perf: optimize system concurrency, I/O stability and fix WebSocket disconnects

backend/services/gateway.py

@@ -148,8 +148,9 @@ class Gateway:
             self.handle_client,
             host,
             port,
-            ping_interval=30,
-            ping_timeout=60,
+            ping_interval=20,
+            ping_timeout=120,
+            max_size=10 * 1024 * 1024,  # 10MB
         )
         logger.info(f"WebSocket server ready: ws://{host}:{port}")
 
@@ -833,12 +834,18 @@ class Gateway:
         if not self.connected_clients:
             return
 
-        message_json = json.dumps(message, ensure_ascii=False, default=str)
+        # Offload potentially heavy JSON serialization to thread
+        message_json = await asyncio.to_thread(
+            json.dumps, message, ensure_ascii=False, default=str
+        )
 
         async with self.lock:
+            # Filter only active clients to minimize unnecessary send attempts
+            # In websockets v13+, we must check state.name == 'OPEN'
+            active_clients = [c for c in self.connected_clients if c.state.name == 'OPEN']
             tasks = [
                 self._send_to_client(client, message_json)
-                for client in self.connected_clients.copy()
+                for client in active_clients
             ]
 
         if tasks:
@@ -849,9 +856,14 @@ class Gateway:
         client: ServerConnection,
         message: str,
     ):
+        if client.state.name != 'OPEN':
+            async with self.lock:
+                self.connected_clients.discard(client)
+            return
+
         try:
             await client.send(message)
-        except websockets.ConnectionClosed:
+        except (websockets.ConnectionClosed, Exception):
             async with self.lock:
                 self.connected_clients.discard(client)