* fix(s3): add retry with exponential backoff for transient S3 503/500 errors
S3 occasionally returns 503 "Slow Down" during PUT operations when
request rates spike above partition limits. The current code makes a
single upload attempt via httpx — unlike boto3, httpx has no built-in
retry for transient S3 errors. Failed uploads permanently lose the
request's audit/logging data.
Add exponential backoff retry (3 attempts, 1s/2s delays) for S3
500/503 responses in both async_upload_data_to_s3 and
upload_data_to_s3. Logs a warning on each retry with the S3 object
key for observability.
In production we observed ~18 permanent S3 upload failures per day
(124 over 7 days) — all transient 503s that would have succeeded on
a single retry.
* test(s3): add unit tests for S3 upload retry logic
Tests cover:
- Async retry on 503 (succeeds on second attempt)
- Async retry on 500
- Exhausted retries on persistent 503 (calls handle_callback_failure)
- No retry on 4xx errors (403)
- Sync retry on 503
* style(s3): move time import to module level
Address review feedback: move `import time` from inside
upload_data_to_s3 to the top-level imports per project style guide.
* fix(logging): preserve proxy key-auth metadata on /v1/messages Langfuse traces
update_from_kwargs() overwrites proxy metadata (user_api_key_hash, etc.)
with Anthropic's native metadata when both exist. Merge instead of replace.
* fix(test): update stale assertion for new metadata merge semantics
* test: add explicit conflict-resolution test for metadata merge
* feat(containers): Azure container routing, managed IDs, and delete response wire format
- Add AzureContainerConfig and safe URL joining for paths with api-version query
- Encode/decode managed container IDs in responses, streaming, and proxy handlers
- Accept OpenAI delete response object literal container.file.deleted
- Tests for Azure URL regression and DeleteContainerFileResponse parsing
Made-with: Cursor
* fix(responses): gate response id update on parsed_chunk having response
Delta stream events do not include a response body; Mock-based tests
(and any truthy synthetic .response on transforms) must not trigger
_update_responses_api_response_id_with_model_id. Fixes
test_stop_async_iteration_not_logged_as_failure (TypeError: Mock not iterable).
Made-with: Cursor
* feat(containers): encode container IDs in SDK responses for routing
- Add ContainerRequestUtils.encode_container_id_in_response utility
- Encode container_id in create/retrieve/delete responses (SDK path)
- Fix streaming iterator: gate response ID update on parsed_chunk key
- Follows responses API pattern (encode after handler, not in handler)
Made-with: Cursor
* fix(containers): module-level imports and managed cntr_ ID encoding
- Move ResponsesAPIRequestUtils imports to module scope (utils, main, handler_factory).
- Serialize absent model_id as empty segment instead of literal None; decode empty
and legacy "None" segments as missing for router affinity.
- Add unit tests for build/decode round-trip and legacy IDs.
Made-with: Cursor
* fix(containers): decode managed IDs in endpoint_factory SDK path
- Add decode_managed_container_id_for_request in containers/utils and reuse from main.
- Strip LiteLLM cntr_ wrappers before generic_container_handler (64-char API limit).
- Resolve provider for logging/errors; add unit test for decode helper.
- Use resolved_custom_llm_provider after decode for mypy-safe provider typing.
Made-with: Cursor
* Fix p1 concern
* Fix p1 concern
1. exclude-newer: change from absolute "2026-04-10" to relative "3 days".
All pinned deps were published before the 3-day cutoff. Re-locked so
uv lock --check passes in test-mcp.yml and test-linting.yml.
2. test_eager_tiktoken_load: run all 10 env var values in a single
subprocess instead of spawning 10 separate processes. Each cold
import litellm takes ~78s on CI, so the old loop took ~13 min on a
single xdist worker. Now takes ~78s total.
3. proxy-db remaining timeout: increase from 20 to 30 minutes. The
remaining group has 51 test files and was consistently timing out at
71% across all branches (pre-existing issue, not migration-related).
When modify_params is true, Bedrock Converse setup no longer prepends or
appends the default user message if the boundary assistant turn has
prefix: true, so OpenAI-style assistant prefill reaches the API unchanged.
Made-with: Cursor
* feat(guardrails): optional skip system message in unified guardrail inputs
Made-with: Cursor
* feat(dashboard): skip_system_message_in_guardrail in guardrail UI
Add a tri-state control (inherit / yes / no) when creating or editing
guardrails so admins can set litellm_params.skip_system_message_in_guardrail
without YAML. Table edit merges existing litellm_params before PUT to avoid
wiping content-filter and other provider fields.
Document the dashboard flow in the guardrails quick start with a screenshot.
Made-with: Cursor
* fix(guardrails): type structured_messages as AllMessageValues for mypy
Use AllMessageValues in openai_messages_without_system and cast adapter
request messages so GenericGuardrailAPIInputs matches TypedDict.
Made-with: Cursor
* fix(responses): map refusal stop_reason to incomplete status in streaming
Fixes streaming responses API translation where Anthropic's stop_reason="refusal"
was incorrectly translated to status="completed" instead of "incomplete".
Root cause: build_base_response was unconditionally overwriting finish_reason
with None from later chunks, losing the terminal content_filter value.
Changes:
- streaming_chunk_builder_utils: skip None finish_reason values in build_base_response
- streaming_iterator: snapshot chunks before returning pending events (sync path)
- streaming_handler: treat usage-only chunks as meaningful content
- transformation: map finish_reason=refusal to status=incomplete
- tests: add regression tests for refusal handling
Made-with: Cursor
* Fix test
Add test_proxy_server_cors_invariant which directly imports and checks the
module-level origins and allow_cors_credentials variables in proxy_server.py.
This catches any future drift between the mirror helper and the real code.
- proxy_server.py: disable allow_credentials when allow_origins=['*'] (wildcard
+ credentials is a browser security misconfiguration). Add LITELLM_CORS_ORIGINS
env var to configure explicit allowed origins.
- create_views.py: narrow broad 'except Exception' to only catch genuine
'view does not exist' errors; re-raise all other DB errors (auth, connection,
etc.) that were previously silently swallowed.
- spend_log_cleanup.py: validate execute_raw() return type is int before using
it as a deletion count; break loop safely on unexpected types to prevent
infinite deletion loops.
1. Cap requires-python to <3.14 — no deps ship 3.14 wheels yet, and
uv's cross-version resolver fails on the Python 3.14 split.
2. Change exclude-newer from relative "30 days" to absolute "2026-04-10"
so the lockfile stays reproducible. The relative date caused
cryptography==46.0.7 (published April 8) to fall outside the window.
3. Parametrize test_eager_loading_env_var_values instead of looping —
with xdist the 6 subprocess cases can run in parallel instead of all
running sequentially on one worker (~13 min → ~2 min).
Also removed redundant case variants (Yes/YES/On/ON) that test the
same str_to_bool code path.
- Changed the import path for `upload_file_to_storage_backend` in test files to reflect the new module structure.
- Ensured consistency in mocking for storage backend service tests.
The raw SQL queries in spend_management_endpoints.py, spend_tracking_utils.py,
and analytics_endpoints.py cast date params to ::timestamptz while comparing
against the plain-timestamp "startTime" column. Postgres resolves the type
mismatch by promoting the column using the DB session timezone, which drifts
the filter window and date_trunc buckets whenever session TZ is not UTC —
silently dropping rows at UTC day boundaries and, for narrow windows, losing
rows entirely.
Wraps every such comparison with `AT TIME ZONE 'UTC'` so the param side
resolves to a plain timestamp matching the column type. Both sides end up
as plain timestamp, Postgres does no implicit conversion, and session TZ
plays no role in the query. The fix is constant-foldable so the existing
startTime index (PR #17504) remains usable.
Also marks strptime-produced datetimes as tz-aware UTC at the call sites
for intent clarity and consistency with parse_date.
Fixes#22529 (Logs page missing recent rows under non-UTC session TZ) and
the Global Usage single-day-returns-two-days symptom reported internally.
- Added validation to ensure credentials include a custom LLM provider before routing.
- Cleaned up type casting for better readability.
- Introduced a new test to verify behavior when a non-OpenAI provider is used, ensuring proper handling of streaming responses.
- Updated imports to include necessary modules for testing.
- Updated `FileContentStreamingHandler` to utilize `custom_llm_provider` from credentials for routing.
- Added error handling for missing `custom_llm_provider` in credentials.
- Introduced new tests to validate streaming behavior with routed providers and non-OpenAI providers.
- Cleaned up imports and ensured proper type casting for improved clarity.
- Static Methods for Streaming Handler Function
- Remove the afile_content_streaming wrapper function. Enabled with a stream boolean in afile_content
- Cleaned up test cases after refactor
- Removed unused imports and streamlined type hints in `litellm/utils.py` and `litellm/files/main.py`.
- Moved `FileContentStreamingResult` to a new `litellm/files/types.py` for better organization.
- Updated `FileContentStreamingResponse` in `litellm/files/streaming.py` to include asynchronous close methods and improved logging capabilities.
- Enhanced tests to ensure proper closure of streaming iterators in `tests/test_litellm/llms/openai/test_openai_file_content_streaming.py` and `tests/test_litellm/proxy/openai_files_endpoint/test_files_endpoint.py`.
- Route multipart forwarding on forward_multipart instead of empty _parsed_body
so litellm_logging_obj no longer forces json= for file uploads.
- Remove custom_body from pass-through endpoint signatures; FastAPI treated it
as a JSON body and rejected multipart before the handler ran. Bedrock passes
JSON via request.state (LITELLM_PASS_THROUGH_CUSTOM_BODY_STATE_KEY).
- Use build_request + send(stream=True) for streaming multipart; httpx 0.28
AsyncClient.request does not accept stream=.
- Add regression test for non-empty _parsed_body multipart path; update Bedrock
custom-body test and query-params test for forward_multipart.
Made-with: Cursor
Non-admins previously skipped RBAC when prisma_client was None but could
still read payloads from custom loggers. Return 403 unless admin view.
Add test_ui_view_request_response_forbids_non_admin_without_db.
Made-with: Cursor
- Drop module-level common_utils import; import team helpers inside callers.
- Inline admin-view role check in _is_admin_view_safe to break import cycle.
- Require non-null row.user before treating spend log as owned by the key
(fixes None==None bypass for service keys).
- Document deferred proxy_server imports in _get_permitted_team_ids_for_spend_logs.
- Update tests (common_utils patches, regression test, ruff cleanups).
Made-with: Cursor
- Introduced `afile_content_streaming` and `file_content_streaming` functions in `litellm/files/main.py` to handle asynchronous and synchronous file content streaming.
- Added `FileContentStreamingResponse` class in `litellm/files/streaming.py` to manage streaming responses with logging capabilities.
- Updated OpenAI API integration in `litellm/llms/openai/openai.py` to support new streaming methods.
- Enhanced file content retrieval in `litellm/proxy/openai_files_endpoints/files_endpoints.py` to route requests for streaming.
- Added unit tests for the new streaming functionality in `tests/test_litellm/llms/openai/test_openai_file_content_streaming.py` and `tests/test_litellm/proxy/openai_files_endpoint/test_files_endpoint.py`.
- Refactored type hints and imports for better clarity and organization across modified files.
* build: migrate packaging metadata to uv
* ci: move automation and local tooling to uv
* docker: migrate image builds and runtime setup to uv
* docs: update install and deployment guidance for uv
* chore: align auxiliary scripts and tests with uv
* test: harden test_litellm isolation
* fix: keep release and health check images self-contained
* build: pin uv tooling and health check deps
* test: isolate bedrock image request formatting from suite state
* test: cover sandbox executor requirements flow
* ci: fix circleci no-op command steps
* ci: fix circleci publish workflow parsing
* fix: stabilize remaining uv migration CI checks
* ci: increase matrix test timeout headroom
* fix: restore published docker and license coverage
* fix: restore proxy runtime build parity
* fix: restore proxy extras parity and venv migrations
* ci: persist uv path across circleci steps
* fix: keep psycopg binary in default test env
* docker: preserve prisma cache across stages
* test: run local proxy checks through uv python
* build: restore runtime deps moved into ci
* build: refresh uv lock after upstream merge
* fix: restore module import in test_check_migration after merge
The conflict resolution imported only the function but the test body
references check_migration as a module throughout.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: revert dependency promotions, remove nodejs-wheel-binaries, fix Docker layer caching
- Move google-generativeai, Pillow, tenacity back to ci group (they are
lazily imported and bloat the base SDK install needlessly)
- Remove nodejs-wheel-binaries from extra_proxy and proxy-dev (redundant
in Docker where system Node.js is already installed via apk)
- Remove all nodejs-wheel node replacement and venv npm patching blocks
from Dockerfiles since the wheel is no longer installed
- Add --no-default-groups to CodSpeed benchmark workflow so the benchmark
environment matches the old minimal pip install footprint
- Apply standard uv two-phase Docker pattern: copy metadata first, install
deps (cached layer), then copy source and install project
- Replace CircleCI enterprise no-op with proper uv sync command
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* chore: regenerate uv.lock after removing nodejs-wheel-binaries
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(ci): use cache/restore instead of cache to prevent cache poisoning
The old workflow used actions/cache/restore (read-only). The uv migration
changed it to actions/cache (read-write), which zizmor flags as a cache
poisoning risk. Restore the safer read-only variant.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(ci): disable setup-uv built-in cache to silence cache-poisoning alert
The setup-uv action enables caching by default, which zizmor flags as a
cache poisoning risk. Disable it since we already use a read-only
cache/restore step.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(ci): disable setup-uv cache in publish workflow
Silences zizmor cache-poisoning alert. Publishing workflow runs
infrequently on protected branches so caching adds no real benefit.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(test): remove duplicate verbose_logger mock in test_check_migration
The logger was patched twice — first via mocker.patch() then via
mocker.patch.object(autospec=True). The second call fails because
autospec cannot inspect an already-mocked attribute. Remove the
redundant first patch.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(ci): free disk space before Docker build in test-server-root-path
The Dockerfile.non_root build ran out of disk on the CI runner. Remove
Android SDK, .NET, Boost, and GHC toolchains (~12GB) to free space.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
