app.py

import os
import gradio as gr
import requests
import pandas as pd
import logging
import time
import traceback
from typing import Dict, Any, Optional, Tuple, List, Union

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# --- Import our GAIA Agent ---
from gaia_agent import GAIAAgent

# Configure logging
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger("gaia_evaluation")

# Initialize the GAIA Agent
def initialize_agent():
    try:
        agent = GAIAAgent()
        logger.info("GAIA Agent initialized successfully")
        return agent
    except Exception as e:
        logger.error(f"Error initializing GAIA Agent: {e}")
        logger.error(traceback.format_exc())
        return None

# Important: Match the exact signature from the template
def run_and_submit_all(profile=None):
    """
    Fetches all questions, runs the GAIA Agent on them, submits all answers,
    and displays the results.
    """
    # --- Determine HF Space Runtime URL and Repo URL ---
    space_id = os.getenv("SPACE_ID", "")

    # Check if user is signed in
    if profile:
        if hasattr(profile, 'username'):
            username = profile.username
            logger.info(f"User logged in: {username}")
        else:
            username = str(profile)
            logger.info(f"Using provided username: {username}")
    else:
        logger.warning("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"

    # 1. Instantiate Agent
    try:
        agent = initialize_agent()
        if agent is None:
            error_msg = "Error initializing GAIA Agent. Check logs for details."
            logger.error(error_msg)
            return error_msg, None
    except Exception as e:
        error_msg = f"Error instantiating agent: {e}"
        logger.error(error_msg)
        return error_msg, None
        
    # Link to the code repository in Hugging Face Space
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    logger.info(f"Using agent code URL: {agent_code}")

    # 2. Fetch Questions
    logger.info(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:
             logger.warning("Fetched questions list is empty.")
             return "Fetched questions list is empty or invalid format.", None
        logger.info(f"Fetched {len(questions_data)} questions.")
    except requests.exceptions.RequestException as e:
        error_msg = f"Error fetching questions: {e}"
        logger.error(error_msg)
        return error_msg, None
    except requests.exceptions.JSONDecodeError as e:
         error_msg = f"Error decoding JSON response from questions endpoint: {e}"
         logger.error(f"{error_msg}\nResponse text: {response.text[:500]}")
         return error_msg, None
    except Exception as e:
        error_msg = f"An unexpected error occurred fetching questions: {e}"
        logger.error(error_msg)
        logger.error(traceback.format_exc())
        return error_msg, None

    # 3. Run the GAIA Agent on all questions
    results_log = []
    answers_payload = []
    logger.info(f"Running agent on {len(questions_data)} questions...")
    
    for i, item in enumerate(questions_data):
        # Extract question information
        task_id = item.get("task_id", item.get("id", f"q{i+1}"))
        question_text = item.get("question")
        
        if not task_id or question_text is None:
            logger.warning(f"Skipping item with missing task_id or question: {item}")
            continue
            
        logger.info(f"Processing question {i+1}/{len(questions_data)}: {question_text[:50]}...")
        start_time = time.time()
        
        try:
            # Process the question with the GAIA Agent
            submitted_answer = agent.process_question(question_text)
            processing_time = time.time() - start_time
            
            # Add to submission payload
            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
            
            # Store for results display
            results_log.append({
                "Task ID": task_id,
                "Question": question_text,
                "Submitted Answer": submitted_answer,
                "Processing Time": f"{processing_time:.2f}s",
                "Status": "Success"
            })
            
            logger.info(f"Question {i+1} processed successfully in {processing_time:.2f}s")
            
        except Exception as e:
            error_msg = f"Error running agent on task {task_id}: {e}"
            logger.error(error_msg)
            logger.error(traceback.format_exc())
            
            results_log.append({
                "Task ID": task_id,
                "Question": question_text,
                "Submitted Answer": f"AGENT ERROR: {e}",
                "Processing Time": f"{time.time() - start_time:.2f}s",
                "Status": "Error"
            })

    # Check if we have answers to submit
    if not answers_payload:
        logger.warning("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}'..."
    logger.info(status_update)

    # 5. Submit
    logger.info(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_data = response.json()
        
        # Extract results data
        correct_count = result_data.get("correct_count", 0)
        total_attempted = result_data.get("total_attempted", 0)
        score = result_data.get("score", "N/A")
        
        final_status = (
            f"Submission Successful!\n"
            f"User: {result_data.get('username', username)}\n"
            f"Overall Score: {score}% "
            f"({correct_count}/{total_attempted} correct)\n"
            f"Message: {result_data.get('message', 'No message received.')}"
        )
        logger.info("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:
            error_detail += f" Response: {e.response.text[:500]}"
        status_message = f"Submission Failed: {error_detail}"
        logger.error(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."
        logger.error(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}"
        logger.error(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except Exception as e:
        status_message = f"An unexpected error occurred during submission: {e}"
        logger.error(status_message)
        logger.error(traceback.format_exc())
        results_df = pd.DataFrame(results_log)
        return status_message, results_df


# --- Build Gradio Interface using Blocks ---
with gr.Blocks() as demo:
    gr.Markdown("# GAIA Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**

        1. Log in to your Hugging Face account using the button below. This uses your HF username for submission.
        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run the GAIA agent, submit answers, and see the score.

        ---
        **Note:** Running the evaluation may take some time as the agent processes all questions. Please be patient.
        """
    )

    # Create login button
    login_btn = gr.LoginButton()
    
    # Output text and result areas
    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
    run_button = gr.Button("Run Evaluation & Submit All Answers")

    # Set up event handler (simplified)
    run_button.click(
        fn=run_and_submit_all,
        inputs=login_btn,  # Connect login button directly
        outputs=[status_output, results_table]
    )

if __name__ == "__main__":
    print("\n" + "-"*30 + " App Starting " + "-"*30)
    # Check for SPACE_HOST and SPACE_ID at startup for information
    space_host_startup = os.getenv("SPACE_HOST")
    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup

    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:
        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")

    if space_id_startup: # Print repo URLs if SPACE_ID is found
        print(f"✅ SPACE_ID found: {space_id_startup}")
        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
        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.")

    print("-"*(60 + len(" App Starting ")) + "\n")

    print("Launching Gradio Interface for GAIA Agent Evaluation...")
    # Determine launch parameters based on environment
    is_running_in_space = bool(space_host_startup and space_id_startup)
    
    if is_running_in_space:
        # Production settings for Hugging Face Space
        demo.launch(
            debug=False,
            share=False,
            server_name="0.0.0.0"
        )
    else:
        # Development settings for local testing
        demo.launch(
            debug=True,
            share=False
        )