●Change8

v1.81.13

📦 litellmView on GitHub →
✨ 5 features🐛 37 fixes🔧 14 symbols

Summary

This release focuses heavily on improving test stability across various integrations (Langfuse, Vertex AI, SSO) and fixing numerous minor bugs. New features include UI enhancements for Access Groups and Content Filters, alongside updates to reasoning handling and model parameter exclusions.

Migration Steps

  1. If using reasoning functionality, ensure the reasoning parameter is set to None instead of Reasoning().
  2. If encountering issues with SSO PKCE in Kubernetes, review configuration as fixes for multi-pod deployments have been applied.

✨ New Features

  • Added Access Group Selector to Create and Edit Flow in the UI for Keys/Teams.
  • Added routing logic based on whether reasoning is supported.
  • Added documentation for OpenAI Agents SDK with LiteLLM.
  • Added documentation for Anthropic beta header in LiteLLM.
  • Added UI improvements for Content Filters, including editing/viewing categories and 1-click add categories.

🐛 Bug Fixes

  • Preserved key_alias and team_id metadata in /user/daily/activity/aggregated after key deletion or regeneration.
  • Fixed an issue where the reasoning parameter used Reasoning() instead of None.
  • Removed unused Reasoning import from transformation.py.
  • Fixed Langfuse test isolation issues causing flaky failures.
  • Resolved merge conflict and fixed bedrock thinking test flakiness.
  • Fixed flaky tests caused by module reloading and missing mocks.
  • Fixed SSO test flakiness by correctly mocking premium_user.
  • Made policy_resolve_endpoints importable without FastAPI.
  • Improved Langfuse test isolation.
  • Added mock isolation for test_video_content_handler_uses_get_for_openai.
  • Added cleanup for disable_aiohttp_transport in test_extra_body_with_fallback.
  • Restored Langfuse client counter in test cleanup.
  • Removed redundant cache flush from test_openai_env_base.
  • Added environment cleanup for Vertex AI rerank tests.
  • Updated reasoning_effort test to expect dict format.
  • Added environment cleanup for Vertex AI GPT-OSS tests.
  • Added environment cleanup for Vertex AI Qwen tests.
  • Used async side_effect for client.post mock in watsonx test.
  • Mocked vertexai module in GPT-OSS tests to prevent authentication issues.
  • Updated test_other_constraints_preserved for new schema filtering.
  • Added fakeredis dependency for pod lock manager tests.
  • Cleared tokenizer LRU cache for test isolation.
  • Mocked environment variables for callback validation test.
  • Fixed unsupported parameters for chatgpt codex.
  • Fixed converse anthropic usage object according to v1/messages specs.
  • Miscellaneous bug fixes for Managed batches.
  • Clamped thinking.budget_tokens to a minimum of 1024 for bedrock.
  • Fixed virtual key grace period retrieval from env/UI.
  • Fixed SSO PKCE support failure in multi-pod Kubernetes deployments.
  • Added pytest-postgresql dependency for db schema migration tests.
  • Replaced caplog with custom handler for parallel execution in tests.
  • Corrected async mock for video generation logging test.
  • Added cleanup fixture and no_parallel mark for MCP tests.
  • Fixed exclusion of tool params for models without function calling support.
  • Handled missing DATABASE_URL in append_query_params for proxy.
  • Reverted StreamableHTTPSessionManager to stateless mode for mcp.
  • Fixed OCI Grok output pricing.

Affected Symbols

policy_resolve_endpointsReasoningtest_video_content_handler_uses_get_for_openaitest_extra_body_with_fallbacktest_openai_env_basetest_other_constraints_preservedtest_reasoning_efforttest_video_content_handler_uses_get_for_openaitest_callback_validationchatgpt codexconverse anthropicbedrock thinking.budget_tokensappend_query_paramsStreamableHTTPSessionManager