[Fix] CI failures: mypy type error, ruff lint, and flaky router test

- Fix mypy arg-type error in background_streaming.py by adding proper
  type annotation and cast for terminal_status
- Fix ruff F401 false positive for httpx import in vantage_destination.py
  caused by from __future__ import annotations
- Fix flaky test_arouter_responses_api_bridge by providing a properly
  structured mock response to prevent exception mapping errors

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

litellm/integrations/focus/destinations/vantage_destination.py

@@ -6,7 +6,7 @@ import csv
 import io
 from typing import Any, Optional
 
-import httpx
+import httpx  # noqa: F401 - used at runtime (AsyncClient, HTTPStatusError)
 
 from litellm._logging import verbose_logger
 

litellm/proxy/response_polling/background_streaming.py

@@ -9,7 +9,7 @@ https://platform.openai.com/docs/api-reference/responses-streaming
 """
 import asyncio
 import json
-from typing import Any
+from typing import Any, Optional, cast
 
 from fastapi import Request, Response
 
@@ -17,6 +17,7 @@ from litellm._logging import verbose_proxy_logger
 from litellm.proxy.auth.user_api_key_auth import UserAPIKeyAuth
 from litellm.proxy.common_request_processing import ProxyBaseLLMRequestProcessing
 from litellm.proxy.response_polling.polling_handler import ResponsePollingHandler
+from litellm.types.llms.openai import ResponsesAPIStatus
 
 
 async def background_streaming_task(  # noqa: PLR0915
@@ -114,7 +115,7 @@ async def background_streaming_task(  # noqa: PLR0915
         UPDATE_INTERVAL = 0.150  # 150ms batching interval
 
         # Track the terminal event from the stream (may not be "completed")
-        terminal_status = None  # Will be set by response.completed/failed/incomplete/cancelled
+        terminal_status: Optional[ResponsesAPIStatus] = None  # Will be set by response.completed/failed/incomplete/cancelled
         terminal_error = None
         _event_to_status = {
             "response.completed": "completed",
@@ -249,9 +250,12 @@ async def background_streaming_task(  # noqa: PLR0915
                             # Terminal event - extract all ResponsesAPIResponse fields
                             # https://platform.openai.com/docs/api-reference/responses-streaming
                             response_data = event.get("response", {})
-                            terminal_status = response_data.get(
-                                "status",
-                                _event_to_status.get(event_type, "completed"),
+                            terminal_status = cast(
+                                ResponsesAPIStatus,
+                                response_data.get(
+                                    "status",
+                                    _event_to_status.get(event_type, "completed"),
+                                ),
                             )
 
                             # Extract error for failed responses

tests/test_litellm/test_router.py

@@ -643,7 +643,13 @@ def test_arouter_responses_api_bridge():
     ## CONFIRM MODEL NAME IS STRIPPED
     client = HTTPHandler()
 
-    with patch.object(client, "post", return_value=MagicMock()) as mock_post:
+    mock_response = MagicMock()
+    mock_response.status_code = 200
+    mock_response.headers = {"content-type": "application/json"}
+    mock_response.json.return_value = {"id": "resp_test", "object": "response", "status": "completed", "output": []}
+    mock_response.text = '{"id": "resp_test", "object": "response", "status": "completed", "output": []}'
+
+    with patch.object(client, "post", return_value=mock_response) as mock_post:
         try:
             result = router.completion(
                 model="[IP-approved] o3-pro",