import os
import gradio as gr
import requests
import pandas as pd

from smolagents import CodeAgent, DuckDuckGoSearchTool, OpenAIServerModel

# Constants
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
MAX_QUESTION_LENGTH = 4000  # to avoid GPT-4 8k token limit

# --- Agent Definition using smolagents ---
class SmartGAIAAgent:
    def __init__(self):
        self.api_key = os.getenv("OPENAI_API_KEY")
        if not self.api_key:
            raise ValueError("Missing OPENAI_API_KEY")
        self.model = OpenAIServerModel(model_id="gpt-4", api_key=self.api_key)

        # Agent with DuckDuckGo + built-in Python interpreter
        self.agent = CodeAgent(
            tools=[DuckDuckGoSearchTool()],
            model=self.model,
            add_base_tools=True
        )

    def __call__(self, question: str) -> str:
        try:
            question = question[:MAX_QUESTION_LENGTH]
            result = self.agent.run(question)
            return result.strip()
        except Exception as e:
            print(f"Agent error: {e}")
            return "error"

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:
        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"

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

    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(f"Code link: {agent_code}")

    try:
        response = requests.get(questions_url, timeout=15)
        response.raise_for_status()
        questions_data = response.json()
    except Exception as e:
        return f"Error fetching questions: {e}", None

    answers_payload = []
    results_log = []

    for item in questions_data:
        task_id = item.get("task_id")
        question_text = item.get("question")

        # Skip invalid or long/multimodal questions
        if not task_id or not question_text:
            continue
        if len(question_text) > MAX_QUESTION_LENGTH:
            print(f"Skipping long question: {task_id}")
            continue
        if any(keyword in question_text.lower() for keyword in ['attached', '.mp3', '.wav', '.png', '.jpg', 'image']):
            print(f"Skipping file/audio/image question: {task_id}")
            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:
            results_log.append({
                "Task ID": task_id,
                "Question": question_text,
                "Submitted Answer": f"ERROR: {e}"
            })

    if not answers_payload:
        return "No answers were submitted.", pd.DataFrame(results_log)

    submission_data = {
        "username": username,
        "agent_code": agent_code,
        "answers": answers_payload
    }

    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"Score: {result_data.get('score')}% "
            f"({result_data.get('correct_count')}/{result_data.get('total_attempted')})\\n"
            f"Message: {result_data.get('message')}"
        )
        return final_status, pd.DataFrame(results_log)
    except Exception as e:
        return f"Submission failed: {e}", pd.DataFrame(results_log)

# --- Gradio Interface ---
with gr.Blocks() as demo:
    gr.Markdown("# GAIA Agent Evaluation")
    gr.Markdown("""
    **Instructions:**
    1. Log in to Hugging Face
    2. Click 'Run Evaluation' to generate and submit answers
    3. Wait for the results
    """)
    gr.LoginButton()
    run_button = gr.Button("Run Evaluation & Submit All Answers")
    status_output = gr.Textbox(label="Submission Status", lines=5)
    results_table = gr.DataFrame(label="Results")

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

if __name__ == "__main__":
    print("Launching Gradio Interface...")
    demo.launch(debug=True, share=False)