app.py

import os
import gradio as gr
import requests
import pandas as pd
from langchain_openai import ChatOpenAI
from os import getenv
from dotenv import load_dotenv
from typing import Annotated
from pydantic import SecretStr

from typing_extensions import TypedDict

from langgraph.graph import StateGraph, START, END
from langgraph.graph.message import add_messages
import asyncio  # Added for async processing
import time  # Added for rate limiting

from langchain_community.tools import WikipediaQueryRun
from langchain_community.utilities.wikipedia import WikipediaAPIWrapper
from langgraph.prebuilt import tools_condition
from langgraph.checkpoint.memory import MemorySaver
from langgraph.prebuilt import create_react_agent

# Phoenix imports
from phoenix.otel import register
import logging

from agent.agent import get_agent
from agent.config import create_agent_config

load_dotenv()

# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
APP_NAME = "OracleBot"

# Phoenix tracing setup
def start_phoenix():
    """Setup Phoenix tracing for the agent."""
    register(
        project_name=APP_NAME,
        auto_instrument=True,
    )
    logging.getLogger("openinference").setLevel(logging.CRITICAL)
    print("Phoenix tracing enabled.")

# Initialize Phoenix (you can comment this out if you don't want tracing)
start_phoenix()

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------

# class State(TypedDict):
#     # Messages have the type "list". The `add_messages` function
#     # in the annotation defines how this state key should be updated
#     # (in this case, it appends messages to the list, rather than overwriting them)
#     messages: Annotated[list, add_messages]

class BasicAgent:
    def __init__(self):
        self.agent = get_agent()
        self._last_request_time = 0
        self._request_lock = asyncio.Lock()

    async def __call__(self, question: str) -> str:
        print(f"Agent received question: {question}")
        
        # Rate limiting: ensure at least 1 second between requests
        async with self._request_lock:
            current_time = time.time()
            time_since_last_request = current_time - self._last_request_time
            if time_since_last_request < 1.0:
                sleep_time = 1.0 - time_since_last_request
                print(f"Rate limiting: sleeping for {sleep_time:.2f} seconds")
                await asyncio.sleep(sleep_time)
            
            self._last_request_time = time.time()
        
        # Create configuration like in main.py
        config = create_agent_config(app_name=APP_NAME)
        
        # Call the agent with the question and config (like main.py)
        answer = await self.agent.ainvoke(
            {"messages": [{"role": "user", "content": question}]},
            config=config
        )

        print(f"Agent returning answer: {answer}")
        
        # Extract content from the last message in the response
        if "messages" in answer and answer["messages"]:
            last_message = answer["messages"][-1]
            if hasattr(last_message, 'content'):
                content = last_message.content
            else:
                content = str(last_message)
        else:
            content = str(answer)
            
        return str(content) if content is not None else ""

# Simplified concurrent processor: launch all tasks immediately and await them together
async def process_questions(agent: BasicAgent, questions_data: list):
    print(f"Running agent on {len(questions_data)} questions concurrently (simple fan-out)...")

    async def handle(item: dict):
        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}")
            return None
        try:
            submitted_answer = await agent(question_text)
            return {
                "log": {"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer},
                "payload": {"task_id": task_id, "submitted_answer": submitted_answer},
            }
        except Exception as e:
            print(f"Error running agent on task {task_id}: {e}")
            return {
                "log": {"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"},
                "payload": {"task_id": task_id, "submitted_answer": f"AGENT ERROR: {e}"},
            }

    results = await asyncio.gather(*(handle(item) for item in questions_data))
    results_log = [r["log"] for r in results if r]
    answers_payload = [r["payload"] for r in results if r]
    return results_log, answers_payload

async 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.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 requests.exceptions.RequestException as e:
        print(f"Error fetching questions: {e}")
        return f"Error fetching 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 concurrently (simple gather)
    results_log, answers_payload = await process_questions(agent, questions_data)

    # Remove everything before "FINAL ANSWER: " in submitted answers
    for answer in answers_payload:
        if "submitted_answer" in answer:
            answer["submitted_answer"] = answer["submitted_answer"].split("FINAL ANSWER: ", 1)[-1].strip()

    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)