* 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.
1. check_code_and_doc_quality: install helm before running helm lint
(Docker image cimg/python:3.11 doesn't include helm)
2. proxy_store_model_in_db_tests: skip MCP tests on Python < 3.10
since MCP module isn't available and functions inside the
`if MCP_AVAILABLE:` block don't exist as module-level attributes
1. check_code_and_doc_quality: add PLR0915 ignore for sandbox_executor.py
2. auth_ui_unit_tests: add prisma generate step (entrypoint.sh only runs
migration, not client generation)
3. proxy_store_model_in_db_tests: move does_mcp_server_exist outside
`if MCP_AVAILABLE:` so it's importable on Python < 3.10
4. build_and_test: fix datetime.fromisoformat('...Z') on Python 3.9
(Z suffix support was added in 3.11)
5. proxy_logging_guardrails: fix container name typo my-app-2 -> my-app-3
6. upload-coverage: use `uv tool run` instead of `uv run --with` to avoid
resolving the full workspace (which fails for Python 3.14)
- 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`.
- Pin `pip==26.0.1` and `uv==0.10.9` in CCI jobs that used unpinned
`pip install uv` (redis_caching_unit_tests, ui_e2e_tests)
- Replace bare `prisma generate` with `uv run --no-sync prisma generate`
in proxy_part1, proxy_part2, and enterprise test jobs
- Remove duplicate `check=True` kwarg in test_basic_python_version.py
that caused TypeError with `_run_uv()` helper
