app.py

import os
import gradio as gr
import requests
import pandas as pd
from typing import TypedDict
from langgraph.graph import StateGraph, END

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
# Using a free Hugging Face model via Inference API (no auth required for public models)
HF_API_URL = "https://api-inference.huggingface.co/models"
HF_MODEL_ID = "mistralai/Mistral-7B-Instruct-v0.2"

# --- State Definition for LangGraph ---
class AgentState(TypedDict):
    question: str
    answer: str

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
    def __init__(self):
        print("BasicAgent initialized with LangGraph and Hugging Face API.")
        self.api_url = f"{HF_API_URL}/{HF_MODEL_ID}"
        print(f"Using Hugging Face Inference API: {self.api_url}")
        
        # Build LangGraph workflow
        self.workflow = self._build_graph()
    
    def _build_graph(self):
        """Build the LangGraph workflow for answering questions."""
        workflow = StateGraph(AgentState)
        
        # Add node: process question
        workflow.add_node("process_question", self._process_question)
        
        # Set entry point
        workflow.set_entry_point("process_question")
        
        # Connect to end
        workflow.add_edge("process_question", END)
        
        # Compile the graph
        return workflow.compile()
    
    def _call_hf_api(self, prompt: str) -> str:
        """Call Hugging Face Inference API directly (free, no auth required for public models)."""
        try:
            # Format prompt for Mistral instruct model
            formatted_prompt = f"<s>[INST] You are a helpful AI assistant. Answer the question concisely and accurately. Provide only the answer without any additional text like 'FINAL ANSWER' or explanations.\n\nQuestion: {prompt} [/INST]"
            
            payload = {
                "inputs": formatted_prompt,
                "parameters": {
                    "max_new_tokens": 512,
                    "temperature": 0.7,
                    "return_full_text": False
                }
            }
            
            response = requests.post(
                self.api_url,
                json=payload,
                headers={"Content-Type": "application/json"},
                timeout=30
            )
            
            if response.status_code == 200:
                result = response.json()
                # Extract generated text from response (HF API returns list with dict)
                generated_text = ""
                if isinstance(result, list) and len(result) > 0:
                    if isinstance(result[0], dict):
                        generated_text = result[0].get("generated_text", "")
                    else:
                        generated_text = str(result[0])
                elif isinstance(result, dict):
                    generated_text = result.get("generated_text", result.get("text", ""))
                else:
                    generated_text = str(result)
                
                # Clean the response
                answer = generated_text.strip()
                # Remove "FINAL ANSWER:" if present (as per requirements)
                answer_upper = answer.upper()
                if "FINAL ANSWER:" in answer_upper:
                    parts = answer.split("FINAL ANSWER:", 1)
                    if len(parts) > 1:
                        answer = parts[1].strip()
                elif "FINAL ANSWER" in answer_upper:
                    parts = answer.split("FINAL ANSWER", 1)
                    if len(parts) > 1:
                        answer = parts[1].strip()
                
                return answer
            elif response.status_code == 503:
                # Model is loading, wait and retry once
                error_msg = "Model is loading, please try again in a moment."
                print(f"Warning: {error_msg}")
                return error_msg
            else:
                error_msg = f"API returned status {response.status_code}: {response.text[:200]}"
                print(f"Error: {error_msg}")
                return f"Error: {error_msg}"
                
        except requests.exceptions.Timeout:
            return "Error: Request to Hugging Face API timed out."
        except requests.exceptions.RequestException as e:
            return f"Error: Failed to connect to Hugging Face API - {str(e)}"
        except Exception as e:
            return f"Error: Unexpected error - {str(e)}"
    
    def _process_question(self, state: AgentState) -> AgentState:
        """Process the question and generate an answer using Hugging Face API."""
        question = state["question"]
        print(f"Processing question: {question[:100]}...")
        
        # Call Hugging Face API
        answer = self._call_hf_api(question)
        print(f"Generated answer (first 100 chars): {answer[:100]}...")
        
        return {"question": question, "answer": answer}
    
    def __call__(self, question: str) -> str:
        """Main entry point for the agent."""
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        
        # Run the LangGraph workflow
        try:
            initial_state = {"question": question, "answer": ""}
            result = self.workflow.invoke(initial_state)
            answer = result.get("answer", "No answer generated.")
            print(f"Agent returning answer: {answer[:100]}...")
            return answer
        except Exception as e:
            print(f"Error in agent workflow: {e}")
            return f"Error processing question: {str(e)}"

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. 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)