app.py

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

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

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
import os
from typing import TypedDict, List, Optional, Literal

from langchain_openai import ChatOpenAI
from langchain_core.messages import SystemMessage, HumanMessage, AIMessage, BaseMessage
from langchain_core.output_parsers import StrOutputParser
from langchain_core.tools import Tool
from langgraph.graph import StateGraph, END
from langgraph.prebuilt import ToolNode
from typing_extensions import Annotated

from langchain_core.messages import BaseMessage
from langgraph.graph.message import add_messages

from tool import web_search, web_fetch, _extract_video_id, youtube_transcript  # wrappers from step 2


# -----------------------------
# State
# -----------------------------
class AgentState(TypedDict):
    question: str
    messages: Annotated[list[BaseMessage], add_messages]
    final: Optional[str]
    steps: int
    last_error: Optional[str]


MAX_STEPS = 10

HELP_PROMPT = (
    "You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string."
)


# -----------------------------
# LLM + Tools
# -----------------------------
llm = ChatOpenAI(
    model="gpt-4o",
    api_key=os.environ["OPENAI_API_KEY"],
    temperature=0,
)

tools = [web_search, web_fetch, youtube_transcript]
tool_node = ToolNode(tools)


# -----------------------------
# Helper: check final format
# -----------------------------
import re

def extract_final(text: str) -> Optional[str]:
    """
    Robustly extracts the final answer, handling case sensitivity and bold formatting.
    """
    # Use regex to find "FINAL ANSWER:" case-insensitive, potentially with ** or ##
    match = re.search(r"(?i)(\*\*|##)?\s*FINAL ANSWER\s*(\*\*|##)?\s*:\s*(.*)", text, re.DOTALL)
    
    if match:
        # Return the captured content (group 3)
        return match.group(3).strip()
    return None


# -----------------------------
# Nodes
# -----------------------------
def start(state: AgentState) -> AgentState:
    state["messages"] = [
        SystemMessage(content=HELP_PROMPT),
        HumanMessage(content=state["question"]),
    ]
    state["steps"] = 0
    state["final"] = None
    state["last_error"] = None
    return state


def call_model(state: AgentState) -> AgentState:
    state["steps"] += 1
    resp = llm.bind_tools(tools).invoke(state["messages"])
    state["messages"].append(resp)
    return state


def maybe_finalize(state: AgentState) -> AgentState:
    """If the model produced FINAL ANSWER, store it. Otherwise keep going."""
    last = state["messages"][-1]
    if isinstance(last, AIMessage):
        final_line = extract_final(last.content if isinstance(last.content, str) else str(last.content))
        if final_line:
            state["final"] = final_line
    return state


def format_guard(state: AgentState) -> AgentState:
    """If we hit step limit and still no FINAL ANSWER, force one."""
    if state["final"] is None:
        # Ask model to rewrite into the required format only
        state["messages"].append(
            HumanMessage(
                content="Rewrite your response to follow the required format exactly. "
                        "Return only one line: FINAL ANSWER: ...")
        )
    return state


# -----------------------------
# Router: decide next step
# -----------------------------
def route(state: AgentState) -> Literal["tools", "finalize", "guard", "end"]:
    # 1. First, check if the model wants to call tools.
    # We MUST execute tools if requested, otherwise we break the conversation chain.
    last = state["messages"][-1]
    if isinstance(last, AIMessage) and getattr(last, "tool_calls", None):
        return "tools"

    # 2. If no tools, check if we are done.
    if state["final"] is not None:
        return "end"

    # 3. TIME LIMIT CHECK
    if state["steps"] >= MAX_STEPS:
        # CHECK FOR DEATH LOOP:
        # Look at the message before the last one. Was it our "Rewrite" prompt?
        # If yes, we already tried to guard and it failed. Don't try again.
        messages = state["messages"]
        if len(messages) >= 2:
            second_to_last = messages[-2]
            if isinstance(second_to_last, HumanMessage) and "Rewrite your response" in str(second_to_last.content):
                # We tried, we failed. Just give up to save the recursion limit.
                return "end"
        
        # Otherwise, try the guard rail once.
        return "guard"
    
    # 4. Default loop
    return "finalize"


# -----------------------------
# Build graph
# -----------------------------
graph = StateGraph(AgentState)

graph.add_node("start", start)
graph.add_node("model", call_model)
graph.add_node("tools", tool_node)
graph.add_node("finalize", maybe_finalize)
graph.add_node("guard", format_guard)

graph.set_entry_point("start")
graph.add_edge("start", "model")
graph.add_edge("model", "finalize")

graph.add_conditional_edges(
    "finalize",
    route,
    {
        "tools": "tools",
        "finalize": "model",
        "guard": "guard",
        "end": END,
    },
)

graph.add_edge("tools", "model")
graph.add_edge("guard", "model")

app = graph.compile()



# -----------------------------
# Public callable (like your BasicAgent)
# -----------------------------
class BasicAgentLangGraph:
    def __init__(self):
        print("BasicAgentLangGraph initialized.")

    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        state: AgentState = {
            "question": question,
            "messages": [],
            "final": None,
            "steps": 0,
            "last_error": None,
        }
        out = app.invoke(state)
        # If still none, fallback
        return out["final"] or "FINAL ANSWER: not available"




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 = BasicAgentLangGraph()
    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. 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.")
        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)