scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

fix(proxy): make inference model selection exhaustive

Browse source
This commit is contained in:
Joshua Valluru 2026-09-30 11:59:36 -07:00
parent 0fd4e93c48
commit 812f6c7024
2 changed files with 4 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
litellm/proxy/common_utils/http_parsing_utils.py
View file

@ -6,7 +6,7 @@ from typing import Annotated, Any, Final, Literal, Union, get_args, get_origin
import orjson
from fastapi import Request, UploadFile, status
from typing_extensions import NotRequired, ReadOnly, Required
from typing_extensions import NotRequired, ReadOnly, Required, assert_never
from litellm._logging import verbose_proxy_logger
from litellm.constants import (
@ -56,6 +56,7 @@ def resolve_inference_model(
return endpoint_model
case "completion":
return settings.get("completion_model") or cli_model or endpoint_model or body_model
assert_never(kind)
def _normalize_media_type(content_type: str) -> str:

2
tests/test_litellm/proxy/auth/test_handle_jwt.py
View file

@ -7932,6 +7932,8 @@ async def test_managed_application_uses_persisted_identity_without_provisioning_
result: Final = await JWTAuthManager.auth_builder(**arguments)
auth: Final = JWTAuthManager.user_api_key_auth_from_result(result)
assert auth.agent_id == "stable-id"
assert auth.api_key is None
assert auth.token is None
assert auth.user_id is None
assert auth.team_id is None
assert auth.managed_agent_context is not None