPServer.model_validate( + { + "server_id": "preview", + "name": "preview", + "transport": "http", + "mcp_info": {"protocol_version": revision}, + **({"protocol_version": explicit} if explicit is not None else {}), + } + ) assert server.protocol_version == (explicit if explicit is not None else revision) @@ -15387,9 +16785,7 @@ class TestToolCatalogGuard: proxy_logging_obj.pre_call_hook = AsyncMock(side_effect=asyncio.CancelledError) with pytest.raises(asyncio.CancelledError): - await manager._get_tools_from_server( - _notes_server(), add_prefix=False, proxy_logging_obj=proxy_logging_obj - ) + await manager._get_tools_from_server(_notes_server(), add_prefix=False, proxy_logging_obj=proxy_logging_obj) proxy_logging_obj.pre_call_hook.assert_awaited_once() proxy_logging_obj.slack_alerting_instance.send_alert.assert_not_awaited() @@ -15446,7 +16842,10 @@ class TestToolCatalogGuard: guardrail, proxy_logging_obj = catalog_guardrail monkeypatch.setattr(signer_module, "_mcp_jwt_signer_instance", None) signer = signer_module.MCPJWTSigner( - guardrail_name="jwt-signer", event_hook="pre_mcp_call", default_on=True, issuer="https://litellm.example.com" + guardrail_name="jwt-signer", + event_hook="pre_mcp_call", + default_on=True, + issuer="https://litellm.example.com", ) monkeypatch.setattr(litellm, "callbacks", [signer, guardrail]) manager = _catalog_manager(LIST_NOTES, POISONED_DELETE) @@ -15666,7 +17065,10 @@ class TestToolCatalogGuard: widened = MCPTool( name="read_note", description="Read a note", - inputSchema={"type": "object", "properties": {"id": {"type": "string"}, "callback_url": {"type": "string"}}}, + inputSchema={ + "type": "object", + "properties": {"id": {"type": "string"}, "callback_url": {"type": "string"}}, + }, ) manager = _catalog_manager(widened) @@ -15728,8 +17130,12 @@ class TestToolCatalogGuard: return "ok" with patch.dict(global_mcp_tool_registry.tools, {}, clear=True): - global_mcp_tool_registry.register_tool("petstore-list_pets", "List pets, newest first", {"type": "object"}, handler) - global_mcp_tool_registry.register_tool("petstore-delete_pets", POISONED_DELETE.description, {"type": "object"}, handler) + global_mcp_tool_registry.register_tool( + "petstore-list_pets", "List pets, newest first", {"type": "object"}, handler + ) + global_mcp_tool_registry.register_tool( + "petstore-delete_pets", POISONED_DELETE.description, {"type": "object"}, handler + ) global_mcp_tool_registry.register_tool("petstore-find_pet", "Find a pet", {"type": "object"}, handler) served = await manager._get_tools_from_server( server, add_prefix=add_prefix, proxy_logging_obj=proxy_logging_obj diff --git a/tests/unit/proxy/_experimental/mcp_server/test_mcp_server_tool_calls_and_headers.py b/tests/unit/proxy/_experimental/mcp_server/test_mcp_server_tool_calls_and_headers.py index 4cc7794d4ad..545b2757ffd 100644 --- a/tests/unit/proxy/_experimental/mcp_server/test_mcp_server_tool_calls_and_headers.py +++ b/tests/unit/proxy/_experimental/mcp_server/test_mcp_server_tool_calls_and_headers.py @@ -9,6 +9,7 @@ from types import SimpleNamespace from typing import Final from unittest.mock import AsyncMock, MagicMock, patch +import httpx import pytest from fastapi import HTTPException from mcp import ReadResourceResult, Resource @@ -23,18 +24,20 @@ from mcp.types import ( TextContent, TextResourceContents, ) +from mcp.types import Tool as MCPTool from mcp_types.version import HANDSHAKE_PROTOCOL_VERSIONS, LATEST_HANDSHAKE_VERSION, MODERN_PROTOCOL_VERSIONS from pydantic import TypeAdapter from starlette.types import Message, Receive, Scope, Send from litellm.proxy._experimental.mcp_server.mcp_context import active_mcp_request_ctx_var +from litellm.proxy._experimental.mcp_server.mcp_server_manager import ListedToolsCaller from litellm.proxy._types import ( LiteLLM_MCPServerTable, MCPTransport, UserAPIKeyAuth, ) from litellm.types.mcp import MCPAuth -from litellm.types.mcp_server.mcp_server_manager import MCPOAuthMetadata, MCPServer +from litellm.types.mcp_server.mcp_server_manager import MCPOAuthMetadata, MCPServer, PinnedMCPTool def test_mcp_available_on_sdk2(): @@ -85,9 +88,6 @@ def cleanup_mcp_global_state(): yield - - - def _call_tool_params(name, arguments=None): from mcp.types import CallToolRequestParams @@ -99,6 +99,7 @@ def _paged_params(): return PaginatedRequestParams() + @pytest.mark.asyncio async def test_mcp_server_tool_call_body_contains_request_data(_mcp_request_ctx): """Test that proxy_server_request body contains name and arguments""" @@ -295,7 +296,9 @@ async def test_mcp_server_tool_call_relays_upstream_auth_error_as_iserror(_mcp_r ): with patch("litellm.proxy.proxy_server.proxy_config", MagicMock()): with patch("litellm.proxy._experimental.mcp_server.operations.verbose_logger", mock_logger): - result = await mcp_server_tool_call(_mcp_request_ctx(), _call_tool_params("test_tool", {"param": "value"})) + result = await mcp_server_tool_call( + _mcp_request_ctx(), _call_tool_params("test_tool", {"param": "value"}) + ) assert result.is_error is True # The dedicated MCPUpstreamAuthError branch (not the generic Exception fallthrough) produces this @@ -1167,20 +1170,32 @@ async def test_read_resource_preserves_content_metadata(_mcp_request_ctx, kind, else BlobResourceContents(uri=uri, blob="aGVsbG8=", mimeType="image/png", meta=metadata) ) with ( - patch.object(server, "get_or_extract_auth_context", AsyncMock(return_value=(caller, None, ["catalog"], None, None, None, None))), + patch.object( + server, + "get_or_extract_auth_context", + AsyncMock(return_value=(caller, None, ["catalog"], None, None, None, None)), + ), patch.object(operations, "_get_allowed_mcp_servers", AsyncMock(return_value=[upstream_server])), - patch.object(operations.global_mcp_server_manager, "read_resource_from_server", AsyncMock(return_value=ReadResourceResult(contents=[content]))), + patch.object( + operations.global_mcp_server_manager, + "read_resource_from_server", + AsyncMock(return_value=ReadResourceResult(contents=[content])), + ), ): result: Final = await server.read_resource(_mcp_request_ctx(), ReadResourceRequestParams(uri=uri)) assert result.model_dump(mode="json", by_alias=True, exclude_none=True) == { - "cacheScope": "private", "resultType": "complete", "ttlMs": 0, - "contents": [{ - "uri": uri, - "mimeType": "text/plain" if kind == "text" else "image/png", - "text" if kind == "text" else "blob": "hello world" if kind == "text" else "aGVsbG8=", - **({"_meta": metadata} if metadata is not None else {}), - }], + "cacheScope": "private", + "resultType": "complete", + "ttlMs": 0, + "contents": [ + { + "uri": uri, + "mimeType": "text/plain" if kind == "text" else "image/png", + "text" if kind == "text" else "blob": "hello world" if kind == "text" else "aGVsbG8=", + **({"_meta": metadata} if metadata is not None else {}), + } + ], } @@ -1674,7 +1689,9 @@ async def test_handle_list_tools_converts_permission_httpexception_to_mcp_error( with ( patch( # test-quality-ok: the protocol handler reads auth from module context; no injection seam "litellm.proxy._experimental.mcp_server.server.get_or_extract_auth_context", - new=AsyncMock(return_value=(None, None, None, None, None, None, None), side_effect=denial if denial_at_auth else None), + new=AsyncMock( + return_value=(None, None, None, None, None, None, None), side_effect=denial if denial_at_auth else None + ), ), patch( # test-quality-ok: the listing helper is the handler's only collaborator; the suite's seam "litellm.proxy._experimental.mcp_server.operations._list_mcp_tools", @@ -1913,8 +1930,8 @@ async def test_streamable_http_session_manager_is_stateless(): ("DELETE", b"", False), ), ) -async def test_mcp_routing_initialize_to_stateful_no_session_to_stateless(_mcp_request_ctx, - debug: bool, method: str, request_body: bytes, stateful: bool +async def test_mcp_routing_initialize_to_stateful_no_session_to_stateless( + _mcp_request_ctx, debug: bool, method: str, request_body: bytes, stateful: bool ) -> None: from starlette.requests import Request from starlette.types import Message, Receive, Scope, Send @@ -4056,7 +4073,8 @@ async def test_truncated_jsonrpc_response_with_nested_method_skips_lock( # parsed, with a nested "method" key in the first bytes to trip a flat # substring heuristic. response_prefix: Final = ( - '{"jsonrpc":"2.0","id":99,"' + response_field + '{"jsonrpc":"2.0","id":99,"' + + response_field + '":{"code":-32000,"message":"test","data":{"method":"GET","payload":"' ).encode() response_body: Final = ( @@ -6564,8 +6582,12 @@ class TestGatewayCreateInitializationOptions: yield (None, None) async def record_request( - serving_server: object, read_stream: object, write_stream: object, - *, lifespan_state: object, init_options: InitializationOptions, + serving_server: object, + read_stream: object, + write_stream: object, + *, + lifespan_state: object, + init_options: InitializationOptions, ) -> None: captured["server_name"] = init_options.server_name @@ -6877,7 +6899,6 @@ async def test_probe_upstream_auth_surfaces_httpx_status_error(): returning the response. The probe must catch that specifically (before the fail-open `except Exception`) so the auth check is not silently defeated. """ - import httpx from litellm.proxy._experimental.mcp_server.server import _probe_upstream_auth @@ -7412,7 +7433,8 @@ async def test_execute_mcp_tool_rest_server_id_authoritative_for_unprefixed_tool return_value=oauth_server, ), patch.object( - mcp_operations, "_handle_managed_mcp_tool", + mcp_operations, + "_handle_managed_mcp_tool", new=fake_handle_managed_mcp_tool, ), patch.object( @@ -7658,7 +7680,8 @@ async def test_execute_mcp_tool_strips_a_prefix_that_contains_the_separator(): return_value=alias_less_server, ), patch.object( - mcp_operations, "_handle_managed_mcp_tool", + mcp_operations, + "_handle_managed_mcp_tool", new=fake_handle_managed_mcp_tool, ), patch.object( @@ -7933,7 +7956,8 @@ async def test_execute_mcp_tool_rest_hyphenated_upstream_tool_name_routes_to_req return_value=None, ), patch.object( - mcp_operations, "_handle_managed_mcp_tool", + mcp_operations, + "_handle_managed_mcp_tool", new=fake_handle_managed_mcp_tool, ), patch.object( @@ -7989,9 +8013,12 @@ async def test_execute_mcp_tool_sets_model_in_model_call_details(): fake_server.server_name = "openapi-petstore" fake_server.alias = None fake_server.short_prefix = None + fake_server.tool_name_to_description = None fake_tool = MagicMock() fake_tool.name = "list_pets" + fake_tool.description = "test tool" + fake_tool.input_schema = {"type": "object"} start_time = datetime.now(timezone.utc) litellm_logging_obj, _ = function_setup( @@ -8042,6 +8069,348 @@ async def test_execute_mcp_tool_sets_model_in_model_call_details(): assert litellm_logging_obj.model == "MCP: list_pets" +@pytest.mark.asyncio +async def test_execute_mcp_tool_hands_openapi_hooks_the_listed_entry_and_nothing_before_a_listing(): + """A local-registry tools/call with no prior tools/list hands the pre-call hooks name and arguments + only, as before this metadata existed, so a pre_mcp_call policy never scans a description the caller was + not served. Once the caller has listed, the same call hands the entry that listing served.""" + from litellm.caching.caching import DualCache + from litellm.proxy._experimental.mcp_server import operations as mcp_module + from litellm.proxy.utils import ProxyLogging + + petstore = MCPServer( + server_id="petstore-id", + name="petstore", + server_name="petstore", + transport=MCPTransport.http, + url=None, + spec_path="https://example.com/petstore.yaml", + tool_name_to_description={"list_pets": "ADMIN DESC"}, + ) + schema = {"type": "object", "properties": {"limit": {"type": "integer"}}} + mcp_module.global_mcp_tool_registry.register_tool( + name="petstore-list_pets", description="List the pets", input_schema=schema, handler=lambda limit: "ok" + ) + manager = mcp_module.global_mcp_server_manager + manager._listed_tools_by_server_id.pop(petstore.server_id, None) + alice = UserAPIKeyAuth(api_key="sk-user", user_id="alice") + proxy_logging = ProxyLogging(user_api_key_cache=DualCache()) + proxy_logging.pre_call_hook = AsyncMock(return_value={}) + pre_call_tool_check = AsyncMock(wraps=manager.pre_call_tool_check) + + async def call() -> tuple[MCPTool | None, dict]: + await mcp_module.execute_mcp_tool( + name="petstore-list_pets", + arguments={"limit": 10}, + allowed_mcp_servers=[petstore], + start_time=datetime.now(), + user_api_key_auth=alice, + ) + return pre_call_tool_check.call_args.kwargs["tool"], proxy_logging.pre_call_hook.call_args.kwargs["data"] + + try: + with ( + patch.object(manager, "_get_mcp_server_from_tool_name", return_value=petstore), + patch.object(manager, "pre_call_tool_check", new=pre_call_tool_check), + patch("litellm.proxy.proxy_server.proxy_logging_obj", proxy_logging), + ): + never_listed_tool, never_listed_data = await call() + manager._record_listed_tools( + petstore, + [MCPTool(name="list_pets", description="ADMIN DESC", inputSchema=schema)], + ListedToolsCaller(user_api_key_auth=alice), + ) + listed_tool, listed_data = await call() + finally: + mcp_module.global_mcp_tool_registry.unregister_tools_with_prefix("petstore-") + manager._listed_tools_by_server_id.pop(petstore.server_id, None) + + assert never_listed_tool is None + assert (never_listed_data.get("mcp_tool_description"), never_listed_data.get("mcp_input_schema")) == (None, None) + assert listed_tool is not None and (listed_tool.description, listed_tool.input_schema) == ("ADMIN DESC", schema) + assert (listed_data["mcp_tool_description"], listed_data["mcp_input_schema"]) == ("ADMIN DESC", schema) + + +@pytest.mark.asyncio +async def test_execute_mcp_tool_hands_openapi_hooks_the_guarded_catalog_entry_clients_saw(): + """When tools/list pinned the schema and masked the description of an OpenAPI tool, the local-registry + call path must hand the pre-call hooks that served entry, not the raw registry one.""" + from litellm.proxy._experimental.mcp_server import operations as mcp_module + + petstore = MCPServer( + server_id="petstore-id", + name="petstore", + server_name="petstore", + transport=MCPTransport.http, + url=None, + spec_path="https://example.com/petstore.yaml", + tool_name_to_description={"getpetbyid": "Find a SECRET pet"}, + ) + registry_schema = {"type": "object", "properties": {"petId": {"type": "integer"}, "dump_all": {"type": "boolean"}}} + pinned_schema = {"type": "object", "properties": {"petId": {"type": "integer"}}} + mcp_module.global_mcp_tool_registry.register_tool( + name="petstore-getpetbyid", + description="Find pet by ID", + input_schema=registry_schema, + handler=lambda petId: "ok", + ) + manager = mcp_module.global_mcp_server_manager + alice = UserAPIKeyAuth(api_key="sk-user", user_id="alice") + manager._record_listed_tools( + petstore, + [MCPTool(name="getpetbyid", description="Find a [MASKED] pet", inputSchema=pinned_schema)], + ListedToolsCaller(user_api_key_auth=alice), + ) + pre_call_tool_check = AsyncMock(return_value={}) + + try: + with ( + patch.object(manager, "_get_mcp_server_from_tool_name", return_value=petstore), + patch.object(manager, "pre_call_tool_check", new=pre_call_tool_check), + ): + await mcp_module.execute_mcp_tool( + name="petstore-getpetbyid", + arguments={"petId": 1}, + allowed_mcp_servers=[petstore], + start_time=datetime.now(), + user_api_key_auth=alice, + ) + finally: + mcp_module.global_mcp_tool_registry.unregister_tools_with_prefix("petstore-") + manager._listed_tools_by_server_id.pop(petstore.server_id, None) + + handed_tool = pre_call_tool_check.call_args.kwargs["tool"] + assert (handed_tool.description, handed_tool.input_schema) == ("Find a [MASKED] pet", pinned_schema), ( + "the pre-call policy must evaluate the entry tools/list served, not the raw registry entry" + ) + + +@pytest.mark.asyncio +async def test_execute_mcp_tool_hands_openapi_hooks_each_callers_own_listed_entry(): + """Two keys can be shown differently guarded OpenAPI catalogs. The call path must evaluate each key + against the entry its own tools/list served, not the entry the most recent listing left behind.""" + from litellm.proxy._experimental.mcp_server import operations as mcp_module + + petstore = MCPServer( + server_id="petstore-id", + name="petstore", + server_name="petstore", + transport=MCPTransport.http, + url=None, + spec_path="https://example.com/petstore.yaml", + ) + schema = {"type": "object", "properties": {"petId": {"type": "integer"}}} + mcp_module.global_mcp_tool_registry.register_tool( + name="petstore-getpetbyid", description="Find a SECRET pet", input_schema=schema, handler=lambda petId: "ok" + ) + manager = mcp_module.global_mcp_server_manager + guarded = UserAPIKeyAuth(api_key="sk-guarded", user_id="alice") + opted_out = UserAPIKeyAuth(api_key="sk-opted-out", user_id="bob") + manager._record_listed_tools( + petstore, + [MCPTool(name="getpetbyid", description="Find a [MASKED] pet", inputSchema=schema)], + ListedToolsCaller(user_api_key_auth=guarded), + ) + manager._record_listed_tools( + petstore, + [MCPTool(name="getpetbyid", description="Find a SECRET pet", inputSchema=schema)], + ListedToolsCaller(user_api_key_auth=opted_out), + ) + pre_call_tool_check = AsyncMock(return_value={}) + + try: + with ( + patch.object(manager, "_get_mcp_server_from_tool_name", return_value=petstore), + patch.object(manager, "pre_call_tool_check", new=pre_call_tool_check), + ): + for caller in (guarded, opted_out): + await mcp_module.execute_mcp_tool( + name="petstore-getpetbyid", + arguments={"petId": 1}, + allowed_mcp_servers=[petstore], + start_time=datetime.now(), + user_api_key_auth=caller, + ) + finally: + mcp_module.global_mcp_tool_registry.unregister_tools_with_prefix("petstore-") + manager._listed_tools_by_server_id.pop(petstore.server_id, None) + + handed = [call.kwargs["tool"].description for call in pre_call_tool_check.call_args_list] + assert handed == ["Find a [MASKED] pet", "Find a SECRET pet"], ( + "each key's tools/call must be evaluated against the OpenAPI entry its own listing served" + ) + + +@pytest.mark.asyncio +async def test_execute_mcp_tool_runs_the_longer_colliding_operation_and_hands_hooks_no_registry_metadata(): + """An OpenAPI operation whose name starts with its own server prefix runs instead of the shorter one, and + with no prior listing the pre-call hooks get name and arguments only, never either registry entry.""" + from litellm.proxy._experimental.mcp_server import operations as mcp_module + + petstore = MCPServer( + server_id="petstore-id", + name="petstore", + server_name="petstore", + transport=MCPTransport.http, + url=None, + spec_path="https://example.com/petstore.yaml", + ) + registry = mcp_module.global_mcp_tool_registry + registry.register_tool(name="petstore-get_pet", description="short", input_schema={}, handler=lambda: "short") + registry.register_tool( + name="petstore-petstore-get_pet", + description="long", + input_schema={"type": "object", "properties": {"petId": {"type": "integer"}}}, + handler=lambda: "long", + ) + manager = mcp_module.global_mcp_server_manager + pre_call_tool_check = AsyncMock(return_value={}) + + try: + with ( + patch.object(manager, "_get_mcp_server_from_tool_name", return_value=petstore), + patch.object(manager, "pre_call_tool_check", new=pre_call_tool_check), + ): + result = await mcp_module.execute_mcp_tool( + name="petstore-petstore-get_pet", + arguments={}, + allowed_mcp_servers=[petstore], + start_time=datetime.now(), + user_api_key_auth=UserAPIKeyAuth(api_key="sk-user", user_id="alice"), + ) + finally: + registry.unregister_tools_with_prefix("petstore-") + + assert pre_call_tool_check.call_args.kwargs["tool"] is None + assert result.content[0].text == "long" + + +@pytest.mark.asyncio +async def test_execute_mcp_tool_hands_hooks_nothing_for_a_never_listed_operation_named_after_a_listed_one(): + """After the caller listed ``get_pet``, a call to the never-listed ``petstore-get_pet`` operation hands the + pre-call hooks name and arguments only, not the listed sibling's description and schema.""" + from litellm.proxy._experimental.mcp_server import operations as mcp_module + + petstore = MCPServer( + server_id="petstore-id", + name="petstore", + server_name="petstore", + transport=MCPTransport.http, + url=None, + spec_path="https://example.com/petstore.yaml", + ) + registry = mcp_module.global_mcp_tool_registry + registry.register_tool( + name="petstore-petstore-get_pet", description="long", input_schema={}, handler=lambda: "long" + ) + manager = mcp_module.global_mcp_server_manager + alice = UserAPIKeyAuth(api_key="sk-user", user_id="alice") + manager._record_listed_tools( + petstore, + [MCPTool(name="get_pet", description="Fetches pet records. FLAGWORD", inputSchema={"type": "object"})], + ListedToolsCaller(user_api_key_auth=alice), + ) + pre_call_tool_check = AsyncMock(return_value={}) + + try: + with ( + patch.object(manager, "_get_mcp_server_from_tool_name", return_value=petstore), + patch.object(manager, "pre_call_tool_check", new=pre_call_tool_check), + ): + result = await mcp_module.execute_mcp_tool( + name="petstore-petstore-get_pet", + arguments={}, + allowed_mcp_servers=[petstore], + start_time=datetime.now(), + user_api_key_auth=alice, + ) + finally: + registry.unregister_tools_with_prefix("petstore-") + manager._listed_tools_by_server_id.pop(petstore.server_id, None) + + assert pre_call_tool_check.call_args.kwargs["tool"] is None + assert result.content[0].text == "long" + + +@pytest.mark.asyncio +async def test_execute_mcp_tool_implicit_listing_before_the_first_call_hands_hooks_no_description(): + """The listing tools/call runs on its own when this worker does not yet expose the tool is never served + to the caller, so it leaves the caller's listed slot empty and the pre-call hooks still get name and + arguments only, as on main.""" + manager = mcp_operations.global_mcp_server_manager + server = _never_listed_passthrough_server() + manager.registry[server.server_id] = server + manager._listed_tools_by_server_id.pop(server.server_id, None) + upstream = AsyncMock() + upstream.call_tool.return_value = CallToolResult(content=[TextContent(type="text", text="ok")], isError=False) + proxy_logging = _mock_mcp_proxy_logging() + proxy_logging._create_mcp_request_object_from_kwargs = MagicMock(return_value={}) + proxy_logging._convert_mcp_to_llm_format = MagicMock(return_value={}) + proxy_logging.pre_call_hook = AsyncMock(return_value={}) + proxy_logging.during_call_hook = AsyncMock(return_value=None) + fetch_tools = AsyncMock( + return_value=[MCPTool(name="add", description="Adds. FLAGWORD", inputSchema={"type": "object"})] + ) + + with ( + patch.object(manager, "_create_mcp_client", new=AsyncMock(return_value=upstream)), + patch.object(manager, "_fetch_tools_with_timeout", new=fetch_tools), + patch("litellm.proxy.proxy_server.proxy_logging_obj", proxy_logging), + ): + result = await mcp_operations.execute_mcp_tool( + name="lazy_map-add", + arguments={"a": 1, "b": 2}, + allowed_mcp_servers=[server], + start_time=datetime.now(), + mcp_auth_header="Bearer caller-token", + raw_headers={"authorization": "Bearer caller-token"}, + ) + + assert fetch_tools.await_count == 1 + assert upstream.call_tool.await_count == 1 + assert result.content[0].text == "ok" + hook_kwargs = proxy_logging._create_mcp_request_object_from_kwargs.call_args.args[0] + assert (hook_kwargs["tool_description"], hook_kwargs["tool_input_schema"]) == (None, None) + assert server.server_id not in manager._listed_tools_by_server_id + + +@pytest.mark.asyncio +async def test_fetch_pinnable_tool_catalog_records_no_listed_catalog_for_the_admin(): + """The pin snapshot lists the raw upstream catalog, without the catalog guard or the admin's description + overrides, so it must not become what the admin's own later tools/call is evaluated against.""" + from litellm.caching.caching import DualCache + from litellm.proxy._experimental.mcp_server.rest_endpoints import fetch_pinnable_tool_catalog + from litellm.proxy.utils import ProxyLogging + + manager = mcp_operations.global_mcp_server_manager + server = MCPServer( + server_id="pin-srv", + name="pin_srv", + transport=MCPTransport.http, + url="https://up.example.com/mcp", + tool_name_to_description={"add": "Admin wording"}, + ) + manager._listed_tools_by_server_id.pop(server.server_id, None) + admin = UserAPIKeyAuth(api_key="sk-admin", user_id="admin") + request = MagicMock() + request.client.host = "10.1.2.3" + request.headers = {"x-litellm-api-key": "sk-admin"} + fetch_tools = AsyncMock( + return_value=[MCPTool(name="add", description="Upstream wording", inputSchema={"type": "object"})] + ) + + with ( + patch.object(manager, "_create_mcp_client", new=AsyncMock(return_value=MagicMock())), + patch.object(manager, "_fetch_tools_with_timeout", new=fetch_tools), + patch("litellm.proxy.proxy_server.proxy_logging_obj", ProxyLogging(user_api_key_cache=DualCache())), + ): + snapshot = await fetch_pinnable_tool_catalog(server, request, admin) + + assert snapshot == {"add": PinnedMCPTool(description="Upstream wording", input_schema={"type": "object"})} + assert server.server_id not in manager._listed_tools_by_server_id + assert manager.get_listed_tool(server, "add", ListedToolsCaller(user_api_key_auth=admin)) is None + + @pytest.mark.asyncio async def test_execute_mcp_tool_rest_unresolved_prefixed_name_routes_to_requested_server(): """A prefixed REST name that resolves to no tool must still dispatch to the server_id. @@ -8098,7 +8467,8 @@ async def test_execute_mcp_tool_rest_unresolved_prefixed_name_routes_to_requeste return_value=None, ), patch.object( - mcp_operations, "_handle_managed_mcp_tool", + mcp_operations, + "_handle_managed_mcp_tool", new=fake_handle_managed_mcp_tool, ), patch.object( @@ -8597,7 +8967,9 @@ class TestMCPMetaTraceCarrier: assert _mcp_meta_trace_carrier(None) is None assert _mcp_meta_trace_carrier(SimpleNamespace(meta=None)) is None - only_progress = CallToolRequestParams.model_validate({"name": "t", "_meta": {"progressToken": "p1"}}, by_name=False).meta + only_progress = CallToolRequestParams.model_validate( + {"name": "t", "_meta": {"progressToken": "p1"}}, by_name=False + ).meta assert _mcp_meta_trace_carrier(SimpleNamespace(meta=only_progress)) is None @@ -10394,7 +10766,9 @@ async def test_mcp_origin_admission_precedes_authentication( patch("litellm.proxy.proxy_server.origins", allowed_origins), patch.object(server, "extract_mcp_auth_context", authenticate), ): - async with httpx.AsyncClient(transport=httpx.ASGITransport(app=server.app), base_url="http://gateway") as client: + async with httpx.AsyncClient( + transport=httpx.ASGITransport(app=server.app), base_url="http://gateway" + ) as client: response: Final = await client.request(method, path, headers=(*session_headers, *origin_headers)) assert response.status_code == expected_status @@ -10477,12 +10851,15 @@ async def test_streamable_http_rejects_modern_protocol_version( @pytest.mark.asyncio -@pytest.mark.parametrize("handler_name,field", [ - ("handle_list_tools", "tools"), - ("list_prompts", "prompts"), - ("list_resources", "resources"), - ("list_resource_templates", "resource_templates"), -]) +@pytest.mark.parametrize( + "handler_name,field", + [ + ("handle_list_tools", "tools"), + ("list_prompts", "prompts"), + ("list_resources", "resources"), + ("list_resource_templates", "resource_templates"), + ], +) async def test_native_listing_preserves_empty_result_on_auth_failure(_mcp_request_ctx, handler_name, field): from litellm.proxy._experimental.mcp_server import server @@ -10500,7 +10877,9 @@ async def test_tool_listing_preserves_permission_denial_when_failure_logging_fai auth = UserAPIKeyAuth(user_id="denied-caller") denial = HTTPException(status_code=403, detail="scope denied") logger = MagicMock() - logger.post_call_failure_hook = AsyncMock(side_effect=RuntimeError("log unavailable") if failure_hook_raises else None) + logger.post_call_failure_hook = AsyncMock( + side_effect=RuntimeError("log unavailable") if failure_hook_raises else None + ) upstream = AsyncMock() with ( patch.object(operations, "_get_allowed_mcp_servers", AsyncMock(side_effect=denial)), @@ -10509,7 +10888,9 @@ async def test_tool_listing_preserves_permission_denial_when_failure_logging_fai patch.object(operations.global_mcp_server_manager, "_get_tools_from_server", upstream), ): with pytest.raises(HTTPException) as rejected: - await operations._get_tools_from_mcp_servers(user_api_key_auth=auth, mcp_auth_header=None, mcp_servers=["catalog"], log_list_tools_to_spendlogs=True) + await operations._get_tools_from_mcp_servers( + user_api_key_auth=auth, mcp_auth_header=None, mcp_servers=["catalog"], log_list_tools_to_spendlogs=True + ) assert rejected.value is denial upstream.assert_not_awaited() logger.post_call_failure_hook.assert_awaited_once() @@ -10521,7 +10902,9 @@ async def test_tool_listing_preserves_permission_denial_when_failure_logging_fai @pytest.mark.parametrize("prefix,suffix", (("", ""), ("/gateway", "/"))) @pytest.mark.parametrize("opening_protocol", (None, *MODERN_PROTOCOL_VERSIONS)) async def test_legacy_sse_mount_emits_message_endpoint( - prefix: str, suffix: str, opening_protocol: str | None, + prefix: str, + suffix: str, + opening_protocol: str | None, ) -> None: from starlette.applications import Starlette from starlette.routing import Mount @@ -10586,16 +10969,20 @@ async def test_legacy_sse_mount_emits_message_endpoint( return (await messages.get())["status"] if opening_protocol is not None: - discover: Final = json.dumps({ - "jsonrpc": "2.0", - "id": 0, - "method": "server/discover", - "params": {"_meta": { - "io.modelcontextprotocol/protocolVersion": opening_protocol, - "io.modelcontextprotocol/clientInfo": {"name": "modern-client", "version": "1"}, - "io.modelcontextprotocol/clientCapabilities": {}, - }}, - }).encode() + discover: Final = json.dumps( + { + "jsonrpc": "2.0", + "id": 0, + "method": "server/discover", + "params": { + "_meta": { + "io.modelcontextprotocol/protocolVersion": opening_protocol, + "io.modelcontextprotocol/clientInfo": {"name": "modern-client", "version": "1"}, + "io.modelcontextprotocol/clientCapabilities": {}, + } + }, + } + ).encode() assert await post(discover) == 202 discovered_frame: Final = (await asyncio.wait_for(outgoing.get(), 2))["body"].decode() discovered: Final = json.loads(discovered_frame.split("data: ", 1)[1].splitlines()[0]) @@ -10628,7 +11015,16 @@ async def test_legacy_sse_mount_emits_message_endpoint( patch.object( mcp_server, "extract_mcp_auth_context", - AsyncMock(return_value=(post_auth, None, [marker], {marker: {"Authorization": marker}}, {"Authorization": marker}, {"x-request-marker": marker})), + AsyncMock( + return_value=( + post_auth, + None, + [marker], + {marker: {"Authorization": marker}}, + {"Authorization": marker}, + {"x-request-marker": marker}, + ) + ), ), patch.object(mcp_server.operations, "_get_tools_from_mcp_servers", listing), ): @@ -10677,7 +11073,11 @@ async def test_discovery_adapter_preserves_authenticated_context(_mcp_request_ct dispatched = AsyncMock(return_value=expected) auth = UserAPIKeyAuth(user_id="discover-caller") with ( - patch.object(server, "get_or_extract_auth_context", AsyncMock(return_value=(auth, None, ["allowed"], None, None, None, None))), + patch.object( + server, + "get_or_extract_auth_context", + AsyncMock(return_value=(auth, None, ["allowed"], None, None, None, None)), + ), patch.object(server.operations.GatewayOperations, "execute", dispatched), ): result = await server.discover(_mcp_request_ctx(), RequestParams()) diff --git a/tests/unit/proxy/_experimental/mcp_server/test_mcp_tool_search.py b/tests/unit/proxy/_experimental/mcp_server/test_mcp_tool_search.py index 1cfe6198b6f..1c987778da6 100644 --- a/tests/unit/proxy/_experimental/mcp_server/test_mcp_tool_search.py +++ b/tests/unit/proxy/_experimental/mcp_server/test_mcp_tool_search.py @@ -23,6 +23,7 @@ from mcp.types import Tool import litellm from litellm.models.object_permission import LiteLLM_ObjectPermissionTable from litellm.proxy._experimental.mcp_server.faults.list_outcomes import AggregateToolListing +from litellm.proxy._experimental.mcp_server.mcp_server_manager import ListedToolsCaller from litellm.proxy._experimental.mcp_server.tool_search import ( AGENT_SEARCH_TOOL_NAME, MCP_TOOL_CALL_TOOL_NAME, @@ -32,12 +33,14 @@ from litellm.proxy._experimental.mcp_server.tool_search import ( ToolSearchResult, coerce_top_k, get_virtual_tool_definitions, + handle_mcp_tool_search, search_mcp_tools, search_tools, ) from litellm.proxy._types import LitellmUserRoles, UserAPIKeyAuth from litellm.proxy.common_utils.semantic_text_index import EmbeddingFailed, SemanticTextIndex, Vector -from litellm.types.mcp import MCPToolSearchSettings +from litellm.types.mcp import MCPToolSearchSettings, MCPTransport +from litellm.types.mcp_server.mcp_server_manager import MCPServer def _make_tools(specs: list[tuple[str, str]]) -> tuple[Tool, ...]: @@ -1353,3 +1356,33 @@ async def test_handle_mcp_tool_call_scoped_denial_names_the_binding_agent() -> N assert exc_info.value.status_code == 403 assert "MCP server 'github'" in exc_info.value.detail["error"] assert "agent 'agent-123'" in exc_info.value.detail["error"] + + +@pytest.mark.asyncio +async def test_mcp_tool_search_leaves_the_listed_tools_slot_empty(monkeypatch: pytest.MonkeyPatch) -> None: + """The search lists the whole catalog but serves only its hits, so the listing must not fill the + caller's listed-tools slot: a later call to a tool the search never returned is not a listed tool.""" + monkeypatch.setattr(litellm, "mcp_tool_search", None) + manager = mcp_operations.global_mcp_server_manager + server = MCPServer(server_id="search-slot", name="search-slot", transport=MCPTransport.http, url="http://slot") + user = UserAPIKeyAuth(api_key="sk-search-slot", user_id="searcher") + upstream = [ + Tool(name="echo", description="Echo text back", inputSchema={"type": "object"}), + Tool(name="delete_note", description="Delete a note", inputSchema={"type": "object"}), + ] + with ( + patch.dict(manager.tool_name_to_mcp_server_name_mapping), + patch.object(mcp_operations, "_get_allowed_mcp_servers", AsyncMock(return_value=[server])), + patch.object(manager, "_create_mcp_client", AsyncMock(return_value=object())), + patch.object(manager, "_fetch_tools_with_timeout", AsyncMock(return_value=upstream)), + ): + try: + result = await handle_mcp_tool_search(query="echo", top_k=1, user_api_key_dict=user) + caller = ListedToolsCaller(user_api_key_auth=user) + listed = [manager.get_listed_tool(server, tool.name, caller) for tool in upstream] + finally: + manager._drop_listed_tools(server.server_id) + + assert result.is_error is False + assert [hit["name"] for hit in json.loads(result.content[0].text)] == ["search-slot-echo"] + assert listed == [None, None] diff --git a/tests/unit/proxy/_experimental/mcp_server/test_openapi_tool_auth.py b/tests/unit/proxy/_experimental/mcp_server/test_openapi_tool_auth.py index a8ec7be55f0..60157193a16 100644 --- a/tests/unit/proxy/_experimental/mcp_server/test_openapi_tool_auth.py +++ b/tests/unit/proxy/_experimental/mcp_server/test_openapi_tool_auth.py @@ -42,9 +42,12 @@ async def test_openapi_local_tool_runs_pre_call_tool_check(): fake_server.server_name = "openapi-petstore" fake_server.alias = None fake_server.short_prefix = None + fake_server.tool_name_to_description = None fake_tool = MagicMock() fake_tool.name = "list_pets" + fake_tool.description = "test tool" + fake_tool.input_schema = {"type": "object"} pre_call = AsyncMock(return_value={}) handle_local = AsyncMock(return_value=CallToolResult(content=[], is_error=False)) @@ -125,9 +128,12 @@ async def test_openapi_local_tool_blocked_when_pre_call_check_raises(): fake_server.server_name = "openapi-petstore" fake_server.alias = None fake_server.short_prefix = None + fake_server.tool_name_to_description = None fake_tool = MagicMock() fake_tool.name = "delete_pet" + fake_tool.description = "test tool" + fake_tool.input_schema = {"type": "object"} pre_call = AsyncMock( side_effect=HTTPException(status_code=403, detail="not allowed") @@ -190,6 +196,8 @@ async def test_openapi_local_tool_denied_when_server_not_resolvable(): fake_tool = MagicMock() fake_tool.name = "list_pets" + fake_tool.description = "test tool" + fake_tool.input_schema = {"type": "object"} pre_call = AsyncMock(return_value={}) handle_local = AsyncMock(return_value=CallToolResult(content=[], is_error=False)) @@ -274,6 +282,8 @@ async def test_openapi_local_tool_injects_resolved_oauth_token(): fake_tool = MagicMock() fake_tool.name = "get_values" + fake_tool.description = "test tool" + fake_tool.input_schema = {"type": "object"} captured: dict = {} async def handle_local(_name, _arguments, _wire_compat): @@ -620,6 +630,8 @@ async def test_per_server_auth_header_reaches_both_openapi_dispatch_arms(dispatc if dispatch_arm == "local_registry": fake_tool = MagicMock() fake_tool.name = "list_reports" + fake_tool.description = "test tool" + fake_tool.input_schema = {"type": "object"} with ( patch.object(manager, "_get_mcp_server_from_tool_name", return_value=server), patch.object(mcp_operations.global_mcp_tool_registry, "get_tool", return_value=fake_tool), @@ -691,6 +703,8 @@ async def test_local_dispatch_reports_the_outcome_instead_of_success(failure: st fake_tool = MagicMock() fake_tool.name = "list_reports" + fake_tool.description = "test tool" + fake_tool.input_schema = {"type": "object"} fake_tool.handler = raising_handler server = MCPServer( server_id="srv-openapi", diff --git a/tests/unit/proxy/_experimental/mcp_server/test_operations.py b/tests/unit/proxy/_experimental/mcp_server/test_operations.py index b16b27ac919..f710bc7f1d7 100644 --- a/tests/unit/proxy/_experimental/mcp_server/test_operations.py +++ b/tests/unit/proxy/_experimental/mcp_server/test_operations.py @@ -1,15 +1,101 @@ import asyncio +from typing import Final from unittest.mock import AsyncMock, patch import pytest from mcp.types import GetPromptRequest, GetPromptRequestParams, GetPromptResult +from mcp.types import Tool as MCPTool +import litellm +from litellm.caching.dual_cache import DualCache +from litellm.integrations.custom_logger import CustomLogger +from litellm.proxy._experimental.mcp_server import operations +from litellm.proxy._experimental.mcp_server import rest_endpoints +from litellm.proxy._experimental.mcp_server.mcp_server_manager import ListedToolsCaller from litellm.proxy._experimental.mcp_server.operations import GatewayOperations, prepare_context +from litellm.proxy._experimental.mcp_server.tool_registry import global_mcp_tool_registry from litellm.proxy._types import UserAPIKeyAuth +from litellm.proxy.common_utils.user_api_key_cache import UserApiKeyCache +from litellm.proxy.utils import ProxyLogging from litellm.types.mcp import MCPAuth, MCPTransport from litellm.types.mcp_server.mcp_server_manager import MCPServer +class _CatalogHookCapture(CustomLogger): + data: dict[str, object] | None = None + + async def async_pre_call_hook( + self, user_api_key_dict: UserAPIKeyAuth, cache: DualCache, data: dict[str, object], call_type: str + ) -> None: + if call_type == "call_mcp_tool": + self.data = data.copy() + + +async def _served_catalog_tool() -> str: + return "ok" + + +@pytest.mark.asyncio +@pytest.mark.parametrize("surface", ["mcp", "rest"]) +@pytest.mark.parametrize("restriction", ["key", "server"]) +async def test_listing_records_only_tools_the_caller_received( + monkeypatch: pytest.MonkeyPatch, surface: str, restriction: str +) -> None: + manager: Final = operations.global_mcp_server_manager + server: Final = MCPServer( + server_id="served-catalog", name="served-catalog", transport=MCPTransport.http, + spec_path="/catalog.yaml", allow_all_keys=True, + allowed_tools=["echo"] if restriction == "server" else None, + ) + auth: Final = UserAPIKeyAuth( + api_key="sk-served-catalog", user_id="lister", + object_permission={ + "object_permission_id": "served-permission", + "mcp_servers": [server.server_id], + "mcp_tool_permissions": {server.server_id: ["echo"]} if restriction == "key" else None, + }, + ) + monkeypatch.setitem(manager.registry, server.server_id, server) + monkeypatch.setitem(manager.tool_name_to_mcp_server_name_mapping, "status", server.server_id) + monkeypatch.setitem(manager.tool_name_to_mcp_server_name_mapping, "served-catalog-status", server.server_id) + capture: Final = _CatalogHookCapture() + monkeypatch.setattr(litellm, "callbacks", [capture]) + for name in ("echo", "status"): + global_mcp_tool_registry.register_tool( + name=f"served-catalog-{name}", description=f"{name} description", + input_schema={"type": "object"}, handler=_served_catalog_tool, + ) + try: + if surface == "mcp": + listing: Final = await operations._list_mcp_tools( + user_api_key_auth=auth, mcp_servers=[server.server_id], record_listing=True, + ) + assert [tool.name for tool in listing.tools] == ["served-catalog-echo"] + else: + rest_listing: Final = await rest_endpoints._get_tools_for_single_server( + server, None, user_api_key_auth=auth, + ) + assert [tool.name for tool in rest_listing] == ["echo"] + granted: Final = auth.model_copy(update={"object_permission": None}) + caller: Final = ListedToolsCaller(user_api_key_auth=granted) + assert manager.get_listed_tool(server, "status", caller) is None + served: Final = manager.get_listed_tool(server, "echo", caller) + assert served is not None + assert (served.description, served.input_schema) == ("echo description", {"type": "object"}) + server.allowed_tools = None + result: Final = await manager.call_tool( + server_name=server.server_id, name="status", arguments={}, user_api_key_auth=granted, + proxy_logging_obj=ProxyLogging(user_api_key_cache=UserApiKeyCache()), + ) + assert result.is_error is False + assert capture.data is not None + assert capture.data["messages"] == [{"role": "user", "content": "Tool: status\nArguments: {}"}] + assert (capture.data.get("mcp_tool_description"), capture.data.get("mcp_input_schema")) == (None, None) + finally: + manager._drop_listed_tools(server.server_id) + global_mcp_tool_registry.unregister_tools_with_prefix("served-catalog-") + + @pytest.mark.asyncio async def test_oauth_prefetch_failure_does_not_log_caller_or_exception_text(caplog): from litellm.proxy._experimental.mcp_server.operations import _prefetch_oauth_creds_for_user @@ -665,3 +751,30 @@ async def test_tools_listing_preserves_explicit_spend_log_policy(log_enabled): ) assert result.tools == [] assert listing.await_args.kwargs["log_list_tools_to_spendlogs"] is log_enabled + assert listing.await_args.kwargs["record_listing"] is True + + +@pytest.mark.asyncio +@pytest.mark.parametrize(("listing_kwargs", "recorded"), [({}, False), ({"record_listing": True}, True)]) +async def test_list_mcp_tools_records_the_catalog_only_when_asked( + listing_kwargs: dict[str, bool], recorded: bool +) -> None: + """The aggregate listing fills the caller's listed-tools slot only when asked: a listing an internal + caller never serves must not hand a later tools/call a description the caller never saw.""" + manager = operations.global_mcp_server_manager + server = MCPServer(server_id="listing-slot", name="listing-slot", transport=MCPTransport.http, url="http://slot") + user = UserAPIKeyAuth(api_key="sk-listing-slot", user_id="lister") + upstream = [MCPTool(name="echo", description="Echo text back", inputSchema={"type": "object"})] + with ( + patch.object(operations, "_get_allowed_mcp_servers", AsyncMock(return_value=[server])), + patch.object(manager, "_create_mcp_client", AsyncMock(return_value=object())), + patch.object(manager, "_fetch_tools_with_timeout", AsyncMock(return_value=upstream)), + patch.dict(manager.tool_name_to_mcp_server_name_mapping), + ): + try: + listing = await operations._list_mcp_tools(user_api_key_auth=user, **listing_kwargs) + listed = manager.get_listed_tool(server, "echo", ListedToolsCaller(user_api_key_auth=user)) + finally: + manager._drop_listed_tools(server.server_id) + assert [tool.name for tool in listing.tools] == ["listing-slot-echo"] + assert (listed is not None) is recorded diff --git a/tests/unit/proxy/auth/test_auth_checks_object_access_and_lookup.py b/tests/unit/proxy/auth/test_auth_checks_object_access_and_lookup.py index 6c8b6571991..059cff0c385 100644 --- a/tests/unit/proxy/auth/test_auth_checks_object_access_and_lookup.py +++ b/tests/unit/proxy/auth/test_auth_checks_object_access_and_lookup.py @@ -109,25 +109,6 @@ def set_salt_key(monkeypatch): monkeypatch.setenv("LITELLM_SALT_KEY", "sk-1234") -@pytest.fixture(autouse=True) -def reset_constants_module(): - """Reset constants module to ensure clean state before each test""" - import importlib - - from litellm import constants - from litellm.proxy.auth import auth_checks - - # Reload modules before test - importlib.reload(constants) - importlib.reload(auth_checks) - - yield - - # Reload modules after test to clean up - importlib.reload(constants) - importlib.reload(auth_checks) - - @pytest.fixture def valid_sso_user_defined_values(): return LiteLLM_UserTable( @@ -875,19 +856,10 @@ def test_get_cli_jwt_auth_token_default_expiration(valid_sso_user_defined_values def test_get_cli_jwt_auth_token_custom_expiration(valid_sso_user_defined_values, monkeypatch): - """Test generating CLI JWT token with custom expiration via environment variable""" - import importlib - - from litellm import constants + """Test generating a CLI JWT token with custom expiration via the configured constant""" from litellm.proxy.auth import auth_checks - # Set custom expiration to 48 hours - monkeypatch.setenv("LITELLM_CLI_JWT_EXPIRATION_HOURS", "48") - - # Reload the constants module to pick up the new env var - importlib.reload(constants) - # Also reload auth_checks to pick up the new constant value - importlib.reload(auth_checks) + monkeypatch.setattr(auth_checks, "CLI_JWT_EXPIRATION_HOURS", 48) token = auth_checks.ExperimentalUIJWTToken.get_cli_jwt_auth_token(valid_sso_user_defined_values) diff --git a/tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py b/tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py index fc8bc289735..8b33202b483 100644 --- a/tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py +++ b/tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py @@ -7321,15 +7321,10 @@ async def test_expired_cli_session_token_is_rejected(monkeypatch): on the shared validation path, not only for DB-backed keys.""" monkeypatch.delenv("EXPERIMENTAL_UI_LOGIN", raising=False) monkeypatch.setenv("LITELLM_SALT_KEY", "sk-salt-cli-test") - monkeypatch.setenv("LITELLM_CLI_JWT_EXPIRATION_HOURS", "-1") - import importlib - - from litellm import constants from litellm.proxy.auth import auth_checks - importlib.reload(constants) - importlib.reload(auth_checks) + monkeypatch.setattr(auth_checks, "CLI_JWT_EXPIRATION_HOURS", -1) user_info = LiteLLM_UserTable( user_id="cli-admin", @@ -7346,22 +7341,17 @@ async def test_expired_cli_session_token_is_rejected(monkeypatch): mock_request.headers = {"authorization": f"Bearer {cli_token}"} mock_request.query_params = {} - try: - with ( - patch("litellm.proxy.proxy_server.master_key", "sk-master"), - patch("litellm.proxy.proxy_server.prisma_client", None), - ): - with pytest.raises(ProxyException) as exc_info: - await user_api_key_auth( - request=mock_request, - api_key=f"Bearer {cli_token}", - ) + with ( + patch("litellm.proxy.proxy_server.master_key", "sk-master"), + patch("litellm.proxy.proxy_server.prisma_client", None), + ): + with pytest.raises(ProxyException) as exc_info: + await user_api_key_auth( + request=mock_request, + api_key=f"Bearer {cli_token}", + ) - assert exc_info.value.type == ProxyErrorTypes.expired_key - finally: - monkeypatch.delenv("LITELLM_CLI_JWT_EXPIRATION_HOURS", raising=False) - importlib.reload(constants) - importlib.reload(auth_checks) + assert exc_info.value.type == ProxyErrorTypes.expired_key @pytest.mark.asyncio diff --git a/tests/unit/proxy/guardrails/guardrail_hooks/test_agent_365.py b/tests/unit/proxy/guardrails/guardrail_hooks/test_agent_365.py index 23131321938..e72b716665c 100644 --- a/tests/unit/proxy/guardrails/guardrail_hooks/test_agent_365.py +++ b/tests/unit/proxy/guardrails/guardrail_hooks/test_agent_365.py @@ -346,6 +346,29 @@ class TestAllowFlow: assert evaluate_call.json["conversationId"] == "sess-123" assert evaluate_call.json["agentId"] == "my-agent-key" + @pytest.mark.asyncio + async def test_evaluate_payload_includes_listed_tool_metadata(self): + handler: Final = FakeHandler([_token_response(), _allow_response()]) + guardrail: Final = _make_guardrail(handler) + schema: Final = {"type": "object", "properties": {"to": {"type": "string"}}, "required": ["to"]} + await _run(guardrail, _mcp_data(mcp_tool_description="Send an email", mcp_input_schema=schema)) + assert handler.calls[1].json["tool"] == { + "name": "send_email", + "description": "Send an email", + "inputSchema": schema, + } + + @pytest.mark.asyncio + @pytest.mark.parametrize( + ("description", "schema"), + [(None, None), ("", None), (None, ["not", "a", "schema"]), (42, "type: object")], + ) + async def test_evaluate_payload_omits_missing_or_malformed_tool_metadata(self, description, schema): + handler: Final = FakeHandler([_token_response(), _allow_response()]) + guardrail: Final = _make_guardrail(handler) + await _run(guardrail, _mcp_data(mcp_tool_description=description, mcp_input_schema=schema)) + assert handler.calls[1].json["tool"] == {"name": "send_email"} + @pytest.mark.asyncio async def test_non_mcp_call_type_skipped(self): handler: Final = FakeHandler([]) diff --git a/tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py b/tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py index 8b9439e25d2..d3a723fe1d3 100644 --- a/tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py +++ b/tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py @@ -13,6 +13,7 @@ from typing import Any, Dict, Final, List, Optional import pytest from fastapi import HTTPException +from pydantic import TypeAdapter import litellm from litellm import Router @@ -21,6 +22,7 @@ from litellm.caching.in_memory_cache import InMemoryCache from litellm.constants import INTERNAL_CALL_ORIGIN_METADATA_KEY from litellm.proxy._types import UserAPIKeyAuth from litellm.proxy.common_utils.proxy_rate_limit_error import ProxyRateLimitError +from litellm.proxy.common_utils.user_api_key_cache import UserApiKeyCache from litellm.proxy.hooks.parallel_request_limiter_v3 import ( PARALLEL_REQUEST_SLOT_TTL_SECONDS, ParallelSlotAcquisition, @@ -39,6 +41,7 @@ from litellm.proxy.hooks.parallel_request_limiter_v3 import ( from litellm.proxy.utils import InternalUsageCache, ProxyLogging, hash_token from litellm.types.caching import RedisPipelineIncrementOperation from litellm.types.llms.openai import ResponsesAPIResponse +from litellm.types.mcp import MCPPreCallRequestObject from litellm.types.utils import ( EmbeddingResponse, ModelResponse, @@ -108,6 +111,159 @@ def test_api_key_descriptor_applies_budget_throttle( assert api_key_descriptor["rate_limit"]["tokens_per_unit"] == expected_tpm +@pytest.mark.asyncio +@pytest.mark.parametrize( + "description", [None, "Gateway metadata, not caller input. " * 100], ids=["unlisted", "listed"] +) +@pytest.mark.parametrize("arguments_rewritten", [False, True]) +async def test_mcp_description_does_not_change_admission_or_reserved_tokens( + description: str | None, arguments_rewritten: bool, monkeypatch: pytest.MonkeyPatch +) -> None: + cache: Final = DualCache() + handler: Final = _PROXY_MaxParallelRequestsHandler(internal_usage_cache=InternalUsageCache(cache)) + logger: Final = ProxyLogging(user_api_key_cache=UserApiKeyCache()) + schema: Final = {"type": "object", "properties": {"q": {"type": "string", "description": "Schema text " * 100}}} + request: Final = MCPPreCallRequestObject( + tool_name="echo", arguments={"q": "hello"}, tool_description=description, tool_input_schema=schema + ) + data: Final = TypeAdapter(dict[str, object]).validate_python(logger._convert_mcp_to_llm_format(request, {})) + messages: Final = data["messages"] + caller: Final = UserAPIKeyAuth(api_key=hash_token("sk-mcp-description-reservation"), tpm_limit=64) + + if arguments_rewritten: + data["mcp_arguments"] = {"q": "Transformed arguments " * 100} + monkeypatch.setattr(litellm, "callbacks", [handler]) + await logger.pre_call_hook(user_api_key_dict=caller, data=data, call_type="call_mcp_tool") + + stash: Final = get_request_stash() + assert stash is not None + assert stash.reserved_tokens == 25 + assert ( + await cache.async_get_cache( + key=handler.create_rate_limit_keys("api_key", caller.api_key, "tokens"), local_only=True + ) + == 25 + ) + assert data["messages"] is messages + assert data.get("mcp_tool_description") == description + assert data["mcp_input_schema"] == schema + assert messages == [ + { + "role": "user", + "content": "Tool: echo\nArguments: {'q': 'hello'}", + } + ] + + +@pytest.mark.asyncio +@pytest.mark.parametrize( + "description", [None, "Gateway metadata, not caller input. " * 100], ids=["unlisted", "listed"] +) +@pytest.mark.parametrize("itpm_limit,otpm_limit", [(64, 4096), (4096, 64), (4096, 4096)]) +@pytest.mark.parametrize("arguments_rewritten", [False, True]) +async def test_mcp_description_preserves_project_input_and_output_reservations( + description: str | None, itpm_limit: int, otpm_limit: int, + arguments_rewritten: bool, monkeypatch: pytest.MonkeyPatch +) -> None: + cache: Final = DualCache() + handler: Final = _PROXY_MaxParallelRequestsHandler(internal_usage_cache=InternalUsageCache(cache)) + logger: Final = ProxyLogging(user_api_key_cache=UserApiKeyCache()) + schema: Final = {"type": "object", "properties": {"q": {"type": "string", "description": "Schema text " * 100}}} + request: Final = MCPPreCallRequestObject( + tool_name="echo", arguments={"q": "hello"}, tool_description=description, tool_input_schema=schema + ) + data: Final = TypeAdapter(dict[str, object]).validate_python(logger._convert_mcp_to_llm_format(request, {})) + messages: Final = data["messages"] + base_data: Final[dict[str, object]] = { + "messages": [{"role": "user", "content": "Tool: echo\nArguments: {'q': 'hello'}"}] + } + expected_input: Final = handler._estimate_precise_input_tokens(base_data, "mcp-tool-call", "call_mcp_tool") + expected_output: Final = handler.no_max_tokens_output_floor(otpm_limit) + expected_combined: Final = handler._estimate_tokens_for_request( + base_data, min_configured_tpm_limit=4096, call_type="call_mcp_tool" + ) + caller: Final = UserAPIKeyAuth( + api_key=hash_token("sk-mcp-project-reservation"), + tpm_limit=4096, + project_id="mcp-project-reservation", + project_metadata={ + "model_itpm_limit": {"mcp-tool-call": itpm_limit}, + "model_otpm_limit": {"mcp-tool-call": otpm_limit}, + }, + ) + + if arguments_rewritten: + data["mcp_arguments"] = {"q": "Transformed arguments " * 100} + monkeypatch.setattr(litellm, "callbacks", [handler]) + await logger.pre_call_hook(user_api_key_dict=caller, data=data, call_type="call_mcp_tool") + + stash: Final = get_request_stash() + assert stash is not None + assert (stash.reserved_tokens, stash.itpm_reserved_tokens, stash.otpm_reserved_tokens) == ( + expected_combined, + expected_input, + expected_output, + ) + assert ( + await cache.async_get_cache( + key=handler.create_rate_limit_keys( + "model_per_project_itpm", f"{caller.project_id}:mcp-tool-call", "tokens" + ), + local_only=True, + ) + == expected_input + ) + assert ( + await cache.async_get_cache( + key=handler.create_rate_limit_keys( + "model_per_project_otpm", f"{caller.project_id}:mcp-tool-call", "tokens" + ), + local_only=True, + ) + == expected_output + ) + assert data["messages"] is messages + assert data.get("mcp_tool_description") == description + assert data["mcp_input_schema"] == schema + assert messages == [ + { + "role": "user", + "content": "Tool: echo\nArguments: {'q': 'hello'}", + } + ] + + +def test_llm_tpm_estimation_still_counts_messages_with_mcp_metadata() -> None: + handler: Final = _PROXY_MaxParallelRequestsHandler(internal_usage_cache=InternalUsageCache(DualCache())) + data: Final[dict[str, object]] = { + "messages": [{"role": "user", "content": "x" * 400}], + "max_tokens": 1, + "mcp_tool_name": "echo", + "mcp_arguments": {}, + } + assert handler._estimate_tokens_for_request(data, call_type="acompletion") == 101 + + +@pytest.mark.asyncio +async def test_unconverted_mcp_request_keeps_its_reservation() -> None: + cache: Final = DualCache() + handler: Final = _PROXY_MaxParallelRequestsHandler(internal_usage_cache=InternalUsageCache(cache)) + caller: Final = UserAPIKeyAuth(api_key=hash_token("sk-raw-mcp-request"), tpm_limit=64) + data: Final[dict[str, object]] = {"name": "echo", "arguments": {"q": "hello"}, "server_id": "fixture"} + + await handler.async_pre_call_hook(user_api_key_dict=caller, cache=cache, data=data, call_type="call_mcp_tool") + + stash: Final = get_request_stash() + assert stash is not None + assert stash.reserved_tokens == 16 + assert ( + await cache.async_get_cache( + key=handler.create_rate_limit_keys("api_key", caller.api_key, "tokens"), local_only=True + ) + == 16 + ) + + @pytest.mark.flaky(reruns=3) @pytest.mark.asyncio async def test_sliding_window_rate_limit_v3(monkeypatch, time_controller): diff --git a/tests/unit/proxy/lens/test_release.py b/tests/unit/proxy/lens/test_release.py index 95d637465c4..a47a84744a7 100644 --- a/tests/unit/proxy/lens/test_release.py +++ b/tests/unit/proxy/lens/test_release.py @@ -21,6 +21,13 @@ def test_private_registry_override_keeps_its_exact_digest(monkeypatch: pytest.Mo assert worker_image() == image +def test_source_build_uses_the_separate_development_package(monkeypatch: pytest.MonkeyPatch) -> None: + tag: Final = "sha-" + "a" * 40 + monkeypatch.setenv("LITELLM_RELEASE_TAG", tag) + monkeypatch.delenv("LENS_WORKER_IMAGE", raising=False) + assert worker_image() == f"ghcr.io/berriai/litellm-lens-worker-dev:{tag}" + + @pytest.mark.parametrize( "installed,expected", (("1.2.3", "v1.2.3"), ("1.2.3rc4", "v1.2.3-rc.4"), ("1.2.3.dev5", "v1.2.3-dev.5")), diff --git a/tests/unit/proxy/test_custom_proxy.py b/tests/unit/proxy/test_custom_proxy.py index b646a4e80e7..a08ceccd4f3 100644 --- a/tests/unit/proxy/test_custom_proxy.py +++ b/tests/unit/proxy/test_custom_proxy.py @@ -1,52 +1,45 @@ import os +from typing import Final import uvicorn from dotenv import load_dotenv -from fastapi import FastAPI, Request +from fastapi import FastAPI from fastapi.middleware.cors import CORSMiddleware -from fastapi.responses import JSONResponse - -load_dotenv() - -# Set the SERVER_ROOT_PATH environment variable to match the custom mount path -os.environ["SERVER_ROOT_PATH"] = "/my-custom-path" - -from litellm.proxy.proxy_server import app as litellm_app -from litellm.proxy.proxy_server import proxy_startup_event - -# Create main FastAPI app -app = FastAPI(title="Custom LiteLLM Server", lifespan=proxy_startup_event) - -# Add CORS middleware -app.add_middleware( - CORSMiddleware, - allow_origins=["*"], - allow_credentials=True, - allow_methods=["*"], - allow_headers=["*"], -) - -custom_path = "/my-custom-path" - -# Mount LiteLLM app at /litellm -app.mount(custom_path, litellm_app) -# Default route at / -@app.get("/") -async def root(): - return { - "message": "Welcome to the API Gateway", - "litellm_endpoint": f"{custom_path}", - } +def build_app() -> FastAPI: + load_dotenv() + os.environ["SERVER_ROOT_PATH"] = "/my-custom-path" + from litellm.proxy.proxy_server import app as litellm_app + from litellm.proxy.proxy_server import proxy_startup_event -# Health check endpoint -@app.get("/health") -async def health_check(): - return {"status": "healthy"} + app: Final = FastAPI(title="Custom LiteLLM Server", lifespan=proxy_startup_event) + custom_path: Final = "/my-custom-path" + + app.add_middleware( + CORSMiddleware, + allow_origins=["*"], + allow_credentials=True, + allow_methods=["*"], + allow_headers=["*"], + ) + + app.mount(custom_path, litellm_app) + + @app.get("/") + async def root() -> dict[str, str]: + return { + "message": "Welcome to the API Gateway", + "litellm_endpoint": custom_path, + } + + @app.get("/health") + async def health_check() -> dict[str, str]: + return {"status": "healthy"} + + return app if __name__ == "__main__": - # Run the server on port 8000 - uvicorn.run(app, host="0.0.0.0", port=4000, log_level="info") + uvicorn.run(build_app(), host="0.0.0.0", port=4000, log_level="info") diff --git a/tests/unit/proxy/utils/proxy_logging/test_mcp_bridging.py b/tests/unit/proxy/utils/proxy_logging/test_mcp_bridging.py index c5bd89645b4..25be3b5de6b 100644 --- a/tests/unit/proxy/utils/proxy_logging/test_mcp_bridging.py +++ b/tests/unit/proxy/utils/proxy_logging/test_mcp_bridging.py @@ -403,6 +403,26 @@ def test_create_mcp_request_object_from_kwargs_full(proxy_logging, make_user_api assert snapshot == {"tool_name": "calc", "arguments": {"x": 1}, "server_name": "math", "auth_user_id": "u-1"} +def test_mcp_tool_metadata_flows_from_kwargs_to_synthetic_data(proxy_logging): + schema = {"type": "object", "properties": {"x": {"type": "integer"}}} + obj = proxy_logging._create_mcp_request_object_from_kwargs( + kwargs={ + "name": "calc", + "arguments": {"x": 1}, + "tool_description": "Adds numbers", + "tool_input_schema": schema, + } + ) + out = proxy_logging._convert_mcp_to_llm_format(request_obj=obj, kwargs={}) + assert (out["mcp_tool_description"], out["mcp_input_schema"]) == ("Adds numbers", schema) + + +def test_mcp_tool_metadata_absent_when_tool_was_never_listed(proxy_logging): + obj = proxy_logging._create_mcp_request_object_from_kwargs(kwargs={"name": "calc", "arguments": {}}) + out = proxy_logging._convert_mcp_to_llm_format(request_obj=obj, kwargs={}) + assert "mcp_tool_description" not in out and "mcp_input_schema" not in out + + def test_create_mcp_request_object_from_kwargs_empty(proxy_logging): obj = proxy_logging._create_mcp_request_object_from_kwargs(kwargs={}) snapshot = { diff --git a/tests/unit/responses/mcp/test_litellm_proxy_mcp_handler.py b/tests/unit/responses/mcp/test_litellm_proxy_mcp_handler.py index 2699f9445c9..73bee304fc2 100644 --- a/tests/unit/responses/mcp/test_litellm_proxy_mcp_handler.py +++ b/tests/unit/responses/mcp/test_litellm_proxy_mcp_handler.py @@ -1,10 +1,11 @@ +import asyncio import importlib import subprocess import sys import textwrap import types -from typing import Any, Final, cast -from unittest.mock import AsyncMock, MagicMock +from typing import Any, Final, Literal, cast +from unittest.mock import AsyncMock, MagicMock, patch import pytest from fastapi import HTTPException @@ -12,15 +13,26 @@ from mcp.types import CallToolResult, TextContent from mcp.types import Tool as MCPTool from openai.types.responses.tool_param import Mcp +import litellm +from litellm.caching.caching import DualCache +from litellm.integrations.custom_guardrail import CustomGuardrail +from litellm.litellm_core_utils.litellm_logging import Logging +from litellm.proxy._experimental.mcp_server import operations as mcp_operations from litellm.proxy._experimental.mcp_server.faults.list_outcomes import AggregateToolListing +from litellm.proxy._experimental.mcp_server.mcp_server_manager import ListedToolsCaller, MCPServerManager +from litellm.proxy._types import UserAPIKeyAuth +from litellm.proxy.utils import ProxyLogging from litellm.responses import main as responses_main from litellm.responses.mcp import litellm_proxy_mcp_handler as mcp_handler_module from litellm.responses.mcp.litellm_proxy_mcp_handler import ( LiteLLM_Proxy_MCP_Handler, ) +from litellm.types.guardrails import GuardrailEventHooks from litellm.types.llms.openai import ResponsesAPIResponse +from litellm.types.mcp import MCPTransport +from litellm.types.mcp_server.mcp_server_manager import MCPServer from litellm.types.responses.main import OutputFunctionToolCall -from litellm.types.utils import ModelResponse +from litellm.types.utils import GenericGuardrailAPIInputs, ModelResponse class _DummyMCPResult: @@ -1310,6 +1322,167 @@ async def test_responses_discovery_logs_sanitized_caller_headers(monkeypatch: py assert headers["x-mcp-deepwiki-authorization"] == "upstream-sentinel" +@pytest.mark.asyncio +@pytest.mark.parametrize("real_listing", [False, True]) +@pytest.mark.parametrize( + ("allowed_tools", "expected_names"), + [ + ([], ["responses_slot-echo", "responses_slot-status"]), + (["echo"], ["responses_slot-echo"]), + (["responses_slot-echo"], ["responses_slot-echo"]), + (["absent"], []), + ], +) +async def test_bridge_listing_leaves_the_callers_catalog_unchanged( + monkeypatch: pytest.MonkeyPatch, allowed_tools: list[str], expected_names: list[str], real_listing: bool +) -> None: + manager: Final = mcp_operations.global_mcp_server_manager + server: Final = MCPServer( + server_id="responses-slot", name="responses_slot", alias="responses_slot", transport=MCPTransport.http + ) + user: Final = UserAPIKeyAuth(api_key="sk-responses-slot", user_id="responder") + upstream: Final = [ + MCPTool(name="echo", description="Echo text back", inputSchema={"type": "object"}), + MCPTool(name="status", description="Report status", inputSchema={"type": "object"}), + MCPTool(name="echo", description="Duplicate echo", inputSchema={"type": "object", "properties": {}}), + ] + fake_manager: Final = types.SimpleNamespace( + get_registry=MagicMock(return_value={}), + get_allowed_mcp_servers=AsyncMock(return_value=[]), + get_mcp_servers_from_ids=MagicMock(return_value=[]), + get_mcp_server_by_name=MagicMock(return_value=None), + ) + monkeypatch.setattr( + "litellm.proxy._experimental.mcp_server.mcp_server_manager.global_mcp_server_manager", + fake_manager, + ) + with ( + patch.dict(manager.tool_name_to_mcp_server_name_mapping), + patch.object(mcp_operations, "_get_allowed_mcp_servers", AsyncMock(return_value=[server])), + patch.object(manager, "_create_mcp_client", AsyncMock(return_value=object())), + patch.object(manager, "_fetch_tools_with_timeout", AsyncMock(return_value=upstream)), + ): + try: + if real_listing: + await manager._get_tools_from_server(server, user_api_key_auth=user, record_listing=True) + caller: Final = ListedToolsCaller(user_api_key_auth=user) + before: Final = { + tool.name: (listed.description, listed.input_schema) + for tool in upstream + if (listed := manager.get_listed_tool(server, tool.name, caller)) is not None + } + assert bool(before) is real_listing + tools, _server_names = await LiteLLM_Proxy_MCP_Handler._process_mcp_tools_without_openai_transform( + user_api_key_auth=user, + mcp_tools_with_litellm_proxy=[ + { + "type": "mcp", + "server_url": "litellm_proxy/mcp/responses-slot", + "allowed_tools": allowed_tools, + } + ], + ) + recorded: Final = { + tool.name: (listed.description, listed.input_schema) + for tool in upstream + if (listed := manager.get_listed_tool(server, tool.name, caller)) is not None + } + assert recorded == before + assert ( + manager.get_listed_tool( + server, "echo", ListedToolsCaller(user_api_key_auth=UserAPIKeyAuth(api_key="sk-other-caller")) + ) + is None + ) + finally: + manager._drop_listed_tools(server.server_id) + + assert [tool.name for tool in tools] == expected_names + + +class _BridgeMetadataGuardrail(CustomGuardrail): + def __init__(self) -> None: + super().__init__(guardrail_name="bridge-metadata", event_hook=GuardrailEventHooks.pre_mcp_call, default_on=True) + self.calls: tuple[tuple[object, object], ...] = () + + async def apply_guardrail( + self, + inputs: GenericGuardrailAPIInputs, + request_data: dict[str, object], + input_type: Literal["request", "response"], + logging_obj: Logging | None = None, + ) -> GenericGuardrailAPIInputs: + if request_data.get("mcp_arguments") == {"probe": "bridge"}: + self.calls += ((request_data.get("mcp_tool_description"), request_data.get("mcp_input_schema")),) + return inputs + + +@pytest.mark.asyncio +async def test_concurrent_bridge_calls_use_their_own_served_metadata(monkeypatch: pytest.MonkeyPatch) -> None: + manager: Final = MCPServerManager() + server: Final = MCPServer(server_id="bridge", name="bridge", transport=MCPTransport.http, url="http://upstream") + manager.registry = {server.server_id: server} + user: Final = UserAPIKeyAuth(api_key="sk-bridge", user_id="bridge-user") + upstream: Final = [ + MCPTool( + name="echo", + description="Echo text", + inputSchema={"type": "object", "properties": {"text": {"type": "string"}}}, + ), + MCPTool(name="status", description="Read status", inputSchema={"type": "object"}), + ] + client: Final = AsyncMock() + client.call_tool.return_value = CallToolResult(content=[TextContent(type="text", text="ok")]) + manager._create_mcp_client = AsyncMock(return_value=client) + manager._fetch_tools_with_timeout = AsyncMock(return_value=upstream) + guardrail: Final = _BridgeMetadataGuardrail() + logger: Final = ProxyLogging(user_api_key_cache=DualCache()) + monkeypatch.setattr(litellm, "callbacks", [guardrail]) + monkeypatch.setattr("litellm.proxy.proxy_server.proxy_logging_obj", logger) + monkeypatch.setattr(mcp_operations, "global_mcp_server_manager", manager) + monkeypatch.setattr(mcp_operations, "_get_allowed_mcp_servers", AsyncMock(return_value=[server])) + monkeypatch.setattr("litellm.proxy._experimental.mcp_server.mcp_server_manager.global_mcp_server_manager", manager) + first_listed: Final = asyncio.Event() + second_listed: Final = asyncio.Event() + + async def bridge(name: str, first: bool) -> None: + if not first: + await first_listed.wait() + tools, server_map = await LiteLLM_Proxy_MCP_Handler._process_mcp_tools_without_openai_transform( + user_api_key_auth=user, + mcp_tools_with_litellm_proxy=[ + {"type": "mcp", "server_url": "litellm_proxy/mcp/bridge", "allowed_tools": [name]} + ], + ) + (first_listed if first else second_listed).set() + await second_listed.wait() + result: Final = await LiteLLM_Proxy_MCP_Handler._execute_tool_calls( + tool_server_map=server_map, + tool_calls=[ + {"type": "function_call", "name": f"bridge-{name}", "arguments": '{"probe":"bridge"}', "call_id": name} + ], + user_api_key_auth=user, + served_tools=tools, + ) + assert [entry["result"] for entry in result] == ["ok"] + + try: + await asyncio.gather(bridge("echo", True), bridge("status", False)) + assert sorted(guardrail.calls, key=str) == sorted( + ((tool.description, tool.input_schema) for tool in upstream), key=str + ) + await manager.call_tool("bridge", "echo", {"probe": "bridge"}, user_api_key_auth=user, proxy_logging_obj=logger) + assert guardrail.calls[-1] == (None, None) + await manager._get_tools_from_server( + server, user_api_key_auth=user, proxy_logging_obj=logger, record_listing=True + ) + await manager.call_tool("bridge", "echo", {"probe": "bridge"}, user_api_key_auth=user, proxy_logging_obj=logger) + assert guardrail.calls[-1] == (upstream[0].description, upstream[0].input_schema) + finally: + manager._drop_listed_tools(server.server_id) + ProxyLogging._callback_capabilities_cache.clear() + + def _toolset_gateway_manager(toolset_id: str, server_id: str) -> types.SimpleNamespace: return types.SimpleNamespace( get_registry=MagicMock(return_value={}), diff --git a/tests/unit/test_constants.py b/tests/unit/test_constants.py index 12e473f68a4..d5981b906a3 100644 --- a/tests/unit/test_constants.py +++ b/tests/unit/test_constants.py @@ -68,3 +68,36 @@ def _build_constant_env_var_map() -> dict[str, str]: env_var_map[constant_name] = env_var_name return env_var_map + + +@pytest.mark.parametrize( + ("cli_value", "litellm_cli_value", "expected"), + [ + ("48", None, 48), + (None, "48", 48), + (None, None, 24), + ("48", "72", 48), + ], + ids=("canonical-only", "alias-only", "default", "canonical-wins"), +) +def test_cli_jwt_expiration_hours_from_environment( + monkeypatch: pytest.MonkeyPatch, + cli_value: str | None, + litellm_cli_value: str | None, + expected: int, +) -> None: + monkeypatch.delenv("CLI_JWT_EXPIRATION_HOURS", raising=False) + monkeypatch.delenv("LITELLM_CLI_JWT_EXPIRATION_HOURS", raising=False) + + try: + if cli_value is not None: + monkeypatch.setenv("CLI_JWT_EXPIRATION_HOURS", cli_value) + if litellm_cli_value is not None: + monkeypatch.setenv("LITELLM_CLI_JWT_EXPIRATION_HOURS", litellm_cli_value) + + importlib.reload(litellm.constants) + assert litellm.constants.CLI_JWT_EXPIRATION_HOURS == expected + finally: + monkeypatch.delenv("CLI_JWT_EXPIRATION_HOURS", raising=False) + monkeypatch.delenv("LITELLM_CLI_JWT_EXPIRATION_HOURS", raising=False) + importlib.reload(litellm.constants) diff --git a/tests/unit/test_lens_dev.py b/tests/unit/test_lens_dev.py index cbc8aced8ac..af61734731e 100644 --- a/tests/unit/test_lens_dev.py +++ b/tests/unit/test_lens_dev.py @@ -163,3 +163,84 @@ def test_cleanup_kills_child_process_trees(tmp_path): assert proc.returncode == 0, proc.stderr assert "lens-dev: stopping" in proc.stdout assert proc.stdout.strip().endswith("CLEAN") + + +def test_seed_only_uses_local_credentials_and_profile(tmp_path: Path) -> None: + proc = _run( + tmp_path, + "parse_args --seed-only --seed large --copies 7; master_key=sk-local; " + 'py() { env; printf "%s\\n" "$@"; }; py=py; seed_data', + ) + assert proc.returncode == 0, proc.stderr + assert "LITELLM_MASTER_KEY=sk-local" in proc.stdout + assert "PROXY_BASE_URL=http://localhost:4000" in proc.stdout + assert "CLICKHOUSE_DATABASE=litellm" in proc.stdout + assert "--profile\nlarge\n--copies\n7" in proc.stdout + + +def test_seed_arguments_reject_invalid_counts_before_startup(tmp_path: Path) -> None: + proc = _run(tmp_path, "parse_args --seed large --copies 0") + assert proc.returncode == 1 + assert "positive integer" in proc.stderr + + +def test_seed_only_defaults_to_small_profile(tmp_path: Path) -> None: + proc = _run(tmp_path, 'parse_args --seed-only; echo "$seed_profile $seed_only"') + assert proc.returncode == 0, proc.stderr + assert proc.stdout.strip() == "default 1" + + +def test_seed_only_with_no_cli_count_preserves_env_controls(tmp_path: Path) -> None: + proc = _run( + tmp_path, + "parse_args --seed-only; master_key=sk-local; py() { " + 'printf "%s %s %s\\n" "$LENS_DEV_SEED_COPIES" "$LENS_DEV_SEED_BATCH_COPIES" "$@"; }; py=py; seed_data', + LENS_DEV_SEED_COPIES="3", + LENS_DEV_SEED_BATCH_COPIES="1", + ) + assert proc.returncode == 0, proc.stderr + assert proc.stdout.startswith("3 1 -m") + + +def test_proxy_uses_this_checkouts_ui_build(tmp_path: Path) -> None: + proc = _run(tmp_path, 'proxy_env "export LITELLM_UI_PATH=/old/build"; echo "$LITELLM_UI_PATH"') + assert proc.returncode == 0, proc.stderr + assert proc.stdout.strip() == str(ROOT / "ui/litellm-dashboard/out") + + +def test_dashboard_build_uses_same_origin_and_captures_failures(tmp_path: Path) -> None: + dashboard = tmp_path / "ui/litellm-dashboard" + dashboard.mkdir(parents=True) + scripts = tmp_path / "scripts" + scripts.mkdir() + runner = scripts / "with_dashboard_node.sh" + runner.write_text('#!/bin/sh\nprintf "base=%s args=%s\\n" "$NEXT_PUBLIC_BASE_URL" "$*"\nexit "$BUILD_STATUS"\n') + runner.chmod(0o755) + snippet = f'repo_root="{tmp_path}"; mkdir -p "$log_dir"; build_dashboard' + success = _run(tmp_path, snippet, BUILD_STATUS="0", LENS_DEV_BUILD_UI="1", NEXT_PUBLIC_BASE_URL="http://old-proxy") + assert success.returncode == 0, success.stderr + log = tmp_path / "state/logs/ui-build.log" + assert log.read_text().strip() == "base= args=npm run build" + failure = _run(tmp_path, snippet, BUILD_STATUS="1", LENS_DEV_BUILD_UI="1") + assert failure.returncode == 1 + assert "UI build failed" in failure.stderr + + +def test_skipping_ui_build_needs_no_static_export(tmp_path: Path) -> None: + proc = _run(tmp_path, f'repo_root="{tmp_path}"; build_dashboard', LENS_DEV_BUILD_UI="0") + assert proc.returncode == 0, proc.stderr + assert not (tmp_path / "ui/litellm-dashboard/out").exists() + + +def test_ui_readiness_uses_live_login_route(tmp_path: Path) -> None: + proc = _run(tmp_path, 'wait_for_ui "$$"', LENS_DEV_UI_PORT="3017") + assert proc.returncode == 0, proc.stderr + assert "http://localhost:3017/ui/login/" in _curl_calls(tmp_path) + + +def test_ui_exit_fails_before_readiness_request(tmp_path: Path) -> None: + proc = _run(tmp_path, 'true & child=$!; wait "$child"; wait_for_ui "$child"') + assert proc.returncode == 1 + assert "UI exited; see" in proc.stderr + assert "ui.log" in proc.stderr + assert _curl_calls(tmp_path) == "" diff --git a/tests/unit/test_seed_tracing_fixtures.py b/tests/unit/test_seed_tracing_fixtures.py index de29a595d98..30cfde9feec 100644 --- a/tests/unit/test_seed_tracing_fixtures.py +++ b/tests/unit/test_seed_tracing_fixtures.py @@ -4,23 +4,30 @@ from datetime import datetime from itertools import chain from pathlib import Path from typing import Final +from unittest.mock import AsyncMock +import httpx import pytest -from prisma import Json +from prisma import Json, Prisma from pydantic import InstanceOf, TypeAdapter -from litellm.rust_bridge.trace.storage import span_rows +from litellm.rust_bridge.trace.storage import Tenant, span_rows from litellm.tracing.types import SpendLogRecord from scripts.seed_tracing_fixtures import ( JSON, TRACE_FIXTURES, + TenantIdentity, + bulk_span_rows, fixture_capture, fixture_replays, postgres_row, rebase, rebase_spend, + replay_batches, response_ids, response_pattern, + seed_arguments, + seed_batch, seed_id, spend_fixtures, timestamps, @@ -76,9 +83,9 @@ def test_all_fixture_replays_are_recent_and_preserve_spans(path: Path) -> None: @pytest.mark.requires_rust_extension def test_replay_preserves_trace_topology_usage_and_event_timing() -> None: - export: Final = JSON.validate_json((TRACE_FIXTURES / "deeplite_swarm.json").read_bytes()) + export: Final = JSON.validate_json((TRACE_FIXTURES / "deepagents_swarm.json").read_bytes()) original: Final = span_rows(json.dumps(export).encode(), "application/json") - spend_rows: Final = dict(spend_fixtures())["deeplite_swarm"] + spend_rows: Final = dict(spend_fixtures())["deepagents_swarm"] pattern: Final = re.compile("|".join(re.escape(row["response_id"]) for row in spend_rows)) shifted: Final = rebase(export, 123_000_000, "first-run", pattern) replayed: Final = span_rows(json.dumps(shifted).encode(), "application/json") @@ -102,36 +109,8 @@ def test_replay_preserves_trace_topology_usage_and_event_timing() -> None: ) -@pytest.mark.requires_rust_extension -def test_paired_fixture_joins_every_successful_llm_span_after_replay() -> None: - export: Final = JSON.validate_json((TRACE_FIXTURES / "deeplite_swarm.json").read_bytes()) - spends: Final = dict(spend_fixtures())["deeplite_swarm"] - pattern: Final = re.compile("|".join(re.escape(row["response_id"]) for row in spends)) - replays: Final = fixture_replays(TRACE_FIXTURES, max(timestamps(export)) // 1_000_000 + 1123, "paired-run", pattern) - replay: Final = next(item for item in replays if item.name == "deeplite_swarm") - rebased_spends: Final = rebase_spend(spends, replay.offset_ms, replay.namespace, pattern) - spans: Final = span_rows(json.dumps(replay.export).encode(), "application/json") - llm_spans: Final = tuple(span for span in spans if span["ObservationType"] == "llm") - by_response: Final = {row["response_id"]: row for row in rebased_spends} - - assert len(by_response) == len(llm_spans) == len(rebased_spends) - assert frozenset(by_response) == frozenset(span["LiteLLMRequestId"] for span in llm_spans) - for span, spend in ((span, by_response[span["LiteLLMRequestId"]]) for span in llm_spans): - assert spend["request_id"] == span["LiteLLMRequestId"] - assert spend["trace_id"] == spend["session_id"] == span["TraceId"] - assert spend["span_id"] == span["SpanId"] - assert spend["start_time"] == span["Timestamp"] // 1_000_000 - assert spend["end_time"] == (span["Timestamp"] + span["Duration"]) // 1_000_000 - assert spend["prompt_tokens"] == span["InputTokens"] - assert spend["completion_tokens"] == span["OutputTokens"] - assert spend["total_tokens"] == spend["prompt_tokens"] + spend["completion_tokens"] - assert json.loads(spend["response"])["id"] == spend["response_id"] - assert json.loads(spend["response"])["usage"]["total_tokens"] == spend["total_tokens"] - assert json.loads(spend["metadata"])["synthetic_spend"] is True - - def test_postgres_rows_preserve_clickhouse_cost_identity_and_payloads() -> None: - spends: Final = dict(spend_fixtures())["deeplite_swarm"] + spends: Final = dict(spend_fixtures())["deepagents_swarm"] for spend, postgres in ((spend, postgres_row(spend)) for spend in spends): start_time, end_time = DATETIMES.validate_python((postgres["startTime"], postgres["endTime"])) @@ -143,7 +122,7 @@ def test_postgres_rows_preserve_clickhouse_cost_identity_and_payloads() -> None: spend["api_key"], spend["team_id"], spend["user"], - spend["trace_id"], + spend["session_id"], ) assert postgres["spend"] == spend["spend"] assert postgres["total_tokens"] == spend["prompt_tokens"] + spend["completion_tokens"] @@ -156,7 +135,7 @@ def test_postgres_rows_preserve_clickhouse_cost_identity_and_payloads() -> None: @pytest.mark.requires_rust_extension -@pytest.mark.parametrize("name,spends", tuple(item for item in spend_fixtures() if item[0] != "deeplite_swarm")) +@pytest.mark.parametrize("name,spends", spend_fixtures()) def test_captured_spend_replay_preserves_real_cost_and_call_identity( name: str, spends: tuple[SpendLogRecord, ...] ) -> None: @@ -184,7 +163,7 @@ def test_captured_spend_replay_preserves_real_cost_and_call_identity( if before["litellm_call_id"]: assert after["litellm_call_id"] != before["litellm_call_id"] identities: Final = frozenset(f"provider_response:{identity}" for identity in response_ids((after,))) | { - f"litellm_request:{after["litellm_call_id"]}" + f"litellm_request:{after['litellm_call_id']}" } assert bool(identities & keys) is capture.spend_linked @@ -193,9 +172,81 @@ def test_captured_spend_replay_preserves_real_cost_and_call_identity( def test_spend_fixture_loading_preserves_gateway_ids_and_defaults_legacy_rows( tmp_path: Path, call_id: str | None ) -> None: - original: Final = dict(spend_fixtures())["deeplite_swarm"][0] + original: Final = dict(spend_fixtures())["deepagents_swarm"][0] fields: Final = {key: value for key, value in original.items() if key != "litellm_call_id"} supplied: Final = fields if call_id is None else {**fields, "litellm_call_id": call_id} (tmp_path / "example_spend_logs.jsonl").write_text(json.dumps(supplied) + "\n") loaded: Final = spend_fixtures(tmp_path) assert loaded == (("example", ({**original, "litellm_call_id": call_id or ""},)),) + + +@pytest.mark.requires_rust_extension +def test_bulk_export_preserves_all_spans_and_disjoint_copy_ids() -> None: + first: Final = fixture_replays(TRACE_FIXTURES, 1_800_000_000_000, "copy-1", re.compile(r"(?!)")) + second: Final = fixture_replays(TRACE_FIXTURES, 1_800_000_001_000, "copy-2", re.compile(r"(?!)")) + merged: Final = bulk_span_rows(first + second, Tenant("", "")) + separate: Final = tuple( + span for replay in first + second for span in span_rows(json.dumps(replay.export).encode(), "application/json") + ) + assert tuple(merged) == separate + first_ids: Final = frozenset(span["TraceId"] for span in bulk_span_rows(first, Tenant("", ""))) + second_ids: Final = frozenset(span["TraceId"] for span in bulk_span_rows(second, Tenant("", ""))) + assert first_ids.isdisjoint(second_ids) + + +@pytest.mark.requires_rust_extension +@pytest.mark.asyncio +async def test_bulk_seed_stamps_authenticated_tenant_and_writes_both_stores() -> None: + from litellm.rust_bridge.trace.storage import ClickHouseStorage, Tenant + + fixtures: Final = spend_fixtures() + pattern: Final = response_pattern(tuple(chain.from_iterable(rows for _, rows in fixtures))) + replays: Final = fixture_replays(TRACE_FIXTURES, 1_800_000_000_000, "bulk", pattern) + storage: Final = AsyncMock(spec=ClickHouseStorage) + database: Final = AsyncMock(spec=Prisma, litellm_spendlogs=AsyncMock()) + tenant: Final = TenantIdentity(team_id="local-team", api_key="local-hash", user="admin") + async with httpx.AsyncClient() as client: + result: Final = await seed_batch(client, storage, database, replays, fixtures, pattern, tenant, False) + assert result == tenant + trace_table, trace_rows = storage.insert_rows.call_args_list[0].args + assert trace_table == "otel_traces" + assert trace_rows == bulk_span_rows(replays, Tenant("local-team", "local-hash", user_id="admin")) + table, rows = storage.insert_rows.call_args_list[1].args + assert table == "spend_logs" + assert len(rows) == sum(len(original) for _, original in fixtures) + assert all((row["team_id"], row["api_key"], row["user"]) == ("local-team", "local-hash", "admin") for row in rows) + saved: Final = database.litellm_spendlogs.create_many.call_args.kwargs["data"] + assert tuple(row["request_id"] for row in saved) == tuple(row["request_id"] for row in rows) + assert tuple(row["spend"] for row in saved) == tuple(row["spend"] for row in rows) + storage.query_sql.assert_not_called() + + +def test_seed_cli_rejects_nonpositive_copies() -> None: + with pytest.raises(SystemExit) as error: + seed_arguments(["--copies", "0"]) + assert error.value.code == 2 + assert seed_arguments(["--profile", "large", "--copies", "5"]).copies == 5 + + +def test_bulk_batches_cover_every_copy_including_partial_tail() -> None: + batches: Final = tuple(replay_batches(8, 1_800_000_000_000, "batch", re.compile(r"(?!)"), 3)) + assert tuple(stop for stop, _ in batches) == (4, 7, 8) + expected: Final = tuple( + tuple(fixture_replays(TRACE_FIXTURES, 1_800_000_000_000 - index * 1000, f"batch-{index}", re.compile(r"(?!)"))) + for index in range(1, 8) + ) + assert tuple(chain.from_iterable(replays for _, replays in batches)) == tuple(chain.from_iterable(expected)) + + +def test_seed_cli_rejects_nonpositive_batch_size() -> None: + with pytest.raises(SystemExit) as error: + seed_arguments(["--batch-copies", "0"]) + assert error.value.code == 2 + assert seed_arguments(["--batch-copies", "2"]).batch_copies == 2 + + +@pytest.mark.parametrize("timeout", ("0", "-1", "inf", "nan")) +def test_seed_cli_rejects_invalid_http_timeouts(timeout: str) -> None: + with pytest.raises(SystemExit) as error: + seed_arguments(["--timeout-seconds", timeout]) + assert error.value.code == 2 diff --git a/tests/unit/test_tool_loop.py b/tests/unit/test_tool_loop.py new file mode 100644 index 00000000000..c2aee58bb5f --- /dev/null +++ b/tests/unit/test_tool_loop.py @@ -0,0 +1,420 @@ +import json +from typing import Final + +import httpx +import pytest +import respx + +import litellm +from litellm.tool_loop import ToolLoopMaxRoundsExceeded +from litellm.types.llms.openai import ChatCompletionToolMessage +from litellm.types.utils import ChatCompletionMessageToolCall + +OPENAI_CHAT_COMPLETIONS_URL: Final = "https://api.openai.com/v1/chat/completions" +WEATHER_TOOLS: Final = ( + { + "type": "function", + "function": { + "name": "get_weather", + "description": "Get the weather for a city", + "parameters": { + "type": "object", + "properties": {"city": {"type": "string"}}, + "required": ["city"], + }, + }, + }, +) + + +def _openai_response(content: str | None, tool_calls: list | None = None) -> dict: + return { + "id": "chatcmpl-tool-loop", + "object": "chat.completion", + "created": 1739462947, + "model": "gpt-5-mini", + "choices": [ + { + "index": 0, + "finish_reason": "tool_calls" if tool_calls else "stop", + "message": { + "role": "assistant", + "content": content, + "tool_calls": tool_calls, + }, + } + ], + "usage": {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15}, + } + + +def _tool_call(call_id: str, name: str, arguments: dict) -> dict: + return { + "id": call_id, + "type": "function", + "function": {"name": name, "arguments": json.dumps(arguments)}, + } + + +def _tool_result(tool_call: ChatCompletionMessageToolCall) -> ChatCompletionToolMessage: + return ChatCompletionToolMessage(role="tool", content='{"temp": "72F"}', tool_call_id=tool_call.id or "") + + +def _request_bodies(respx_mock: respx.MockRouter) -> list[dict]: + return [json.loads(call.request.content) for call in respx_mock.calls] + + +def test_final_answer_without_tool_calls_returns_content(respx_mock: respx.MockRouter) -> None: + route: Final = respx_mock.post(OPENAI_CHAT_COMPLETIONS_URL).mock( + return_value=httpx.Response(200, json=_openai_response("done")) + ) + executor_called: Final = [] + + def executor(tc: ChatCompletionMessageToolCall) -> ChatCompletionToolMessage: + executor_called.append(tc) + return _tool_result(tc) + + answer: Final = litellm.run_tool_loop( + model="openai/gpt-5-mini", + messages=[{"role": "user", "content": "hi"}], + tools=WEATHER_TOOLS, + execute_tool=executor, + api_key="sk-test", + ) + + assert answer == "done" + assert executor_called == [] + assert route.call_count == 1 + + +def test_two_rounds_appends_assistant_and_tool_messages_in_order(respx_mock: respx.MockRouter) -> None: + tool_calls: Final = [ + _tool_call("call_1", "get_weather", {"city": "Paris"}), + _tool_call("call_2", "get_weather", {"city": "Tokyo"}), + ] + route: Final = respx_mock.post(OPENAI_CHAT_COMPLETIONS_URL).mock( + side_effect=[ + httpx.Response(200, json=_openai_response(None, tool_calls)), + httpx.Response(200, json=_openai_response("Paris 72F, Tokyo 60F")), + ] + ) + executed: Final = [] + + def executor(tc: ChatCompletionMessageToolCall) -> ChatCompletionToolMessage: + executed.append(tc) + return _tool_result(tc) + + messages: Final = [{"role": "user", "content": "weather in Paris and Tokyo?"}] + messages_snapshot: Final = [dict(message) for message in messages] + + answer: Final = litellm.run_tool_loop( + model="openai/gpt-5-mini", + messages=messages, + tools=WEATHER_TOOLS, + execute_tool=executor, + api_key="sk-test", + ) + + assert answer == "Paris 72F, Tokyo 60F" + assert route.call_count == 2 + assert [tc.id for tc in executed] == ["call_1", "call_2"] + assert [tc.function.name for tc in executed] == ["get_weather", "get_weather"] + assert [tc.function.arguments for tc in executed] == [ + '{"city": "Paris"}', + '{"city": "Tokyo"}', + ] + + second_body: Final = _request_bodies(respx_mock)[1] + assert second_body["messages"] == [ + {"role": "user", "content": "weather in Paris and Tokyo?"}, + { + "role": "assistant", + "tool_calls": [ + { + "id": "call_1", + "type": "function", + "function": {"name": "get_weather", "arguments": '{"city": "Paris"}'}, + }, + { + "id": "call_2", + "type": "function", + "function": {"name": "get_weather", "arguments": '{"city": "Tokyo"}'}, + }, + ], + }, + {"role": "tool", "content": '{"temp": "72F"}', "tool_call_id": "call_1"}, + {"role": "tool", "content": '{"temp": "72F"}', "tool_call_id": "call_2"}, + ] + + assert len(messages) == len(messages_snapshot) + assert messages == messages_snapshot + + +def test_response_format_and_tools_forwarded_every_round(respx_mock: respx.MockRouter) -> None: + respx_mock.post(OPENAI_CHAT_COMPLETIONS_URL).mock( + side_effect=[ + httpx.Response(200, json=_openai_response(None, [_tool_call("call_1", "get_weather", {"city": "Paris"})])), + httpx.Response(200, json=_openai_response('{"summary": "sunny"}')), + ] + ) + response_format: Final = { + "type": "json_schema", + "json_schema": { + "name": "weather_report", + "schema": { + "type": "object", + "properties": {"summary": {"type": "string"}}, + "required": ["summary"], + }, + }, + } + + litellm.run_tool_loop( + model="openai/gpt-5-mini", + messages=[{"role": "user", "content": "weather?"}], + tools=WEATHER_TOOLS, + execute_tool=_tool_result, + response_format=response_format, + api_key="sk-test", + ) + + bodies: Final = _request_bodies(respx_mock) + assert len(bodies) == 2 + for body in bodies: + assert body["response_format"] == response_format + assert body["tools"] == list(WEATHER_TOOLS) + + +def test_max_rounds_exceeded_raises_without_executing_last_round(respx_mock: respx.MockRouter) -> None: + tool_call: Final = _tool_call("call_1", "get_weather", {"city": "Paris"}) + route: Final = respx_mock.post(OPENAI_CHAT_COMPLETIONS_URL).mock( + return_value=httpx.Response(200, json=_openai_response(None, [tool_call])) + ) + executed: Final = [] + + def executor(tc: ChatCompletionMessageToolCall) -> ChatCompletionToolMessage: + executed.append(tc) + return _tool_result(tc) + + with pytest.raises(ToolLoopMaxRoundsExceeded) as exc_info: + litellm.run_tool_loop( + model="openai/gpt-5-mini", + messages=[{"role": "user", "content": "weather?"}], + tools=WEATHER_TOOLS, + execute_tool=executor, + max_rounds=2, + api_key="sk-test", + ) + + assert exc_info.value.max_rounds == 2 + assert route.call_count == 2 + assert [tc.id for tc in executed] == ["call_1"] + + +def test_max_rounds_below_one_rejected_before_any_request(respx_mock: respx.MockRouter) -> None: + route: Final = respx_mock.post(OPENAI_CHAT_COMPLETIONS_URL).mock( + return_value=httpx.Response(200, json=_openai_response("done")) + ) + + with pytest.raises(ValueError, match="max_rounds must be >= 1"): + litellm.run_tool_loop( + model="openai/gpt-5-mini", + messages=[{"role": "user", "content": "hi"}], + tools=WEATHER_TOOLS, + execute_tool=_tool_result, + max_rounds=0, + api_key="sk-test", + ) + + assert route.call_count == 0 + + +def test_stream_rejected_before_any_request(respx_mock: respx.MockRouter) -> None: + route: Final = respx_mock.post(OPENAI_CHAT_COMPLETIONS_URL).mock( + return_value=httpx.Response(200, json=_openai_response("done")) + ) + + with pytest.raises(ValueError, match="stream=True is not supported"): + litellm.run_tool_loop( + model="openai/gpt-5-mini", + messages=[{"role": "user", "content": "hi"}], + tools=WEATHER_TOOLS, + execute_tool=_tool_result, + stream=True, + api_key="sk-test", + ) + + assert route.call_count == 0 + + +def test_custom_tool_call_raises_type_error_without_executing(respx_mock: respx.MockRouter) -> None: + custom_response: Final = _openai_response( + None, + [{"id": "call_custom", "type": "custom", "custom": {"name": "apply_patch", "input": "*** patch"}}], + ) + route: Final = respx_mock.post(OPENAI_CHAT_COMPLETIONS_URL).mock( + return_value=httpx.Response(200, json=custom_response) + ) + executor_called: Final = [] + + def executor(tc: ChatCompletionMessageToolCall) -> ChatCompletionToolMessage: + executor_called.append(tc) + return _tool_result(tc) + + with pytest.raises(TypeError, match="custom tool call call_custom"): + litellm.run_tool_loop( + model="openai/gpt-5-mini", + messages=[{"role": "user", "content": "hi"}], + tools=WEATHER_TOOLS, + execute_tool=executor, + api_key="sk-test", + ) + + assert executor_called == [] + assert route.call_count == 1 + + +def _responses_payload(response_id: str, output: list) -> dict: + return { + "id": response_id, + "object": "response", + "created_at": 1734366691, + "status": "completed", + "model": "gpt-5.5", + "output": output, + "parallel_tool_calls": True, + "usage": {"input_tokens": 10, "output_tokens": 5, "total_tokens": 15}, + "error": None, + "incomplete_details": None, + "instructions": None, + "metadata": None, + "temperature": None, + "tool_choice": "auto", + "tools": [], + "top_p": None, + "max_output_tokens": None, + "previous_response_id": None, + "reasoning": None, + "truncation": None, + "user": None, + } + + +def test_responses_bridge_replays_reasoning_items_across_rounds(respx_mock: respx.MockRouter) -> None: + round_one: Final = _responses_payload( + "resp_1", + [ + {"type": "reasoning", "id": "rs_abc123", "summary": [], "encrypted_content": "enc_xyz"}, + { + "type": "function_call", + "id": "fc_1", + "call_id": "call_1", + "name": "get_weather", + "arguments": '{"city": "Paris"}', + "status": "completed", + }, + ], + ) + round_two: Final = _responses_payload( + "resp_2", + [ + { + "type": "message", + "id": "msg_1", + "status": "completed", + "role": "assistant", + "content": [{"type": "output_text", "text": "Paris is 72F", "annotations": []}], + } + ], + ) + route: Final = respx_mock.post("https://api.openai.com/v1/responses").mock( + side_effect=[httpx.Response(200, json=round_one), httpx.Response(200, json=round_two)] + ) + executed: Final = [] + + def executor(tc: ChatCompletionMessageToolCall) -> ChatCompletionToolMessage: + executed.append(tc) + return _tool_result(tc) + + answer: Final = litellm.run_tool_loop( + model="openai/responses/gpt-5.5", + messages=[{"role": "user", "content": "weather in Paris?"}], + tools=WEATHER_TOOLS, + execute_tool=executor, + api_key="sk-test", + ) + + assert answer == "Paris is 72F" + assert route.call_count == 2 + assert [tc.id for tc in executed] == ["fc_1"] + + second_input: Final = _request_bodies(respx_mock)[1]["input"] + item_types: Final = [item.get("type") for item in second_input] + reasoning_index: Final = next(i for i, item in enumerate(second_input) if item.get("type") == "reasoning") + function_call_index: Final = next( + i for i, item in enumerate(second_input) if item.get("type") == "function_call" + ) + reasoning_item: Final = second_input[reasoning_index] + assert reasoning_item["id"] == "rs_abc123" + assert reasoning_item["encrypted_content"] == "enc_xyz" + assert reasoning_index < function_call_index, f"reasoning item must precede function_call: {item_types}" + + +async def test_arun_tool_loop_two_rounds(respx_mock: respx.MockRouter, monkeypatch: pytest.MonkeyPatch) -> None: + from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler + + monkeypatch.setattr(litellm, "disable_aiohttp_transport", True) + monkeypatch.setattr(litellm, "module_level_aclient", AsyncHTTPHandler()) + tool_calls: Final = [ + _tool_call("call_1", "get_weather", {"city": "Paris"}), + _tool_call("call_2", "get_weather", {"city": "Tokyo"}), + ] + route: Final = respx_mock.post(OPENAI_CHAT_COMPLETIONS_URL).mock( + side_effect=[ + httpx.Response(200, json=_openai_response(None, tool_calls)), + httpx.Response(200, json=_openai_response("Paris 72F, Tokyo 60F")), + ] + ) + executed: Final = [] + + async def executor(tc: ChatCompletionMessageToolCall) -> ChatCompletionToolMessage: + executed.append(tc) + return _tool_result(tc) + + messages: Final = [{"role": "user", "content": "weather in Paris and Tokyo?"}] + messages_snapshot: Final = [dict(message) for message in messages] + + answer: Final = await litellm.arun_tool_loop( + model="openai/gpt-5-mini", + messages=messages, + tools=WEATHER_TOOLS, + execute_tool=executor, + api_key="sk-test", + ) + + assert answer == "Paris 72F, Tokyo 60F" + assert route.call_count == 2 + assert [tc.id for tc in executed] == ["call_1", "call_2"] + + second_body: Final = _request_bodies(respx_mock)[1] + assert second_body["messages"] == [ + {"role": "user", "content": "weather in Paris and Tokyo?"}, + { + "role": "assistant", + "tool_calls": [ + { + "id": "call_1", + "type": "function", + "function": {"name": "get_weather", "arguments": '{"city": "Paris"}'}, + }, + { + "id": "call_2", + "type": "function", + "function": {"name": "get_weather", "arguments": '{"city": "Tokyo"}'}, + }, + ], + }, + {"role": "tool", "content": '{"temp": "72F"}', "tool_call_id": "call_1"}, + {"role": "tool", "content": '{"temp": "72F"}', "tool_call_id": "call_2"}, + ] + assert messages == messages_snapshot diff --git a/ui/litellm-dashboard/eslint.config.mjs b/ui/litellm-dashboard/eslint.config.mjs index 5bb7cc29792..ad2923bf2a0 100644 --- a/ui/litellm-dashboard/eslint.config.mjs +++ b/ui/litellm-dashboard/eslint.config.mjs @@ -99,6 +99,11 @@ const eslintConfig = [ ], rules: { "local/no-ad-hoc-z-index": ["error", { allowPopupLayer: true }] }, }, + { + files: ["src/components/view_logs/TraceView/**/*.tsx", "src/components/lens/**/*.tsx"], + ignores: ["src/**/*.test.tsx"], + rules: { "local/no-arbitrary-design-value": "error" }, + }, { files: ["tests/eslint-rules/**/*.{ts,tsx}"], rules: { "local/no-noop-hover-variant": "off", "local/no-ad-hoc-z-index": "off" }, diff --git a/ui/litellm-dashboard/next.config.mjs b/ui/litellm-dashboard/next.config.mjs index f1d59f99dcc..d4fdc7af36f 100644 --- a/ui/litellm-dashboard/next.config.mjs +++ b/ui/litellm-dashboard/next.config.mjs @@ -5,8 +5,27 @@ import { fileURLToPath } from "url"; const __filename = fileURLToPath(import.meta.url); const __dirname = path.dirname(__filename); +const devProxyUrl = process.env.LENS_DEV_PROXY_URL; + const nextConfig = { - output: "export", + ...(devProxyUrl + ? { + async rewrites() { + return { + beforeFiles: [ + { + source: "/:path*", + has: [{ type: "header", key: "content-type", value: "application/json.*" }], + destination: `${devProxyUrl}/:path*`, + }, + { source: "/ui/:path*", destination: "/:path*" }, + ], + fallback: [{ source: "/:path*", destination: `${devProxyUrl}/:path*` }], + }; + }, + } + : {}), + output: devProxyUrl ? undefined : "export", typescript: { tsconfigPath: "tsconfig.production.json" }, experimental: { useTypeScriptCli: false, @@ -21,7 +40,8 @@ const nextConfig = { }, basePath: "", assetPrefix: "/litellm-asset-prefix", - trailingSlash: true, + trailingSlash: !devProxyUrl, + skipTrailingSlashRedirect: Boolean(devProxyUrl), turbopack: { // Must be absolute; "." is no longer allowed root: __dirname, diff --git a/ui/litellm-dashboard/package-lock.json b/ui/litellm-dashboard/package-lock.json index c64db5abb93..37027f215fe 100644 --- a/ui/litellm-dashboard/package-lock.json +++ b/ui/litellm-dashboard/package-lock.json @@ -10,6 +10,7 @@ "dependencies": { "@anthropic-ai/sdk": "0.92.0", "@base-ui/react": "^1.6.0", + "@handlewithcare/react-prosemirror": "3.2.9", "@headlessui/tailwindcss": "0.2.2", "@heroicons/react": "1.0.6", "@hookform/resolvers": "5.4.0", @@ -17,6 +18,7 @@ "@tanstack/react-pacer": "0.22.1", "@tanstack/react-query": "5.100.7", "@tanstack/react-table": "8.21.3", + "@tanstack/react-virtual": "3.14.13", "@types/papaparse": "5.5.2", "class-variance-authority": "0.7.1", "clsx": "^2.1.1", @@ -32,17 +34,25 @@ "openapi-fetch": "^0.17.0", "openapi-react-query": "^0.5.4", "papaparse": "5.5.3", + "prosemirror-model": "1.25.12", + "prosemirror-state": "1.4.4", + "prosemirror-view": "1.42.3", "react": "19.2.8", "react-copy-to-clipboard": "5.1.1", "react-dom": "19.2.8", + "react-error-boundary": "6.1.6", "react-hook-form": "7.82.0", + "react-hotkeys-hook": "5.3.3", + "react-intersection-observer": "11.0.1", "react-json-view-lite": "2.5.0", "react-markdown": "9.1.0", + "react-reconciler": "0.33.0", "react-syntax-highlighter": "15.6.6", "recharts": "3.9.2", "remark-gfm": "4.0.1", "sonner": "2.0.8", "tailwind-merge": "3.4.0", + "usehooks-ts": "3.1.1", "uuid": "14.0.0", "zod": "4.6.5" }, @@ -1343,6 +1353,40 @@ "integrity": "sha512-HpCo8tmWzLVad5s2d19EhAz5zqrrQ6s69qd6moPMQvkOuSwDT1YgRfWSVuc4ennqrgv3OHppiOGMQ7oC13yIww==", "license": "MIT" }, + "node_modules/@handlewithcare/react-prosemirror": { + "version": "3.2.9", + "resolved": "https://registry.npmjs.org/@handlewithcare/react-prosemirror/-/react-prosemirror-3.2.9.tgz", + "integrity": "sha512-zNGR4BDAvXQGY0ph2ZVK/wDdOr3nL3kTjtXv9Bwwmvzy39Gtooc+vQHSHRtWg0AoN33csJgg0ev78dtoScAR9g==", + "license": "Apache-2.0", + "dependencies": { + "classnames": "^2.5.1" + }, + "engines": { + "node": ">=16.9" + }, + "peerDependencies": { + "@tiptap/core": "^3.0.0", + "@tiptap/pm": "^3.0.0", + "@tiptap/react": "^3.0.0", + "prosemirror-model": "^1.0.0", + "prosemirror-state": "^1.0.0", + "prosemirror-view": "1.42.3", + "react": ">=17 <20", + "react-dom": ">=17 <20", + "react-reconciler": ">=0.26.1 <=0.33.0" + }, + "peerDependenciesMeta": { + "@tiptap/core": { + "optional": true + }, + "@tiptap/pm": { + "optional": true + }, + "@tiptap/react": { + "optional": true + } + } + }, "node_modules/@headlessui/tailwindcss": { "version": "0.2.2", "resolved": "https://registry.npmjs.org/@headlessui/tailwindcss/-/tailwindcss-0.2.2.tgz", @@ -3498,6 +3542,23 @@ "react-dom": ">=16.8" } }, + "node_modules/@tanstack/react-virtual": { + "version": "3.14.13", + "resolved": "https://registry.npmjs.org/@tanstack/react-virtual/-/react-virtual-3.14.13.tgz", + "integrity": "sha512-JbDTAwtzZ99aOeCrAfW5EsE5KSq5RWh6Af2dtFwyLIIk48Ja7vm6n4axu/43T3vfjFnEGJalxJ1wyYjSQD6bSg==", + "license": "MIT", + "dependencies": { + "@tanstack/virtual-core": "3.17.11" + }, + "funding": { + "type": "github", + "url": "https://github.com/sponsors/tannerlinsley" + }, + "peerDependencies": { + "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", + "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0" + } + }, "node_modules/@tanstack/store": { "version": "0.11.1", "resolved": "https://registry.npmjs.org/@tanstack/store/-/store-0.11.1.tgz", @@ -3521,6 +3582,16 @@ "url": "https://github.com/sponsors/tannerlinsley" } }, + "node_modules/@tanstack/virtual-core": { + "version": "3.17.11", + "resolved": "https://registry.npmjs.org/@tanstack/virtual-core/-/virtual-core-3.17.11.tgz", + "integrity": "sha512-+ILjvtHup6Y2hzQ6YzwMgX1Q+oQpxEGOXCEsCNaPoIP0VxMbizIBTmYTDtkerkIQS8/CbP1BRuyt8V/8BCsy1g==", + "license": "MIT", + "funding": { + "type": "github", + "url": "https://github.com/sponsors/tannerlinsley" + } + }, "node_modules/@testing-library/dom": { "version": "10.4.1", "resolved": "https://registry.npmjs.org/@testing-library/dom/-/dom-10.4.1.tgz", @@ -5160,6 +5231,12 @@ "url": "https://polar.sh/cva" } }, + "node_modules/classnames": { + "version": "2.5.1", + "resolved": "https://registry.npmjs.org/classnames/-/classnames-2.5.1.tgz", + "integrity": "sha512-saHYOzhIQs6wy2sVxTM6bUDsQO4F50V9RQ22qBpEdCW+I+/Wmke2HOl6lS6dTpdxVhb88/I6+Hs+438c3lfUow==", + "license": "MIT" + }, "node_modules/client-only": { "version": "0.0.1", "resolved": "https://registry.npmjs.org/client-only/-/client-only-0.0.1.tgz", @@ -8449,6 +8526,12 @@ "url": "https://github.com/sponsors/sindresorhus" } }, + "node_modules/lodash.debounce": { + "version": "4.0.8", + "resolved": "https://registry.npmjs.org/lodash.debounce/-/lodash.debounce-4.0.8.tgz", + "integrity": "sha512-FT1yDzDYEoYWhnSGnpE/4Kj1fLZkDFyqRb7fNt6FdYOSxlUWAtp42Eh6Wb0rGIv/m9Bgo7x4GhQbm5Ys4SG5ow==", + "license": "MIT" + }, "node_modules/lodash.merge": { "version": "4.6.2", "resolved": "https://registry.npmjs.org/lodash.merge/-/lodash.merge-4.6.2.tgz", @@ -9965,6 +10048,12 @@ "node": ">= 0.8.0" } }, + "node_modules/orderedmap": { + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/orderedmap/-/orderedmap-2.1.1.tgz", + "integrity": "sha512-TvAWxi0nDe1j/rtMcWcIj94+Ffe6n7zhow33h40SKxmsmozs6dz/e+EajymfoFcHd7sxNn8yHM8839uixMOV6g==", + "license": "MIT" + }, "node_modules/own-keys": { "version": "1.0.1", "resolved": "https://registry.npmjs.org/own-keys/-/own-keys-1.0.1.tgz", @@ -10313,6 +10402,46 @@ "url": "https://github.com/sponsors/wooorm" } }, + "node_modules/prosemirror-model": { + "version": "1.25.12", + "resolved": "https://registry.npmjs.org/prosemirror-model/-/prosemirror-model-1.25.12.tgz", + "integrity": "sha512-Ue2gTmXMa7EhpLNhC7J+h4+ykD8ha12K6rrZFFKKJHBForfIStw5gJ6Zrf1mqqAa9NmpmEB4wp9bKmA4eUVjWg==", + "license": "MIT", + "dependencies": { + "orderedmap": "^2.0.0" + } + }, + "node_modules/prosemirror-state": { + "version": "1.4.4", + "resolved": "https://registry.npmjs.org/prosemirror-state/-/prosemirror-state-1.4.4.tgz", + "integrity": "sha512-6jiYHH2CIGbCfnxdHbXZ12gySFY/fz/ulZE333G6bPqIZ4F+TXo9ifiR86nAHpWnfoNjOb3o5ESi7J8Uz1jXHw==", + "license": "MIT", + "dependencies": { + "prosemirror-model": "^1.0.0", + "prosemirror-transform": "^1.0.0", + "prosemirror-view": "^1.27.0" + } + }, + "node_modules/prosemirror-transform": { + "version": "1.12.2", + "resolved": "https://registry.npmjs.org/prosemirror-transform/-/prosemirror-transform-1.12.2.tgz", + "integrity": "sha512-PE/aY0HEY4zczvmqrilgkUK/WautF0chvMqkmM/iN5/aPHvwrCWaQZjS6CIZp+K84YrvPFqrL+YArrfJX8xX7g==", + "license": "MIT", + "dependencies": { + "prosemirror-model": "^1.21.0" + } + }, + "node_modules/prosemirror-view": { + "version": "1.42.3", + "resolved": "https://registry.npmjs.org/prosemirror-view/-/prosemirror-view-1.42.3.tgz", + "integrity": "sha512-oTN7EtH+CpwxU9NrwEYWd0UZ4JUx7l048l5A2Xppm4p/60isZYLnth9QVQmC3VRIvdrIWCxwZSd+Uz791G31/w==", + "license": "MIT", + "dependencies": { + "prosemirror-model": "^1.25.8", + "prosemirror-state": "^1.0.0", + "prosemirror-transform": "^1.1.0" + } + }, "node_modules/punycode": { "version": "2.3.1", "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.1.tgz", @@ -10378,6 +10507,21 @@ "react": "^19.2.8" } }, + "node_modules/react-error-boundary": { + "version": "6.1.6", + "resolved": "https://registry.npmjs.org/react-error-boundary/-/react-error-boundary-6.1.6.tgz", + "integrity": "sha512-CDXPnXDGyFIbkwaaJ6u+xgsRmJhSi6YdgUDW1vnyKHfXp1a9pfAlM+ZET2CDu80/A+8iRcmXN0NSY9BCCoWP5A==", + "license": "MIT", + "peerDependencies": { + "@types/react": "^18.0.0 || ^19.0.0", + "react": "^18.0.0 || ^19.0.0" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, "node_modules/react-hook-form": { "version": "7.82.0", "resolved": "https://registry.npmjs.org/react-hook-form/-/react-hook-form-7.82.0.tgz", @@ -10394,6 +10538,34 @@ "react": "^16.8.0 || ^17 || ^18 || ^19" } }, + "node_modules/react-hotkeys-hook": { + "version": "5.3.3", + "resolved": "https://registry.npmjs.org/react-hotkeys-hook/-/react-hotkeys-hook-5.3.3.tgz", + "integrity": "sha512-aswgyWUnE25hmhzHTfKDmKzsaSE5DJ4LKaU/o6rQSXkDd/1Bh9TfAFQbHkf6fLy11HvlYkp+cDDarGdhmCDhoQ==", + "license": "MIT", + "workspaces": [ + "packages/*" + ], + "peerDependencies": { + "react": ">=16.8.0", + "react-dom": ">=16.8.0" + } + }, + "node_modules/react-intersection-observer": { + "version": "11.0.1", + "resolved": "https://registry.npmjs.org/react-intersection-observer/-/react-intersection-observer-11.0.1.tgz", + "integrity": "sha512-BIZ1M40GPSKDIT1MJbXK7SB0BwBaTKr84QfZCs5asKer7YMOYLzMi+RI1F4VStbZLGHoosJmd+aOQDDipUV1gA==", + "license": "MIT", + "peerDependencies": { + "react": "^17.0.0 || ^18.0.0 || ^19.0.0", + "react-dom": "^17.0.0 || ^18.0.0 || ^19.0.0" + }, + "peerDependenciesMeta": { + "react-dom": { + "optional": true + } + } + }, "node_modules/react-is": { "version": "17.0.2", "resolved": "https://registry.npmjs.org/react-is/-/react-is-17.0.2.tgz", @@ -10439,6 +10611,21 @@ "react": ">=18" } }, + "node_modules/react-reconciler": { + "version": "0.33.0", + "resolved": "https://registry.npmjs.org/react-reconciler/-/react-reconciler-0.33.0.tgz", + "integrity": "sha512-KetWRytFv1epdpJc3J4G75I4WrplZE5jOL7Yq0p34+OVOKF4Se7WrdIdVC45XsSSmUTlht2FM/fM1FZb1mfQeA==", + "license": "MIT", + "dependencies": { + "scheduler": "^0.27.0" + }, + "engines": { + "node": ">=0.10.0" + }, + "peerDependencies": { + "react": "^19.2.0" + } + }, "node_modules/react-redux": { "version": "9.3.0", "resolved": "https://registry.npmjs.org/react-redux/-/react-redux-9.3.0.tgz", @@ -12101,6 +12288,21 @@ "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0" } }, + "node_modules/usehooks-ts": { + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/usehooks-ts/-/usehooks-ts-3.1.1.tgz", + "integrity": "sha512-I4diPp9Cq6ieSUH2wu+fDAVQO43xwtulo+fKEidHUwZPnYImbtkTjzIJYcDcJqxgmX31GVqNFURodvcgHcW0pA==", + "license": "MIT", + "dependencies": { + "lodash.debounce": "^4.0.8" + }, + "engines": { + "node": ">=16.15.0" + }, + "peerDependencies": { + "react": "^16.8.0 || ^17 || ^18 || ^19 || ^19.0.0-rc" + } + }, "node_modules/uuid": { "version": "14.0.0", "resolved": "https://registry.npmjs.org/uuid/-/uuid-14.0.0.tgz", diff --git a/ui/litellm-dashboard/package.json b/ui/litellm-dashboard/package.json index 80d08bc870b..388b6c7eab9 100644 --- a/ui/litellm-dashboard/package.json +++ b/ui/litellm-dashboard/package.json @@ -27,6 +27,7 @@ "dependencies": { "@anthropic-ai/sdk": "0.92.0", "@base-ui/react": "^1.6.0", + "@handlewithcare/react-prosemirror": "3.2.9", "@headlessui/tailwindcss": "0.2.2", "@heroicons/react": "1.0.6", "@hookform/resolvers": "5.4.0", @@ -34,6 +35,7 @@ "@tanstack/react-pacer": "0.22.1", "@tanstack/react-query": "5.100.7", "@tanstack/react-table": "8.21.3", + "@tanstack/react-virtual": "3.14.13", "@types/papaparse": "5.5.2", "class-variance-authority": "0.7.1", "clsx": "^2.1.1", @@ -49,17 +51,25 @@ "openapi-fetch": "^0.17.0", "openapi-react-query": "^0.5.4", "papaparse": "5.5.3", + "prosemirror-model": "1.25.12", + "prosemirror-state": "1.4.4", + "prosemirror-view": "1.42.3", "react": "19.2.8", "react-copy-to-clipboard": "5.1.1", "react-dom": "19.2.8", + "react-error-boundary": "6.1.6", "react-hook-form": "7.82.0", + "react-hotkeys-hook": "5.3.3", + "react-intersection-observer": "11.0.1", "react-json-view-lite": "2.5.0", "react-markdown": "9.1.0", + "react-reconciler": "0.33.0", "react-syntax-highlighter": "15.6.6", "recharts": "3.9.2", "remark-gfm": "4.0.1", "sonner": "2.0.8", "tailwind-merge": "3.4.0", + "usehooks-ts": "3.1.1", "uuid": "14.0.0", "zod": "4.6.5" }, diff --git a/ui/litellm-dashboard/scripts/eslint-rules/index.mjs b/ui/litellm-dashboard/scripts/eslint-rules/index.mjs index 750b8df4e27..3988a810fca 100644 --- a/ui/litellm-dashboard/scripts/eslint-rules/index.mjs +++ b/ui/litellm-dashboard/scripts/eslint-rules/index.mjs @@ -4,6 +4,7 @@ import noComplexJsxArrow from "./no-complex-jsx-arrow.mjs"; import filenamePascalCase from "./filename-pascal-case.mjs"; import noNoopHoverVariant from "./no-noop-hover-variant.mjs"; import noAdHocZIndex from "./no-ad-hoc-z-index.mjs"; +import noArbitraryDesignValue from "./no-arbitrary-design-value.mjs"; const plugin = { rules: { @@ -13,6 +14,7 @@ const plugin = { "filename-pascal-case": filenamePascalCase, "no-noop-hover-variant": noNoopHoverVariant, "no-ad-hoc-z-index": noAdHocZIndex, + "no-arbitrary-design-value": noArbitraryDesignValue, }, }; diff --git a/ui/litellm-dashboard/scripts/eslint-rules/no-ad-hoc-z-index.mjs b/ui/litellm-dashboard/scripts/eslint-rules/no-ad-hoc-z-index.mjs index 6af86d2c501..d349539c5a3 100644 --- a/ui/litellm-dashboard/scripts/eslint-rules/no-ad-hoc-z-index.mjs +++ b/ui/litellm-dashboard/scripts/eslint-rules/no-ad-hoc-z-index.mjs @@ -1,26 +1,7 @@ +import { utilityOf } from "./tailwind-utility.mjs"; + const AD_HOC_Z = /^-?z-(?:\d+|\[[^\]]*\]|\([^)]*\))$/; -const OPENERS = { "[": "]", "(": ")" }; - -const utilityOf = (token) => { - const closers = []; - const lastTopLevelColon = [...token].reduce((found, ch, i) => { - if (closers.length > 0 && ch === closers[closers.length - 1]) { - closers.pop(); - return found; - } - if (ch in OPENERS) { - closers.push(OPENERS[ch]); - return found; - } - return ch === ":" && closers.length === 0 ? i : found; - }, -1); - return token - .slice(lastTopLevelColon + 1) - .replace(/^!/, "") - .replace(/!$/, ""); -}; - const classify = (token, allowPopupLayer) => { const utility = utilityOf(token); if (AD_HOC_Z.test(utility)) return "adHoc"; diff --git a/ui/litellm-dashboard/scripts/eslint-rules/no-arbitrary-design-value.mjs b/ui/litellm-dashboard/scripts/eslint-rules/no-arbitrary-design-value.mjs new file mode 100644 index 00000000000..421a5e15cfc --- /dev/null +++ b/ui/litellm-dashboard/scripts/eslint-rules/no-arbitrary-design-value.mjs @@ -0,0 +1,42 @@ +import { utilityOf } from "./tailwind-utility.mjs"; + +const ARBITRARY_SCALE = /^(?:text|tracking|leading|rounded(?:-[a-z]+)?|border(?:-[a-z]+)?)-\[/; +const ARBITRARY_PROPERTY = /^\[[a-z-]+:/; + +const isOffending = (token) => { + const utility = utilityOf(token); + return ARBITRARY_SCALE.test(utility) || ARBITRARY_PROPERTY.test(utility); +}; + +const rule = { + meta: { + type: "problem", + docs: { + description: + "Disallow arbitrary font size, tracking, leading, radius and border values, and arbitrary CSS properties. Use the theme scale so surfaces share one type and shape system.", + }, + schema: [], + messages: { + arbitrary: + "`{{token}}` bypasses the theme scale. Use a scale utility (text-xs/sm, leading-*, tracking-*, rounded-sm/md/lg, border/border-2) instead.", + }, + }, + create(context) { + const check = (node, value) => { + if (typeof value !== "string" || !value.includes("[")) return; + for (const token of value.split(/\s+/).filter(isOffending)) { + context.report({ node, messageId: "arbitrary", data: { token } }); + } + }; + return { + Literal(node) { + check(node, node.value); + }, + TemplateElement(node) { + check(node, node.value.cooked); + }, + }; + }, +}; + +export default rule; diff --git a/ui/litellm-dashboard/scripts/eslint-rules/tailwind-utility.mjs b/ui/litellm-dashboard/scripts/eslint-rules/tailwind-utility.mjs new file mode 100644 index 00000000000..69c80a51d5e --- /dev/null +++ b/ui/litellm-dashboard/scripts/eslint-rules/tailwind-utility.mjs @@ -0,0 +1,20 @@ +const OPENERS = { "[": "]", "(": ")" }; + +export const utilityOf = (token) => { + const closers = []; + const lastTopLevelColon = [...token].reduce((found, ch, i) => { + if (closers.length > 0 && ch === closers[closers.length - 1]) { + closers.pop(); + return found; + } + if (ch in OPENERS) { + closers.push(OPENERS[ch]); + return found; + } + return ch === ":" && closers.length === 0 ? i : found; + }, -1); + return token + .slice(lastTopLevelColon + 1) + .replace(/^!/, "") + .replace(/!$/, ""); +}; diff --git a/ui/litellm-dashboard/src/app/globals.css b/ui/litellm-dashboard/src/app/globals.css index 72d304c0dc7..cad79f64ea0 100644 --- a/ui/litellm-dashboard/src/app/globals.css +++ b/ui/litellm-dashboard/src/app/globals.css @@ -64,8 +64,6 @@ } @theme inline { - --animate-slide-left: slide-left 200ms cubic-bezier(0, 0, 0.2, 1) both; - --animate-view-fade-in: view-fade-in 100ms cubic-bezier(0.4, 0, 0.2, 1) both; --animate-slot-slide-in: slot-slide-in 150ms cubic-bezier(0, 0, 0.2, 1) both; --animate-trace-drawer-in: trace-drawer-in 200ms cubic-bezier(0.25, 1, 0.5, 1) both; --animate-trace-drawer-out: trace-drawer-out 200ms cubic-bezier(0.4, 0, 1, 1) both; @@ -91,24 +89,6 @@ } } - @keyframes slide-left { - from { - opacity: 0; - transform: translateX(2rem) scaleX(0.98); - } - to { - opacity: 1; - transform: none; - } - } - @keyframes view-fade-in { - from { - opacity: 0; - } - to { - opacity: 1; - } - } @keyframes slot-slide-in { from { opacity: 0; @@ -137,8 +117,6 @@ @media (prefers-reduced-motion: reduce) { .animate-trace-drawer-in, .animate-trace-drawer-out, - .animate-slide-left, - .animate-view-fade-in, .animate-slot-slide-in { animation: none !important; } diff --git a/ui/litellm-dashboard/src/app/layout.tsx b/ui/litellm-dashboard/src/app/layout.tsx index 60db7104a03..7bb05ef11a7 100644 --- a/ui/litellm-dashboard/src/app/layout.tsx +++ b/ui/litellm-dashboard/src/app/layout.tsx @@ -7,6 +7,7 @@ import { ThemeProvider } from "next-themes"; import { AuthProvider } from "@/contexts/AuthContext"; import ReactQueryProvider from "@/contexts/ReactQueryProvider"; +import HotkeysProvider from "@/contexts/HotkeysProvider"; import { Toaster } from "@/components/ui/sonner"; const inter = Inter({ subsets: ["latin"] }); @@ -30,7 +31,9 @@ export default function RootLayout({ - {children} + + {children} + diff --git a/ui/litellm-dashboard/src/components/lens/LensDemoContext.tsx b/ui/litellm-dashboard/src/components/lens/LensDemoContext.tsx deleted file mode 100644 index fc7fbbdb65c..00000000000 --- a/ui/litellm-dashboard/src/components/lens/LensDemoContext.tsx +++ /dev/null @@ -1,10 +0,0 @@ -"use client"; - -import { createContext, useContext } from "react"; - -export interface LensDemo { - copyTrace: (traceId: string, spanId?: string) => string; -} - -export const LensDemoContext = createContext(null); -export const useLensDemo = () => useContext(LensDemoContext); diff --git a/ui/litellm-dashboard/src/components/lens/LensModeSwitch.tsx b/ui/litellm-dashboard/src/components/lens/LensModeSwitch.tsx new file mode 100644 index 00000000000..11d02567799 --- /dev/null +++ b/ui/litellm-dashboard/src/components/lens/LensModeSwitch.tsx @@ -0,0 +1,101 @@ +"use client"; + +import { Tabs as TabsPrimitive } from "@base-ui/react/tabs"; +import { Activity, ScanSearch, Settings } from "lucide-react"; +import { StatusDot } from "@/components/shared/StatusDot"; +import { cn } from "@/lib/cva.config"; +import type { InvestigationActivity } from "./model/status"; +import { useWorkerConnected } from "./hooks/useWorkerConnected"; +import type { LensList } from "./model/types"; +import { LENS_TABS, type LensTab } from "./route"; +import { frameCorner, frameTab } from "./ui/frame"; + +const MODE_ICONS = { traces: Activity, investigations: ScanSearch, settings: Settings } as const; + +const ACTIVITY_DOT: Record, { className: string; label: string }> = { + running: { className: "bg-info motion-safe:animate-pulse", label: "An investigation is running" }, + queued: { className: "bg-muted-foreground/60", label: "An investigation is queued" }, +}; + +function ActivityDot({ activity }: { activity: InvestigationActivity }) { + if (activity === "idle") return null; + return ( +