feat: 建立可观测性、容量与恢复验证基线

ai-service/app/main.py

@@ -2,6 +2,7 @@ import shutil
 import subprocess
 import threading
 import time
+import uuid
 
 from fastapi import FastAPI, File, HTTPException, Request, UploadFile
 
@@ -21,8 +22,10 @@ stream_worker = StreamTaskWorker(config.STREAM_TASK_MAX_WORKERS)
 async def count_requests(request: Request, call_next):
     global _requests, _latency_total
     start = time.time()
+    request_id = request.headers.get("x-request-id") or str(uuid.uuid4())
     response = await call_next(request)
     latency = (time.time() - start) * 1000
+    response.headers["X-Request-ID"] = request_id
     with _lock:
         _requests += 1
         _latency_total += latency