Fix 13 mypy type errors across 6 files

- in_flight_requests_middleware.py: Fix type: ignore error codes from
  [union-attr] to [attr-defined], add [arg-type] for Gauge **kwargs
- transformation.py: Add [assignment] ignore for output_format reassignment,
  add fallback empty string for tool use id to fix arg-type
- responses/main.py: Remove redundant type annotation on second
  secret_fields assignment to fix no-redef
- streaming_iterator.py: Add [assignment] ignores for intermediate
  cache token assignments
- handler.py: Add [typeddict-item] ignore for AnthropicMessagesRequest
  construction from dict
- public_endpoints.py: Add [arg-type] ignore for _load_endpoints()
  return type mismatch with SupportedEndpoint model

Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>

litellm/llms/anthropic/experimental_pass_through/responses_adapters/handler.py

@@ -65,7 +65,7 @@ def _build_responses_kwargs(
     if output_format:
         request_data["output_format"] = output_format
 
-    anthropic_request = AnthropicMessagesRequest(**request_data)
+    anthropic_request = AnthropicMessagesRequest(**request_data)  # type: ignore[typeddict-item]
     responses_kwargs = _ADAPTER.translate_request(anthropic_request)
 
     if stream:

litellm/llms/anthropic/experimental_pass_through/responses_adapters/streaming_iterator.py

@@ -188,8 +188,8 @@ class AnthropicResponsesStreamWrapper:
                 if usage is not None:
                     input_tokens = getattr(usage, "input_tokens", 0) or 0
                     output_tokens = getattr(usage, "output_tokens", 0) or 0
-                    cache_creation_tokens = getattr(usage, "input_tokens_details", None)
-                    cache_read_tokens = getattr(usage, "output_tokens_details", None)
+                    cache_creation_tokens = getattr(usage, "input_tokens_details", None)  # type: ignore[assignment]
+                    cache_read_tokens = getattr(usage, "output_tokens_details", None)  # type: ignore[assignment]
                     # Prefer direct cache fields if present
                     cache_creation_tokens = getattr(usage, "cache_creation_input_tokens", 0) or 0
                     cache_read_tokens = getattr(usage, "cache_read_input_tokens", 0) or 0

litellm/llms/anthropic/experimental_pass_through/responses_adapters/transformation.py

@@ -313,7 +313,7 @@ class LiteLLMAnthropicToResponsesAPIAdapter:
         output_format = anthropic_request.get("output_format")
         output_config = anthropic_request.get("output_config")
         if not isinstance(output_format, dict) and isinstance(output_config, dict):
-            output_format = output_config.get("format")
+            output_format = output_config.get("format")  # type: ignore[assignment]
         if isinstance(output_format, dict) and output_format.get("type") == "json_schema":
             schema = output_format.get("schema")
             if schema:
@@ -392,7 +392,7 @@ class LiteLLMAnthropicToResponsesAPIAdapter:
                 content.append(
                     AnthropicResponseContentBlockToolUse(
                         type="tool_use",
-                        id=item.call_id or item.id,
+                        id=item.call_id or item.id or "",
                         name=item.name,
                         input=input_data,
                     ).model_dump()

litellm/proxy/middleware/in_flight_requests_middleware.py

@@ -41,13 +41,13 @@ class InFlightRequestsMiddleware:
         InFlightRequestsMiddleware._in_flight += 1
         gauge = InFlightRequestsMiddleware._get_gauge()
         if gauge is not None:
-            gauge.inc()  # type: ignore[union-attr]
+            gauge.inc()  # type: ignore[attr-defined]
         try:
             await self.app(scope, receive, send)
         finally:
             InFlightRequestsMiddleware._in_flight -= 1
             if gauge is not None:
-                gauge.dec()  # type: ignore[union-attr]
+                gauge.dec()  # type: ignore[attr-defined]
 
     @staticmethod
     def get_count() -> int:
@@ -69,7 +69,7 @@ class InFlightRequestsMiddleware:
             InFlightRequestsMiddleware._gauge = Gauge(
                 "litellm_in_flight_requests",
                 "Number of HTTP requests currently in-flight on this uvicorn worker",
-                **kwargs,
+                **kwargs,  # type: ignore[arg-type]
             )
         except Exception:
             InFlightRequestsMiddleware._gauge = None

litellm/proxy/public_endpoints/public_endpoints.py

@@ -337,7 +337,7 @@ async def get_supported_endpoints() -> SupportedEndpointsResponse:
     """
     global _cached_endpoints
     if _cached_endpoints is None:
-        _cached_endpoints = SupportedEndpointsResponse(endpoints=_load_endpoints())
+        _cached_endpoints = SupportedEndpointsResponse(endpoints=_load_endpoints())  # type: ignore[arg-type]
     return _cached_endpoints
 
 

litellm/responses/main.py

@@ -304,7 +304,7 @@ async def aresponses_api_with_mcp(
             )
 
             # Extract MCP auth headers from the request to pass to MCP server
-            secret_fields: Optional[Dict[str, Any]] = kwargs.get("secret_fields")
+            secret_fields = kwargs.get("secret_fields")
             (
                 mcp_auth_header,
                 mcp_server_auth_headers,