app.py

import contextlib
import io
import os
import re
import tempfile
import traceback
from pathlib import Path
from typing import Annotated, Optional, TypedDict
from urllib.parse import parse_qs, urlparse

import gradio as gr
import pandas as pd
import requests
from langchain_community.tools import DuckDuckGoSearchResults, WikipediaQueryRun
from langchain_community.utilities import DuckDuckGoSearchAPIWrapper, WikipediaAPIWrapper
from langchain_core.messages import AnyMessage, HumanMessage, SystemMessage
from langchain_core.tools import tool
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
from langgraph.graph import START, StateGraph
from langgraph.graph.message import add_messages
from langgraph.prebuilt import ToolNode, tools_condition

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
DEFAULT_MODEL_ID = os.getenv("AGENT_MODEL_ID", "Qwen/Qwen2.5-Coder-32B-Instruct")
AGENT_RECURSION_LIMIT = int(os.getenv("AGENT_RECURSION_LIMIT", "30"))
MAX_TOOL_OUTPUT_CHARS = int(os.getenv("MAX_TOOL_OUTPUT_CHARS", "15000"))
HF_TOKEN_ENV_VARS = ("HUGGINGFACEHUB_API_TOKEN", "HF_TOKEN", "HUGGING_FACE_HUB_TOKEN")

SYSTEM_PROMPT = """You are a helpful assistant tasked with answering GAIA benchmark questions using tools.

Use tools aggressively when they can verify the answer: web search, Wikipedia, web pages, YouTube transcripts, task files, downloaded files, and Python calculations.
If the user message includes a task_id and the question mentions an image, spreadsheet, audio, pdf, or other attachment, first call download_task_file(task_id), then inspect it with read_file.

Report your thoughts internally through tool use, but finish your answer with the following template:
FINAL ANSWER: [YOUR FINAL ANSWER].

YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings.
If you are asked for a number, don't use commas and don't use units such as $, percent sign, km, etc. unless explicitly specified.
If you are asked for a string, don't use articles or abbreviations, and write digits in plain text unless explicitly specified.
If you are asked for a comma separated list, apply the rules above for each element and ensure there is exactly one space after each comma.
Your final message should only start with "FINAL ANSWER: ", followed by the answer. Do not write anything after the final answer.
"""

_FINAL_ANSWER_RE = re.compile(r"FINAL\s*ANSWER\s*:\s*(.+?)\s*$", re.IGNORECASE | re.DOTALL)


def _resolve_hf_token() -> Optional[str]:
    for var_name in HF_TOKEN_ENV_VARS:
        value = os.getenv(var_name)
        if value:
            return value
    return None


def _trim(text: str, limit: int = MAX_TOOL_OUTPUT_CHARS) -> str:
    if len(text) <= limit:
        return text
    return text[:limit] + "\n\n[TRUNCATED]"


def _safe_filename_from_response(response: requests.Response, fallback: str) -> str:
    content_disposition = response.headers.get("Content-Disposition", "")
    match = re.search(r'filename\*?=(?:UTF-8\'\')?"?([^";]+)"?', content_disposition)
    if match:
        return Path(match.group(1)).name
    parsed = urlparse(response.url)
    name = Path(parsed.path).name
    return name or fallback


@tool
def visit_webpage(url: str) -> str:
    """Fetch a webpage and return readable markdown/text.

    Args:
        url: HTTP or HTTPS URL to fetch.
    """
    try:
        from markdownify import markdownify as md

        response = requests.get(
            url,
            timeout=25,
            headers={"User-Agent": "GAIA-Agent/1.0"},
        )
        response.raise_for_status()
        content_type = response.headers.get("Content-Type", "")
        if "text/html" in content_type:
            text = md(response.text)
        else:
            text = response.text
        text = re.sub(r"\n{3,}", "\n\n", text).strip()
        return _trim(text)
    except Exception as exc:
        return f"Error fetching webpage: {exc}"


@tool
def download_file_from_url(url: str, filename: Optional[str] = None) -> str:
    """Download a file from a URL to a temporary path and return that path.

    Args:
        url: Direct URL to the file.
        filename: Optional output filename.
    """
    try:
        response = requests.get(url, timeout=45, stream=True, headers={"User-Agent": "GAIA-Agent/1.0"})
        response.raise_for_status()
        filename = filename or _safe_filename_from_response(response, "downloaded_file")
        out_dir = Path(tempfile.gettempdir()) / "gaia_downloads"
        out_dir.mkdir(parents=True, exist_ok=True)
        out_path = out_dir / filename
        with out_path.open("wb") as f:
            for chunk in response.iter_content(chunk_size=8192):
                if chunk:
                    f.write(chunk)
        return str(out_path)
    except Exception as exc:
        return f"Error downloading file: {exc}"


def _make_download_task_file_tool(api_url: str):
    @tool
    def download_task_file(task_id: str) -> str:
        """Download the file attached to a GAIA task and return the local path.

        Args:
            task_id: The task_id returned by the questions API.
        """
        try:
            response = requests.get(f"{api_url}/files/{task_id}", timeout=45, stream=True)
            if response.status_code == 404:
                return f"No file is attached to task {task_id}."
            response.raise_for_status()
            filename = _safe_filename_from_response(response, task_id)
            out_dir = Path(tempfile.gettempdir()) / "gaia_task_files"
            out_dir.mkdir(parents=True, exist_ok=True)
            out_path = out_dir / filename
            with out_path.open("wb") as f:
                for chunk in response.iter_content(chunk_size=8192):
                    if chunk:
                        f.write(chunk)
            return str(out_path)
        except Exception as exc:
            return f"Error downloading task file: {exc}"

    return download_task_file


@tool
def read_file(path: str) -> str:
    """Read a local file and return text or a compact structured summary.

    Supports text, csv, xlsx/xls, pdf, and basic image metadata/OCR when available.

    Args:
        path: Local file path.
    """
    file_path = Path(path)
    if not file_path.exists():
        return f"File does not exist: {path}"

    suffix = file_path.suffix.lower()
    try:
        if suffix == ".csv":
            df = pd.read_csv(file_path)
            summary = [
                f"CSV rows={len(df)}, columns={len(df.columns)}",
                f"Columns: {', '.join(map(str, df.columns))}",
                "Preview:",
                df.head(20).to_csv(index=False),
            ]
            return _trim("\n".join(summary))

        if suffix in {".xlsx", ".xls"}:
            sheets = pd.read_excel(file_path, sheet_name=None)
            chunks = []
            for name, df in sheets.items():
                chunks.append(
                    "\n".join(
                        [
                            f"Sheet: {name}",
                            f"rows={len(df)}, columns={len(df.columns)}",
                            f"Columns: {', '.join(map(str, df.columns))}",
                            "Preview:",
                            df.head(20).to_csv(index=False),
                        ]
                    )
                )
            return _trim("\n\n---\n\n".join(chunks))

        if suffix == ".pdf":
            try:
                from pypdf import PdfReader
            except ImportError:
                return "pypdf is not installed."
            reader = PdfReader(str(file_path))
            text = "\n\n".join(page.extract_text() or "" for page in reader.pages)
            return _trim(text)

        if suffix in {".png", ".jpg", ".jpeg", ".webp", ".bmp", ".gif"}:
            try:
                from PIL import Image

                image = Image.open(file_path)
                lines = [f"Image: {file_path.name}", f"size={image.size}", f"mode={image.mode}"]
                try:
                    import pytesseract

                    ocr_text = pytesseract.image_to_string(image).strip()
                    if ocr_text:
                        lines.extend(["OCR text:", ocr_text])
                    else:
                        lines.append("OCR text: (empty)")
                except Exception as exc:
                    lines.append(f"OCR unavailable: {exc}")
                return _trim("\n".join(lines))
            except Exception as exc:
                return f"Error reading image: {exc}"

        return _trim(file_path.read_text(encoding="utf-8", errors="replace"))
    except Exception as exc:
        return f"Error reading file: {exc}"


@tool
def python_repl(code: str) -> str:
    """Run Python code and return stdout or errors.

    Use this for math, data wrangling, date logic, parsing, and exact computations.

    Args:
        code: Python code. Use print(...) for values you need returned.
    """
    stdout = io.StringIO()
    namespace = {"pd": pd, "requests": requests, "re": re, "Path": Path}
    try:
        with contextlib.redirect_stdout(stdout):
            exec(code, namespace, namespace)  # noqa: S102 - intentional agent tool
    except Exception:
        return _trim(f"ERROR:\n{traceback.format_exc()}\nSTDOUT:\n{stdout.getvalue()}")
    output = stdout.getvalue().strip()
    return _trim(output or "(no stdout; print the result explicitly)")


@tool
def youtube_transcript(url_or_video_id: str) -> str:
    """Fetch a YouTube transcript when captions are available.

    Args:
        url_or_video_id: YouTube URL or video id.
    """
    try:
        from youtube_transcript_api import YouTubeTranscriptApi

        video_id = url_or_video_id.strip()
        if "youtube.com" in video_id or "youtu.be" in video_id:
            parsed = urlparse(video_id)
            if parsed.netloc.endswith("youtu.be"):
                video_id = parsed.path.strip("/")
            else:
                video_id = parse_qs(parsed.query).get("v", [video_id])[0]
        transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=["en"])
        text = " ".join(item.get("text", "") for item in transcript)
        return _trim(text)
    except Exception as exc:
        return f"Could not fetch transcript: {exc}"


@tool
def arxiv_search(query: str) -> str:
    """Search arXiv and return up to three compact results.

    Args:
        query: Search query.
    """
    try:
        from langchain_community.document_loaders import ArxivLoader

        docs = ArxivLoader(query=query, load_max_docs=3).load()
        if not docs:
            return "No arXiv results found."
        return _trim(
            "\n\n---\n\n".join(
                f"Title: {doc.metadata.get('Title', '')}\n"
                f"Authors: {doc.metadata.get('Authors', '')}\n"
                f"Published: {doc.metadata.get('Published', '')}\n"
                f"Summary: {doc.page_content[:1500]}"
                for doc in docs
            )
        )
    except Exception as exc:
        return f"Error searching arXiv: {exc}"


class AgentState(TypedDict):
    messages: Annotated[list[AnyMessage], add_messages]


def build_graph(chat_model_with_tools, tools):
    """Build the explicit LangGraph ReAct loop used by BasicAgent."""

    def assistant(state: AgentState) -> dict:
        messages = [SystemMessage(content=SYSTEM_PROMPT), *state["messages"]]
        return {"messages": [chat_model_with_tools.invoke(messages)]}

    builder = StateGraph(AgentState)
    builder.add_node("assistant", assistant)
    builder.add_node("tools", ToolNode(tools))
    builder.add_edge(START, "assistant")
    builder.add_conditional_edges("assistant", tools_condition)
    builder.add_edge("tools", "assistant")
    return builder.compile()


# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
    def __init__(self, api_url: str = DEFAULT_API_URL):
        token = _resolve_hf_token()
        if not token:
            raise RuntimeError("Set HUGGINGFACEHUB_API_TOKEN or HF_TOKEN in your Space secrets.")

        print(f"BasicAgent initializing with LangGraph and {DEFAULT_MODEL_ID}.")
        llm = HuggingFaceEndpoint(
            repo_id=DEFAULT_MODEL_ID,
            task="text-generation",
            max_new_tokens=1024,
            do_sample=False,
            repetition_penalty=1.03,
            huggingfacehub_api_token=token,
            provider="auto",
        )
        chat_model = ChatHuggingFace(llm=llm)

        search = DuckDuckGoSearchResults(
            api_wrapper=DuckDuckGoSearchAPIWrapper(max_results=5),
            output_format="list",
        )
        wikipedia = WikipediaQueryRun(
            api_wrapper=WikipediaAPIWrapper(top_k_results=3, doc_content_chars_max=5000)
        )
        download_task_file = _make_download_task_file_tool(api_url)

        self.tools = [
            search,
            wikipedia,
            visit_webpage,
            arxiv_search,
            youtube_transcript,
            download_file_from_url,
            download_task_file,
            read_file,
            python_repl,
        ]
        self.graph = build_graph(chat_model.bind_tools(self.tools), self.tools)
        print("BasicAgent initialized.")

    def __call__(self, question: str, task_id: Optional[str] = None) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        user_prompt = f"task_id: {task_id}\n\nQuestion: {question}" if task_id else question
        try:
            result = self.graph.invoke(
                {"messages": [HumanMessage(content=user_prompt)]},
                config={"recursion_limit": AGENT_RECURSION_LIMIT},
            )
        except Exception as exc:
            print(f"Agent error: {exc}")
            return f"AGENT ERROR: {exc}"

        content = result["messages"][-1].content
        if isinstance(content, list):
            content = "\n".join(
                item.get("text", "") if isinstance(item, dict) else str(item)
                for item in content
            )
        answer = extract_final_answer(str(content))
        print(f"Agent returning answer: {answer}")
        return answer


def extract_final_answer(text: str) -> str:
    match = _FINAL_ANSWER_RE.search(text.strip())
    if match:
        return match.group(1).strip().strip("`").rstrip(".").strip()
    lines = [line.strip() for line in text.splitlines() if line.strip()]
    return lines[-1] if lines else text.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(api_url=api_url)
    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 idx, item in enumerate(questions_data, start=1):
        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:
            print(f"Running task {idx}/{len(questions_data)}: {task_id}")
            submitted_answer = agent(question_text, task_id=task_id)
            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.")

    if not _resolve_hf_token():
        print("⚠️  No HUGGINGFACEHUB_API_TOKEN / HF_TOKEN set. The agent will fail to initialise until you provide one.")

    print("-"*(60 + len(" App Starting ")) + "\n")

    print("Launching Gradio Interface for Basic Agent Evaluation...")
    demo.launch(debug=True, share=False)
import os
import gradio as gr
import requests
import inspect
import pandas as pd

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

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
    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 = 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)