app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
import json
from pathlib import Path
from smolagents import CodeAgent, DuckDuckGoSearchTool, InferenceClientModel,WebSearchTool, VisitWebpageTool, ToolCallingAgent,LiteLLMModel,OpenAIServerModel
from dotenv import load_dotenv
load_dotenv()

GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")

model = OpenAIServerModel(
    model_id="gemini-2.5-flash-lite-preview-06-17",
    # Google Gemini OpenAI-compatible API base URL
    api_base="https://generativelanguage.googleapis.com/v1beta/openai/",
    api_key=GEMINI_API_KEY,
)
# web_agent = ToolCallingAgent(
#     tools=[WebSearchTool(), visit_webpage],
#     model=model,
#     max_steps=10,
#     name="web_search_agent",
#     description="Runs web searches for you.",
# )

# manager_agent = CodeAgent(
#     tools=[],
#     model=model,
#     managed_agents=[web_agent],
#     additional_authorized_imports=["time", "numpy", "pandas"],
# )
# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"


agent = CodeAgent(
    tools=[WebSearchTool(), VisitWebpageTool()], 
    model=model,
    planning_interval=3,
    additional_authorized_imports=["time", "numpy", "pandas", "requests", "bs4", "re", "markdownify"],
    max_steps=5
    )

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
    def __init__(self):
        print("BasicAgent initialized.")
    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        PROMPT = """
        You are a helpful assistant that can answer questions and help with tasks. 
        You will receive a question that can be either a question, a task, some common knowledge, some information related to documents, combination of all. 

        You can use the following tools to help you:
        - DuckDuckGoSearchTool: Search the web for information.
        - WebSearchTool: Search the web for information.
        - VisitWebpageTool: Visit a webpage and return the content.

        You will the answer only, no other text.    
        Provide the answer as a string. Do not include any other text. Provide the answer in <answer> tags.
        Question: {question}
        Answer:
        """
        agent_answer = agent.run(PROMPT.format(question=question))
        final_answer = agent_answer.split("<answer>")[1].split("</answer>")[0]
        print(f"Agent returning fixed answer: {final_answer}")
        return final_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)

    # 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. Load cached answers from model_answer.json (if present)
    answers_file = Path(__file__).with_name("model_answer.json")
    cached_answers = []
    if answers_file.exists():
        try:
            cached_answers = json.loads(answers_file.read_text(encoding="utf-8"))
            print(f"Loaded {len(cached_answers)} cached answers from {answers_file.name}.")
        except json.JSONDecodeError as e:
            print(f"Warning: Could not parse {answers_file.name}: {e}. Continuing without cached answers.")
            cached_answers = []
    else:
        print(f"No cached answers file found at {answers_file}. Will rely entirely on the agent.")

    # Make a lookup dict by task_id for quick access
    cached_by_task_id = {item.get("task_id"): item.get("answer") for item in cached_answers if item.get("task_id")}

    # 4. Run your Agent OR use cached answers
    results_log = []
    answers_payload = []
    print(f"Answering {len(questions_data)} questions (cached answers will be used when available)...")
    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

        # Prefer cached answer if we have one
        submitted_answer = cached_by_task_id.get(task_id)
        if submitted_answer is None:
            try:
                submitted_answer = agent(question_text)
                print(f"Generated answer for task {task_id}: {submitted_answer}")
            except Exception as e:
                print(f"Error running agent on task {task_id}: {e}")
                submitted_answer = f"AGENT ERROR: {e}"
        else:
            print(f"Using cached answer for task {task_id}: {submitted_answer}")

        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})

    if not answers_payload:
        print("No answers produced to submit.")
        return "No answers produced to submit.", pd.DataFrame(results_log)

    # 5. Submit each answer individually
    print(f"Submitting {len(answers_payload)} answers one-by-one to: {submit_url}")
    successes = 0
    submission_results = []
    
    for answer_item in answers_payload:
        submission_data = {
            "username": username.strip(),
            "agent_code": agent_code,
            "answers": [answer_item],  # single answer per request
        }
        try:
            response = requests.post(submit_url, json=submission_data, timeout=60)
            response.raise_for_status()
            result_json = response.json()
            successes += 1
            score = result_json.get('score', 0)
            message = result_json.get('message', 'No message')
            print(f"Submitted task {answer_item['task_id']} ✓ Score: {score} Message: {message}")
            submission_results.append({
                "task_id": answer_item['task_id'],
                "score": score,
                "success": True,
                "message": message
            })
        except Exception as e:
            print(f"Failed to submit task {answer_item['task_id']}: {e}")
            submission_results.append({
                "task_id": answer_item['task_id'],
                "score": 0,
                "success": False,
                "message": str(e)
            })

    # Calculate overall statistics
    total_score = sum(result['score'] for result in submission_results if result['success'])
    successful_submissions = len([r for r in submission_results if r['success']])
    correct_answers = len([r for r in submission_results if r['score'] > 0])
    
    # ALSO do a batch submission for leaderboard purposes
    print(f"\n--- BATCH SUBMISSION FOR LEADERBOARD ---")
    batch_submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
    try:
        batch_response = requests.post(submit_url, json=batch_submission_data, timeout=60)
        batch_response.raise_for_status()
        batch_result = batch_response.json()
        batch_status = (
            f"BATCH SUBMISSION:\n"
            f"User: {batch_result.get('username')}\n"
            f"Overall Score: {batch_result.get('score', 'N/A')}% "
            f"({batch_result.get('correct_count', '?')}/{batch_result.get('total_attempted', '?')} correct)\n"
            f"Message: {batch_result.get('message', 'No message received.')}"
        )
        print(batch_status)
    except Exception as e:
        batch_status = f"Batch submission failed: {e}"
        print(batch_status)
    
    final_status = (
        f"Individual Submission Results:\n"
        f"Successfully submitted: {successful_submissions}/{len(answers_payload)} answers\n"
        f"Total accumulated score: {total_score}\n"
        f"Average score per question: {total_score/len(answers_payload):.1f}\n"
        f"Questions answered correctly: {correct_answers}/{len(answers_payload)}\n\n"
        f"{batch_status}"
    )
    
    results_df = pd.DataFrame(results_log)
    return final_status, 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)