* fix: SSO PKCE support fails in multi-pod Kubernetes deployments
* fix: virutal key grace period from env/UI
* fix: refactor, race condition handle, fstring sql injection
* fix: add async call to avoid server pauses
* Update tests/test_litellm/proxy/management_endpoints/test_ui_sso.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix: add await in tests
* add modify test to perform async run
* Update tests/test_litellm/proxy/management_endpoints/test_ui_sso.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Update tests/test_litellm/proxy/management_endpoints/test_ui_sso.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix grace period with better error handling on frontend and as per best practices
* Update tests/test_litellm/proxy/management_endpoints/test_ui_sso.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix: as per request changes
* Update litellm/proxy/utils.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Fix errors when callbacks are invoked for file delete operations:
* Fix errors when callbacks are invoked for file operations
* Fix: pass deployment credentials to afile_retrieve in managed_files post-call hook
* Fix: bypass managed files access check in batch polling by calling afile_content directly
* Update tests/test_litellm/proxy/management_endpoints/test_ui_sso.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix: afile_retrieve returns unified ID for batch output files
* fix: batch retrieve returns unified input_file_id
* fix(chatgpt): drop unsupported responses params for Codex
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(chatgpt): ensure Codex request filters unsupported params
Co-authored-by: Cursor <cursoragent@cursor.com>
* Fix deleted managed files returning 403 instead of 404
* Add comments
* Update litellm/proxy/utils.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix: thread deployment model_info through batch cost calculation
batch_cost_calculator only checked the global cost map, ignoring
deployment-level custom pricing (input_cost_per_token_batches etc.).
Add optional model_info param through the batch cost chain and pass
it from CheckBatchCost.
* fix(deps): add pytest-postgresql for db schema migration tests
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>
* fix(test): replace caplog with custom handler for parallel execution
The cost calculation log level tests were failing when run with pytest-xdist
parallel execution because caplog doesn't work reliably across worker processes.
This causes "ValueError: I/O operation on closed file" errors.
Solution: Replace caplog fixture with a custom LogRecordHandler that directly
attaches to the logger. This approach works correctly in parallel execution
because each worker process has its own handler instance.
Fixes test failures in PR #21277 when running with --dist=loadscope.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix(test): correct async mock for video generation logging test
The test was failing with AuthenticationError because the mock wasn't
intercepting the actual HTTP handler calls. This caused real API calls
with no API key, resulting in 401 errors.
Root cause: The test was patching the wrong target using string path
'litellm.videos.main.base_llm_http_handler' instead of using patch.object
on the actual handler instance. Additionally, it was mocking the sync
method instead of async_video_generation_handler.
Solution: Use patch.object with side_effect pattern on the correct
async handler method, following the same pattern used in
test_video_generation_async().
Fixes test failure in PR #21277 when running with --dist=loadscope.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix(test): add cleanup fixture and no_parallel mark for MCP tests
Two MCP server tests were failing when run with pytest-xdist parallel
execution (--dist=loadscope):
- test_mcp_routing_with_conflicting_alias_and_group_name
- test_oauth2_headers_passed_to_mcp_client
Both tests showed assertion failures where mocks weren't being called
(0 times instead of expected 1 time).
Root cause: These tests rely on global_mcp_server_manager singleton
state and complex async mocking that doesn't work reliably with
parallel execution. Each worker process can have different state
and patches may not apply correctly.
Solution:
1. Added autouse fixture to clean up global_mcp_server_manager registry
before and after each test for better isolation
2. Added @pytest.mark.no_parallel to these specific tests to ensure
they run sequentially, avoiding parallel execution issues
This approach maintains test reliability while allowing other tests
in the file to still benefit from parallelization.
Fixes test failures exposed by PR #21277.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* Regenerate poetry.lock with Poetry 2.3.2
Updated lock file to use Poetry 2.3.2 (matching main branch standard).
This addresses Greptile feedback about Poetry version mismatch.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* Remove unused pytest import and add trailing newline
- Removed unused pytest import (caplog fixture was removed)
- Added missing trailing newline at end of file
Addresses Greptile feedback (minor style issues).
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* Remove redundant import inside test method
The module litellm.videos.main is already imported at the top of
the file (line 21), so the import inside the test method is redundant.
Addresses Greptile feedback (minor style issue).
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* Fix converse anthropic usage object according to v1/messages specs
* Add routing based on if reasoning is supported or not
* add fireworks_ai/accounts/fireworks/models/kimi-k2p5 in model map
* Removed stray .md file
* fix(bedrock): clamp thinking.budget_tokens to minimum 1024
Bedrock rejects thinking.budget_tokens values below 1024 with a 400
error. This adds automatic clamping in the LiteLLM transformation
layer so callers (e.g. router with reasoning_effort="low") don't
need to know about the provider-specific minimum.
Fixes#21297
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: improve Langfuse test isolation to prevent flaky failures (#21093)
The test was creating fresh mocks but not fully isolating from setUp state,
causing intermittent CI failures with 'Expected generation to be called once.
Called 0 times.'
Instead of creating fresh mocks, properly reset the existing setUp mocks to
ensure clean state while maintaining proper mock chain configuration.
* feat(s3): add support for virtual-hosted-style URLs (#21094)
Add s3_use_virtual_hosted_style parameter to support AWS S3 virtual-hosted-style URL format (bucket.endpoint/key) alongside the existing path-style format (endpoint/bucket/key).
This enables compatibility with S3-compatible services like MinIO and aligns with AWS S3 official terminology.
* Addressed greptile comments to extract common helpers and return 404
* Allow effort="max" for Claude Opus 4.6 (#21112)
* fix(aiohttp): prevent closing shared ClientSession in AiohttpTransport (#21117)
When a shared ClientSession is passed to LiteLLMAiohttpTransport,
calling aclose() on the transport would close the shared session,
breaking other clients still using it.
Add owns_session parameter (default True for backwards compatibility)
to AiohttpTransport and LiteLLMAiohttpTransport. When a shared session
is provided in http_handler.py, owns_session=False is set to prevent
the transport from closing a session it does not own.
This aligns AiohttpTransport with the ownership pattern already used
in AiohttpHandler (aiohttp_handler.py).
* perf(spend): avoid duplicate daily agent transaction computation (#21187)
* fix: proxy/batches_endpoints/endpoints.py:309:11: PLR0915 Too many statements (54 > 50)
* fix mypy
* Add doc for OpenAI Agents SDK with LiteLLM
* Add doc for OpenAI Agents SDK with LiteLLM
* Update docs/my-website/sidebars.js
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix mypy
* Update tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_server.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Add blog fffor Managing Anthropic Beta Headers
* Add blog fffor Managing Anthropic Beta Headers
* correct the time
* Fix: Exclude tool params for models without function calling support (#21125) (#21244)
* Fix tool params reported as supported for models without function calling (#21125)
JSON-configured providers (e.g. PublicAI) inherited all OpenAI params
including tools, tool_choice, function_call, and functions — even for
models that don't support function calling. This caused an inconsistency
where get_supported_openai_params included "tools" but
supports_function_calling returned False.
The fix checks supports_function_calling in the dynamic config's
get_supported_openai_params and removes tool-related params when the
model doesn't support it. Follows the same pattern used by OVHCloud
and Fireworks AI providers.
* Style: move verbose_logger to module-level import, remove redundant try/except
Address review feedback from Greptile bot:
- Move verbose_logger import to top-level (matches project convention)
- Remove redundant try/except around supports_function_calling() since it
already handles exceptions internally via _supports_factory()
* fix(index.md): cleanup str
* fix(proxy): handle missing DATABASE_URL in append_query_params (#21239)
* fix: handle missing database url in append_query_params
* Update litellm/proxy/proxy_cli.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix(mcp): revert StreamableHTTPSessionManager to stateless mode (#21323)
PR #19809 changed stateless=True to stateless=False to enable progress
notifications for MCP tool calls. This caused the mcp library to enforce
mcp-session-id headers on all non-initialize requests, breaking MCP
Inspector, curl, and any client without automatic session management.
Revert to stateless=True to restore compatibility with all MCP clients.
The progress notification code already handles missing sessions gracefully
(defensive checks + try/except), so no other changes are needed.
Fixes#20242
* UI - Content Filters, help edit/view categories and 1-click add categories + go to next page (#21223)
* feat(ui/): allow viewing content filter categories on guardrail info
* fix(add_guardrail_form.tsx): add validation check to prevent adding empty content filter guardrails
* feat(ui/): improve ux around adding new content filter categories
easy to skip adding a category, so make it a 1-click thing
* Fix OCI Grok output pricing (#21329)
* fix(proxy): fix master key rotation Prisma validation errors
_rotate_master_key() used jsonify_object() which converts Python dicts
to JSON strings. Prisma's Python client rejects strings for Json-typed
fields — it requires prisma.Json() wrappers or native dicts.
This affected three code paths:
- Model table (create_many): litellm_params and model_info converted to
strings, plus created_at/updated_at were None (non-nullable DateTime)
- Config table (update): param_value converted to string
- Credentials table (update): credential_values/credential_info
converted to strings
Fix: replace jsonify_object() with model_dump(exclude_none=True) +
prisma.Json() wrappers for all Json fields. Wrap model delete+insert
in a Prisma transaction for atomicity. Add try/except around MCP
server rotation to prevent non-critical failures from blocking the
entire rotation.
---------
Co-authored-by: Harshit Jain <harshitjain0562@gmail.com>
Co-authored-by: Harshit Jain <48647625+Harshit28j@users.noreply.github.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Ephrim Stanley <ephrim.stanley@point72.com>
Co-authored-by: Jay Prajapati <79649559+jayy-77@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Julio Quinteros Pro <jquinter@gmail.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Sameer Kankute <sameer@berri.ai>
Co-authored-by: mjkam <mjkam@naver.com>
Co-authored-by: Fly <48186978+tuzkiyoung@users.noreply.github.com>
Co-authored-by: Kristoffer Arlind <13228507+KristofferArlind@users.noreply.github.com>
Co-authored-by: Constantine <Runixer@gmail.com>
Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com>
Co-authored-by: Atharva Jaiswal <92455570+AtharvaJaiswal005@users.noreply.github.com>
Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
When using the Responses API (e.g., Azure gpt-5.1-codex-mini), the response.completed
event was always returning finish_reason='stop', even when the response contained
function_call items in its output. This caused agents like OpenCode to incorrectly
conclude the stream ended without tools to execute, breaking tool/function calling
workflows.
The fix inspects the response.output field in the response.completed event to determine
the correct finish_reason:
- 'tool_calls' when output contains function_call items
- 'stop' otherwise (text-only responses)
Added tests to verify:
- response.completed with function_call output returns finish_reason='tool_calls'
- response.completed with message-only output returns finish_reason='stop'
- response.completed with empty output returns finish_reason='stop' (backward compat)
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
* fix: preserve metadata for custom callbacks on codex/responses path (#21204)
- Use metadata or litellm_metadata when calling update_environment_variables
in responses/main.py so metadata is not overwritten by None on the
bridge path (completion -> responses API).
- Add tests for metadata in custom callback for codex models and for
litellm_metadata in aresponses().
Co-authored-by: Cursor <cursoragent@cursor.com>
* Update tests/test_litellm/responses/test_metadata_codex_callback.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
The test test_proxy_config_state_post_init_callback_call was failing with:
```
ValidationError: 2 validation errors for TeamCallbackMetadata
callback_vars.langfuse_public_key
Input should be a valid string [type=string_type, input_value=None, input_type=NoneType]
```
Root cause: The test uses environment variable references like
"os.environ/LANGFUSE_PUBLIC_KEY" which get resolved at runtime. In
parallel execution with --dist=loadscope, these environment variables
may not be set in all worker processes, causing the resolution to
return None, which fails Pydantic validation expecting strings.
Solution: Use monkeypatch to set the required environment variables
before the test runs. This ensures consistent behavior across all
test execution environments (local, CI, parallel workers).
Fixes test failure exposed by PR #21277.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Based on Greptile feedback:
- Removed autouse fixture (applied too broadly to unrelated tests)
- Removed setUpClass (redundant since setUp runs before every test)
- Kept module-level clear and setUp() method (sufficient for test isolation)
- Added blank line for proper formatting
The simplified approach still ensures test isolation under --dist=loadscope
while avoiding unnecessary complexity.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
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 _select_tokenizer_helper function is decorated with @lru_cache, which
causes test failures when tests run sequentially with --dist=loadscope.
Previous tests' cached results prevent from_pretrained from being called,
causing mock assertions to fail.
Implemented triple-layer cache clearing:
1. Module-level clear on import
2. Class-level clear in setUpClass
3. Function-level clear in setUp + pytest fixture
This ensures test isolation while allowing --dist=loadscope to provide better
overall CI stability (70% pass rate vs 40% without loadscope).
Fixes the intermittent failure in TestTokenizerSelection where
'from_pretrained' mock was never called due to cache hits.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
The test_vertex_ai_gpt_oss_simple_request and test_vertex_ai_gpt_oss_reasoning_effort
tests were failing in CI with 401 authentication errors. This was because the
vertexai module import was triggering authentication attempts even though the
_ensure_access_token method was mocked.
Added patch.dict('sys.modules', ...) to mock the vertexai module entirely,
preventing it from trying to authenticate when imported. This ensures tests
are fully isolated and don't attempt real API calls regardless of environment
variables or test execution order.
This follows the same pattern used in other Vertex AI tests and works in
combination with the autouse fixture that clears environment variables.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
The test_watsonx_gpt_oss_prompt_transformation was using return_value to mock
an async method (AsyncHTTPHandler.post), which doesn't work correctly with
async/await. This could cause intermittent failures in CI due to test ordering.
Changed to use side_effect with an async function (mock_post_func) to properly
mock the async post method, following the same pattern used in other async
tests like test_vertex_ai_gpt_oss_reasoning_effort.
This ensures the mock is always called correctly regardless of test execution
order or parallel test execution.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add autouse pytest fixture to clear Google/Vertex AI environment
variables before each test, preventing authentication errors in CI.
Previous tests may set GOOGLE_APPLICATION_CREDENTIALS or other Vertex
environment variables and not clean them up, causing this test to
attempt real Google authentication instead of using mocks.
This fix:
- Adds clean_vertex_env fixture with autouse=True
- Saves and clears Google/Vertex env vars before each test
- Restores them after each test
- Prevents "AuthenticationError: Request had invalid authentication
credentials" (401) in CI when run with other tests
Same fix pattern as PR #21268 (rerank) and PR #21272 (GPT-OSS).
Related: test was failing on PR #21217, but NOT caused by PR #21217
(which only modifies test_anthropic_structured_output.py). This is
another test isolation issue.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add autouse pytest fixture to clear Google/Vertex AI environment
variables before each test, preventing authentication errors in CI.
Previous tests may set GOOGLE_APPLICATION_CREDENTIALS or other Vertex
environment variables and not clean them up, causing this test to
attempt real Google authentication instead of using mocks.
This fix:
- Adds clean_vertex_env fixture with autouse=True
- Saves and clears Google/Vertex env vars before each test
- Restores them after each test
- Prevents "AuthenticationError: Request had invalid authentication
credentials" in CI when run with other tests
Test makes real API calls in CI without this fix, gets 401 error.
Locally fails with "No module named 'vertexai'" (expected).
Related: test was failing on PR #21217, but NOT caused by PR #21217
(which only modifies test_anthropic_structured_output.py). This is
another test isolation issue.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
PR #20813 changed the Anthropic schema filter to remove string and numeric constraints
(minLength/maxLength, minimum/maximum) per Anthropic API requirements, but forgot to
update the corresponding test.
The new behavior (per Anthropic SDK):
1. Remove unsupported constraints from schema (Anthropic API doesn't support them)
2. Add constraint info to description field (e.g., "Note: minimum length: 1")
**Changes:**
- Updated test to expect constraints REMOVED from schema
- Added assertions to verify constraints are added to description
- Updated docstring to explain the new behavior
**Testing:**
- ✅ test_other_constraints_preserved now passes
- ✅ All 4 tests in test_anthropic_structured_output.py pass
**Related:**
- Fixes test broken by PR #20813
- Aligns with Anthropic API requirements documented in commit 84934a7258
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Update test expectations to match the current code behavior where
reasoning_effort is transformed from a string to a dict with
'effort' and 'summary' fields.
The transformation happens in:
litellm/llms/anthropic/experimental_pass_through/adapters/handler.py:72-74
When reasoning_effort is a string like "minimal", it's converted to:
{"effort": "minimal", "summary": "detailed"}
The test was expecting just the string "minimal", causing it to fail.
Test now passes ✅
Related: test was failing on PR #21217, but NOT caused by PR #21217
(which only modifies test_anthropic_structured_output.py). This is a
pre-existing broken test that also fails on main branch.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add setup_method and teardown_method to clean up Google/Vertex AI
environment variables that may be left by previous tests.
Previous tests may set GOOGLE_APPLICATION_CREDENTIALS or other Vertex
environment variables and not clean them up, causing this test to
attempt real Google authentication instead of using mocks.
This fix:
- Saves and clears Google/Vertex env vars in setup_method
- Restores them in teardown_method
- Prevents "DefaultCredentialsError" in CI when run with other tests
Test passes in isolation but fails in CI due to test ordering. This
is another test isolation issue, NOT related to PR #21217.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
The manual cache flush is redundant since the autouse fixture
clear_client_cache (lines 21-32) already flushes the cache before
and after every test in this module.
The manual flush was added in Jan 2026 before the autouse fixture
existed. Now that the fixture handles it, the manual flush is unnecessary.
Related: greptile review comment on PR #21255
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Fixes persistent test isolation issue in TestLangfuseUsageDetails by
saving and restoring the global litellm.initialized_langfuse_clients
counter.
Changes:
- Save litellm.initialized_langfuse_clients in setUp
- Restore original value in tearDown
- Prevents counter accumulation across tests
Root Cause:
PR #21248 added logger cleanup but missed the global client counter.
Each test increments litellm.initialized_langfuse_clients when creating
a LangFuseLogger, but the counter was never reset. This caused state
accumulation that could affect test behavior when tests run in certain
orders, leading to "Expected 'generation' to have been called once.
Called 0 times" failures.
Impact:
- test_log_langfuse_v2_handles_null_usage_values was still flaky
- Counter would accumulate: 1, 2, 3... across all tests
- While unlikely to hit MAX (50), accumulated state affected behavior
This completes the test isolation fix started in PR #21248.
Related: #21248
Fixes: Remaining test isolation issues in Langfuse tests
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Follow-up to PR #21248 addressing greptile code review feedback.
Removes hasattr checks for non-existent attributes that were identified
as dead code by greptile automated code review.
Changes:
- Remove hasattr check for LangFuseLogger._langfuse_clients (class attribute doesn't exist)
- Remove hasattr check for self.logger._langfuse_client_cache (instance attribute doesn't exist)
- Update comments to be more accurate about what cleanup is being done
The core fix from PR #21248 (nulling Langfuse reference and deleting
logger instance) remains unchanged and effective. This just removes
misleading dead code that serves no purpose.
Context:
These checks were added defensively but reference attributes that don't
actually exist on the LangFuseLogger class, making them always no-ops.
Greptile correctly identified these as dead code in PR #21248 review,
but the PR was merged before the cleanup could be applied.
Related: #21248
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Fixes test isolation issue where test_video_content_handler_uses_get_for_openai
was making real HTTP requests to OpenAI API instead of using the mock client.
Changes:
- Patch _get_httpx_client to ensure it returns the mock client
- Prevents creation of real HTTP client even if isinstance check fails
- Wraps handler call in context manager for proper cleanup
Root Cause:
When run after other tests, the isinstance(mock_client, HTTPHandler) check
in video_content_handler() could fail due to state pollution, causing the
handler to create a real HTTP client via _get_httpx_client(). This resulted in:
- Real API calls to https://api.openai.com/v1/videos/video_abc/content
- 401 errors: "Incorrect API key provided: sk-test"
- Test expecting b'mp4-bytes' but getting actual error response
Impact:
Test passes in isolation but fails when run with other tests, especially
in CI environments with parallel execution.
Fixes: Test isolation for test_video_content_handler_uses_get_for_openai
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Fixes test isolation issue where test_extra_body_with_fallback was setting
litellm.disable_aiohttp_transport = True but never resetting it, causing
state pollution that affected other tests.
Changes:
- Save original value of disable_aiohttp_transport before modifying
- Wrap test logic in try/finally block
- Restore original value in finally to ensure cleanup even on failure
Root Cause:
The test was modifying global litellm state without cleanup. When run in
certain orders with other tests:
- If this test ran first, it left disable_aiohttp_transport=True globally
- If other tests ran first, their state could interfere with this test
- Result: "All fallback attempts failed" error in CI
Impact:
Test passes in isolation but fails when run with other tests, especially
in parallel execution or CI environments.
Fixes: Test isolation for test_extra_body_with_fallback
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Enhances test isolation in TestLangfuseUsageDetails by ensuring the
logger instance is completely fresh for each test and properly cleaned
up afterward.
Changes:
- Clear any class-level cached Langfuse clients before creating logger
- Reset logger's cached client instances in setUp
- Properly clean up logger instance and its state in tearDown
Root Cause:
The test_log_langfuse_v2_handles_null_usage_values test was failing
when run after other tests due to lingering state in the logger instance.
While the test passes in isolation, test ordering issues caused it to
fail with "Expected 'generation' to have been called once. Called 0 times."
This builds on PR #21214 which added sys.modules cleanup, but that wasn't
sufficient to prevent all state leakage between tests.
Fixes: Test isolation issues in test_log_langfuse_v2_handles_null_usage_values
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
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
