Update app.py

app.py

@@ -159,12 +159,19 @@ class XylariaChat:
                 content=user_input
             ).to_dict())
 
+            # Calculate available tokens
+            input_tokens = sum(len(msg['content'].split()) for msg in messages)
+            max_new_tokens = 16384 - input_tokens - 50 # Reserve some tokens for safety
+
+            # Limit max_new_tokens to prevent exceeding the total limit
+            max_new_tokens = min(max_new_tokens, 10020)
+
             # Generate response with streaming
             stream = self.client.chat_completion(
                 messages=messages,
                 model="Qwen/QwQ-32B-Preview",
                 temperature=0.7,
-                max_tokens=16384,
+                max_tokens=max_new_tokens,
                 top_p=0.9,
                 stream=True
             )