feat(observability): wire request metrics into PryHttpMiddleware

api.py

@@ -47,7 +47,7 @@ from extractor import SchemaExtractor
 from mconfig import PryConfig
 from mcp_production import make_fallback_server, register_all
 from mcp_sse import mcp_post_message, mcp_sse_endpoint
-from observability import get_metrics_output, setup_tracing
+from observability import REQUEST_COUNT, REQUEST_LATENCY, get_metrics_output, setup_tracing
 from pipeline import HOOK_POINTS, get_pipeline, run_pipeline
 from pryextras import BatchProcessor, TransformEngine, recorder, streams
 from routers.auth import router as auth_router
@@ -254,8 +254,10 @@ class PryHttpMiddleware:
         start = time.time()
         request_id = self._get_header(scope, b"x-request-id") or uuid.uuid4().hex[:12]
         path = scope.get("path", "")
+        method = scope.get("method", "GET")
         client = scope.get("client")
         ip = client[0] if client else "unknown"
+        response_status = 200
 
         # Authentication check
         api_key = settings.api_key
@@ -329,7 +331,9 @@ class PryHttpMiddleware:
         request_id_bytes = request_id.encode()
 
         async def wrapped_send(message: dict[str, Any]) -> None:
+            nonlocal response_status
             if message["type"] == "http.response.start":
+                response_status = message.get("status", 200)
                 headers = list(message.get("headers", []))
                 headers.append((b"x-ratelimit-limit", ratelimit_limit))
                 headers.append((b"x-ratelimit-remaining", ratelimit_remaining))
@@ -341,12 +345,16 @@ class PryHttpMiddleware:
         await self.app(scope, receive, wrapped_send)
 
         elapsed = time.time() - start
+        if REQUEST_COUNT and REQUEST_LATENCY:
+            REQUEST_COUNT.labels(method=method, endpoint=path, status=str(response_status)).inc()
+            REQUEST_LATENCY.labels(endpoint=path).observe(elapsed)
         logger.info(
             "request_end",
             extra={
                 "request_id": request_id,
-                "method": scope.get("method", "GET"),
+                "method": method,
                 "path": path,
+                "status": response_status,
                 "duration": f"{elapsed:.3f}s",
             },
         )