The test_end_to_end_rerank_flow mock for _ensure_access_token was not
being applied because conftest reloads litellm, causing the
VertexAIRerankConfig class to be a different object than what's patched.
Fix: Reload the transformation module in setup_method and re-import the
class to ensure the patch targets the same class object used by tests.
The tests were making real API calls instead of using mocks because
conftest.py reloads litellm at module scope, causing the HTTPHandler
class reference in the HuggingFace embedding handler to become stale.
The patches were applied to the new class, but the handler used the old one.
Fix: Add a reload_huggingface_modules fixture that reloads the relevant
modules BEFORE the mock fixtures apply their patches. This ensures all
references point to the same class object.
The test was making real API calls instead of using mocks because the
conftest.py reloads litellm at module scope, causing stale module
references. The mock was patching the old reference while the actual
code used the new one.
Fix: Reload litellm.containers.main inside the test to get a fresh
reference to base_llm_http_handler, then re-import create_container
after the reload.
The setup_and_teardown fixture was failing with "ImportError: module
litellm not in sys.modules" during parallel test execution. This occurs
because another worker might have removed/modified litellm from
sys.modules before this test tries to reload it.
Fix: Check if litellm is in sys.modules before attempting reload.
- Reload litellm_pre_call_utils module inside test to get fresh litellm reference
- Use string-based patch("litellm.model_group_settings") instead of patch.object
- These changes ensure the patch targets the correct module after conftest reloads litellm
Fix several tests that fail in CI due to parallel test execution and
module reloading in conftest.py.
1. test_empty_assistant_message_handling:
- Use patch.object on factory_module.litellm instead of direct assignment
- Ensures the correct litellm reference is modified after conftest reloads
2. test_embedding_header_forwarding_with_model_group:
- Use patch.object on pre_call_utils_module.litellm instead of direct assignment
- Same fix for module reloading issue
3. test_embedding_input_array_of_tokens:
- Move mock inside test function (after fixture initializes router)
- Add skip condition if llm_router is None
- Fixes "AttributeError: None does not have 'aembedding'" in parallel execution
Root cause: conftest.py reloads litellm at module scope, which can cause:
- Different litellm references between test code and library code
- Global state (like llm_router) being None at decorator execution time
- isinstance checks failing due to class identity mismatches
1. test_bedrock_converse_budget_tokens_preserved:
- Fixed mocking at the correct level (litellm.acompletion instead of client.post)
- The previous mock didn't work because the code runs through run_in_executor
and the passed client parameter was not being used
2. test_error_class_returns_volcengine_error:
- Changed isinstance check to class name comparison
- This avoids issues when module reloading (in conftest.py) causes class
identity mismatches during parallel test execution
1. test_acompletion_with_mcp_streaming_metadata_in_correct_chunks:
- Moved stream consumption inside patch context to avoid real API calls
- The previous implementation had assertions outside the `with patch(...)`
block, causing real OpenAI API calls when consuming the stream
2. TestCheckResponsesCost tests:
- Added skip condition when litellm_enterprise module is not available
- These tests import from litellm_enterprise.proxy.common_utils.check_responses_cost
which is only available in the enterprise version
The test_sso_key_generate_shows_deprecation_banner test was failing in CI
with a 403 Forbidden error because the SSO endpoint checks for premium_user
at line 297 in ui_sso.py.
The fix adds a monkeypatch for premium_user at its source location
(litellm.proxy.proxy_server.premium_user) to bypass the enterprise check
during testing.
Fixes the intermittent test failure where the endpoint would return 403
instead of the expected 200 status code.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit addresses two issues:
1. **Merge conflict resolution**: Resolved merge conflict in litellm/integrations/opentelemetry.py
that was preventing imports from working. The conflict was in the OpenTelemetry SDK
LogRecord import section.
2. **Test flakiness fix**: Fixed intermittent failures in test_bedrock_converse_budget_tokens_preserved
by properly configuring mock objects to avoid unawaited coroutine warnings.
The test was failing in CI with "Expected 'post' to have been called once. Called 0 times."
The root cause was improper mock setup where AsyncMock was creating async child methods
(raise_for_status, json) that returned unawaited coroutines, causing unreliable behavior
across different Python versions and test environments.
**Changes:**
- Set raise_for_status() and json() as explicit MagicMock instances on the response
- Use AsyncMock explicitly for the post() method via patch.object's 'new' parameter
- This ensures response methods are synchronous while the HTTP call remains async
**Testing:**
- Test now passes consistently across 5 consecutive runs
- RuntimeWarnings about unawaited coroutines eliminated (18 warnings → 16 warnings)
- Request JSON verification shows budget_tokens correctly preserved
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
The manual sys.modules restoration code was redundant because
patch.dict.stop() automatically handles the cleanup. This simplifies
the tearDown method and removes the now-unused _original_langfuse_module
instance variable.
Addresses review comment: https://github.com/BerriAI/litellm/pull/21214#pullrequestreview-3802348462
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Fixes test_log_langfuse_v2_handles_null_usage_values flaky test failure
by properly cleaning up sys.modules['langfuse'] in tearDown.
Changes:
- Store original langfuse module in setUp before mocking
- Restore original or remove mock in tearDown to prevent state pollution
- Remove invalid print_verbose parameter from log_event_on_langfuse
Root Cause:
The tearDown method was not cleaning up sys.modules['langfuse'] after
each test, causing mock state to leak between tests. This caused
intermittent failures in CI, especially when tests run in parallel or
in different orders.
Impact:
This test has a long history of flakiness with multiple attempted fixes
(#20475, #17599, #17594, #17591, #17588). The missing sys.modules cleanup
was the underlying issue causing continued failures despite those patches.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Allow passing enable_json_schema_validation as a parameter to completion()
and acompletion() instead of only relying on the global
litellm.enable_json_schema_validation flag. The per-request value takes
priority when provided; otherwise falls back to the global (backward
compatible). This makes JSON schema validation safe for concurrent usage
in FastAPI and other multi-threaded environments.
Address three additional root causes that prevented connection cleanup
on client disconnect: Starlette/Uvicorn disconnect detection gap,
content= vs stream= no-op wrapper in aiohttp transport, and anyio
CancelledError interrupting cleanup awaits.
- Add `definitions` handling alongside `$defs` in schema normalization
(older JSON Schema drafts use `definitions` instead of `$defs`)
- Fall back to tool-call approach when `response_format: {type: json_object}`
has no explicit schema, since the native API requires one
- Add tests for both cases
* fix(content_filter.py): fix filter on toxic keywords
* feat: improve toxic/abusive language detection
* fix: additional improvements to nsfw filters
* feat: more improvements to nsfw filter
* feat(content_filter.json): add new australia specific nsfw content filter
ensure complete coverage for australia nsfw
* fix: cleanup policy templates
* fix(index.tsx): alert notice
* fix(index.tsx): add disclaimer notice
* feat(harmful_child_safety.yaml): new child safety content filter
ensure we catch inappropriate, child-specific content
* feat(policy_templates.json): add child safety and self harm filters
* fix(content_filter.py): improve racial bias filter to use a similar identifier + block word pattern and cover a wider range of ethnicities
* feat(policy_templates.json): add racial bias to nsfw policy template
* feat: add json content viewer
* fix(model_cost): add missing supports_system_messages and supports_tool_choice to bedrock/moonshotai.kimi-k2.5
* fix(streaming): ensure role=assistant is set on first streaming chunk via strip_role_from_delta
* fix(vertex_ai): ensure role=assistant on first streaming chunk for Llama models
Add VertexAILlama3StreamingHandler that injects role='assistant' into the
first streaming chunk delta when the Vertex AI Llama API omits it.
