app.py

import os
import nltk

# 1) Asegurarnos de que la carpeta nltk_data exista
os.makedirs("nltk_data", exist_ok=True)

# 2) Apuntar NLTK a usar esa carpeta
os.environ["NLTK_DATA"] = "nltk_data"
nltk.data.path.insert(0, "nltk_data")

# 3) Verificar si 'punkt' y 'stopwords' ya están descargados; si no, descargarlos ahora.
#    Así evitamos el error y hacemos la descarga solo una vez en runtime.
def ensure_nltk_resource(res_name):
    try:
        nltk.data.find(res_name)
        return True
    except LookupError:
        return False

# Si falta 'punkt', lo descargamos
if not ensure_nltk_resource("tokenizers/punkt"):
    print("DEBUG: 'punkt' no encontrado en nltk_data, descargando...")
    nltk.download("punkt", download_dir="nltk_data", quiet=True)

# Si falta 'stopwords', lo descargamos
if not ensure_nltk_resource("corpora/stopwords"):
    print("DEBUG: 'stopwords' no encontrado en nltk_data, descargando...")
    nltk.download("stopwords", download_dir="nltk_data", quiet=True)

# ── Ahora SÍ traemos el resto de librerías que usan nltk y llama_index  ──────
import gradio as gr
import requests
import inspect
import pandas as pd
import time

# --- AGENTE SIMPLIFICADO CON FUNCIONALIDAD PERSONALIZADA ---
from my_tools import basic_agent_response



# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

def run_and_submit_all(profile: gr.OAuthProfile | None):
    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"
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"

    # --- 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 "Fetched questions list is empty or invalid format.", None
    except Exception as e:
        return f"Error fetching questions: {e}", None

    # --- Run Agent ---
    results_log = []
    answers_payload = []

    total_questions = len(questions_data)
    #for item in questions_data:
    for item_index, item in enumerate(questions_data):
        task_id = item.get("task_id")
        question_text = item.get("question")
        if not task_id or question_text is None:
            continue
        try:
            submitted_answer = basic_agent_response(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:
            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
        
        # ----- LÍNEA DE TIME.SLEEP VA AQUÍ -----
        # Esperar después de procesar cada pregunta, excepto la última
        # item_index y total_questions AHORA ESTÁN DEFINIDOS CORRECTAMENTE en este alcance
        if item_index < total_questions - 1:
            wait_duration = 20  # Segundos de espera
            print(f"--- Question {item_index + 1} processed. Waiting {wait_duration} seconds before next question to manage API rate limits... ---")
            time.sleep(wait_duration)
        else:
            print(f"--- All {total_questions} questions processed. Proceeding to submission. ---")
        # ----- FIN DE LA SECCIÓN DE TIME.SLEEP -----
        
    if not answers_payload:
        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)

    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
    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_data = response.json()
        final_status = (
            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.')}")
        return final_status, pd.DataFrame(results_log)
    except Exception as e:
        return f"Submission Failed: {e}", pd.DataFrame(results_log)

# --- Interfaz Gradio ---
with gr.Blocks() as demo:
    gr.Markdown("# Basic Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**
        1. Clone this space and modify the code to define your agent's logic and tools.
        2. Log in to Hugging Face with the button below.
        3. Click 'Run Evaluation & Submit All Answers' to evaluate your agent.
        """
    )

    gr.LoginButton()
    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__":
    print("🔍 Prueba de pregunta GAIA manual")
    test_question = "¿Cuánto es 37 por 19?"
    print("Pregunta:", test_question)
    print("Respuesta del agente:", basic_agent_response(test_question))
    
    print("Launching Gradio Interface for Basic Agent Evaluation...")
    demo.launch(debug=True, share=False)