349f2fd9fe
* feat: add claude support * feat: add script for end-to-end evaluation with logging and task distribution * feat&fix: add tool result handling and update model default in evaluation script * chore: remove run_test_env.py script * feat&fix: implement action parsing for tool calls and update default action space * fix: update text formatting in action parsing and replace logger import * feat&fix: implement action parsing for tool calls and add screen size handling * feat: add setup instructions for Anthropic API integration * feat: add notice about image size limitations for Anthropic API * Delete test_env/logger.py * Delete test_env/utils.py
42 lines
1.6 KiB
Python
42 lines
1.6 KiB
Python
"""Utility to run shell commands asynchronously with a timeout."""
|
|
|
|
import asyncio
|
|
from typing import Optional
|
|
TRUNCATED_MESSAGE: str = "<response clipped><NOTE>To save on context only part of this file has been shown to you. You should retry this tool after you have searched inside the file with `grep -n` in order to find the line numbers of what you are looking for.</NOTE>"
|
|
MAX_RESPONSE_LEN: int = 16000
|
|
|
|
|
|
def maybe_truncate(content: str, truncate_after: Optional[int] = MAX_RESPONSE_LEN):
|
|
"""Truncate content and append a notice if content exceeds the specified length."""
|
|
return (
|
|
content
|
|
if not truncate_after or len(content) <= truncate_after
|
|
else content[:truncate_after] + TRUNCATED_MESSAGE
|
|
)
|
|
|
|
|
|
async def run(
|
|
cmd: str,
|
|
timeout: Optional[float] = 120.0, # seconds
|
|
truncate_after: Optional[int] = MAX_RESPONSE_LEN,
|
|
):
|
|
"""Run a shell command asynchronously with a timeout."""
|
|
process = await asyncio.create_subprocess_shell(
|
|
cmd, stdout=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.PIPE
|
|
)
|
|
|
|
try:
|
|
stdout, stderr = await asyncio.wait_for(process.communicate(), timeout=timeout)
|
|
return (
|
|
process.returncode or 0,
|
|
maybe_truncate(stdout.decode(), truncate_after=truncate_after),
|
|
maybe_truncate(stderr.decode(), truncate_after=truncate_after),
|
|
)
|
|
except asyncio.TimeoutError as exc:
|
|
try:
|
|
process.kill()
|
|
except ProcessLookupError:
|
|
pass
|
|
raise TimeoutError(
|
|
f"Command '{cmd}' timed out after {timeout} seconds"
|
|
) from exc |