scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-06 08:16:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

fix: correct timeout precedence in async_anthropic_messages_handler

Browse source 
Per-request litellm_params.timeout should take priority over the proxy
global kwargs["request_timeout"]. Fixes the precedence flagged in code review.
This commit is contained in:
Christian-Sidak 2026-09-01 20:08:43 -07:00
parent 44d3d53f95
commit 29e96f5823
1 changed files with 5 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
litellm/llms/custom_httpx/llm_http_handler.py
View file

@ -1955,11 +1955,12 @@ class BaseLLMHTTPHandler:
)
# Resolve the request timeout so a silent upstream is not waited on
# indefinitely. Priority: per-request kwargs["request_timeout"] >
# litellm_params.timeout > litellm.request_timeout > client default.
# indefinitely. Priority: litellm_params.timeout (per-request explicit)
# > kwargs["request_timeout"] (proxy global) > litellm.request_timeout
# (library global) > client default.
_request_timeout: Optional[Union[float, httpx.Timeout]] = (
kwargs.get("request_timeout")
or litellm_params.get("timeout")
litellm_params.get("timeout")
or kwargs.get("request_timeout")
or litellm.request_timeout
or None
)