Update app.py

app.py

@@ -177,19 +177,180 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     results_log = [] # Used to make a DataFrame for UI display (question + answer)
     answers_payload = [] # sent to grading API in the final submission
 
+    # Loops through each question:
     for item in questions_data:
+        # Extracts task_id
         task_id = item.get("task_id")
+        # Extracts the question
         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
+        # Use your agent (__call__) to answer the question
+        # Logs both result and metadata
         try: 
             submitted_answer = agent(question_text)
             answers_payload.append({"task_id": task_id, "submmitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+        # On failure (bad formatting, model error, etc), logs an error message in the results.
         except Exception as e:
             print(f"Erron running agent on task {task_id}: {e}")
-            results_log.append
-    
+            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 asnwer to submit.")
+        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+    # 4. Prepare submission
+    # A JSON-safe dict with everything the backend expects: Username (from loging), Code link (for peer review or reproducibility), All answers in the required format
+    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:
+        # submits the payload to the grading server.
+        response = requests.post(submit_url, json=submission_data, timeout=60)
+        
+        response.raise_for_status()
+        # if succesful;
+        result_data = response.json()
+        # Parse final score
+        final_status = (
+            f"Submission Succesful!\n"
+            f"User: {result_data.get('username')}\n"
+            # Final score
+            f"Overall Score: {result_data.get('score','N/A')}%"
+            # Number of correct answers
+            f"({result_data.get('correct_count','?')}/{result_data.get('total_attempted','?')} correct)\n"
+            # Backend message
+            f"Message: {result_data.get('message','No message received.')}"
+        )
+        print("Submission succesful.")
+        results_df = pd.DataFrame(results_log)
+        # Return a user-friendly summary string and a Pandas Dataframe to display in Gradio
+        return final_status, results_df
+    # Handles possible errors
+    # Catchees and logs:
+    # - HTTP errors
+    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)}"
+        # Unexpected server responses
+        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
+    # - Timeout error
+    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
+    # Network issues
+    except Exception as e:
+        status_message = f"An unexpected error occurred during submission: {e}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        # Ensure the return is still clean, with a Dataframe of what happened so far.
+        return status_message, results_df
 
-    
+# --- build Gradio Interface using Blocks ---
+# Layout-based API
+with gr.Blocks() as demo:
+    # Display the title
+    gr.Markdown("# Basic Agent Evaluation Runner")
+    # Display the instructions
+    gr.Markdown(
+        """
+        **Instructions:**
+
+        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
+        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
+        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+
+        ---
+        **Disclaimers:**
+        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
+        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        
+        """
+    )
+    # Hugging Face Login button - allows users to authenticate with Hugging Face OAuth.
+    # This is required for tracking who is submitting.
+    # It returns a profile object once logged in.
+    gr.LoginButton()
+
+    # Define a Button to Trigger the Agent Run
+    # When clicked ,Instantiate your BasicAgent, Fetch questions, Run the agent, Submit answers,Show results
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    # Output Display Components
+    # shows messages like “Submission Successful” or errors.
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+
+    # Removed max_rows=10 from DataFrame constructor
+    # displays a log of all questions and answers in tabular form.
+    # Useful for transparency or debugging agent behavior.
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+
+    # Connect Logic to the Button
+    # This is where everything connects together.
+    # Whent the button is clicked;
+    # 1. Runs run_and_submit_all(profile)
+    # 2. The login_button provides the gr.OAuthProfile
+    # 3. The return value (status + DataFrame) is sent to the Textbox and Dataframe.
+    run_button.click(
+        fn=run_and_submit_all,
+        outputs=[status_output, results_table]
+    )
+
+    # Entry point for the Python app.
+    ## controls what happens when the script is run directly (e.g. on HF Space or locally).
+    ### Purpose: main execution trigger
+    #### * Checks for environment setup (SPACE_HOST, SPACE_ID)
+    ##### * Provides useful diagnostics (like URLs)
+    ###### * Finally, it launches the Gradio app interface.
+    # A standard Python syntax to ensure the code only runs if the file is executed directly (not imported as module)
+    # Since app.py is the main file, this block is the app's entry point.
+    if __name__ == "__main__":
+        # Login app startup
+        # Pretty foramtion to indicate that the app is initializing.
+        # Outputs a visible header 
+        print("\n" + "-"*30 + " App Starting " + "-"*30) # ------------------------------ App Starting ------------------------------
+        # Check for SPACE_HOST and SPACE_ID at startup for information
+        # Check for HF environment variables
+        # NOTE: These are automatically set when the app is deployed on Hugging Face Spaces.
+        space_host_startup = os.getenv("SPACE_HOST") # subdomain for the Space (e.g., my-agent-space)
+        space_id_startup = os.getenv("SPACE_ID")  # repo path (e.g., username/space-name)
+    
+        # Print SPACE_HOST info
+        # If found, it logs the public URL of your Space.
+        if space_host_startup:
+            print(f"✅ SPACE_HOST found: {space_host_startup}")
+            print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+        else:
+            # If not found, the app might be running locally or in a non-Space environment.
+            print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+        # If found, it prints:
+        if space_id_startup:
+            # The repo homepage (good for credit/visibility)
+            print(f"✅ SPACE_ID found: {space_id_startup}")
+            # The repo tree (code browser)
+            print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
+            # These links are often included in the final submission for review.
+            print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
+        else:
+            print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+        # 🔹 Final log and UI launch
+        # Finishes the startup banner and logs a message that the UI is about to appear.
+        print("-"*(60 + len(" App Starting ")) + "\n")
+        print("Launching Gradio Interface for Basic Agent Evaluation...")
+    
+        # LAUNCH THE APP
+        # debug=True: Gradio will print extra logs (useful during development).
+        # share=False: disables Gradio's external link feature (you don’t need it on Hugging Face Spaces).
+        demo.launch(debug=True, share=False)  # starts the Gradio interface.
+