Update app.py

app.py

@@ -45,13 +45,50 @@ async def run_and_submit_all(profile: gr.OAuthProfile | None):
         question_text = item.get("question")
         if not task_id or question_text is None:
             continue
-        try:
-            loop = asyncio.get_event_loop()
-            submitted_answer = await loop.run_in_executor(None, agent, question_text)
-            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
-        except Exception as e:
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+        # 1. Add system prompt before the question
+system_prompt = (
+    "You are a general AI assistant. I will ask you a question. "
+    "Report your thoughts, and finish your answer with the following template: "
+    "FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. "
+    "If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. "
+    "If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. "
+    "If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.\n\n"
+)
+full_prompt = system_prompt + f"Question: {question_text.strip()}"
+
+try:
+    agent_response = agent(full_prompt)
+
+    # 2. Extract final answer and reasoning
+    if "FINAL ANSWER:" in agent_response:
+        reasoning_trace, final_answer = agent_response.rsplit("FINAL ANSWER:", 1)
+        final_answer = final_answer.strip()
+        reasoning_trace = reasoning_trace.strip()
+    else:
+        final_answer = agent_response.strip()
+        reasoning_trace = "Model did not follow format; full response returned."
+
+    answer_entry = {
+        "task_id": task_id,
+        "model_answer": final_answer,
+        "reasoning_trace": reasoning_trace
+    }
+    answers_payload.append(answer_entry)
+    results_log.append({
+        "Task ID": task_id,
+        "Question": question_text,
+        "Submitted Answer": final_answer,
+        "Reasoning Trace": reasoning_trace
+    })
+
+except Exception as e:
+    print(f"Error running agent on task {task_id}: {e}")
+    results_log.append({
+        "Task ID": task_id,
+        "Question": question_text,
+        "Submitted Answer": f"AGENT ERROR: {e}",
+        "Reasoning Trace": "N/A"
+    })
 
     if not answers_payload:
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)