app.py

import os
import gradio as gr
import requests
import pandas as pd
import json
from openai import OpenAI
from dotenv import load_dotenv

load_dotenv()

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

# --- Agent Using OpenAI GPT-4o ---
class BasicAgent:
    def __init__(self, model="gpt-4o"):
        self.model = model
        api_key = os.getenv("OPENAI_API_KEY")
        if not api_key:
            raise ValueError("OPENAI_API_KEY not set.")
        self.client = OpenAI(api_key=api_key)
        print(f"BasicAgent initialized using model: {self.model}")

    def __call__(self, question: str) -> dict:
        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 on whether the element to be put in the list is a number or a string."
        )

        try:
            response = self.client.chat.completions.create(
                model=self.model,
                messages=[
                    {"role": "system", "content": system_prompt},
                    {"role": "user", "content": question}
                ],
                temperature=0.2,
                max_tokens=500
            )

            full_answer = response.choices[0].message.content.strip()

            if "FINAL ANSWER:" in full_answer:
                final = full_answer.split("FINAL ANSWER:")[-1].strip()
            else:
                final = full_answer  # fallback

            return {
                "model_answer": f"FINAL ANSWER: {final}",
                "reasoning_trace": full_answer
            }

        except Exception as e:
            return {
                "model_answer": "FINAL ANSWER: AGENT ERROR",
                "reasoning_trace": str(e)
            }

# --- Evaluation and Submission ---
def run_and_submit_all(profile: gr.OAuthProfile | None):
    if profile:
        print(f"User logged in: {profile.username}")
    else:
        print("User not logged in.")
        return "Please Login to Hugging Face with the button.", None

    questions_url = f"{DEFAULT_API_URL}/questions"
    submit_url = f"{DEFAULT_API_URL}/submit"

    try:
        agent = BasicAgent()
    except Exception as e:
        return f"Error initializing agent: {e}", None

    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.", None
        print(f"Fetched {len(questions_data)} questions.")
    except Exception as e:
        return f"Error fetching questions: {e}", None

    results_log = []
    answers_payload = []

    for item in questions_data:
        task_id = item.get("task_id")
        question_text = item.get("question")
        if not task_id or not question_text:
            continue

        try:
            result = agent(question_text)
            model_answer = result["model_answer"]
            trace = result["reasoning_trace"]

            answers_payload.append({
                "task_id": task_id,
                "model_answer": model_answer,
                "reasoning_trace": trace
            })

            results_log.append({
                "Task ID": task_id,
                "Question": question_text,
                "Model Answer": model_answer
            })

        except Exception as e:
            results_log.append({
                "Task ID": task_id,
                "Question": question_text,
                "Model Answer": f"AGENT ERROR: {e}"
            })

    if not answers_payload:
        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)

    # Optional: save submission.jsonl for debug
    with open("submission.jsonl", "w") as f:
        for ans in answers_payload:
            f.write(json.dumps(ans) + "\n")

    # Submit: API expects just a list of {"task_id", "model_answer", "reasoning_trace"}
    try:
        response = requests.post(submit_url, json=answers_payload, timeout=60)
        response.raise_for_status()
        result_data = response.json()

        final_status = (
            f"Submission Successful!\n"
            f"User: {profile.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)

# --- Gradio UI ---
with gr.Blocks() as demo:
    gr.Markdown("# GPT-4o Agent Evaluation Runner")
    gr.Markdown("""
    1. Log into your Hugging Face account.
    2. Click the button to fetch questions, generate answers using GPT-4o, and submit.
    3. You will see your score and submitted answers below.
    """)

    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])

# --- Entry Point ---
if __name__ == "__main__":
    print("\n" + "-"*30 + " App Starting " + "-"*30)
    space_host = os.getenv("SPACE_HOST")
    space_id = os.getenv("SPACE_ID")

    if space_host:
        print(f"✅ SPACE_HOST found: https://{space_host}.hf.space")
    else:
        print("ℹ️  SPACE_HOST not found.")

    if space_id:
        print(f"✅ SPACE_ID found: https://huggingface.co/spaces/{space_id}")
    else:
        print("ℹ️  SPACE_ID not found.")

    print("-"*(60 + len(" App Starting ")) + "\n")
    demo.launch(debug=True, share=False)