Update app.py

app.py

@@ -7,6 +7,9 @@ import random
 from transformers import Tool
 from transformers.agents import Agent
 
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
 # --- Enhanced Agent Definition ---
 class EnhancedAgent:
     def __init__(self):
@@ -61,84 +64,166 @@ class EnhancedAgent:
             print(f"Agent error: {e}")
             return "I couldn't find an answer to that question."
 
-# --- Gradio App ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """Main function to run evaluation"""
-    if not profile:
-        return "Please login with your Hugging Face account", None
-    
-    username = profile.username
-    api_url = os.getenv("API_URL", "https://agents-course-unit4-scoring.hf.space")
+    """
+    Fetches all questions, runs the EnhancedAgent on them, submits all answers,
+    and displays the results.
+    """
+    # --- Determine HF Space Runtime URL and Repo URL ---
+    space_id = os.getenv("SPACE_ID")
+
+    if profile:
+        username = f"{profile.username}"
+        print(f"User logged in: {username}")
+    else:
+        print("User not logged in.")
+        return "Please Login to Hugging Face with the button.", None
+
+    api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
-    space_id = os.getenv("SPACE_ID", "your-space-id")
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
 
+    # 1. Instantiate Agent
     try:
         agent = EnhancedAgent()
-        
-        # Fetch questions
+    except Exception as e:
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
+    
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
+
+    # 2. Fetch Questions
+    print(f"Fetching questions from: {questions_url}")
+    try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
         questions_data = response.json()
-        
         if not questions_data:
-            return "No questions received from server", None
-
-        # Process questions
-        results_log = []
-        answers_payload = []
-        for item in questions_data:
-            task_id = item.get("task_id")
-            question = item.get("question")
-            if not task_id or not question:
-                continue
-            
-            try:
-                answer = agent(question)
-                answers_payload.append({"task_id": task_id, "submitted_answer": answer})
-                results_log.append({"Task ID": task_id, "Question": question, "Answer": answer})
-            except Exception as e:
-                results_log.append({"Task ID": task_id, "Question": question, "Answer": f"Error: {str(e)}"})
-
-        # Submit answers
-        submission_data = {
-            "username": username,
-            "agent_code": agent_code,
-            "answers": answers_payload
-        }
+             print("Fetched questions list is empty.")
+             return "Fetched questions list is empty or invalid format.", None
+        print(f"Fetched {len(questions_data)} questions.")
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching questions: {e}")
+        return f"Error fetching questions: {e}", None
+    except requests.exceptions.JSONDecodeError as e:
+         print(f"Error decoding JSON response from questions endpoint: {e}")
+         print(f"Response text: {response.text[:500]}")
+         return f"Error decoding server response for questions: {e}", None
+    except Exception as e:
+        print(f"An unexpected error occurred fetching questions: {e}")
+        return f"An unexpected error occurred fetching questions: {e}", None
+
+    # 3. Run your Agent
+    results_log = []
+    answers_payload = []
+    print(f"Running agent on {len(questions_data)} questions...")
+    for item in questions_data:
+        task_id = item.get("task_id")
+        question_text = item.get("question")
+        if not task_id or question_text is None:
+            print(f"Skipping item with missing task_id or question: {item}")
+            continue
+        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})
+        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}"})
+
+    if not answers_payload:
+        print("Agent did not produce any answers to submit.")
+        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+
+    # 4. Prepare Submission 
+    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
+    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    print(status_update)
+
+    # 5. Submit
+    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
-        result = response.json()
-        
-        return (
+        result_data = response.json()
+        final_status = (
             f"Submission Successful!\n"
-            f"Score: {result.get('score', 'N/A')}%\n"
-            f"Correct: {result.get('correct_count', '?')}/{result.get('total_attempted', '?')}\n"
-            f"Message: {result.get('message', '')}",
-            pd.DataFrame(results_log)
+            f"User: {result_data.get('username')}\n"
+            f"Overall Score: {result_data.get('score', 'N/A')}% "
+            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
+            f"Message: {result_data.get('message', 'No message received.')}"
         )
-        
+        print("Submission successful.")
+        results_df = pd.DataFrame(results_log)
+        return final_status, results_df
+    except requests.exceptions.HTTPError as e:
+        error_detail = f"Server responded with status {e.response.status_code}."
+        try:
+            error_json = e.response.json()
+            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
+        except requests.exceptions.JSONDecodeError:
+            error_detail += f" Response: {e.response.text[:500]}"
+        status_message = f"Submission Failed: {error_detail}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+    except requests.exceptions.Timeout:
+        status_message = "Submission Failed: The request timed out."
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+    except requests.exceptions.RequestException as e:
+        status_message = f"Submission Failed: Network error - {e}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
     except Exception as e:
-        return f"Error: {str(e)}", None
+        status_message = f"An unexpected error occurred during submission: {e}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
 
-# --- Gradio Interface ---
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("""
-    # Hugging Face Agent Evaluation
-    Submit your agent to be evaluated against the benchmark questions.
-    """)
-    
+    gr.Markdown("# Enhanced Agent Evaluation Runner")
+    gr.Markdown(
+        """
+        **Instructions:**
+        1. Log in to your Hugging Face account using the button below.
+        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run the enhanced agent, submit answers, and see the score.
+
+        **Agent Capabilities:**
+        - Math calculations
+        - Current time lookup
+        - Random choice selection
+        - Complex question handling via AI
+        """
+    )
+
     gr.LoginButton()
-    run_btn = gr.Button("Run Evaluation & Submit Answers")
-    
-    status_output = gr.Textbox(label="Results", interactive=False)
-    results_table = gr.DataFrame(label="Question Log", wrap=True)
-    
-    run_btn.click(
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+
+    run_button.click(
         fn=run_and_submit_all,
         outputs=[status_output, results_table]
     )
 
 if __name__ == "__main__":
-    demo.launch()
+    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    space_host_startup = os.getenv("SPACE_HOST")
+    space_id_startup = os.getenv("SPACE_ID")
+
+    if space_host_startup:
+        print(f"✅ SPACE_HOST found: {space_host_startup}")
+        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+
+    if space_id_startup:
+        print(f"✅ SPACE_ID found: {space_id_startup}")
+        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
+
+    print("-"*(60 + len(" App Starting ")) + "\n")
+    print("Launching Gradio Interface for Enhanced Agent Evaluation...")
+    demo.launch(debug=True, share=False)