feat(audit): daily filename + 7-day retention sweep

Replaces the per-session ``datatools-<ts>-<sid>.jsonl`` filename
with a single daily file ``datatools-YYYY-MM-DD.jsonl`` (local
date). Sessions on the same calendar day share a file via the
writer thread's per-batch open+append; multiple DataTools
instances running concurrently on the same day fan into the same
file (append-mode small writes are atomic on POSIX, safe-enough on
Windows under realistic load).

Drops the ``_LOG_PATH`` module global and the lock around it —
``audit_log_path()`` is now pure date math, recomputed on every
call so a session that crosses midnight follows the rollover into
the next day's file.

Adds ``_sweep_old_logs()`` invoked once per process at writer-
thread start. Deletes any ``datatools-*.jsonl`` whose mtime is
older than 7 days. The glob deliberately matches the legacy
per-session filename too, so users upgrading from the previous
build don't keep a permanent backlog of pre-retention files.

Event ``ts`` fields stay UTC; only the filename uses local date,
because users go looking for "today's log" on their wall clock.

Tests cover: daily filename shape, sweep removes stale files,
sweep keeps fresh files, sweep also clears legacy filenames.

Rollback: ``git revert HEAD`` restores the per-session filename
and removes the sweep. No data migration needed either way —
existing files keep working as JSONL.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-19 21:22:47 +00:00
parent ba07dcb6c7
commit b3ae913bb9
2 changed files with 105 additions and 23 deletions

View File

@@ -174,6 +174,63 @@ class TestKillSwitchContract:
audit.reset_for_tests()
class TestDailyFileRetention:
"""Daily filename + 7-day retention sweep on writer-thread start."""
def test_filename_is_daily_local_date(self, isolated_audit, tmp_path):
from datetime import datetime
audit = isolated_audit
audit.log_event("test", "today")
audit.flush_audit_log(timeout_s=2.0)
today = datetime.now().strftime("%Y-%m-%d")
expected = tmp_path / f"datatools-{today}.jsonl"
assert expected.exists(), (
f"expected daily file {expected.name}, got "
f"{[p.name for p in tmp_path.iterdir()]}"
)
def test_sweep_deletes_files_older_than_retention(
self, isolated_audit, tmp_path,
):
"""Files with mtime > _RETENTION_DAYS old get pruned when the
writer thread starts. Files within the window survive."""
import os
audit = isolated_audit
stale = tmp_path / "datatools-2025-01-01.jsonl"
stale.write_text('{"ts": "stale"}\n', encoding="utf-8")
old_mtime = time.time() - (audit._RETENTION_DAYS + 1) * 86400
os.utime(stale, (old_mtime, old_mtime))
fresh = tmp_path / "datatools-2026-05-18.jsonl"
fresh.write_text('{"ts": "fresh"}\n', encoding="utf-8")
recent_mtime = time.time() - 1 * 86400
os.utime(fresh, (recent_mtime, recent_mtime))
audit.log_event("test", "kick the writer")
audit.flush_audit_log(timeout_s=2.0)
assert not stale.exists(), "Stale log should have been swept."
assert fresh.exists(), "Fresh log must not be swept."
def test_sweep_also_clears_legacy_per_session_files(
self, isolated_audit, tmp_path,
):
"""Old ``datatools-<ts>-<sid>.jsonl`` filenames must also match
the sweep glob, so upgrading users don't keep a permanent
backlog from before the retention switch."""
import os
audit = isolated_audit
legacy = tmp_path / "datatools-20250101T120000Z-abc12345.jsonl"
legacy.write_text('{"ts": "legacy"}\n', encoding="utf-8")
old_mtime = time.time() - (audit._RETENTION_DAYS + 1) * 86400
os.utime(legacy, (old_mtime, old_mtime))
audit.log_event("test", "kick the writer")
audit.flush_audit_log(timeout_s=2.0)
assert not legacy.exists(), "Legacy per-session file not swept."
class TestSerializationSafety:
def test_non_json_extras_get_str_coerced(self, isolated_audit, tmp_path):
audit = isolated_audit