Update app.py

app.py

@@ -140,14 +140,12 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     except Exception as e:
         return f"Error initializing agent: {e}", None
 
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    agent_code = f"[https://huggingface.co/spaces/](https://huggingface.co/spaces/){space_id}/tree/main"
 
     try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
         questions_data = response.json()
-        if not questions_data:
-            return "Fetched questions list is empty or invalid format.", None
     except Exception as e:
         return f"Error fetching questions: {e}", None
 
@@ -163,23 +161,35 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         if not task_id or question_text is None:
             continue
             
+        # --- MODIFICATION: Handle the dictionary output from the agent ---
         try:
-            submitted_answer = 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})
+            agent_result = agent(question_text)
+            # Build the payload with the required keys for submission
+            answers_payload.append({
+                "task_id": task_id,
+                "model_answer": agent_result["model_answer"],
+                "reasoning_trace": agent_result["reasoning_trace"]
+            })
+            # Log for display in the UI
+            results_log.append({
+                "Task ID": task_id,
+                "Question": question_text,
+                "Submitted Answer": agent_result["model_answer"],
+                "Reasoning Trace": agent_result["reasoning_trace"]
+            })
         except Exception as e:
             error_message = f"AGENT ERROR: {e}"
             print(f"Error running agent on task {task_id}: {e}")
             print(traceback.format_exc())
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": error_message})
-            
-        # Add a delay to avoid hitting the API rate limit.
-        print("Pausing for 3 seconds to respect API rate limits...")
-        time.sleep(20)
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": error_message, "Reasoning Trace": ""})
+        
+        print("Pausing for 5 seconds to respect API rate limits...")
+        time.sleep(5)
 
     if not answers_payload:
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
+    # The submission payload is now a list of dictionaries with the correct keys
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
     
     try: