chore: sync upstream 2026-06-23

basedpyright-code-budget.json

@@ -1,18 +1,18 @@
 {
   "reportAny": {
-    "baseline": 25453,
+    "baseline": 25467,
     "slack": 2500
   },
   "reportArgumentType": {
-    "baseline": 1961,
+    "baseline": 1960,
     "slack": 180
   },
   "reportAssignmentType": {
     "baseline": 221,
     "slack": 3
   },
   "reportAttributeAccessIssue": {
-    "baseline": 339,
+    "baseline": 330,
     "slack": 3
   },
   "reportCallIssue": {
@@ -32,15 +32,15 @@
     "slack": 3
   },
   "reportExplicitAny": {
-    "baseline": 7022,
+    "baseline": 7034,
     "slack": 700
   },
   "reportFunctionMemberAccess": {
     "baseline": 8,
     "slack": 3
   },
   "reportGeneralTypeIssues": {
-    "baseline": 155,
+    "baseline": 153,
     "slack": 3
   },
   "reportIncompatibleMethodOverride": {
@@ -60,7 +60,7 @@
     "slack": 3
   },
   "reportInvalidTypeForm": {
-    "baseline": 22,
+    "baseline": 23,
     "slack": 3
   },
   "reportInvalidTypeVarUse": {
@@ -80,7 +80,7 @@
     "slack": 1000
   },
   "reportMissingTypeStubs": {
-    "baseline": 30,
+    "baseline": 20,
     "slack": 10
   },
   "reportOperatorIssue": {
@@ -112,7 +112,7 @@
     "slack": 10
   },
   "reportPrivateUsage": {
-    "baseline": 1648,
+    "baseline": 1652,
     "slack": 160
   },
   "reportRedeclaration": {
@@ -128,43 +128,43 @@
     "slack": 3
   },
   "reportUndefinedVariable": {
-    "baseline": 2,
+    "baseline": 5,
     "slack": 3
   },
   "reportUnknownArgumentType": {
-    "baseline": 31622,
+    "baseline": 31662,
     "slack": 3000
   },
   "reportUnknownLambdaType": {
     "baseline": 75,
     "slack": 10
   },
   "reportUnknownMemberType": {
-    "baseline": 27135,
+    "baseline": 27400,
     "slack": 2500
   },
   "reportUnknownParameterType": {
-    "baseline": 13686,
+    "baseline": 13704,
     "slack": 1000
   },
   "reportUnknownVariableType": {
-    "baseline": 21499,
+    "baseline": 21694,
     "slack": 2000
   },
   "reportUnnecessaryCast": {
-    "baseline": 124,
+    "baseline": 119,
     "slack": 10
   },
   "reportUnnecessaryComparison": {
-    "baseline": 683,
+    "baseline": 688,
     "slack": 10
   },
   "reportUnnecessaryContains": {
     "baseline": 4,
     "slack": 3
   },
   "reportUnnecessaryIsInstance": {
-    "baseline": 816,
+    "baseline": 819,
     "slack": 10
   },
   "reportUntypedBaseClass": {
@@ -180,15 +180,15 @@
     "slack": 3
   },
   "reportUnusedFunction": {
-    "baseline": 138,
+    "baseline": 135,
     "slack": 10
   },
   "reportUnusedImport": {
-    "baseline": 670,
+    "baseline": 648,
     "slack": 10
   },
   "reportUnusedVariable": {
-    "baseline": 866,
+    "baseline": 573,
     "slack": 10
   }
 }

litellm/litellm_core_utils/exception_mapping_utils.py

@@ -1,7 +1,7 @@
 import json
 import re
 import traceback
-from typing import Any, Optional, Protocol, cast
+from typing import Any, Protocol, cast
 
 import httpx
 
@@ -124,7 +124,7 @@ def is_azure_content_policy_violation_error(error_str: str) -> bool:
         return False
 
 
-def get_error_message(error_obj) -> Optional[str]:
+def get_error_message(error_obj) -> str | None:
     """
     OpenAI Returns Error message that is nested, this extract the message
 
@@ -180,13 +180,13 @@ def _get_body_error_code(error_str: str) -> int | None:
         return None
 
 
-def _get_response_headers(original_exception: Exception) -> Optional[httpx.Headers]:
+def _get_response_headers(original_exception: Exception) -> httpx.Headers | None:
     """
     Extract and return the response headers from an exception, if present.
 
     Used for accurate retry logic.
     """
-    _response_headers: Optional[httpx.Headers] = None
+    _response_headers: httpx.Headers | None = None
     try:
         _response_headers = getattr(original_exception, "headers", None)
         error_response = getattr(original_exception, "response", None)
@@ -203,7 +203,7 @@ def _get_response_headers(original_exception: Exception) -> Optional[httpx.Heade
 
 
 def extract_and_raise_litellm_exception(
-    response: Optional[Any],
+    response: Any | None,
     error_str: str,
     model: str,
     custom_llm_provider: str,
@@ -1954,7 +1954,7 @@ def _map_azure_exception(
     # Azure OpenAI (especially Images) often nests error details under
     # body["error"]. Detect content policy violations using the structured
     # payload in addition to string matching.
-    azure_error_code: Optional[str] = None
+    azure_error_code: str | None = None
     try:
         body_dict = getattr(original_exception, "body", None) or {}
         if isinstance(body_dict, dict):

litellm/llms/anthropic/cost_calculation.py

@@ -3,7 +3,7 @@
 - e.g.: prompt caching
 """
 
-from typing import TYPE_CHECKING, Optional
+from typing import TYPE_CHECKING, Optional, Tuple
 
 from litellm.litellm_core_utils.llm_cost_calc.utils import (
     _get_token_base_cost,
@@ -62,7 +62,7 @@ def _compute_cache_only_cost(
 
 def cost_per_token(
     model: str, usage: "Usage", service_tier: str | None = None
-) -> tuple[float, float]:
+) -> Tuple[float, float]:
     """
     Calculates the cost per token for a given model, prompt tokens, and completion tokens.
 

litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py

@@ -614,7 +614,7 @@ def _resolve_search_tool_conflict(
 
         return googleSearch, googleSearchRetrieval, enterpriseWebSearch, urlContext
 
-    def _map_function(self, value: list[dict], optional_params: dict) -> list[Tools]:
+    def _map_function(self, value: List[dict], optional_params: dict) -> List[Tools]:
         """
         Map OpenAI-style tools/functions to Vertex AI format.
 

litellm/proxy/proxy_cli.py

@@ -417,8 +417,8 @@ def _run_gunicorn_server(
         num_workers: int,
         ssl_certfile_path: str,
         ssl_keyfile_path: str,
-        max_requests_before_restart: int | None = None,
-        max_requests_before_restart_jitter: int | None = None,
+        max_requests_before_restart: Optional[int] = None,
+        max_requests_before_restart_jitter: Optional[int] = None,
     ):
         """
         Run litellm with `gunicorn`
@@ -912,7 +912,7 @@ def run_server(
     keepalive_timeout,
     timeout_worker_healthcheck,
     max_requests_before_restart,
-    max_requests_before_restart_jitter: int | None,
+    max_requests_before_restart_jitter: Optional[int],
     enforce_prisma_migration_check: bool,
     use_v2_migration_resolver: bool,
     reload: bool,

litellm/proxy/proxy_server.py

@@ -419,10 +419,6 @@ def generate_feedback_box():
 )
 from litellm.proxy.management_helpers.audit_logs import create_audit_log_for_update
 from litellm.proxy.memory.memory_endpoints import router as memory_router
-from litellm.proxy.plugin_routes import (
-    router as plugin_router,
-    register_plugins_from_config,
-)
 from litellm.proxy.middleware.in_flight_requests_middleware import (
     InFlightRequestsMiddleware,
 )
@@ -455,6 +451,10 @@ def generate_feedback_box():
 from litellm.proxy.pass_through_endpoints.pass_through_endpoints import (
     router as pass_through_router,
 )
+from litellm.proxy.plugin_routes import (
+    register_plugins_from_config,
+    router as plugin_router,
+)
 from litellm.proxy.public_endpoints import router as public_endpoints_router
 from litellm.proxy.rag_endpoints.endpoints import router as rag_router
 from litellm.proxy.rerank_endpoints.endpoints import router as rerank_router
@@ -8758,8 +8758,8 @@ async def model_list(
 async def model_info(
     model_id: str,
     user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
-    team_id: str | None = None,
-    healthy_only: bool | None = False,
+    team_id: Optional[str] = None,
+    healthy_only: Optional[bool] = False,
 ):
     """
     Retrieve information about a specific model accessible to your API key.
@@ -16456,7 +16456,6 @@ async def get_routes():
 app.include_router(tag_management_router)
 app.include_router(workflow_management_router)
 app.include_router(memory_router)
-app.include_router(plugin_router)
 app.include_router(cost_tracking_settings_router)
 app.include_router(router_settings_router)
 app.include_router(fallback_management_router)
@@ -16466,6 +16465,7 @@ async def get_routes():
 app.include_router(ui_discovery_endpoints_router)
 # Eager: /models/{name}:method overlaps with the OpenAI /models endpoint.
 app.include_router(google_router)
+app.include_router(plugin_router)
 
 attach_lazy_features(app)
 app.add_middleware(

osv-scanner.toml

@@ -8,12 +8,3 @@ id = "GHSA-gr75-jv2w-4656"
 ignoreUntil = 2026-12-31
 reason = "langchain fix requires >=1.3.9, but that needs langgraph>=1.2.4,<1.3.0 which conflicts with our pinned langgraph==1.0.10 (langgraph-prebuilt==1.0.8 requires langgraph==1.0.10). Blocked until langgraph family can be bumped as a coordinated upgrade."
 
-[[IgnoredVulns]]
-id = "GHSA-f4xh-w4cj-qxq8"
-ignoreUntil = 2026-06-24
-reason = "langsmith 0.8.18 (the fix) was published within the past 3 days; blocked by exclude-newer-span = P3D until 2026-06-24. Remove this entry once the daily lock refresh picks up 0.8.18."
-
-[[IgnoredVulns]]
-id = "GHSA-4xgf-cpjx-pc3j"
-ignoreUntil = 2026-06-24
-reason = "pydantic-settings 2.14.2 (the fix) was published within the past 3 days; blocked by exclude-newer-span = P3D until 2026-06-24. Remove this entry once the daily lock refresh picks up 2.14.2."

ruff-strict-budget.json

@@ -32,7 +32,7 @@
     "slack": 10
   },
   "ANN401": {
-    "baseline": 1941,
+    "baseline": 1942,
     "slack": 50
   },
   "ASYNC230": {
@@ -108,7 +108,7 @@
     "slack": 3
   },
   "C901": {
-    "baseline": 304,
+    "baseline": 311,
     "slack": 15
   },
   "D419": {
@@ -232,7 +232,7 @@
     "slack": 3
   },
   "PLR0913": {
-    "baseline": 1831,
+    "baseline": 1849,
     "slack": 50
   },
   "PLR1704": {
@@ -412,7 +412,7 @@
     "slack": 3
   },
   "TID251": {
-    "baseline": 2669,
+    "baseline": 2670,
     "slack": 50
   },
   "TRY002": {
@@ -436,11 +436,11 @@
     "slack": 30
   },
   "UP006": {
-    "baseline": 13066,
+    "baseline": 13065,
     "slack": 100
   },
   "UP007": {
-    "baseline": 2541,
+    "baseline": 2542,
     "slack": 50
   },
   "UP008": {
@@ -476,7 +476,7 @@
     "slack": 3
   },
   "UP035": {
-    "baseline": 2261,
+    "baseline": 2262,
     "slack": 50
   },
   "UP036": {