app_local.py

# /Users/yagoairm2/Desktop/agents/final project/HF_Agents_Final_Project/app_local.py
"""
A simplified version of app2.py that works better for local development.
This version doesn't require OAuth authentication and uses a test username instead.
"""

import os
import sys
import gradio as gr
import requests
import pandas as pd
import json
import re
import time
import logging
import io
import contextlib
from typing import Dict, List, Optional, Union, Any
from pathlib import Path
try:
    from dotenv import load_dotenv
except ImportError:
    print("dotenv not found. Using os.environ only.")
    def load_dotenv():
        pass

# Configure logging
logging.basicConfig(
    level=logging.INFO, 
    format='%(asctime)s - %(levelname)s - %(message)s',
    handlers=[logging.StreamHandler()]
)
logger = logging.getLogger(__name__)

# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
DEFAULT_FILES_DIR = "dataset"
SYSTEM_PROMPT = """
You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
"""

# --- Mock Agent Implementation ---
class MockAgent:
    """A simple agent that returns mock answers for testing purposes."""
    
    def __init__(self):
        logger.info("Initializing Mock Agent")
    
    def __call__(self, question: str) -> str:
        """Return a mock answer based on the question content."""
        logger.info(f"Mock Agent received question: {question[:50]}...")
        
        # Return different mock answers based on question content
        if "how many" in question.lower():
            answer = "42"
        elif "what is" in question.lower():
            answer = "Example answer for a what-is question"
        elif "?" in question:
            answer = "Yes, that is correct."
        else:
            answer = "This is a mock answer for testing purposes."
        
        logger.info(f"Mock Agent returning answer: {answer}")
        return answer

# --- Runner Function for Gradio Interface ---
def run_and_submit_all(test_username: str = "test_user"):
    """
    Fetches all questions, runs the agent on them, submits answers,
    and displays the results.
    """
    if not test_username:
        test_username = "test_user"
        
    print(f"Using test username: {test_username}")
    
    api_url = DEFAULT_API_URL
    questions_url = f"{api_url}/questions"
    submit_url = f"{api_url}/submit"

    # 1. Instantiate Agent
    try:
        agent = MockAgent()  # Use the mock agent for testing
    except Exception as e:
        print(f"Error instantiating agent: {e}")
        return f"Error initializing agent: {e}", None
        
    agent_code = "https://huggingface.co/spaces/test/test/tree/main"  # Mock URL

    # 2. Fetch Questions (or use local file for faster testing)
    questions_file = "question_set/common_questions.json"
    if os.path.exists(questions_file):
        print(f"Using local questions file: {questions_file}")
        try:
            with open(questions_file, 'r') as f:
                questions_data = json.load(f)
            print(f"Loaded {len(questions_data)} questions from local file.")
            # For testing, limit to just a few questions
            questions_data = questions_data[:3]
            print(f"Limited to first {len(questions_data)} questions for testing.")
        except Exception as e:
            print(f"Error loading questions from local file: {e}")
            return f"Error loading questions from local file: {e}", None
    else:
        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:
                print("Fetched questions list is empty.")
                return "Fetched questions list is empty or invalid format.", None
            print(f"Fetched {len(questions_data)} questions.")
            # For testing, limit to just a few questions
            questions_data = questions_data[:3]
            print(f"Limited to first {len(questions_data)} questions for testing.")
        except Exception as e:
            print(f"Error fetching questions: {e}")
            return f"Error fetching questions: {e}", None

    # 3. Run 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")
            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": test_username.strip(), "agent_code": agent_code, "answers": answers_payload}
    status_update = f"Agent finished. Prepared {len(answers_payload)} answers for user '{test_username}'..."
    print(status_update)
    
    # 5. Show Results (but don't submit in local testing mode)
    print("In local development mode - showing results without submitting")
    final_status = (
        f"Local Testing Complete!\n"
        f"User: {test_username}\n"
        f"Generated {len(answers_payload)} answers\n"
        f"Message: This is a local test - no answers were submitted to the API"
    )
    results_df = pd.DataFrame(results_log)
    return final_status, results_df

# --- Simple Gradio Interface ---
with gr.Blocks() as demo:
    gr.Markdown("# GAIA Agent Local Testing Interface")
    gr.Markdown(
        """
        **Local Development Version**
        
        This is a simplified version of the agent interface for local testing.
        It uses a mock agent implementation that returns test answers.
        
        Enter a username below and click the button to run the agent on a few sample questions.
        """
    )

    test_username = gr.Textbox(label="Test Username", value="test_user")
    run_button = gr.Button("Run Test Evaluation")

    status_output = gr.Textbox(label="Run Status", lines=5, interactive=False)
    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)

    run_button.click(
        fn=run_and_submit_all,
        inputs=[test_username],
        outputs=[status_output, results_table]
    )

if __name__ == "__main__":
    print("\n" + "-"*30 + " GAIA Agent Local Testing " + "-"*30)
    
    # Try to load environment variables (optional)
    load_dotenv()
    
    print("Launching Gradio Interface for local testing...")
    demo.launch(debug=True, share=False)