app.py

import os
import io
import inspect
import contextlib
from typing import Annotated, TypedDict
 
import gradio as gr
import requests
import pandas as pd
from bs4 import BeautifulSoup
from ddgs import DDGS
 
from langchain_openai import ChatOpenAI
from langchain_core.tools import tool
from langchain_core.messages import AnyMessage, HumanMessage, SystemMessage
from langgraph.graph import StateGraph, START
from langgraph.graph.message import add_messages
from langgraph.prebuilt import ToolNode, tools_condition
 
import spaces
 
@spaces.GPU
def gpu_placeholder():
    pass
 
 
# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
# --- Agent configuration ---
# Any chat model served by HF Inference Providers with tool calling works here.
# You can override it with a MODEL_ID variable in the Space settings.
MODEL_ID = os.getenv("MODEL_ID", "openai/gpt-oss-120b")
MAX_CHARS = 20000  # cap on text returned by tools, to keep the context small
HEADERS = {"User-Agent": "Mozilla/5.0 (GAIA agent - HF Agents Course)"}
 
 
# --- Tools ---
def _page_text(url: str) -> str:
    """Download a web page and return its visible text."""
    r = requests.get(url, headers=HEADERS, timeout=30)
    r.raise_for_status()
    soup = BeautifulSoup(r.text, "html.parser")
    for tag in soup(["script", "style", "nav", "footer", "header"]):
        tag.decompose()
    return soup.get_text("\n", strip=True)[:MAX_CHARS]
 
 
@tool
def web_search(query: str) -> str:
    """Search the web with DuckDuckGo. Returns title, URL and snippet of the top 5 results."""
    try:
        results = DDGS().text(query, max_results=5)
        return "\n\n".join(f"{r['title']}\n{r['href']}\n{r['body']}" for r in results) or "No results."
    except Exception as e:
        return f"Search error: {e}"
 
 
@tool
def fetch_webpage(url: str) -> str:
    """Download a web page and return its text content. Use it to read pages found with web_search."""
    try:
        return _page_text(url)
    except Exception as e:
        return f"Error fetching {url}: {e}"
 
 
@tool
def wikipedia_search(query: str) -> str:
    """Search English Wikipedia and return the full text (tables included) of the best matching article."""
    try:
        data = requests.get(
            "https://en.wikipedia.org/w/api.php",
            params={"action": "query", "list": "search", "srsearch": query, "format": "json", "srlimit": 1},
            headers=HEADERS,
            timeout=20,
        ).json()
        hits = data["query"]["search"]
        if not hits:
            return "No Wikipedia results."
        title = hits[0]["title"]
        url = "https://en.wikipedia.org/wiki/" + title.replace(" ", "_")
        return f"# {title} ({url})\n\n{_page_text(url)}"
    except Exception as e:
        return f"Wikipedia error: {e}"
 
 
@tool
def read_task_file(task_id: str, file_name: str) -> str:
    """Download the file attached to a task and return its content as text.
    Supports spreadsheets (xlsx, xls, csv) and text/code files (py, txt, md, json)."""
    try:
        r = requests.get(f"{DEFAULT_API_URL}/files/{task_id}", timeout=60)
        r.raise_for_status()
    except Exception as e:
        return f"Error downloading file: {e}"
    ext = file_name.rsplit(".", 1)[-1].lower()
    if ext in ("xlsx", "xls"):
        sheets = pd.read_excel(io.BytesIO(r.content), sheet_name=None)
        return "\n\n".join(f"Sheet '{name}':\n{df.to_csv(index=False)}" for name, df in sheets.items())
    if ext == "csv":
        return pd.read_csv(io.BytesIO(r.content)).to_csv(index=False)
    if ext in ("py", "txt", "md", "json"):
        return r.content.decode("utf-8", errors="replace")[:MAX_CHARS]
    return f"Files of type .{ext} are not supported yet."
 
 
@tool
def run_python(code: str) -> str:
    """Execute Python code and return what it prints (use print!).
    Useful for math, counting, string manipulation and data analysis."""
    buffer = io.StringIO()
    try:
        with contextlib.redirect_stdout(buffer):
            exec(code, {})
        return buffer.getvalue() or "The code ran but printed nothing. Use print()."
    except Exception as e:
        return f"{buffer.getvalue()}\nError: {type(e).__name__}: {e}"
 
 
TOOLS = [web_search, fetch_webpage, wikipedia_search, read_task_file, run_python]
 
SYSTEM_PROMPT = """You are a general AI assistant solving questions from the GAIA benchmark.
Use the tools to look up and verify information; do not guess facts you can check.
When you are done, reply with ONLY the final answer: no explanation, no "FINAL ANSWER" prefix.
 
Answer format:
- Number: digits only, no thousands separators, no units ($, %, km...) unless the question asks for them.
- String: as few words as possible, no articles, no abbreviations (e.g. write city names in full).
- List: comma separated values, each following the rules above.
Always follow any extra formatting instruction in the question (order, rounding, capitalization...)."""
 
 
# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class AgentState(TypedDict):
    messages: Annotated[list[AnyMessage], add_messages]
 
 
class BasicAgent:
    def __init__(self):
        # llm = ChatOpenAI(
        #     model=MODEL_ID,
        #     base_url="https://router.huggingface.co/v1",  # HF Inference Providers (OpenAI-compatible)
        #     api_key=os.environ["HF_TOKEN"],
        #     temperature=0,
        # )

        llm = ChatOpenAI(
            model=MODEL_ID,
            base_url=os.getenv("LLM_BASE_URL", "https://api.groq.com/openai/v1"),
            api_key=os.getenv("LLM_API_KEY") or os.environ["HF_TOKEN"],
            temperature=0,
            max_retries=5,  # riprova in caso di rate limit (429)
        )
        self.llm = llm.bind_tools(TOOLS)
 
        # Graph: assistant -> (tools -> assistant)* -> end
        builder = StateGraph(AgentState)
        builder.add_node("assistant", self._assistant)
        builder.add_node("tools", ToolNode(TOOLS))
        builder.add_edge(START, "assistant")
        builder.add_conditional_edges("assistant", tools_condition)  # tool call? -> tools, else END
        builder.add_edge("tools", "assistant")
        self.graph = builder.compile()
        print(f"LangGraph agent initialized with model {MODEL_ID}.")
 
    def _assistant(self, state: AgentState):
        messages = [SystemMessage(content=SYSTEM_PROMPT)] + state["messages"]
        return {"messages": [self.llm.invoke(messages)]}
 
    def __call__(self, question: str, task_id: str | None = None, file_name: str | None = None) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        prompt = question
        if file_name:
            prompt += (
                f"\n\nThis task has an attached file named '{file_name}'. "
                f"Read it with read_task_file(task_id='{task_id}', file_name='{file_name}')."
            )
        try:
            result = self.graph.invoke(
                {"messages": [HumanMessage(content=prompt)]},
                config={"recursion_limit": 25},
            )
        except Exception as e:
            import traceback
            traceback.print_exc()
            return f"AGENT ERROR: {type(e).__name__}: {e}"

        last = result["messages"][-1]
        answer = self._clean(last.content)
        if not answer:
            # show what the model actually returned instead of an empty string
            return f"EMPTY: steps={len(result['messages'])}, last={repr(last)[:300]}"
        print(f"Agent returning answer: {answer}")
        return answer
 
    @staticmethod
    def _clean(answer) -> str:
        if isinstance(answer, list):  # some models return content blocks
            answer = " ".join(b.get("text", "") if isinstance(b, dict) else str(b) for b in answer)
        answer = answer.strip()
        if answer.upper().startswith("FINAL ANSWER"):
            answer = answer[len("FINAL ANSWER"):].lstrip(" :")
        return answer.rstrip(".").strip()
 
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, task_id, item.get("file_name"))
            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)