mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-09-24 21:46:17 +00:00
3e536944b7
* fix(sandbox): stop remote grep/glob from reporting failures as no matches E2B, OpenSandbox, BoxLite and Tenki ran grep/find behind `2>/dev/null | head`, so a missing search root, a missing grep/find binary or an unreadable tree exited 0 with empty stdout and the tools reported "No matches found". Wrap the search in sandbox/remote_search.py, which checks the root first and records the search's own status after head, as remote_list_dir does for list_dir: a missing root raises FileNotFoundError, a failed search raises OSError, and a genuine no-match still returns []. glob's find gains -H for symlinked roots, OpenSandbox's BusyBox fallback keeps the primary grep status, and E2B no longer swallows client errors. Regression tests run each provider's real command in a local POSIX sh. Fixes #5376 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(sandbox): fail remote grep/glob on partial traversal errors grep 2 / find 1 after some results were printed (an unreadable file or subdirectory) were returned as a complete search. Callers have no partial-result channel, and #5376 asks for permission and command failures to raise, so these statuses now raise OSError like any other failure. Only grep 0/1/141 and find 0/141 pass. The error for grep 2 / find 1 says that some files or directories could not be read and asks for a narrower path, so the agent can retry instead of giving up. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> --------- Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com> Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
80 lines
3.6 KiB
Python
80 lines
3.6 KiB
Python
"""Remote ``grep`` / ``glob`` command wrapper and stdout contract.
|
|
|
|
Remote providers search with ``grep ... | head`` or ``find ... | head`` under
|
|
``sh -lc``. POSIX ``sh`` has no ``pipefail`` and the search's stderr is
|
|
discarded, so the pipeline status is ``head``'s: a missing search root, a
|
|
missing ``grep``/``find`` binary (127) or an unreadable tree all printed
|
|
nothing and exited 0, exactly like a genuine "no matches" (#5376).
|
|
|
|
:func:`remote_search_command` checks the root first and records the search
|
|
command's own status after the bounded output, the same technique as
|
|
:mod:`deerflow.sandbox.remote_list_dir`. The script always exits 0 so SDKs that
|
|
raise on a non-zero exit still return the marker; the marker alone decides.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import shlex
|
|
from typing import Literal
|
|
|
|
SearchTool = Literal["grep", "find"]
|
|
|
|
_STATUS_PREFIX = "__DF_SEARCH_STATUS__:"
|
|
_MISSING_ROOT = "missing"
|
|
# head closing the pipe after the limit kills the search with SIGPIPE: a
|
|
# successful truncation, not an error.
|
|
_SIGPIPE = 141
|
|
# Statuses of a complete search. grep: 0 = matches, 1 = no match. Everything
|
|
# else fails, even after printed results.
|
|
_OK_STATUSES: dict[str, tuple[int, ...]] = {"grep": (0, 1, _SIGPIPE), "find": (0, _SIGPIPE)}
|
|
# grep 2 / find 1 usually mean an unreadable file or subdirectory. Printed
|
|
# results are then incomplete and callers have no partial-result channel, so
|
|
# the error tells the agent to narrow the search instead.
|
|
_READ_ERROR_STATUS: dict[str, int] = {"grep": 2, "find": 1}
|
|
|
|
|
|
def remote_search_command(search: str, root: str, *, limit: int) -> str:
|
|
"""Wrap a ``grep``/``find`` command so its outcome survives ``| head``.
|
|
|
|
``search`` must write only results to stdout; callers keep ``2>/dev/null``.
|
|
"""
|
|
quoted = shlex.quote(root)
|
|
n = int(limit)
|
|
return (
|
|
f"set +e; if [ ! -e {quoted} ]; then printf '%s\\n' {_STATUS_PREFIX}{_MISSING_ROOT}; exit 0; fi; "
|
|
f'_st=/tmp/df_search_$$; {{ {search}; echo $? > "$_st"; }} | head -n {n}; '
|
|
f'st=$(cat "$_st" 2>/dev/null); rm -f "$_st"; '
|
|
f"printf '\\n%s\\n' {_STATUS_PREFIX}\"$st\"; exit 0"
|
|
)
|
|
|
|
|
|
def parse_remote_search_output(stdout: str | None, root: str, *, tool: SearchTool) -> str:
|
|
"""Return the search output without the status marker.
|
|
|
|
Raises:
|
|
FileNotFoundError: The search root does not exist.
|
|
OSError: The search did not complete (missing binary, unreadable
|
|
root or subtree, invalid invocation) or its status was lost.
|
|
"""
|
|
# Split on "\n" only: splitlines() would also split on characters that are
|
|
# legal in Linux filenames. Callers keep their own per-line handling.
|
|
lines = (stdout or "").split("\n")
|
|
if lines and lines[-1] == "":
|
|
lines.pop()
|
|
if not lines or not lines[-1].startswith(_STATUS_PREFIX):
|
|
raise OSError(f"Failed to {tool} under {root}: search status marker missing")
|
|
raw = lines.pop()[len(_STATUS_PREFIX) :]
|
|
if raw == _MISSING_ROOT:
|
|
raise FileNotFoundError(root)
|
|
if lines and lines[-1] == "":
|
|
lines.pop()
|
|
try:
|
|
status = int(raw)
|
|
except ValueError:
|
|
raise OSError(f"Failed to {tool} under {root}: search status unavailable") from None
|
|
if status in _OK_STATUSES[tool]:
|
|
return "\n".join(lines)
|
|
if status == _READ_ERROR_STATUS[tool]:
|
|
raise OSError(f"Failed to {tool} under {root}: {tool} exited with code {status}, usually because some files or directories could not be read; results would be incomplete, so search a narrower path")
|
|
raise OSError(f"Failed to {tool} under {root}: command exited with code {status}")
|