litellm

mirror of https://github.com/tiennm99/litellm.git synced 2026-06-27 01:07:02 +00:00

Files

T

yuneng-jiang 79817ff796 [Fix] Constrain feature_name to Literal, deduplicate runtime flags, fix silent test swallowing

- rbac_utils.py: change feature_name from str to Literal["agents", "vector_stores"]
  so typos are caught by type checkers at import time
- proxy_setting_endpoints.py: extract _RUNTIME_GENERAL_SETTINGS_FLAGS as a module-level
  constant, replacing duplicated inline lists in get_ui_settings and update_ui_settings
- test_vector_store_rbac.py: remove try/except pattern that silently swallowed non-403
  HTTPExceptions; tests now let any unexpected exception propagate as a test failure

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-05 15:42:17 -08:00

a2a_protocol/providers/pydantic_ai_agents

[Feat] New provider - Agent Gateway, add pydantic ai agents (#18013 )

2025-12-15 17:40:58 -08:00

integrations/helicone

test: add provider_url routing test for vertex_ai/gemini models

2026-03-03 15:20:51 -03:00

litellm_core_utils

test: create fresh ModelResponse per test to avoid shared mutable state

2026-03-03 14:54:11 -03:00

llms

Revert "fix(adapter): double-stripping of model names with provider-matching prefixes"