app.py

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

from langgraph.graph import StateGraph, END
from typing import TypedDict
import string

import sys
import io
import contextlib
import re
import textwrap


def code_interpreter(code: str) -> str:
    """
    Executes the given Python code string and captures its final printed output.
    """
    buffer = io.StringIO()
    try:
        # Redirect stdout to buffer
        with contextlib.redirect_stdout(buffer):
            exec(code, {})
        return buffer.getvalue().strip()
    except Exception as e:
        return f"Execution Error: {e}"



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

# Define the State for the graph
import string
from langgraph.graph import StateGraph, END
from typing import TypedDict

class AgentState(TypedDict):
    question: str
    response: str
    is_reversed: bool
    is_riddle: bool
    is_python: bool
    file_name: str | None 

class SuperSmartAgent:
    def __init__(self):
        os.chdir(os.path.dirname(os.path.abspath(__file__)))
        self.graph = self._build_graph()

    def _build_graph(self):
        workflow = StateGraph(AgentState)

        workflow.add_node("check_reversed", self.check_reversed)
        workflow.add_node("fix_question", self.fix_question)
        workflow.add_node("check_riddle_or_trick", self.check_riddle_or_trick)
        workflow.add_node("solve_riddle", self.solve_riddle)
        workflow.add_node("check_python_suitability", self.check_python_suitability)
        workflow.add_node("execute_python_code", self.execute_python_code)

        workflow.set_entry_point("check_reversed")

        workflow.add_conditional_edges(
            "check_reversed",
            lambda state: "fix_question" if state["is_reversed"] else "check_riddle_or_trick",
        )
        workflow.add_conditional_edges(
            "check_riddle_or_trick",
            lambda state: "solve_riddle" if state["is_riddle"] else "check_python_suitability",
        )
        workflow.add_conditional_edges(
            "check_python_suitability",
            lambda state: "execute_python_code" if state["is_python"] else END,
        )
        workflow.add_edge("fix_question", "check_riddle_or_trick")
        workflow.add_edge("solve_riddle", END)
        workflow.add_edge("execute_python_code", END)

        return workflow.compile()

    def __call__(self, question: str, file_name: str | None = None) -> str:
        initial_state = AgentState(
            question=question,
            response="",
            is_reversed=False,
            is_riddle=False,
            is_python=False,
            file_name=file_name
        )
        final_state = self.graph.invoke(initial_state)
        return final_state["response"]


    def score_text(self, text):
        alnum_count = sum(c.isalnum() for c in text)
        space_count = text.count(' ')
        punctuation_count = sum(c in string.punctuation for c in text)
        ends_properly = text[-1] in '.!?'
        score = alnum_count + space_count
        if ends_properly:
            score += 5
        return score

    def check_reversed(self, state):
        question = state["question"]
        reversed_candidate = question[::-1]
        original_score = self.score_text(question)
        reversed_score = self.score_text(reversed_candidate)
        if reversed_score > original_score:
            state["is_reversed"] = True
        else:
            state["is_reversed"] = False
        return state

    def fix_question(self, state):
        if state.get("is_reversed", False):
            state["question"] = state["question"][::-1]
        return state

    def check_riddle_or_trick(self, state):
        q = state["question"].lower()
        keywords = ["opposite of", "if you understand", "riddle", "trick question", "what comes next", "i speak without"]
        state["is_riddle"] = any(kw in q for kw in keywords)
        return state

    def solve_riddle(self, state):
        q = state["question"].lower()
        if "opposite of the word" in q:
            if "left" in q:
                state["response"] = "right"
            elif "up" in q:
                state["response"] = "down"
            elif "hot" in q:
                state["response"] = "cold"
            else:
                state["response"] = "Unknown opposite."
        else:
            state["response"] = "Could not solve riddle."
        return state

    def check_python_suitability(self, state):
        question = state["question"].lower()
        patterns = ["output", "python", "execute", "run", "script"]
        state["is_python"] = any(word in question for word in patterns)
        return state

    def execute_python_code(self, state):
        file_name = state.get("file_name")
    
        # Debug logging for file_name presence and value
        print(f"[DEBUG] file_name from state: {file_name!r}")
    
        if file_name and file_name.endswith(".py"):
            file_path = file_name
            print(f"[DEBUG] Attempting to open Python file at: {file_path}")
            try:
                with open(file_path, "r") as f:
                    code = f.read()
                print(f"[DEBUG] Successfully read code from {file_path}. Code length: {len(code)} chars")
            except Exception as e:
                error_msg = f"Error loading Python file: {e}"
                print(f"[ERROR] {error_msg}")
                state["response"] = error_msg
                return state
        else:
            print("[WARN] No valid Python file attached or filename missing/incorrect extension.")
            state["response"] = "No valid Python file attached."
            return state
    
        try:
            result = code_interpreter(code)
            print(f"[DEBUG] Execution result: {result[:100]}...")  # Print first 100 chars max
            state["response"] = str(result)
        except Exception as e:
            error_msg = f"Error executing Python code: {e}"
            print(f"[ERROR] {error_msg}")
            state["response"] = error_msg
    
        return state

########################################
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("https://huggingface.co/spaces/selim-ba/Final_Agent_HF_Course/tree/main") # 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 = SuperSmartAgent() #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)