tools/exec_code.py

"""파이썬 코드 실행 도구.

GAIA에 "attached Python code"의 출력을 묻는 질문(예: f918266a)이 등장.
첨부 파일은 텍스트로 받지만 출력을 알려면 실제 실행이 필요. smolagents의 자체
코드 sandbox로 처리할 수도 있지만 명시 도구로 분리하면 (a) LLM이 의도를 명확히
표현 (b) stdout 캡처를 단순화한다.

안전: 첨부된 코드를 직접 실행하므로 신뢰되지 않은 입력에 노출. GAIA 채점
컨텍스트 한정으로 사용. 실서비스에는 sandbox 강화 필요.
"""
import os
import subprocess
import sys
import tempfile
from smolagents import tool


@tool
def exec_python_code(code: str) -> str:
    """Execute Python source code and return its captured stdout.
    Use this when the question asks for the output of a piece of attached or referenced
    Python code (e.g., "What is the final numeric output of the code?"). Pass the code
    body verbatim. Captures both stdout and stderr; returns up to ~12k characters.

    Args:
        code: The Python source code to execute.
    """
    if len(code) > 50000:
        return "exec_python_code error: code is too large to execute safely"

    try:
        with tempfile.TemporaryDirectory(prefix="gaia_exec_") as tmpdir:
            script_path = os.path.join(tmpdir, "snippet.py")
            with open(script_path, "w", encoding="utf-8") as f:
                f.write(code)
            result = subprocess.run(
                [sys.executable, "-I", script_path],
                cwd=tmpdir,
                capture_output=True,
                text=True,
                timeout=8,
            )
        out = (result.stdout or "") + (result.stderr or "")
        if result.returncode != 0:
            out = f"exec_python_code exited with status {result.returncode}\n{out}"
    except subprocess.TimeoutExpired as e:
        partial = ((e.stdout or "") + (e.stderr or ""))[:4000]
        return f"exec_python_code error: TimeoutExpired after 8s\n--- partial output ---\n{partial}"
    except Exception as e:
        return (
            f"exec_python_code error: {type(e).__name__}: {e}\n"
            f"--- partial output ---\n"
        )

    if len(out) > 12000:
        out = out[:12000] + "\n...[truncated]"
    return out or "(no stdout output)"