Update app.py

app.py

@@ -2,166 +2,149 @@ import os
 import gradio as gr
 import requests
 import pandas as pd
+import json
 
 # Import your upgraded agent
 from agent import GeminiAgent
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-# This is the security gate. Only this user can run submissions.
 MY_HF_USERNAME = "benjipeng"
+ANSWERS_FILE = "answers.json"
 
-def run_and_submit_all(profile: gr.OAuthProfile | None):
+# --- Logic for Running the Agent ---
+def run_agent_only(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the GeminiAgent on them, submits all answers,
-    and displays the results. This function is restricted to a specific user and
-    provides file context to the agent.
+    Fetches questions, runs the agent on them, and saves the answers to a file.
+    This is the long-running part of the process.
     """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID")
-
-    # --- User Authentication and Authorization ---
-    if not profile:
-        return "Please Login to Hugging Face with the button to run the evaluation.", None
-    
-    username = profile.username
-    print(f"User logged in: {username}")
+    if not profile or profile.username != MY_HF_USERNAME:
+        yield "Error: Please log in as the correct user (`benjipeng`) to run the agent.", pd.DataFrame()
+        return
 
-    if username != MY_HF_USERNAME:
-        print(f"Access denied for user: {username}. Allowed user is {MY_HF_USERNAME}.")
-        return f"Error: This Space is configured for a specific user. Access denied for '{username}'.", None
-    
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
+    print("Starting agent run...")
+    yield "Fetching questions...", pd.DataFrame()
 
-    # 1. Instantiate Agent
-    print("Instantiating agent...")
     try:
-        agent = GeminiAgent()
-    except Exception as e:
-        error_msg = f"Error initializing agent: {e}"
-        print(error_msg)
-        return error_msg, None
-    
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(f"Code link for submission: {agent_code}")
-
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
-    try:
-        response = requests.get(questions_url, timeout=20)
+        response = requests.get(f"{DEFAULT_API_URL}/questions", timeout=20)
         response.raise_for_status()
         questions_data = response.json()
-        if not questions_data:
-             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:
-        error_msg = f"Error fetching questions: {e}"
-        print(error_msg)
-        return error_msg, None
-    except requests.exceptions.JSONDecodeError as e:
-         error_msg = f"Error decoding server response for questions: {e}"
-         print(error_msg)
-         print(f"Response text: {response.text[:500]}")
-         return error_msg, None
-
-    # 3. Run your Agent (with context injection)
+    except Exception as e:
+        yield f"Error fetching questions: {e}", pd.DataFrame()
+        return
+    
+    yield f"Fetched {len(questions_data)} questions. Initializing agent...", pd.DataFrame()
+    agent = GeminiAgent()
+    
+    all_answers = []
     results_log = []
-    answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+
+    for i, item in enumerate(questions_data):
         task_id = item.get("task_id")
         question_text = item.get("question")
-        
-        # This is the key improvement: check if a file is associated with the question
         has_file = item.get("file", None) is not None
         
-        if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
-            continue
-
-        # Modify the question to give the agent context about the file's existence
-        if has_file:
-            modified_question = f"{question_text}\n\n[Agent Note: A file is attached to this question. Use the 'read_file_from_api' tool to access it if needed.]"
-        else:
-            modified_question = question_text
-
+        status_message = f"Processing question {i+1}/{len(questions_data)} (Task ID: {task_id})..."
+        yield status_message, pd.DataFrame(results_log)
+        
+        modified_question = f"{question_text}\n\n[Agent Note: A file is attached.]" if has_file else question_text
+        
         try:
-            # Pass BOTH the modified question and the task_id to the agent
             submitted_answer = agent(modified_question, task_id)
-            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}"})
+            submitted_answer = f"AGENT ERROR: {e}"
+        
+        all_answers.append({"task_id": task_id, "submitted_answer": submitted_answer})
+        results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
 
-    if not answers_payload:
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+        # Save progress incrementally
+        with open(ANSWERS_FILE, 'w') as f:
+            json.dump(all_answers, f, indent=2)
 
-    # 4. Prepare Submission 
+    yield f"Agent run complete. All {len(all_answers)} answers saved to {ANSWERS_FILE}. Ready to submit.", pd.DataFrame(results_log)
+
+
+# --- Logic for Submitting Answers ---
+def submit_saved_answers(profile: gr.OAuthProfile | None):
+    """
+    Reads the answers from the saved file and submits them to the scoring server.
+    This is the fast part of the process.
+    """
+    if not profile or profile.username != MY_HF_USERNAME:
+        return "Error: Please log in as the correct user (`benjipeng`) to submit."
+
+    space_id = os.getenv("SPACE_ID")
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    username = profile.username
+
+    try:
+        with open(ANSWERS_FILE, 'r') as f:
+            answers_payload = json.load(f)
+    except FileNotFoundError:
+        return f"Error: Answers file '{ANSWERS_FILE}' not found. Please run the agent first."
+    except json.JSONDecodeError:
+        return f"Error: Could not read the answers file. It might be corrupted."
+
+    if not answers_payload:
+        return "Error: Answers file is empty."
+        
     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)
+    
+    submit_url = f"{DEFAULT_API_URL}/submit"
+    print(f"Submitting {len(answers_payload)} answers for user '{username}'...")
 
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=120) # Increased timeout
+        response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
         result_data = response.json()
-        final_status = (
+        return (
             f"Submission Successful!\n"
             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.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
+        return f"Submission Failed: Server responded with status {e.response.status_code}. Detail: {e.response.text}"
+    except Exception as e:
+        return f"An unexpected error occurred during submission: {e}"
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Gemini ReAct Agent for GAIA")
+    gr.Markdown("# Gemini ReAct Agent for GAIA (Two-Step Submission)")
     gr.Markdown(
         """
-        **Instructions:**
-        1.  Log in using the Hugging Face login button below.
-        2.  Click 'Run Evaluation & Submit' to start the process.
-        3.  The agent will fetch all 20 questions, reason about them step-by-step, use tools (like web search and a file reader), and submit the final answers for scoring.
-
-        **Note:** This process can take several minutes. Please be patient.
+        **Step 1: Run Agent & Save Answers**
+        - This is the long process that can take 10-20 minutes.
+        - The agent will answer all 20 questions and save the results to a file.
+        - You will see the progress in the status box and the table below.
+        
+        **Step 2: Submit Saved Answers**
+        - Once Step 1 is complete, click this button.
+        - This will be very fast and will send your saved answers to be scored.
         """
     )
+    
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    with gr.Row():
+        run_button = gr.Button("Step 1: Run Agent & Save Answers")
+        submit_button = gr.Button("Step 2: Submit Saved 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)
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True, interactive=False)
 
     run_button.click(
-        fn=run_and_submit_all,
+        fn=run_agent_only,
+        inputs=None, # LoginButton profile is passed implicitly
         outputs=[status_output, results_table]
     )
+    
+    submit_button.click(
+        fn=submit_saved_answers,
+        inputs=None, # LoginButton profile is passed implicitly
+        outputs=[status_output]
+    )
 
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)