fix(realtime): post-tool-call function_response id omission

litellm/llms/custom_httpx/llm_http_handler.py

@@ -5537,9 +5537,7 @@ async def async_realtime(
         import websockets
         from websockets.asyncio.client import ClientConnection
 
-        url = self._append_query_params(
-            provider_config.get_complete_url(api_base, model, api_key), query_params
-        )
+        url = provider_config.get_complete_url(api_base, model, api_key)
         headers = provider_config.validate_environment(
             headers=headers,
             model=model,

litellm/llms/gemini/realtime/transformation.py

@@ -103,6 +103,10 @@ def __init__(self):
         # bypassing spend and budget accounting.
         self._pending_usage_metadata: Optional[dict] = None
 
+    def _include_function_response_id(self) -> bool:
+        """Google AI Studio Gemini 3.5+ accepts ``id`` on functionResponses; Vertex AI rejects it."""
+        return True
+
     @staticmethod
     def _usage_detail_alias(details: Any, defaults: Dict[str, int]) -> Dict[str, Any]:
         if not isinstance(details, dict):
@@ -604,10 +608,9 @@ def _handle_function_call_output(self, item: dict) -> List[str]:
             )
 
         # Build Gemini toolResponse format
-        function_response = {
-            "id": call_id,
-            "response": output_dict,
-        }
+        function_response: dict[str, Any] = {"response": output_dict}
+        if self._include_function_response_id() and call_id:
+            function_response["id"] = call_id
         if function_name:
             function_response["name"] = function_name
 

litellm/llms/vertex_ai/realtime/transformation.py

@@ -32,6 +32,9 @@ def __init__(self, access_token: str, project: str, location: str) -> None:
         self._project = project
         self._location = location
 
+    def _include_function_response_id(self) -> bool:
+        return False
+
     # ------------------------------------------------------------------
     # URL
     # ------------------------------------------------------------------

litellm/main.py

@@ -5044,9 +5044,7 @@ def completion(  # type: ignore
         if LiteLLM_Proxy_MCP_Handler._should_use_litellm_mcp_gateway(
             tools=tools_for_mcp
         ):
-            # Return coroutine - acompletion will await it
-            # completion() can return a coroutine when MCP tools are present, which acompletion() awaits
-            return acompletion_with_mcp(  # type: ignore[return-value]
+            return acompletion_with_mcp(  # pyright: ignore[reportReturnType]  # MCP path returns a coroutine that acompletion() awaits; completion()'s sync return type omits it
                 model=model,
                 messages=messages,
                 functions=functions,
@@ -5218,12 +5216,16 @@ def completion(  # type: ignore
         logging: LiteLLMLoggingObj = cast(LiteLLMLoggingObj, litellm_logging_obj)
         fallbacks = fallbacks or litellm.model_fallbacks
         if fallbacks is not None:
-            return completion_with_fallbacks(**args)
+            return completion_with_fallbacks(  # pyright: ignore[reportReturnType]  # fallback runner is untyped; resolves to ModelResponse|CustomStreamWrapper at runtime
+                **args
+            )
         if model_list is not None:
             deployments = [
                 m["litellm_params"] for m in model_list if m["model_name"] == model
             ]
-            return litellm.batch_completion_models(deployments=deployments, **args)
+            return litellm.batch_completion_models(  # pyright: ignore[reportReturnType]  # batch path returns a list of responses, outside completion()'s single-response return type
+                deployments=deployments, **args
+            )
         if litellm.model_alias_map and model in litellm.model_alias_map:
             model = litellm.model_alias_map[
                 model
@@ -5545,7 +5547,7 @@ def completion(  # type: ignore
                 else:
                     optional_params["reasoning_effort"] = {"summary": rs_val}
 
-            return responses_api_bridge.completion(
+            return responses_api_bridge.completion(  # pyright: ignore[reportReturnType]  # bridge returns a coroutine on the acompletion path; awaited by the async caller
                 model=model,
                 messages=messages,
                 headers=headers,

tests/test_litellm/llms/vertex_ai/realtime/test_vertex_ai_realtime_transformation.py

@@ -346,3 +346,74 @@ def test_vertex_does_not_warn_when_dropping_non_guardrail_session_update(caplog)
         "Vertex AI Realtime" in record.message and "session.update" in record.message
         for record in caplog.records
     )
+
+
+async def test_async_realtime_does_not_forward_client_query_params_to_vertex_backend(
+    monkeypatch,
+):
+    """Regression: forwarding client ?model=/?intent= to the Vertex Live WSS URL causes 1007 errors.
+
+    Exercises ``async_realtime`` end-to-end so that re-adding ``_append_query_params``
+    (the reverted bug) would push ``model=``/``intent=`` onto the backend URL and fail here.
+    """
+    import websockets
+
+    from litellm.llms.custom_httpx.llm_http_handler import BaseLLMHTTPHandler
+
+    cfg = VertexAIRealtimeConfig(
+        access_token="tok", project="my-proj", location="us-central1"
+    )
+
+    captured = {}
+
+    def fake_connect(url, *args, **kwargs):
+        captured["url"] = url
+        raise RuntimeError("stop before establishing the backend connection")
+
+    monkeypatch.setattr(websockets, "connect", fake_connect)
+
+    await BaseLLMHTTPHandler().async_realtime(
+        model="gemini-live-2.5-flash-native-audio",
+        websocket=AsyncMock(),
+        logging_obj=MagicMock(),
+        provider_config=cfg,
+        headers={},
+        query_params={
+            "model": "gemini-live-2.5-flash-native-audio",
+            "intent": "chat",
+        },
+    )
+
+    assert "?" not in captured["url"]
+    assert "model=" not in captured["url"]
+    assert "intent=" not in captured["url"]
+
+
+def test_vertex_function_call_output_omits_id():
+    """Regression: Vertex Live rejects ``id`` on toolResponse.functionResponses (1007)."""
+    cfg = VertexAIRealtimeConfig(
+        access_token="tok", project="my-proj", location="us-central1"
+    )
+    cfg._tool_call_id_to_name["call_abc123"] = "terminate_call"
+
+    messages = cfg.transform_realtime_request(
+        json.dumps(
+            {
+                "type": "conversation.item.create",
+                "item": {
+                    "type": "function_call_output",
+                    "call_id": "call_abc123",
+                    "output": '{"status": "ok"}',
+                },
+            }
+        ),
+        "gemini-live-2.5-flash-native-audio",
+        session_configuration_request="existing",
+    )
+
+    assert len(messages) == 1
+    payload = json.loads(messages[0])
+    function_response = payload["toolResponse"]["functionResponses"][0]
+    assert "id" not in function_response
+    assert function_response["name"] == "terminate_call"
+    assert function_response["response"] == {"status": "ok"}