app.py

import os

# Disable Hugging Face login for local execution
os.environ["DISABLE_HF_LOGIN"] = "1"

import gradio as gr
import pandas as pd
import requests

from dotenv import load_dotenv

from agent import BasicAgent, agent_graph_mermaid
from agent.graph import agent_graph_png_base64

load_dotenv()

# Generate the agent graph visualizations
try:
    GRAPH_MERMAID = agent_graph_mermaid()
except Exception as exc:
    GRAPH_MERMAID = f"Error generating graph diagram: {exc}"

GRAPH_PNG_BASE64 = agent_graph_png_base64()


def _env_flag(name: str, default: bool = False) -> bool:
    value = os.getenv(name)
    if value is None:
        return default
    return value.strip().lower() in {"1", "true", "yes", "on"}
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
_SPACE_ENV_CONFIGURED = bool(os.getenv("SPACE_ID") or os.getenv("SPACE_HOST"))
FORCE_LOCAL_MODE = _env_flag("FORCE_LOCAL_MODE") or _env_flag("DISABLE_HF_LOGIN") or _env_flag("GRADIO_FORCE_LOCAL")
RUNNING_IN_SPACE = _SPACE_ENV_CONFIGURED and not FORCE_LOCAL_MODE

def run_and_submit_all(profile: gr.OAuthProfile | None = None, username: str | None = 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 and getattr(profile, "username", None):
        username = f"{profile.username}".strip()
        print(f"User logged in via OAuth: {username}")
    elif username:
        username = username.strip()
        print(f"Using provided username: {username}")
    else:
        env_username = (os.getenv("HF_USERNAME") or os.getenv("LOCAL_HF_USERNAME") or "").strip()
        if env_username:
            username = env_username
            print(f"Using username from environment: {username}")
        else:
            print("User not logged in and no username supplied.")
            return (
                "Please login to Hugging Face, provide a username locally, or set the `HF_USERNAME`/`LOCAL_HF_USERNAME` environment variable.",
                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.")
        
        # Debug: Print first question structure to understand format
        if questions_data and len(questions_data) > 0:
            print(f"\n🔍 DEBUG - First question structure:")
            print(f"Keys: {list(questions_data[0].keys())}")
            if len(questions_data[0].keys()) > 2:
                print(f"Sample: {str(questions_data[0])[:300]}...\n")
    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")
        if not task_id or question_text is None:
            print(f"Skipping item with missing task_id or question: {item}")
            continue
        
        # Check for attached files and download them
        file_name = item.get("file_name", "")
        if file_name and file_name.strip():
            try:
                from pathlib import Path
                
                # Create downloads directory if it doesn't exist
                download_dir = Path("downloads")
                download_dir.mkdir(exist_ok=True)
                
                # Construct file download URL
                file_url = f"{api_url}/files/{task_id}"  # Note: /files/ (plural)
                print(f"📥 Downloading file: {file_name} from {file_url}")
                
                # Download the file
                file_response = requests.get(file_url, timeout=30)
                file_response.raise_for_status()
                
                # Save file to downloads directory
                filepath = download_dir / file_name
                with open(filepath, 'wb') as f:
                    f.write(file_response.content)
                print(f"✅ Saved file: {filepath} ({len(file_response.content)} bytes)")
            except Exception as e:
                print(f"⚠️ Error downloading file {file_name}: {e}")
        
        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:
            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.")
        results_df = pd.DataFrame(results_log, columns=["Task ID", "Question", "Submitted Answer"]).fillna("")
        return "Agent did not produce any answers to submit.", results_df

    # 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, columns=["Task ID", "Question", "Submitted Answer"]).fillna("")
        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, columns=["Task ID", "Question", "Submitted Answer"]).fillna("")
        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, columns=["Task ID", "Question", "Submitted Answer"]).fillna("")
        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, columns=["Task ID", "Question", "Submitted Answer"]).fillna("")
        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, columns=["Task ID", "Question", "Submitted Answer"]).fillna("")
        return status_message, results_df


# --- Build Gradio Interface using Blocks ---


def run_and_submit_all_local(username_input: str | None):
    return run_and_submit_all(profile=None, username=username_input)


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.
        """
    )

    # Display the agent graph
    gr.Markdown("## Agent Flow Graph")
    gr.Markdown("This diagram shows how your agent processes questions using LangGraph:")
    
    if GRAPH_PNG_BASE64:
        gr.HTML(
            f'<img src="data:image/png;base64,{GRAPH_PNG_BASE64}" alt="Agent Flow Graph" style="max-width:100%;height:auto;border:1px solid #ddd;border-radius:4px;padding:10px;"/>'
        )
    else:
        gr.Markdown("*Graph visualization not available. The agent is still functional.*")

    login_button = None
    username_box = None
    if RUNNING_IN_SPACE:
        login_button = gr.LoginButton()
    else:
        username_box = gr.Textbox(
            label="Hugging Face Username",
            placeholder="Enter the username to associate with your submission",
            value=(os.getenv("HF_USERNAME") or os.getenv("LOCAL_HF_USERNAME") or ""),
        )

    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",
        value=pd.DataFrame(columns=["Task ID", "Question", "Submitted Answer"]),
        interactive=False,
        wrap=True,
    )

    if RUNNING_IN_SPACE:
        run_button.click(
            fn=run_and_submit_all,
            inputs=[login_button],
            outputs=[status_output, results_table],
        )
    else:
        run_button.click(
            fn=run_and_submit_all_local,
            inputs=[username_box],
            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)