fix: ensure responses stream always completes

Emit a fallback response.completed and [DONE] when upstream SSE closes early so OpenAI /v1/responses clients do not fail on incomplete streams.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

app/main.py

@@ -1193,6 +1193,21 @@ async def _responses_stream_from_chat_stream(
                         }
                     )
 
+    yield _sse_data(
+        {
+            "type": "response.completed",
+            "response": {
+                "id": response_id,
+                "object": "response",
+                "created_at": created_at,
+                "status": "completed",
+                "model": model,
+                "usage": usage,
+            },
+        }
+    )
+    yield "data: [DONE]\\n\\n"
+
 
 
 @app.post("/v1/responses", dependencies=[Depends(auth_guard)])