app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
from pathlib import Path
from PIL import Image as PILImage

from agent import agent

import os
print("Gemini_Key in env:", "Gemini_Key" in os.environ)

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

# Helper function to check for images
def is_image_file(filepath: Path) -> bool:
    if not filepath or not filepath.is_file():
        return False
    try:
        with PILImage.open(filepath) as img:
            img.verify()  # Verify it's an image without loading all pixel data
        return True
    except Exception:  # Catches PIL.UnidentifiedImageError, IOError, SyntaxError, etc.
        return False

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
    def __init__(self):
        print("BasicAgent initialized.")
        self.agent = agent
    def __call__(self, task_id: str, question: str, filename: Path | None = None) -> str:
        print(f"Agent received task_id: {task_id}, question (first 50 chars): {question[:50]}...")
        if filename:
            print(f"Associated file: {filename.name}")

        # Augment the question for the LLM
        prompt = f"Task ID: {task_id}\\nQuestion: {question}"
        if filename:
            # Still inform about the file in the text prompt, as a fallback or for context
            prompt += f"\\n\\nThis question may relate to an attached file named: '{filename.name}'. The file has been downloaded if it was provided with the question."

        run_kwargs = {}
        if filename and is_image_file(filename):
            print(f"File {filename.name} is an image. Adding to agent.run arguments.")
            # Assuming agent.run can take an 'images' kwarg with a list of Path objects or PIL.Image objects
            # Passing Path object directly for simplicity, smolagents might handle it.
            run_kwargs["images"] = [filename]
        
        answer = self.agent.run(prompt, **run_kwargs)
        print(f"Agent returning answer: {answer}")
        return answer

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)

    # Create a directory for downloaded files
    files_dir = Path("downloaded_files")
    files_dir.mkdir(exist_ok=True)
    print(f"Files will be downloaded to: {files_dir.resolve()}")

    # 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 item in questions_data:
        task_id = item.get("task_id")
        question_text = item.get("question")
        file_name_str = item.get("file_name") # Check for a filename
        file_path: Path | None = None # Initialize file_path

        if not task_id or question_text is None:
            print(f"Skipping item with missing task_id or question: {item}")
            continue

        if file_name_str:
            print(f"Task {task_id} has an associated file: {file_name_str}")
            # Construct download URL - using the structure suggested by GaiaClient in the prompt
            # The API seems to be GET /files/{task_id} and filename is for local saving
            file_url = f"{api_url}/files/{task_id}"
            local_file_path = files_dir / file_name_str
            
            try:
                print(f"Attempting to download file from: {file_url} to {local_file_path}")
                response = requests.get(file_url, timeout=30) # Increased timeout for file download
                response.raise_for_status() # Will raise an HTTPError for bad responses (4XX or 5XX)
                with open(local_file_path, "wb") as f:
                    f.write(response.content)
                file_path = local_file_path
                print(f"Successfully downloaded {file_name_str} for task {task_id}.")
            except requests.exceptions.HTTPError as e_http:
                print(f"HTTP error downloading file for task {task_id} ({file_name_str}): {e_http}")
                print(f"Response status: {e_http.response.status_code}, Response text: {e_http.response.text[:200]}")
            except requests.exceptions.RequestException as e_req:
                print(f"Error downloading file for task {task_id} ({file_name_str}): {e_req}")
            except Exception as e_file:
                print(f"An unexpected error occurred downloading file for task {task_id} ({file_name_str}): {e_file}")
        
        try:
            # Pass task_id, original question_text, and file_path to the agent
            submitted_answer = agent(task_id, question_text, file_path)
            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
            results_log.append({
                "Task ID": task_id,
                "Question": question_text,
                "File": file_name_str if file_name_str else "N/A", # Log file name
                "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,
                 "File": file_name_str if file_name_str else "N/A",
                 "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()

    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)