* fix(test): add missing mocks for test_streamable_http_mcp_handler_mock
The test was missing mocks for extract_mcp_auth_context and set_auth_context,
causing the handler to fail silently in the except block instead of reaching
session_manager.handle_request. This mirrors the fix already applied to the
sibling test_sse_mcp_handler_mock.
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
* fix(ci): route OpenAI models through chat completions in pass-through tests
The test_anthropic_messages_openai_model_streaming_cost_injection test fails
because the OpenAI Responses API returns 400 for requests routed through the
Anthropic Messages endpoint. Setting LITELLM_USE_CHAT_COMPLETIONS_URL_FOR_ANTHROPIC_MESSAGES=true
routes OpenAI models through the stable chat completions path instead.
Cost injection still works since it happens at the proxy level.
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
* fix(ci): fix assemblyai custom auth and router wildcard test flakiness
1. custom_auth_basic.py: Add user_role='proxy_admin' so the custom auth
user can access management endpoints like /key/generate. The test
test_assemblyai_transcribe_with_non_admin_key was hidden behind an
earlier -x failure and was never reached before.
2. test_router_utils.py: Add flaky(retries=3) and increase sleep from 1s
to 2s for test_router_get_model_group_usage_wildcard_routes. The async
callback needs time to write usage to cache, and 1s is insufficient on
slower CI hardware.
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
* ci: retrigger CI pipeline
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
* fix(mypy): use LitellmUserRoles enum instead of raw string in custom_auth_basic
Fixes mypy error: Argument 'user_role' has incompatible type 'str'; expected 'LitellmUserRoles | None'
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
* fix: don't close HTTP/SDK clients on LLMClientCache eviction (#22926)
* fix: don't close HTTP/SDK clients on LLMClientCache eviction
Removing the _remove_key override that eagerly called aclose()/close()
on evicted clients. Evicted clients may still be held by in-flight
streaming requests; closing them causes:
RuntimeError: Cannot send a request, as the client has been closed.
This is a regression from commit fb72979432. Clients that are no longer
referenced will be garbage-collected naturally. Explicit shutdown cleanup
happens via close_litellm_async_clients().
Fixes production crashes after the 1-hour cache TTL expires.
* test: update LLMClientCache unit tests for no-close-on-eviction behavior
Flip the assertions: evicted clients must NOT be closed. Replace
test_remove_key_closes_async_client → test_remove_key_does_not_close_async_client
and equivalents for sync/eviction paths.
Add test_remove_key_removes_plain_values for non-client cache entries.
Remove test_background_tasks_cleaned_up_after_completion (no more _background_tasks).
Remove test_remove_key_no_event_loop variant that depended on old behavior.
* test: add e2e tests for OpenAI SDK client surviving cache eviction
Add two new e2e tests using real AsyncOpenAI clients:
- test_evicted_openai_sdk_client_stays_usable: verifies size-based eviction
doesn't close the client
- test_ttl_expired_openai_sdk_client_stays_usable: verifies TTL expiry
eviction doesn't close the client
Both tests sleep after eviction so any create_task()-based close would
have time to run, making the regression detectable.
Also expand the module docstring to explain why the sleep is required.
* docs(AGENTS.md): add rule — never close HTTP/SDK clients on cache eviction
* docs(CLAUDE.md): add HTTP client cache safety guideline
* [Fix] Install bsdmainutils for column command in security scans
The security_scans.sh script uses `column` to format vulnerability
output, but the package wasn't installed in the CI environment.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: handle string callback values in prometheus multiproc setup
When callbacks are configured as a plain string (e.g., `callbacks: "my_callback"`)
instead of a list, the proxy crashes on startup with:
TypeError: can only concatenate str (not "list") to str
Normalize each callback setting to a list before concatenating.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* bump: version 1.82.2 → 1.82.3
* fix(test): update test_startup_fails_when_db_setup_fails for opt-in enforcement
The --enforce_prisma_migration_check flag is now required to trigger
sys.exit(1) on DB migration failure, after #23675 flipped the default
behavior to warn-and-continue.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(cost_calculator): use model name for per-request custom pricing when router_model_id has no pricing
When custom pricing is passed as per-request kwargs (input_cost_per_token/output_cost_per_token),
completion() registers pricing under the model name, but _select_model_name_for_cost_calc was
selecting the router deployment hash (which has no pricing data), causing response_cost to be 0.0.
Now checks whether the router_model_id entry actually has pricing before preferring it.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix(ci): handle inline table in pyproject.toml for litellm-proxy-extras version check
* fix: bump litellm-proxy-extras to 0.4.50 in pyproject.toml, requirements.txt, and poetry.lock
* fix(tests): set status_code=200 on JWT mocks and pass pii_tokens through data in presidio test
* fix(migrations): add ensure_project_id_verification_token migration
Ensures project_id column exists on LiteLLM_VerificationToken. The original
migration (20251113000000_add_project_table) adds this column, but may have
been skipped if LiteLLM_ProjectTable already existed and the migration was
resolved as idempotent. Uses IF NOT EXISTS for safety.
* bump: litellm-proxy-extras 0.4.45 → 0.4.46
- Remove pytest-retry from dev dependencies in pyproject.toml
- Add pytest-xdist as proper dev dependency (was only in pip install)
- Update CI workflow to reflect proper dependency management
- Prevents conflict between pytest-retry and pytest-rerunfailures
Having both pytest-retry and pytest-rerunfailures installed simultaneously
causes unpredictable behavior and excessive retries.
- Remove retries=20 and retry_delay=5 from pytest.ini_options
- These settings are for pytest-retry plugin (different from pytest-rerunfailures)
- Having both pytest-retry + pytest-rerunfailures causes excessive retries
- CI workflow now uses only pytest-rerunfailures with --reruns flag
- Reduce workers from 4 to 2 to avoid race conditions
- Add --reruns with 2-3 retries per test group
- Increase timeout from 15 to 20 minutes
- Add better test isolation
The test file test_e2e_pod_lock_manager.py requires fakeredis but it was
not declared as a dev dependency, causing import errors when the test
module is loaded.
This is a pre-existing issue that was exposed by better test coverage in
PR 21277 but is not caused by that PR.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
The test_db_schema_migration.py test requires pytest-postgresql but it was
missing from dependencies, causing import errors:
ModuleNotFoundError: No module named 'pytest_postgresql'
Added pytest-postgresql ^6.0.0 to dev dependencies to fix test collection
errors in proxy_unit_tests.
This is a pre-existing issue, not related to PR #21277.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Uvicorn 0.31.x falsely advertised ASGI spec_version "2.4" without
implementing send() raising OSError on disconnect. Starlette trusted
this and skipped its disconnect listener, causing generators to run
forever. Uvicorn 0.32.1 corrected this to "2.3", restoring native
disconnect detection. The monkey-patch is no longer needed.
Also adds fallback_response cleanup in stream_with_fallbacks and
moves inline import anyio to module level in streaming_handler.
jyeros