4157494d2f
The canonical writer defaults to ensure_ascii=False, but ~10 of the sites repointed onto it (terminal breadcrumbs, shell-hook allowlist, active sessions, debug pending, model-catalog cache, the credential writers) previously used json's ensure_ascii=True default. A surrogate-escaped str (os.fsdecode of a non-UTF-8 cwd/argv) that json used to persist as \udcff now made the utf-8 text handle raise UnicodeEncodeError - a ValueError that the callers' `except OSError` never catches, so breadcrumbs silently stopped writing and the other sites leaked a new error type. Fix at the canonical: serialize to a str first (so nothing lands in the temp file on failure), and on UnicodeEncodeError retry the dump with ensure_ascii=True. That escape round-trips - json.loads returns the same str with the lone surrogate - whereas encoding with surrogateescape emits a raw 0xFF byte the reader's utf-8 decode rejects. The happy path is unchanged: normal content keeps its raw UTF-8 bytes on disk.
86 lines
2.6 KiB
Python
86 lines
2.6 KiB
Python
"""Tests for utils.atomic_json_write — crash-safe JSON file writes."""
|
|
|
|
import json
|
|
import os
|
|
from pathlib import Path
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
from utils import atomic_json_write
|
|
|
|
|
|
class TestAtomicJsonWrite:
|
|
"""Core atomic write behavior."""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_cleans_up_temp_file_on_baseexception(self, tmp_path):
|
|
class SimulatedAbort(BaseException):
|
|
pass
|
|
|
|
target = tmp_path / "data.json"
|
|
original = {"preserved": True}
|
|
target.write_text(json.dumps(original), encoding="utf-8")
|
|
|
|
with patch("utils.json.dumps", side_effect=SimulatedAbort):
|
|
with pytest.raises(SimulatedAbort):
|
|
atomic_json_write(target, {"new": True})
|
|
|
|
tmp_files = [f for f in tmp_path.iterdir() if ".tmp" in f.name]
|
|
assert len(tmp_files) == 0
|
|
assert json.loads(target.read_text(encoding="utf-8")) == original
|
|
|
|
|
|
|
|
|
|
def test_mode_does_not_crash_without_fchmod(self, tmp_path):
|
|
"""Regression: os.fchmod is Unix-only and absent on Windows. Passing a
|
|
mode must not raise AttributeError when fchmod is unavailable.
|
|
|
|
Simulates the Windows os module by removing fchmod from the namespace.
|
|
Previously this crashed in `hermes memory setup` while saving the
|
|
Hindsight config with mode=0o600 (GitHub: Windows setup traceback).
|
|
"""
|
|
import utils
|
|
|
|
target = tmp_path / "secret.json"
|
|
no_fchmod = {k: getattr(os, k) for k in dir(os) if k != "fchmod"}
|
|
fake_os = type("FakeOs", (), no_fchmod)
|
|
assert not hasattr(fake_os, "fchmod")
|
|
|
|
with patch.object(utils, "os", fake_os):
|
|
atomic_json_write(target, {"api_key": "secret"}, mode=0o600)
|
|
|
|
assert json.loads(target.read_text(encoding="utf-8")) == {"api_key": "secret"}
|
|
|
|
|
|
def test_concurrent_writes_dont_corrupt(self, tmp_path):
|
|
"""Multiple rapid writes should each produce valid JSON."""
|
|
import threading
|
|
|
|
target = tmp_path / "concurrent.json"
|
|
errors = []
|
|
|
|
def writer(n):
|
|
try:
|
|
atomic_json_write(target, {"writer": n, "data": list(range(100))})
|
|
except Exception as e:
|
|
errors.append(e)
|
|
|
|
threads = [threading.Thread(target=writer, args=(i,)) for i in range(10)]
|
|
for t in threads:
|
|
t.start()
|
|
for t in threads:
|
|
t.join()
|
|
|
|
assert not errors
|
|
# File should contain valid JSON from one of the writers
|
|
result = json.loads(target.read_text())
|
|
assert "writer" in result
|
|
assert len(result["data"]) == 100
|