scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-14 09:03:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 214

Merge remote-tracking branch 'origin/main' into litellm_azure_create_no_blind_retry
Some checks failed
Cost map pins recheck / rerun-cost-map-guard (push) Has been cancelled
Details
LiteLLM Rust DB / db-queries (push) Has been cancelled
Details
LiteLLM Rust / rust-lint (push) Has been cancelled
Details
LiteLLM Rust / rust-test (push) Has been cancelled
Details
LiteLLM Rust / rust-wheel (push) Has been cancelled
Details

Browse source 
Main's #50278 replaced the Router type stub this branch had added, so both conflicting files take main's version
This commit is contained in:
mateo-berri 2026-11-05 17:41:13 -08:00
commit af1cf2afe7
341 changed files with 13125 additions and 2068 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
.github/PULL_REQUEST_TEMPLATE/general.md vendored
View file

@ -93,6 +93,7 @@ If you're seeing a delay in your PR being merged, ping the LiteLLM Team on [Slac
Otherwise proof must be fully e2e, no mocks, with real provider calls where applicable. Pytest alone is insufficient. The following format applies to live proof
Show only the latest proof. Before uses the merge base and After the tested tip. Rerun affected QA after behavior changes. Verified neutral diffs may carry proof with the tested SHA, current tip, equivalence reason and focused checks, following AGENTS.md and /qa
Use matching Before/After case headings with numbered commands and observed output. Put shared setup above them. For one case, omit case headings
A reviewer must be able to rerun every case from the body alone, so the shared setup gives the proxy start command, the config.yaml, env var names (never values) and the client code or curl used, all exactly as run. Wrap any block longer than about 20 lines in a collapsed <details> with a one-line summary
### Before (<hash>)

2
.github/workflows/image-scan.yml vendored
View file

@ -53,7 +53,7 @@ jobs:
if: >-
github.event_name != 'pull_request' ||
github.event.pull_request.head.repo.full_name == github.repository
timeout-minutes: 30
timeout-minutes: 60
permissions:
contents: read
steps:

4
.github/workflows/interactions-spec-canary.yml vendored
View file

@ -49,9 +49,9 @@ jobs:
id: compliance
run: |
uv run --no-sync pytest tests/unit/interactions/test_openapi_compliance.py \
--interactions-spec-url=https://ai.google.dev/static/api/interactions.openapi.json \
--interactions-spec-url=https://aistudio.google.com/api-reference/interactions.openapi.json \
--tb=short -vv -p no:rerunfailures -p no:pytest-retry \
--allow-hosts=127.0.0.1,::1,localhost,ai.google.dev
--allow-hosts=127.0.0.1,::1,localhost,ai.google.dev,aistudio.google.com
tracking-issue:
name: tracking-issue

2
.github/workflows/test-linting.yml vendored
View file

@ -21,7 +21,7 @@ jobs:
pull-requests: read
actions: read
runs-on: ubuntu-latest
timeout-minutes: 20
timeout-minutes: 30
services:
redis:
image: redis@sha256:e2debfb7956fa12c7ddc79d7e645c8cf26b30c99a6e9161ea9bf4171e1668a5f

18
.github/workflows/test-unit.yml vendored
View file

@ -45,7 +45,7 @@ jobs:
id: rust-bridge-key
if: steps.changes.outputs.decision != 'skip'
env:
RUST_BRIDGE_CACHE_KEY: ${{ runner.os }}-rust-bridge-editable-${{ hashFiles('litellm-rust/Cargo.lock', 'litellm-rust/Cargo.toml', 'litellm-rust/crates/**', 'model_prices_and_context_window.json', 'pyproject.toml') }}
RUST_BRIDGE_CACHE_KEY: ${{ runner.os }}-rust-bridge-editable-${{ hashFiles('litellm-rust/Cargo.lock', 'litellm-rust/Cargo.toml', 'litellm-rust/crates/**', 'model_prices_and_context_window.json', 'pyproject.toml', 'packaging/litellm-proxy/pyproject.toml') }}
run: echo "key=$RUST_BRIDGE_CACHE_KEY" >> "$GITHUB_OUTPUT"
- name: Set up Python
@ -98,6 +98,18 @@ jobs:
mkdir -p rust-bridge-dist/litellm/rust_bridge
cp litellm/rust_bridge/_native.abi3.so rust-bridge-dist/litellm/rust_bridge/_native.abi3.so
- name: Build the gateway wheel once for test shards
if: steps.changes.outputs.decision != 'skip' && steps.rust-bridge-cache.outputs.cache-hit != 'true'
timeout-minutes: 15
working-directory: packaging/litellm-proxy
env:
RUSTC_WRAPPER: sccache
SCCACHE_GHA_ENABLED: "true"
SCCACHE_GHA_VERSION: litellm-ci-v1
SCCACHE_GHA_RW_MODE: ${{ github.event_name == 'push' && github.ref == 'refs/heads/main' && 'READ_WRITE' || 'READ_ONLY' }}
CARGO_INCREMENTAL: "0"
run: uv run --no-project --with maturin==1.15.0 maturin build --profile dev --strip --out ../../rust-bridge-dist
- name: Upload Rust bridge artifact
if: steps.changes.outputs.decision != 'skip'
timeout-minutes: 10
@ -1024,7 +1036,7 @@ jobs:
if [ -z "$RUST_BRIDGE_ARTIFACT" ]; then
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra extra_proxy --extra proxy-runtime --extra utils
else
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra extra_proxy --extra proxy-runtime --extra utils --no-install-project
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra extra_proxy --extra proxy-runtime --extra utils --no-install-project --no-install-package litellm-proxy
uv pip install --no-deps --python .venv/bin/python rust-bridge-dist/*.whl
cp rust-bridge-dist/litellm/rust_bridge/_native.abi3.so litellm/rust_bridge/_native.abi3.so
uv run --no-sync python -c "import importlib.metadata; import litellm.rust_bridge._native; print(importlib.metadata.version('litellm'))"
@ -1486,7 +1498,7 @@ jobs:
if [ -z "$RUST_BRIDGE_ARTIFACT" ]; then
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra extra_proxy --extra proxy-runtime --extra utils
else
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra extra_proxy --extra proxy-runtime --extra utils --no-install-project
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra extra_proxy --extra proxy-runtime --extra utils --no-install-project --no-install-package litellm-proxy
uv pip install --no-deps --python .venv/bin/python rust-bridge-dist/*.whl
cp rust-bridge-dist/litellm/rust_bridge/_native.abi3.so litellm/rust_bridge/_native.abi3.so
fi

2
AGENTS.md
View file

@ -45,7 +45,7 @@ Run QA proxies with `python litellm/proxy/proxy_cli.py --config litellm/proxy/de
Simple PRs may skip before/after e2e when the full diff is mechanical and focused checks completely prove it, such as #49030 restoring an existing helper name. Trace affected callers and run relevant tests/static checks at the tip. For a bug fix, establish that the regression catches the original defect. Size alone never qualifies. New behavior, API/provider semantics, auth, billing, persistence, concurrency or uncertain integration risk need live e2e. In Screenshots / Proof of Fix, record `E2E exception at <tip SHA>`, scope, rationale, commands and results. Tests count as proof only for this exception. Reassess changed diffs, retain CI/bot gates, and honor explicit e2e requests (2026-10-28, unnecessary live QA for #49030)
For other PRs, proof must show the end user's real flow before and after, with commands and output against a live proxy and real provider calls where applicable. Pytest alone is insufficient. For UI or interactive coding-tool flows, drive that surface and embed before/after screenshots, with URLs, clicks and input fields a reviewer can reproduce
For other PRs, proof must show the end user's real flow before and after, with commands and output against a live proxy and real provider calls where applicable. The body alone must let a reviewer rerun it, with the proxy command, config, env var names and client code exactly as run, and long blocks collapsed in <details>. Pytest alone is insufficient. For UI or interactive coding-tool flows, drive that surface and embed before/after screenshots, with URLs, clicks and input fields a reviewer can reproduce
If you ever write any human-facing text (pull requests, issues, commit messages, discussion posts, github comments, release notes, docs, etc.), always follow these guidelines to sound less AI-y:
- don't use emojis

6
Dockerfile
View file

@ -76,6 +76,7 @@ ENV UV_PROJECT_ENVIRONMENT=/app/.venv \
COPY pyproject.toml uv.lock ./
COPY enterprise/pyproject.toml enterprise/
COPY litellm-proxy-extras/pyproject.toml litellm-proxy-extras/
COPY packaging/litellm-proxy/pyproject.toml packaging/litellm-proxy/
# Install third-party dependencies (cached unless pyproject.toml/uv.lock change)
RUN uv sync --frozen --no-install-project --no-install-workspace --no-default-groups --no-editable \
@ -101,7 +102,8 @@ COPY --from=ui-builder /ui/out/. litellm/proxy/_experimental/out/
RUN sed -i 's/\r$//' docker/build_admin_ui.sh && chmod +x docker/build_admin_ui.sh && ./docker/build_admin_ui.sh
# Install project and workspace packages (fast - deps already cached)
RUN uv sync --frozen --no-default-groups --no-editable \
RUN uv build --package litellm-proxy --wheel --out-dir /wheels
RUN uv sync --frozen --no-install-package litellm-proxy --no-default-groups --no-editable \
--extra proxy \
--extra proxy-runtime \
--group admin-mcp \
@ -111,6 +113,8 @@ RUN uv sync --frozen --no-default-groups --no-editable \
--extra bedrock-realtime \
--python python3.13
RUN uv pip install --python /app/.venv/bin/python --no-deps /wheels/litellm_proxy-*.whl
RUN HOME=/opt/prisma XDG_CACHE_HOME=/opt/prisma/.cache PRISMA_BINARY_CACHE_DIR=/opt/prisma/binaries \
npm_config_cache=/root/.npm \
prisma generate --schema=./schema.prisma

6
docker/Dockerfile.database
View file

@ -74,6 +74,7 @@ ENV UV_PROJECT_ENVIRONMENT=/app/.venv \
COPY pyproject.toml uv.lock ./
COPY enterprise/pyproject.toml enterprise/
COPY litellm-proxy-extras/pyproject.toml litellm-proxy-extras/
COPY packaging/litellm-proxy/pyproject.toml packaging/litellm-proxy/
# Install third-party dependencies (cached unless pyproject.toml/uv.lock change)
RUN uv sync --frozen --no-install-project --no-install-workspace --no-default-groups --no-editable \
@ -99,7 +100,8 @@ COPY --from=ui-builder /ui/out/. litellm/proxy/_experimental/out/
RUN sed -i 's/\r$//' docker/build_admin_ui.sh && chmod +x docker/build_admin_ui.sh && ./docker/build_admin_ui.sh
# Install project and workspace packages (fast - deps already cached)
RUN uv sync --frozen --no-default-groups --no-editable \
RUN uv build --package litellm-proxy --wheel --out-dir /wheels
RUN uv sync --frozen --no-install-package litellm-proxy --no-default-groups --no-editable \
--extra proxy \
--extra proxy-runtime \
--group admin-mcp \
@ -109,6 +111,8 @@ RUN uv sync --frozen --no-default-groups --no-editable \
--extra bedrock-realtime \
--python python3.13
RUN uv pip install --python /app/.venv/bin/python --no-deps /wheels/litellm_proxy-*.whl
RUN HOME=/opt/prisma XDG_CACHE_HOME=/opt/prisma/.cache PRISMA_BINARY_CACHE_DIR=/opt/prisma/binaries \
npm_config_cache=/root/.npm \
prisma generate --schema=./schema.prisma

9
gateway/Dockerfile
View file

@ -41,10 +41,14 @@ COPY pyproject.toml README.md rust-toolchain.toml ./
COPY .cargo ./.cargo
COPY litellm-rust ./litellm-rust
COPY model_prices_and_context_window.json ./
COPY packaging/litellm-proxy/pyproject.toml packaging/litellm-proxy/
RUN --mount=type=cache,target=/root/.cache/uv \
mkdir -p litellm/rust_bridge /wheels && \
touch litellm/__init__.py litellm/rust_bridge/__init__.py && \
uvx --python python3.13 --from maturin==1.15.0 --with puccinialin==0.1.14 \
python -c "import maturin; maturin.build_wheel('/wheels')" && \
cd packaging/litellm-proxy && \
uvx --python python3.13 --from maturin==1.15.0 --with puccinialin==0.1.14 \
python -c "import maturin; maturin.build_wheel('/wheels')"
@ -85,6 +89,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
--mount=type=bind,source=uv.lock,target=uv.lock \
--mount=type=bind,source=enterprise/pyproject.toml,target=enterprise/pyproject.toml \
--mount=type=bind,source=litellm-proxy-extras/pyproject.toml,target=litellm-proxy-extras/pyproject.toml \
--mount=type=bind,source=packaging/litellm-proxy/pyproject.toml,target=packaging/litellm-proxy/pyproject.toml \
uv sync --frozen --no-install-project --no-install-workspace --no-default-groups --no-editable \
--extra proxy \
--extra proxy-runtime \
@ -98,7 +103,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
COPY . .
RUN --mount=type=cache,target=/root/.cache/uv \
uv sync --frozen --no-install-project --no-default-groups --no-editable \
uv sync --frozen --no-install-project --no-install-package litellm-proxy --no-default-groups --no-editable \
--extra proxy \
--extra proxy-runtime \
--group admin-mcp \
@ -108,7 +113,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
--python python3.13
RUN --mount=type=bind,from=rust-native,source=/wheels,target=/wheels \
uv pip install --python /app/.venv/bin/python --no-deps /wheels/litellm-*.whl
uv pip install --python /app/.venv/bin/python --no-deps /wheels/litellm-*.whl /wheels/litellm_proxy-*.whl
# PYTHONPATH=/app makes the source tree shadow the installed package, so the
# compiled Rust extension must live next to the source or it is never imported.

2
litellm-rust/.agents/skills/rust-gateway/SKILL.md
View file

@ -7,7 +7,7 @@ metadata:
# Rust gateway
`crates/gateway` mounts endpoint routers and serves the listener. `crates/gateway-inference`, `gateway-mcp` and `gateway-ui` own their endpoints, `gateway-auth` is the inbound authentication middleware and `gateway-management` holds management logic that has no router yet. A crate's `AGENTS.md`, where it has one, says what belongs in it. Read the reference for the part you are touching
`crates/gateway` mounts endpoint routers and serves the listener. `crates/gateway-inference`, `gateway-mcp` and `gateway-ui` own their endpoints, `gateway-auth` is the inbound authentication middleware and `gateway-management` holds management logic that has no router yet. `gateway-forward` is the reverse proxy that relays every request to the Python proxy and has no routes of its own. A crate's `AGENTS.md`, where it has one, says what belongs in it. Read the reference for the part you are touching
- [surfaces](references/surfaces.md)
- Each API surface mirrors the envelope the Python proxy returns there, so the shapes differ on purpose

59
litellm-rust/Cargo.lock generated
View file

@ -547,7 +547,7 @@ dependencies = [
"http 1.4.2",
"http-body 0.4.6",
"hyper 0.14.32",
"hyper 1.10.1",
"hyper 1.12.0",
"hyper-rustls 0.24.2",
"hyper-rustls 0.27.9",
"hyper-util",
@ -736,7 +736,7 @@ dependencies = [
"http 1.4.2",
"http-body 1.1.0",
"http-body-util",
"hyper 1.10.1",
"hyper 1.12.0",
"hyper-util",
"itoa",
"matchit",
@ -1000,7 +1000,7 @@ dependencies = [
"home",
"http 1.4.2",
"http-body-util",
"hyper 1.10.1",
"hyper 1.12.0",
"hyper-named-pipe",
"hyper-rustls 0.27.9",
"hyper-util",
@ -2255,7 +2255,7 @@ dependencies = [
"chrono",
"http 1.4.2",
"http-body-util",
"hyper 1.10.1",
"hyper 1.12.0",
"hyper-rustls 0.27.9",
"hyper-util",
"ring",
@ -2391,7 +2391,7 @@ dependencies = [
"http 1.4.2",
"http-body 1.1.0",
"http-body-util",
"hyper 1.10.1",
"hyper 1.12.0",
"lazy_static",
"opentelemetry",
"opentelemetry-semantic-conventions",
@ -2833,9 +2833,9 @@ dependencies = [
[[package]]
name = "hyper"
version = "1.10.1"
version = "1.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "55281c53a1894c864990125767da440a4e630446785086f52523b20033b74498"
checksum = "2c3e324da4c95177d6291d4c8730197c0d1822f8a9766814a4a44fa5ab797c9c"
dependencies = [
"atomic-waker",
"bytes",
@ -2860,7 +2860,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fab3637d6b04a8037af8a266fdf6cf92ea957e8c53981a2bf6136572531025bf"
dependencies = [
"hex",
"hyper 1.10.1",
"hyper 1.12.0",
"hyper-util",
"pin-project-lite",
"tokio",
@ -2889,7 +2889,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "33ca68d021ef39cf6463ab54c1d0f5daf03377b70561305bb89a8f83aab66e0f"
dependencies = [
"http 1.4.2",
"hyper 1.10.1",
"hyper 1.12.0",
"hyper-util",
"rustls 0.23.42",
"rustls-native-certs",
@ -2904,7 +2904,7 @@ version = "0.5.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2b90d566bffbce6a75bd8b09a05aa8c2cb1fabb6cb348f8840c9e4c90a0d83b0"
dependencies = [
"hyper 1.10.1",
"hyper 1.12.0",
"hyper-util",
"pin-project-lite",
"tokio",
@ -2923,7 +2923,7 @@ dependencies = [
"futures-util",
"http 1.4.2",
"http-body 1.1.0",
"hyper 1.10.1",
"hyper 1.12.0",
"ipnet",
"libc",
"percent-encoding",
@ -2942,7 +2942,7 @@ checksum = "986c5ce3b994526b3cd75578e62554abd09f0899d6206de48b3e96ab34ccc8c7"
dependencies = [
"hex",
"http-body-util",
"hyper 1.10.1",
"hyper 1.12.0",
"hyper-util",
"pin-project-lite",
"tokio",
@ -3769,6 +3769,7 @@ dependencies = [
"litellm-config",
"litellm-error",
"litellm-gateway-auth",
"litellm-gateway-forward",
"litellm-gateway-inference",
"litellm-gateway-mcp",
"litellm-gateway-ui",
@ -3815,6 +3816,29 @@ dependencies = [
"veil",
]
[[package]]
name = "litellm-gateway-forward"
version = "0.1.0"
dependencies = [
"axum",
"bytes",
"envy",
"futures-util",
"http-body-util",
"httparse",
"hyper 1.12.0",
"hyper-util",
"proptest",
"rstest",
"serde",
"thiserror 2.0.19",
"tokio",
"tokio-tungstenite",
"tokio-util",
"tower-service",
"tracing",
]
[[package]]
name = "litellm-gateway-inference"
version = "0.1.0"
@ -6031,7 +6055,7 @@ dependencies = [
"http 1.4.2",
"http-body 1.1.0",
"http-body-util",
"hyper 1.10.1",
"hyper 1.12.0",
"hyper-rustls 0.27.9",
"hyper-util",
"js-sys",
@ -7512,6 +7536,7 @@ dependencies = [
"bytes",
"futures-core",
"futures-sink",
"futures-util",
"pin-project-lite",
"tokio",
]
@ -7591,7 +7616,7 @@ dependencies = [
"http 1.4.2",
"http-body 1.1.0",
"http-body-util",
"hyper 1.10.1",
"hyper 1.12.0",
"hyper-timeout",
"hyper-util",
"percent-encoding",
@ -8167,9 +8192,9 @@ dependencies = [
[[package]]
name = "want"
version = "0.3.1"
version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bfa7760aed19e106de2c7c0b581b509f2f25d3dacaf737cb82ac61bc6d760b0e"
checksum = "ec4cdd0dd910afe868b7ef477227d8d538b46b3075031afee8a9f2acb0a2ed0b"
dependencies = [
"try-lock",
]
@ -8551,7 +8576,7 @@ dependencies = [
"futures",
"http 1.4.2",
"http-body-util",
"hyper 1.10.1",
"hyper 1.12.0",
"hyper-util",
"log",
"once_cell",

1
litellm-rust/Cargo.toml
View file

@ -26,6 +26,7 @@ litellm-inference-ocr = { path = "crates/inference-ocr" }
litellm-inference-testing = { path = "crates/inference-testing" }
litellm-gateway-mcp = { path = "crates/gateway-mcp" }
litellm-gateway = { path = "crates/gateway" }
litellm-gateway-forward = { path = "crates/gateway-forward" }
litellm-gateway-inference = { path = "crates/gateway-inference" }
litellm-gateway-auth = { path = "crates/gateway-auth" }
litellm-gateway-management = { path = "crates/gateway-management" }

37
litellm-rust/crates/gateway-forward/AGENTS.md Normal file
View file

@ -0,0 +1,37 @@
# Forwarding gateway
`Forward` is a reverse proxy in front of the Python proxy on loopback. Python must see each request as if the client had connected to it directly, because every Python route (inference, MCP, pass-through, UI, WebSocket) is served behind it without Rust knowing which one it is
- Serve HTTP/1.1 only, as uvicorn does. The supervisor never puts Rust in front of a Python server that speaks HTTP/2
- Never branch on a route or path. A behavior one endpoint needs is a protocol behavior every endpoint gets
- Forward the method, request target, headers, and body byte for byte within the [URL contract](FORWARDING.md#url-fragments-and-literal-hashes). An unescaped `#` starts a fragment and is omitted with everything after it, while `%23` is preserved. Only drop hop-by-hop headers (RFC 9110 section 7.6.1) and set `x-litellm-rust-peer`, which replaces any client copy
- Stream both bodies. Never buffer, cap, or time out a body, since uploads and provider streams have no upper bound
- A client disconnect closes the upstream connection at every stage, because that is how Python learns to stop a provider stream
- An upstream that dies mid-response fails the client body. Never end it cleanly, or SSE clients treat a truncated stream as complete
- Never invent a Host. Python builds absolute URLs from it, so a missing one must never become the private upstream address
- A request Python could not have received unchanged (HTTP/1.1 without Host, a transfer coding other than chunked, a target without a path) gets the status uvicorn would have given, from Rust
- Pooled upstream connections are retired well before Python's keep-alive timeout, so a request never lands on a connection Python is closing
- Idle client connections close after Python's keep-alive timeout, as uvicorn closed them, so a client that vanishes cannot hold a socket forever. Only the wait for the next request is timed, never an exchange in progress
- WebSocket is the one protocol switch Python serves. Upgrades are relayed as raw bytes after the 101 and drained on shutdown
## Layout
Every forwarding decision has one home. `rewrite.rs` owns what Python and the client receive, as pure functions over requests and responses. `Rejection` in `error.rs` is the only place that picks a status for a request Rust answers itself. `settings.rs` parses the environment into typed values, so an `Upstream` is a loopback origin by construction. `server.rs` accepts client connections and owns their timeouts, since `axum::serve` exposes none, and `connections.rs` tracks every connection and relay for shutdown. `forward.rs` and `websocket.rs` only move requests, bodies and upgraded connections and never touch a header themselves. `connector.rs` keeps hyper reading Python's answer after Python stops reading the request
## Environment
`Settings` reads only these variables, and only when `LITELLM_FORWARD_UPSTREAM` is set. The Python supervisor in `litellm/proxy/rust_forward/` sets every one of them from the values Python actually runs with, so all of them are required and a missing or invalid one fails startup naming it. The crate never reads Python's own settings (`HOST`, `PORT`, `KEEPALIVE_TIMEOUT`, `GRACEFUL_SHUTDOWN_TIMEOUT`) and keeps no copy of Python's defaults, since Python can get those values from CLI flags the environment never shows
| Variable | Meaning |
|---|---|
| `LITELLM_FORWARD_UPSTREAM` | Python's loopback origin, e.g. `http://127.0.0.1:53211` |
| `LITELLM_FORWARD_HOST` | public bind host |
| `LITELLM_FORWARD_PORT` | public bind port |
| `LITELLM_FORWARD_UPSTREAM_KEEPALIVE` | seconds uvicorn keeps an idle connection open. Pooled connections are retired at half of it, and idle client connections are closed after it |
| `LITELLM_FORWARD_SHUTDOWN_DRAIN` | seconds to drain on shutdown, already including Python's graceful timeout and teardown headroom |
## Tests
Test through real sockets with `tests/support`, never `oneshot`. `Gateway` runs the forwarder on a listener like production, `recording` is a well-behaved upstream that captures what Python would receive, and `raw_upstream` and `Raw` drive bytes by hand for framing, timing and disconnects a real server would not produce. Waits measured in minutes use paused tokio time instead of real sleeps
The forwarder sees HTTP/1.1 messages, not routes, so the tests are split into one file per traffic shape uvicorn can emit: `exchange` (plain request and response), `framing` (requests whose framing a parser could read two ways), `slow_head` (minutes before response headers), `stream` (incremental response bodies), `idle_stream` (long-lived streams that go quiet), `upload`, `download`, `websocket`, `client_identity`, `lifecycle` (disconnects, pooling, idle timeouts, shutdown) and `roundtrip` (the forwarding invariant for generated messages). A new route never gets its own test. Add its behavior to the shape it already has, and when it needs a wire behavior none of the files covers, add a new shape file for it

30
litellm-rust/crates/gateway-forward/Cargo.toml Normal file
View file

@ -0,0 +1,30 @@
[package]
name = "litellm-gateway-forward"
version = "0.1.0"
edition.workspace = true
rust-version.workspace = true
license.workspace = true
repository.workspace = true
[dependencies]
axum.workspace = true
envy = "0.4.2"
hyper = { version = "1.12.0", features = ["http1", "server"] }
hyper-util = { workspace = true, features = ["client-legacy", "http1", "tokio"] }
serde.workspace = true
thiserror.workspace = true
tokio = { workspace = true, features = ["io-util"] }
tokio-util = { version = "0.7", features = ["rt"] }
tower-service = "0.3.3"
tracing.workspace = true
[dev-dependencies]
bytes.workspace = true
futures-util.workspace = true
http-body-util = "0.1"
httparse = "1"
hyper = { version = "1.12.0", features = ["client"] }
proptest.workspace = true
rstest.workspace = true
tokio = { workspace = true, features = ["io-util", "sync", "test-util"] }
tokio-tungstenite.workspace = true

31
litellm-rust/crates/gateway-forward/FORWARDING.md Normal file
View file

@ -0,0 +1,31 @@
# Python forwarding compatibility
The opt-in forwarding gateway serves HTTP/1.1 and WebSockets in front of Python. Python still owns every route and policy. Its protocol contract and environment settings are in [AGENTS.md](AGENTS.md)
## URL fragments and literal hashes
The gateway follows Hyper's `http::Uri` parsing. If a raw client sends an unescaped `#` in the request target, only the path and query before the first `#` reach Python. For example, `/v1/files?purpose=batch#retry&limit=1` becomes `/v1/files?purpose=batch`, and `/gemini/v1beta/files/a#b?key=k` becomes `/gemini/v1beta/files/a`
This is accepted behavior because `#` starts a URL fragment, which is separated before dereferencing ([RFC 3986 section 3.5](https://www.rfc-editor.org/rfc/rfc3986.html#section-3.5)). HTTP origin-form contains only the path and optional query, not a fragment ([RFC 9112 section 3.2.1](https://www.rfc-editor.org/rfc/rfc9112.html#section-3.2.1)). Browsers and URL-based clients omit the fragment before sending the request, so UI hash routing is unaffected
A literal hash in path or query data must be encoded as `%23`, which the gateway forwards unchanged. Direct Python with h11 also accepts unescaped hashes as data, but that permissive raw-target behavior is outside this URL contract. Active socket tests cover both [fragment omission](tests/exchange.rs) and [encoded-hash preservation](tests/exchange.rs)
## Known differences from uvicorn with h11
These cases remain executable as ignored socket tests. They are not passing parity checks
| Input | Direct Python | Through Rust | Regression test |
|---|---|---|---|
| Header after a removed hop-by-hop field | Keeps the remaining header order | `HeaderMap::remove` can move a later header | [dropping_a_hop_by_hop_header_keeps_the_others_in_order](tests/exchange.rs) |
| Repeated header names interleaved with other names | Keeps the interleaving | Groups values by name, keeping their order within that name | [interleaved_repeated_headers_reach_python_interleaved](tests/exchange.rs) |
| Obsolete folded header, such as `x-a: b\r\n c` | Unfolds to `b c` | Rejects with 400 | [a_folded_header_reaches_python_unfolded](tests/exchange.rs) |
| Identical Content-Length list, such as `7, 7` | Accepts length 7 | Rejects with 400 | [a_content_length_list_of_one_value_reaches_python](tests/framing.rs) |
| HTTP/1.0 request with chunked transfer coding | Decodes the body | Rejects with 400 | [an_http10_chunked_upload_reaches_python](tests/framing.rs) |
Clients can avoid the parser rejections by sending unfolded headers, one Content-Length value, and HTTP/1.1 for chunked uploads. Integrations must not depend on header ordering across different field names
Run `cargo test -p litellm-gateway-forward --test exchange --test framing -- --ignored` from this directory to reproduce the differences
## Connection header handling
The gateway strips standard hop-by-hop fields and fields named by Connection, except routing, representation, credential, forwarding, and WebSocket handshake headers. A client cannot nominate those end-to-end fields for removal. The private `x-litellm-rust-peer` always replaces any client-supplied copy

58
litellm-rust/crates/gateway-forward/src/connections.rs Normal file
View file

@ -0,0 +1,58 @@
use tokio_util::{
sync::{CancellationToken, DropGuard},
task::TaskTracker,
};
/// Every client connection and WebSocket relay the gateway runs, so shutdown can wait for them
/// and then close whatever outlives the drain.
#[derive(Clone, Default)]
pub(crate) struct Connections {
tasks: TaskTracker,
draining: CancellationToken,
closed: CancellationToken,
}
impl Connections {
/// Runs `work` until it finishes or the gateway closes every connection.
pub fn spawn(&self, work: impl Future<Output = ()> + Send + 'static) {
let closed = self.closed.clone();
self.tasks.spawn(async move {
tokio::select! {
() = closed.cancelled() => {}
() = work => {}
}
});
}
pub fn begin_shutdown(&self) {
self.draining.cancel();
}
pub async fn draining(&self) {
self.draining.cancelled().await;
}
pub fn is_draining(&self) -> bool {
self.draining.is_cancelled()
}
pub async fn until_closed<T>(&self, future: impl Future<Output = T>) -> Option<T> {
tokio::select! {
() = self.closed.cancelled() => None,
output = future => Some(output),
}
}
pub fn close(&self) {
self.closed.cancel();
}
pub fn close_on_drop(&self) -> DropGuard {
self.closed.clone().drop_guard()
}
pub async fn wait(&self) {
self.tasks.close();
self.tasks.wait().await;
}
}

122
litellm-rust/crates/gateway-forward/src/connector.rs Normal file
View file

@ -0,0 +1,122 @@
use std::{
io::{self, IoSlice},
pin::Pin,
task::{Context, Poll, ready},
};
use axum::http::Uri;
use hyper::rt::{Read, ReadBufCursor, Write};
use hyper_util::{
client::legacy::connect::{Connected, Connection, HttpConnector},
rt::TokioIo,
};
use tokio::net::TcpStream;
/// Connects to Python like `HttpConnector`, but keeps hyper reading Python's answer after Python
/// stops reading the request. uvicorn rejects an upload (413, 401) as soon as it reads the head
/// and closes with the body unread, so writing the rest fails, and hyper would fail the request
/// and drop the answer it already received. Like curl and httpcore, the forwarder discards the
/// rest of the request instead and reads on. A connection that never answered still fails, on the
/// read, and no request is ever sent twice.
#[derive(Clone)]
pub(crate) struct Connector(pub HttpConnector);
impl tower_service::Service<Uri> for Connector {
type Response = AnswerAfterRefusal;
type Error = <HttpConnector as tower_service::Service<Uri>>::Error;
type Future = Pin<Box<dyn Future<Output = Result<Self::Response, Self::Error>> + Send>>;
fn poll_ready(&mut self, context: &mut Context<'_>) -> Poll<Result<(), Self::Error>> {
self.0.poll_ready(context)
}
fn call(&mut self, uri: Uri) -> Self::Future {
let connecting = self.0.call(uri);
Box::pin(async move {
Ok(AnswerAfterRefusal {
stream: connecting.await?,
refused: false,
})
})
}
}
pub(crate) struct AnswerAfterRefusal {
stream: TokioIo<TcpStream>,
refused: bool,
}
impl AnswerAfterRefusal {
fn written(&mut self, written: io::Result<usize>, length: usize) -> io::Result<usize> {
match written {
Err(error)
if matches!(
error.kind(),
io::ErrorKind::BrokenPipe | io::ErrorKind::ConnectionReset
) =>
{
self.refused = true;
Ok(length)
}
written => written,
}
}
}
impl Read for AnswerAfterRefusal {
fn poll_read(
mut self: Pin<&mut Self>,
context: &mut Context<'_>,
buffer: ReadBufCursor<'_>,
) -> Poll<io::Result<()>> {
Pin::new(&mut self.stream).poll_read(context, buffer)
}
}
impl Write for AnswerAfterRefusal {
fn poll_write(
mut self: Pin<&mut Self>,
context: &mut Context<'_>,
buffer: &[u8],
) -> Poll<io::Result<usize>> {
if self.refused {
return Poll::Ready(Ok(buffer.len()));
}
let written = ready!(Pin::new(&mut self.stream).poll_write(context, buffer));
Poll::Ready(self.written(written, buffer.len()))
}
fn poll_write_vectored(
mut self: Pin<&mut Self>,
context: &mut Context<'_>,
buffers: &[IoSlice<'_>],
) -> Poll<io::Result<usize>> {
let length = buffers.iter().map(|buffer| buffer.len()).sum();
if self.refused {
return Poll::Ready(Ok(length));
}
let written = ready!(Pin::new(&mut self.stream).poll_write_vectored(context, buffers));
Poll::Ready(self.written(written, length))
}
fn is_write_vectored(&self) -> bool {
self.stream.is_write_vectored()
}
fn poll_flush(mut self: Pin<&mut Self>, context: &mut Context<'_>) -> Poll<io::Result<()>> {
if self.refused {
return Poll::Ready(Ok(()));
}
Pin::new(&mut self.stream).poll_flush(context)
}
fn poll_shutdown(mut self: Pin<&mut Self>, context: &mut Context<'_>) -> Poll<io::Result<()>> {
Pin::new(&mut self.stream).poll_shutdown(context)
}
}
impl Connection for AnswerAfterRefusal {
fn connected(&self) -> Connected {
self.stream.connected()
}
}

91
litellm-rust/crates/gateway-forward/src/error.rs Normal file
View file

@ -0,0 +1,91 @@
use axum::{
http::StatusCode,
response::{IntoResponse, Response},
};
#[derive(Debug, thiserror::Error)]
pub enum Error {
#[error("invalid forwarding upstream URI")]
UpstreamUri(#[source] axum::http::uri::InvalidUri),
#[error(
"LITELLM_FORWARD_UPSTREAM must be a loopback IPv4 http origin without a path, query or credentials"
)]
Upstream,
#[error("{0} must be set in forward mode")]
MissingSetting(String),
#[error("invalid forwarding setting: {0}")]
InvalidSetting(String),
#[error("forwarding gateway I/O failed: {0}")]
Io(#[from] std::io::Error),
}
/// Why a request got an answer from Rust instead of from Python.
#[derive(Debug, thiserror::Error)]
pub(crate) enum Rejection {
#[error("HTTP/1.1 request without a Host header")]
MissingHost,
#[error("request target has no path to forward")]
NoPath,
#[error("request uses a transfer coding other than chunked")]
UnsupportedTransferCoding,
#[error("client request body failed: {0}")]
ClientBody(#[source] hyper_util::client::legacy::Error),
#[error("python proxy unreachable: {0}")]
Unreachable(#[source] hyper_util::client::legacy::Error),
#[error("python proxy switched protocols without being asked to")]
UnrequestedUpgrade,
#[error("python proxy websocket upgrade failed: {0}")]
UpgradeFailed(#[source] hyper::Error),
#[error("forwarding gateway is shutting down")]
ShuttingDown,
#[error("could not build the request for the python proxy")]
Internal,
}
impl Rejection {
/// A client body that ends early or breaks its framing fails the upstream request too, but
/// the fault is the client's, not Python's.
pub fn from_upstream(error: hyper_util::client::legacy::Error) -> Self {
let client_body = std::error::Error::source(&error)
.and_then(|source| source.downcast_ref::<hyper::Error>())
.is_some_and(hyper::Error::is_user);
match client_body {
true => Self::ClientBody(error),
false => Self::Unreachable(error),
}
}
fn status(&self) -> StatusCode {
match self {
Self::MissingHost
| Self::NoPath
| Self::UnsupportedTransferCoding
| Self::ClientBody(_) => StatusCode::BAD_REQUEST,
Self::Unreachable(_) | Self::UnrequestedUpgrade | Self::UpgradeFailed(_) => {
StatusCode::BAD_GATEWAY
}
Self::ShuttingDown => StatusCode::SERVICE_UNAVAILABLE,
Self::Internal => StatusCode::INTERNAL_SERVER_ERROR,
}
}
fn is_gateway_fault(&self) -> bool {
matches!(
self,
Self::Unreachable(_)
| Self::UnrequestedUpgrade
| Self::UpgradeFailed(_)
| Self::Internal
)
}
}
impl IntoResponse for Rejection {
fn into_response(self) -> Response {
match self.is_gateway_fault() {
true => tracing::warn!(error = %self, "request not forwarded"),
false => tracing::debug!(error = %self, "request not forwarded"),
}
self.status().into_response()
}
}

169
litellm-rust/crates/gateway-forward/src/forward.rs Normal file
View file

@ -0,0 +1,169 @@
use std::{
pin::Pin,
task::{Context, Poll},
time::Duration,
};
use axum::{
body::Body,
extract::Request,
http::{StatusCode, Uri},
response::{IntoResponse, Response},
};
use hyper::body::{Frame, Incoming, SizeHint};
use hyper_util::{
client::legacy::{Client, connect::HttpConnector},
rt::{TokioExecutor, TokioTimer},
};
use tokio::net::TcpListener;
use crate::{
Rejection, Upstream, connections::Connections, connector::Connector, rewrite, server,
server::ClientSocket, websocket,
};
// h11 counts no headers and only caps a head at 16 KiB, so it accepts as many headers as fit in
// that many shortest lines (`a:\r\n`). Python copies every provider header into its response
// too, so hyper's default of 100 would turn ordinary traffic into 431s and 502s.
pub(crate) const MAX_HEADERS: usize = 16 * 1024 / b"a:\r\n".len();
#[derive(Clone)]
pub struct Forward {
upstream: Uri,
client: Client<Connector, Body>,
connections: Connections,
keepalive: Duration,
}
impl Forward {
/// `upstream_keepalive` is how long the upstream keeps an idle connection open. Pooled
/// connections are dropped well before that, so a request never lands on one it is closing,
/// and idle client connections are closed after it, as uvicorn did.
pub fn new(upstream: &Upstream, upstream_keepalive: Duration) -> Self {
let mut connector = HttpConnector::new();
connector.set_nodelay(true);
let client = Client::builder(TokioExecutor::new())
.http1_max_headers(MAX_HEADERS)
.pool_timer(TokioTimer::new())
.pool_idle_timeout(upstream_keepalive / 2)
.set_host(false)
.build(Connector(connector));
Self {
upstream: upstream.uri().clone(),
client,
connections: Connections::default(),
keepalive: upstream_keepalive,
}
}
/// Serves until `shutdown` resolves, then lets open requests and WebSockets finish for up to
/// `drain` before closing whatever is left. Python shuts down alongside and ends long streams
/// itself, so `drain` only backstops a Python that never does.
pub async fn serve(
self,
listener: TcpListener,
shutdown: impl Future<Output = ()>,
drain: Duration,
) {
server::serve(self, listener, shutdown, drain).await;
}
pub(crate) fn connections(&self) -> &Connections {
&self.connections
}
pub(crate) fn keepalive(&self) -> Duration {
self.keepalive
}
pub(crate) async fn handle(&self, client: ClientSocket, request: Request) -> Response {
self.forward(client, request)
.await
.unwrap_or_else(IntoResponse::into_response)
}
async fn forward(
&self,
client: ClientSocket,
mut request: Request,
) -> Result<Response, Rejection> {
if let Some(downstream) = websocket::take_handshake(&self.connections, &mut request)? {
return self.forward_websocket(client, request, downstream).await;
}
let request = rewrite::upstream_request(request, &self.upstream, client, false)?;
let response = self
.client
.request(request)
.await
.map_err(Rejection::from_upstream)?;
http_response(response)
}
async fn forward_websocket(
&self,
client: ClientSocket,
request: Request,
downstream: hyper::upgrade::OnUpgrade,
) -> Result<Response, Rejection> {
let request = rewrite::upstream_request(request, &self.upstream, client, true)?;
let response = self
.connections
.until_closed(self.client.request(request))
.await
.ok_or(Rejection::ShuttingDown)?
.map_err(Rejection::from_upstream)?;
if response.status() == StatusCode::SWITCHING_PROTOCOLS {
return websocket::switch(&self.connections, downstream, response).await;
}
http_response(response)
}
}
fn http_response(response: Response<Incoming>) -> Result<Response, Rejection> {
if response.status() == StatusCode::SWITCHING_PROTOCOLS {
return Err(Rejection::UnrequestedUpgrade);
}
Ok(
rewrite::downstream_response(response)
.map(|body| Body::new(Relayed { body, failed: None })),
)
}
/// Python's response body on its way to the client.
struct Relayed {
body: Incoming,
failed: Option<hyper::Error>,
}
impl hyper::body::Body for Relayed {
type Data = <Incoming as hyper::body::Body>::Data;
type Error = hyper::Error;
// hyper aborts a client connection whose response body fails without flushing the head it
// buffered, so a head Python sent right before dying would never arrive and SDKs would retry
// a request Python already ran. Holding the error for one poll lets hyper flush the head.
fn poll_frame(
mut self: Pin<&mut Self>,
context: &mut Context<'_>,
) -> Poll<Option<Result<Frame<Self::Data>, Self::Error>>> {
if let Some(error) = self.failed.take() {
return Poll::Ready(Some(Err(error)));
}
match Pin::new(&mut self.body).poll_frame(context) {
Poll::Ready(Some(Err(error))) => {
self.failed = Some(error);
context.waker().wake_by_ref();
Poll::Pending
}
frame => frame,
}
}
fn is_end_stream(&self) -> bool {
self.failed.is_none() && self.body.is_end_stream()
}
fn size_hint(&self) -> SizeHint {
self.body.size_hint()
}
}

29
litellm-rust/crates/gateway-forward/src/lib.rs Normal file
View file

@ -0,0 +1,29 @@
mod connections;
mod connector;
mod error;
mod forward;
mod rewrite;
mod server;
mod settings;
mod websocket;
pub use error::Error;
pub(crate) use error::Rejection;
pub use forward::Forward;
pub use rewrite::PEER_HEADER;
pub use settings::{Settings, Upstream};
/// Binds the public listener and forwards to Python until `shutdown` resolves, then drains for
/// `settings.shutdown_drain`.
pub async fn run(
settings: Settings,
shutdown: impl Future<Output = ()> + Send + 'static,
) -> Result<(), Error> {
let forward = Forward::new(&settings.upstream, settings.upstream_keepalive);
let listener = tokio::net::TcpListener::bind((settings.host.as_str(), settings.port)).await?;
tracing::info!(address = %listener.local_addr()?, "forwarding gateway listening");
forward
.serve(listener, shutdown, settings.shutdown_drain)
.await;
Ok(())
}

161
litellm-rust/crates/gateway-forward/src/rewrite.rs Normal file
View file

@ -0,0 +1,161 @@
use axum::{
body::HttpBody,
extract::Request,
http::{HeaderMap, HeaderValue, Response, Uri, Version, header},
};
use crate::{Rejection, server::ClientSocket};
pub const PEER_HEADER: &str = "x-litellm-rust-peer";
/// The request Python receives: the client's method, target, headers and body unchanged, sent to
/// `upstream` over HTTP/1.1 without the client connection's own headers, plus the client's TCP
/// peer in `PEER_HEADER`, which replaces any copy the client sent.
pub(crate) fn upstream_request(
mut request: Request,
upstream: &Uri,
client: ClientSocket,
websocket: bool,
) -> Result<Request, Rejection> {
if !only_chunked(request.headers()) {
return Err(Rejection::UnsupportedTransferCoding);
}
let path_and_query = request
.uri()
.path_and_query()
.cloned()
.ok_or(Rejection::NoPath)?;
if let Some(host) = public_host(&request, client)? {
request.headers_mut().insert(header::HOST, host);
}
let mut uri = upstream.clone().into_parts();
uri.path_and_query = Some(path_and_query);
*request.uri_mut() = Uri::from_parts(uri).map_err(|_| Rejection::Internal)?;
*request.version_mut() = Version::HTTP_11;
let chunked = request.body().size_hint().exact().is_none();
let headers = request.headers_mut();
strip_hop_by_hop(headers);
if chunked {
// hyper sends no body for a GET with an unknown length unless told it is chunked.
headers.insert(
header::TRANSFER_ENCODING,
HeaderValue::from_static("chunked"),
);
}
if websocket {
restore_websocket_handshake(headers);
}
headers.insert(
PEER_HEADER,
HeaderValue::from_str(&client.peer.to_string()).map_err(|_| Rejection::Internal)?,
);
Ok(request)
}
// Python builds absolute URLs from Host and, without a usable one, from the address it listens
// on, which behind Rust is the private loopback port. A client that sent no usable Host gets the
// public address it connected to, which is what Python used before. h11 rejects HTTP/1.1 without
// Host.
fn public_host(request: &Request, client: ClientSocket) -> Result<Option<HeaderValue>, Rejection> {
let host = request.headers().get(header::HOST);
if host.is_some_and(|host| !host.is_empty()) {
return Ok(None);
}
if host.is_none() && request.version() == Version::HTTP_11 {
return Err(Rejection::MissingHost);
}
HeaderValue::from_str(&client.local.to_string())
.map(Some)
.map_err(|_| Rejection::Internal)
}
// hyper only decodes chunked framing, so anything else would reach Python still coded but framed
// as a plain body. uvicorn rejects it with the 400 it sends for every h11 parse error.
fn only_chunked(headers: &HeaderMap) -> bool {
headers
.get_all(header::TRANSFER_ENCODING)
.iter()
.flat_map(|value| value.as_bytes().split(|byte| *byte == b','))
.all(|coding| coding.trim_ascii().eq_ignore_ascii_case(b"chunked"))
}
/// The response the client receives: Python's, without the upstream connection's own headers.
pub(crate) fn downstream_response<B>(mut response: Response<B>) -> Response<B> {
strip_hop_by_hop(response.headers_mut());
response
}
/// Python's 101 as the client receives it, still naming the protocol both sides switch to.
pub(crate) fn switched_response<B>(mut response: Response<B>) -> Response<B> {
strip_hop_by_hop(response.headers_mut());
restore_websocket_handshake(response.headers_mut());
response
}
pub(crate) fn is_websocket_handshake(headers: &HeaderMap) -> bool {
headers
.get(header::UPGRADE)
.is_some_and(|value| value.as_bytes().eq_ignore_ascii_case(b"websocket"))
&& headers
.get_all(header::CONNECTION)
.iter()
.filter_map(|value| value.to_str().ok())
.flat_map(|value| value.split(','))
.any(|token| token.trim().eq_ignore_ascii_case("upgrade"))
}
const HOP_BY_HOP: [&str; 9] = [
"connection",
"keep-alive",
"proxy-authenticate",
"proxy-authorization",
"te",
"trailer",
"transfer-encoding",
"upgrade",
"proxy-connection",
];
// Per-connection headers (RFC 9110 section 7.6.1) describe the client's connection to Rust, not
// Rust's connection to Python, so a proxy must drop them instead of forwarding them.
fn strip_hop_by_hop(headers: &mut HeaderMap) {
let named: Vec<_> = headers
.get_all(header::CONNECTION)
.iter()
.filter_map(|value| value.to_str().ok())
.flat_map(|value| value.split(','))
.filter_map(|name| header::HeaderName::from_bytes(name.trim().as_bytes()).ok())
.filter(|name| !must_forward(name))
.collect();
for name in named {
headers.remove(name);
}
for name in HOP_BY_HOP {
headers.remove(name);
}
}
fn must_forward(name: &header::HeaderName) -> bool {
matches!(
name.as_str(),
"host"
| "authorization"
| "cookie"
| "set-cookie"
| "www-authenticate"
| "authentication-info"
| "api-key"
| "x-api-key"
| "litellm-api-key"
| "forwarded"
| PEER_HEADER
) || name.as_str().starts_with("content-")
|| name.as_str().starts_with("x-forwarded-")
|| name.as_str().starts_with("sec-websocket-")
}
// Stripping drops the handshake's Connection and Upgrade, so each hop gets them back.
fn restore_websocket_handshake(headers: &mut HeaderMap) {
headers.insert(header::CONNECTION, HeaderValue::from_static("upgrade"));
headers.insert(header::UPGRADE, HeaderValue::from_static("websocket"));
}

116
litellm-rust/crates/gateway-forward/src/server.rs Normal file
View file

@ -0,0 +1,116 @@
use std::{convert::Infallible, io, net::SocketAddr, pin::pin, time::Duration};
use axum::{body::Body, extract::Request};
use hyper::{body::Incoming, server::conn::http1, service::service_fn};
use hyper_util::rt::{TokioIo, TokioTimer};
use tokio::net::TcpListener;
use crate::{Forward, forward::MAX_HEADERS};
/// The client's TCP connection to the public listener.
#[derive(Clone, Copy, Debug)]
pub(crate) struct ClientSocket {
pub peer: SocketAddr,
pub local: SocketAddr,
}
/// Serves each public connection with hyper directly, because `axum::serve` cannot configure
/// the connection timeouts uvicorn applied to the same clients.
pub(crate) async fn serve(
forward: Forward,
listener: TcpListener,
shutdown: impl Future<Output = ()>,
drain: Duration,
) {
let connections = forward.connections().clone();
let _close_on_drop = connections.close_on_drop();
let keepalive = forward.keepalive();
let builder = builder(keepalive);
let mut shutdown = pin!(shutdown);
loop {
let (stream, peer) = tokio::select! {
() = &mut shutdown => break,
accepted = listener.accept() => match accepted {
Ok(accepted) => accepted,
Err(error) => {
back_off(error).await;
continue;
}
},
};
let local = match stream.local_addr() {
Ok(local) => local,
Err(error) => {
tracing::debug!(%error, "client connection closed before it was served");
continue;
}
};
if let Err(error) = stream.set_nodelay(true) {
tracing::warn!(%error, "could not disable Nagle on a client connection");
}
let socket = ClientSocket { peer, local };
let forward = forward.clone();
let service = service_fn(move |request: Request<Incoming>| {
let forward = forward.clone();
async move { Ok::<_, Infallible>(forward.handle(socket, request.map(Body::new)).await) }
});
let connection = builder
.serve_connection(TokioIo::new(stream), service)
.with_upgrades();
let draining = connections.clone();
connections.spawn(async move {
let mut connection = pin!(connection);
let ended = tokio::select! {
ended = connection.as_mut() => ended,
() = draining.draining() => {
connection.as_mut().graceful_shutdown();
connection.await
}
};
if let Err(error) = ended {
tracing::debug!(%error, "client connection ended with an error");
}
});
}
drop(listener);
connections.begin_shutdown();
if tokio::time::timeout(drain, connections.wait())
.await
.is_err()
{
tracing::warn!(
?drain,
"closing connections still open after the shutdown drain"
);
}
connections.close();
connections.wait().await;
}
// uvicorn closes a client connection that sits idle for `--keepalive_timeout` between requests.
// Without the same limit, a client that vanishes without closing (NAT expiry, a crashed host)
// would hold its socket for the life of the process until the gateway runs out of descriptors.
// Operators already tune that timeout against their load balancer, so the public side keeps
// Python's value instead of introducing its own. hyper only runs the header timer while a
// connection waits for its next request, so it never cuts a long stream, upload or WebSocket.
fn builder(keepalive: Duration) -> http1::Builder {
let mut builder = http1::Builder::new();
builder
.max_headers(MAX_HEADERS)
.timer(TokioTimer::new())
.header_read_timeout(keepalive);
builder
}
async fn back_off(error: io::Error) {
if matches!(
error.kind(),
io::ErrorKind::ConnectionRefused
| io::ErrorKind::ConnectionAborted
| io::ErrorKind::ConnectionReset
) {
return;
}
tracing::error!(%error, "could not accept a client connection");
tokio::time::sleep(Duration::from_secs(1)).await;
}

113
litellm-rust/crates/gateway-forward/src/settings.rs Normal file
View file

@ -0,0 +1,113 @@
use std::{ffi::OsString, net::SocketAddr, str::FromStr, time::Duration};
use axum::http::Uri;
use serde::Deserialize;
use crate::Error;
const UPSTREAM: &str = "LITELLM_FORWARD_UPSTREAM";
/// The Python proxy's private origin. Only a loopback IPv4 address parses, so nothing can point
/// the forwarder at another host.
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct Upstream(Uri);
impl Upstream {
pub(crate) fn uri(&self) -> &Uri {
&self.0
}
}
impl FromStr for Upstream {
type Err = Error;
fn from_str(value: &str) -> Result<Self, Error> {
let uri: Uri = value.parse().map_err(Error::UpstreamUri)?;
let address = uri
.authority()
.filter(|_| uri.scheme_str() == Some("http"))
.filter(|authority| !authority.as_str().contains('@'))
.filter(|_| uri.path() == "/" && uri.query().is_none())
.and_then(|authority| authority.as_str().parse::<SocketAddr>().ok());
match address {
Some(SocketAddr::V4(address)) if address.ip().is_loopback() => Ok(Self(uri)),
_ => Err(Error::Upstream),
}
}
}
#[derive(Deserialize)]
struct Environment {
litellm_forward_upstream: String,
litellm_forward_host: String,
litellm_forward_port: u16,
litellm_forward_upstream_keepalive: f64,
litellm_forward_shutdown_drain: f64,
}
/// Everything forward mode runs with. The Python supervisor resolves each value from the settings
/// Python actually runs with, so none of them is guessed or defaulted here.
/// Setting `LITELLM_FORWARD_UPSTREAM` requires every other `LITELLM_FORWARD_*` setting below.
#[derive(Debug, Clone, PartialEq)]
pub struct Settings {
pub upstream: Upstream,
pub host: String,
pub port: u16,
pub upstream_keepalive: Duration,
pub shutdown_drain: Duration,
}
impl Settings {
/// `None` when `LITELLM_FORWARD_UPSTREAM` is unset, which means the gateway is not forwarding.
pub fn from_env() -> Result<Option<Self>, Error> {
Self::from_vars(std::env::vars_os())
}
pub fn from_vars(
variables: impl IntoIterator<Item = (OsString, OsString)>,
) -> Result<Option<Self>, Error> {
let variables: Vec<(String, String)> = variables
.into_iter()
.filter_map(|(key, value)| Some((key.into_string().ok()?, value.into_string().ok()?)))
.collect();
if !variables.iter().any(|(key, _)| key == UPSTREAM) {
return Ok(None);
}
let environment: Environment = envy::from_iter(variables).map_err(|error| match error {
envy::Error::MissingValue(field) => Error::MissingSetting(field.to_uppercase()),
envy::Error::Custom(message) => Error::InvalidSetting(message),
})?;
Ok(Some(Self {
upstream: environment.litellm_forward_upstream.parse()?,
host: environment.litellm_forward_host,
port: environment.litellm_forward_port,
upstream_keepalive: positive_seconds(
"LITELLM_FORWARD_UPSTREAM_KEEPALIVE",
environment.litellm_forward_upstream_keepalive,
)?,
shutdown_drain: seconds(
"LITELLM_FORWARD_SHUTDOWN_DRAIN",
environment.litellm_forward_shutdown_drain,
)?,
}))
}
}
fn seconds(variable: &str, value: f64) -> Result<Duration, Error> {
Duration::try_from_secs_f64(value).map_err(|_| {
Error::InvalidSetting(format!(
"{variable} must be a non-negative number of seconds, got {value}"
))
})
}
/// The keep-alive also bounds the wait for a client's first request, so zero would close every
/// client connection before it could send one.
fn positive_seconds(variable: &str, value: f64) -> Result<Duration, Error> {
match seconds(variable, value)? {
Duration::ZERO => Err(Error::InvalidSetting(format!(
"{variable} must be a positive number of seconds, got {value}"
))),
duration => Ok(duration),
}
}

86
litellm-rust/crates/gateway-forward/src/websocket.rs Normal file
View file

@ -0,0 +1,86 @@
use axum::{
body::Body,
extract::Request,
http::{Method, Version},
response::Response,
};
use hyper::{
body::Incoming,
upgrade::{OnUpgrade, Upgraded},
};
use hyper_util::rt::TokioIo;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
use crate::{Rejection, connections::Connections, rewrite};
pub(crate) fn take_handshake(
connections: &Connections,
request: &mut Request,
) -> Result<Option<OnUpgrade>, Rejection> {
if request.method() != Method::GET
|| request.version() != Version::HTTP_11
|| !rewrite::is_websocket_handshake(request.headers())
{
return Ok(None);
}
if connections.is_draining() {
return Err(Rejection::ShuttingDown);
}
Ok(Some(hyper::upgrade::on(request)))
}
pub(crate) async fn switch(
connections: &Connections,
downstream: OnUpgrade,
mut response: Response<Incoming>,
) -> Result<Response, Rejection> {
if !rewrite::is_websocket_handshake(response.headers()) {
return Err(Rejection::UnrequestedUpgrade);
}
let upstream = connections
.until_closed(hyper::upgrade::on(&mut response))
.await
.ok_or(Rejection::ShuttingDown)?
.map_err(Rejection::UpgradeFailed)?;
connections.spawn(async move {
match downstream.await {
Ok(downstream) => relay(downstream, upstream).await,
Err(_) => tracing::debug!("websocket upgrade did not complete"),
}
});
Ok(rewrite::switched_response(response).map(|_| Body::empty()))
}
// uvicorn never half-closes a WebSocket, so Python's EOF means the socket is gone and the relay
// ends. Only a client that is gone ends it from the other side: the client's EOF just half-closes
// Python's side, and a write Python refuses means it closed with its last frames still in flight
// to the client.
async fn relay(downstream: Upgraded, upstream: Upgraded) {
let (mut client_read, mut client_write) = tokio::io::split(TokioIo::new(downstream));
let (mut python_read, mut python_write) = tokio::io::split(TokioIo::new(upstream));
let to_python = async {
let mut buffer = vec![0; 8192];
loop {
let read = match client_read.read(&mut buffer).await {
Ok(0) => break,
Ok(read) => read,
Err(_) => return,
};
if python_write.write_all(&buffer[..read]).await.is_err() {
return std::future::pending().await;
}
}
python_write.shutdown().await.ok();
std::future::pending().await
};
let to_client = async {
tokio::io::copy(&mut python_read, &mut client_write)
.await
.ok();
client_write.shutdown().await.ok();
};
tokio::select! {
() = to_python => tracing::debug!("websocket client disconnected"),
() = to_client => {}
}
}

223
litellm-rust/crates/gateway-forward/tests/client_identity.rs Normal file
View file

@ -0,0 +1,223 @@
mod support;
use std::sync::{
Arc,
atomic::{AtomicUsize, Ordering},
};
use axum::{body::Body, http::StatusCode, response::Response};
use litellm_gateway_forward::{Forward, PEER_HEADER};
use rstest::rstest;
use support::{DRAIN, Gateway, Raw, UVICORN_KEEPALIVE, raw_upstream, recording, within};
use tokio::net::{TcpListener, TcpStream};
fn ok() -> Response {
Response::new(Body::from("ok"))
}
#[rstest]
#[case::ordinary("")]
#[case::connection_nominated(
"connection: X-Forwarded-For, X-Forwarded-Proto, Forwarded, X-Litellm-Rust-Peer\r\n"
)]
#[tokio::test]
async fn python_sees_forwarding_headers_untouched_and_the_tcp_peer_rust_saw(
#[case] connection: &str,
) {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!(
"GET /sso/callback HTTP/1.1\r\n\
host: public.example\r\n\
x-forwarded-for: 192.0.2.1\r\n\
x-forwarded-for: 192.0.2.2\r\n\
x-forwarded-proto: https\r\n\
forwarded: for=192.0.2.1;proto=https\r\n\
x-litellm-rust-peer: 10.1.2.3:1\r\n{connection}\r\n",
))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
let request = received.recv().await.unwrap();
let forwarded_for: Vec<_> = request.headers.get_all("x-forwarded-for").iter().collect();
assert_eq!(forwarded_for, ["192.0.2.1", "192.0.2.2"]);
assert_eq!(request.headers["x-forwarded-proto"], "https");
assert_eq!(request.headers["forwarded"], "for=192.0.2.1;proto=https");
let peers: Vec<_> = request.headers.get_all(PEER_HEADER).iter().collect();
assert_eq!(peers, [raw.local_address().to_string().as_str()]);
}
/// Python builds redirects and OAuth metadata from Host, and without one from the address it
/// listens on, which behind Rust is its private loopback port. So a request without a usable Host
/// carries the public address the client connected to, except HTTP/1.1, which h11 rejects.
#[rstest]
#[case::http11_without_host("HTTP/1.1", "", false)]
#[case::http10_without_host("HTTP/1.0", "", true)]
#[case::http11_with_an_empty_host("HTTP/1.1", "host:\r\n", true)]
#[tokio::test]
async fn a_request_without_a_usable_host_never_names_the_private_upstream(
#[case] version: &str,
#[case] host: &str,
#[case] forwarded: bool,
) {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!("GET /sso/key/generate {version}\r\n{host}\r\n"))
.await;
let status = within(raw.response_head()).await.unwrap().status;
let hosts = received.try_recv().ok().map(|request| {
request
.headers
.get_all("host")
.iter()
.map(|value| value.to_str().unwrap().to_owned())
.collect::<Vec<_>>()
});
let expected = if forwarded {
(StatusCode::OK, Some(vec![gateway.address.to_string()]))
} else {
(StatusCode::BAD_REQUEST, None)
};
assert_eq!((status, hosts), expected);
}
#[rstest]
#[case::uppercase_with_port("PUBLIC.Example:4000")]
#[case::ipv6_literal("[::1]:4000")]
#[case::ipv4_with_port("192.0.2.10:8443")]
#[tokio::test]
async fn python_sees_the_host_header_byte_for_byte(#[case] host: &str) {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!("GET /ui HTTP/1.1\r\nHost: {host}\r\n\r\n"))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
let request = received.recv().await.unwrap();
let hosts: Vec<_> = request.headers.get_all("host").iter().collect();
assert_eq!(hosts, [host]);
}
/// Python's IP allowlists and rate limits read the peer exactly as uvicorn would have seen it on
/// the public socket, so a dual-stack listener reports IPv4 clients in their mapped form.
#[rstest]
#[case::ipv6("[::1]:0", "[::1]", "[::1]")]
#[case::ipv4_on_a_dual_stack_listener("[::]:0", "127.0.0.1", "[::ffff:127.0.0.1]")]
#[tokio::test]
async fn ipv6_listeners_report_the_peer_bracketed_with_its_port(
#[case] bind: &str,
#[case] connect: &str,
#[case] peer_ip: &str,
) {
let (upstream, mut received) = recording(ok).await;
let forward = Forward::new(
&format!("http://{upstream}").parse().unwrap(),
UVICORN_KEEPALIVE,
);
let public = TcpListener::bind(bind).await.unwrap();
let port = public.local_addr().unwrap().port();
tokio::spawn(forward.serve(public, std::future::pending(), DRAIN));
let mut raw = Raw::new(
TcpStream::connect(format!("{connect}:{port}"))
.await
.unwrap(),
);
raw.send("GET / HTTP/1.1\r\nhost: public.example\r\n\r\n")
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
assert_eq!(
received.recv().await.unwrap().headers[PEER_HEADER],
format!("{peer_ip}:{}", raw.local_address().port()).as_str()
);
}
/// Without the peer header Python would take Rust's loopback hop as the client, which allowlists
/// often trust, so no spelling, repetition or Connection token may remove or replace it.
#[rstest]
#[case::named_as_hop_by_hop(
"connection: x-litellm-rust-peer\r\nx-litellm-rust-peer: 127.0.0.1:1\r\n"
)]
#[case::mixed_case_copies(
"X-LiteLLM-Rust-Peer: 127.0.0.1:1\r\nx-litellm-rust-peer: 192.0.2.7:2\r\n"
)]
#[case::comma_joined("x-litellm-rust-peer: 127.0.0.1:1, 192.0.2.7:2\r\n")]
#[tokio::test]
async fn a_client_can_neither_strip_nor_spoof_the_peer(#[case] spoof: &str) {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!(
"GET /key/info HTTP/1.1\r\nhost: public.example\r\n{spoof}\r\n"
))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
let request = received.recv().await.unwrap();
let peers: Vec<_> = request.headers.get_all(PEER_HEADER).iter().collect();
assert_eq!(peers, [raw.local_address().to_string().as_str()]);
}
/// Pooled upstream connections carry requests from many clients in turn, so the peer belongs to
/// each request and never to the connection it travels on.
#[rstest]
#[tokio::test]
async fn each_request_carries_its_own_peer_over_a_shared_upstream_connection() {
let connections = Arc::new(AtomicUsize::new(0));
let accepted = connections.clone();
let upstream = raw_upstream(move |mut python| {
accepted.fetch_add(1, Ordering::SeqCst);
async move {
while let Some(head) = python.request_head().await {
let peer = head.header(PEER_HEADER).unwrap().to_vec();
python
.send(
[
format!("HTTP/1.1 200 OK\r\ncontent-length: {}\r\n\r\n", peer.len())
.as_bytes(),
&peer,
]
.concat(),
)
.await;
}
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut clients = [
gateway.connect().await,
gateway.connect().await,
gateway.connect().await,
];
for index in [0, 1, 2, 2, 1, 0] {
let raw = &mut clients[index];
raw.send("GET /v1/models HTTP/1.1\r\nhost: public.example\r\n\r\n")
.await;
let head = within(raw.response_head()).await.unwrap();
let peer = raw.body(head.content_length().unwrap()).await;
assert_eq!(peer, raw.local_address().to_string().into_bytes());
}
assert_eq!(connections.load(Ordering::SeqCst), 1);
}

192
litellm-rust/crates/gateway-forward/tests/download.rs Normal file
View file

@ -0,0 +1,192 @@
mod support;
use std::{
sync::{
Arc,
atomic::{AtomicUsize, Ordering},
},
time::Duration,
};
use axum::{body::Body, extract::Request, http::StatusCode, response::Response};
use http_body_util::BodyExt;
use rstest::rstest;
use support::{Gateway, client, raw_upstream, recording, within};
use tokio::sync::{Notify, mpsc};
#[rstest]
#[tokio::test]
async fn streams_a_body_without_a_content_length_as_python_produces_it() {
let first: &[u8] = &[0xff, 0xfb, 0x90, 0x64, 0x00, 0x0d, 0x0a];
let rest = vec![0xa5; 64 * 1024];
let finish = Arc::new(Notify::new());
let finished = finish.clone();
let tail = rest.clone();
let upstream = raw_upstream(move |mut python| {
let finished = finished.clone();
let tail = tail.clone();
async move {
python.request_head().await.unwrap();
python
.send([&b"HTTP/1.1 200 OK\r\ncontent-type: audio/mpeg\r\ntransfer-encoding: chunked\r\n\r\n7\r\n"[..], first, b"\r\n"].concat())
.await;
finished.notified().await;
python
.send([format!("{:x}\r\n", tail.len()).as_bytes(), &tail, b"\r\n0\r\n\r\n"].concat())
.await;
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut response = within(
client().request(
Request::post(gateway.url("/v1/audio/speech"))
.body(Body::empty())
.unwrap(),
),
)
.await
.unwrap();
assert!(!response.headers().contains_key("content-length"));
let frame = within(response.body_mut().frame()).await.unwrap().unwrap();
assert_eq!(frame.into_data().unwrap(), first);
finish.notify_one();
let body = within(response.into_body().collect())
.await
.unwrap()
.to_bytes();
assert_eq!(body, rest);
}
#[rstest]
#[tokio::test]
async fn range_requests_and_partial_content_pass_unchanged() {
let (upstream, mut received) = recording(|| -> Response {
Response::builder()
.status(StatusCode::PARTIAL_CONTENT)
.header("content-range", "bytes 2-5/10")
.header("accept-ranges", "bytes")
.body(Body::from("2345"))
.unwrap()
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET /v1/videos/video_1/content HTTP/1.1\r\nhost: x\r\nrange: bytes=2-5\r\nif-range: \"v1\"\r\n\r\n")
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::PARTIAL_CONTENT);
assert_eq!(head.header("content-range"), Some(&b"bytes 2-5/10"[..]));
assert_eq!(raw.body(head.content_length().unwrap()).await, b"2345");
let request = received.recv().await.unwrap();
assert_eq!(request.headers["range"], "bytes=2-5");
assert_eq!(request.headers["if-range"], "\"v1\"");
}
#[rstest]
#[tokio::test]
async fn a_large_download_is_paced_by_the_client_and_keeps_its_content_length() {
const LENGTH: usize = 128 * 1024 * 1024;
let written = Arc::new(AtomicUsize::new(0));
let writing = written.clone();
let upstream = raw_upstream(move |mut python| {
let writing = writing.clone();
async move {
python.request_head().await.unwrap();
python
.send(format!("HTTP/1.1 200 OK\r\ncontent-type: application/octet-stream\r\ncontent-length: {LENGTH}\r\n\r\n"))
.await;
let chunk = [0xa5; 64 * 1024];
while writing.load(Ordering::SeqCst) < LENGTH {
python.send(chunk).await;
writing.fetch_add(chunk.len(), Ordering::SeqCst);
}
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET /v1/files/file-1/content HTTP/1.1\r\nhost: x\r\n\r\n")
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.content_length(), Some(LENGTH));
assert_eq!(head.header("transfer-encoding"), None);
tokio::time::sleep(Duration::from_secs(1)).await;
assert!(
written.load(Ordering::SeqCst) < LENGTH / 4,
"the forwarder buffered a download the client was not reading"
);
let mut remaining = LENGTH;
while remaining > 0 {
remaining -= within(raw.body(remaining.min(1 << 20))).await.len();
}
}
/// The UI revalidates its static assets, and a 304 must carry exactly the validators Python sent,
/// with no length invented for a body it never has.
#[rstest]
#[tokio::test]
async fn a_conditional_request_gets_python_304_with_its_validators_only() {
let (event, mut events) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python| {
let event = event.clone();
async move {
while let Some(head) = python.request_head().await {
event
.send(head.header("if-none-match").map(<[u8]>::to_vec))
.unwrap();
python
.send("HTTP/1.1 304 Not Modified\r\netag: \"5f1-abc\"\r\ncache-control: no-cache\r\nvary: Accept-Encoding\r\ndate: Tue, 03 Nov 2026 10:00:00 GMT\r\n\r\n")
.await;
}
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
for _ in 0..2 {
raw.send("GET /ui/_next/static/chunks/main.js HTTP/1.1\r\nhost: x\r\nif-none-match: \"5f1-abc\"\r\n\r\n")
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::NOT_MODIFIED);
let mut names: Vec<_> = head.headers.iter().map(|(name, _)| name.as_str()).collect();
names.sort_unstable();
assert_eq!(names, ["cache-control", "date", "etag", "vary"]);
assert_eq!(head.header("etag"), Some(&b"\"5f1-abc\""[..]));
assert_eq!(
head.header("date"),
Some(&b"Tue, 03 Nov 2026 10:00:00 GMT"[..])
);
assert_eq!(
within(events.recv()).await.unwrap().as_deref(),
Some(&b"\"5f1-abc\""[..])
);
}
}
/// A client knows a download was cut short only because fewer bytes than the Content-Length
/// arrived before the connection closed, so the length must survive and the connection must end.
#[rstest]
#[tokio::test]
async fn a_download_python_cuts_short_closes_the_client_connection_before_its_length() {
let upstream = raw_upstream(|mut python| async move {
python.request_head().await.unwrap();
python
.send([&b"HTTP/1.1 200 OK\r\ncontent-type: application/octet-stream\r\ncontent-length: 1000\r\n\r\n"[..], &[0xa5; 500]].concat())
.await;
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET /v1/files/file-1/content HTTP/1.1\r\nhost: x\r\n\r\n")
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::OK);
assert_eq!(head.content_length(), Some(1000));
assert_eq!(within(raw.until_closed()).await, [0xa5; 500]);
}

855
litellm-rust/crates/gateway-forward/tests/exchange.rs Normal file
View file

@ -0,0 +1,855 @@
mod support;
use std::{
convert::Infallible,
sync::{
Arc,
atomic::{AtomicUsize, Ordering},
},
};
use axum::{
Router,
body::{Body, Bytes},
extract::Request,
http::{HeaderValue, StatusCode},
response::Response,
};
use litellm_gateway_forward::PEER_HEADER;
use rstest::rstest;
use support::{Gateway, Head, client, raw_upstream, recording, serve, within};
use tokio::{
io::{AsyncReadExt, AsyncWriteExt},
sync::mpsc,
};
fn ok() -> Response {
Response::new(Body::from("ok"))
}
/// An upstream that reports each bodiless request head exactly as it arrived on the wire.
async fn heads() -> (std::net::SocketAddr, mpsc::UnboundedReceiver<Head>) {
let (sender, receiver) = mpsc::unbounded_channel();
let address = raw_upstream(move |mut python| {
let sender = sender.clone();
async move {
while let Some(head) = python.request_head().await {
sender.send(head).unwrap();
python
.send("HTTP/1.1 200 OK\r\ncontent-length: 2\r\n\r\nok")
.await;
}
}
})
.await;
(address, receiver)
}
#[rstest]
#[tokio::test]
async fn forwards_the_request_as_the_client_sent_it_minus_hop_headers() {
let (upstream, mut received) = recording(|| {
Response::builder()
.status(StatusCode::UNAUTHORIZED)
.header("connection", "x-upstream-hop")
.header("x-upstream-hop", "remove")
.header("x-response", "keep")
.body(Body::from("python error"))
.unwrap()
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(
"PATCH /v1/messages?x=a%2Fb&x=c HTTP/1.1\r\n\
host: public.example\r\n\
authorization: Bearer test\r\n\
connection: x-remove, keep-alive\r\n\
x-remove: remove\r\n\
proxy-authorization: remove\r\n\
te: trailers\r\n\
content-length: 7\r\n\r\npayload",
)
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::UNAUTHORIZED);
assert_eq!(head.header("x-response"), Some(&b"keep"[..]));
assert_eq!(head.header("x-upstream-hop"), None);
let body = raw.body(head.content_length().unwrap()).await;
assert_eq!(body, b"python error");
let request = received.recv().await.unwrap();
assert_eq!(request.method, "PATCH");
assert_eq!(request.uri, "/v1/messages?x=a%2Fb&x=c");
assert_eq!(request.headers["host"], "public.example");
assert_eq!(request.headers["authorization"], "Bearer test");
assert!(!request.headers.contains_key("x-remove"));
assert!(!request.headers.contains_key("proxy-authorization"));
assert!(!request.headers.contains_key("te"));
assert!(!request.headers.contains_key("connection"));
assert_eq!(request.body, "payload");
}
#[rstest]
#[case::host("HoSt", "public.example")]
#[case::length("Content-Length", "7")]
#[case::authorization("AUTHORIZATION", "Bearer test")]
#[case::cookie("Cookie", "session=test")]
#[case::api_key("X-Api-Key", "test")]
#[case::azure_key("Api-Key", "test")]
#[case::litellm_key("Litellm-Api-Key", "test")]
#[case::forwarded("Forwarded", "for=192.0.2.1;proto=https")]
#[case::forwarded_for("X-Forwarded-For", "192.0.2.1")]
#[case::forwarded_proto("X-Forwarded-Proto", "https")]
#[case::forwarded_host("X-Forwarded-Host", "public.example")]
#[case::content_type("Content-Type", "application/octet-stream")]
#[case::content_encoding("Content-Encoding", "identity")]
#[tokio::test]
async fn connection_cannot_remove_end_to_end_headers(#[case] name: &str, #[case] value: &str) {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
let host = if name.eq_ignore_ascii_case("host") {
""
} else {
"host: public.example\r\n"
};
let length = if name.eq_ignore_ascii_case("content-length") {
""
} else {
"content-length: 7\r\n"
};
raw.send(format!(
"POST / HTTP/1.1\r\n{host}{length}{name}: {value}\r\nconnection: x-remove\r\nconnection: {name}, keep-alive\r\nx-remove: remove\r\n\r\npayload"
)).await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
let request = within(received.recv()).await.unwrap();
assert_eq!(request.headers[name], value);
assert_eq!(request.body, "payload");
assert!(!request.headers.contains_key("connection"));
assert!(!request.headers.contains_key("x-remove"));
}
#[rstest]
#[tokio::test]
async fn connection_cannot_remove_response_credentials_or_representation_metadata() {
let (upstream, _received) = recording(|| {
Response::builder()
.status(StatusCode::UNAUTHORIZED)
.header("connection", "Content-Length, Set-Cookie, WWW-Authenticate, Authentication-Info, Content-Type, Content-Encoding, x-remove")
.header("content-length", "2")
.header("set-cookie", "session=; Max-Age=0")
.header("www-authenticate", "Bearer")
.header("authentication-info", "nextnonce=test")
.header("content-type", "text/plain")
.header("content-encoding", "identity")
.header("x-remove", "remove")
.body(Body::from("ok"))
.unwrap()
}).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET / HTTP/1.1\r\nhost: x\r\n\r\n").await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::UNAUTHORIZED);
assert_eq!(head.content_length(), Some(2));
assert_eq!(head.header("set-cookie"), Some(&b"session=; Max-Age=0"[..]));
assert_eq!(head.header("www-authenticate"), Some(&b"Bearer"[..]));
assert_eq!(
head.header("authentication-info"),
Some(&b"nextnonce=test"[..])
);
assert_eq!(head.header("content-type"), Some(&b"text/plain"[..]));
assert_eq!(head.header("content-encoding"), Some(&b"identity"[..]));
assert_eq!(head.header("x-remove"), None);
assert_eq!(raw.body(2).await, b"ok");
}
#[rstest]
#[case::get("GET")]
#[case::post("POST")]
#[case::put("PUT")]
#[case::delete("DELETE")]
#[case::options("OPTIONS")]
#[case::extension("PURGE")]
#[case::webdav("PROPFIND")]
#[case::lowercase("get")]
#[case::punctuated("M-SEARCH")]
#[tokio::test]
async fn forwards_every_method(#[case] method: &str) {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let response = client()
.request(
Request::builder()
.method(method)
.uri(gateway.url("/mcp"))
.body(Body::from("body"))
.unwrap(),
)
.await
.unwrap();
assert_eq!(response.status(), StatusCode::OK);
let request = received.recv().await.unwrap();
assert_eq!(request.method, method);
assert_eq!(request.body, "body");
}
#[rstest]
#[case::double_slash("//v1//models")]
#[case::encoded_slash("/v1/files/a%2Fb/content")]
#[case::encoded_hash_in_query("/v1/files?purpose=batch%23retry&limit=1")]
#[case::encoded_hash_in_path("/v1/files/report%231.pdf/content")]
#[case::encoded_hash_before_query("/gemini/v1beta/files/a%23b?key=k")]
#[case::encoded_query("/v1/models?q=%E2%9C%93&empty=&flag")]
#[case::utf8_bytes_escaped("/mcp/%F0%9F%A6%80")]
#[case::lowercase_encoded_slash("/v1/files/a%2fb/content")]
#[case::dot_segments("/openai/./v1/../v1/models")]
#[case::encoded_dot_segments("/openai/%2e%2e/v1/%2E/models")]
#[case::matrix_params("/langfuse/api;v=1/public;x=y/traces")]
#[case::plus_and_encoded_space("/gemini/v1beta/models?q=a+b&r=a%20b&s=%2B")]
#[case::empty_query("/v1/models?")]
#[case::question_marks_in_query("/v1/models??a=b?c")]
#[case::colons_in_segments(
"/v1/projects/p/locations/l/publishers/google/models/m:streamGenerateContent?alt=sse"
)]
#[case::sub_delims("/~u/@:!$&'()*+,=/x")]
#[case::raw_bytes_browsers_leave_unescaped("/a{b}|c^d\\e\"f?g={}|^`")]
#[case::invalid_percent_escapes("/a%zz%00b?%")]
#[tokio::test]
async fn forwards_the_request_target_byte_for_byte(#[case] target: &str) {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!("GET {target} HTTP/1.1\r\nhost: x\r\n\r\n"))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
assert_eq!(received.recv().await.unwrap().uri, target);
}
#[rstest]
#[tokio::test]
async fn forwards_a_query_string_as_long_as_uvicorn_accepts() {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
let target = format!("/vertex_ai/v1/models?key=%2F{}&end", "a%20b".repeat(3000));
raw.send(format!("GET {target} HTTP/1.1\r\nhost: x\r\n\r\n"))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
assert_eq!(received.recv().await.unwrap().uri, target.as_str());
}
#[rstest]
#[case::in_query("/v1/files?purpose=batch#retry&limit=1", "/v1/files?purpose=batch")]
#[case::in_path("/v1/files/report#1.pdf/content", "/v1/files/report")]
#[case::before_query("/gemini/v1beta/files/a#b?key=k", "/gemini/v1beta/files/a")]
#[tokio::test]
async fn forwards_only_the_path_and_query_before_a_fragment(
#[case] target: &str,
#[case] expected: &str,
) {
let (upstream, mut received) = heads().await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!("GET {target} HTTP/1.1\r\nhost: x\r\n\r\n"))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
assert_eq!(within(received.recv()).await.unwrap().path, expected);
}
#[rstest]
#[tokio::test]
async fn absolute_form_targets_reach_python_as_origin_form() {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(
"GET http://elsewhere.example/v1/models?x=1 HTTP/1.1\r\nhost: elsewhere.example\r\n\r\n",
)
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
let request = received.recv().await.unwrap();
assert_eq!(request.uri, "/v1/models?x=1");
}
#[rstest]
#[tokio::test]
async fn relays_a_response_with_more_headers_than_hyper_allows_by_default() {
let upstream = serve(axum::Router::new().fallback(|| async {
let headers = (0..150).map(|index| (format!("llm_provider-x-{index}"), "v"));
let mut response = ok();
for (name, value) in headers {
response.headers_mut().insert(
axum::http::HeaderName::from_bytes(name.as_bytes()).unwrap(),
HeaderValue::from_static(value),
);
}
response
}))
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET /v1/chat/completions HTTP/1.1\r\nhost: public.example\r\n\r\n")
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::OK);
assert_eq!(head.header("llm_provider-x-149"), Some(&b"v"[..]));
}
/// uvicorn's h11 parser has no header count limit, only a 16 KiB cap on the whole head.
#[rstest]
#[tokio::test]
async fn forwards_a_request_with_as_many_headers_as_uvicorn_accepts() {
let (sender, mut received) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |python| {
let sender = sender.clone();
async move {
let mut stream = python.into_stream();
let mut head = Vec::new();
while !head.ends_with(b"\r\n\r\n") {
head.push(stream.read_u8().await.unwrap());
}
sender.send(head).unwrap();
stream
.write_all(b"HTTP/1.1 200 OK\r\ncontent-length: 0\r\n\r\n")
.await
.unwrap();
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
let headers: String = (0..1000).map(|index| format!("x-{index}: v\r\n")).collect();
raw.send(format!(
"GET /v1/chat/completions HTTP/1.1\r\nhost: x\r\n{headers}\r\n"
))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
let head = String::from_utf8(within(received.recv()).await.unwrap()).unwrap();
assert!(head.contains(&headers));
}
async fn header_fields_python_receives(fields: &str) -> Vec<(String, Vec<u8>)> {
let (upstream, mut received) = heads().await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!(
"GET /anthropic/v1/messages HTTP/1.1\r\nhost: x\r\n{fields}\r\n"
))
.await;
within(raw.response_head()).await.unwrap();
within(received.recv())
.await
.unwrap()
.headers
.into_iter()
.filter(|(name, _)| name.starts_with("x-") && name != PEER_HEADER)
.collect()
}
fn fields(expected: &[(&str, &str)]) -> Vec<(String, Vec<u8>)> {
expected
.iter()
.map(|(name, value)| ((*name).to_owned(), value.as_bytes().to_vec()))
.collect()
}
/// Python reads `scope["headers"]` as the list the client sent, in that order.
#[rstest]
#[ignore = "divergence: HeaderMap::remove can move the headers after a dropped hop-by-hop one"]
#[tokio::test]
async fn dropping_a_hop_by_hop_header_keeps_the_others_in_order() {
let received = header_fields_python_receives(
"x-a: 1\r\nconnection: keep-alive\r\nx-b: 2\r\nx-c: 3\r\nx-d: 4\r\n",
)
.await;
assert_eq!(
received,
fields(&[("x-a", "1"), ("x-b", "2"), ("x-c", "3"), ("x-d", "4")])
);
}
/// uvicorn speaks only HTTP/1.1, so an HTTP/2 prior-knowledge client never reaches Python through
/// Rust either. hyper closes the connection where h11 answers 400, which no HTTP/2 client reads.
#[rstest]
#[tokio::test]
async fn an_http2_client_never_reaches_python() {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(b"PRI * HTTP/2.0\r\n\r\nSM\r\n\r\n\x00\x00\x00\x04\x00\x00\x00\x00\x00")
.await;
assert!(within(raw.until_closed()).await.is_empty());
assert!(received.try_recv().is_err());
}
#[rstest]
#[ignore = "divergence: HeaderMap groups every value of a name at its first position"]
#[tokio::test]
async fn interleaved_repeated_headers_reach_python_interleaved() {
let received = header_fields_python_receives("x-a: 1\r\nx-b: 2\r\nx-a: 3\r\n").await;
assert_eq!(
received,
fields(&[("x-a", "1"), ("x-b", "2"), ("x-a", "3")])
);
}
/// h11 trims optional whitespace around a value and keeps everything inside it, including empty
/// values and names using every token character.
#[rstest]
#[tokio::test]
async fn python_sees_header_values_as_h11_would_parse_them() {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET / HTTP/1.1\r\nhost: x\r\nx-empty:\r\nx-blank: \r\nx-inner: a \t b \t\r\nX-Token!#$%&'*+.^_`|~: v\r\nx-empty: second\r\n\r\n")
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
let request = received.recv().await.unwrap();
let values = |name: &str| -> Vec<&[u8]> {
request
.headers
.get_all(name)
.iter()
.map(HeaderValue::as_bytes)
.collect()
};
assert_eq!(values("x-empty"), [&b""[..], b"second"]);
assert_eq!(values("x-blank"), [&b""[..]]);
assert_eq!(values("x-inner"), [&b"a \t b"[..]]);
assert_eq!(values("x-token!#$%&'*+.^_`|~"), [&b"v"[..]]);
}
/// RFC 9112 section 5.2 lets a server either reject obs-fold or unfold it, and h11 unfolds.
#[rstest]
#[ignore = "divergence: hyper rejects obs-fold with a 400 where uvicorn unfolds it to one space"]
#[tokio::test]
async fn a_folded_header_reaches_python_unfolded() {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET / HTTP/1.1\r\nhost: x\r\nx-a: b\r\n c\r\n\r\n")
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
assert_eq!(received.recv().await.unwrap().headers["x-a"], "b c");
}
#[rstest]
#[tokio::test]
async fn keeps_repeated_response_headers_and_opaque_header_bytes() {
let (upstream, mut received) = recording(|| {
Response::builder()
.header("set-cookie", "a=1; Path=/")
.header("set-cookie", "b=2; HttpOnly")
.header("x-opaque", HeaderValue::from_bytes(b"caf\xe9").unwrap())
.body(Body::empty())
.unwrap()
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(b"GET / HTTP/1.1\r\nhost: x\r\nx-opaque: caf\xe9\r\n\r\n")
.await;
let head = within(raw.response_head()).await.unwrap();
let cookies: Vec<_> = head
.headers
.iter()
.filter(|(name, _)| name == "set-cookie")
.map(|(_, value)| value.as_slice())
.collect();
assert_eq!(cookies, [&b"a=1; Path=/"[..], b"b=2; HttpOnly"]);
assert_eq!(head.header("x-opaque"), Some(&b"caf\xe9"[..]));
assert_eq!(
received.recv().await.unwrap().headers["x-opaque"].as_bytes(),
b"caf\xe9"
);
}
/// An HTTP/1.0 client cannot decode chunked framing, so a streamed answer reaches it delimited by
/// the connection closing, as uvicorn sends it.
#[rstest]
#[tokio::test]
async fn an_http10_client_gets_a_streamed_answer_unframed_and_python_gets_its_body() {
let (upstream, mut received) = recording(|| {
Response::new(Body::from_stream(futures_util::stream::iter(
["str", "eamed"].map(|piece| Ok::<_, Infallible>(Bytes::from_static(piece.as_bytes()))),
)))
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("POST /v1/completions HTTP/1.0\r\nhost: x\r\ncontent-length: 7\r\n\r\npayload")
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::OK);
assert_eq!(head.header("transfer-encoding"), None);
assert_eq!(within(raw.until_closed()).await, b"streamed");
let request = received.recv().await.unwrap();
assert_eq!(request.method, "POST");
assert_eq!(request.body, "payload");
}
#[rstest]
#[tokio::test]
async fn answers_pipelined_requests_in_order() {
let upstream = serve(
Router::new().fallback(|request: Request| async move { request.uri().path().to_owned() }),
)
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET /first HTTP/1.1\r\nhost: x\r\n\r\nHEAD /second HTTP/1.1\r\nhost: x\r\n\r\nGET /third HTTP/1.1\r\nhost: x\r\n\r\n")
.await;
let first = within(raw.response_head()).await.unwrap();
assert_eq!(raw.body(first.content_length().unwrap()).await, b"/first");
let second = within(raw.response_head()).await.unwrap();
assert_eq!(second.content_length(), Some(7));
let third = within(raw.response_head()).await.unwrap();
assert_eq!(raw.body(third.content_length().unwrap()).await, b"/third");
}
#[rstest]
#[case::no_content(StatusCode::NO_CONTENT)]
#[case::not_modified(StatusCode::NOT_MODIFIED)]
#[tokio::test]
async fn bodiless_statuses_keep_the_connection_reusable(#[case] status: StatusCode) {
let upstream = serve(Router::new().fallback(move |request: Request| async move {
match request.uri().path() {
"/next" => (StatusCode::OK, "next"),
_ => (status, ""),
}
}))
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET /empty HTTP/1.1\r\nhost: x\r\n\r\nGET /next HTTP/1.1\r\nhost: x\r\n\r\n")
.await;
assert_eq!(within(raw.response_head()).await.unwrap().status, status);
let next = within(raw.response_head()).await.unwrap();
assert_eq!(raw.body(next.content_length().unwrap()).await, b"next");
}
#[rstest]
#[tokio::test]
async fn informational_responses_keep_the_connection_reusable() {
let upstream = raw_upstream(|mut python| async move {
while let Some(head) = python.request_head().await {
match head.path.as_str() {
"/hints" => {
python
.send("HTTP/1.1 103 Early Hints\r\nlink: </ui/app.css>; rel=preload\r\n\r\nHTTP/1.1 200 OK\r\ncontent-length: 5\r\n\r\nfinal")
.await
}
_ => {
python
.send("HTTP/1.1 200 OK\r\ncontent-length: 4\r\n\r\nnext")
.await
}
}
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET /hints HTTP/1.1\r\nhost: x\r\n\r\nGET /next HTTP/1.1\r\nhost: x\r\n\r\n")
.await;
let mut hinted = within(raw.response_head()).await.unwrap();
while hinted.status.is_informational() {
hinted = within(raw.response_head()).await.unwrap();
}
assert_eq!(hinted.status, StatusCode::OK);
assert_eq!(raw.body(hinted.content_length().unwrap()).await, b"final");
let next = within(raw.response_head()).await.unwrap();
assert_eq!(raw.body(next.content_length().unwrap()).await, b"next");
}
#[rstest]
#[case::found(
StatusCode::FOUND,
"https://idp.example/authorize?state=a%2Fb&redirect_uri=https%3A%2F%2Fpublic.example%2Fsso%2Fcallback"
)]
#[case::see_other(StatusCode::SEE_OTHER, "/ui/?login=success")]
#[case::temporary(StatusCode::TEMPORARY_REDIRECT, "./mcp/oauth/authorize?client_id=x")]
#[tokio::test]
async fn redirects_reach_the_client_with_location_and_cookies_unchanged(
#[case] status: StatusCode,
#[case] location: &'static str,
) {
let (upstream, _received) = recording(move || {
Response::builder()
.status(status)
.header("location", location)
.header(
"set-cookie",
"token=a%2Fb; Path=/; HttpOnly; Secure; SameSite=Lax",
)
.header("set-cookie", "state=; Max-Age=0")
.header(
"set-cookie",
"session=x; Expires=Wed, 04 Nov 2026 10:00:00 GMT; Path=/",
)
.body(Body::empty())
.unwrap()
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET /sso/key/generate HTTP/1.1\r\nhost: public.example\r\n\r\n")
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, status);
assert_eq!(head.header("location"), Some(location.as_bytes()));
let cookies: Vec<_> = head
.headers
.iter()
.filter(|(name, _)| name == "set-cookie")
.map(|(_, value)| value.as_slice())
.collect();
assert_eq!(
cookies,
[
&b"token=a%2Fb; Path=/; HttpOnly; Secure; SameSite=Lax"[..],
b"state=; Max-Age=0",
b"session=x; Expires=Wed, 04 Nov 2026 10:00:00 GMT; Path=/",
]
);
}
#[rstest]
#[tokio::test]
async fn non_websocket_upgrades_reach_python_as_plain_requests() {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET / HTTP/1.1\r\nhost: x\r\nconnection: upgrade, http2-settings\r\nupgrade: h2c\r\nhttp2-settings: AAMAAABkAAQAoAAAAAIAAAAA\r\n\r\n")
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
let request = received.recv().await.unwrap();
assert!(!request.headers.contains_key("upgrade"));
assert!(!request.headers.contains_key("connection"));
assert!(!request.headers.contains_key("http2-settings"));
}
#[rstest]
#[tokio::test]
async fn forwards_an_asterisk_form_options_request() {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("OPTIONS * HTTP/1.1\r\nhost: x\r\n\r\n").await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
let request = received.recv().await.unwrap();
assert_eq!(request.method, "OPTIONS");
assert_eq!(request.uri, "*");
}
#[rstest]
#[tokio::test]
async fn an_authority_form_target_is_a_400_python_never_sees() {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("CONNECT api.example:443 HTTP/1.1\r\nhost: api.example:443\r\n\r\n")
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::BAD_REQUEST
);
assert!(received.try_recv().is_err());
}
#[rstest]
#[tokio::test]
async fn a_client_connection_close_ends_only_the_client_connection() {
let connections = Arc::new(AtomicUsize::new(0));
let accepted = connections.clone();
let upstream = raw_upstream(move |mut python| {
accepted.fetch_add(1, Ordering::SeqCst);
async move {
while python.request_head().await.is_some() {
python
.send("HTTP/1.1 200 OK\r\ncontent-length: 2\r\n\r\nok")
.await;
}
}
})
.await;
let gateway = Gateway::start(upstream).await;
for _ in 0..2 {
let mut raw = gateway.connect().await;
raw.send("GET / HTTP/1.1\r\nhost: x\r\nconnection: close\r\n\r\n")
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.header("connection"), Some(&b"close"[..]));
assert_eq!(raw.body(2).await, b"ok");
within(raw.closed()).await;
}
assert_eq!(connections.load(Ordering::SeqCst), 1);
}
#[rstest]
#[tokio::test]
async fn a_python_connection_close_ends_only_the_upstream_connection() {
let connections = Arc::new(AtomicUsize::new(0));
let accepted = connections.clone();
let upstream = raw_upstream(move |mut python| {
accepted.fetch_add(1, Ordering::SeqCst);
async move {
python.request_head().await.unwrap();
python
.send("HTTP/1.1 500 Internal Server Error\r\ncontent-length: 5\r\nconnection: close\r\n\r\nerror")
.await;
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
for _ in 0..2 {
raw.send("GET / HTTP/1.1\r\nhost: x\r\n\r\n").await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::INTERNAL_SERVER_ERROR);
assert_eq!(head.header("connection"), None);
assert_eq!(raw.body(5).await, b"error");
}
assert_eq!(connections.load(Ordering::SeqCst), 2);
}
/// uvicorn answers HEAD on a streaming route with chunked framing and no body, so the client
/// must not be told the body is empty, and must not wait for one before its next request.
#[rstest]
#[tokio::test]
async fn head_answered_with_chunked_framing_claims_no_length_and_keeps_the_connection() {
let upstream = raw_upstream(|mut python| async move {
while let Some(head) = python.request_head().await {
match head.path.as_str() {
"/next" => {
python
.send("HTTP/1.1 200 OK\r\ncontent-length: 4\r\n\r\nnext")
.await
}
_ => {
python
.send("HTTP/1.1 200 OK\r\ncontent-type: text/event-stream\r\ntransfer-encoding: chunked\r\n\r\n")
.await
}
}
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("HEAD /mcp HTTP/1.1\r\nhost: x\r\n\r\nGET /next HTTP/1.1\r\nhost: x\r\n\r\n")
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::OK);
assert_eq!(head.content_length(), None);
let next = within(raw.response_head()).await.unwrap();
assert_eq!(raw.body(next.content_length().unwrap()).await, b"next");
}
const GZIP: &[u8] = &[
0x1f, 0x8b, 0x08, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0xff, 0x4b, 0x49, 0x2c, 0x49, 0xb4, 0x52,
0x30, 0xe4, 0xe2, 0x02, 0x00, 0xce, 0xcd, 0x78, 0x54, 0x09, 0x00, 0x00, 0x00,
];
#[rstest]
#[case::fixed_length(false)]
#[case::streamed(true)]
#[tokio::test]
async fn content_codings_cross_unchanged_both_ways(#[case] streamed: bool) {
let (upstream, mut received) = recording(move || {
let body = match streamed {
true => Body::from_stream(futures_util::stream::iter(
GZIP.chunks(5)
.map(|piece| Ok::<_, Infallible>(Bytes::from_static(piece))),
)),
false => Body::from(GZIP),
};
Response::builder()
.header("content-encoding", "gzip")
.header("vary", "Accept-Encoding")
.body(body)
.unwrap()
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(
[
format!(
"POST /v1/chat/completions HTTP/1.1\r\nhost: x\r\ncontent-encoding: gzip\r\naccept-encoding: gzip, br;q=0.5\r\ncontent-length: {}\r\n\r\n",
GZIP.len()
)
.as_bytes(),
GZIP,
]
.concat(),
)
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.header("content-encoding"), Some(&b"gzip"[..]));
assert_eq!(head.header("vary"), Some(&b"Accept-Encoding"[..]));
let body = match head.content_length() {
Some(length) => raw.body(length).await,
None => within(raw.chunked_body()).await,
};
assert_eq!(body, GZIP);
assert_eq!(head.content_length().is_none(), streamed);
let request = received.recv().await.unwrap();
assert_eq!(request.headers["content-encoding"], "gzip");
assert_eq!(request.headers["accept-encoding"], "gzip, br;q=0.5");
assert_eq!(request.body, GZIP);
}
#[rstest]
#[tokio::test]
async fn python_sees_no_accept_encoding_the_client_did_not_send() {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET /metrics/ HTTP/1.1\r\nhost: x\r\n\r\n").await;
within(raw.response_head()).await.unwrap();
assert!(
!received
.recv()
.await
.unwrap()
.headers
.contains_key("accept-encoding")
);
}

259
litellm-rust/crates/gateway-forward/tests/framing.rs Normal file
View file

@ -0,0 +1,259 @@
mod support;
use std::{collections::BTreeSet, net::SocketAddr};
use axum::http::StatusCode;
use rstest::rstest;
use support::{Gateway, Head, Raw, raw_upstream, within};
use tokio::sync::mpsc;
struct Captured {
head: Head,
body: Vec<u8>,
}
/// A keep-alive upstream that decodes framing like h11 and reports every request it reads.
async fn capturing() -> (SocketAddr, mpsc::UnboundedReceiver<Captured>) {
let (sender, receiver) = mpsc::unbounded_channel();
let address = raw_upstream(move |mut python: Raw| {
let sender = sender.clone();
async move {
while let Some(head) = python.request_head().await {
let body = match head.header("transfer-encoding") {
Some(_) => python.chunked_body().await,
None => python.body(content_length(&head)).await,
};
sender.send(Captured { head, body }).unwrap();
python
.send("HTTP/1.1 200 OK\r\ncontent-length: 2\r\n\r\nok")
.await;
}
}
})
.await;
(address, receiver)
}
/// The length h11 reads from every Content-Length field, which may repeat one value.
fn content_length(head: &Head) -> usize {
let lengths: BTreeSet<usize> = head
.headers
.iter()
.filter(|(name, _)| name.eq_ignore_ascii_case("content-length"))
.flat_map(|(_, value)| value.split(|byte| *byte == b','))
.map(|length| {
std::str::from_utf8(length.trim_ascii())
.unwrap()
.parse()
.unwrap()
})
.collect();
assert!(
lengths.len() < 2,
"python got conflicting lengths {lengths:?}"
);
lengths.first().copied().unwrap_or(0)
}
/// RFC 9112 section 6.3: Transfer-Encoding overrides Content-Length. Forwarding both would let
/// Python split the stream at a different place than Rust did. Section 6.1 then closes the
/// connection after the response, so a request smuggled behind it never runs.
#[rstest]
#[tokio::test]
async fn a_request_framed_two_ways_reaches_python_framed_by_transfer_encoding_and_closes() {
let (upstream, mut received) = capturing().await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("POST /v1/files HTTP/1.1\r\nhost: x\r\ncontent-length: 3\r\ntransfer-encoding: chunked\r\n\r\n5\r\nhello\r\n0\r\n\r\nGET /next HTTP/1.1\r\nhost: x\r\n\r\n")
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
raw.body(2).await;
within(raw.until_closed()).await;
let upload = received.recv().await.unwrap();
assert_eq!(upload.head.header("content-length"), None);
assert_eq!(
upload.head.header("transfer-encoding"),
Some(&b"chunked"[..])
);
assert_eq!(upload.body, b"hello");
assert!(
received.try_recv().is_err(),
"python ran the smuggled request"
);
}
#[rstest]
#[case::conflicting_content_lengths("content-length: 4\r\ncontent-length: 40\r\n")]
#[case::content_length_list("content-length: 4, 40\r\n")]
#[case::signed_content_length("content-length: +4\r\n")]
#[case::chunked_not_last("transfer-encoding: chunked, identity\r\ncontent-length: 4\r\n")]
#[case::unknown_coding("transfer-encoding: xchunked\r\ncontent-length: 4\r\n")]
#[case::space_before_colon("transfer-encoding : chunked\r\ncontent-length: 4\r\n")]
#[case::folded_transfer_encoding("transfer-encoding:\r\n chunked\r\ncontent-length: 4\r\n")]
#[case::bare_cr("x-a: b\rx-b: c\r\ncontent-length: 4\r\n")]
#[case::nul_byte("x-a: b\x00c\r\ncontent-length: 4\r\n")]
#[tokio::test]
async fn ambiguous_framing_never_reaches_python(#[case] headers: &str) {
let (upstream, mut received) = capturing().await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!(
"POST /v1/files HTTP/1.1\r\nhost: x\r\n{headers}\r\nbodyGET /smuggled HTTP/1.1\r\nhost: x\r\n\r\n"
))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::BAD_REQUEST
);
within(raw.closed()).await;
assert!(received.try_recv().is_err(), "python received a request");
}
#[rstest]
#[case::bare_lf("4\nbody\n0\n\n")]
#[case::invalid_size("zz\r\nbody\r\n0\r\n\r\n")]
#[case::size_overflow("10000000000000004\r\nbody\r\n0\r\n\r\n")]
#[tokio::test]
async fn a_malformed_request_body_is_a_400_not_a_502(#[case] chunks: &str) {
let upstream = raw_upstream(|mut python| async move { python.closed().await }).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!(
"POST /v1/files HTTP/1.1\r\nhost: x\r\ntransfer-encoding: chunked\r\n\r\n{chunks}"
))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::BAD_REQUEST
);
}
/// hyper decodes only the chunked layer, so any other coding would reach Python still coded but
/// framed as a plain body. uvicorn turns every h11 parse error into a 400, ignoring the 501 h11
/// suggests for codings.
#[rstest]
#[case::listed_before_chunked("transfer-encoding: gzip, chunked\r\n")]
#[case::split_across_fields("transfer-encoding: gzip\r\ntransfer-encoding: chunked\r\n")]
#[tokio::test]
async fn a_transfer_coding_other_than_chunked_is_the_400_uvicorn_sends_python_never_sees(
#[case] headers: &str,
) {
let (upstream, mut received) = capturing().await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!(
"POST /v1/files HTTP/1.1\r\nhost: x\r\n{headers}\r\n4\r\nbody\r\n0\r\n\r\n"
))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::BAD_REQUEST
);
assert!(
received.try_recv().is_err(),
"python received a still-coded body"
);
}
async fn assert_python_reads_the_body_and_the_next_request(headers: &str) {
let (upstream, mut received) = capturing().await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!(
"POST /v1/files HTTP/1.1\r\nhost: x\r\n{headers}\r\npayloadGET /next HTTP/1.1\r\nhost: x\r\n\r\n"
))
.await;
for _ in 0..2 {
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
raw.body(2).await;
}
assert_eq!(received.recv().await.unwrap().body, b"payload");
assert_eq!(received.recv().await.unwrap().head.path, "/next");
}
#[rstest]
#[case::repeated_fields("content-length: 7\r\ncontent-length: 7\r\n")]
#[case::leading_zeros("content-length: 007\r\n")]
#[tokio::test]
async fn a_content_length_h11_reads_one_way_reaches_python_framed_the_same(#[case] headers: &str) {
assert_python_reads_the_body_and_the_next_request(headers).await;
}
/// h11 accepts a Content-Length list that repeats one value, as RFC 9110 section 8.6 allows.
#[rstest]
#[ignore = "divergence: hyper's server parses each Content-Length field as one number and 400s a list"]
#[tokio::test]
async fn a_content_length_list_of_one_value_reaches_python() {
assert_python_reads_the_body_and_the_next_request("content-length: 7, 7\r\n").await;
}
#[rstest]
#[case::leading_zeros("0004\r\nbody\r\n0\r\n\r\n", "body")]
#[case::uppercase_hex("A\r\nbody\r\nbody\r\n0\r\n\r\n", "body\r\nbody")]
#[case::whitespace_after_size("4 \r\nbody\r\n0\r\n\r\n", "body")]
#[case::extension_and_trailer("4;a=\"b;c\"\r\nbody\r\n0\r\nx-sum: 1\r\n\r\n", "body")]
#[tokio::test]
async fn chunk_framing_h11_accepts_reaches_python_decoded(
#[case] chunks: &str,
#[case] body: &str,
) {
let (upstream, mut received) = capturing().await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!(
"POST /v1/files HTTP/1.1\r\nhost: x\r\ntransfer-encoding: chunked\r\n\r\n{chunks}GET /next HTTP/1.1\r\nhost: x\r\n\r\n"
))
.await;
for _ in 0..2 {
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
raw.body(2).await;
}
assert_eq!(received.recv().await.unwrap().body, body.as_bytes());
assert_eq!(received.recv().await.unwrap().head.path, "/next");
}
/// h11 reads a head whose lines end in a bare LF, so Python gets the same request through Rust.
#[rstest]
#[tokio::test]
async fn a_head_with_bare_lf_line_endings_reaches_python() {
let (upstream, mut received) = capturing().await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("POST /v1/files HTTP/1.1\nhost: x\nx-a: b\ncontent-length: 4\n\nbody")
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
let upload = received.recv().await.unwrap();
assert_eq!(upload.head.header("x-a"), Some(&b"b"[..]));
assert_eq!(upload.body, b"body");
}
/// h11 decodes a chunked body from an HTTP/1.0 client, and RFC 9112 section 6.1 only asks the
/// server to close the connection afterwards.
#[rstest]
#[ignore = "divergence: hyper rejects Transfer-Encoding on HTTP/1.0 with a 400 that uvicorn never sends"]
#[tokio::test]
async fn an_http10_chunked_upload_reaches_python() {
let (upstream, mut received) = capturing().await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("POST /v1/files HTTP/1.0\r\nhost: x\r\ntransfer-encoding: chunked\r\n\r\n4\r\nbody\r\n0\r\n\r\n")
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
assert_eq!(received.recv().await.unwrap().body, b"body");
}

102
litellm-rust/crates/gateway-forward/tests/idle_stream.rs Normal file
View file

@ -0,0 +1,102 @@
mod support;
use std::time::Duration;
use axum::{
body::Body,
extract::Request,
http::StatusCode,
response::{IntoResponse, Response},
};
use http_body_util::BodyExt;
use rstest::rstest;
use support::{Gateway, client, raw_upstream, recording, within};
use tokio::{sync::mpsc, time::Instant};
const SSE_HEAD: &str = "HTTP/1.1 200 OK\r\n\
date: Tue, 03 Nov 2026 00:00:00 GMT\r\n\
server: uvicorn\r\n\
cache-control: no-cache, no-transform\r\n\
connection: keep-alive\r\n\
content-type: text/event-stream\r\n\
mcp-session-id: session-1\r\n\
x-accel-buffering: no\r\n\
transfer-encoding: chunked\r\n\r\n";
const PING: &str = ": ping - 2026-11-03 00:20:00.000000+00:00\r\n\r\n";
const MESSAGE: &str = "event: message\r\ndata: {\"jsonrpc\":\"2.0\",\"method\":\"notifications/tools/list_changed\"}\r\n\r\n";
fn chunk(data: &str) -> String {
format!("{:x}\r\n{data}\r\n", data.len())
}
/// An MCP client holds a GET stream open for server-initiated messages, which may not come for
/// many minutes, so neither hop may close a stream for being idle.
#[rstest]
#[tokio::test(start_paused = true)]
async fn an_idle_mcp_stream_stays_open_in_both_directions() {
let idle = Duration::from_secs(20 * 60);
let (session, mut sessions) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python| {
let session = session.clone();
async move {
let head = python.request_head().await.unwrap();
session
.send(head.header("mcp-session-id").map(<[u8]>::to_vec))
.unwrap();
python.send(SSE_HEAD).await;
tokio::time::sleep(idle).await;
python.send(chunk(PING)).await;
python.send(chunk(MESSAGE)).await;
python.send("0\r\n\r\n").await;
}
})
.await;
let gateway = Gateway::start(upstream).await;
let started = Instant::now();
let response = client()
.request(
Request::get(gateway.url("/github/mcp"))
.header("accept", "text/event-stream")
.header("mcp-session-id", "session-1")
.body(Body::empty())
.unwrap(),
)
.await
.unwrap();
assert_eq!(response.headers()["mcp-session-id"], "session-1");
assert_eq!(response.headers()["x-accel-buffering"], "no");
assert!(!response.headers().contains_key("connection"));
assert_eq!(
sessions.recv().await.unwrap().as_deref(),
Some(&b"session-1"[..])
);
let body = response.into_body().collect().await.unwrap().to_bytes();
assert_eq!(body, [PING, MESSAGE].concat());
assert!(started.elapsed() >= idle);
}
#[rstest]
#[tokio::test]
async fn ends_a_session_with_a_bodiless_delete() {
let (upstream, mut received) = recording(|| -> Response {
([("mcp-session-id", "session-1")], StatusCode::NO_CONTENT).into_response()
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("DELETE /mcp HTTP/1.1\r\nhost: x\r\nmcp-session-id: session-1\r\n\r\n")
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::NO_CONTENT);
assert_eq!(head.header("mcp-session-id"), Some(&b"session-1"[..]));
let request = received.recv().await.unwrap();
assert_eq!(request.method, "DELETE");
assert_eq!(request.headers["mcp-session-id"], "session-1");
assert!(!request.headers.contains_key("transfer-encoding"));
assert!(request.body.is_empty());
}

473
litellm-rust/crates/gateway-forward/tests/lifecycle.rs Normal file
View file

@ -0,0 +1,473 @@
mod support;
use std::{
sync::Arc,
time::{Duration, Instant},
};
use axum::{Router, body::Body, extract::Request, http::StatusCode, response::Response};
use http_body_util::BodyExt;
use rstest::rstest;
use support::{
DRAIN, Gateway, Raw, client, raw_upstream, recording, serve, unreachable_upstream, within,
};
use tokio::{
net::{TcpListener, TcpStream},
sync::{Notify, mpsc},
};
fn ok() -> Response {
Response::new(Body::from("ok"))
}
/// Python stops a provider stream when it sees the client go away, so a client disconnect must
/// close Rust's connection to Python at every stage of the exchange.
#[rstest]
#[case::waiting_for_headers(
"POST /v1/chat/completions HTTP/1.1\r\nhost: x\r\ncontent-length: 0\r\n\r\n",
false
)]
#[case::mid_stream(
"POST /v1/chat/completions HTTP/1.1\r\nhost: x\r\ncontent-length: 0\r\n\r\n",
true
)]
#[case::mid_upload(
"POST /v1/files HTTP/1.1\r\nhost: x\r\ncontent-length: 1000000\r\n\r\npartial",
false
)]
#[case::waiting_for_websocket_handshake(
"GET /v1/realtime HTTP/1.1\r\nhost: x\r\nconnection: Upgrade\r\nupgrade: websocket\r\nsec-websocket-version: 13\r\nsec-websocket-key: dGhlIHNhbXBsZSBub25jZQ==\r\n\r\n",
false
)]
#[tokio::test]
async fn client_disconnect_closes_the_upstream_connection(
#[case] request: &'static str,
#[case] headers_sent: bool,
) {
let (event, mut events) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python: Raw| {
let event = event.clone();
async move {
python.request_head().await.unwrap();
if headers_sent {
python
.send("HTTP/1.1 200 OK\r\ntransfer-encoding: chunked\r\n\r\n6\r\ndata: \r\n")
.await;
}
event.send("received").unwrap();
python.closed().await;
event.send("closed").unwrap();
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(request).await;
assert_eq!(within(events.recv()).await, Some("received"));
if headers_sent {
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
}
drop(raw);
assert_eq!(within(events.recv()).await, Some("closed"));
}
/// Python treats EOF on its socket as the client leaving, so Rust must not half-close the
/// upstream connection once it has sent the request body.
#[rstest]
#[tokio::test]
async fn python_sees_no_eof_while_its_response_is_pending() {
let (verdict, mut verdicts) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python: Raw| {
let verdict = verdict.clone();
async move {
let head = python.request_head().await.unwrap();
python.body(head.content_length().unwrap()).await;
let eof = tokio::time::timeout(Duration::from_millis(200), python.closed())
.await
.is_ok();
verdict.send(eof).unwrap();
python
.send("HTTP/1.1 200 OK\r\ncontent-length: 2\r\n\r\nok")
.await;
}
})
.await;
let gateway = Gateway::start(upstream).await;
let response = within(
client().request(
Request::post(gateway.url("/mcp"))
.body(Body::from("{}"))
.unwrap(),
),
)
.await
.unwrap();
assert_eq!(response.status(), StatusCode::OK);
assert_eq!(verdicts.recv().await, Some(false));
}
/// uvicorn closes a connection that sat idle past its keep-alive timeout. A request Rust sends on
/// that connection as uvicorn closes it is lost, so Rust must retire idle connections first.
#[rstest]
#[case::reused_while_fresh(Duration::from_millis(0))]
#[case::past_the_pool_timeout(Duration::from_millis(250))]
#[case::past_python_keepalive(Duration::from_millis(450))]
#[tokio::test]
async fn never_reuses_a_connection_python_is_closing_for_idleness(#[case] idle: Duration) {
let keepalive = Duration::from_millis(400);
let upstream = raw_upstream(move |mut python: Raw| async move {
let mut idle_since = None::<Instant>;
while python.request_head().await.is_some() {
if idle_since.is_some_and(|since| since.elapsed() >= keepalive) {
return;
}
python
.send("HTTP/1.1 200 OK\r\ncontent-length: 2\r\n\r\nok")
.await;
idle_since = Some(Instant::now());
}
})
.await;
let gateway = Gateway::with_keepalive(upstream, keepalive).await;
let client = client();
let first = within(client.request(Request::get(gateway.url("/")).body(Body::empty()).unwrap()))
.await
.unwrap();
first.into_body().collect().await.unwrap();
tokio::time::sleep(idle).await;
let second =
within(client.request(Request::get(gateway.url("/")).body(Body::empty()).unwrap()))
.await
.unwrap();
assert_eq!(second.status(), StatusCode::OK);
}
#[rstest]
#[case::health("/health/liveliness")]
#[case::messages("/v1/messages")]
#[tokio::test]
async fn unreachable_python_is_a_502(#[case] path: &str) {
let gateway = Gateway::start(unreachable_upstream()).await;
let response =
within(client().request(Request::get(gateway.url(path)).body(Body::empty()).unwrap()))
.await
.unwrap();
assert_eq!(response.status(), StatusCode::BAD_GATEWAY);
}
#[rstest]
#[case::bad_status_line(b"HTTP/1.1 OK\r\ncontent-length: 0\r\n\r\n".to_vec())]
#[case::header_without_colon(b"HTTP/1.1 200 OK\r\nbroken header\r\ncontent-length: 0\r\n\r\n".to_vec())]
#[case::not_http(b"SSH-2.0-OpenSSH_9.6\r\n".to_vec())]
#[case::conflicting_lengths(
b"HTTP/1.1 200 OK\r\ncontent-length: 2\r\ncontent-length: 3\r\n\r\nok".to_vec()
)]
#[case::oversized_head(
[&b"HTTP/1.1 200 OK\r\nx-big: "[..], &vec![b'a'; 1024 * 1024], b"\r\n\r\n"].concat()
)]
#[case::closed_without_reply(Vec::new())]
#[tokio::test]
async fn an_upstream_that_breaks_http_is_a_502_and_the_client_connection_survives(
#[case] reply: Vec<u8>,
) {
let upstream = raw_upstream(move |mut python: Raw| {
let reply = reply.clone();
async move {
python.request_head().await.unwrap();
if reply.is_empty() {
return;
}
python.send(reply).await;
std::future::pending::<()>().await;
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
for _ in 0..2 {
raw.send("GET / HTTP/1.1\r\nhost: x\r\n\r\n").await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::BAD_GATEWAY);
assert_eq!(head.content_length(), Some(0));
}
}
#[rstest]
#[tokio::test]
async fn python_restarting_is_a_502_until_it_listens_again() {
let address = unreachable_upstream();
let gateway = Gateway::start(address).await;
let get = || client().request(Request::get(gateway.url("/")).body(Body::empty()).unwrap());
assert_eq!(
within(get()).await.unwrap().status(),
StatusCode::BAD_GATEWAY
);
let listener = TcpListener::bind(address).await.unwrap();
let router = Router::new().fallback(|| async { "up" });
tokio::spawn(async move { axum::serve(listener, router).await });
assert_eq!(within(get()).await.unwrap().status(), StatusCode::OK);
}
/// A request Python already read may have run, so it is answered with a 502 and never replayed.
#[rstest]
#[tokio::test]
async fn a_request_python_read_before_closing_is_a_502_and_never_replayed() {
let (event, mut seen) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python: Raw| {
let event = event.clone();
async move {
while let Some(head) = python.request_head().await {
python.body(head.content_length().unwrap()).await;
event.send(head.path.clone()).unwrap();
if head.path == "/v1/chat/completions" {
return;
}
python
.send("HTTP/1.1 200 OK\r\ncontent-length: 2\r\n\r\nok")
.await;
}
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("POST /warm HTTP/1.1\r\nhost: x\r\ncontent-length: 0\r\n\r\n")
.await;
let warm = within(raw.response_head()).await.unwrap();
raw.body(warm.content_length().unwrap()).await;
raw.send("POST /v1/chat/completions HTTP/1.1\r\nhost: x\r\ncontent-length: 2\r\n\r\n{}")
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::BAD_GATEWAY);
let paths: Vec<_> = std::iter::from_fn(|| seen.try_recv().ok()).collect();
assert_eq!(paths, ["/warm", "/v1/chat/completions"]);
}
#[rstest]
#[tokio::test]
async fn shutdown_lets_an_in_flight_stream_finish() {
let release = Arc::new(Notify::new());
let released = release.clone();
let upstream = raw_upstream(move |mut python: Raw| {
let released = released.clone();
async move {
python.request_head().await.unwrap();
python
.send("HTTP/1.1 200 OK\r\ntransfer-encoding: chunked\r\n\r\n5\r\nfirst\r\n")
.await;
released.notified().await;
python.send("4\r\nlast\r\n0\r\n\r\n").await;
}
})
.await;
let gateway = Gateway::start(upstream).await;
let response =
within(client().request(Request::get(gateway.url("/")).body(Body::empty()).unwrap()))
.await
.unwrap();
let server = gateway.shutdown();
tokio::time::sleep(Duration::from_millis(100)).await;
assert!(!server.is_finished());
release.notify_one();
let body = within(response.into_body().collect())
.await
.unwrap()
.to_bytes();
assert_eq!(body, "firstlast");
within(server).await.unwrap();
}
#[rstest]
#[tokio::test]
async fn shutdown_stops_waiting_for_a_stream_still_open_after_the_drain() {
let upstream = raw_upstream(|mut python: Raw| async move {
python.request_head().await.unwrap();
python
.send("HTTP/1.1 200 OK\r\ntransfer-encoding: chunked\r\n\r\n5\r\nfirst\r\n")
.await;
std::future::pending::<()>().await;
})
.await;
let gateway = Gateway::start(upstream).await;
let response =
within(client().request(Request::get(gateway.url("/")).body(Body::empty()).unwrap()))
.await
.unwrap();
let started = std::time::Instant::now();
within(gateway.shutdown()).await.unwrap();
assert!(started.elapsed() >= DRAIN);
drop(response);
}
#[rstest]
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
async fn concurrent_keep_alive_connections_each_get_their_own_responses() {
let upstream = serve(Router::new().fallback(|request: Request| async move {
let index: usize = request.uri().query().unwrap().parse().unwrap();
Response::builder()
.header("etag", format!("\"{index}\""))
.body(Body::from(index.to_string().repeat(1 + index * 1000)))
.unwrap()
}))
.await;
let gateway = Gateway::start(upstream).await;
let connections = 6;
let tasks: Vec<_> = (0..connections)
.map(|first| {
let address = gateway.address;
tokio::spawn(async move {
let mut raw = Raw::new(TcpStream::connect(address).await.unwrap());
for index in (first..50).step_by(connections) {
raw.send(format!(
"GET /ui/chunk.js?{index} HTTP/1.1\r\nhost: x\r\n\r\n"
))
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.header("etag"), Some(format!("\"{index}\"").as_bytes()));
let body = raw.body(head.content_length().unwrap()).await;
assert_eq!(
body,
index.to_string().repeat(1 + index * 1000).into_bytes()
);
}
})
})
.collect();
for task in tasks {
within(task).await.unwrap();
}
}
// Python's `--keepalive_timeout` governed idle client connections before Rust took the public
// port, and operators tune it against their load balancer's idle timeout, so it still does.
// Without it, a client that vanishes without closing its connection holds a socket forever and
// the gateway eventually runs out of file descriptors.
const IDLE: Duration = Duration::from_millis(400);
#[rstest]
#[tokio::test]
async fn closes_a_client_connection_idle_past_python_keepalive() {
let (upstream, _received) = recording(ok).await;
let gateway = Gateway::with_keepalive(upstream, IDLE).await;
let mut raw = gateway.connect().await;
for _ in 0..2 {
tokio::time::sleep(IDLE / 2).await;
raw.send("GET /health/liveliness HTTP/1.1\r\nhost: x\r\n\r\n")
.await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::OK);
raw.body(head.content_length().unwrap()).await;
}
let idle_since = Instant::now();
within(raw.closed()).await;
assert!(idle_since.elapsed() >= IDLE * 3 / 4);
}
/// uvicorn would hold a connection that never sends a request, which lets a client park sockets
/// for free, so the same limit applies before the first request too.
#[rstest]
#[tokio::test]
async fn closes_a_client_connection_that_never_sends_a_request() {
let (upstream, _received) = recording(ok).await;
let gateway = Gateway::with_keepalive(upstream, IDLE).await;
let mut raw = gateway.connect().await;
within(raw.closed()).await;
}
/// The limit only covers the wait for the next request. A response that goes quiet for longer
/// belongs to Python, which decides how long it may take.
#[rstest]
#[tokio::test]
async fn keeps_a_connection_open_while_a_response_goes_quiet() {
let upstream = raw_upstream(|mut python: Raw| async move {
python.request_head().await.unwrap();
python
.send("HTTP/1.1 200 OK\r\ntransfer-encoding: chunked\r\n\r\n")
.await;
tokio::time::sleep(IDLE * 3).await;
python.send("4\r\ndone\r\n0\r\n\r\n").await;
})
.await;
let gateway = Gateway::with_keepalive(upstream, IDLE).await;
let mut raw = gateway.connect().await;
raw.send("GET /v1/chat/completions HTTP/1.1\r\nhost: x\r\n\r\n")
.await;
within(raw.response_head()).await.unwrap();
assert_eq!(within(raw.chunked_body()).await, b"done");
}
/// Likewise for an upload that pauses longer than the limit before it finishes.
#[rstest]
#[tokio::test]
async fn keeps_a_connection_open_while_an_upload_goes_quiet() {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::with_keepalive(upstream, IDLE).await;
let mut raw = gateway.connect().await;
raw.send("POST /v1/files HTTP/1.1\r\nhost: x\r\ncontent-length: 8\r\n\r\nhalf")
.await;
tokio::time::sleep(IDLE * 3).await;
raw.send("done").await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
assert_eq!(received.recv().await.unwrap().body, "halfdone");
}
/// uvicorn answers a request it rejects (413, 401) as soon as it reads the head and then closes,
/// leaving the upload unread. The client must get that answer, not a 502 or a reset.
#[rstest]
#[case::sized("content-length: 16777216\r\n", vec![b'x'; 256 * 1024])]
#[case::chunked(
"transfer-encoding: chunked\r\n",
[&b"40000\r\n"[..], &[b'x'; 256 * 1024], b"\r\n"].concat()
)]
#[tokio::test]
async fn python_rejecting_an_upload_unread_and_closing_still_answers_the_client(
#[case] framing: &'static str,
#[case] partial_upload: Vec<u8>,
) {
let upstream = raw_upstream(|mut python: Raw| async move {
python.request_head().await.unwrap();
python
.send("HTTP/1.1 413 Payload Too Large\r\ncontent-type: application/json\r\ncontent-length: 26\r\nconnection: close\r\n\r\n{\"error\":\"file too large\"}")
.await;
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!(
"POST /v1/files HTTP/1.1\r\nhost: x\r\n{framing}\r\n"
))
.await;
raw.send(partial_upload).await;
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::PAYLOAD_TOO_LARGE);
assert_eq!(
raw.body(head.content_length().unwrap()).await,
b"{\"error\":\"file too large\"}"
);
}

360
litellm-rust/crates/gateway-forward/tests/roundtrip.rs Normal file
View file

@ -0,0 +1,360 @@
mod support;
use std::{
convert::Infallible,
sync::{Arc, Mutex},
};
use axum::{
body::{Body, Bytes},
http::{HeaderMap, HeaderName, HeaderValue, Method, Request, StatusCode},
response::Response,
};
use http_body_util::BodyExt;
use litellm_gateway_forward::PEER_HEADER;
use proptest::{prelude::*, test_runner::TestRunner};
use support::{Gateway, client, recording, within};
#[derive(Clone, Debug)]
struct Message {
headers: Vec<(String, Vec<Vec<u8>>)>,
body: Vec<u8>,
chunked: bool,
}
#[derive(Clone, Debug)]
struct Exchange {
method: Method,
target: String,
request: Message,
status: StatusCode,
response: Message,
}
/// Any value h11 reads back unchanged: visible ASCII, obs-text and interior whitespace.
fn header_value() -> impl Strategy<Value = Vec<u8>> {
prop::collection::vec(
prop_oneof![8 => 0x21u8..=0x7e, 2 => 0x80u8..=0xff, 1 => Just(b' '), 1 => Just(b'\t')],
0..24,
)
.prop_map(|value| value.trim_ascii().to_vec())
}
fn method() -> impl Strategy<Value = Method> {
prop_oneof![
Just(Method::GET),
Just(Method::POST),
Just(Method::PUT),
Just(Method::PATCH),
Just(Method::DELETE),
Just(Method::OPTIONS),
"[A-Za-z0-9!#$%&'*+.^_`|~-]{1,16}"
.prop_filter("HEAD and CONNECT frame differently", |method| {
!["HEAD", "CONNECT"].contains(&method.as_str())
})
.prop_map(|method| Method::from_bytes(method.as_bytes()).unwrap()),
]
}
fn message() -> impl Strategy<Value = Message> {
(
prop::collection::btree_map(
"x-[a-z0-9!#$%&'*+.^_`|~-]{1,12}",
prop::collection::vec(header_value(), 1..4),
0..12,
),
prop::collection::vec(any::<u8>(), 0..32 * 1024),
any::<bool>(),
)
.prop_map(|(headers, body, chunked)| Message {
headers: headers.into_iter().collect(),
body,
chunked,
})
}
fn target() -> impl Strategy<Value = String> {
let segment = prop_oneof![
"[A-Za-z0-9._~!$&'()*+,;=:@-]{0,8}",
"%[0-9A-Fa-f]{2}",
Just(".".to_owned()),
Just("..".to_owned()),
Just(String::new()),
];
(
prop::collection::vec(segment, 0..6),
prop::option::of("[A-Za-z0-9=&._~%/?:@!$'()*+,;-]{0,40}"),
)
.prop_map(|(segments, query)| {
let path = format!("/{}", segments.join("/"));
match query {
Some(query) => format!("{path}?{query}"),
None => path,
}
})
}
fn exchange() -> impl Strategy<Value = Exchange> {
let status = (200u16..600)
.prop_filter("bodiless status", |code| ![204, 205, 304].contains(code))
.prop_map(|code| StatusCode::from_u16(code).unwrap());
(method(), target(), message(), status, message()).prop_map(
|(method, target, request, status, response)| Exchange {
method,
target,
request,
status,
response,
},
)
}
fn body(message: &Message) -> Body {
if !message.chunked {
return Body::from(message.body.clone());
}
let chunks: Vec<Result<Bytes, Infallible>> = message
.body
.chunks(1000)
.map(|chunk| Ok(Bytes::copy_from_slice(chunk)))
.collect();
Body::from_stream(futures_util::stream::iter(chunks))
}
fn apply(headers: &mut HeaderMap, message: &Message) {
if message.chunked {
headers.insert("transfer-encoding", HeaderValue::from_static("chunked"));
}
for (name, values) in &message.headers {
for value in values {
headers.append(
HeaderName::from_bytes(name.as_bytes()).unwrap(),
HeaderValue::from_bytes(value).unwrap(),
);
}
}
}
fn assert_carried(headers: &HeaderMap, message: &Message, framing_and_hop: &[&str]) {
for (name, values) in &message.headers {
let carried: Vec<&[u8]> = headers
.get_all(name)
.iter()
.map(HeaderValue::as_bytes)
.collect();
let sent: Vec<&[u8]> = values.iter().map(Vec::as_slice).collect();
assert_eq!(carried, sent, "header {name}");
}
for name in headers.keys() {
assert!(
framing_and_hop.contains(&name.as_str())
|| message
.headers
.iter()
.any(|(sent, _)| sent == name.as_str()),
"unexpected header {name}"
);
}
}
/// Any request a client can send and any response Python can give cross the forwarder unchanged,
/// apart from the framing and peer headers the forwarder owns.
#[test]
fn every_exchange_crosses_the_forwarder_unchanged() {
let runtime = tokio::runtime::Runtime::new().unwrap();
let current = Arc::new(Mutex::new(None::<Exchange>));
let responding = current.clone();
let (gateway, received) = runtime.block_on(async {
let (upstream, received) = recording(move || {
let exchange = responding.lock().unwrap().clone().unwrap();
let mut response = Response::new(body(&exchange.response));
*response.status_mut() = exchange.status;
apply(response.headers_mut(), &exchange.response);
response
})
.await;
(
Gateway::start(upstream).await,
tokio::sync::Mutex::new(received),
)
});
let client = client();
TestRunner::new(ProptestConfig::with_cases(256))
.run(&exchange(), |exchange| {
*current.lock().unwrap() = Some(exchange.clone());
runtime.block_on(async {
while received.lock().await.try_recv().is_ok() {}
let mut request = Request::builder()
.method(exchange.method.clone())
.uri(gateway.url(&exchange.target))
.body(body(&exchange.request))
.unwrap();
apply(request.headers_mut(), &exchange.request);
let response = support::within(client.request(request)).await.unwrap();
let python = received.lock().await.recv().await.unwrap();
assert_eq!(python.method, exchange.method);
assert_eq!(python.uri, exchange.target.as_str());
assert_eq!(python.body, exchange.request.body);
assert_carried(
&python.headers,
&exchange.request,
&["host", "content-length", "transfer-encoding", PEER_HEADER],
);
assert_eq!(python.headers.get_all(PEER_HEADER).iter().count(), 1);
assert_eq!(response.status(), exchange.status);
let headers = response.headers().clone();
assert_carried(
&headers,
&exchange.response,
&["date", "content-length", "transfer-encoding"],
);
let body = support::within(response.into_body().collect())
.await
.unwrap();
assert_eq!(body.to_bytes(), exchange.response.body);
});
Ok(())
})
.unwrap();
}
#[derive(Clone, Debug)]
enum Framing {
Unframed,
Length,
Chunked(usize),
}
#[derive(Clone, Debug)]
struct WireRequest {
method: Method,
target: String,
headers: Vec<(String, Vec<u8>)>,
body: Vec<u8>,
framing: Framing,
}
fn wire_request() -> impl Strategy<Value = WireRequest> {
let framing = prop_oneof![
Just(Framing::Unframed),
Just(Framing::Length),
(1usize..2048).prop_map(Framing::Chunked),
];
(
method(),
target(),
prop::collection::vec(
("[xX]-[A-Za-z0-9!#$%&'*+.^_`|~-]{1,12}", header_value()),
0..24,
),
prop::collection::vec(any::<u8>(), 0..8 * 1024),
framing,
)
.prop_map(|(method, target, headers, body, framing)| WireRequest {
method,
target,
headers,
body: match framing {
Framing::Unframed => Vec::new(),
_ => body,
},
framing,
})
}
fn encode(request: &WireRequest) -> Vec<u8> {
let framing = match request.framing {
Framing::Unframed => String::new(),
Framing::Length => format!("Content-Length: {}\r\n", request.body.len()),
Framing::Chunked(_) => "Transfer-Encoding: chunked\r\n".to_owned(),
};
let fields = request
.headers
.iter()
.flat_map(|(name, value)| [name.as_bytes(), b": ", value, b"\r\n"].concat());
let body = match request.framing {
Framing::Chunked(size) => request
.body
.chunks(size)
.flat_map(|chunk| {
[format!("{:x}\r\n", chunk.len()).as_bytes(), chunk, b"\r\n"].concat()
})
.chain(*b"0\r\n\r\n")
.collect(),
_ => request.body.clone(),
};
[
format!(
"{} {} HTTP/1.1\r\nHost: x\r\n",
request.method, request.target
)
.into_bytes(),
fields.collect(),
framing.into_bytes(),
b"\r\n".to_vec(),
body,
]
.concat()
}
fn by_name<'a>(fields: impl Iterator<Item = (&'a str, &'a [u8])>) -> Vec<(String, &'a [u8])> {
let mut fields: Vec<_> = fields
.map(|(name, value)| (name.to_ascii_lowercase(), value))
.collect();
fields.sort_by(|(left, _), (right, _)| left.cmp(right));
fields
}
/// Pipelined requests in any framing, written in arbitrary pieces, reach Python one by one with
/// the bytes h11 would have read from the client directly.
#[test]
fn pipelined_wire_requests_reach_python_as_sent() {
let runtime = tokio::runtime::Runtime::new().unwrap();
let (gateway, received) = runtime.block_on(async {
let (upstream, received) = recording(|| Response::new(Body::from("ok"))).await;
(
Gateway::start(upstream).await,
tokio::sync::Mutex::new(received),
)
});
let requests = (prop::collection::vec(wire_request(), 1..5), 1usize..4096);
TestRunner::new(ProptestConfig::with_cases(256))
.run(&requests, |(requests, piece)| {
runtime.block_on(async {
let mut received = received.lock().await;
while received.try_recv().is_ok() {}
let mut raw = gateway.connect().await;
let wire: Vec<u8> = requests.iter().flat_map(encode).collect();
for bytes in wire.chunks(piece) {
raw.send(bytes).await;
}
for request in &requests {
let head = within(raw.response_head()).await.unwrap();
assert_eq!(head.status, StatusCode::OK, "{request:?}");
assert_eq!(raw.body(2).await, b"ok");
let python = within(received.recv()).await.unwrap();
assert_eq!(python.method, request.method);
assert_eq!(python.uri, request.target.as_str());
assert_eq!(python.body, request.body);
assert_eq!(python.headers["host"], "x");
let forwarded = python.headers.iter().filter(|(name, _)| {
!["host", "content-length", "transfer-encoding", PEER_HEADER]
.contains(&name.as_str())
});
assert_eq!(
by_name(forwarded.map(|(name, value)| (name.as_str(), value.as_bytes()))),
by_name(
request
.headers
.iter()
.map(|(name, value)| (name.as_str(), value.as_slice()))
)
);
}
});
Ok(())
})
.unwrap();
}

110
litellm-rust/crates/gateway-forward/tests/settings.rs Normal file
View file

@ -0,0 +1,110 @@
use std::{ffi::OsString, time::Duration};
use litellm_gateway_forward::{Error, Settings};
use rstest::rstest;
const COMPLETE: [(&str, &str); 5] = [
("LITELLM_FORWARD_UPSTREAM", "http://127.0.0.1:53211"),
("LITELLM_FORWARD_HOST", "0.0.0.0"),
("LITELLM_FORWARD_PORT", "4000"),
("LITELLM_FORWARD_UPSTREAM_KEEPALIVE", "2"),
("LITELLM_FORWARD_SHUTDOWN_DRAIN", "40"),
];
fn parse(variables: &[(&str, &str)]) -> Result<Option<Settings>, Error> {
Settings::from_vars(
variables
.iter()
.map(|(key, value)| (OsString::from(key), OsString::from(value))),
)
}
fn without(variable: &str) -> Vec<(&'static str, &'static str)> {
COMPLETE
.into_iter()
.filter(|(key, _)| *key != variable)
.collect()
}
fn with<'a>(variable: &'a str, value: &'a str) -> Vec<(&'a str, &'a str)> {
without(variable)
.into_iter()
.chain([(variable, value)])
.collect()
}
#[rstest]
fn reads_every_variable() {
assert_eq!(
parse(&COMPLETE).unwrap(),
Some(Settings {
upstream: "http://127.0.0.1:53211".parse().unwrap(),
host: "0.0.0.0".into(),
port: 4000,
upstream_keepalive: Duration::from_secs(2),
shutdown_drain: Duration::from_secs(40),
})
);
}
#[rstest]
fn without_an_upstream_the_gateway_is_not_forwarding() {
assert_eq!(parse(&without("LITELLM_FORWARD_UPSTREAM")).unwrap(), None);
}
#[rstest]
#[case::host("LITELLM_FORWARD_HOST")]
#[case::port("LITELLM_FORWARD_PORT")]
#[case::upstream_keepalive("LITELLM_FORWARD_UPSTREAM_KEEPALIVE")]
#[case::shutdown_drain("LITELLM_FORWARD_SHUTDOWN_DRAIN")]
fn a_missing_variable_fails_naming_it(#[case] variable: &str) {
let error = parse(&without(variable)).unwrap_err();
assert!(error.to_string().contains(variable), "{error}");
}
#[rstest]
#[case::port_overflow("LITELLM_FORWARD_PORT", "65536")]
#[case::port_text("LITELLM_FORWARD_PORT", "http")]
#[case::keepalive_text("LITELLM_FORWARD_UPSTREAM_KEEPALIVE", "soon")]
#[case::keepalive_negative("LITELLM_FORWARD_UPSTREAM_KEEPALIVE", "-1")]
#[case::keepalive_zero("LITELLM_FORWARD_UPSTREAM_KEEPALIVE", "0")]
#[case::drain_text("LITELLM_FORWARD_SHUTDOWN_DRAIN", "soon")]
#[case::drain_negative("LITELLM_FORWARD_SHUTDOWN_DRAIN", "-1")]
#[case::drain_infinite("LITELLM_FORWARD_SHUTDOWN_DRAIN", "inf")]
fn an_invalid_variable_fails_naming_it(#[case] variable: &str, #[case] value: &str) {
let error = parse(&with(variable, value)).unwrap_err();
assert!(error.to_string().contains(variable), "{error}");
}
#[rstest]
fn fractional_drain_seconds_are_used_as_given() {
let settings = parse(&with("LITELLM_FORWARD_SHUTDOWN_DRAIN", "12.5"))
.unwrap()
.unwrap();
assert_eq!(settings.shutdown_drain, Duration::from_millis(12_500));
}
#[rstest]
#[case::keepalive("KEEPALIVE_TIMEOUT")]
#[case::graceful_shutdown("GRACEFUL_SHUTDOWN_TIMEOUT")]
#[case::host("HOST")]
#[case::port("PORT")]
fn python_settings_are_never_read(#[case] variable: &str) {
let mut variables = COMPLETE.to_vec();
variables.push((variable, "9"));
assert_eq!(parse(&variables).unwrap(), parse(&COMPLETE).unwrap());
}
#[rstest]
fn a_non_loopback_upstream_fails_startup() {
let error = parse(&with("LITELLM_FORWARD_UPSTREAM", "http://192.0.2.1:4000")).unwrap_err();
assert!(
error.to_string().contains("LITELLM_FORWARD_UPSTREAM"),
"{error}"
);
}

41
litellm-rust/crates/gateway-forward/tests/slow_head.rs Normal file
View file

@ -0,0 +1,41 @@
mod support;
use std::time::Duration;
use axum::{body::Body, extract::Request, http::StatusCode};
use http_body_util::BodyExt;
use rstest::rstest;
use support::{Gateway, client, raw_upstream};
use tokio::time::Instant;
/// Reasoning models with `stream=false`, image and video generation, and model health checks send
/// no response headers until the provider finishes, which can take many minutes.
#[rstest]
#[tokio::test(start_paused = true)]
async fn waits_for_response_headers_as_long_as_python_takes() {
let thinking = Duration::from_secs(30 * 60);
let upstream = raw_upstream(move |mut python| async move {
python.request_head().await.unwrap();
tokio::time::sleep(thinking).await;
python
.send("HTTP/1.1 200 OK\r\ncontent-length: 5\r\n\r\nimage")
.await;
})
.await;
let gateway = Gateway::start(upstream).await;
let started = Instant::now();
let response = client()
.request(
Request::post(gateway.url("/v1/images/generations"))
.body(Body::from("{}"))
.unwrap(),
)
.await
.unwrap();
assert_eq!(response.status(), StatusCode::OK);
assert!(started.elapsed() >= thinking);
let body = response.into_body().collect().await.unwrap().to_bytes();
assert_eq!(body, "image");
}

313
litellm-rust/crates/gateway-forward/tests/stream.rs Normal file
View file

@ -0,0 +1,313 @@
mod support;
use std::{
sync::{
Arc,
atomic::{AtomicUsize, Ordering},
},
time::Duration,
};
use axum::{body::Body, extract::Request, http::StatusCode};
use http_body_util::BodyExt;
use hyper::body::Incoming;
use rstest::rstest;
use support::{Gateway, client, raw_upstream, within};
use tokio::{
io::AsyncWriteExt,
sync::{Notify, mpsc},
};
fn chunk(bytes: &[u8]) -> Vec<u8> {
[format!("{:x}\r\n", bytes.len()).as_bytes(), bytes, b"\r\n"].concat()
}
const EVENTS: [&str; 3] = ["data: 1\n\n", "data: 2\n\n", "data: [DONE]\n\n"];
#[rstest]
#[tokio::test]
async fn each_event_reaches_the_client_before_python_produces_the_next(
#[values(true, false)] chunked: bool,
) {
let produce = Arc::new(Notify::new());
let next = produce.clone();
let upstream = raw_upstream(move |mut python| {
let next = next.clone();
async move {
python.request_head().await.unwrap();
let framing = match chunked {
true => "transfer-encoding: chunked".to_owned(),
false => format!("content-length: {}", EVENTS.concat().len()),
};
python
.send(format!(
"HTTP/1.1 200 OK\r\ncontent-type: text/event-stream\r\n{framing}\r\n\r\n"
))
.await;
for event in EVENTS {
match chunked {
true => python.send(chunk(event.as_bytes())).await,
false => python.send(event).await,
}
next.notified().await;
}
if chunked {
python.send("0\r\n\r\n").await;
}
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut response = within(
client().request(
Request::post(gateway.url("/v1/chat/completions"))
.body(Body::from(r#"{"stream":true}"#))
.unwrap(),
),
)
.await
.unwrap();
for event in EVENTS {
let frame = within(response.body_mut().frame()).await.unwrap().unwrap();
assert_eq!(frame.into_data().unwrap(), event);
produce.notify_one();
}
let rest = within(response.into_body().collect()).await.unwrap();
assert!(rest.to_bytes().is_empty());
}
#[rstest]
#[tokio::test]
async fn relays_a_binary_framed_stream_unchanged() {
let message: Vec<u8> = [
&[
0x00, 0x00, 0x00, 0x3d, 0x00, 0x00, 0x00, 0x20, 0x8a, 0x0d, 0x0a, 0xff,
][..],
b"\x0b:event-type\x07\x00\x05chunk\x0d:content-type\x07\x00\x10application/json",
b"0\r\n\r\n{\"bytes\":\"eyJ0eXBlIjoiY29udGVudCJ9\"}",
&[0xc3, 0x28, 0x00, 0x0d],
]
.concat();
let sent = message.clone();
let upstream = raw_upstream(move |mut python| {
let sent = sent.clone();
async move {
python.request_head().await.unwrap();
python
.send("HTTP/1.1 200 OK\r\ncontent-type: application/vnd.amazon.eventstream\r\ntransfer-encoding: chunked\r\n\r\n")
.await;
for piece in sent.chunks(7) {
python.send(chunk(piece)).await;
}
python.send("0\r\n\r\n").await;
}
})
.await;
let gateway = Gateway::start(upstream).await;
let response = within(
client().request(
Request::post(gateway.url("/bedrock/model/m/converse-stream"))
.body(Body::empty())
.unwrap(),
),
)
.await
.unwrap();
assert_eq!(
response.headers()["content-type"],
"application/vnd.amazon.eventstream"
);
let body = within(response.into_body().collect())
.await
.unwrap()
.to_bytes();
assert_eq!(body, message);
}
#[rstest]
#[tokio::test]
async fn relays_a_body_delimited_by_the_upstream_closing() {
let upstream = raw_upstream(|mut python| async move {
python.request_head().await.unwrap();
python
.send("HTTP/1.1 200 OK\r\nconnection: close\r\n\r\nuntil eof")
.await;
})
.await;
let gateway = Gateway::start(upstream).await;
let response = client().request(Request::get(gateway.url("/")).body(Body::empty()).unwrap());
let body = within(response).await.unwrap().into_body().collect();
assert_eq!(within(body).await.unwrap().to_bytes(), "until eof");
}
async fn drain(mut body: Incoming) -> (Vec<u8>, Result<(), hyper::Error>) {
let mut delivered = Vec::new();
loop {
match within(body.frame()).await {
None => return (delivered, Ok(())),
Some(Err(error)) => return (delivered, Err(error)),
Some(Ok(frame)) => delivered.extend_from_slice(&frame.into_data().unwrap()),
}
}
}
#[rstest]
#[case::after_the_head("transfer-encoding: chunked", "", "")]
#[case::between_events("transfer-encoding: chunked", "6\r\ndata: \r\n", "data: ")]
#[case::mid_event("transfer-encoding: chunked", "a\r\ndata:", "data:")]
#[case::short_of_its_content_length("content-length: 100", "data: 1\n\n", "data: 1\n\n")]
#[tokio::test]
async fn an_upstream_dying_mid_stream_fails_the_client_body_instead_of_ending_it(
#[case] framing: &'static str,
#[case] sent: &'static str,
#[case] delivered: &'static str,
) {
let upstream = raw_upstream(move |mut python| async move {
python.request_head().await.unwrap();
python
.send(format!(
"HTTP/1.1 200 OK\r\ncontent-type: text/event-stream\r\n{framing}\r\n\r\n{sent}"
))
.await;
})
.await;
let gateway = Gateway::start(upstream).await;
let response =
within(client().request(Request::get(gateway.url("/")).body(Body::empty()).unwrap()))
.await
.unwrap();
assert_eq!(response.status(), StatusCode::OK);
let (received, ended) = drain(response.into_body()).await;
assert_eq!(received, delivered.as_bytes());
assert!(ended.is_err());
}
#[rstest]
#[tokio::test]
async fn response_headers_reach_the_client_before_python_sends_any_body() {
let release = Arc::new(Notify::new());
let released = release.clone();
let upstream = raw_upstream(move |mut python| {
let released = released.clone();
async move {
python.request_head().await.unwrap();
python
.send("HTTP/1.1 200 OK\r\ncontent-type: text/event-stream; charset=utf-8\r\nx-accel-buffering: no\r\nx-litellm-call-id: call-1\r\ntransfer-encoding: chunked\r\n\r\n")
.await;
released.notified().await;
python.send(chunk(b"data: 1\n\n")).await;
python.send("0\r\n\r\n").await;
}
})
.await;
let gateway = Gateway::start(upstream).await;
let response =
within(client().request(Request::post(gateway.url("/")).body(Body::empty()).unwrap()))
.await
.unwrap();
assert_eq!(response.headers()["x-litellm-call-id"], "call-1");
assert_eq!(response.headers()["x-accel-buffering"], "no");
release.notify_one();
let body = within(response.into_body().collect())
.await
.unwrap()
.to_bytes();
assert_eq!(body, "data: 1\n\n");
}
/// A connection closed without any response looks retryable to client SDKs, which would re-run a
/// request Python already ran. Python dying right after its head races the relay, hence the loop.
#[rstest]
#[tokio::test]
async fn a_head_python_sent_right_before_dying_still_reaches_the_client() {
let upstream = raw_upstream(|mut python| async move {
python.request_head().await.unwrap();
python
.send("HTTP/1.1 200 OK\r\ncontent-type: text/event-stream\r\ntransfer-encoding: chunked\r\n\r\n")
.await;
})
.await;
let gateway = Gateway::start(upstream).await;
for _ in 0..20 {
let mut raw = gateway.connect().await;
raw.send("POST / HTTP/1.1\r\nhost: x\r\ncontent-length: 0\r\n\r\n")
.await;
let head = within(raw.response_head()).await;
assert_eq!(head.map(|head| head.status), Some(StatusCode::OK));
}
}
#[rstest]
#[tokio::test]
async fn a_client_that_stops_reading_stalls_python_instead_of_being_buffered_for() {
let written = Arc::new(AtomicUsize::new(0));
let counted = written.clone();
let (failed, mut write_failed) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python| {
let counted = counted.clone();
let failed = failed.clone();
async move {
python.request_head().await.unwrap();
let mut python = python.into_stream();
python
.write_all(b"HTTP/1.1 200 OK\r\ntransfer-encoding: chunked\r\n\r\n")
.await
.unwrap();
let piece = chunk(&[0x5a; 64 * 1024]);
while python.write_all(&piece).await.is_ok() {
counted.fetch_add(piece.len(), Ordering::SeqCst);
}
failed.send(()).unwrap();
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("POST / HTTP/1.1\r\nhost: x\r\ncontent-length: 0\r\n\r\n")
.await;
within(raw.response_head()).await.unwrap();
tokio::time::sleep(Duration::from_secs(1)).await;
let stalled = written.load(Ordering::SeqCst);
tokio::time::sleep(Duration::from_millis(250)).await;
assert_eq!(written.load(Ordering::SeqCst), stalled);
assert!(stalled < 64 * 1024 * 1024, "{stalled} bytes in flight");
drop(raw);
within(write_failed.recv()).await.unwrap();
}
#[rstest]
#[tokio::test]
async fn an_http10_client_receives_a_streamed_body_delimited_by_close() {
let upstream = raw_upstream(|mut python| async move {
python.request_head().await.unwrap();
python
.send([
&b"HTTP/1.1 200 OK\r\ncontent-type: text/event-stream\r\ntransfer-encoding: chunked\r\n\r\n"[..],
&chunk(b"data: 1\n"),
&chunk(b"data: 2\n"),
b"0\r\n\r\n",
]
.concat())
.await;
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("GET /v1/stream HTTP/1.0\r\nhost: x\r\n\r\n").await;
let response = String::from_utf8(within(raw.until_closed()).await).unwrap();
let (head, body) = response.split_once("\r\n\r\n").unwrap();
assert!(head.starts_with("HTTP/1.0 200 OK"), "{head}");
assert!(
!head.to_ascii_lowercase().contains("transfer-encoding"),
"{head}"
);
assert_eq!(body, "data: 1\ndata: 2\n");
}

311
litellm-rust/crates/gateway-forward/tests/support/mod.rs Normal file
View file

@ -0,0 +1,311 @@
#![allow(
dead_code,
reason = "each test binary uses a different subset of the harness"
)]
use std::{future::Future, net::SocketAddr, time::Duration};
use axum::{
Router,
body::{Body, Bytes},
extract::Request,
http::{HeaderMap, Method, StatusCode, Uri},
};
use http_body_util::BodyExt;
use hyper_util::{
client::legacy::{Client, connect::HttpConnector},
rt::TokioExecutor,
};
use litellm_gateway_forward::Forward;
use tokio::{
io::{AsyncReadExt, AsyncWriteExt},
net::{TcpListener, TcpStream},
sync::{mpsc, oneshot},
task::JoinHandle,
};
pub const WAIT: Duration = Duration::from_secs(5);
pub const UVICORN_KEEPALIVE: Duration = Duration::from_secs(5);
pub const DRAIN: Duration = Duration::from_secs(1);
pub async fn within<T>(future: impl Future<Output = T>) -> T {
tokio::time::timeout(WAIT, future).await.expect("timed out")
}
/// A running forwarder in front of `upstream`, listening on a real socket like production.
pub struct Gateway {
pub address: SocketAddr,
stop: oneshot::Sender<()>,
server: JoinHandle<()>,
}
impl Gateway {
pub async fn start(upstream: SocketAddr) -> Self {
Self::with_keepalive(upstream, UVICORN_KEEPALIVE).await
}
pub async fn with_keepalive(upstream: SocketAddr, keepalive: Duration) -> Self {
let forward = Forward::new(&format!("http://{upstream}").parse().unwrap(), keepalive);
let public = TcpListener::bind("127.0.0.1:0").await.unwrap();
let address = public.local_addr().unwrap();
let (stop, stopped) = oneshot::channel::<()>();
let server = tokio::spawn(forward.serve(
public,
async {
stopped.await.ok();
},
DRAIN,
));
Self {
address,
stop,
server,
}
}
pub fn url(&self, path_and_query: &str) -> Uri {
format!("http://{}{path_and_query}", self.address)
.parse()
.unwrap()
}
pub async fn connect(&self) -> Raw {
Raw::new(TcpStream::connect(self.address).await.unwrap())
}
/// Starts graceful shutdown and returns the server task, which ends once in-flight work drains
/// or `DRAIN` passes.
pub fn shutdown(self) -> JoinHandle<()> {
self.stop.send(()).unwrap();
self.server
}
}
pub fn client() -> Client<HttpConnector, Body> {
Client::builder(TokioExecutor::new()).build_http()
}
/// What the upstream received, after the forwarder rewrote it.
pub struct Received {
pub method: Method,
pub uri: Uri,
pub headers: HeaderMap,
pub body: Bytes,
}
/// An axum upstream that records every request it fully reads and answers with `respond`.
pub async fn recording(
respond: impl Fn() -> axum::response::Response + Clone + Send + Sync + 'static,
) -> (SocketAddr, mpsc::UnboundedReceiver<Received>) {
let (sender, receiver) = mpsc::unbounded_channel();
let address = serve(Router::new().fallback(move |request: Request| {
let sender = sender.clone();
let respond = respond.clone();
async move {
let (parts, body) = request.into_parts();
let body = body.collect().await.unwrap().to_bytes();
sender
.send(Received {
method: parts.method,
uri: parts.uri,
headers: parts.headers,
body,
})
.unwrap();
respond()
}
}))
.await;
(address, receiver)
}
pub async fn serve(router: Router) -> SocketAddr {
let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
let address = listener.local_addr().unwrap();
tokio::spawn(async move { axum::serve(listener, router).await.unwrap() });
address
}
/// An upstream that hands each accepted connection to `handle` as raw bytes, for behavior a
/// well-behaved HTTP server would never produce.
pub async fn raw_upstream<F, Fut>(handle: F) -> SocketAddr
where
F: Fn(Raw) -> Fut + Send + Sync + 'static,
Fut: Future<Output = ()> + Send + 'static,
{
let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
let address = listener.local_addr().unwrap();
tokio::spawn(async move {
loop {
let (stream, _) = listener.accept().await.unwrap();
tokio::spawn(handle(Raw::new(stream)));
}
});
address
}
pub fn unreachable_upstream() -> SocketAddr {
let listener = std::net::TcpListener::bind("127.0.0.1:0").unwrap();
listener.local_addr().unwrap()
}
pub struct Head {
pub status: StatusCode,
pub headers: Vec<(String, Vec<u8>)>,
pub path: String,
}
impl Head {
pub fn header(&self, name: &str) -> Option<&[u8]> {
self.headers
.iter()
.find(|(key, _)| key.eq_ignore_ascii_case(name))
.map(|(_, value)| value.as_slice())
}
pub fn content_length(&self) -> Option<usize> {
self.header("content-length")
.map(|value| std::str::from_utf8(value).unwrap().parse().unwrap())
}
}
/// One TCP connection driven byte by byte, so tests control framing, timing and disconnects.
/// Bytes read past a message head stay buffered for the next read.
pub struct Raw {
stream: TcpStream,
buffer: Vec<u8>,
}
impl Raw {
pub fn new(stream: TcpStream) -> Self {
Self {
stream,
buffer: Vec::new(),
}
}
pub fn into_stream(self) -> TcpStream {
assert!(self.buffer.is_empty(), "buffered bytes would be lost");
self.stream
}
pub fn local_address(&self) -> SocketAddr {
self.stream.local_addr().unwrap()
}
pub async fn send(&mut self, bytes: impl AsRef<[u8]>) {
self.stream.write_all(bytes.as_ref()).await.unwrap();
}
/// Reads one request head, or `None` when the peer closed the connection first.
pub async fn request_head(&mut self) -> Option<Head> {
self.head(|bytes| {
let mut headers = [httparse::EMPTY_HEADER; 256];
let mut request = httparse::Request::new(&mut headers);
let httparse::Status::Complete(length) = request.parse(bytes).unwrap() else {
return None;
};
Some((
length,
Head {
status: StatusCode::OK,
headers: owned(request.headers),
path: request.path.unwrap().to_owned(),
},
))
})
.await
}
pub async fn response_head(&mut self) -> Option<Head> {
self.head(|bytes| {
let mut headers = [httparse::EMPTY_HEADER; 256];
let mut response = httparse::Response::new(&mut headers);
let httparse::Status::Complete(length) = response.parse(bytes).unwrap() else {
return None;
};
Some((
length,
Head {
status: StatusCode::from_u16(response.code.unwrap()).unwrap(),
headers: owned(response.headers),
path: String::new(),
},
))
})
.await
}
async fn head(&mut self, parse: impl Fn(&[u8]) -> Option<(usize, Head)>) -> Option<Head> {
loop {
if let Some((length, head)) = parse(&self.buffer) {
self.buffer.drain(..length);
return Some(head);
}
if self.fill().await == 0 {
return None;
}
}
}
/// Reads exactly `length` body bytes, using what is already buffered first.
pub async fn body(&mut self, length: usize) -> Vec<u8> {
while self.buffer.len() < length {
assert_ne!(self.fill().await, 0, "closed mid-body");
}
self.buffer.drain(..length).collect()
}
/// Reads a whole chunked body and returns its decoded bytes.
pub async fn chunked_body(&mut self) -> Vec<u8> {
let mut decoded = Vec::new();
loop {
let size_line = self.line().await;
let size =
usize::from_str_radix(size_line.split(';').next().unwrap().trim(), 16).unwrap();
if size == 0 {
while !self.line().await.is_empty() {}
return decoded;
}
decoded.extend(self.body(size).await);
assert_eq!(self.body(2).await, b"\r\n");
}
}
async fn line(&mut self) -> String {
loop {
if let Some(end) = self.buffer.windows(2).position(|window| window == b"\r\n") {
let line = String::from_utf8(self.buffer[..end].to_vec()).unwrap();
self.buffer.drain(..end + 2);
return line;
}
assert_ne!(self.fill().await, 0, "closed mid-line");
}
}
async fn fill(&mut self) -> usize {
let mut chunk = [0; 8192];
let read = self.stream.read(&mut chunk).await.unwrap_or(0);
self.buffer.extend_from_slice(&chunk[..read]);
read
}
/// Everything the peer sends until it closes, including bytes already buffered.
pub async fn until_closed(&mut self) -> Vec<u8> {
while self.fill().await != 0 {}
std::mem::take(&mut self.buffer)
}
/// Resolves once the peer closes the connection, discarding anything it still sends.
pub async fn closed(&mut self) {
let mut chunk = [0; 8192];
while self.stream.read(&mut chunk).await.unwrap_or(0) != 0 {}
}
}
fn owned(headers: &[httparse::Header<'_>]) -> Vec<(String, Vec<u8>)> {
headers
.iter()
.map(|header| (header.name.to_owned(), header.value.to_vec()))
.collect()
}

339
litellm-rust/crates/gateway-forward/tests/upload.rs Normal file
View file

@ -0,0 +1,339 @@
mod support;
use std::{
convert::Infallible,
sync::{
Arc,
atomic::{AtomicUsize, Ordering},
},
time::Duration,
};
use axum::{
Router,
body::{Body, Bytes},
extract::Request,
http::StatusCode,
response::Response,
};
use http_body_util::BodyExt;
use rstest::rstest;
use support::{Gateway, Raw, client, raw_upstream, recording, serve, within};
use tokio::{
io::AsyncWriteExt,
sync::{Notify, mpsc},
};
fn ok() -> Response {
Response::new(Body::from("ok"))
}
#[rstest]
#[tokio::test]
async fn streams_upload_and_response_incrementally_without_a_body_limit() {
let upstream = serve(
Router::new().fallback(|request: Request| async { Response::new(request.into_body()) }),
)
.await;
let gateway = Gateway::start(upstream).await;
let (sender, receiver) = mpsc::channel::<Result<Bytes, Infallible>>(1);
let stream = futures_util::stream::unfold(receiver, |mut receiver| async {
receiver.recv().await.map(|chunk| (chunk, receiver))
});
sender.send(Ok(Bytes::from_static(b"first"))).await.unwrap();
let mut response = within(
client().request(
Request::post(gateway.url("/v1/files"))
.body(Body::from_stream(stream))
.unwrap(),
),
)
.await
.unwrap();
let frame = within(response.body_mut().frame()).await.unwrap().unwrap();
assert_eq!(frame.into_data().unwrap(), "first");
let large = Bytes::from(vec![b'x'; 8 * 1024 * 1024]);
sender.send(Ok(large.clone())).await.unwrap();
drop(sender);
let rest = within(response.into_body().collect())
.await
.unwrap()
.to_bytes();
assert_eq!(rest, large);
}
/// hyper sends the 100 as soon as the request is forwarded, where uvicorn waits for the app to
/// read the body, so an upload Python rejects on headers alone is still sent in full.
#[rstest]
#[tokio::test]
async fn answers_expect_continue_so_large_uploads_start() {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send("POST /v1/audio/transcriptions HTTP/1.1\r\nhost: x\r\nexpect: 100-continue\r\ncontent-length: 4\r\n\r\n")
.await;
let interim = within(raw.response_head()).await.unwrap();
assert_eq!(interim.status, StatusCode::CONTINUE);
raw.send("data").await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
assert_eq!(received.recv().await.unwrap().body, "data");
}
/// curl sends `expect: 100-continue` for any body over 1 MiB and waits for the 100 before sending
/// the multipart body, which must reach Python intact even where it looks like framing.
#[rstest]
#[tokio::test]
async fn expect_continue_delivers_a_large_multipart_upload_byte_for_byte() {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let boundary = "------------------------d74496d66958873e";
let audio: Vec<u8> = (0..3 * 1024 * 1024)
.map(|index: u32| (index.wrapping_mul(2_654_435_761) >> 24) as u8)
.chain(*b"\r\n0\r\n\r\nPOST /smuggled HTTP/1.1\r\n\r\n--")
.collect();
let body = [
format!("--{boundary}\r\ncontent-disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n--{boundary}\r\ncontent-disposition: form-data; name=\"file\"; filename=\"a b.wav\"\r\ncontent-type: audio/wav\r\n\r\n").into_bytes(),
audio,
format!("\r\n--{boundary}--\r\n").into_bytes(),
]
.concat();
let content_type = format!("multipart/form-data; boundary={boundary}");
let mut raw = gateway.connect().await;
raw.send(format!(
"POST /v1/audio/transcriptions HTTP/1.1\r\nhost: x\r\ncontent-type: {content_type}\r\nexpect: 100-continue\r\ncontent-length: {}\r\n\r\n",
body.len()
))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::CONTINUE
);
raw.send(&body).await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
let request = received.recv().await.unwrap();
assert_eq!(request.headers["content-type"], content_type.as_str());
assert_eq!(request.body, body);
}
#[rstest]
#[case::get("GET")]
#[case::delete("DELETE")]
#[case::options("OPTIONS")]
#[case::post("POST")]
#[tokio::test]
async fn forwards_a_chunked_body_on_any_method(#[case] method: &str) {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!(
"{method} /v1/search HTTP/1.1\r\nhost: x\r\ntransfer-encoding: chunked\r\n\r\n4\r\nbody\r\n0\r\n\r\n"
))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
assert_eq!(received.recv().await.unwrap().body, "body");
}
#[rstest]
#[case::no_framing("", "", &[], "")]
#[case::empty_content_length("content-length: 0\r\n", "", &[("content-length", "0")], "")]
#[case::empty_chunked(
"transfer-encoding: chunked\r\n",
"0\r\n\r\n",
&[("transfer-encoding", "chunked")],
""
)]
#[case::sized(
"content-length: 7\r\n",
"payload",
&[("content-length", "7")],
"payload"
)]
#[case::chunk_extensions_and_trailers(
"transfer-encoding: chunked\r\n",
"4;name=\"v\"\r\nbody\r\n0\r\nx-checksum: 1\r\n\r\n",
&[("transfer-encoding", "chunked")],
"body"
)]
#[tokio::test]
async fn a_body_reaches_python_with_the_framing_the_client_chose(
#[values("POST", "GET")] method: &str,
#[case] framing: &str,
#[case] wire_body: &str,
#[case] python_framing: &[(&str, &str)],
#[case] python_body: &str,
) {
let (upstream, mut received) = recording(ok).await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!(
"{method} /v1/files HTTP/1.1\r\nhost: x\r\n{framing}\r\n{wire_body}"
))
.await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
let request = received.recv().await.unwrap();
let forwarded: Vec<(&str, &str)> = ["content-length", "transfer-encoding"]
.into_iter()
.flat_map(|name| {
request
.headers
.get_all(name)
.iter()
.map(move |value| (name, value.to_str().unwrap()))
})
.collect();
assert_eq!(request.method, method);
assert_eq!(forwarded, python_framing);
assert_eq!(request.body, python_body);
}
#[rstest]
#[tokio::test]
async fn a_large_upload_is_paced_by_python_reading_it() {
const LENGTH: usize = 128 * 1024 * 1024;
let start_reading = Arc::new(Notify::new());
let reading = start_reading.clone();
let upstream = raw_upstream(move |mut python| {
let reading = reading.clone();
async move {
let head = python.request_head().await.unwrap();
reading.notified().await;
let mut remaining = head.content_length().unwrap();
while remaining > 0 {
remaining -= python.body(remaining.min(1 << 20)).await.len();
}
python
.send("HTTP/1.1 200 OK\r\ncontent-length: 0\r\n\r\n")
.await;
}
})
.await;
let gateway = Gateway::start(upstream).await;
let (read, mut write) = gateway.connect().await.into_stream().into_split();
let sent = Arc::new(AtomicUsize::new(0));
let sending = sent.clone();
let upload = tokio::spawn(async move {
write
.write_all(
format!("POST /v1/files HTTP/1.1\r\nhost: x\r\ncontent-length: {LENGTH}\r\n\r\n")
.as_bytes(),
)
.await
.unwrap();
let chunk = [0x5a; 64 * 1024];
while sending.load(Ordering::SeqCst) < LENGTH {
write.write_all(&chunk).await.unwrap();
sending.fetch_add(chunk.len(), Ordering::SeqCst);
}
write
});
tokio::time::sleep(Duration::from_secs(1)).await;
assert!(
sent.load(Ordering::SeqCst) < LENGTH / 4,
"the forwarder buffered an upload Python was not reading"
);
start_reading.notify_one();
let write = tokio::time::timeout(Duration::from_secs(60), upload)
.await
.unwrap()
.unwrap();
let mut raw = Raw::new(read.reunite(write).unwrap());
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::OK
);
}
#[rstest]
#[case::between_chunks("5\r\nhello\r\n")]
#[case::mid_chunk("100\r\nhello")]
#[tokio::test]
async fn a_client_abandoning_a_chunked_upload_never_ends_python_body_cleanly(
#[case] sent: &'static str,
) {
let (forwarded, mut received) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python| {
let forwarded = forwarded.clone();
async move {
python.request_head().await.unwrap();
forwarded.send(python.until_closed().await).unwrap();
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(format!(
"POST /v1/files HTTP/1.1\r\nhost: x\r\ntransfer-encoding: chunked\r\n\r\n{sent}"
))
.await;
tokio::time::sleep(Duration::from_millis(100)).await;
drop(raw);
let body = within(received.recv()).await.unwrap();
assert!(body.starts_with(b"5\r\nhello\r\n"));
assert!(
!body.ends_with(b"0\r\n\r\n"),
"python saw a truncated upload end cleanly"
);
}
#[rstest]
#[tokio::test]
async fn an_early_answer_during_an_upload_keeps_both_connections_in_sync() {
let (event, mut events) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python| {
let event = event.clone();
async move {
while let Some(head) = python.request_head().await {
let length = head.content_length();
event.send(head.path.into_bytes()).unwrap();
let Some(length) = length else {
python
.send("HTTP/1.1 200 OK\r\ncontent-length: 4\r\n\r\nnext")
.await;
continue;
};
python
.send("HTTP/1.1 413 Payload Too Large\r\ncontent-length: 2\r\n\r\n{}")
.await;
event.send(python.body(length).await).unwrap();
}
}
})
.await;
let gateway = Gateway::start(upstream).await;
let upload = b"GET /smuggled HTTP/1.1\r\nhost: x\r\n\r\n".repeat(1024);
let (first_half, second_half) = upload.split_at(upload.len() / 2);
let mut raw = gateway.connect().await;
raw.send(format!(
"POST /v1/files HTTP/1.1\r\nhost: x\r\ncontent-length: {}\r\n\r\n",
upload.len()
))
.await;
raw.send(first_half).await;
let rejected = within(raw.response_head()).await.unwrap();
assert_eq!(rejected.status, StatusCode::PAYLOAD_TOO_LARGE);
assert_eq!(raw.body(2).await, b"{}");
raw.send(second_half).await;
raw.send("GET /next HTTP/1.1\r\nhost: x\r\n\r\n").await;
let next = within(raw.response_head()).await.unwrap();
assert_eq!(raw.body(next.content_length().unwrap()).await, b"next");
assert_eq!(within(events.recv()).await.unwrap(), b"/v1/files");
assert_eq!(within(events.recv()).await.unwrap(), upload);
assert_eq!(within(events.recv()).await.unwrap(), b"/next");
}

21
litellm-rust/crates/gateway-forward/tests/upstream.rs Normal file
View file

@ -0,0 +1,21 @@
use litellm_gateway_forward::Upstream;
use rstest::rstest;
#[rstest]
#[case::https("https://127.0.0.1:4000")]
#[case::public("http://192.0.2.1:4000")]
#[case::hostname("http://localhost:4000")]
#[case::ipv6("http://[::1]:4000")]
#[case::path("http://127.0.0.1:4000/api")]
#[case::query("http://127.0.0.1:4000/?x=y")]
#[case::credentials("http://user@127.0.0.1:4000")]
fn rejects_anything_but_a_loopback_http_origin(#[case] upstream: &str) {
assert!(upstream.parse::<Upstream>().is_err());
}
#[rstest]
#[case::standard("http://127.0.0.1:4000")]
#[case::loopback_range("http://127.0.0.2:4000/")]
fn accepts_a_loopback_http_origin(#[case] upstream: &str) {
assert!(upstream.parse::<Upstream>().is_ok());
}

719
litellm-rust/crates/gateway-forward/tests/websocket.rs Normal file
View file

@ -0,0 +1,719 @@
mod support;
use std::{
net::SocketAddr,
sync::Arc,
time::{Duration, Instant},
};
use axum::{
Router,
http::{HeaderValue, StatusCode},
response::IntoResponse,
};
use futures_util::{SinkExt, StreamExt, future::join_all};
use litellm_gateway_forward::PEER_HEADER;
use rstest::rstest;
use support::{DRAIN, Gateway, Head, Raw, raw_upstream, serve, within};
use tokio::{
io::{AsyncReadExt, AsyncWriteExt},
net::TcpStream,
sync::{Barrier, mpsc},
};
use tokio_tungstenite::{
WebSocketStream, accept_hdr_async, client_async,
tungstenite::{
Error, Message,
client::IntoClientRequest,
handshake::{
derive_accept_key,
server::{ErrorResponse, Request as Handshake, Response as Accepted},
},
protocol::{CloseFrame, frame::coding::CloseCode},
},
};
const KEY: &str = "dGhlIHNhbXBsZSBub25jZQ==";
async fn connect(
address: SocketAddr,
connection: &'static str,
) -> Result<WebSocketStream<TcpStream>, Box<Error>> {
let mut request = format!("ws://{address}/v1/realtime?model=m")
.into_client_request()
.unwrap();
let headers = request.headers_mut();
headers.insert("authorization", HeaderValue::from_static("Bearer test"));
headers.insert(
"sec-websocket-protocol",
HeaderValue::from_static("realtime"),
);
headers.insert("connection", HeaderValue::from_static(connection));
let stream = TcpStream::connect(address).await.unwrap();
let (socket, response) = client_async(request, stream).await.map_err(Box::new)?;
assert_eq!(response.headers()["sec-websocket-protocol"], "realtime");
Ok(socket)
}
/// Greets, echoes every message, and closes with 4000 when told to "bye".
#[expect(
clippy::result_large_err,
reason = "tungstenite's handshake callback returns ErrorResponse"
)]
async fn echo() -> SocketAddr {
raw_upstream(|python| async move {
let callback = |request: &Handshake, mut response: Accepted| {
assert_eq!(request.uri(), "/v1/realtime?model=m");
assert_eq!(request.headers()["authorization"], "Bearer test");
assert!(request.headers().contains_key(PEER_HEADER));
response.headers_mut().insert(
"sec-websocket-protocol",
HeaderValue::from_static("realtime"),
);
Ok::<_, ErrorResponse>(response)
};
let mut socket = accept_hdr_async(python.into_stream(), callback)
.await
.unwrap();
socket.send(Message::text("greeting")).await.unwrap();
while let Some(Ok(message)) = socket.next().await {
if message == Message::text("bye") {
socket
.close(Some(CloseFrame {
code: CloseCode::Library(4000),
reason: "done".into(),
}))
.await
.unwrap();
continue;
}
if message.is_close() {
break;
}
socket.send(message).await.unwrap();
}
})
.await
}
fn handshake(target: &str, headers: &str) -> String {
format!(
"GET {target} HTTP/1.1\r\nhost: public.example\r\nconnection: Upgrade\r\nupgrade: websocket\r\nsec-websocket-version: 13\r\nsec-websocket-key: {KEY}\r\n{headers}\r\n"
)
}
/// The 101 uvicorn writes for `handshake`, with `headers` added.
fn switching(handshake: &Head, headers: &str) -> String {
let accept = derive_accept_key(handshake.header("sec-websocket-key").unwrap());
format!(
"HTTP/1.1 101 Switching Protocols\r\nupgrade: websocket\r\nconnection: Upgrade\r\nsec-websocket-accept: {accept}\r\n{headers}\r\n"
)
}
fn values(head: &Head, name: &str) -> Vec<String> {
head.headers
.iter()
.filter(|(key, _)| key.eq_ignore_ascii_case(name))
.map(|(_, value)| String::from_utf8(value.clone()).unwrap())
.collect()
}
/// Accepts with `headers` in the 101, hands the handshake head to the test, then echoes bytes.
async fn byte_echo(headers: &'static str) -> (SocketAddr, mpsc::UnboundedReceiver<Head>) {
let (sender, handshakes) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python: Raw| {
let sender = sender.clone();
async move {
let handshake = python.request_head().await.unwrap();
python.send(switching(&handshake, headers)).await;
sender.send(handshake).unwrap();
echo_bytes(python).await;
}
})
.await;
(upstream, handshakes)
}
async fn echo_bytes(python: Raw) {
let mut stream = python.into_stream();
let (mut read, mut write) = stream.split();
tokio::io::copy(&mut read, &mut write).await.ok();
}
async fn assert_echoes(socket: &mut TcpStream, message: &[u8]) {
socket.write_all(message).await.unwrap();
let mut echoed = vec![0; message.len()];
within(socket.read_exact(&mut echoed)).await.unwrap();
assert_eq!(echoed, message);
}
async fn open(gateway: &Gateway, handshake: String) -> (TcpStream, Head) {
let mut raw = gateway.connect().await;
raw.send(handshake).await;
let switched = within(raw.response_head()).await.unwrap();
assert_eq!(switched.status, StatusCode::SWITCHING_PROTOCOLS);
(raw.into_stream(), switched)
}
#[rstest]
#[tokio::test]
async fn relays_messages_both_ways(
#[values(
"Upgrade",
"keep-alive, Upgrade",
"upgrade",
"Upgrade, Sec-WebSocket-Key, Sec-WebSocket-Version"
)]
connection: &'static str,
#[values(
Message::text("hello"),
Message::binary(vec![0, 1, 2]),
Message::binary(vec![7; 4 * 1024 * 1024])
)]
message: Message,
) {
let gateway = Gateway::start(echo().await).await;
let mut socket = within(connect(gateway.address, connection)).await.unwrap();
assert_eq!(
socket.next().await.unwrap().unwrap(),
Message::text("greeting")
);
socket.send(message.clone()).await.unwrap();
assert_eq!(within(socket.next()).await.unwrap().unwrap(), message);
socket.close(None).await.unwrap();
while socket.next().await.is_some() {}
drop(socket);
within(gateway.shutdown()).await.unwrap();
}
#[rstest]
#[tokio::test]
async fn relays_a_close_python_initiates() {
let gateway = Gateway::start(echo().await).await;
let mut socket = within(connect(gateway.address, "Upgrade")).await.unwrap();
socket.next().await.unwrap().unwrap();
socket.send(Message::text("bye")).await.unwrap();
let Message::Close(Some(frame)) = within(socket.next()).await.unwrap().unwrap() else {
panic!("expected python's close frame");
};
assert_eq!(frame.code, CloseCode::Library(4000));
assert_eq!(frame.reason, "done");
}
#[rstest]
#[tokio::test]
async fn passes_an_upstream_rejection_through() {
let upstream = serve(
Router::new()
.fallback(|| async { (StatusCode::FORBIDDEN, "origin not allowed").into_response() }),
)
.await;
let gateway = Gateway::start(upstream).await;
let error = within(connect(gateway.address, "Upgrade"))
.await
.unwrap_err();
let Error::Http(response) = *error else {
panic!("expected the upstream rejection, got {error}");
};
assert_eq!(response.status(), StatusCode::FORBIDDEN);
assert_eq!(response.body().as_deref(), Some(&b"origin not allowed"[..]));
}
/// The idle timeout only covers a connection waiting for its next HTTP request, and a realtime
/// session may sit silent between turns.
#[rstest]
#[tokio::test]
async fn keeps_a_quiet_socket_open_past_the_keepalive() {
let gateway = Gateway::with_keepalive(echo().await, Duration::from_millis(400)).await;
let mut socket = within(connect(gateway.address, "Upgrade")).await.unwrap();
socket.next().await.unwrap().unwrap();
tokio::time::sleep(Duration::from_millis(1200)).await;
socket.send(Message::text("still here")).await.unwrap();
assert_eq!(
within(socket.next()).await.unwrap().unwrap(),
Message::text("still here")
);
}
/// Browsers carry the API key in a subprotocol, Python accepts with the first one it was offered,
/// and uvicorn negotiates permessage-deflate, so every handshake header must cross unchanged.
#[rstest]
#[tokio::test]
async fn handshake_headers_cross_unchanged_both_ways() {
let (upstream, mut handshakes) = byte_echo(
"sec-websocket-protocol: realtime\r\nsec-websocket-extensions: permessage-deflate; server_max_window_bits=12; client_max_window_bits=12\r\nset-cookie: a=1\r\nset-cookie: b=2\r\nx-litellm-call-id: abc\r\n",
)
.await;
let gateway = Gateway::start(upstream).await;
let target = "/v1/realtime?model=gpt-realtime&api-key=sk%2Fa%2Bb%3D&dup=1&dup=2";
let (_socket, switched) = open(
&gateway,
handshake(
target,
"sec-websocket-protocol: realtime, openai-insecure-api-key.sk-websocket-test, openai-beta.realtime-v1\r\nsec-websocket-protocol: second-line\r\nsec-websocket-extensions: permessage-deflate; client_max_window_bits\r\ncookie: token=abc\r\n",
),
)
.await;
let handshake = within(handshakes.recv()).await.unwrap();
assert_eq!(handshake.path, target);
assert_eq!(
values(&handshake, "sec-websocket-protocol"),
[
"realtime, openai-insecure-api-key.sk-websocket-test, openai-beta.realtime-v1",
"second-line"
]
);
assert_eq!(
values(&handshake, "sec-websocket-extensions"),
["permessage-deflate; client_max_window_bits"]
);
assert_eq!(values(&handshake, "cookie"), ["token=abc"]);
assert_eq!(values(&switched, "sec-websocket-protocol"), ["realtime"]);
assert_eq!(
values(&switched, "sec-websocket-extensions"),
["permessage-deflate; server_max_window_bits=12; client_max_window_bits=12"]
);
assert_eq!(values(&switched, "set-cookie"), ["a=1", "b=2"]);
assert_eq!(values(&switched, "x-litellm-call-id"), ["abc"]);
}
#[rstest]
#[tokio::test]
async fn invents_no_subprotocol_or_extension() {
let (upstream, mut handshakes) = byte_echo("").await;
let gateway = Gateway::start(upstream).await;
let (_socket, switched) = open(&gateway, handshake("/v1/realtime", "")).await;
let handshake = within(handshakes.recv()).await.unwrap();
for name in ["sec-websocket-protocol", "sec-websocket-extensions"] {
assert!(handshake.header(name).is_none());
assert!(switched.header(name).is_none());
}
}
#[rstest]
#[case::capitalized_upgrade("Upgrade: WebSocket\r\nConnection: keep-alive, Upgrade\r\n")]
#[case::uppercase("UPGRADE: WEBSOCKET\r\nCONNECTION: UPGRADE\r\n")]
#[case::split_connection("Upgrade: websocket\r\nConnection: keep-alive\r\nConnection: Upgrade\r\n")]
#[tokio::test]
async fn accepts_any_spelling_of_the_upgrade_headers(#[case] upgrade: &str) {
let (upstream, _handshakes) = byte_echo("").await;
let gateway = Gateway::start(upstream).await;
let (mut socket, _) = open(
&gateway,
format!(
"GET /v1/realtime HTTP/1.1\r\nhost: x\r\n{upgrade}sec-websocket-version: 13\r\nsec-websocket-key: {KEY}\r\n\r\n"
),
)
.await;
socket.write_all(b"ping").await.unwrap();
let mut echoed = [0; 4];
within(socket.read_exact(&mut echoed)).await.unwrap();
assert_eq!(&echoed, b"ping");
}
/// Compressed frames set RSV1 and every client frame is masked, so the socket is relayed as bytes,
/// never re-framed.
#[rstest]
#[tokio::test]
async fn relays_socket_bytes_exactly() {
let (upstream, _handshakes) = byte_echo("").await;
let gateway = Gateway::start(upstream).await;
let (socket, _) = open(&gateway, handshake("/v1/realtime", "")).await;
let sent: Vec<u8> = (0..3_000_017u32)
.map(|index| index.wrapping_mul(2_654_435_761).to_be_bytes()[1])
.collect();
let (mut read, mut write) = socket.into_split();
let writing = sent.clone();
let writer = tokio::spawn(async move {
for chunk in writing.chunks(7919) {
write.write_all(chunk).await.unwrap();
}
write
});
let mut echoed = vec![0; sent.len()];
within(read.read_exact(&mut echoed)).await.unwrap();
assert!(echoed == sent);
drop(writer.await.unwrap());
}
/// uvicorn writes the 101, an error event and a close frame back to back and then closes, so they
/// share a segment with the FIN, and a client may send its first frame with the handshake.
#[rstest]
#[tokio::test]
async fn keeps_bytes_that_arrive_with_the_handshake() {
let (early, mut received) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python: Raw| {
let early = early.clone();
async move {
let handshake = python.request_head().await.unwrap();
let mut segment = switching(&handshake, "").into_bytes();
segment.extend(b"\x81\x05error\x88\x08\x03\xf0denied");
python.send(segment).await;
early.send(within(python.body(6)).await).unwrap();
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(handshake("/v1/realtime", "") + "early!").await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::SWITCHING_PROTOCOLS
);
assert_eq!(within(received.recv()).await.unwrap(), b"early!");
assert_eq!(
within(raw.until_closed()).await,
b"\x81\x05error\x88\x08\x03\xf0denied"
);
}
/// Python frees a realtime session's budget and parallel slot when its socket closes, so a client
/// that disappears without a close frame must still close Python's socket.
#[rstest]
#[case::fin(false)]
#[case::reset(true)]
#[tokio::test]
async fn a_vanished_client_closes_the_python_socket(#[case] reset: bool) {
let (event, mut events) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python: Raw| {
let event = event.clone();
async move {
let handshake = python.request_head().await.unwrap();
python.send(switching(&handshake, "")).await;
event.send("open").unwrap();
python.closed().await;
event.send("closed").unwrap();
}
})
.await;
let gateway = Gateway::start(upstream).await;
let (socket, _) = open(&gateway, handshake("/v1/realtime", "")).await;
assert_eq!(within(events.recv()).await, Some("open"));
if reset {
#[expect(deprecated, reason = "a zero linger is how a test sends a TCP reset")]
socket.set_linger(Some(Duration::ZERO)).unwrap();
}
drop(socket);
assert_eq!(within(events.recv()).await, Some("closed"));
}
#[rstest]
#[case::fin(false)]
#[case::reset(true)]
#[tokio::test]
async fn a_vanished_python_ends_the_client_socket(#[case] reset: bool) {
let upstream = raw_upstream(move |mut python: Raw| async move {
let handshake = python.request_head().await.unwrap();
python.send(switching(&handshake, "")).await;
let socket = python.into_stream();
if reset {
#[expect(deprecated, reason = "a zero linger is how a test sends a TCP reset")]
socket.set_linger(Some(Duration::ZERO)).unwrap();
}
drop(socket);
})
.await;
let gateway = Gateway::start(upstream).await;
let (mut socket, _) = open(&gateway, handshake("/v1/realtime", "")).await;
let mut rest = Vec::new();
assert!(matches!(
within(socket.read_to_end(&mut rest)).await,
Ok(0) | Err(_)
));
}
#[rstest]
#[tokio::test]
async fn shutdown_closes_open_sockets_after_drain() {
let gateway = Gateway::start(echo().await).await;
let mut socket = within(connect(gateway.address, "Upgrade")).await.unwrap();
socket.next().await.unwrap().unwrap();
let started = Instant::now();
within(gateway.shutdown()).await.unwrap();
assert!(started.elapsed() >= DRAIN);
assert!(!matches!(socket.next().await, Some(Ok(Message::Text(_)))));
}
#[rstest]
#[tokio::test]
async fn shutdown_relays_the_close_python_sends_while_draining() {
let gateway = Gateway::start(echo().await).await;
let mut socket = within(connect(gateway.address, "Upgrade")).await.unwrap();
socket.next().await.unwrap().unwrap();
let server = gateway.shutdown();
tokio::time::sleep(Duration::from_millis(100)).await;
socket.send(Message::text("bye")).await.unwrap();
let Message::Close(Some(frame)) = within(socket.next()).await.unwrap().unwrap() else {
panic!("expected python's close frame");
};
assert_eq!(frame.code, CloseCode::Library(4000));
while socket.next().await.is_some() {}
drop(socket);
let started = Instant::now();
within(server).await.unwrap();
assert!(started.elapsed() < DRAIN / 2);
}
#[rstest]
#[tokio::test]
async fn refuses_new_sockets_while_draining() {
let gateway = Gateway::start(echo().await).await;
let mut open = within(connect(gateway.address, "Upgrade")).await.unwrap();
open.next().await.unwrap().unwrap();
let address = gateway.address;
let server = gateway.shutdown();
tokio::time::sleep(Duration::from_millis(100)).await;
assert!(
TcpStream::connect(address).await.is_err() || connect(address, "Upgrade").await.is_err()
);
open.send(Message::text("still open")).await.unwrap();
assert_eq!(
within(open.next()).await.unwrap().unwrap(),
Message::text("still open")
);
drop(open);
within(server).await.unwrap();
}
/// uvicorn never half-closes: once Python closes the socket nothing more can cross it, so the
/// relay must end instead of waiting for the client to close its side too.
#[rstest]
#[tokio::test]
async fn relay_ends_when_python_closes_while_the_client_holds_its_socket() {
let upstream = raw_upstream(move |mut python: Raw| async move {
let handshake = python.request_head().await.unwrap();
python.send(switching(&handshake, "")).await;
})
.await;
let gateway = Gateway::start(upstream).await;
let (mut socket, _) = open(&gateway, handshake("/v1/realtime", "")).await;
assert_eq!(within(socket.read(&mut [0; 1])).await.unwrap(), 0);
let started = Instant::now();
within(gateway.shutdown()).await.unwrap();
assert!(started.elapsed() < DRAIN / 2);
drop(socket);
}
/// uvicorn answers a handshake Python closes before accepting with a 403, and one Python denies
/// through `websocket.http.response` with any status, headers and body, then drops the socket. The
/// client gets that response whole and keeps a connection that still reaches Python.
#[rstest]
#[case::closed_before_accept("403 Forbidden", None, "")]
#[case::denial_response(
"401 Unauthorized",
Some("Bearer realm=\"litellm\""),
"{\"error\":\"invalid api key\"}"
)]
#[tokio::test]
async fn a_denied_handshake_reaches_the_client_whole(
#[case] status: &'static str,
#[case] authenticate: Option<&'static str>,
#[case] body: &'static str,
) {
let upstream = raw_upstream(move |mut python: Raw| async move {
python.request_head().await.unwrap();
let authenticate = authenticate
.map(|value| format!("www-authenticate: {value}\r\n"))
.unwrap_or_default();
python
.send(format!(
"HTTP/1.1 {status}\r\ndate: Tue, 03 Nov 2026 08:00:00 GMT\r\nconnection: close\r\ncontent-length: {}\r\ncontent-type: text/plain; charset=utf-8\r\n{authenticate}\r\n{body}",
body.len()
))
.await;
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
for _ in 0..2 {
raw.send(handshake("/v1/realtime", "")).await;
let denied = within(raw.response_head()).await.unwrap();
assert_eq!(denied.status.as_str(), &status[..3]);
assert_eq!(
values(&denied, "www-authenticate"),
Vec::from_iter(authenticate.map(String::from))
);
assert!(denied.header("sec-websocket-accept").is_none());
let length = denied.content_length().unwrap();
assert_eq!(within(raw.body(length)).await, body.as_bytes());
}
}
/// Only Python's EOF ends a relay, so a client that half-closes after its close frame still gets
/// everything Python sends before closing its own side.
#[rstest]
#[tokio::test]
async fn a_client_half_close_still_receives_what_python_sends_after_it() {
let upstream = raw_upstream(|mut python: Raw| async move {
let handshake = python.request_head().await.unwrap();
python.send(switching(&handshake, "")).await;
let received = python.until_closed().await;
python.send(received).await;
})
.await;
let gateway = Gateway::start(upstream).await;
let (mut socket, _) = open(&gateway, handshake("/v1/realtime", "")).await;
let close = b"\x88\x82\x01\x02\x03\x04\x02\xea";
socket.write_all(close).await.unwrap();
socket.shutdown().await.unwrap();
let mut replied = Vec::new();
within(socket.read_to_end(&mut replied)).await.unwrap();
assert_eq!(replied, close);
}
/// Python authenticates every handshake before accepting it, so sessions opened together must all
/// reach Python before any of them is accepted, and each must stay on its own socket.
#[rstest]
#[tokio::test]
async fn opens_many_sockets_at_once_without_crossing_them() {
const SOCKETS: usize = 64;
let everyone = Arc::new(Barrier::new(SOCKETS));
let upstream = raw_upstream(move |mut python: Raw| {
let everyone = everyone.clone();
async move {
let handshake = python.request_head().await.unwrap();
everyone.wait().await;
python.send(switching(&handshake, "")).await;
echo_bytes(python).await;
}
})
.await;
let gateway = Gateway::start(upstream).await;
let gateway = &gateway;
within(join_all((0..SOCKETS).map(|index| async move {
let (mut socket, _) = open(gateway, handshake("/v1/realtime", "")).await;
assert_echoes(&mut socket, format!("socket {index}").as_bytes()).await;
})))
.await;
}
/// Python resolves the key, budget and model before it accepts, and nothing bounds how long that
/// takes, so the idle timeout must not cut a handshake waiting on its 101.
#[rstest]
#[tokio::test]
async fn waits_for_a_101_slower_than_the_keepalive() {
let upstream = raw_upstream(|mut python: Raw| async move {
let handshake = python.request_head().await.unwrap();
tokio::time::sleep(Duration::from_millis(1200)).await;
python.send(switching(&handshake, "")).await;
echo_bytes(python).await;
})
.await;
let gateway = Gateway::with_keepalive(upstream, Duration::from_millis(400)).await;
let (mut socket, _) = open(&gateway, handshake("/v1/realtime", "")).await;
assert_echoes(&mut socket, b"late").await;
}
/// A 101 the client did not ask for, or to a protocol other than the one it asked for, would hand
/// the client a socket it cannot speak, so it is a 502 and Python's socket is closed.
#[rstest]
#[case::plain_request("GET /v1/models HTTP/1.1\r\nhost: x\r\n\r\n".to_owned(), "websocket")]
#[case::other_protocol(handshake("/v1/realtime", ""), "h2c")]
#[tokio::test]
async fn an_unrequested_switch_is_a_502_that_closes_python(
#[case] request: String,
#[case] protocol: &'static str,
) {
let (closed, mut closes) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python: Raw| {
let closed = closed.clone();
async move {
python.request_head().await.unwrap();
python
.send(format!(
"HTTP/1.1 101 Switching Protocols\r\nconnection: upgrade\r\nupgrade: {protocol}\r\n\r\n"
))
.await;
python.closed().await;
closed.send(()).unwrap();
}
})
.await;
let gateway = Gateway::start(upstream).await;
let mut raw = gateway.connect().await;
raw.send(request).await;
assert_eq!(
within(raw.response_head()).await.unwrap().status,
StatusCode::BAD_GATEWAY
);
within(closes.recv()).await.unwrap();
}
/// A realtime session streams audio for as long as the client reads it, so a client that stops
/// reading must stall Python's writes instead of piling them up in the gateway.
#[rstest]
#[tokio::test]
async fn a_client_that_stops_reading_stalls_python() {
let (sent, mut totals) = mpsc::unbounded_channel();
let upstream = raw_upstream(move |mut python: Raw| {
let sent = sent.clone();
async move {
let handshake = python.request_head().await.unwrap();
python.send(switching(&handshake, "")).await;
python.body(2).await;
let mut stream = python.into_stream();
let chunk = vec![0x82; 64 * 1024];
let mut total = 0;
while let Ok(Ok(())) =
tokio::time::timeout(Duration::from_millis(300), stream.write_all(&chunk)).await
{
total += chunk.len();
}
sent.send(total).unwrap();
}
})
.await;
let gateway = Gateway::start(upstream).await;
let (mut socket, _) = open(&gateway, handshake("/v1/realtime", "")).await;
socket.write_all(b"go").await.unwrap();
let total = within(totals.recv()).await.unwrap();
assert!(
total < 64 << 20,
"python wrote {total} bytes into a stalled socket"
);
}
/// Python closes a session that is still streaming audio by sending an error event and a close
/// frame and dropping its socket with the client's next frames unread, which resets it. Those last
/// bytes reached the client when it talked to uvicorn directly, so they must reach it through the
/// relay too, even though writing the client's frames to Python now fails.
#[rstest]
#[tokio::test]
async fn python_closing_mid_stream_still_delivers_its_last_frames() {
const LAST: &[u8] = b"\x81\x05error\x88\x02\x03\xf0";
let upstream = raw_upstream(|mut python: Raw| async move {
let handshake = python.request_head().await.unwrap();
python.send(switching(&handshake, "")).await;
python.body(1).await;
tokio::time::sleep(Duration::from_millis(20)).await;
python.send(LAST).await;
})
.await;
let gateway = Gateway::start(upstream).await;
for _ in 0..20 {
let (mut socket, _) = open(&gateway, handshake("/v1/realtime", "")).await;
let (mut read, mut write) = socket.split();
let streaming = async {
while write.write_all(b"\x82\x80\0\0\0\0").await.is_ok() {
tokio::time::sleep(Duration::from_micros(200)).await;
}
std::future::pending().await
};
let mut received = Vec::new();
let receiving = async {
let mut chunk = [0; 4096];
while let Ok(read @ 1..) = read.read(&mut chunk).await {
received.extend_from_slice(&chunk[..read]);
}
};
within(async {
tokio::select! {
() = streaming => {}
() = receiving => {}
}
})
.await;
assert_eq!(received, LAST);
}
}

1
litellm-rust/crates/gateway/Cargo.toml
View file

@ -12,6 +12,7 @@ envy = "0.4.2"
http-body-util = "0.1"
litellm-inference.workspace = true
litellm-gateway-inference.workspace = true
litellm-gateway-forward.workspace = true
litellm-gateway-mcp.workspace = true
tokio-util = "0.7"
thiserror.workspace = true

26
litellm-rust/crates/gateway/src/main.rs
View file

@ -10,7 +10,7 @@ use serde_json::json;
mod settings;
use settings::{Settings, UiSettings};
use settings::{LogSettings, Settings, UiSettings};
struct StderrSink {
level: Level,
@ -41,6 +41,15 @@ impl Sink for StderrSink {
#[tokio::main]
async fn main() -> Result<(), Box<dyn Error>> {
if let Some(forward) = litellm_gateway_forward::Settings::from_env()? {
let log: LogSettings = settings::from_iter(std::env::vars_os())?;
Logger::new(StderrSink {
level: log.log_level(),
})
.install_global()?;
litellm_gateway_forward::run(forward, shutdown_signal()).await?;
return Ok(());
}
let settings: Settings = settings::from_iter(std::env::vars_os())?;
let level = settings.log_level();
Logger::new(StderrSink { level }).install_global()?;
@ -126,7 +135,20 @@ async fn shutdown_signal() {
}
}
}
#[cfg(not(unix))]
// Windows support exists for local CLI runs only, the proxy is never deployed on Windows. The supervisor
// stops the gateway with CTRL_BREAK_EVENT, which has to drain the same way SIGTERM does.
#[cfg(windows)]
{
match tokio::signal::windows::ctrl_break() {
Ok(mut ctrl_break) => {
tokio::select! { _ = tokio::signal::ctrl_c() => (), _ = ctrl_break.recv() => () }
}
Err(_) => {
let _ = tokio::signal::ctrl_c().await;
}
}
}
#[cfg(not(any(unix, windows)))]
{
let _ = tokio::signal::ctrl_c().await;
}

22
litellm-rust/crates/gateway/src/settings.rs
View file

@ -4,6 +4,23 @@ use litellm_secret_value::SecretValue;
use litellm_tracing::Level;
use serde::{Deserialize, de::DeserializeOwned};
#[derive(Deserialize)]
pub(super) struct LogSettings {
rust_log: Option<String>,
}
impl LogSettings {
pub fn log_level(&self) -> Level {
log_level(self.rust_log.as_deref())
}
}
fn log_level(rust_log: Option<&str>) -> Level {
rust_log
.and_then(|value| value.parse().ok())
.unwrap_or(Level::INFO)
}
#[derive(Deserialize)]
#[serde(default)]
pub(super) struct Settings {
@ -26,10 +43,7 @@ impl Default for Settings {
impl Settings {
pub fn log_level(&self) -> Level {
self.rust_log
.as_deref()
.and_then(|value| value.parse().ok())
.unwrap_or(Level::INFO)
log_level(self.rust_log.as_deref())
}
}

18
litellm-rust/crates/router-core/src/call.rs
View file

@ -4,13 +4,7 @@
//! `should_retry_this_error` and `_time_to_sleep_before_retry` in `litellm/router.py`, and
//! `run_async_fallback` in `router_utils/fallback_event_handlers.py`.
use std::{
borrow::Cow,
future::Future,
pin::Pin,
sync::Arc,
time::{Duration, Instant},
};
use std::{borrow::Cow, future::Future, pin::Pin, sync::Arc, time::Duration};
use serde_json::{Map, Value};
@ -1247,7 +1241,7 @@ impl Core {
.unrouted_attempt(snapshot, op, request, target, (retry, max_retries), at)
.await;
}
let pick_started = Instant::now();
let pick_started = self.health.now_time();
let (deployment, candidates) = match self
.picked(snapshot, op, request, target, inputs, retry, at)
.await
@ -1264,7 +1258,11 @@ impl Core {
self.host.observe(&RouterEvent::Selected {
model_group: candidates.model_group.clone(),
deployment_id: deployment.id.clone(),
pick: pick_started.elapsed(),
pick: self
.health
.now_time()
.duration_since(pick_started)
.unwrap_or_default(),
});
if !self.host.supports(op, deployment.provider()) {
return Err(Error::Config(ConfigError::Unsupported(Unsupported::Op {
@ -1290,7 +1288,7 @@ impl Core {
},
None,
snapshot.settings.dynamic.default_ref(),
jiff::Timestamp::now(),
self.health.timestamp(),
),
Ok(None)
);

4
litellm-rust/crates/router-core/src/health.rs
View file

@ -247,6 +247,10 @@ impl Health {
self.clock.now()
}
pub(crate) fn timestamp(&self) -> jiff::Timestamp {
jiff::Timestamp::try_from(self.clock.now()).unwrap_or(jiff::Timestamp::UNIX_EPOCH)
}
fn now(&self) -> f64 {
unix_seconds(self.clock.now())
}

4
litellm-rust/crates/router-core/src/lookup.rs
View file

@ -433,6 +433,10 @@ impl<'a> Lookup<'a> {
.collect()
}
pub fn has_team_wildcards(&self, team_id: &str) -> bool {
self.host.team_patterns.iter().any(|(t, _)| t == team_id)
}
/// The deployments `team_id`'s own wildcard pattern routes `name` to
/// (`_core_team_pattern_routers`, keyed by `team_public_model_name`).
pub fn team_wildcard(&self, name: &str, team_id: &str) -> Vec<Arc<Deployment>> {

80
litellm-rust/crates/router-core/src/resolve.rs
View file

@ -223,14 +223,20 @@ pub(crate) fn wildcard_name<'a>(
registry: &'a Registry,
name: &'a str,
specific_deployment: bool,
team_id: Option<&str>,
) -> Option<&'a str> {
let model = registry.alias_of(name).unwrap_or(name);
(registry.has_wildcards()
let lookup = crate::lookup::Lookup::new(registry);
let team_patterns = team_id.is_some_and(|team| lookup.has_team_wildcards(team));
let team_misses = || team_id.is_none_or(|team| lookup.team_wildcard(model, team).is_empty());
let global_misses = || registry.has_wildcards() && registry.wildcard_for(model).is_none();
((team_patterns || registry.has_wildcards())
&& !specific_deployment
&& !registry.has_name(model)
&& (registry.has_name(name) || registry.deployment(name).is_none())
&& registry.routing_group_named(model).is_none()
&& registry.wildcard_for(model).is_none())
&& team_misses()
&& (team_patterns || global_misses()))
.then_some(model)
}
@ -339,15 +345,21 @@ pub fn resolve_request(
let kept = reserved(model, deployments, caller, now)?;
return resolved(ResolveKind::Group, model, kept);
}
// `_core_wildcard_route_deployments`: the team's own pattern, else the proxy-wide one.
let team_owned = team_id
.map(|team| crate::lookup::Lookup::new(registry).team_wildcard(model, team))
.filter(|deployments| !deployments.is_empty());
if let Some(deployments) = team_owned {
// `_core_wildcard_route_deployments`: the team's own pattern, else the proxy-wide one,
// each tried as spelled and then under the name's provider (`get_pattern`).
let team_owned = team_id.and_then(|team| {
let lookup = crate::lookup::Lookup::new(registry);
[Some(model), caller.wildcard_request]
.into_iter()
.flatten()
.map(|request| (request, lookup.team_wildcard(request, team)))
.find(|(_, deployments)| !deployments.is_empty())
});
if let Some((request, deployments)) = team_owned {
let routed = deployments.iter().flat_map(|deployment| {
let public = deployment.model_info.team_public_model_name.as_deref();
let pattern = public.unwrap_or(model);
routed_wildcard(pattern, model, std::slice::from_ref(deployment))
let pattern = public.unwrap_or(request);
routed_wildcard(pattern, request, std::slice::from_ref(deployment))
});
let kept = reserved(model, routed.collect(), caller, now)?;
return resolved(ResolveKind::Wildcard, model, kept);
@ -428,6 +440,7 @@ pub fn resolve_request(
mod tests {
use std::collections::BTreeMap;
use rstest::rstest;
use serde_json::{Value, json};
use super::*;
@ -544,8 +557,11 @@ mod tests {
#[test]
fn a_name_no_pattern_matches_is_tried_under_its_provider() {
let registry = registry(wildcard_group());
assert_eq!(wildcard_name(&registry, "gpt-4o", false), Some("gpt-4o"));
assert_eq!(wildcard_name(&registry, "openai/gpt-4o", false), None);
assert_eq!(
wildcard_name(&registry, "gpt-4o", false, None),
Some("gpt-4o")
);
assert_eq!(wildcard_name(&registry, "openai/gpt-4o", false, None), None);
let caller = Caller {
wildcard_request: Some("openai/gpt-4o"),
..Caller::default()
@ -564,6 +580,48 @@ mod tests {
assert_eq!(resolution.deployments[0].params.model, "openai/gpt-4o");
}
#[rstest]
fn a_bare_name_is_tried_under_its_provider_against_the_teams_own_wildcard() {
let registry = registry(json!([
{"model_name": "model_name_tw_1", "litellm_params": {"model": "openai/*"},
"model_info": {"id": "tw", "team_id": "TW", "team_public_model_name": "openai/*"}},
{"model_name": "g", "litellm_params": {"model": "openai/g"}, "model_info": {"id": "g"}},
]));
// No proxy-wide wildcard: only the team's patterns call for the provider spelling.
assert_eq!(
wildcard_name(&registry, "gpt-4o-mini", false, Some("TW")),
Some("gpt-4o-mini")
);
assert_eq!(wildcard_name(&registry, "gpt-4o-mini", false, None), None);
assert_eq!(
wildcard_name(&registry, "openai/gpt-4o-mini", false, Some("TW")),
None
);
let resolve = |team_id| {
let caller = Caller {
team_id,
wildcard_request: Some("openai/gpt-4o-mini"),
..Caller::default()
};
resolve_request(
&registry,
"gpt-4o-mini",
false,
caller,
None,
None,
Timestamp::now(),
)
.unwrap()
};
let resolution = resolve(Some("TW")).unwrap();
assert_eq!(resolution.kind, ResolveKind::Wildcard);
assert_eq!(resolution.group, "gpt-4o-mini");
assert_eq!(ids(Some(resolution.clone())), ["tw"]);
assert_eq!(resolution.deployments[0].params.model, "openai/gpt-4o-mini");
assert!(resolve(Some("OTHER")).is_none());
}
#[test]
fn a_deployment_named_by_id_refuses_the_endpoint_like_any_other() {
let registry = registry(json!([

10
litellm-rust/crates/router-core/src/select.rs
View file

@ -281,8 +281,12 @@ impl Core {
// No deployment for the name: route to the first default fallback.
let default_target = crate::resolve::default_target(&snapshot.settings.dynamic);
// `get_pattern`: a name no pattern matches is tried again under its inferred provider.
let wildcard_name =
crate::resolve::wildcard_name(registry, name, request.specific_deployment);
let wildcard_name = crate::resolve::wildcard_name(
registry,
name,
request.specific_deployment,
request.team_id.as_deref(),
);
let wildcard_request = match wildcard_name {
Some(model) => {
let scope = StrategyScope::Default;
@ -308,7 +312,7 @@ impl Core {
caller,
default_target,
snapshot.settings.dynamic.default_ref(),
jiff::Timestamp::now(),
self.health.timestamp(),
)?
.ok_or_else(|| Error::UnknownModel {
// The name `_common_checks_available_deployment` looked for, past the alias.

54
litellm-rust/crates/router-core/tests/call_loop.rs
View file

@ -1808,3 +1808,57 @@ async fn a_listed_pass_through_pick_names_the_group_an_alias_resolves_to(config:
Error::NoPassThroughDeployments { model } if model == "primary"
));
}
struct StoppedClock(u64);
impl litellm_router_core::health::Clock for StoppedClock {
fn now(&self) -> std::time::SystemTime {
std::time::UNIX_EPOCH + Duration::from_secs(self.0)
}
}
fn utc_hour(hour: u64) -> u64 {
1_767_225_600 + hour * 3_600
}
#[rstest]
#[case::inside_the_window(utc_hour(10), vec!["open"])]
#[case::outside_the_window(utc_hour(20), vec!["open", "reserved"])]
#[tokio::test]
async fn access_windows_follow_the_routers_clock(#[case] now: u64, #[case] expected: Vec<&str>) {
let config: RouterConfig = serde_json::from_value(json!({
"model_list": [
{"model_name": "chat", "litellm_params": {"model": "openai/a"}, "model_info": {"id": "open"}},
{"model_name": "chat", "litellm_params": {"model": "openai/b"}, "model_info": {
"id": "reserved",
"access_windows": [{"start": "09:00", "end": "17:00", "timezone": "UTC", "team_ids": ["batch"]}],
}},
]
}))
.unwrap();
let router = Router::builder(
config,
RouterDynamicConfig::default(),
Arc::new(ScriptedHost::default()),
)
.randomness(Arc::new(SeededRandomness::new(7)))
.clock(Arc::new(StoppedClock(now)))
.build()
.unwrap();
let mut picked = std::collections::BTreeSet::new();
for _ in 0..40 {
let deployment = router
.select(&Op::from("acompletion"), &request_for("chat"))
.await
.unwrap();
picked.insert(deployment.id.clone());
}
assert_eq!(picked.into_iter().collect::<Vec<_>>(), expected);
}
fn request_for(model: &str) -> RouterRequest {
RouterRequest {
model: model.to_owned(),
..RouterRequest::default()
}
}

5
litellm/integrations/custom_logger.py
View file

@ -898,6 +898,11 @@ class CustomLogger: # https://docs.litellm.ai/docs/observability/custom_callbac
def redacts_messages_itself(self) -> bool:
return False
def exempt_from_message_redaction(self) -> bool:
"""Router pre-call checks that key routing off the request and never log it return True, so
`turn_off_message_logging` leaves the success event they receive unredacted."""
return False
def redact_standard_logging_payload_from_model_call_details(self, model_call_details: dict) -> dict:
"""
Redacts or excludes fields from StandardLoggingPayload before callbacks receive it.

4
litellm/interactions/background_cost_polling.py
View file

@ -71,12 +71,12 @@ if TYPE_CHECKING:
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
_TERMINAL_STATUSES: Final = frozenset(
{"completed", "failed", "cancelled", "incomplete", "budget_exceeded", "requires_action"}
{"completed", "failed", "cancelled", "incomplete", "budget_exceeded", "requires_action", "requires_continuation"}
)
_POLLABLE_STATUSES: Final = frozenset({"in_progress", "queued"})
_STATUSES_THAT_PRODUCED_OUTPUT: Final = frozenset({"completed", "requires_action"})
_STATUSES_THAT_PRODUCED_OUTPUT: Final = frozenset({"completed", "requires_action", "requires_continuation"})
SettlementOutcome: TypeAlias = Literal["billed", "released", "unsettled"]

5
litellm/interactions/main.py
View file

@ -95,6 +95,7 @@ async def acreate(
response_mime_type: str | None = None,
# Continuation
previous_interaction_id: str | None = None,
continuation_token: str | None = None,
# Extra params
extra_headers: dict[str, str] | None = None,
extra_body: Mapping[str, object] | None = None,
@ -129,6 +130,7 @@ async def acreate(
response_format: JSON schema for response format
response_mime_type: MIME type of the response
previous_interaction_id: ID of previous interaction for continuation
continuation_token: Token from a `requires_continuation` interaction to resume its long decode
extra_headers: Additional headers
extra_body: Additional body parameters
timeout: Request timeout
@ -164,6 +166,7 @@ async def acreate(
response_format=response_format,
response_mime_type=response_mime_type,
previous_interaction_id=previous_interaction_id,
continuation_token=continuation_token,
extra_headers=extra_headers,
extra_body=extra_body,
timeout=timeout,
@ -224,6 +227,7 @@ def create(
response_mime_type: str | None = None,
# Continuation
previous_interaction_id: str | None = None,
continuation_token: str | None = None,
# Extra params
extra_headers: dict[str, str] | None = None,
extra_body: Mapping[str, object] | None = None,
@ -262,6 +266,7 @@ def create(
response_format: JSON schema for response format
response_mime_type: MIME type of the response
previous_interaction_id: ID of previous interaction for continuation
continuation_token: Token from a `requires_continuation` interaction to resume its long decode
extra_headers: Additional headers
extra_body: Additional body parameters
timeout: Request timeout

1
litellm/interactions/utils.py
View file

@ -20,6 +20,7 @@ INTERACTIONS_API_OPTIONAL_PARAMS: Final = {
"response_format",
"response_mime_type",
"previous_interaction_id",
"continuation_token",
"agent_config",
}

21
litellm/litellm_core_utils/litellm_logging.py
View file

@ -4405,7 +4405,11 @@ class Logging(LiteLLMLoggingBaseClass):
if isinstance(callback, CustomLogger): # custom logger class
from litellm.integrations.shadow_eval_logger import ShadowEvalLogger
model_call_details: dict = self.model_call_details
model_call_details: dict = (
self._model_call_details_with_request_messages()
if callback.exempt_from_message_redaction()
else self.model_call_details
)
##################################
# call redaction hook for custom logger
model_call_details = callback.redact_standard_logging_payload_from_model_call_details(
@ -4969,6 +4973,21 @@ class Logging(LiteLLMLoggingBaseClass):
) -> None:
executor.submit(self.success_handler, result, start_time, end_time, cache_hit)
def _model_call_details_with_request_messages(self) -> dict[str, object]: # mutable-ok: loggers take a dict
"""The success-event payload with the request messages put back where `turn_off_message_logging`
redacted them in place, for a callback that routes on the request and never logs it."""
request_messages: Final = cast(object, self.messages) # cast-ok: the request messages are only put back as-is
standard_logging_object: Final = self.model_call_details.get("standard_logging_object")
return {
**self.model_call_details,
"messages": request_messages,
**(
{"standard_logging_object": {**standard_logging_object, "messages": request_messages}}
if isinstance(standard_logging_object, dict)
else {}
),
}
def _get_completed_success_callbacks(
self, *, asynchronous: bool
) -> tuple[str | Callable[..., object] | CustomLogger, ...]:

2
litellm/litellm_core_utils/prompt_templates/factory.py
View file

@ -5879,7 +5879,7 @@ def _bedrock_tools_pt(
description = name
defs = parameters.pop("$defs", {})
defs_copy = copy.deepcopy(defs) if isinstance(defs, dict) else {}
defs_copy = defs if isinstance(defs, dict) else {}
# Expand $ref references in parameters using the definitions
# Note: We don't pre-flatten defs as that causes exponential memory growth
# with circular references (see issue #19098). unpack_defs handles nested

4
litellm/llms/anthropic/chat/transformation.py
View file

@ -827,11 +827,11 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
return cls._raise_invalid_reasoning_effort(model, value, llm_provider)
def get_supported_openai_params(self, model: str):
sampling_params: Final = ("temperature", "top_p") if self._supports_sampling_params(model) else ()
params: Final = [
"stream",
"stop",
"temperature",
"top_p",
*sampling_params,
"max_tokens",
"max_completion_tokens",
"tools",

4
litellm/llms/gemini/interactions/transformation.py
View file

@ -126,6 +126,7 @@ class GoogleAIStudioInteractionsConfig(BaseInteractionsAPIConfig):
"response_format",
"response_mime_type",
"previous_interaction_id",
"continuation_token",
]
def validate_environment(
@ -206,6 +207,7 @@ class GoogleAIStudioInteractionsConfig(BaseInteractionsAPIConfig):
"environment",
"response_modalities",
"previous_interaction_id",
"continuation_token",
]
dropped_keys: Final = (
frozenset({"agent_config"})
@ -301,7 +303,7 @@ class GoogleAIStudioInteractionsConfig(BaseInteractionsAPIConfig):
) -> InteractionsAPIStreamingResponse:
"""Parse streaming chunk."""
verbose_logger.debug("Google AI Interactions streaming chunk: %s", parsed_chunk)
return InteractionsAPIStreamingResponse(**parsed_chunk)
return InteractionsAPIStreamingResponse.model_validate(parsed_chunk)
# GET / DELETE / CANCEL - just build URLs, responses match spec directly

157
litellm/model_prices_and_context_window_backup.json
View file

@ -4046,6 +4046,8 @@
"cache_creation_input_token_cost": 1.25e-05,
"cache_creation_input_token_cost_above_1hr": 2e-05,
"cache_read_input_token_cost": 2.5e-07,
"deprecation_date": "2027-09-01",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
@ -4068,7 +4070,7 @@
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": false,
"prompt_cache_min_tokens": 512,
"source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models"
"source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement"
},
"azure_ai/claude-opus-5": {
"deprecation_date": "2027-07-08",
@ -13458,13 +13460,16 @@
"supports_reasoning": true
},
"azure_ai/mistral-document-ai-2512": {
"deprecation_date": "2027-02-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
"litellm_provider": "azure_ai",
"ocr_cost_per_page": 0.003,
"mode": "ocr",
"supported_endpoints": [
"/v1/ocr"
],
"source": "https://ai.azure.com/catalog/models/mistral-document-ai-2512"
"source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
"successor_model": "azure_ai/mistral-ocr-4-0"
},
"azure_ai/mistral-ocr-4-0": {
"litellm_provider": "azure_ai",
@ -40893,6 +40898,22 @@
"output_cost_per_token": 4e-07,
"supports_tool_choice": true
},
"jina-reranker-v3.5": {
"input_cost_per_token": 5e-08,
"litellm_provider": "jina_ai",
"max_input_tokens": 131072,
"mode": "rerank",
"output_cost_per_token": 0.0,
"source": "https://api.jina.ai/v1/models"
},
"jina-reranker-m0": {
"input_cost_per_token": 5e-08,
"litellm_provider": "jina_ai",
"max_input_tokens": 10240,
"mode": "rerank",
"output_cost_per_token": 0.0,
"source": "https://api.jina.ai/v1/models"
},
"jina-reranker-v2-base-multilingual": {
"input_cost_per_token": 5e-08,
"litellm_provider": "jina_ai",
@ -43771,7 +43792,8 @@
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"supports_vision": true
},
"mistral/zai-glm-5-3": {
"cache_read_input_token_cost": 1.4e-07,
@ -45270,6 +45292,18 @@
"source": "https://tokenfactory.nebius.com/api/public/models_info",
"cache_read_input_token_cost": 1.5e-07
},
"nebius/moonshotai/Kimi-K3.1-Pro": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 2e-07,
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_vision": true,
"supports_prompt_caching": true,
"source": "https://tokenfactory.nebius.com/api/public/models_info"
},
"nebius/moonshotai/Kimi-K3": {
"max_input_tokens": 1048576,
"max_output_tokens": 1024000,
@ -71189,6 +71223,8 @@
},
"gpt-5.5-cyber-preview": {
"cache_read_input_token_cost": 1.25e-06,
"deprecation_date": "2027-02-01",
"deprecation_source": "https://developers.openai.com/api/docs/deprecations",
"input_cost_per_token": 1.25e-05,
"litellm_provider": "openai",
"mode": "chat",
@ -72148,6 +72184,7 @@
"output_cost_per_token": 4.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supports_audio_input": true,
"supports_audio_output": true,
"tpm": 250000,
"rpm": 10,
"search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
@ -72170,6 +72207,7 @@
"output_cost_per_token": 4.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supports_audio_input": true,
"supports_audio_output": true,
"tpm": 250000,
"rpm": 10,
"search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
@ -76469,6 +76507,33 @@
"supports_tool_choice": true,
"supports_vision": true
},
"us-gov.xai.grok-4.7": {
"supports_regex_lookaround": false,
"supported_endpoints": ["/v1/chat/completions"],
"supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
"supports_bedrock_runtime_chat_completions_response_format": true,
"cache_read_input_token_cost": 6.6e-07,
"cache_read_input_token_cost_flex": 3.3e-07,
"cache_read_input_token_cost_priority": 1.155e-06,
"input_cost_per_token": 2.64e-06,
"input_cost_per_token_batches": 1.32e-06,
"input_cost_per_token_flex": 1.32e-06,
"input_cost_per_token_priority": 4.62e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 524288,
"max_output_tokens": 524288,
"mode": "chat",
"output_cost_per_token": 7.92e-06,
"output_cost_per_token_batches": 3.96e-06,
"output_cost_per_token_flex": 3.96e-06,
"output_cost_per_token_priority": 1.386e-05,
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json",
"supports_function_calling": true,
"supports_prompt_caching": false,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": {
"cache_read_input_token_cost": 1.4e-08,
"input_cost_per_token": 6e-07,
@ -78437,7 +78502,7 @@
"cache_creation_input_token_cost": 1e-05,
"cache_creation_input_token_cost_above_1hr": 1.6e-05,
"cache_read_input_token_cost": 4e-07,
"deprecation_date": "2027-10-01",
"deprecation_date": "2027-01-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
"input_cost_per_token": 8e-06,
"litellm_provider": "azure_ai",
@ -78447,7 +78512,7 @@
"output_cost_per_token": 4e-05,
"prompt_cache_min_tokens": 512.0,
"search_context_cost_per_query": {"search_context_size_high":0.02,"search_context_size_low":0.02,"search_context_size_medium":0.02},
"source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models",
"source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
@ -82782,6 +82847,39 @@
"supports_vision": true,
"supports_xhigh_reasoning_effort": true
},
"gpt-6-cyber": {
"cache_creation_input_token_cost": 2.5e-05,
"cache_creation_input_token_cost_above_12hr": 5e-05,
"cache_read_input_token_cost": 2e-06,
"input_cost_per_token": 2e-05,
"litellm_provider": "openai",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.0001,
"source": "https://developers.openai.com/api/docs/models/gpt-6-cyber",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_search": true,
"supports_vision": true,
"supports_web_search": true
},
"gpt-6-astra-law": {
"cache_read_input_token_cost": 1e-06,
"input_cost_per_token": 1e-05,
@ -83380,6 +83478,28 @@
"supports_response_schema": true,
"source": "https://empiriolabs.ai/models/kimi-k3"
},
"empiriolabs/kimi-k3-1-pro": {
"litellm_provider": "empiriolabs",
"mode": "chat",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"input_cost_per_token": 2e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.8e-06,
"supports_system_messages": true,
"supports_vision": true,
"supports_reasoning": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.015,
"search_context_size_medium": 0.015,
"search_context_size_high": 0.015
},
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_function_calling": true,
"source": "https://empiriolabs.ai/models/kimi-k3-1-pro"
},
"empiriolabs/mimo-v2-6-flash": {
"litellm_provider": "empiriolabs",
"mode": "chat",
@ -86383,5 +86503,32 @@
"supports_system_messages": false,
"supports_video_input": true,
"supports_vision": true
},
"databricks/databricks-kimi-k3-1-pro": {
"cache_creation_input_token_cost": 1.99997e-06,
"cache_read_input_token_cost": 1.9999e-07,
"input_cost_per_token": 1.99997e-06,
"input_dbu_cost_per_token": 2.8571e-05,
"litellm_provider": "databricks",
"max_input_tokens": 1048576,
"max_output_tokens": 1048576,
"metadata": {"notes":"Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference."},
"mode": "chat",
"output_cost_per_token": 9.99999e-06,
"output_dbu_cost_per_token": 0.000142857,
"source": "https://www.databricks.com/product/pricing/foundation-model-serving",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"token_count_framing": 100.0
}
}

13
litellm/models/plugin_upload.py
View file

@ -41,6 +41,14 @@ class PluginArchiveMetadata:
description: str | None = None
has_agent_skill_metadata: bool = False
updated_at: datetime | None = None
created_at: datetime | None = None
created_by: str | None = None
@dataclass(frozen=True, slots=True)
class PluginReview:
approved_by: str
security_scan_passed: bool
@dataclass(frozen=True, slots=True)
@ -51,6 +59,7 @@ class PluginPublication:
manifest: Mapping[str, object]
created_by: str | None
content: bytes | None = None
review: PluginReview | None = None
@dataclass(frozen=True, slots=True)
@ -66,6 +75,10 @@ class PublishedPlugin:
version: str
enabled: bool
updated_at: datetime
created_at: datetime | None = None
created_by: str | None = None
review: PluginReview | None = None
published_by: str | None = None
@dataclass(frozen=True, slots=True)

169
litellm/proxy/_lazy_openapi_snapshot.json
View file

@ -7683,6 +7683,17 @@
"PluginListItem": {
"description": "Plugin item in list responses.",
"properties": {
"approved_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Approved By"
},
"author": {
"anyOf": [
{
@ -7715,6 +7726,17 @@
],
"title": "Created At"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Created By"
},
"description": {
"anyOf": [
{
@ -7737,6 +7759,17 @@
],
"title": "Domain"
},
"download_count": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Download Count"
},
"enabled": {
"title": "Enabled",
"type": "boolean"
@ -7801,6 +7834,22 @@
],
"title": "Namespace"
},
"published_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Published By"
},
"security_scan_passed": {
"default": false,
"title": "Security Scan Passed",
"type": "boolean"
},
"source": {
"additionalProperties": {
"type": "string"
@ -59415,6 +59464,14 @@
},
"title": "Skills",
"type": "array"
},
"tags": {
"default": [],
"items": {
"type": "string"
},
"title": "Tags",
"type": "array"
}
},
"required": [
@ -59690,6 +59747,17 @@
},
"SkillHubSkill": {
"properties": {
"approved_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Approved By"
},
"content_url": {
"anyOf": [
{
@ -59701,6 +59769,29 @@
],
"title": "Content Url"
},
"created_at": {
"anyOf": [
{
"format": "date-time",
"type": "string"
},
{
"type": "null"
}
],
"title": "Created At"
},
"created_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Created By"
},
"description": {
"anyOf": [
{
@ -59732,7 +59823,7 @@
"type": "null"
}
],
"description": "Gateway ZIP downloads, included in proxy-admin catalog listings",
"description": "Gateway ZIP downloads, including repeat downloads",
"title": "Download Count"
},
"download_url": {
@ -59779,6 +59870,22 @@
],
"title": "Namespace"
},
"published_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Published By"
},
"security_scan_passed": {
"default": false,
"title": "Security Scan Passed",
"type": "boolean"
},
"source": {
"additionalProperties": {
"type": "string"
@ -60434,6 +60541,66 @@
"title": "Limit",
"type": "integer"
}
},
{
"in": "query",
"name": "tag",
"required": false,
"schema": {
"default": "",
"title": "Tag",
"type": "string"
}
},
{
"in": "query",
"name": "security_scan_passed",
"required": false,
"schema": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Security Scan Passed"
}
},
{
"in": "query",
"name": "sort_by",
"required": false,
"schema": {
"default": "name",
"enum": [
"name",
"download_count",
"updated_at",
"created_at",
"created_by",
"published_by",
"approved_by",
"security_scan_passed"
],
"title": "Sort By",
"type": "string"
}
},
{
"in": "query",
"name": "sort_order",
"required": false,
"schema": {
"default": "asc",
"enum": [
"asc",
"desc"
],
"title": "Sort Order",
"type": "string"
}
}
],
"responses": {

18
litellm/proxy/anthropic_endpoints/claude_code_endpoints/claude_code_marketplace.py
View file

@ -60,6 +60,7 @@ from litellm.proxy.common_utils.claude_code_marketplace_auth import (
)
from litellm.proxy.common_utils.resource_ownership import is_proxy_admin
from litellm.proxy.deps.repositories import PluginUploadRepositoryDep
from litellm.repositories.plugin_publication import read_plugin_publisher, read_plugin_review
from litellm.repositories.table_repositories import ClaudeCodePluginRepository
from litellm.types.proxy.auth.special_headers import SpecialHeaders
from litellm.types.proxy.claude_code_endpoints import (
@ -666,6 +667,7 @@ async def register_plugin(
response_model=ListPluginsResponse,
)
async def list_plugins(
uploads: PluginUploadRepositoryDep,
enabled_only: bool = False,
user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
) -> ListPluginsResponse:
@ -678,6 +680,17 @@ async def list_plugins(
Returns:
List of plugins with their metadata.
"""
catalog: Final = await list_visible_plugins(enabled_only, user_api_key_dict)
if uploads is None:
raise _error_response(500, CommonProxyErrors.db_not_connected_error.value)
counts: Final = await uploads.download_counts(tuple(plugin.id for plugin in catalog.plugins))
return ListPluginsResponse(
plugins=[plugin.model_copy(update={"download_count": counts.get(plugin.id, 0)}) for plugin in catalog.plugins],
count=catalog.count,
)
async def list_visible_plugins(enabled_only: bool, user_api_key_dict: UserAPIKeyAuth) -> ListPluginsResponse:
try:
prisma_client: Final = await get_prisma_client()
@ -693,9 +706,14 @@ async def list_plugins(
# Parse manifest to get additional fields
manifest = json.loads(p.manifest_json) if p.manifest_json else {}
review = read_plugin_review(MANIFEST_FIELDS.validate_python(manifest))
plugin_list.append(
PluginListItem(
id=p.id,
created_by=p.created_by,
approved_by=review.approved_by if review else None,
published_by=read_plugin_publisher(MANIFEST_FIELDS.validate_python(manifest)),
security_scan_passed=review.security_scan_passed if review else False,
name=p.name,
version=p.version,
description=p.description,

85
litellm/proxy/discovery_endpoints/skill_hub_endpoints.py
View file

@ -3,7 +3,8 @@ import hashlib
from collections.abc import Mapping
from dataclasses import dataclass, replace
from datetime import datetime
from typing import Annotated, Final
from itertools import chain
from typing import Annotated, Final, Literal
from urllib.parse import quote
import httpx
@ -33,7 +34,7 @@ from litellm.proxy.anthropic_endpoints.claude_code_endpoints.claude_code_marketp
enable_plugin,
get_plugin_downloads,
header_key_caller,
list_plugins,
list_visible_plugins,
plugin_archive_source_matches,
plugin_archive_url,
plugin_downloader,
@ -65,6 +66,7 @@ from litellm.proxy.discovery_endpoints.skill_import import (
parse_skill_source,
select_imported_skill,
)
from litellm.repositories.plugin_publication import read_plugin_publisher, read_plugin_review
from litellm.types.proxy.claude_code_endpoints import PluginListItem
from litellm.types.proxy.discovery_endpoints.agent_skills_endpoints import AgentSkillsIndexEntry
from litellm.types.proxy.skill_hub import (
@ -78,6 +80,7 @@ from litellm.types.proxy.skill_hub import (
SkillHubSkill,
SkillHubVersion,
SkillHubVersions,
SkillSortField,
)
router: Final = APIRouter(prefix="/skill-hub/skills", tags=["Skills Hub"])
@ -121,6 +124,11 @@ def _skill_response(request: Request, plugin: PluginListItem, download_count: in
namespace=plugin.namespace,
keywords=None if plugin.keywords is None else tuple(plugin.keywords),
updated_at=None if plugin.updated_at is None else datetime.fromisoformat(plugin.updated_at),
created_at=None if plugin.created_at is None else datetime.fromisoformat(plugin.created_at),
created_by=plugin.created_by,
approved_by=plugin.approved_by,
published_by=plugin.published_by,
security_scan_passed=plugin.security_scan_passed,
visibility="public" if plugin.enabled else "private",
source={"source": "archive", "url": _download_url(request, plugin.name)} if local_archive else plugin.source,
download_url=_download_url(request, plugin.name) if local_archive else None,
@ -137,28 +145,74 @@ async def list_skills(
query: str = "",
offset: Annotated[int, Query(ge=0)] = 0,
limit: Annotated[int, Query(ge=1, le=100)] = 50,
tag: str = "",
security_scan_passed: bool | None = None,
sort_by: SkillSortField = "name",
sort_order: Literal["asc", "desc"] = "asc",
) -> SkillHubList:
"""Browse the caller's public and granted private skills."""
catalog: Final = await list_plugins(enabled_only=False, user_api_key_dict=caller)
needle: Final = query.casefold()
catalog: Final = await list_visible_plugins(enabled_only=False, user_api_key_dict=caller)
needle: Final = query.strip().casefold()
selected_tag: Final = tag.strip().casefold()
matched: Final = tuple(
plugin
for plugin in sorted(catalog.plugins, key=lambda item: item.name)
if needle in " ".join((plugin.name, plugin.description or "", *(plugin.keywords or ()))).casefold()
if needle
in " ".join(
(
plugin.name,
plugin.description or "",
plugin.domain or "",
plugin.namespace or "",
plugin.created_by or "",
plugin.approved_by or "",
plugin.published_by or "",
*(plugin.keywords or ()),
)
).casefold()
and (not selected_tag or selected_tag in {word.casefold() for word in plugin.keywords or ()})
and (security_scan_passed is None or plugin.security_scan_passed == security_scan_passed)
)
page: Final = matched[offset : offset + limit]
counts: Final[Mapping[str, int]] = (
await _require_store(uploads).download_counts(tuple(plugin.id for plugin in page))
if is_proxy_admin(caller)
await _require_store(uploads).download_counts(tuple(plugin.id for plugin in matched))
if sort_by == "download_count"
else {}
)
ordered: Final = sorted(
matched, key=lambda plugin: _skill_sort_key(plugin, sort_by, counts), reverse=sort_order == "desc"
)
page: Final = ordered[offset : offset + limit]
page_counts: Final = (
await _require_store(uploads).download_counts(tuple(plugin.id for plugin in page))
if sort_by != "download_count"
else counts
)
return SkillHubList(
skills=tuple(_skill_response(request, plugin, counts.get(plugin.id)) for plugin in page),
skills=tuple(_skill_response(request, plugin, page_counts.get(plugin.id)) for plugin in page),
count=len(matched),
next_offset=offset + limit if offset + limit < len(matched) else None,
tags=tuple(
sorted(set(chain.from_iterable(plugin.keywords or () for plugin in catalog.plugins)), key=str.casefold)
),
)
def _skill_sort_key(plugin: PluginListItem, field: SkillSortField, counts: Mapping[str, int]) -> str | float:
if field == "download_count":
return counts.get(plugin.id, 0)
if field == "security_scan_passed":
return int(plugin.security_scan_passed)
if field in {"created_at", "updated_at"}:
value: Final = plugin.created_at if field == "created_at" else plugin.updated_at
return datetime.fromisoformat(value).timestamp() if value else 0
return {
"name": plugin.name,
"created_by": plugin.created_by or "",
"published_by": plugin.published_by or "",
"approved_by": plugin.approved_by or "",
}[field].casefold()
@router.get("/{name}", response_model=SkillHubSkill)
async def get_skill(
request: Request,
@ -176,6 +230,7 @@ async def get_skill(
def skill_metadata_response(request: Request, metadata: PluginArchiveMetadata) -> SkillHubSkill:
manifest: Final = MANIFEST_FIELDS.validate_json(metadata.manifest_json or "{}")
review: Final = read_plugin_review(manifest)
return _skill_response(
request,
PluginListItem.model_validate(
@ -187,7 +242,11 @@ def skill_metadata_response(request: Request, metadata: PluginArchiveMetadata) -
"source": dict(metadata.source),
"has_agent_skill_metadata": metadata.has_agent_skill_metadata,
"enabled": metadata.enabled,
"created_at": None,
"created_at": metadata.created_at.isoformat() if metadata.created_at is not None else None,
"created_by": metadata.created_by,
"approved_by": review.approved_by if review else None,
"published_by": read_plugin_publisher(manifest),
"security_scan_passed": review.security_scan_passed if review else False,
"updated_at": metadata.updated_at.isoformat() if metadata.updated_at is not None else None,
"domain": manifest.get("domain"),
"namespace": manifest.get("namespace"),
@ -416,7 +475,11 @@ def skill_publication_response(
"version": published.version,
"enabled": published.enabled,
"has_agent_skill_metadata": has_agent_skill_metadata(publication.manifest),
"created_at": None,
"created_at": published.created_at.isoformat() if published.created_at is not None else None,
"created_by": published.created_by,
"approved_by": published.review.approved_by if published.review else None,
"published_by": published.published_by,
"security_scan_passed": published.review.security_scan_passed if published.review else False,
"updated_at": published.updated_at.isoformat(),
"domain": publication.manifest.get("domain"),
"namespace": publication.manifest.get("namespace"),

45
litellm/proxy/guardrails/guardrail_hooks/zscaler_ai_guard/zscaler_ai_guard.py
View file

@ -4,7 +4,8 @@
#
# +-------------------------------------------------------------+
import os
from collections.abc import Mapping
from collections.abc import Mapping, Sequence
from itertools import chain, dropwhile, takewhile
from typing import TYPE_CHECKING, Final, Literal, Optional
from fastapi import HTTPException
@ -14,6 +15,10 @@ from litellm.integrations.custom_guardrail import (
CustomGuardrail,
log_guardrail_information,
)
from litellm.litellm_core_utils.core_helpers import as_object_list, as_str_mapping
from litellm.llms.base_llm.guardrail_translation.utils import (
effective_scan_only_tool_results_for_guardrail,
)
from litellm.llms.custom_httpx.http_handler import (
get_async_httpx_client,
httpxSpecialProvider,
@ -218,15 +223,14 @@ class ZscalerAIGuard(CustomGuardrail):
zscaler_ai_guard_result = None
direction: Final = "OUT" if input_type == "response" else "IN"
verbose_proxy_logger.debug("direction: %s", direction)
# Concatenate all texts and send to Zscaler AI Guard
if texts:
concatenated_text: Final = " ".join(texts)
content: Final = self._content_to_scan(inputs, input_type)
if content:
zscaler_ai_guard_result = await self.make_zscaler_ai_guard_api_call(
zscaler_ai_guard_url=self.zscaler_ai_guard_url,
api_key=self.api_key,
policy_id=policy_id,
direction=direction,
content=concatenated_text,
content=content,
user=user_for_payload,
**kwargs,
)
@ -244,6 +248,37 @@ class ZscalerAIGuard(CustomGuardrail):
verbose_proxy_logger.debug("ZscalerAIGuard: Successfully applied guardrail.")
return inputs
def _content_to_scan(
self,
inputs: GenericGuardrailAPIInputs,
input_type: Literal["request", "response"],
) -> str | None:
structured_messages: Final = inputs.get("structured_messages") or []
scans_last_user_turn: Final = (
input_type == "request"
and not effective_scan_only_tool_results_for_guardrail(self)
and any("content" in message for message in structured_messages)
)
texts: Final = (
self._last_user_turn_texts(structured_messages) if scans_last_user_turn else inputs.get("texts", [])
)
return " ".join(texts) if texts else None
@staticmethod
def _last_user_turn_texts(messages: Sequence[Mapping[str, object]]) -> tuple[str, ...]:
from_last_user_message: Final = dropwhile(lambda message: message.get("role") != "user", reversed(messages))
last_user_turn: Final = tuple(takewhile(lambda message: message.get("role") == "user", from_last_user_message))
texts: Final = tuple(chain.from_iterable(map(ZscalerAIGuard._content_texts, reversed(last_user_turn))))
return texts if any(text.strip() for text in texts) else ()
@staticmethod
def _content_texts(message: Mapping[str, object]) -> tuple[str, ...]:
content: Final = message.get("content")
if isinstance(content, str):
return (content,)
parts: Final = (as_str_mapping(part) for part in as_object_list(content) or ())
return tuple(text for part in parts if part is not None and isinstance(text := part.get("text"), str))
def extract_blocking_info(self, response):
"""
Extracts transaction ID and blocking detector details from a response.

4
litellm/proxy/management_endpoints/key_management_endpoints.py
View file

@ -5482,7 +5482,9 @@ async def generate_key_helper_fn(
if query_type == "insert_data":
user_row = cast( # cast-ok: table_name="user" is the insert_data branch returning the user row
"prisma_models.LiteLLM_UserTable | None",
await prisma_client.insert_data(data=user_data, table_name="user"),
await prisma_client.insert_data(
data=user_data, table_name="user", allow_existing_user=request_type != "user"
),
)
if user_row is None:

2
litellm/proxy/management_endpoints/router_settings_endpoints.py
View file

@ -68,7 +68,7 @@ def _get_routing_strategies_from_router_class() -> list[str]:
Dynamically extract routing strategies from the Router class __init__ method.
"""
# Get the __init__ signature
sig: Final = inspect.signature(Router.__init__) # pyright: ignore[reportUnknownMemberType, reportUnknownArgumentType] # untyped params, only routing_strategy is read
sig: Final = inspect.signature(Router)
# Get the routing_strategy parameter
routing_strategy_param: Final = sig.parameters.get("routing_strategy")

4
litellm/proxy/management_endpoints/scim/scim_v2.py
View file

@ -1294,7 +1294,7 @@ async def _create_user_if_not_exists(user_id: str, created_via: str = "scim_grou
if litellm.default_internal_user_params:
default_role = litellm.default_internal_user_params.get("user_role")
new_user_request: Final = NewUserRequest(
new_user_request: Final = SCIMNewUserRequest(
user_id=user_id,
user_email=user_id, # We don't have email from group membership
user_alias=None,
@ -1873,7 +1873,7 @@ async def create_user(
admin_group: Final = await _get_scim_admin_group()
resolved_role: Final = _resolve_scim_user_role(user.groups or [], admin_group, default_role)
new_user_request: Final = NewUserRequest(
new_user_request: Final = SCIMNewUserRequest(
user_id=user_id,
user_email=user_data["user_email"],
user_alias=user_data["user_alias"],

8
litellm/proxy/management_endpoints/ui_sso.py
View file

@ -78,7 +78,6 @@ from litellm.proxy._types import (
LitellmUserRoles,
Member,
NewTeamRequest,
NewUserRequest,
NewUserRequestTeam,
NewUserResponse,
ProxyErrorTypes,
@ -164,6 +163,7 @@ from litellm.types.proxy.management_endpoints.ui_sso import (
MicrosoftGraphAPIUserGroupResponse,
MicrosoftServicePrincipalTeam,
RoleMappings,
SSONewUserRequest,
TeamMappings,
)
from litellm.types.proxy.ui_sso import ParsedOpenIDResult
@ -2915,7 +2915,7 @@ async def insert_sso_user(
if user_defined_values["user_role"] is None:
user_defined_values["user_role"] = LitellmUserRoles.INTERNAL_USER_VIEW_ONLY
new_user_request: Final = NewUserRequest(
new_user_request: Final = SSONewUserRequest(
user_id=user_defined_values["user_id"],
user_email=normalize_email(user_defined_values["user_email"]),
user_alias=_get_sso_user_alias(result_openid),
@ -2924,11 +2924,9 @@ async def insert_sso_user(
budget_duration=user_defined_values["budget_duration"],
sso_user_id=user_defined_values["user_id"],
auto_create_key=False,
metadata={"auth_provider": getattr(result_openid, "provider")} if hasattr(result_openid, "provider") else {},
)
if result_openid and hasattr(result_openid, "provider"):
new_user_request.metadata = {"auth_provider": getattr(result_openid, "provider")}
from litellm.proxy.proxy_server import premium_user
with free_sso_user_creation(new_user_request.user_id, enabled=premium_user is not True):

16
litellm/proxy/public_endpoints/public_endpoints.py
View file

@ -24,7 +24,9 @@ from litellm.proxy._types import (
CommonProxyErrors,
)
from litellm.proxy.db.health_check_latest import latest_by_model_name
from litellm.proxy.deps.repositories import PluginUploadRepositoryDep
from litellm.proxy.utils import get_custom_url
from litellm.repositories.plugin_publication import read_plugin_publisher, read_plugin_review
from litellm.repositories.table_repositories import ClaudeCodePluginRepository
from litellm.router_strategy.complexity_router.fuse_presets import FusePresetCatalog, get_fuse_presets
from litellm.types.agents import AgentCard
@ -71,6 +73,9 @@ class _EndpointEntry(TypedDict):
class _PluginRow(Protocol):
@property
def created_by(self) -> str | None: ...
@property
def id(self) -> str: ...
@ -366,7 +371,7 @@ async def get_mcp_servers():
"/public/skill_hub",
tags=["public", "Claude Code Marketplace"],
)
async def public_skill_hub():
async def public_skill_hub(uploads: PluginUploadRepositoryDep):
"""Return enabled (public) Claude Code skills, or none when the marketplace requires a key."""
from litellm.proxy.anthropic_endpoints.claude_code_endpoints.claude_code_marketplace import (
MANIFEST_FIELDS,
@ -385,13 +390,22 @@ async def public_skill_hub():
raise HTTPException(status_code=500, detail=CommonProxyErrors.db_not_connected_error.value)
try:
plugins: Final = await _plugin_table(prisma_client).find_many(where={"enabled": True})
counts: Final[Mapping[str, int]] = (
await uploads.download_counts(tuple(plugin.id for plugin in plugins)) if uploads else {}
)
items: Final = []
for plugin in plugins:
raw = plugin.manifest_json or {}
manifest = json.loads(raw) if isinstance(raw, str) else raw
review = read_plugin_review(MANIFEST_FIELDS.validate_python(manifest))
items.append(
PluginListItem(
id=plugin.id,
download_count=counts.get(plugin.id),
created_by=plugin.created_by,
approved_by=review.approved_by if review else None,
published_by=read_plugin_publisher(MANIFEST_FIELDS.validate_python(manifest)),
security_scan_passed=review.security_scan_passed if review else False,
name=plugin.name,
enabled=plugin.enabled,
created_at=str(plugin.created_at) if plugin.created_at else None,

9
litellm/proxy/route_llm_request.py
View file

@ -271,6 +271,10 @@ REQUIRED_ONE_OF_BODY_PARAMS_BY_ROUTE: Final[Mapping[str, tuple[str, str]]] = Map
{"acreate_interaction": ("model", "agent"), "acreate_agent": ("id", "name")}
)
BODY_PARAM_ALTERNATIVES_BY_ROUTE: Final[Mapping[str, Mapping[str, tuple[str, ...]]]] = MappingProxyType(
{"acreate_interaction": MappingProxyType({"input": ("continuation_token",)})}
)
JSON_OBJECT_ADAPTER: Final[TypeAdapter[dict[str, object]]] = TypeAdapter(dict[str, object])
_OPTIONAL_JSON_OBJECT_ADAPTER: Final[TypeAdapter[Mapping[str, object] | None]] = TypeAdapter(
Mapping[str, object] | None
@ -320,8 +324,11 @@ def _find_missing_required_body_param(
)
if missing_merge_base_param is not None:
return MissingBodyParam(name=missing_merge_base_param, model_deployments_loaded=True)
alternatives: Final = BODY_PARAM_ALTERNATIVES_BY_ROUTE.get(route_type, {})
missing_present_params: Final = tuple(
param for param in REQUIRED_PRESENT_BODY_PARAMS_BY_ROUTE.get(route_type, ()) if param not in data
param
for param in REQUIRED_PRESENT_BODY_PARAMS_BY_ROUTE.get(route_type, ())
if param not in data and not any(alternative in data for alternative in alternatives.get(param, ()))
)
if not missing_present_params:
return None

31
litellm/proxy/utils.py
View file

@ -313,6 +313,7 @@ if TYPE_CHECKING:
from prisma import models as prisma_models
from prisma.actions import LiteLLM_DeprecatedVerificationTokenActions
from prisma.client import TransactionManager
from prisma.errors import UniqueViolationError
from prisma.models import LiteLLM_DeprecatedVerificationToken
from prisma.types import HttpConfig, LiteLLM_VerificationTokenInclude
@ -5559,6 +5560,25 @@ _LOCK_TEAMS_BY_ID_SQL: Final = (
)
def _user_unique_conflict_message(metadata: object, user_id: object) -> str:
match metadata:
case {"target": ["user_id"]}:
return f"User with id {user_id} already exists"
case {"target": ["sso_user_id"]}:
return "User with this sso_user_id already exists"
case _:
return "User conflicts with an existing unique value"
def _raise_user_unique_conflict(error: "UniqueViolationError", user_id: object, *, allow_existing: bool) -> NoReturn:
if allow_existing:
raise error
raise HTTPException(
status_code=409,
detail={"error": _user_unique_conflict_message(error.meta, user_id)},
) from error
class PrismaClient:
spend_log_transactions: list = []
_spend_log_transactions_lock = asyncio.Lock()
@ -6446,12 +6466,15 @@ class PrismaClient:
max_tries=3, # maximum number of retries
max_time=10, # maximum total time to retry for
on_backoff=on_backoff, # specifying the function to call on backoff
giveup=lambda exc: isinstance(exc, HTTPException) and exc.status_code == 409,
)
@log_db_metrics
async def insert_data(
self,
data: Mapping[str, object],
table_name: Literal["user", "key", "config", "spend", "team", "user_notification"],
*,
allow_existing_user: bool = True,
):
"""
Add a key to the database. If it already exists, do nothing.
@ -6487,14 +6510,20 @@ class PrismaClient:
verbose_proxy_logger.info("Data Inserted into Keys Table")
return new_verification_token
elif table_name == "user":
from prisma.errors import UniqueViolationError
db_data = self.jsonify_object(data=data)
try:
new_user_row: Final = await UserRepository(self).upsert_user(db_data)
new_user_row: Final = await UserRepository(self).upsert_user(
db_data, allow_existing=allow_existing_user
)
if new_user_row is None:
raise HTTPException(
status_code=403,
detail="SSO for more than 5 users requires a LiteLLM Enterprise license. Existing users can still sign in.",
)
except UniqueViolationError as e:
_raise_user_unique_conflict(e, db_data["user_id"], allow_existing=allow_existing_user)
except Exception as e:
if (
"Foreign key constraint failed on the field: `LiteLLM_UserTable_organization_id_fkey (index)`"

72
litellm/repositories/plugin_publication.py
View file

@ -1,15 +1,18 @@
import hashlib
import json
from collections.abc import Mapping
from dataclasses import asdict
from datetime import datetime, timezone
from typing import TYPE_CHECKING, Final, Protocol
from pydantic import TypeAdapter
from pydantic import TypeAdapter, ValidationError
from semver import Version
from litellm.models.plugin_upload import (
PluginPublication,
PluginPublicationBase,
PluginPublicationError,
PluginReview,
PublishedPlugin,
)
from litellm.repositories.prisma_protocols import TableActions
@ -23,6 +26,22 @@ if TYPE_CHECKING:
_MANIFEST: Final = TypeAdapter(dict[str, object])
_SOURCE: Final = TypeAdapter(dict[str, str])
_REVIEW: Final = TypeAdapter(PluginReview)
_PUBLISHER: Final = TypeAdapter[str | None](str | None)
def read_plugin_review(manifest: Mapping[str, object]) -> PluginReview | None:
try:
return _REVIEW.validate_python(manifest.get("_litellm_review"))
except ValidationError:
return None
def read_plugin_publisher(manifest: Mapping[str, object]) -> str | None:
try:
return _PUBLISHER.validate_python(manifest.get("_litellm_published_by"))
except ValidationError:
return None
class PluginPublicationTransaction(Protocol):
@ -122,7 +141,22 @@ async def publish_plugin(
)
if isinstance(version, PluginPublicationError):
return version
manifest_json: Final = json.dumps({**publication.manifest, "version": version})
current_manifest: Final = _MANIFEST.validate_json(current.manifest_json or "{}") if current is not None else {}
same_source: Final = current is not None and current_manifest.get("source") == publication.manifest.get("source")
review: Final = publication.review or (read_plugin_review(current_manifest) if same_source else None)
publisher: Final = publication.review.approved_by if publication.review is not None else publication.created_by
manifest_json: Final = json.dumps(
{
**{
key: value
for key, value in publication.manifest.items()
if key not in {"_litellm_review", "_litellm_published_by"}
},
"version": version,
**({"_litellm_published_by": publisher} if publisher is not None else {}),
**({"_litellm_review": asdict(review)} if review is not None else {}),
}
)
if publication.content is not None and verified_archive(publication.content, manifest_json) is None:
return PluginPublicationError("conflict", "Uploaded archive does not match its published source digest")
timestamp: Final = datetime.now(timezone.utc)
@ -141,8 +175,18 @@ async def publish_plugin(
await tx.litellm_claudecodepluginupload.create(
data={"plugin_name": publication.name, "content": Base64.encode(publication.content)}
)
await _snapshot(tx, created, publication.content, publication.created_by)
return PublishedPlugin(created.id, created.name, version, created.enabled, created.updated_at or timestamp)
await _snapshot(tx, created, publication.content, publisher)
return PublishedPlugin(
created.id,
created.name,
version,
created.enabled,
created.updated_at or timestamp,
created.created_at,
created.created_by,
review,
publisher,
)
previous_archive: Final = await tx.litellm_claudecodepluginupload.find_unique(where={"plugin_name": current.name})
previous_content: Final = (
verified_archive(previous_archive.content.decode(), current.manifest_json)
@ -152,11 +196,7 @@ async def publish_plugin(
history_count: Final = await tx.litellm_claudecodepluginversion.count(where={"plugin_id": current.id}, take=1)
if history_count == 0:
await _snapshot(tx, current, previous_content, None)
unchanged_content: Final = (
previous_content
if _MANIFEST.validate_json(current.manifest_json or "{}").get("source") == publication.manifest.get("source")
else None
)
unchanged_content: Final = previous_content if same_source else None
content: Final = publication.content if publication.content is not None else unchanged_content
updated: Final = await tx.litellm_claudecodeplugintable.update(where={"id": current.id}, data=data)
if updated is None:
@ -171,5 +211,15 @@ async def publish_plugin(
"update": {"content": Base64.encode(content)},
},
)
await _snapshot(tx, updated, content, publication.created_by)
return PublishedPlugin(updated.id, updated.name, version, updated.enabled, updated.updated_at or timestamp)
await _snapshot(tx, updated, content, publisher)
return PublishedPlugin(
updated.id,
updated.name,
version,
updated.enabled,
updated.updated_at or timestamp,
updated.created_at,
updated.created_by,
review,
publisher,
)

2
litellm/repositories/plugin_upload_repository.py
View file

@ -287,4 +287,6 @@ def _archive_metadata(plugin: "prisma_models.LiteLLM_ClaudeCodePluginTable") ->
description=plugin.description,
has_agent_skill_metadata=has_agent_skill_metadata(manifest),
updated_at=plugin.updated_at,
created_at=plugin.created_at,
created_by=plugin.created_by,
)

26
litellm/repositories/skill_submission_repository.py
View file

@ -7,12 +7,13 @@ from datetime import datetime, timezone
from typing import TYPE_CHECKING, Final, Protocol, cast # noqa: TID251 # Prisma's generated delegates are dynamic
from urllib.parse import urlsplit
from pydantic import BaseModel, ConfigDict, TypeAdapter
from pydantic import BaseModel, ConfigDict, TypeAdapter, ValidationError
from litellm.models.plugin_upload import (
PluginPublication,
PluginPublicationBase,
PluginPublicationError,
PluginReview,
PublishedPlugin,
uploaded_plugin_source,
)
@ -312,7 +313,9 @@ class SkillSubmissionRepository:
if approve and content is not None and publication_base_url
else _SOURCE.validate_python(submission.proposal.manifest.get("source"))
)
publication: Final = await _publish_submission(transaction, row, source, content) if approve else None
publication: Final = (
await _publish_submission(transaction, row, source, content, reviewer) if approve else None
)
if isinstance(publication, PluginPublicationError):
return publication
reviewed_at: Final = datetime.now(timezone.utc)
@ -346,6 +349,7 @@ async def _publish_submission(
row: "prisma_models.LiteLLM_SkillSubmission",
source: Mapping[str, str],
content: bytes | None,
reviewer: str,
) -> PublishedPlugin | PluginPublicationError:
stored: Final = _StoredProposal.model_validate_json(row.proposal_json)
proposal: Final = stored.proposal(row.plugin_name)
@ -363,6 +367,24 @@ async def _publish_submission(
manifest={**stored.manifest, "source": dict(source)},
content=content,
created_by=row.submitted_by,
review=PluginReview(reviewer, scan_passed_for_archive(row.scan_json, source.get("sha256"))),
),
base,
)
def scan_passed_for_archive(scan_json: str | None, digest: str | None) -> bool:
if not scan_json or not digest:
return False
try:
scan: Final = SkillScan.model_validate_json(scan_json)
except ValidationError:
return False
return (
scan.status == "completed"
and scan.archive_sha256 == digest
and scan.report is not None
and scan.report.complete
and scan.report.risk_score == 0
and not scan.report.findings
)

6
litellm/repositories/user_repository.py
View file

@ -168,7 +168,9 @@ class UserRepository(BaseRepository[LiteLLM_UserTable]):
"""
return await _count_billable_users(self.table)
async def upsert_user(self, data: Mapping[str, object]) -> "prisma_models.LiteLLM_UserTable | None":
async def upsert_user(
self, data: Mapping[str, object], *, allow_existing: bool = True
) -> "prisma_models.LiteLLM_UserTable | None":
"""Return the user row, or None when a new free SSO user would exceed capacity."""
scope: Final = _FREE_SSO_CREATION.get()
if (
@ -176,6 +178,8 @@ class UserRepository(BaseRepository[LiteLLM_UserTable]):
or (scope[0] is not None and scope[0] != data["user_id"])
or scope[1] is not asyncio.current_task()
):
if not allow_existing:
return await self.table.create(data=dict(data))
return await self.table.upsert(
where={"user_id": data["user_id"]}, data={"create": dict(data), "update": {}}
)

8
litellm/responses/mcp/stream_round_billing.py
View file

@ -1,5 +1,5 @@
import asyncio
from collections.abc import Callable, Coroutine, Sequence
from collections.abc import Callable, Sequence
from dataclasses import dataclass
from datetime import datetime
from typing import Final, TypeAlias
@ -297,12 +297,8 @@ class StreamedRoundBilling:
self._close(parked)
self._bank((self._dispatch(row, billed, self._logging_obj.attempt_scoped_copy()),), row)
def _dispatch(
self, row: _RoundRow, billed: _BilledRounds, logger: LiteLLMLoggingObj
) -> BilledRoundsDispatch | Coroutine[object, object, None]:
def _dispatch(self, row: _RoundRow, billed: _BilledRounds, logger: LiteLLMLoggingObj) -> BilledRoundsDispatch:
dispatch: Final = self._log_success(_SuccessLog(logger, row, billed.chat_usage))
if billed.chat_usage is None:
return dispatch
return BilledRoundsDispatch(dispatch, billed.spend)
@staticmethod

24
litellm/responses/streaming_iterator.py
View file

@ -53,7 +53,7 @@ from litellm.litellm_core_utils.internal_call_metadata import (
requests_background,
without_budget_reservation,
)
from litellm.litellm_core_utils.litellm_logging import BilledRoundsSpend
from litellm.litellm_core_utils.litellm_logging import BilledRoundsDispatch, BilledRoundsSpend, UncachedPrice
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
from litellm.litellm_core_utils.llm_response_utils.get_api_base import get_api_base
from litellm.litellm_core_utils.llm_response_utils.get_headers import provider_request_id_headers
@ -638,6 +638,24 @@ class BaseResponsesAPIStreamingIterator:
self._handle_failure(e)
raise
def _deferred_logging_dispatch(
self, logging_coroutine: Coroutine[object, object, None], logging_response: object
) -> BilledRoundsDispatch | Coroutine[object, object, None]:
response: Final[object] = getattr(logging_response, "response", None)
if not isinstance(response, ResponsesAPIResponse):
return logging_coroutine
price: Final = (
UncachedPrice(0.0, None)
if self._completed_response_cache_hit
else self.logging_obj.uncached_price(response)
)
spend: Final = BilledRoundsSpend(
ResponseAPILoggingUtils.transform_response_api_usage_to_chat_usage(response.usage),
price.cost or 0.0,
price.cost_breakdown,
)
return BilledRoundsDispatch(logging_coroutine, spend)
def _log_completed_response(self, *, is_async: bool) -> None:
if self._completed_response_logged:
return
@ -662,7 +680,9 @@ class BaseResponsesAPIStreamingIterator:
if deferred_dispatch_armed:
# End-of-stream guardrail scans write guardrail_information after
# the terminal event; dispatching now would snapshot metadata early.
self.logging_obj._deferred_stream_complete_args = (logging_coroutine,)
self.logging_obj._deferred_stream_complete_args = (
self._deferred_logging_dispatch(logging_coroutine, logging_response),
)
else:
spawn_logging_task(
asyncio.get_running_loop(), logging_coroutine, task_name="Responses stream success logging"

12
litellm/router.py
View file

@ -52,7 +52,7 @@ if TYPE_CHECKING:
# ``Router(...)``'s parameters, their defaults and its docstring: ``router_arguments`` binds a call
# against them and ``Router.__init__`` reports them. The body is never run.
def _router_init(
self,
self: object,
model_list: list[DeploymentTypedDict] | list[dict[str, Any]] | None = None,
## ASSISTANTS API ##
assistants_config: AssistantsTypedDict | None = None,
@ -228,18 +228,16 @@ if TYPE_CHECKING:
from litellm.types.llms.openai import AllMessageValues, OpenAIFileObject
from litellm.types.utils import EmbeddingResponse, LiteLLMBatch, ModelResponse
_InitParams: Final = ParamSpec("_InitParams")
_P: Final = ParamSpec("_P")
def _signature_of(
source: Callable[_InitParams, None],
) -> Callable[[Callable[..., None]], Callable[_InitParams, None]]: ...
def _takes_parameters_of(source: Callable[_P, None]) -> Callable[[Callable[..., None]], Callable[_P, None]]: ...
class Router(RustCore, DeprecatedRouterMembers):
"""What type checkers see: the constructor's parameters and the endpoints' return types. The
endpoints are served by the core at run time (litellm/router_rust/invoke/endpoints.py)."""
@_signature_of(_router_init) # pyright: ignore[reportUnknownArgumentType] # _router_init's untyped dict params
def __init__(self) -> None: ...
@_takes_parameters_of(_router_init)
def __init__(self) -> None: ... # pyright: ignore[reportMissingSuperCall] # a type-checking stub
@classmethod
def from_config(cls, config: RouterConfig, host: PythonHost = python_host) -> "Router": ...

7
litellm/router_rust/invoke/endpoints.py
View file

@ -1911,10 +1911,9 @@ class RustEndpoints:
if self._scheduler is None:
from litellm.scheduler import Scheduler
self._scheduler = (
Scheduler(polling_interval=self._polling_interval) # pyright: ignore[reportArgumentType] # as configured
if self._polling_interval is not None
else Scheduler()
self._scheduler = Scheduler(
polling_interval=self._polling_interval, # pyright: ignore[reportArgumentType] # as configured
redis_cache=self._core.routing_cache.redis_cache,
)
return self._scheduler

12
litellm/router_rust/invoke/walk.py
View file

@ -264,10 +264,18 @@ class WalkMetadata:
def hop_kwargs(self, event: Mapping[str, object]) -> dict[str, object]: # mutable-ok: a fresh dict for the loggers
"""The kwargs the level held after a hop (``kwargs["model"] = target``), as the
fallback loggers see them."""
fallback loggers see them: the request's own metadata (the proxy's ``user_api_key_*``
labels) with the level's walk stamps laid over it, as ``run_async_fallback``'s
``_hop_metadata`` copies it."""
scope: Final = self._scope(event.get("scope"))
model: Final = scope.metadata.get("model_group", event.get("to"))
return {**self._request, **scope.kwargs, "model": model, self._field: dict(scope.metadata)}
request_bucket: Final = as_str_mapping(self._request.get(self._field)) or {}
return {
**self._request,
**scope.kwargs,
"model": model,
self._field: {**request_bucket, **scope.metadata},
}
def log_retry(self, event: Mapping[str, object], error: BaseException | None) -> None:
"""A ``retry_logged`` event: the failure joins the scope's ``previous_models``."""

2
litellm/router_rust/surface/health.py
View file

@ -279,6 +279,7 @@ class RustHealthCallbacks:
is_caller_scoped_auth_failure,
is_caller_timeout_408,
is_failure_outside_selected_deployment,
is_response_lookup_not_found,
is_video_lookup_not_found,
)
@ -288,6 +289,7 @@ class RustHealthCallbacks:
is_failure_outside_selected_deployment(exception if isinstance(exception, BaseException) else None)
or (isinstance(exception, Exception) and is_background_response_poll_not_found(exception, litellm_params))
or is_video_lookup_not_found(exception, logged)
or is_response_lookup_not_found(exception, logged)
or is_caller_timeout_408(logged, status) # pyright: ignore[reportArgumentType] # the status as raised
or is_caller_scoped_auth_failure(self._deployment_of(deployment_id), status) # pyright: ignore[reportArgumentType] # see above
)

20
litellm/router_utils/cooldown_handlers.py
View file

@ -108,6 +108,26 @@ def is_video_lookup_not_found(exception: object, failure_kwargs: Mapping[str, ob
return getattr(exception, "status_code", None) == 404 and failure_kwargs.get("call_type") in VIDEO_ID_CALL_TYPES
# The calls on an existing response id. ``compact_responses`` is left out: it sends a model and input,
# so its 404 can mean a missing model rather than a missing response.
RESPONSE_ID_CALL_TYPES: Final = frozenset(
{
"aget_responses",
"get_responses",
"adelete_responses",
"delete_responses",
"acancel_responses",
"cancel_responses",
"alist_input_items",
}
)
def is_response_lookup_not_found(exception: object, failure_kwargs: Mapping[str, object]) -> bool:
"""Whether a call on an existing response id failed with a provider 404: the response is not on that account."""
return getattr(exception, "status_code", None) == 404 and failure_kwargs.get("call_type") in RESPONSE_ID_CALL_TYPES
_EXCEPTION_POLICY_FIELDS: Final[tuple[tuple[type, str], ...]] = (
# ContentPolicyViolationError subclasses BadRequestError, so it must be checked first.
(litellm.ContentPolicyViolationError, "ContentPolicyViolationErrorAllowedFails"),

4
litellm/router_utils/handle_error.py
View file

@ -26,7 +26,7 @@ async def send_llm_exception_alert(
ctx: "RoutingContext | None",
request_kwargs: dict,
error_traceback_str: str,
original_exception,
original_exception: Exception,
):
"""
Only runs if router.slack_alerting_logger is set
@ -34,7 +34,7 @@ async def send_llm_exception_alert(
Parameters:
ctx (RoutingContext): The router's routing context.
original_exception (Any): The original exception that occurred.
original_exception (Exception): The original exception that occurred.
Returns:
None

3
litellm/router_utils/pre_call_checks/prompt_caching_deployment_check.py
View file

@ -163,6 +163,9 @@ class PromptCachingDeploymentCheck(CustomLogger):
return healthy_deployments
def exempt_from_message_redaction(self) -> bool:
return True
async def async_log_success_event(
self,
kwargs: _PromptCachingSuccessEventKwargs,

24
litellm/types/interactions/generated.py
View file

@ -176,11 +176,16 @@ class Status1(Enum):
incomplete = "incomplete"
budget_exceeded = "budget_exceeded"
queued = "queued"
requires_continuation = "requires_continuation"
class InteractionStatusUpdate(LiteLLMBaseModel):
interaction_id: str | None = None
status: Status1 | None = None
continuation_token: str | None = Field(
None,
description="Opaque token to resume a long decode. Output: set when status is\nREQUIRES_CONTINUATION and decoding can be resumed. Input: pass the latest\ntoken back unchanged in CreateInteraction to continue decoding.",
)
event_type: Literal["interaction.status_update"] = "interaction.status_update"
event_id: str | None = Field(
None,
@ -343,6 +348,7 @@ class Status3(Enum):
INCOMPLETE = "incomplete"
BUDGET_EXCEEDED = "budget_exceeded"
QUEUED = "queued"
REQUIRES_CONTINUATION = "requires_continuation"
class ModelOption(RootModel[str]):
@ -604,6 +610,9 @@ class ToolChoice(RootModel[ToolChoiceType | ToolChoiceConfig]):
class Usage(LiteLLMBaseModel):
total_input_tokens: int | None = Field(None, description="Number of tokens in the prompt (context).")
initial_input_tokens: int | None = Field(
None, description="Number of tokens in the prompt of the first hop of a long decode."
)
input_tokens_by_modality: list[ModalityTokens] | None = Field(
None, description="A breakdown of input token usage by modality."
)
@ -625,6 +634,7 @@ class Usage(LiteLLMBaseModel):
None, description="A breakdown of tool-use token usage by modality."
)
total_reasoning_tokens: int | None = Field(None, description="Number of tokens of thoughts for thinking models.")
total_thought_tokens: int | None = Field(None, description="Number of tokens of thoughts for thinking models.")
total_tokens: int | None = Field(
None,
description="Total token count for the interaction request (prompt + responses + other\ninternal tokens).",
@ -787,6 +797,10 @@ class Interaction(LiteLLMBaseModel):
description="The mime type of the response. This is required if response_format is set.",
)
previous_interaction_id: str | None = Field(None, description="The ID of the previous interaction, if any.")
continuation_token: str | None = Field(
None,
description="Opaque token to resume a long decode. Output: set when status is\nREQUIRES_CONTINUATION and decoding can be resumed. Input: pass the latest\ntoken back unchanged in CreateInteraction to continue decoding.",
)
input: str | list[Content] | list[Turn] | Content | None = Field(
None, description="The inputs for the interaction."
)
@ -843,6 +857,10 @@ class CreateModelInteractionParams(LiteLLMBaseModel):
description="The mime type of the response. This is required if response_format is set.",
)
previous_interaction_id: str | None = Field(None, description="The ID of the previous interaction, if any.")
continuation_token: str | None = Field(
None,
description="Opaque token to resume a long decode. Output: set when status is\nREQUIRES_CONTINUATION and decoding can be resumed. Input: pass the latest\ntoken back unchanged in CreateInteraction to continue decoding.",
)
input: str | list[Content] | list[Turn] | Content = Field(..., description="The inputs for the interaction.")
generation_config: GenerationConfig | None = Field(
None,
@ -894,6 +912,10 @@ class CreateAgentInteractionParams(LiteLLMBaseModel):
description="The mime type of the response. This is required if response_format is set.",
)
previous_interaction_id: str | None = Field(None, description="The ID of the previous interaction, if any.")
continuation_token: str | None = Field(
None,
description="Opaque token to resume a long decode. Output: set when status is\nREQUIRES_CONTINUATION and decoding can be resumed. Input: pass the latest\ntoken back unchanged in CreateInteraction to continue decoding.",
)
input: str | list[Content] | list[Turn] | Content = Field(..., description="The inputs for the interaction.")
agent_config: DynamicAgentConfig | DeepResearchAgentConfig | None = Field(
None, description="Configuration for the agent.", discriminator="type"
@ -1080,6 +1102,7 @@ class InteractionsAPIResponse(BaseLiteLLMOpenAIResponseObject):
# New schema field (Api-Revision: 2026-05-20).
steps: list[dict[str, Any]] | None = None
usage: dict[str, Any] | None = None
continuation_token: str | None = None
_hidden_params: dict = PrivateAttr(default_factory=dict)
@ -1126,6 +1149,7 @@ class InteractionsAPIStreamingResponse(BaseLiteLLMOpenAIResponseObject):
step: dict[str, Any] | None = None
interaction_id: str | None = None
interaction: dict[str, Any] | None = None
continuation_token: str | None = None
_hidden_params: dict = PrivateAttr(default_factory=dict)

5
litellm/types/proxy/claude_code_endpoints.py
View file

@ -154,6 +154,11 @@ class PluginListItem(LiteLLMBaseModel):
enabled: bool
created_at: str | None
updated_at: str | None
created_by: str | None = None
approved_by: str | None = None
published_by: str | None = None
security_scan_passed: bool = False
download_count: int | None = None
has_agent_skill_metadata: bool = Field(default=False, exclude=True)

1
litellm/types/proxy/management_endpoints/internal_user_endpoints.py
View file

@ -120,6 +120,7 @@ class BulkNewUserItem(NewUserRequest):
model_config = ConfigDict(extra="forbid", protected_namespaces=())
user_id: str | None = None
auto_create_key: bool = False
@field_validator("send_invite_email")

9
litellm/types/proxy/management_endpoints/scim_v2.py
View file

@ -13,6 +13,7 @@ from pydantic import (
from pydantic_core.core_schema import SerializerFunctionWrapHandler
from litellm.types.llms.base import LiteLLMBaseModel
from litellm.types.proxy.management_endpoints.user_requests import NewUserRequest
SCIM_ENTERPRISE_USER_SCHEMA: Final = "urn:ietf:params:scim:schemas:extension:enterprise:2.0:User"
SCIM_ENTERPRISE_METADATA_KEY: Final = "scim_enterprise"
@ -26,6 +27,14 @@ _SCIM_SERIALIZED_FIELDS_ADAPTER: Final = TypeAdapter(
)
class SCIMNewUserRequest(NewUserRequest):
"""Preserve opaque directory IDs when provisioning SCIM users and group members."""
model_config = ConfigDict(frozen=True)
user_id: str | None = None
class LiteLLM_UserScimMetadata(LiteLLMBaseModel):
"""
Scim metadata stored in LiteLLM_UserTable.metadata

9
litellm/types/proxy/management_endpoints/ui_sso.py
View file

@ -1,12 +1,19 @@
from typing import Literal
from pydantic import Field
from pydantic import ConfigDict, Field
from typing_extensions import TypedDict
from litellm.types.proxy.auth.user_roles import KeyManagementRoutes, LitellmUserRoles
from litellm.types.proxy.management_endpoints.user_requests import NewUserRequest
from litellm.types.utils import LiteLLMPydanticObjectBase
class SSONewUserRequest(NewUserRequest):
model_config = ConfigDict(frozen=True)
user_id: str | None = None
class LiteLLM_UpperboundKeyGenerateParams(LiteLLMPydanticObjectBase):
"""
Set default upperbound to max budget a key called via `/key/generate` can be.

14
litellm/types/proxy/management_endpoints/user_requests.py
View file

@ -1,7 +1,7 @@
from collections.abc import Mapping
from typing import Literal
from typing import Annotated, Final, Literal
from pydantic import Field, field_validator, model_validator
from pydantic import AfterValidator, Field, field_validator, model_validator
from litellm.models.user import LiteLLM_UserTable
from litellm.types.proxy.auth.user_roles import LitellmUserRoles
@ -15,7 +15,17 @@ class NewUserRequestTeam(LiteLLMPydanticObjectBase):
user_role: Literal["user", "admin"] = "user"
def _validate_custom_user_id(value: str) -> str:
normalized: Final = value.strip()
if not normalized:
raise ValueError("user_id must not be empty or contain only whitespace")
if "\x00" in normalized:
raise ValueError("user_id must not contain NUL characters")
return normalized
class NewUserRequest(GenerateRequestBase):
user_id: Annotated[str, AfterValidator(_validate_custom_user_id)] | None = None
tpm_limit: int | None = Field(default=None, ge=0)
rpm_limit: int | None = Field(default=None, ge=0)
max_budget: float | None = None

21
litellm/types/proxy/skill_hub.py
View file

@ -7,6 +7,17 @@ from pydantic import ConfigDict, Field
from litellm.models.skill_submission import SubmissionOperation, SubmissionStatus
from litellm.types.llms.base import LiteLLMBaseModel
SkillSortField: TypeAlias = Literal[
"name",
"download_count",
"updated_at",
"created_at",
"created_by",
"published_by",
"approved_by",
"security_scan_passed",
]
class SkillHubSkill(LiteLLMBaseModel):
model_config = ConfigDict(frozen=True)
@ -16,6 +27,11 @@ class SkillHubSkill(LiteLLMBaseModel):
description: str | None = None
version: str | None = None
updated_at: datetime | None = None
created_at: datetime | None = None
created_by: str | None = None
approved_by: str | None = None
published_by: str | None = None
security_scan_passed: bool = False
visibility: Literal["public", "private"]
source: Mapping[str, str]
download_url: str | None = None
@ -23,12 +39,11 @@ class SkillHubSkill(LiteLLMBaseModel):
domain: str | None = None
namespace: str | None = None
keywords: tuple[str, ...] | None = None
download_count: int | None = Field(
None, description="Gateway ZIP downloads, included in proxy-admin catalog listings"
)
download_count: int | None = Field(None, description="Gateway ZIP downloads, including repeat downloads")
class SkillHubList(LiteLLMBaseModel):
tags: tuple[str, ...] = ()
model_config = ConfigDict(frozen=True)
skills: tuple[SkillHubSkill, ...]

4
litellm/types/utils.py
View file

@ -703,6 +703,8 @@ class CallTypes(str, Enum):
adelete_responses = "adelete_responses"
cancel_responses = "cancel_responses"
acancel_responses = "acancel_responses"
compact_responses = "compact_responses"
acompact_responses = "acompact_responses"
alist_input_items = "alist_input_items"
llm_passthrough_route = "llm_passthrough_route"
allm_passthrough_route = "allm_passthrough_route"
@ -806,6 +808,8 @@ CallTypesLiteral = Literal[
"send_message",
"aresponses",
"responses",
"compact_responses",
"acompact_responses",
"acreate_skill",
"acreate_realtime_client_secret",
"arealtime_calls",

157
model_prices_and_context_window.json
View file

@ -4046,6 +4046,8 @@
"cache_creation_input_token_cost": 1.25e-05,
"cache_creation_input_token_cost_above_1hr": 2e-05,
"cache_read_input_token_cost": 2.5e-07,
"deprecation_date": "2027-09-01",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
@ -4068,7 +4070,7 @@
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": false,
"prompt_cache_min_tokens": 512,
"source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models"
"source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement"
},
"azure_ai/claude-opus-5": {
"deprecation_date": "2027-07-08",
@ -13458,13 +13460,16 @@
"supports_reasoning": true
},
"azure_ai/mistral-document-ai-2512": {
"deprecation_date": "2027-02-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
"litellm_provider": "azure_ai",
"ocr_cost_per_page": 0.003,
"mode": "ocr",
"supported_endpoints": [
"/v1/ocr"
],
"source": "https://ai.azure.com/catalog/models/mistral-document-ai-2512"
"source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
"successor_model": "azure_ai/mistral-ocr-4-0"
},
"azure_ai/mistral-ocr-4-0": {
"litellm_provider": "azure_ai",
@ -40893,6 +40898,22 @@
"output_cost_per_token": 4e-07,
"supports_tool_choice": true
},
"jina-reranker-v3.5": {
"input_cost_per_token": 5e-08,
"litellm_provider": "jina_ai",
"max_input_tokens": 131072,
"mode": "rerank",
"output_cost_per_token": 0.0,
"source": "https://api.jina.ai/v1/models"
},
"jina-reranker-m0": {
"input_cost_per_token": 5e-08,
"litellm_provider": "jina_ai",
"max_input_tokens": 10240,
"mode": "rerank",
"output_cost_per_token": 0.0,
"source": "https://api.jina.ai/v1/models"
},
"jina-reranker-v2-base-multilingual": {
"input_cost_per_token": 5e-08,
"litellm_provider": "jina_ai",
@ -43771,7 +43792,8 @@
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"supports_vision": true
},
"mistral/zai-glm-5-3": {
"cache_read_input_token_cost": 1.4e-07,
@ -45270,6 +45292,18 @@
"source": "https://tokenfactory.nebius.com/api/public/models_info",
"cache_read_input_token_cost": 1.5e-07
},
"nebius/moonshotai/Kimi-K3.1-Pro": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 2e-07,
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_vision": true,
"supports_prompt_caching": true,
"source": "https://tokenfactory.nebius.com/api/public/models_info"
},
"nebius/moonshotai/Kimi-K3": {
"max_input_tokens": 1048576,
"max_output_tokens": 1024000,
@ -71189,6 +71223,8 @@
},
"gpt-5.5-cyber-preview": {
"cache_read_input_token_cost": 1.25e-06,
"deprecation_date": "2027-02-01",
"deprecation_source": "https://developers.openai.com/api/docs/deprecations",
"input_cost_per_token": 1.25e-05,
"litellm_provider": "openai",
"mode": "chat",
@ -72148,6 +72184,7 @@
"output_cost_per_token": 4.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supports_audio_input": true,
"supports_audio_output": true,
"tpm": 250000,
"rpm": 10,
"search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
@ -72170,6 +72207,7 @@
"output_cost_per_token": 4.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supports_audio_input": true,
"supports_audio_output": true,
"tpm": 250000,
"rpm": 10,
"search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014},
@ -76469,6 +76507,33 @@
"supports_tool_choice": true,
"supports_vision": true
},
"us-gov.xai.grok-4.7": {
"supports_regex_lookaround": false,
"supported_endpoints": ["/v1/chat/completions"],
"supports_bedrock_runtime_chat_completions_tools_with_reasoning": true,
"supports_bedrock_runtime_chat_completions_response_format": true,
"cache_read_input_token_cost": 6.6e-07,
"cache_read_input_token_cost_flex": 3.3e-07,
"cache_read_input_token_cost_priority": 1.155e-06,
"input_cost_per_token": 2.64e-06,
"input_cost_per_token_batches": 1.32e-06,
"input_cost_per_token_flex": 1.32e-06,
"input_cost_per_token_priority": 4.62e-06,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 524288,
"max_output_tokens": 524288,
"mode": "chat",
"output_cost_per_token": 7.92e-06,
"output_cost_per_token_batches": 3.96e-06,
"output_cost_per_token_flex": 3.96e-06,
"output_cost_per_token_priority": 1.386e-05,
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json",
"supports_function_calling": true,
"supports_prompt_caching": false,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": {
"cache_read_input_token_cost": 1.4e-08,
"input_cost_per_token": 6e-07,
@ -78437,7 +78502,7 @@
"cache_creation_input_token_cost": 1e-05,
"cache_creation_input_token_cost_above_1hr": 1.6e-05,
"cache_read_input_token_cost": 4e-07,
"deprecation_date": "2027-10-01",
"deprecation_date": "2027-01-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
"input_cost_per_token": 8e-06,
"litellm_provider": "azure_ai",
@ -78447,7 +78512,7 @@
"output_cost_per_token": 4e-05,
"prompt_cache_min_tokens": 512.0,
"search_context_cost_per_query": {"search_context_size_high":0.02,"search_context_size_low":0.02,"search_context_size_medium":0.02},
"source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models",
"source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
@ -82782,6 +82847,39 @@
"supports_vision": true,
"supports_xhigh_reasoning_effort": true
},
"gpt-6-cyber": {
"cache_creation_input_token_cost": 2.5e-05,
"cache_creation_input_token_cost_above_12hr": 5e-05,
"cache_read_input_token_cost": 2e-06,
"input_cost_per_token": 2e-05,
"litellm_provider": "openai",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.0001,
"source": "https://developers.openai.com/api/docs/models/gpt-6-cyber",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_search": true,
"supports_vision": true,
"supports_web_search": true
},
"gpt-6-astra-law": {
"cache_read_input_token_cost": 1e-06,
"input_cost_per_token": 1e-05,
@ -83380,6 +83478,28 @@
"supports_response_schema": true,
"source": "https://empiriolabs.ai/models/kimi-k3"
},
"empiriolabs/kimi-k3-1-pro": {
"litellm_provider": "empiriolabs",
"mode": "chat",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"input_cost_per_token": 2e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.8e-06,
"supports_system_messages": true,
"supports_vision": true,
"supports_reasoning": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.015,
"search_context_size_medium": 0.015,
"search_context_size_high": 0.015
},
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_function_calling": true,
"source": "https://empiriolabs.ai/models/kimi-k3-1-pro"
},
"empiriolabs/mimo-v2-6-flash": {
"litellm_provider": "empiriolabs",
"mode": "chat",
@ -86383,5 +86503,32 @@
"supports_system_messages": false,
"supports_video_input": true,
"supports_vision": true
},
"databricks/databricks-kimi-k3-1-pro": {
"cache_creation_input_token_cost": 1.99997e-06,
"cache_read_input_token_cost": 1.9999e-07,
"input_cost_per_token": 1.99997e-06,
"input_dbu_cost_per_token": 2.8571e-05,
"litellm_provider": "databricks",
"max_input_tokens": 1048576,
"max_output_tokens": 1048576,
"metadata": {"notes":"Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference."},
"mode": "chat",
"output_cost_per_token": 9.99999e-06,
"output_dbu_cost_per_token": 0.000142857,
"source": "https://www.databricks.com/product/pricing/foundation-model-serving",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"token_count_framing": 100.0
}
}

5
osv-scanner.toml
View file

@ -83,11 +83,6 @@ id = "GHSA-45c3-73f7-pv4m"
ignoreUntil = 2026-11-27
reason = "dnspython 2.9.0 (published 2026-10-09) is the only fix and requires Python >= 3.11, so the Python 3.10 resolution stays on 2.8.0 while 3.11+ locks 2.9.0; the advisory is CPU use in dns.name.from_wire_parser and litellm only reaches dnspython through pydantic EmailStr, which never does DNS lookups; remove this entry once 3.10 is dropped or a 3.10-compatible fix ships"
[[IgnoredVulns]]
id = "GHSA-xcx6-jx8p-x3h5"
ignoreUntil = 2026-11-24
reason = "@azure/msal-node is fixed only in 7.1.0 (published 2026-10-13), but it is dev-only in vscode-extension via @vscode/vsce > @azure/identity, and the latest @azure/identity (4.14.0) still requires msal-node ^6.0.0, so the lock cannot move without forcing a major override; the advisory is in the auth_code flow, which extension packaging does not run; bump and remove this entry once @azure/identity accepts msal-node >= 7.1.0"
[[PackageOverrides]]
name = "pillow"
version = "12.3.0"

22
packaging/litellm-proxy/pyproject.toml Normal file
View file

@ -0,0 +1,22 @@
[project]
name = "litellm-proxy"
version = "1.109.0"
description = "Opt-in Rust HTTP forwarding server for the LiteLLM Python proxy"
requires-python = ">=3.10, <3.16"
license = "MIT"
[build-system]
requires = ["maturin==1.15.0"]
build-backend = "maturin"
[tool.maturin]
manifest-path = "../../litellm-rust/crates/gateway/Cargo.toml"
bindings = "bin"
targets = [{ name = "litellm-gateway", kind = "bin" }]
profile = "release"
editable-profile = "dev"
include = [
{ path = "rust-toolchain.toml", format = "sdist" },
{ path = ".cargo/config.toml", format = "sdist" },
{ path = "model_prices_and_context_window.json", format = "sdist" },
]

4
pyproject.toml
View file

@ -359,6 +359,7 @@ exclude = [
]
[tool.uv]
concurrent-builds = 1
cache-keys = [
{ file = "pyproject.toml" },
{ file = "rust-toolchain.toml" },
@ -395,11 +396,12 @@ brotli = "2026-10-22T14:01:00Z"
pypdf = "2026-10-28T17:01:00Z"
[tool.uv.sources]
litellm-proxy = { workspace = true }
litellm-proxy-extras = { workspace = true }
litellm-enterprise = { workspace = true }
[tool.uv.workspace]
members = ["enterprise", "litellm-proxy-extras"]
members = ["enterprise", "litellm-proxy-extras", "packaging/litellm-proxy"]
[tool.commitizen]
version = "1.109.0"

30
scripts/build_core_distribution.py
View file

@ -1,4 +1,4 @@
"""Build the independent core distribution from shared repository sources."""
"""Build standalone core or gateway distributions from shared repository sources."""
import argparse
import shutil
@ -19,8 +19,16 @@ SOURCES: Final = (
"LICENSE",
)
IN_TREE_RUST_PATH: Final = "../../litellm-rust/"
def stage_core_distribution(source: Path, destination: Path) -> None:
class BuildOptions(argparse.Namespace):
package: str
out_dir: Path
sdist_only: bool
def stage_core_distribution(source: Path, destination: Path, *, package: str = "litellm-core") -> None:
version: Final = subprocess.run(
["uv", "version", "--short"], cwd=source, check=True, capture_output=True, text=True
).stdout.strip()
@ -53,8 +61,7 @@ def stage_core_distribution(source: Path, destination: Path) -> None:
)(directory, names)
destination.mkdir(parents=True, exist_ok=True)
for name in SOURCES:
path: Final = source / name
for name, path in ((name, source / name) for name in SOURCES if package == "litellm-core" or name != "litellm"):
if path.is_dir():
shutil.copytree(
path,
@ -63,15 +70,19 @@ def stage_core_distribution(source: Path, destination: Path) -> None:
)
else:
shutil.copy2(path, destination / name)
shutil.copy2(source / "packaging/litellm-core/pyproject.toml", destination / "pyproject.toml")
template: Final = (source / "packaging" / package / "pyproject.toml").read_text()
if package == "litellm-proxy" and IN_TREE_RUST_PATH not in template:
raise SystemExit(f"packaging/{package}/pyproject.toml no longer points at {IN_TREE_RUST_PATH}")
metadata: Final = template.replace(IN_TREE_RUST_PATH, "litellm-rust/")
(destination / "pyproject.toml").write_text(metadata)
subprocess.run(["uv", "version", version, "--frozen"], cwd=destination, check=True)
def build_core_distribution(output: Path, *, sdist_only: bool = False) -> None:
def build_core_distribution(output: Path, *, sdist_only: bool = False, package: str = "litellm-core") -> None:
output_path: Final = output.resolve()
with tempfile.TemporaryDirectory(prefix="litellm-core-") as temporary:
stage: Final = Path(temporary)
stage_core_distribution(ROOT, stage)
stage_core_distribution(ROOT, stage, package=package)
subprocess.run(
["uv", "build", "--python", sys.executable, "--out-dir", str(output_path)]
+ (["--sdist"] if sdist_only else []),
@ -82,12 +93,13 @@ def build_core_distribution(output: Path, *, sdist_only: bool = False) -> None:
def main() -> None:
parser: Final = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--package", choices=("litellm-core", "litellm-proxy"), default="litellm-core")
parser.add_argument("--out-dir", type=Path, default=ROOT / "dist/core")
parser.add_argument(
"--sdist-only", action="store_true", help="Build only the source archive, without compiling a wheel"
)
args: Final = parser.parse_args()
build_core_distribution(Path(args.out_dir), sdist_only=args.sdist_only)
args: Final = parser.parse_args(namespace=BuildOptions())
build_core_distribution(Path(args.out_dir), sdist_only=args.sdist_only, package=args.package)
if __name__ == "__main__":

61
tests/base_sdk_tests/test_core_distribution.py
View file

@ -20,12 +20,21 @@ else:
ROOT: Final = Path(__file__).resolve().parents[2]
@pytest.mark.parametrize(
("package_cli_args", "package"),
[
(("--package", "litellm-proxy"), "litellm-proxy"),
((), "litellm-core"),
],
)
@pytest.mark.parametrize("sdist_only", [False, True])
def test_build_command_selects_requested_distributions(tmp_path: Path, sdist_only: bool) -> None:
def test_build_command_selects_requested_distributions(
tmp_path: Path, sdist_only: bool, package_cli_args: tuple[str, ...], package: str
) -> None:
from scripts.build_core_distribution import main
output: Final = tmp_path / "dist"
arguments: Final = ["build_core_distribution.py", "--out-dir", str(output)] + (
arguments: Final = ["build_core_distribution.py", *package_cli_args, "--out-dir", str(output)] + (
["--sdist-only"] if sdist_only else []
)
with (
@ -42,6 +51,7 @@ def test_build_command_selects_requested_distributions(tmp_path: Path, sdist_onl
assert command[command.index("--out-dir") + 1] == str(output)
assert run.call_args.kwargs["check"] is True
assert run.call_args.kwargs["cwd"] == stage.call_args.args[1]
assert stage.call_args.kwargs["package"] == package
assert not stage.call_args.args[1].exists()
@ -53,7 +63,10 @@ def source_repository(tmp_path: Path) -> Path:
return source
def test_staging_stamps_release_version_without_modifying_sources(tmp_path: Path, source_repository: Path) -> None:
@pytest.mark.parametrize("package", ["litellm-core", "litellm-proxy"])
def test_staging_stamps_release_version_without_modifying_sources(
tmp_path: Path, source_repository: Path, package: str
) -> None:
from scripts.build_core_distribution import SOURCES, stage_core_distribution
source: Final = source_repository
@ -61,16 +74,44 @@ def test_staging_stamps_release_version_without_modifying_sources(tmp_path: Path
path: Final = source / name
path.write_text(f"shared {name}")
(source / "pyproject.toml").write_text('[project]\nname = "litellm"\nversion = "9.8.7rc1"\n')
manifest: Final = source / "packaging/litellm-core/pyproject.toml"
manifest: Final = source / "packaging" / package / "pyproject.toml"
manifest.parent.mkdir(parents=True)
manifest.write_bytes((ROOT / "packaging/litellm-core/pyproject.toml").read_bytes())
manifest.write_bytes((ROOT / "packaging" / package / "pyproject.toml").read_bytes())
original: Final = manifest.read_bytes()
stage: Final = tmp_path / "stage"
stage_core_distribution(source, stage)
assert tomllib.loads((stage / "pyproject.toml").read_text())["project"]["version"] == "9.8.7rc1"
stage_core_distribution(source, stage, package=package)
staged_project: Final = tomllib.loads((stage / "pyproject.toml").read_text())
assert staged_project["project"]["name"] == package
assert staged_project["project"]["version"] == "9.8.7rc1"
if package == "litellm-proxy":
assert staged_project["tool"]["maturin"]["targets"] == [{"name": "litellm-gateway", "kind": "bin"}]
assert not (stage / "litellm").exists()
assert all(
(stage / name).exists()
for name in ("litellm-rust", ".cargo", "rust-toolchain.toml", "model_prices_and_context_window.json")
)
assert manifest.read_bytes() == original
assert (source / "pyproject.toml").read_text() == '[project]\nname = "litellm"\nversion = "9.8.7rc1"\n'
assert all((stage / name).read_bytes() == (source / name).read_bytes() for name in SOURCES)
expected: Final = tuple(name for name in SOURCES if package == "litellm-core" or name != "litellm")
assert all((stage / name).read_bytes() == (source / name).read_bytes() for name in expected)
def test_gateway_staging_refuses_manifest_without_in_tree_rust_path(tmp_path: Path, source_repository: Path) -> None:
from scripts.build_core_distribution import SOURCES, stage_core_distribution
source: Final = source_repository
for name in SOURCES:
(source / name).write_text(f"shared {name}")
(source / "pyproject.toml").write_text('[project]\nname = "litellm"\nversion = "9.8.7"\n')
manifest: Final = source / "packaging" / "litellm-proxy" / "pyproject.toml"
manifest.parent.mkdir(parents=True)
manifest.write_text(
(ROOT / "packaging" / "litellm-proxy" / "pyproject.toml")
.read_text()
.replace("../../litellm-rust/", "../../rust/")
)
with pytest.raises(SystemExit, match="no longer points at"):
stage_core_distribution(source, tmp_path / "stage", package="litellm-proxy")
@pytest.fixture(scope="module")
@ -99,7 +140,9 @@ def test_core_wheel_metadata_and_resources(distributions: tuple[Path, Path]) ->
assert metadata["Version"] == tomllib.loads((ROOT / "pyproject.toml").read_text())["project"]["version"]
assert not metadata.get_all("Provides-Extra")
assert not any(n.endswith(".dist-info/entry_points.txt") for n in names)
requirements: Final = tomllib.loads((ROOT / "packaging/litellm-core/pyproject.toml").read_text())["project"]["dependencies"]
requirements: Final = tomllib.loads((ROOT / "packaging/litellm-core/pyproject.toml").read_text())["project"][
"dependencies"
]
for python_version in ("3.10", "3.11", "3.12", "3.13", "3.14"):
environment: Final = {"python_version": python_version, "python_full_version": python_version + ".0"}
assert {

1
tests/code_coverage_tests/liccheck.ini
View file

@ -89,6 +89,7 @@ importlib-metadata: >=6.8.0 # Apache 2.0 License
tokenizers: >=0.20.2 # Apache 2.0 License
jinja2: >=3.1.4 # BSD 3-Clause License
litellm-proxy-extras: >=0.1.1 # MIT License
litellm-proxy: >=1.109.0 # MIT, verified in repository LICENSE for litellm-rust and packaging/litellm-proxy
litellm-enterprise: >=0.1.1 # LiteLLM Enterprise License
a2a-sdk: >=0.3.22 # Apache 2.0 license
anyio: >=4.5.0 # Unknown license

18
tests/integration/_support/daily_activity.py
View file

@ -272,16 +272,32 @@ def assert_key_reported(
date: str,
metadata: Mapping[str, JsonValue],
metrics: Mapping[str, float],
*,
entity_rows: Mapping[str, int] | None = None,
) -> None:
assert response.status_code == 200, response.text
body: Final = object_value(response.json())
records: Final = tuple(object_value(record) for record in records_of_key(body, api_key))
assert records, response.text
assert all(record["metadata"] == metadata for record in records), response.text
assert all(counted(record["metrics"]) == pytest.approx(metrics) for record in records), response.text
days: Final = body["results"]
assert isinstance(days, list) and len(days) == 1, response.text
day: Final = object_value(days[0])
breakdown: Final = object_value(day["breakdown"])
if entity_rows is None:
assert all(counted(record["metrics"]) == pytest.approx(metrics) for record in records), response.text
else:
totals: Final = records_of_key({name: value for name, value in breakdown.items() if name != "entities"}, api_key)
assert totals, response.text
assert all(counted(object_value(record)["metrics"]) == pytest.approx(metrics) for record in totals), response.text
entities: Final = object_value(breakdown["entities"])
assert set(entities) == set(entity_rows), response.text
for entity, rows in entity_rows.items():
bucket: Final = object_value(entities[entity])
assert counted(bucket["metrics"]) == pytest.approx(seeded_metrics(rows)), response.text
keys: Final = object_value(bucket["api_key_breakdown"])
assert set(keys) == {api_key}, response.text
assert counted(object_value(keys[api_key])["metrics"]) == pytest.approx(seeded_metrics(rows)), response.text
assert day["date"] == date, response.text
assert counted(day["metrics"]) == pytest.approx(metrics), response.text
assert object_value(body["metadata"])["total_spend"] == pytest.approx(metrics["spend"]), response.text

64
tests/integration/_support/device_login.py
View file

@ -25,6 +25,7 @@ from pydantic import JsonValue
CHATGPT_AUTH_HOST: Final = "auth.openai.com"
GITHUB_HOST: Final = "github.com"
GITHUB_API_HOST: Final = "api.github.com"
COPILOT_API_HOST: Final = "api.githubcopilot.com"
AUTH_HOSTS: Final = (CHATGPT_AUTH_HOST, GITHUB_HOST, GITHUB_API_HOST)
CHATGPT_ACCOUNT: Final = "acct-device-login"
_FAR_FUTURE: Final = 4102444800
@ -79,7 +80,17 @@ COPILOT_MINTED_KEY: Final = "tid=device-login;minted"
COPILOT_REJECTED_KEY: Final = "tid=device-login;rejected"
CONTROL_KEY: Final = "device-login-control-key"
ACCEPTED_BEARERS: Final = frozenset(
{CHATGPT_STORED, CHATGPT_REFRESHED, CHATGPT_FIRST_LOGIN, COPILOT_STORED_KEY, COPILOT_MINTED_KEY, CONTROL_KEY}
{
CHATGPT_STORED,
CHATGPT_REFRESHED,
CHATGPT_FIRST_LOGIN,
COPILOT_ACCESS,
COPILOT_FIRST_LOGIN_ACCESS,
COPILOT_UNSAVED_KEY_ACCESS,
COPILOT_STORED_KEY,
COPILOT_MINTED_KEY,
CONTROL_KEY,
}
)
REJECTED_DETAIL: Final = "the scripted provider rejected this bearer token"
_DEVICE_AUTH_ID: Final = "device-auth-synthetic"
@ -180,6 +191,10 @@ def _auth_hosts(api_url: str, grant: threading.Event) -> Callable[[Request], Rep
return _json(200, {"access_token": COPILOT_FIRST_LOGIN_ACCESS, "token_type": "bearer"})
case ("api.github.com", "GET", "/copilot_internal/v2/token"):
return _copilot_api_key(request, api_url)
case ("api.github.com", "GET", "/copilot_internal/user"):
if request.headers.get("authorization") == f"token {COPILOT_REJECTED_ACCESS}":
return _json(401, {"message": "Bad credentials"})
return _json(200, {"endpoints": {"api": f"https://{COPILOT_API_HOST}"}})
case _:
return _switched_off()
@ -204,9 +219,22 @@ class Switches:
switch.clear()
@dataclass(frozen=True, slots=True)
class _ProviderAPI:
plain: Wire
secure: Wire
@property
def url(self) -> str:
return self.plain.url
def drain(self) -> tuple[Request, ...]:
return (*self.plain.drain(), *self.secure.drain())
@dataclass(frozen=True, slots=True)
class Peers:
api: Wire
api: _ProviderAPI
auth: Wire
tunnel: str
cert: Path
@ -228,6 +256,14 @@ class Peers:
def auth_connections(self) -> tuple[str, ...]:
return tuple(self.authorities.get_nowait() for _ in range(self.authorities.qsize()))
def assert_only_copilot_discovery(self, access_token: str) -> None:
assert set(self.auth_connections()) <= {f"{GITHUB_API_HOST}:443"}
requests: Final = self.auth.drain()
assert {
(request.method, request.target, request.headers.get("host"), request.headers.get("authorization"))
for request in requests
} <= {("GET", "/copilot_internal/user", GITHUB_API_HOST, f"token {access_token}")}, requests
def dropped(self) -> tuple[Hangup, ...]:
return tuple(self.hangups.get_nowait() for _ in range(self.hangups.qsize()))
@ -279,9 +315,8 @@ class _TunnelServer(socketserver.ThreadingTCPServer):
@contextmanager
def _tunnel(
destination: Wire, switches: Switches, authorities: SimpleQueue[str], hangups: SimpleQueue[Hangup]
destination: Wire, provider: Wire, switches: Switches, authorities: SimpleQueue[str], hangups: SimpleQueue[Hangup]
) -> Generator[str]:
destination_port: Final = int(destination.url.rsplit(":", 1)[1])
class Tunnel(socketserver.StreamRequestHandler):
rbufsize = 0
@ -306,20 +341,24 @@ def _tunnel(
if len(request_line) < 2:
return
authority: Final = request_line[1]
if authority.rsplit(":", 1)[0] not in AUTH_HOSTS:
host: Final = authority.rsplit(":", 1)[0]
if host not in (*AUTH_HOSTS, COPILOT_API_HOST):
self.wfile.write(b"HTTP/1.1 403 Forbidden\r\ncontent-length: 0\r\n\r\n")
return
authorities.put(authority)
if switches.refuse_connect.is_set():
is_auth: Final = host in AUTH_HOSTS
if is_auth:
authorities.put(authority)
if is_auth and switches.refuse_connect.is_set():
self.wfile.write(b"HTTP/1.1 502 Bad Gateway\r\ncontent-length: 0\r\n\r\n")
return
if self.hold(authority, opened, switches.hold_connect) is None:
if is_auth and self.hold(authority, opened, switches.hold_connect) is None:
return
self.wfile.write(b"HTTP/1.1 200 Connection established\r\n\r\n")
client_hello: Final = self.hold(authority, opened, switches.stall_tls)
client_hello: Final = self.hold(authority, opened, switches.stall_tls) if is_auth else b""
if client_hello is None:
return
self.request.settimeout(10)
destination_port: Final = int((destination if is_auth else provider).url.rsplit(":", 1)[1])
with socket.create_connection(("127.0.0.1", destination_port), timeout=10) as upstream:
upstream.sendall(client_hello)
outbound: Final = threading.Thread(target=_pipe, args=(self.request, upstream))
@ -340,16 +379,17 @@ def _tunnel(
@contextmanager
def device_login_peers(directory: Path) -> Generator[Peers]:
cert, key = write_self_signed_cert(directory, AUTH_HOSTS)
cert, key = write_self_signed_cert(directory, (*AUTH_HOSTS, COPILOT_API_HOST))
switches: Final = Switches(threading.Event(), threading.Event(), threading.Event(), threading.Event())
authorities: Final[SimpleQueue[str]] = SimpleQueue()
hangups: Final[SimpleQueue[Hangup]] = SimpleQueue()
with (
wire_server(_provider_api(rv.ResponsesVendor())) as api,
wire_server(_provider_api(rv.ResponsesVendor()), tls=server_context(cert, key)) as copilot_api,
wire_server(_auth_hosts(api.url, switches.grant), tls=server_context(cert, key)) as auth,
_tunnel(auth, switches, authorities, hangups) as tunnel,
_tunnel(auth, copilot_api, switches, authorities, hangups) as tunnel,
):
yield Peers(api, auth, tunnel, cert, authorities, hangups, switches)
yield Peers(_ProviderAPI(api, copilot_api), auth, tunnel, cert, authorities, hangups, switches)
def chatgpt_record(

114
tests/integration/authorization/test_responses_lifecycle_during_call_guardrail.py Normal file
View file

@ -0,0 +1,114 @@
"""GET, compact, DELETE and cancel on /v1/responses answer 200 when a during_call guardrail is on by default
(LIT-9770): the hook used to raise `'acompact_responses' is not a valid CallTypes` and the proxy returned 500"""
import json
import uuid
from collections.abc import Iterator
from pathlib import Path
from typing import Final
import httpx
import pytest
import yaml
from integration._support.client import Gateway, string_value
from integration._support.process import owned_proxy
from integration._support.provider import SharedProvider
from integration._support.wire import Reply
from pydantic import JsonValue, TypeAdapter
pytestmark: Final = pytest.mark.shares_worker_state
_JSON_OBJECT: Final = TypeAdapter(dict[str, JsonValue])
_MODEL: Final = "openai/gpt-5.4-mini"
def _input() -> list[JsonValue]:
return [
{"role": "user", "content": f"Remember the number {uuid.uuid4().hex}."},
{"role": "assistant", "content": "Got it."},
]
def _response(response_id: str) -> Reply:
body: Final[dict[str, JsonValue]] = {
"id": response_id,
"object": "response",
"created_at": 1,
"status": "completed",
"model": _MODEL.removeprefix("openai/"),
"output": [
{
"type": "message",
"id": f"msg_{uuid.uuid4().hex}",
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Got it.", "annotations": []}],
}
],
"parallel_tool_calls": False,
"tool_choice": "auto",
"tools": [],
"usage": {"input_tokens": 12, "output_tokens": 5, "total_tokens": 17},
}
return Reply(body=json.dumps(body).encode())
def _deleted(response_id: str) -> Reply:
return Reply(body=json.dumps({"id": response_id, "object": "response.deleted", "deleted": True}).encode())
def _guarded_config(path: Path) -> Path:
base: Final = _JSON_OBJECT.validate_python(yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text()))
guardrail: Final[dict[str, JsonValue]] = {
"guardrail_name": f"content-filter-{uuid.uuid4().hex}",
"litellm_params": {
"guardrail": "litellm_content_filter",
"mode": "during_call",
"default_on": True,
"blocked_words": [{"keyword": "forbiddenword", "action": "BLOCK"}],
},
}
path.write_text(yaml.safe_dump({**base, "guardrails": [guardrail]}))
return path
@pytest.fixture(scope="module")
def guarded(session_gateway: Gateway, tmp_path_factory: pytest.TempPathFactory) -> Iterator[Gateway]:
directory: Final = tmp_path_factory.mktemp("during-call-guardrail")
with owned_proxy(session_gateway, directory, {}, config=_guarded_config(directory / "config.yaml")) as candidate:
yield candidate
def _create(guarded: Gateway, provider: SharedProvider, upstream_id: str) -> str:
provider.expect(_response(upstream_id))
created: Final = guarded.request("POST", "/v1/responses", {"model": _MODEL, "input": _input(), "store": True})
assert created.status_code == 200, created.text
(upstream,) = provider.received()
assert upstream.target.endswith("/responses"), upstream.target
return string_value(_JSON_OBJECT.validate_json(created.content)["id"])
def _lifecycle(guarded: Gateway, provider: SharedProvider, operation: str) -> tuple[httpx.Response, str]:
if operation == "compact":
provider.expect(_response(f"resp_{uuid.uuid4().hex}"))
return guarded.request(
"POST", "/v1/responses/compact", {"model": _MODEL, "input": _input()}
), "/responses/compact"
upstream_id: Final = f"resp_{uuid.uuid4().hex}"
managed_id: Final = _create(guarded, provider, upstream_id)
provider.expect(_deleted(upstream_id) if operation == "delete" else _response(upstream_id))
if operation == "get":
return guarded.request("GET", f"/v1/responses/{managed_id}"), f"/responses/{upstream_id}"
if operation == "delete":
return guarded.request("DELETE", f"/v1/responses/{managed_id}"), f"/responses/{upstream_id}"
return guarded.request("POST", f"/v1/responses/{managed_id}/cancel"), f"/responses/{upstream_id}/cancel"
@pytest.mark.parametrize("operation", ["get", "compact", "delete", "cancel"])
def test_responses_lifecycle_answers_200_with_a_during_call_guardrail_on(
guarded: Gateway, provider: SharedProvider, operation: str
) -> None:
response, upstream_target = _lifecycle(guarded, provider, operation)
assert response.status_code == 200, response.text
(upstream,) = provider.received()
assert upstream.target.endswith(upstream_target), upstream.target

11
tests/integration/database/test_skill_submissions.py
View file

@ -134,6 +134,8 @@ async def test_approval_commits_version_archive_history_and_review(pending_updat
assert current is not None
published_manifest: Final = {
**case.proposal.manifest,
"_litellm_review": {"approved_by": "integration-reviewer", "security_scan_passed": False},
"_litellm_published_by": "integration-reviewer",
"source": {
**TypeAdapter(dict[str, str]).validate_python(case.submission.proposal.manifest["source"]),
"url": f"https://skills.example.test/claude-code/plugins/{case.original.name}/archive/"
@ -148,17 +150,22 @@ async def test_approval_commits_version_archive_history_and_review(pending_updat
)
metadata: Final = await case.publications.get_metadata(case.original.name)
assert metadata is not None
assert metadata.created_by == before.created_by == case.original.created_by
assert metadata.created_at == before.created_at
assert metadata.updated_at is not None and before.updated_at is not None
assert metadata.updated_at > before.updated_at
assert await case.publications.get_content(metadata) == case.proposal.content
history: Final = await case.publications.versions(metadata, 10, 0)
assert tuple((version.version, version.description, version.archive_available) for version in history) == (
("1.0.1", case.proposal.description, True),
("1.0.0", case.original.description, True),
)
assert history[0].published_by == "integration-reviewer"
assert history[1].published_by == case.original.created_by
for version, publication, manifest in zip(
history, (case.proposal, case.original), (published_manifest, case.original.manifest), strict=True
history, (case.proposal, case.original), (published_manifest, {**case.original.manifest, "_litellm_published_by": case.original.created_by}), strict=True
):
assert version.manifest == {**manifest, "version": version.version}
assert version.published_by == publication.created_by
assert await case.publications.version_content(metadata, version.id) == publication.content

Some files were not shown because too many files have changed in this diff Show more