litellm/tests/unit/native
narmstrong-berri 74715e0ddf
Some checks failed
LiteLLM Rust / rust-wheel (push) Has been cancelled
LiteLLM Rust / rust-lint (push) Has been cancelled
LiteLLM Rust / rust-test (push) Has been cancelled
refactor: call execute_chat from the Messages to chat bridge
The /v1/messages bridge for chat-only models now plans the chat call once
and runs execute_chat directly instead of re-entering litellm.acompletion,
so deployment hooks run once per request. Requests that need the chat
surface (fallbacks, model_list, MCP gateway tools, prompt management,
litellm_system_prompt) still go through litellm.acompletion
2026-10-26 19:03:02 +00:00
..
__init__.py refactor: decide the native API format once with plan_route 2026-10-20 13:31:42 -07:00
test_chat_plan.py refactor: call execute_chat from the Messages to chat bridge 2026-10-26 19:03:02 +00:00
test_route_plan.py refactor: decide the native API format once with plan_route 2026-10-20 13:31:42 -07:00