Litellm UI qa 04 12 2025 p1 (#9955)

* fix(model_info_view.tsx): cleanup text

* fix(key_management_endpoints.py): fix filtering litellm-dashboard keys for internal users

* fix(proxy_track_cost_callback.py): prevent flooding spend logs with admin endpoint errors

* test: add unit testing for logic

* test(test_auth_exception_handler.py): add more unit testing

* fix(router.py): correctly handle retrieving model info on get_model_group_info

fixes issue where model hub was showing None prices

* fix: fix linting errors

Author: krrishdholakia

litellm/litellm_core_utils/get_model_cost_map.py

@@ -13,7 +13,7 @@
 import httpx
 
 
-def get_model_cost_map(url: str):
+def get_model_cost_map(url: str) -> dict:
     if (
         os.getenv("LITELLM_LOCAL_MODEL_COST_MAP", False)
         or os.getenv("LITELLM_LOCAL_MODEL_COST_MAP", False) == "True"

litellm/proxy/_experimental/out/onboarding.html

@@ -644,9 +644,9 @@ class GenerateRequestBase(LiteLLMPydanticObjectBase):
     allowed_cache_controls: Optional[list] = []
     config: Optional[dict] = {}
     permissions: Optional[dict] = {}
-    model_max_budget: Optional[dict] = (
-        {}
-    )  # {"gpt-4": 5.0, "gpt-3.5-turbo": 5.0}, defaults to {}
+    model_max_budget: Optional[
+        dict
+    ] = {}  # {"gpt-4": 5.0, "gpt-3.5-turbo": 5.0}, defaults to {}
 
     model_config = ConfigDict(protected_namespaces=())
     model_rpm_limit: Optional[dict] = None
@@ -902,12 +902,12 @@ class NewCustomerRequest(BudgetNewRequest):
     alias: Optional[str] = None  # human-friendly alias
     blocked: bool = False  # allow/disallow requests for this end-user
     budget_id: Optional[str] = None  # give either a budget_id or max_budget
-    allowed_model_region: Optional[AllowedModelRegion] = (
-        None  # require all user requests to use models in this specific region
-    )
-    default_model: Optional[str] = (
-        None  # if no equivalent model in allowed region - default all requests to this model
-    )
+    allowed_model_region: Optional[
+        AllowedModelRegion
+    ] = None  # require all user requests to use models in this specific region
+    default_model: Optional[
+        str
+    ] = None  # if no equivalent model in allowed region - default all requests to this model
 
     @model_validator(mode="before")
     @classmethod
@@ -929,12 +929,12 @@ class UpdateCustomerRequest(LiteLLMPydanticObjectBase):
     blocked: bool = False  # allow/disallow requests for this end-user
     max_budget: Optional[float] = None
     budget_id: Optional[str] = None  # give either a budget_id or max_budget
-    allowed_model_region: Optional[AllowedModelRegion] = (
-        None  # require all user requests to use models in this specific region
-    )
-    default_model: Optional[str] = (
-        None  # if no equivalent model in allowed region - default all requests to this model
-    )
+    allowed_model_region: Optional[
+        AllowedModelRegion
+    ] = None  # require all user requests to use models in this specific region
+    default_model: Optional[
+        str
+    ] = None  # if no equivalent model in allowed region - default all requests to this model
 
 
 class DeleteCustomerRequest(LiteLLMPydanticObjectBase):
@@ -1070,9 +1070,9 @@ class BlockKeyRequest(LiteLLMPydanticObjectBase):
 
 class AddTeamCallback(LiteLLMPydanticObjectBase):
     callback_name: str
-    callback_type: Optional[Literal["success", "failure", "success_and_failure"]] = (
-        "success_and_failure"
-    )
+    callback_type: Optional[
+        Literal["success", "failure", "success_and_failure"]
+    ] = "success_and_failure"
     callback_vars: Dict[str, str]
 
     @model_validator(mode="before")
@@ -1329,9 +1329,9 @@ class ConfigList(LiteLLMPydanticObjectBase):
     stored_in_db: Optional[bool]
     field_default_value: Any
     premium_field: bool = False
-    nested_fields: Optional[List[FieldDetail]] = (
-        None  # For nested dictionary or Pydantic fields
-    )
+    nested_fields: Optional[
+        List[FieldDetail]
+    ] = None  # For nested dictionary or Pydantic fields
 
 
 class ConfigGeneralSettings(LiteLLMPydanticObjectBase):
@@ -1558,6 +1558,7 @@ class UserAPIKeyAuth(
     user_tpm_limit: Optional[int] = None
     user_rpm_limit: Optional[int] = None
     user_email: Optional[str] = None
+    request_route: Optional[str] = None
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
@@ -1597,9 +1598,9 @@ class LiteLLM_OrganizationMembershipTable(LiteLLMPydanticObjectBase):
     budget_id: Optional[str] = None
     created_at: datetime
     updated_at: datetime
-    user: Optional[Any] = (
-        None  # You might want to replace 'Any' with a more specific type if available
-    )
+    user: Optional[
+        Any
+    ] = None  # You might want to replace 'Any' with a more specific type if available
     litellm_budget_table: Optional[LiteLLM_BudgetTable] = None
 
     model_config = ConfigDict(protected_namespaces=())
@@ -2345,9 +2346,9 @@ class TeamModelDeleteRequest(BaseModel):
 # Organization Member Requests
 class OrganizationMemberAddRequest(OrgMemberAddRequest):
     organization_id: str
-    max_budget_in_organization: Optional[float] = (
-        None  # Users max budget within the organization
-    )
+    max_budget_in_organization: Optional[
+        float
+    ] = None  # Users max budget within the organization
 
 
 class OrganizationMemberDeleteRequest(MemberDeleteRequest):
@@ -2536,9 +2537,9 @@ class ProviderBudgetResponse(LiteLLMPydanticObjectBase):
     Maps provider names to their budget configs.
     """
 
-    providers: Dict[str, ProviderBudgetResponseObject] = (
-        {}
-    )  # Dictionary mapping provider names to their budget configurations
+    providers: Dict[
+        str, ProviderBudgetResponseObject
+    ] = {}  # Dictionary mapping provider names to their budget configurations
 
 
 class ProxyStateVariables(TypedDict):
@@ -2666,9 +2667,9 @@ class LiteLLM_JWTAuth(LiteLLMPydanticObjectBase):
     enforce_rbac: bool = False
     roles_jwt_field: Optional[str] = None  # v2 on role mappings
     role_mappings: Optional[List[RoleMapping]] = None
-    object_id_jwt_field: Optional[str] = (
-        None  # can be either user / team, inferred from the role mapping
-    )
+    object_id_jwt_field: Optional[
+        str
+    ] = None  # can be either user / team, inferred from the role mapping
     scope_mappings: Optional[List[ScopeMapping]] = None
     enforce_scope_based_access: bool = False
     enforce_team_based_model_access: bool = False

litellm/proxy/_types.py

@@ -68,6 +68,7 @@ async def _handle_authentication_error(
                 key_name="failed-to-connect-to-db",
                 token="failed-to-connect-to-db",
                 user_id=litellm_proxy_admin_name,
+                request_route=route,
             )
         else:
             # raise the exception to the caller
@@ -87,6 +88,7 @@ async def _handle_authentication_error(
             user_api_key_dict = UserAPIKeyAuth(
                 parent_otel_span=parent_otel_span,
                 api_key=api_key,
+                request_route=route,
             )
             asyncio.create_task(
                 proxy_logging_obj.post_call_failure_hook(

litellm/proxy/auth/auth_exception_handler.py

@@ -1023,6 +1023,7 @@ async def user_api_key_auth(
     """
 
     request_data = await _read_request_body(request=request)
+    route: str = get_request_route(request=request)
 
     user_api_key_auth_obj = await _user_api_key_auth_builder(
         request=request,
@@ -1038,6 +1039,8 @@ async def user_api_key_auth(
     if end_user_id is not None:
         user_api_key_auth_obj.end_user_id = end_user_id
 
+    user_api_key_auth_obj.request_route = route
+
     return user_api_key_auth_obj
 
 

litellm/proxy/auth/user_api_key_auth.py

@@ -13,6 +13,7 @@
 from litellm.litellm_core_utils.litellm_logging import StandardLoggingPayloadSetup
 from litellm.proxy._types import UserAPIKeyAuth
 from litellm.proxy.auth.auth_checks import log_db_metrics
+from litellm.proxy.auth.route_checks import RouteChecks
 from litellm.proxy.utils import ProxyUpdateSpend
 from litellm.types.utils import (
     StandardLoggingPayload,
@@ -33,8 +34,13 @@ async def async_post_call_failure_hook(
         original_exception: Exception,
         user_api_key_dict: UserAPIKeyAuth,
     ):
+        request_route = user_api_key_dict.request_route
         if _ProxyDBLogger._should_track_errors_in_db() is False:
             return
+        elif request_route is not None and not RouteChecks.is_llm_api_route(
+            route=request_route
+        ):
+            return
 
         from litellm.proxy.proxy_server import proxy_logging_obj
 

litellm/proxy/hooks/proxy_track_cost_callback.py

@@ -577,9 +577,9 @@ async def generate_key_fn(  # noqa: PLR0915
             request_type="key", **data_json, table_name="key"
         )
 
-        response["soft_budget"] = (
-            data.soft_budget
-        )  # include the user-input soft budget in the response
+        response[
+            "soft_budget"
+        ] = data.soft_budget  # include the user-input soft budget in the response
 
         response = GenerateKeyResponse(**response)
 
@@ -1467,10 +1467,10 @@ async def delete_verification_tokens(
     try:
         if prisma_client:
             tokens = [_hash_token_if_needed(token=key) for key in tokens]
-            _keys_being_deleted: List[LiteLLM_VerificationToken] = (
-                await prisma_client.db.litellm_verificationtoken.find_many(
-                    where={"token": {"in": tokens}}
-                )
+            _keys_being_deleted: List[
+                LiteLLM_VerificationToken
+            ] = await prisma_client.db.litellm_verificationtoken.find_many(
+                where={"token": {"in": tokens}}
             )
 
             # Assuming 'db' is your Prisma Client instance
@@ -1572,9 +1572,9 @@ async def _rotate_master_key(
     from litellm.proxy.proxy_server import proxy_config
 
     try:
-        models: Optional[List] = (
-            await prisma_client.db.litellm_proxymodeltable.find_many()
-        )
+        models: Optional[
+            List
+        ] = await prisma_client.db.litellm_proxymodeltable.find_many()
     except Exception:
         models = None
     # 2. process model table
@@ -1861,11 +1861,11 @@ async def validate_key_list_check(
             param="user_id",
             code=status.HTTP_403_FORBIDDEN,
         )
-    complete_user_info_db_obj: Optional[BaseModel] = (
-        await prisma_client.db.litellm_usertable.find_unique(
-            where={"user_id": user_api_key_dict.user_id},
-            include={"organization_memberships": True},
-        )
+    complete_user_info_db_obj: Optional[
+        BaseModel
+    ] = await prisma_client.db.litellm_usertable.find_unique(
+        where={"user_id": user_api_key_dict.user_id},
+        include={"organization_memberships": True},
     )
 
     if complete_user_info_db_obj is None:
@@ -1926,10 +1926,10 @@ async def get_admin_team_ids(
     if complete_user_info is None:
         return []
     # Get all teams that user is an admin of
-    teams: Optional[List[BaseModel]] = (
-        await prisma_client.db.litellm_teamtable.find_many(
-            where={"team_id": {"in": complete_user_info.teams}}
-        )
+    teams: Optional[
+        List[BaseModel]
+    ] = await prisma_client.db.litellm_teamtable.find_many(
+        where={"team_id": {"in": complete_user_info.teams}}
     )
     if teams is None:
         return []
@@ -2080,7 +2080,6 @@ async def _list_key_helper(
             "total_pages": int,
         }
     """
-
     # Prepare filter conditions
     where: Dict[str, Union[str, Dict[str, Any], List[Dict[str, Any]]]] = {}
     where.update(_get_condition_to_filter_out_ui_session_tokens())
@@ -2110,7 +2109,7 @@ async def _list_key_helper(
 
     # Combine conditions with OR if we have multiple conditions
     if len(or_conditions) > 1:
-        where["OR"] = or_conditions
+        where = {"AND": [where, {"OR": or_conditions}]}
     elif len(or_conditions) == 1:
         where.update(or_conditions[0])