mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-10-26 21:26:39 +00:00
346ff7b253
* fix(memory): rank capacity eviction per record, not per fact_id select_facts_for_capacity keyed every score by fact_id, so an imported batch that repeats an id collapsed into a single dict entry: the last record's score won, and both the ranking pass and the evicted audit read that one value for every position. A 0.9-confidence record could therefore be evicted while its own 0.1-confidence duplicate survived. The import path keeps caller-supplied ids without checking them for uniqueness, and any over-cap import lands here. Score by position instead: a parallel list next to the indexed facts, so ranking and the audit read each record's own score. The public ``scores`` dict stays keyed by fact_id with last-write-wins semantics, keeping the DeerMem benchmark contract and the callers that never read it unchanged. Red on main: test_confidence_policy_scores_duplicate_fact_ids_per_record fails with the highest-confidence record evicted; green on this branch. * fix(utils): keep share-less UNC roots out of the extended-length prefix extended_length_path prefixed every absolute UNC path with \\?\UNC\, but Win32 only accepts \\?\UNC\server\share\... — a share-less root (\\server, \\server\, or a bare \) is not a valid device path, so every Win32 call handed the prefixed spelling fails. Only prefix when both the server and the share are present; otherwise return the ordinary spelling unchanged. Red on main: the \\server, \\server\, //, and //server cases of test_windows_extended_spelling assert the forged prefix; green on this branch.
77 lines
2.9 KiB
Python
77 lines
2.9 KiB
Python
"""Windows filesystem spelling and document confinement regressions."""
|
|
|
|
import ntpath
|
|
import os
|
|
from pathlib import Path
|
|
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
|
|
from deerflow.config.paths import Paths
|
|
from deerflow.utils import host_paths
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("raw", "expected"),
|
|
[
|
|
(r"C:\shelf\..\documents", r"\\?\C:\documents"),
|
|
("C:/shelf/documents", r"\\?\C:\shelf\documents"),
|
|
(r"\\server\share\shelf", r"\\?\UNC\server\share\shelf"),
|
|
(r"\\server", r"\\server"),
|
|
("\\\\server\\", "\\\\server\\"),
|
|
(r"//", r"\\"),
|
|
(r"//server", r"\\server"),
|
|
(r"\\?\C:\shelf", r"\\?\C:\shelf"),
|
|
(r"\\?\UNC\server\share\shelf", r"\\?\UNC\server\share\shelf"),
|
|
(r"\\.\C:\shelf", r"\\.\C:\shelf"),
|
|
(r"\\.\pipe\deerflow", r"\\.\pipe\deerflow"),
|
|
(r"\\?\C:\shelf\..\documents", r"\\?\C:\shelf\..\documents"),
|
|
],
|
|
)
|
|
def test_windows_extended_spelling(monkeypatch, raw, expected):
|
|
# Patch this module's OS binding, never the process-wide os.name (pathlib
|
|
# and pytest need to keep using the actual host's path implementation).
|
|
monkeypatch.setattr(host_paths, "os", SimpleNamespace(name="nt", path=ntpath))
|
|
assert str(host_paths.extended_length_path(Path(raw))) == expected
|
|
|
|
|
|
def test_posix_path_is_unchanged(monkeypatch):
|
|
monkeypatch.setattr(host_paths, "os", SimpleNamespace(name="posix"))
|
|
path = Path("relative/documents")
|
|
assert host_paths.extended_length_path(path) is path
|
|
|
|
|
|
@pytest.mark.skipif(os.name != "nt", reason="native Windows relative-path normalization")
|
|
def test_windows_relative_path_is_absolutized(monkeypatch, tmp_path):
|
|
monkeypatch.chdir(tmp_path)
|
|
actual = host_paths.extended_length_path(Path("shelf/../documents"))
|
|
assert str(actual) == "\\\\?\\" + str(tmp_path / "documents")
|
|
|
|
|
|
def test_document_traversal_is_still_rejected(tmp_path):
|
|
paths = Paths(base_dir=tmp_path)
|
|
with pytest.raises(ValueError, match="path traversal"):
|
|
paths.project_document_path("alice", "../outside")
|
|
with pytest.raises(ValueError, match="path traversal"):
|
|
paths.project_document_path("alice", str(tmp_path / "outside"))
|
|
|
|
|
|
@pytest.mark.parametrize("outside_root", [False, True])
|
|
def test_document_symlink_confinement(tmp_path, outside_root):
|
|
paths = Paths(base_dir=tmp_path)
|
|
base = paths.user_projects_dir("alice")
|
|
base.mkdir(parents=True)
|
|
target = tmp_path / "outside" if outside_root else base / "target"
|
|
target.mkdir()
|
|
try:
|
|
(base / "link").symlink_to(target, target_is_directory=True)
|
|
except OSError:
|
|
if os.name == "nt":
|
|
pytest.skip("Windows symlink privilege is not available")
|
|
raise
|
|
if outside_root:
|
|
with pytest.raises(ValueError, match="path traversal"):
|
|
paths.project_document_path("alice", "link/content")
|
|
else:
|
|
assert paths.project_document_path("alice", "link/content") == (target / "content").resolve()
|