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

# --- Smolagents/Tools Imports ---
from smolagents import CodeAgent, DuckDuckGoSearchTool, FinalAnswerTool, InferenceClientModel

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

# --- Smart Agent Definition ---
class MySmartAgent:
    def __init__(self):
        # Use a strong code/instruct model hosted by Hugging Face Inference API
        self.model = InferenceClientModel(
            model_id="Qwen/Qwen2.5-Coder-32B-Instruct",  # Or try Llama, Mistral, etc.
            max_tokens=2048,
            temperature=0.3
        )
        # Give agent both web search & final answer generation
        self.agent = CodeAgent(
            model=self.model,
            tools=[
                DuckDuckGoSearchTool(),
                FinalAnswerTool()
            ],
            max_steps=6,
            verbosity_level=1
        )

    def __call__(self, question: str) -> str:
        return self.agent.run(question)

def run_and_submit_all(profile: gr.OAuthProfile | None):
    space_id = os.getenv("SPACE_ID")
    if profile:
        username = f"{profile.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"
    # Instantiate smart agent
    try:
        agent = MySmartAgent()
    except Exception as e:
        return f"Error initializing agent: {e}", None
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    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

    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 question_text is None:
            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"AGENT ERROR: {e}"})

    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}
    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.')}"
        )
        results_df = pd.DataFrame(results_log)
        return final_status, results_df
    except Exception as e:
        results_df = pd.DataFrame(results_log)
        return f"Submission Failed: {e}", results_df

with gr.Blocks() as demo:
    gr.Markdown("# Smart Agent Evaluation Runner")
    gr.Markdown(
        """
        1. Clone this space and modify your agent (uses LLM + DuckDuckGo search)!
        2. Log in with Hugging Face.
        3. Click 'Run Evaluation & Submit' to score your assignment.
        """
    )
    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__":
    demo.launch(debug=True, share=False)