mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-11 09:08:31 +00:00
- Cache litellm logger instance globally for performance optimization - Implement more specific warning pattern filtering instead of broad matching - Add robust error handling with graceful degradation in suppression - Enhance streaming error handling with better logging and continue logic - Add 3 new comprehensive tests: - test_concurrent_llm_calls: Verify thread safety with concurrent LLM calls - test_logger_caching_performance: Confirm logger instance caching works - test_suppression_error_handling: Test graceful degradation on logger errors - Fix all lint errors (unused imports) in test file Co-Authored-By: João <joao@crewai.com>
6.1 KiB
6.1 KiB