app.py

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

# 🔹 NOVO: imports do smolagents
from smolagents import CodeAgent, DuckDuckGoSearchTool, InferenceClientModel


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


# =========================================================
#  Helper: limpeza de resposta para EXACT MATCH
# =========================================================
def clean_answer(text: str) -> str:
    """
    Limpa a saída do modelo para ficar mais adequada ao EXACT MATCH.
    Remove prefixos como 'Answer:', 'Final answer:' etc.,
    aspas externas e ponto final solto.
    """
    if text is None:
        return ""

    ans = str(text).strip()

    # remove prefixos comuns
    prefixes = [
        "answer:", "resposta:", "final answer:", "final:", "ans:", "a:",
        "the answer is", "the final answer is",
    ]
    lower = ans.lower()
    for p in prefixes:
        if lower.startswith(p):
            ans = ans[len(p):].strip()
            break

    # remove ponto final se não parecer número decimal
    if ans.endswith(".") and not ans.replace(".", "", 1).isdigit():
        ans = ans[:-1].strip()

    # remove aspas externas
    if len(ans) > 1 and ans[0] == ans[-1] and ans[0] in ["'", '"']:
        ans = ans[1:-1].strip()

    return ans


# =========================================================
#  Basic Agent Definition – AGORA usando smolagents
# =========================================================

SYSTEM_PROMPT = (
    "You are an AI agent solving GAIA-style questions.\n"
    "You have access to a web search tool (DuckDuckGoSearchTool).\n"
    "For each question, you MUST search the web when needed to obtain accurate, "
    "up-to-date factual information before answering.\n"
    "Use the search tool, read the results, reason, and then produce ONLY the final answer.\n"
    "Do NOT output explanations, steps, reasoning, citations, links, or any extra words.\n"
    "Do NOT output labels like 'Final answer', 'Answer:', etc.\n"
    "If the answer is a number, output just the number. "
    "If it is a word or short phrase, output just that.\n"
    "Your output will be compared to the ground truth using EXACT MATCH."
)


class BasicAgent:
    """
    Agente smolagents com DuckDuckGoSearchTool,
    otimizado para GAIA EXACT MATCH.
    """

    def __init__(self):
        print("Initializing improved GAIA agent with search...")

        self.search_tool = DuckDuckGoSearchTool()

        # Prompt especializado
        self.model = InferenceClientModel(
            system_prompt=(
                "You are a GAIA evaluation agent that must answer EXACTLY the final answer.\n"
                "You MUST use the search tool to retrieve verified information.\n"
                "When you use search, read the results and extract ONLY the exact required answer.\n"
                "RULES:\n"
                " - Output MUST be a SINGLE short string.\n"
                " - NO explanations.\n"
                " - NO reasoning.\n"
                " - NO multi-sentence output.\n"
                " - NO citations or URLs.\n"
                " - NO extra words.\n"
                "Examples of valid outputs:\n"
                "   '2002'\n"
                "   '7'\n"
                "   'egalitarian'\n"
                "   'Mercedes Sosa'\n"
                "INVALID OUTPUTS:\n"
                "   'The final answer is 7.'\n"
                "   'According to Wikipedia, the answer is 2002.'\n"
                "   'After checking, I think it is 3.'\n"
                "Your response MUST be only the exact final answer.\n"
            )
        )

        # CodeAgent com raciocínio guiado
        self.agent = CodeAgent(
            model=self.model,
            tools=[self.search_tool],
            max_steps=8,    # permite buscar e refinar
        )

    def __call__(self, question: str) -> str:
        print(f"Processing: {question[:80]}...")
        try:
            raw = self.agent.run(
                f"Answer this question using search:\n{question}\n"
                "Return ONLY the exact final answer."
            )
            final = clean_answer(raw)
            print(f"Final cleaned answer: {final}")
            return final
        except Exception as e:
            print(f"Error: {e}")
            return ""


# =========================================================
#  Runner + submit (mantido do template, só usando BasicAgent novo)
# =========================================================
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 (agora nosso agente smolagents)
    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
    # (useful for others so please keep it public)
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(f"Agent code URL: {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 (smolagents)")
    gr.Markdown(
        """
        **Instructions:**
        1.  This space uses a simple agent built with `smolagents` + `InferenceClientModel`.
        2.  Log in to your Hugging Face account using the button below.
        3.  Click **'Run Evaluation & Submit All Answers'** to fetch questions,
            run the agent, submit answers, and see your score.
        ---
        **Notes:**
        - The correction on the server uses EXACT MATCH, so the agent is prompted
          to output only the final answer (sem 'FINAL ANSWER', sem explicações).
        - This template is intentionally simples; você pode adicionar tools,
          melhorar o prompt, etc., se quiser subir seu score.
        """
    )

    gr.LoginButton()

    run_button = gr.Button("Run Evaluation & Submit All Answers")

    status_output = gr.Textbox(
        label="Run Status / Submission Result", lines=5, interactive=False
    )
    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)