app.py

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

# Stage 1: Import GAIAAgent (LangGraph-based agent)
from src.agent import GAIAAgent

# Configure logging
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger(__name__)

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


# --- Helper Functions ---
def check_api_keys():
    """Check which API keys are configured."""
    keys_status = {
        "GOOGLE_API_KEY (Gemini)": "✓ SET" if os.getenv("GOOGLE_API_KEY") else "✗ MISSING",
        "HF_TOKEN (HuggingFace)": "✓ SET" if os.getenv("HF_TOKEN") else "✗ MISSING",
        "ANTHROPIC_API_KEY (Claude)": "✓ SET" if os.getenv("ANTHROPIC_API_KEY") else "✗ MISSING",
        "TAVILY_API_KEY (Search)": "✓ SET" if os.getenv("TAVILY_API_KEY") else "✗ MISSING",
        "EXA_API_KEY (Search)": "✓ SET" if os.getenv("EXA_API_KEY") else "✗ MISSING",
    }
    return "\n".join([f"{k}: {v}" for k, v in keys_status.items()])


def export_results_to_json(results_log: list, submission_status: str) -> str:
    """Export evaluation results to JSON file for easy processing.

    - Local: Saves to ~/Downloads/gaia_results_TIMESTAMP.json
    - HF Spaces: Saves to ./exports/gaia_results_TIMESTAMP.json
    - Format: Clean JSON with full error messages, no truncation
    """
    from datetime import datetime

    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
    filename = f"gaia_results_{timestamp}.json"

    # Detect environment: HF Spaces or local
    if os.getenv("SPACE_ID"):
        # HF Spaces: save to local exports directory for Gradio to serve
        export_dir = os.path.join(os.getcwd(), "exports")
        os.makedirs(export_dir, exist_ok=True)
        filepath = os.path.join(export_dir, filename)
    else:
        # Local: save to Downloads folder
        downloads_dir = os.path.expanduser("~/Downloads")
        filepath = os.path.join(downloads_dir, filename)

    # Build JSON structure
    export_data = {
        "metadata": {
            "generated": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
            "timestamp": timestamp,
            "total_questions": len(results_log)
        },
        "submission_status": submission_status,
        "results": [
            {
                "task_id": result.get("Task ID", "N/A"),
                "question": result.get("Question", "N/A"),
                "submitted_answer": result.get("Submitted Answer", "N/A")
            }
            for result in results_log
        ]
    }

    # Write JSON file with pretty formatting
    with open(filepath, 'w', encoding='utf-8') as f:
        json.dump(export_data, f, indent=2, ensure_ascii=False)

    logger.info(f"Results exported to: {filepath}")
    return filepath


def format_diagnostics(final_state: dict) -> str:
    """Format agent state for diagnostic display."""
    diagnostics = []

    # Question
    diagnostics.append(f"**Question:** {final_state.get('question', 'N/A')}\n")

    # Plan
    plan = final_state.get('plan', 'No plan generated')
    diagnostics.append(f"**Plan:**\n{plan}\n")

    # Tool calls
    tool_calls = final_state.get('tool_calls', [])
    if tool_calls:
        diagnostics.append(f"**Tools Selected:** {len(tool_calls)} tool(s)")
        for idx, tc in enumerate(tool_calls, 1):
            tool_name = tc.get('tool', 'unknown')
            params = tc.get('params', {})
            diagnostics.append(f"  {idx}. {tool_name}({params})")
        diagnostics.append("")
    else:
        diagnostics.append("**Tools Selected:** None\n")

    # Tool results
    tool_results = final_state.get('tool_results', [])
    if tool_results:
        diagnostics.append(f"**Tool Execution Results:** {len(tool_results)} result(s)")
        for idx, tr in enumerate(tool_results, 1):
            tool_name = tr.get('tool', 'unknown')
            status = tr.get('status', 'unknown')
            if status == 'success':
                result_preview = str(tr.get('result', ''))[:100] + "..." if len(str(tr.get('result', ''))) > 100 else str(tr.get('result', ''))
                diagnostics.append(f"  {idx}. {tool_name}: ✓ SUCCESS")
                diagnostics.append(f"     Result: {result_preview}")
            else:
                error = tr.get('error', 'Unknown error')
                diagnostics.append(f"  {idx}. {tool_name}: ✗ FAILED - {error}")
        diagnostics.append("")

    # Evidence
    evidence = final_state.get('evidence', [])
    if evidence:
        diagnostics.append(f"**Evidence Collected:** {len(evidence)} item(s)")
        for idx, ev in enumerate(evidence, 1):
            ev_preview = ev[:150] + "..." if len(ev) > 150 else ev
            diagnostics.append(f"  {idx}. {ev_preview}")
        diagnostics.append("")
    else:
        diagnostics.append("**Evidence Collected:** None\n")

    # Errors
    errors = final_state.get('errors', [])
    if errors:
        diagnostics.append(f"**Errors:** {len(errors)} error(s)")
        for idx, err in enumerate(errors, 1):
            diagnostics.append(f"  {idx}. {err}")
        diagnostics.append("")

    # Answer
    answer = final_state.get('answer', 'No answer generated')
    diagnostics.append(f"**Final Answer:** {answer}")

    return "\n".join(diagnostics)


def test_single_question(question: str):
    """Test agent with a single question and return diagnostics."""
    if not question or not question.strip():
        return "Please enter a question.", "", check_api_keys()

    try:
        # Initialize agent
        agent = GAIAAgent()

        # Run agent (this stores final_state in agent.last_state)
        answer = agent(question)

        # Get final state from agent
        final_state = agent.last_state or {}

        # Format diagnostics
        diagnostics = format_diagnostics(final_state)
        api_status = check_api_keys()

        return answer, diagnostics, api_status

    except Exception as e:
        logger.error(f"Error in test_single_question: {e}", exc_info=True)
        return f"ERROR: {str(e)}", f"Exception occurred: {str(e)}", check_api_keys()


# --- GAIA Agent (Replaced BasicAgent) ---
# LangGraph-based agent with sequential workflow
# Stage 1: Placeholder nodes, returns fixed answer
# Stage 2: Tool integration
# Stage 3: Planning and reasoning logic
# Stage 4: Error handling and robustness
# Stage 5: Performance optimization


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 (Stage 1: GAIAAgent with LangGraph)
    try:
        logger.info("Initializing GAIAAgent...")
        agent = GAIAAgent()
        logger.info("GAIAAgent initialized successfully")
    except Exception as e:
        logger.error(f"Error instantiating agent: {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 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:
            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.")
        status_message = "Agent did not produce any answers to submit."
        results_df = pd.DataFrame(results_log)
        export_path = export_results_to_json(results_log, status_message)
        return status_message, results_df, export_path

    # 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)
        # Export to JSON
        export_path = export_results_to_json(results_log, final_status)
        return final_status, results_df, export_path
    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)
        export_path = export_results_to_json(results_log, status_message)
        return status_message, results_df, export_path
    except requests.exceptions.Timeout:
        status_message = "Submission Failed: The request timed out."
        print(status_message)
        results_df = pd.DataFrame(results_log)
        export_path = export_results_to_json(results_log, status_message)
        return status_message, results_df, export_path
    except requests.exceptions.RequestException as e:
        status_message = f"Submission Failed: Network error - {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        export_path = export_results_to_json(results_log, status_message)
        return status_message, results_df, export_path
    except Exception as e:
        status_message = f"An unexpected error occurred during submission: {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        export_path = export_results_to_json(results_log, status_message)
        return status_message, results_df, export_path


# --- Build Gradio Interface using Blocks ---
with gr.Blocks() as demo:
    gr.Markdown("# GAIA Agent Evaluation Runner (Stage 4: MVP - Real Integration)")
    gr.Markdown(
        """
        **Stage 4 Progress:** Adding diagnostics, error handling, and fallback mechanisms.
        """
    )

    with gr.Tabs():
        # Tab 1: Test Single Question (NEW - for diagnostics)
        with gr.Tab("🔍 Test & Debug"):
            gr.Markdown("""
            **Test Mode:** Run the agent on a single question and see detailed diagnostics.

            This mode shows:
            - API key status
            - Execution plan
            - Tools selected and executed
            - Evidence collected
            - Errors encountered
            - Final answer
            """)

            test_question_input = gr.Textbox(
                label="Enter Test Question",
                placeholder="e.g., What is the capital of France?",
                lines=3
            )
            test_button = gr.Button("Run Test", variant="primary")

            with gr.Row():
                with gr.Column(scale=1):
                    test_answer_output = gr.Textbox(
                        label="Answer",
                        lines=3,
                        interactive=False
                    )
                    test_api_status = gr.Textbox(
                        label="API Keys Status",
                        lines=5,
                        interactive=False
                    )
                with gr.Column(scale=2):
                    test_diagnostics_output = gr.Textbox(
                        label="Execution Diagnostics",
                        lines=20,
                        interactive=False
                    )

            test_button.click(
                fn=test_single_question,
                inputs=[test_question_input],
                outputs=[test_answer_output, test_diagnostics_output, test_api_status]
            )

        # Tab 2: Full Evaluation (existing functionality)
        with gr.Tab("📊 Full Evaluation"):
            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)

            export_output = gr.File(
                label="Download Results",
                type="filepath"
            )

            run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table, export_output])

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)