simplify Athena runtime and centralize MCP management

dev/mock_upstream.py

@@ -99,6 +99,9 @@ class Handler(BaseHTTPRequestHandler):
         self.send_header("Connection", "close")
         self.end_headers()
         model = body.get("model")
+        delay = body.get("mock_stream_delay", 0.05)
+        if not isinstance(delay, (int, float)) or delay < 0 or delay > 10:
+            delay = 0.05
         for tok in ["Mock-", "Streaming", "-Antwort", f" ({model})"]:
             chunk = {
                 "id": "chatcmpl-mock",
@@ -109,9 +112,12 @@ class Handler(BaseHTTPRequestHandler):
             }
             self.wfile.write(f"data: {json.dumps(chunk)}\n\n".encode())
             self.wfile.flush()
-            time.sleep(0.05)
-        self.wfile.write(b"data: [DONE]\n\n")
-        self.wfile.flush()
+            time.sleep(delay)
+        try:
+            self.wfile.write(b"data: [DONE]\n\n")
+            self.wfile.flush()
+        except (BrokenPipeError, ConnectionResetError):
+            pass
 
     def _json(self, code: int, payload: dict) -> None:
         body = json.dumps(payload).encode()