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(auth): pass llm_router to _check_team_member_model_access

Browse source 
Without the router, _can_object_call_model cannot resolve wildcard model
names (e.g. openai/*) or access-group names in allowed_models, causing
legitimate requests to be denied.  Thread the existing llm_router from
_run_common_checks through to the new member-scope check.
This commit is contained in:
Ishaan Jaffer 2026-04-01 16:20:02 -07:00
parent 48ecd59aa5
commit ed9009347b
1 changed files with 3 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
litellm/proxy/auth/auth_checks.py
View file

@ -435,6 +435,7 @@ async def common_checks( # noqa: PLR0915
model=_model,
team_object=team_object,
valid_token=valid_token,
llm_router=llm_router,
prisma_client=prisma_client,
user_api_key_cache=user_api_key_cache,
proxy_logging_obj=proxy_logging_obj,
@ -3085,6 +3086,7 @@ async def _check_team_member_model_access(
model: Union[str, List[str]],
team_object: LiteLLM_TeamTable,
valid_token: UserAPIKeyAuth,
llm_router: Optional[Router],
prisma_client: Optional["PrismaClient"],
user_api_key_cache: DualCache,
proxy_logging_obj: ProxyLogging,
@ -3119,7 +3121,7 @@ async def _check_team_member_model_access(
try:
_can_object_call_model(
model=model,
llm_router=None,
llm_router=llm_router,
models=member_allowed_models,
object_type="team",
)