Backport of #46712 to stable/1.106.x.
Cherry-picked from 9c62573005 (litellm_dashboard_only_gzip). The line never took #46362, so the OFF_LOOP_SIZE_BYTES hunks resolve to the pick, which removes the constant.
Backport adaptation for rc/1.105.0. main merges a pass-through caller's metadata and litellm_metadata into the logging metadata only when they are dicts. This line merged any value, so a list of pairs could carry standard_logging_guardrail_information past the guardrail strip from #59.
Backport of #59 to rc/1.105.0.
Cherry-picked from 79e48b9b19 (main). This line has no client pricing strip on pass-through, so only the guardrail strip is ported there.
metadata and litellm_metadata leave the proxy-only failure-log allowlist, so a rejected request can no longer point its failure log at its own Langsmith or Langfuse host through nested metadata.
(cherry picked from commit 30f6715f480ee7e2854514fe53b91d1b16e1be03)
The component runtime stages copied the builder's whole /app, which is the
entire repository plus build output: six lockfiles, helm, terraform, docs,
.env.example and the Rust build tree. Measured at runtime with an audit hook
on a booted container, the gateway reads only gateway/, litellm/ and
enterprise/ from /app, the backend only backend/, litellm/ and enterprise/,
and the migrations job only litellm/ and run.py. The pyproject.toml read is
prisma-python's optional [tool.prisma] lookup, which ours does not define
Copy just those, plus .venv, the entrypoint script and schema.prisma for the
gateway and backend. PYTHONPATH=/app and the in-Dockerfile asserts are
unchanged
Bump the pinned wolfi-base digest in every Wolfi Dockerfile to 360896ef, which
ships brotli 1.2.1-r1 and ca-certificates-bundle 20260909-r3. The previous
digest already carried libbrotli 1.2.0-r6 as an OpenSSL dependency, and
`apk add --no-cache` never upgrades a package the base already has
Move the UI image to nginx 1.31.8-alpine3.24, whose CA bundle is the 20261020
Mozilla set, and upgrade brotli-libs in its runtime stage since no nginx
digest ships 1.2.1 yet
Move the liteadmin-builder pin from litellm-admin-agent ef501e9 to
5661c80, which ships certifi 2026.10.19 and aiohttp 3.14.5 in the
/opt/liteadmin venv. That certifi drops emSign ECC Root CA - G3, whose
intermediates were revoked; the earlier bundled-CA updates did not
reach this venv because it installs from the agent's own lock file.
The only other change in ef501e9..5661c80 is the AgentChat bump from
litellm-admin-agent#24 (Slack follow-up routing with models that reject
structured output).
(cherry picked from commit 755fdc570d)
Redoes #48110 on this line. The lock moves mlflow, mlflow-skinny and mlflow-tracing to 3.17.2, pypdf to 6.21.2 and setuptools to 84.1.0 inside their existing ranges. mlflow 3.17.2 and pypdf 6.21.2 are still inside the 3-day exclude-newer window, so they get their own exclude-newer-package cutoffs, matching main. The lock was regenerated with uv 0.11.7
vitest goes to 4.1.12 and the lock moves vite from 8.3.0 to 8.3.4, along with the rolldown, postcss and nanoid releases that vite 8.3.4 requires, matching main. chai and tinyrainbow stay on their current versions because nothing needs them to move
next goes to 16.4.1, zod to 4.6.6, vite to 7.3.7, and vitest and @vitest/ui to 4.1.12. @vitest/coverage-v8 moves to 4.1.12 as well because it pins vitest to its own version as a peer. A top-level zod override keeps every consumer on the root zod, matching main
The lock only moves these packages and their own @next and @vitest entries, which match the entries on main. A plain npm install also pulled rollup, chai, std-env and a few other dev-only packages to newer releases that nothing required, so those stay on their current versions. sharp is already on 0.35.5 and does not move
Move the OpenTelemetry API, SDK and OTLP exporter pins to 1.45.1 and the FastAPI instrumentation to 0.66b1, which the exporter and mount changes in the previous commit rely on. logfire goes to 5.2.0, and Pillow goes to 13.0.0 on Python 3.11 and newer while 3.10 stays on 12.3.0, matching main
The lock also moves GitPython to 3.2.1, graphql-core to 3.2.12, Brotli to 1.2.1 and pypdf to 6.21.1 within their existing ranges. Brotli 1.2.1 is still inside the 3-day exclude-newer window, so it gets its own exclude-newer-package cutoff. The lock was regenerated with uv 0.11.7 so it stays on revision 3
* fix(deps): upgrade Python dependencies
* fix(deps): lock patched Python dependency versions
* fix(otel): preserve JSON export with the updated SDK
* test(otel): cover JSON export with the updated SDK
* test(otel): update SDK log records and worker discovery
* fix(ui): align Lens peer dependency with patched Next.js
* fix(otel): hand the AgentOps exporter a session it owns for the JWT header
OpenTelemetry 1.45 moved the OTLP HTTP exporter's requests.Session behind a
transport, so writing the minted JWT to the exporter's private _session raised,
was swallowed, and every AgentOps batch went out unauthenticated. The exporter
now creates the session, passes it through the public session= argument and
sets the Authorization header on it
The tests now drive a real export, serving the token endpoint with respx and
capturing the OTLP POST with requests_mock, instead of reading SDK internals
* fix(otel): skip FastAPI instrumentation once the app has started
opentelemetry-instrumentation-fastapi 0.66b1 wraps build_middleware_stack instead
of calling add_middleware, so instrumenting an app whose middleware stack is
already built no longer raises. The call silently did nothing while we still
registered the global response propagator. Check the built stack up front and
skip both, which is what the existing test expects
* test(otel): assert exported requests and span flags instead of SDK internals
OpenTelemetry 1.45 dropped the exporter's private _headers and sets the W3C
random-trace-id flag on new traces, so traceresponse ends in -03. The Langtrace
and Langfuse tests now export through requests_mock and check the URL and headers
the collector receives, and the traceresponse tests expect the server span's own
trace flags
* fix(deps): bump dashboard zod to 4.6.6 and make the vendored Lens use it
zod 4.6.5 is flagged by the dependency scan and blocks osv-scan on every PR. A
root bump alone leaves the vendored Lens tarball, which pins zod 4.6.5 exactly,
on its own nested copy, so a top-level zod override points every consumer at the
root version and the lock carries a single zod 4.6.6
* test(ui): stub the tag summary fetch the client panel retry refreshes
Retrying the model breakdown refetches /tag/summary, which this integration test
left on the real network. When that request failed before the assertion, the
panel switched to its summary error and unmounted the model row, so the test
passed or failed by timing
* fix(deps): drop the duplicated Lens override from the dashboard package.json
* style(ui): format the client panel fetch stub
---------
Dependency files (pyproject.toml, uv.lock and the dashboard package.json and package-lock.json) were left out of this pick and re-derived on the 1.106 line in the following commits
The ClientUsagePanel integration test does not exist on this line, so its hunk was dropped
The traceresponse hunks in test_otel_v2_mount.py were dropped because those tests do not exist on this line
Co-authored-by: Yuneng Jiang <yuneng@berri.ai>
(cherry picked from commit 8f9894fbd6)
* fix(security): bump grpcio and boto3 so their bundled CA files drop the compromised eMudhra roots
grpc ignores SSL_CERT_FILE and verifies every channel against its own bundled roots.pem. In 1.78.0 that file still trusts emSign ECC Root CA - G3 and AAA Certificate Services, so Vertex AI, Google KMS, Chirp STT and OTLP gRPC exporters (Arize) accept all 14 advisory chains. 1.84.1 is the first release whose roots.pem drops both roots.
botocore uses certifi when it is installed and falls back to its bundled cacert.pem otherwise. Through 1.43.116 that file still trusts AAA Certificate Services. Requiring boto3 1.43.117 pulls in botocore 1.43.117, the first release whose cacert.pem rejects all 14 advisory chains, so the fallback stays safe if certifi is ever absent
* fix(docker): provide OpenSSL 3 when generating Prisma engines
(cherry picked from commit 52166b51a1)
Update certifi, Rust trust roots, and the Docker CA bundle to remove emSign ECC Root CA - G3
Require the fixed certifi release in litellm-core and retain libssl3 in Docker runtimes for Prisma compatibility
Co-authored-by: shin-berri <shin-laptop@berri.ai>
(cherry picked from commit f2118fc767)
The bundled beta map stripped dangerous-tool-use-2026-09-03 for providers
main supports it on, so safeguards requests went upstream without the beta
whenever the proxy used the bundled map. The worker-SIGKILL chaos test needs
OwnedProxy.replacing_worker, which this line's integration harness lacks.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
agentcore/search and vertex_ai/semantic-ranker-default-004 are priced in main's map, so these tests follow main: the search test asserts the mapped per-query price and the custom-pricing rerank test uses an unmapped deployment name.
aiohttp 3.14.3 -> 3.14.5 (yarl 1.23.0 -> 1.25.1 with it), mlflow 3.15.0 -> 3.17.0 (mlflow-skinny and mlflow-tracing with it), claude-agent-sdk 0.1.44 -> 0.2.165 with its dev pin widened to main's ==0.2.165. Every moved version matches main's uv.lock.
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Backport of #47635 to stable/1.106.x
Cherry-picked from 2cba80cd0d (main)
* fix(logging): report pay-as-you-go rates for spilled over PTU requests without base_model
* fix(logging): keep the provider response model so spilled over PTU payloads price the served model
* fix(logging): keep a provider_response_model the response already carries
* fix(logging): read the carried provider_response_model through a typed adapter
---------
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Backport of #47655 to stable/1.106.x
Cherry-picked from 6b1f4ed46f (main)
* fix(proxy): bill every earlier timed-out retry attempt at its own deployment's model rate
* fix(router): read the retry record's base_model through the typed metadata helper
* fix(router): keep the four-record retry breadcrumb cap
* fix(router): carry a deployment's litellm_params base_model on its retry record
* chore(router): place the cast-ok reason on the cast line and list the base_model helper as covered through log_retry
---------
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Backport of #47648 to stable/1.106.x
Cherry-picked from 27efc387f7 (main)
