Simplifies the _handle_reasoning_item method to only filter out None values
without attempting to construct ResponseReasoningItem objects. This approach:
- Avoids mutation of encrypted_content in reasoning items
- Fixes compatibility with gpt-5-codex and Codex CLI
- Removes dependency on ResponseReasoningItem import
- Simplifies the code by removing complex fallback logic
The previous approach was trying to construct ResponseReasoningItem objects
with required fields (id, summary), which caused issues with encrypted
payloads. The new approach simply filters None values while preserving
all other data intact.
Issue: https://github.com/BerriAI/litellm/issues/13484
Reported-by: rajpathak (OpenAI)
Tested-by: rajpathak (OpenAI Codex CLI)
* feat(vector_stores/): initial commit adding Vertex AI Search API support for litellm
new vector store provider
* feat(vector_store/): use vector store id for vertex ai search api
* fix: transformation.py
cleanup
* fix: implement abstract function
* fix: fix linting error
* fix: main.py
fix check
* feat(cohere): Enhance embedding transformation to support Bedrock's embeddings by type
* test(cohere): Add unit tests for embedding transformation responses
* fix: Apply max_connections configuration to Redis async client
- Add max_connections to available Redis cluster kwargs
- Add connection_pool parameter to get_redis_async_client()
- Pass connection_pool to Redis client if provided
- Prevents Redis connection exhaustion under high load
* test: Add tests for Redis max_connections feature
- Test max_connections is included in cluster kwargs
- Test connection_pool parameter is properly passed to async client
- Test async client works without connection_pool parameter
All 3 tests pass successfully
- Change variable name in litellm/__init__.py from configured_cold_storage_logger to cold_storage_custom_logger
- Update all references across the codebase to use the new variable name
- This fixes silent failure of cold storage logging due to variable name mismatch
- Configuration files use cold_storage_custom_logger, code should match
Files updated:
- litellm/__init__.py
- litellm/litellm_core_utils/litellm_logging.py
- litellm/proxy/spend_tracking/cold_storage_handler.py
- litellm/responses/litellm_completion_transformation/session_handler.py
- tests/test_litellm/litellm_core_utils/test_litellm_logging.py
- tests/test_litellm/responses/litellm_completion_transformation/test_session_handler.py
* fix(add_pass_through.tsx): allow setting 'auth' to true for passthrough endpoints on the UI
* fix: working update auth on passthrough endpoints + show auth on passthrough table
* Add imageConfig parameter support for Vertex AI to enable gemini-2.5-flash-image model requirements
* Add test for imageConfig parameter support in Vertex AI Gemini transformation
* [Feat] Add SENTRY_ENVIRONMENT configuration for Sentry integration and corresponding tests
* [Refactor] Enhance test_sentry_environment by mocking sentry_sdk and improving environment handling
* [Fix] Update default SENTRY_ENVIRONMENT to 'production' and enhance test for Sentry integration
* [Fix] Update test_sentry_environment to verify correct handling of SENTRY_ENVIRONMENT values
* [Fix] Update test_sentry_environment to assert correct handling of production environment
* fixed the Auth header for MCP Tool Call
* Final fix for Auth header
* testcase for mcp_auth_header_extraction, insensitive_alias_matching, insensitive_servername_matching added
