app.py

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

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

def load_cache() -> dict:
    if os.path.exists(CACHE_FILE):
        try:
            with open(CACHE_FILE, "r", encoding="utf-8") as f:
                return json.load(f)
        except Exception as e:
            print(f"  [warn] Failed to load cache: {e}")
    return {}

def save_cache(cache: dict) -> None:
    try:
        with open(CACHE_FILE, "w", encoding="utf-8") as f:
            json.dump(cache, f, indent=4, ensure_ascii=False)
    except Exception as e:
        print(f"  [warn] Failed to save cache: {e}")


def fetch_task_file(task_id: str, file_name: str | None = None) -> str | None:
    """Download the file attached to a GAIA task, if any.

    Args:
        task_id: Unique identifier of the GAIA task.
        file_name: Optional name of the file.

    Returns:
        Local path of the downloaded file, or None if no file is attached.
    """
    import os
    import glob

    # 1. Try local cache first for direct HF file
    if file_name:
        filename = f"task_{task_id}_{file_name}"
        if os.path.exists(filename) and os.path.getsize(filename) > 0:
            print(f"  [file] Using cached attachment: {filename}")
            return filename

    # 2. Try local cache first for fallback files (e.g. task_{task_id}.bin, task_{task_id}.pdf, etc.)
    existing_fallbacks = glob.glob(f"task_{task_id}.*")
    if existing_fallbacks:
        filename = existing_fallbacks[0]
        if os.path.exists(filename) and os.path.getsize(filename) > 0:
            print(f"  [file] Using cached fallback attachment: {filename}")
            return filename

    # Try downloading from Hugging Face dataset if file_name is provided
    if file_name:
        url = f"https://huggingface.co/datasets/gaia-benchmark/GAIA/resolve/main/2023/validation/{file_name}"
        token = os.environ.get("HUGGINGFACEHUB_API_TOKEN")
        headers = {"Authorization": f"Bearer {token}"} if token else {}
        try:
            response = requests.get(url, headers=headers, timeout=30)
            if response.status_code == 200 and len(response.content) > 0:
                filename = f"task_{task_id}_{file_name}"
                with open(filename, "wb") as f:
                    f.write(response.content)
                print(f"  [file] Downloaded attachment from HF GAIA repo: {filename} ({len(response.content)} bytes)")
                return filename
        except Exception as e:
            print(f"  [warn] Direct HF GAIA download failed for {file_name}: {e}")

    # Fallback to course scoring API
    url = f"{DEFAULT_API_URL}/files/{task_id}"
    try:
        response = requests.get(url, timeout=30)
        if response.status_code == 200 and len(response.content) > 0:
            # Detect file extension from Content-Type header
            content_type = response.headers.get("Content-Type", "")
            ext = ".bin"
            if "pdf" in content_type:
                ext = ".pdf"
            elif "image" in content_type:
                ext = ".png"
            elif "text/csv" in content_type:
                ext = ".csv"
            elif "audio" in content_type:
                ext = ".mp3"

            filename = f"task_{task_id}{ext}"
            with open(filename, "wb") as f:
                f.write(response.content)
            print(f"  [file] Downloaded attachment from scoring server: {filename} ({len(response.content)} bytes)")
            return filename
    except Exception as e:
        print(f"  [warn] Could not fetch file from scoring server for task {task_id}: {e}")
    return None


# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
from agent import GAIAAgent

class BasicAgent:
    def __init__(self):
        self.agent = GAIAAgent()
        print("BasicAgent (GAIAAgent wrapper) initialized.")

    def __call__(self, question: str, task_id: str | None = None, file_name: str | None = None) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        if task_id:
            filepath = fetch_task_file(task_id, file_name)
            if filepath:
                question = f"{question}\n\n[Attached file available locally: {filepath}]"
        return self.agent(question)

def run_and_submit_all(profile: gr.OAuthProfile | None, ignore_cache: bool = False):
    """
    Fetches all questions, runs the BasicAgent on them (or loads from cache),
    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 = []
    
    # Load cache unless ignore_cache is True
    cache = {} if ignore_cache else load_cache()
    if not ignore_cache and cache:
        print(f"Loaded {len(cache)} cached answers from {CACHE_FILE}.")

    print(f"Running agent on {len(questions_data)} questions...")
    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:
            print(f"Skipping item with missing task_id or question: {item}")
            continue
        try:
            file_name = item.get("file_name", "")
            
            # Check cache
            if task_id in cache and cache[task_id]:
                submitted_answer = cache[task_id]
                print(f"  [cache] Using cached answer for task {task_id}: {submitted_answer}")
            else:
                submitted_answer = agent(question_text, task_id=task_id, file_name=file_name)
                cache[task_id] = submitted_answer
                save_cache(cache)
                
            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:
             print(f"Error running agent on task {task_id}: {e}")
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})

    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"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.')}"
        )
        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()

    ignore_cache_cb = gr.Checkbox(label="Ignorer le cache (Forcer le recalcul des réponses)", value=False)

    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,
        inputs=[ignore_cache_cb],
        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)