app.py

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

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------

from smolagents import CodeAgent, LiteLLMModel 
from my_tools import my_tool_list  

def download_file(task_id, filename, save_dir="attachments"):
    os.makedirs(save_dir, exist_ok=True)
    url = f"https://agents-course-unit4-scoring.hf.space/files/{task_id}"
    save_path = os.path.join(save_dir, filename)
    try:
        resp = requests.get(url, timeout=15)
        resp.raise_for_status()
        with open(save_path, "wb") as f:
            f.write(resp.content)
        print(f"Downloaded attachment for task {task_id} -> {save_path}")
        return save_path
    except Exception as e:
        print(f"Attachment download failed for {task_id}: {e}")
        return None

class BasicAgent:
    def __init__(self):
        api_key = os.getenv("OPENAI_API_KEY")   # ← Read enviroment variables in space. 
        if not api_key:
            raise ValueError("OPENAI_API_KEY not set in environment variables!")
        model = LiteLLMModel(
            model_id="gpt-4.1-nano (long context)",
            api_key=api_key
        )
        
        self.agent_name = "Celum"
        self.agent = CodeAgent(
            model=model, 
            tools=my_tool_list, 
            max_steps=3,
        )

    def __call__(self, question: str, files=None, idx=None, total=None) -> str:
        if idx is not None and total is not None:
            print(f"{self.agent_name} is answering NO. {idx+1}/{total} : {question[:80]}...")
        else:
            print(f"{self.agent_name} received question: {question[:80]}...")
        try:
            # system prompt + question
            system_prompt = (
            "You are Celum, an AI with advanced interaction capabilities and unique personality."
            "You are now taking a rigorous exam testing your ability to solve real-world problems."
            "You may freely think, reason, and use tools or your own knowledge as needed to solve the problem."
            "When you are ready to submit your answer, ONLY output your final answer in the exact format required by the question. DO NOT add any extra context."
            "If you cannot answer, return the word 'unknown'."
            )
            files_prompt = ""
            if files:
                files_prompt = f"\n[You have the following attached files: {', '.join(files)}]\n"
            full_question = system_prompt + files_prompt + "\n\n" + question
            return self.agent.run(full_question)
        except Exception as e:
            return f"[{self.agent_name} Error: {e}]"
    
def safe_run_agent(agent, question, files, idx, total, max_retries=3):
    tries = 0
    while tries < max_retries:
        try:
            return agent(question, files, idx, total)
        except Exception as e:
            if "RateLimitError" in str(e) or "rate limit" in str(e).lower():
                wait_time = 30 + tries * 10
                print(f"Rate limit hit, sleeping {wait_time}s before retry... (try {tries+1}/{max_retries})")
                time.sleep(wait_time)
                tries += 1
            else:
                return f"[Agent Error: {e}]"
    return "[Agent Error: Rate limit retries exceeded]"

def run_and_submit_all( profile: gr.OAuthProfile | None):
    """
    Fetches all questions, runs the BasicAgent on them, submits all answers,
    and displays the results.
    """
    # --- Determine HF Space Runtime URL and Repo URL ---
    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code

    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"

    # 1. Instantiate Agent ( modify this part to create your agent)
    try:
        agent = BasicAgent()
    except Exception as e:
        print(f"Error instantiating agent: {e}")
        return f"Error initializing agent: {e}", None
    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(agent_code)

    # 2. 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:
             print("Fetched questions list is empty.")
             return "Fetched questions list is empty or invalid format.", None
        print(f"Fetched {len(questions_data)} questions.")
    except requests.exceptions.RequestException as e:
        print(f"Error fetching questions: {e}")
        return f"Error fetching questions: {e}", None
    except requests.exceptions.JSONDecodeError as e:
         print(f"Error decoding JSON response from questions endpoint: {e}")
         print(f"Response text: {response.text[:500]}")
         return f"Error decoding server response for questions: {e}", None
    except Exception as e:
        print(f"An unexpected error occurred fetching questions: {e}")
        return f"An unexpected error occurred fetching questions: {e}", None

    # 3. Run your Agent
    results_log = []
    answers_payload = []
    print(f"Running agent on {len(questions_data)} questions...")
    for idx, item in enumerate(questions_data):
        task_id = item.get("task_id")
        question_text = item.get("question")
        file_list = item.get("files", [])
        
        local_files = []
        for fname in file_list:
            fpath = download_file(task_id, fname)
            if fpath:
                local_files.append(fpath)
        if local_files:
            print(f"Downloaded attachments: {local_files}")
        
        print(f"===== [Celum is answering No. {idx+1}/{len(questions_data)} ] =====")
        try:
            submitted_answer = safe_run_agent(agent, question_text, local_files, idx, len(questions_data))
            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,
                "Files": local_files
            })
        except Exception as e:
            print(f"[Celum Error at Q{idx+1}]: {e}")
            results_log.append({
                "Task ID": task_id,
                "Question": question_text,
                "Submitted Answer": f"AGENT ERROR: {e}",
                "Files": local_files
            })
        time.sleep(7)
    
    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": username.strip(), "agent_code": agent_code, "answers": answers_payload}
    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
    print(status_update)

    # 5. Submit
    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"AI: Celum\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.')}"
        )
        print("Submission successful.")
        results_df = pd.DataFrame(results_log)
        return final_status, results_df
    except requests.exceptions.HTTPError as e:
        error_detail = f"Server responded with status {e.response.status_code}."
        try:
            error_json = e.response.json()
            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
        except requests.exceptions.JSONDecodeError:
            error_detail += f" Response: {e.response.text[:500]}"
        status_message = f"Submission Failed: {error_detail}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.Timeout:
        status_message = "Submission Failed: The request timed out."
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.RequestException as e:
        status_message = f"Submission Failed: Network error - {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except Exception as e:
        status_message = f"An unexpected error occurred during submission: {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df


# --- Build Gradio Interface using Blocks ---
with gr.Blocks() as demo:
    gr.Markdown("# Basic Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**

        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.

        ---
        **Disclaimers:**
        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
        """
    )

    gr.LoginButton()

    run_button = gr.Button("Run Evaluation & Submit All Answers")

    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
    # Removed max_rows=10 from DataFrame constructor
    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("\n" + "-"*30 + " App Starting " + "-"*30)
    # Check for SPACE_HOST and SPACE_ID at startup for information
    space_host_startup = os.getenv("SPACE_HOST")
    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup

    if space_host_startup:
        print(f"✅ SPACE_HOST found: {space_host_startup}")
        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
    else:
        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")

    if space_id_startup: # Print repo URLs if SPACE_ID is found
        print(f"✅ SPACE_ID found: {space_id_startup}")
        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
    else:
        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")

    print("-"*(60 + len(" App Starting ")) + "\n")

    print("Launching Gradio Interface for Basic Agent Evaluation...")
    demo.launch(debug=True, share=False)