Add system prompt, add correct stop tokens

app.py

@@ -86,9 +86,12 @@ def stream_response(message, history, max_tokens, temperature, top_p):
         "messages": messages,
         "max_tokens": max_tokens,
         "temperature": temperature,
+        "system" : "You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.",
         "top_p": top_p,
         "stream": True,
-        "stop": ["</output>"]  # Add stop sequence
+        "stop": [ "<|start_header_id|>",
+        "<|end_header_id|>",
+        "<|eot_id|>"]  # Add stop sequence
     }
     
     debug_print(f"Sending request to API: {API_URL}")