app.py

import os
import json
import gradio as gr
import requests
import inspect
import torch
import pandas as pd
import yaml

# Tool disponibili di default:
# ApiWebSearchTool
# PythonInterpreterTool
# FinalAnswerTool
# UserInputTool
# WebSearchTool
# DuckDuckGoSearchTool
# GoogleSearchTool
# VisitWebpageTool
# WikipediaSearchTool
# SpeechToTextTool
from smolagents import CodeAgent, ToolCallingAgent, TransformersModel, VisitWebpageTool, PythonInterpreterTool, WebSearchTool, WikipediaSearchTool, FinalAnswerTool, Tool, tool # InferenceClientModel, GoogleSearchTool (usa SERPAPI_API_KEY), DuckDuckGoSearchTool
from smolagents.agents import PromptTemplates, EMPTY_PROMPT_TEMPLATES

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

@tool
def invert_sentence_tool(sentence: str) -> str:
	"""
	Inverts the order of all characters in a sentence.
	Args:
		sentence (str): The sentence to invert.
	Returns:
		str: The sentence with characters in reverse order.
	"""
	return sentence[::-1]

# --- First Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class FirstAgent:
	### First Agent is the first attempt to develop an agent for the course. ###
	def __init__(self):
		""" Initializes the FirstAgent with a TransformersModel and a CodeAgent. """
		# microsoft/Phi-4-reasoning-plus, microsoft/Phi-4-reasoning, microsoft/Phi-4-mini-reasoning, microsoft/Phi-4-mini-instruct, microsoft/Phi-4-multimodal-instruct, "Qwen/Qwen2.5-Coder-32B-Instruct", "HuggingFaceTB/SmolLM2-1.7B-Instruct"
		model_id = "Qwen/Qwen2.5-Coder-32B-Instruct"
		model = TransformersModel(model_id=model_id, trust_remote_code=True, max_new_tokens=4096)

		# Inizializza l'agente
		with open("prompts.yaml", "r", encoding="utf-8") as file:
			prompts = yaml.safe_load(file)

		prompt_templates = PromptTemplates(**prompts)

		# prompt_templates = EMPTY_PROMPT_TEMPLATES
		# prompt_templates["system_prompt"] = """You are an intelligent agent that answers questions and uses tools to help users.
		# Think step by step and use tools when needed.
		# If you need to search the web, use the WebSearchTool.
		# If you need to visit a webpage, use the VisitWebpageTool.
		# If you need to run Python code, use the PythonInterpreterTool.
		# If you need to generate code to extract information, generate the code and use the PythonInterpreterTool to execute the code and extract the informations.
		# If you find information in Wikipedia, use the WikipediaSearchTool.
		# Verify your final answer and the format of the final answer before returning it.
		# When you have found the definitive answer, return it by calling final_answer(answer) within a Python code block.
		# If you don't know the answer, say 'I don't know'."""

		# prompt_templates = PromptTemplates(
		# 	system_prompt="You are an intelligent agent that helps users solve complex tasks using tools.",
		# 	planning="Determine the logical steps to solve the user's problem.",
		# 	managed_agent="Execute each planned step using the available tools.",
		# 	final_answer="When you have completed all steps, return the final answer using final_answer()."
		# )


		self.agent = CodeAgent(
			model=model,
			prompt_templates=prompt_templates,
			stream_outputs=True,  # Enable streaming outputs
			additional_authorized_imports=['requests', 'bs4'],
			# add_base_tools=True,  # Add base tools like UserInputTool
			# use_structured_outputs_internally=True,  # Use structured outputs internally
			tools=[
				WebSearchTool(),
				PythonInterpreterTool(),
				WikipediaSearchTool(),
				VisitWebpageTool(),
				invert_sentence_tool, # Custom tool to invert sentences
				FinalAnswerTool()  # Final answer tool to extract the final answer
			]
		)
		print("FirstAgent inizializzato.")
	
	def __call__(self, question: str) -> str:
		""" Runs the agent with the provided question and returns the answer. """
		print(f"Agent ricevuto domanda (primi 50 char): {question[:50]}...")
		try:
			answer = self.agent.run(question)
			print(f"Agent restituisce risposta: {str(answer)[:100]}...")
			return answer
		except Exception as e:
			print(f"Errore nell'agente: {e}")
			return f"Errore nell'agente: {str(e)}"

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
	### Basic Agent is a placeholder for a simple agent that always returns a fixed answer. ###
	### It is used to demonstrate the structure of an agent. ###
	def __init__(self):
		print("BasicAgent initialized.")
	def __call__(self, question: str) -> str:
		print(f"Agent received question (first 50 chars): {question[:50]}...")
		fixed_answer = "This is a default answer."
		print(f"Agent returning fixed answer: {fixed_answer}")
		return fixed_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 = FirstAgent()
	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 from API: {e}")
		print("Attempting to load questions from local file 'questions.json'...")
		try:
			with open("questions.json", "r", encoding="utf-8") as f:
				questions_data = json.load(f)
			if not questions_data:
				return "Both API and local questions file are empty.", None
			print(f"Successfully loaded {len(questions_data)} questions from local file.")
		except FileNotFoundError:
			return "Error: Could not fetch questions from API and 'questions.json' file not found.", None
		except json.JSONDecodeError as json_e:
			return f"Error: Could not fetch questions from API and local file has invalid JSON: {json_e}", None
		except Exception as file_e:
			return f"Error: Could not fetch questions from API and failed to read local file: {file_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]}")
		print("Attempting to load questions from local file 'questions.json'...")
		try:
			with open("questions.json", "r", encoding="utf-8") as f:
				questions_data = json.load(f)
			if not questions_data:
				return "Both API response is invalid and local questions file is empty.", None
			print(f"Successfully loaded {len(questions_data)} questions from local file.")
		except FileNotFoundError:
			return "Error: Could not decode API response and 'questions.json' file not found.", None
		except json.JSONDecodeError as json_e:
			return f"Error: Could not decode API response and local file has invalid JSON: {json_e}", None
		except Exception as file_e:
			return f"Error: Could not decode API response and failed to read local file: {file_e}", None
	except Exception as e:
		print(f"An unexpected error occurred fetching questions: {e}")
		print("Attempting to load questions from local file 'questions.json'...")
		try:
			with open("questions.json", "r", encoding="utf-8") as f:
				questions_data = json.load(f)
			if not questions_data:
				return "Unexpected API error occurred and local questions file is empty.", None
			print(f"Successfully loaded {len(questions_data)} questions from local file.")
		except FileNotFoundError:
			return "Error: Unexpected API error occurred and 'questions.json' file not found.", None
		except json.JSONDecodeError as json_e:
			return f"Error: Unexpected API error occurred and local file has invalid JSON: {json_e}", None
		except Exception as file_e:
			return f"Error: Unexpected API error occurred and failed to read local file: {file_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("# Raffaele Agent Evaluation Runner")
	gr.Markdown(
		"""
		1.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
		2.  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)