refactor: retire the images tarball backup
CI and images / lint (push) Successful in 2s
CI and images / extension-version (push) Successful in 2s
CI and images / extension-test (push) Successful in 20s
CI and images / frontend-build (push) Successful in 25s
CI and images / backend-lint-and-test (push) Successful in 50s
CI and images / integration (push) Successful in 2m38s
CI and images / build-agent (push) Successful in 5s
CI and images / sign-extension (push) Successful in 8s
CI and images / build-web (push) Successful in 4m10s
CI and images / smoke-web (push) Successful in 1m3s
CI and images / promote (push) Successful in 1s
CI and images / refresh-dev (push) Skipped
CI and images / unattended-failure (push) Skipped

Images and attachments are backed up off-site, one object per file, so the
tar+zstd of /images goes: its service and restore, both tasks, the trigger and
restore routes, the Keep last setting, the screen's Images section, and the
tests. Migration 0122 drops backup_run.tar_path and
import_settings.backup_images_keep_last_n and deletes any images runs.

The local database dump stays for an install with no off-site destination,
and the Backups card now says plainly that images and attachments are backed
up only off-site.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-11-07 22:07:44 -05:00
co-authored by Claude Opus 5.5
parent 794b04a64e
commit 14936b62dc
14 changed files with 92 additions and 393 deletions
+3 -103
View File
@@ -125,55 +125,6 @@ def backup_db_task(self, *, tag: str | None = None,
return {"backup_run_id": run_id}
@celery.task(
name="backend.app.tasks.backup.backup_images_task",
bind=True,
autoretry_for=(OperationalError, DBAPIError),
retry_backoff=30, retry_backoff_max=300, max_retries=1,
soft_time_limit=21600, time_limit=23400,
)
def backup_images_task(self, *, tag: str | None = None,
triggered_by: str = "manual") -> dict:
"""Create one images backup. Same shape as backup_db_task; uses
tar_path instead of sql_path."""
SessionLocal = _sync_session_factory()
now = datetime.now(UTC)
with SessionLocal() as session:
row = BackupRun(
kind="images", status="running", tag=tag,
triggered_by=triggered_by, started_at=now, manifest={},
)
session.add(row)
session.commit()
session.refresh(row)
run_id = row.id
try:
result = backup_service.backup_images(
images_root=IMAGES_ROOT,
tag=tag, triggered_by=triggered_by,
)
except (SoftTimeLimitExceeded, Exception) as exc:
with SessionLocal() as session:
row = session.get(BackupRun, run_id)
if row is not None:
_mark_failed(session, row, exc)
raise
with SessionLocal() as session:
row = session.get(BackupRun, run_id)
row.status = "ok"
row.finished_at = datetime.now(UTC)
row.tar_path = result["tar_path"]
row.size_bytes = result["size_bytes"]
row.manifest = {
"manifest_path": result["manifest_path"],
"ts": result["ts"],
}
session.commit()
return {"backup_run_id": run_id}
@celery.task(
name="backend.app.tasks.backup.restore_db_task",
bind=True,
@@ -225,52 +176,6 @@ def restore_db_task(self, *, source_backup_run_id: int) -> dict:
return {"backup_run_id": marker_id}
@celery.task(
name="backend.app.tasks.backup.restore_images_task",
bind=True, max_retries=0,
soft_time_limit=21600, time_limit=23400,
)
def restore_images_task(self, *, source_backup_run_id: int) -> dict:
"""Mirrors restore_db_task; uses backup_service.restore_images."""
SessionLocal = _sync_session_factory()
now = datetime.now(UTC)
with SessionLocal() as session:
src = session.get(BackupRun, source_backup_run_id)
if src is None or src.kind != "images" or not src.tar_path:
raise ValueError(
f"BackupRun id={source_backup_run_id} is not a valid images backup"
)
marker = BackupRun(
kind="images", status="restoring",
triggered_by="restore", started_at=now,
restored_from_id=src.id,
manifest={"source_tar_path": src.tar_path},
)
session.add(marker)
session.commit()
session.refresh(marker)
marker_id = marker.id
tar_path = src.tar_path
try:
backup_service.restore_images(
images_root=IMAGES_ROOT, tar_path=Path(tar_path),
)
except (SoftTimeLimitExceeded, Exception) as exc:
with SessionLocal() as session:
row = session.get(BackupRun, marker_id)
if row is not None:
_mark_failed(session, row, exc)
raise
with SessionLocal() as session:
row = session.get(BackupRun, marker_id)
row.status = "restored"
row.finished_at = datetime.now(UTC)
session.commit()
return {"backup_run_id": marker_id}
@celery.task(
name="backend.app.tasks.backup.prune_backups",
soft_time_limit=300, time_limit=600,
@@ -278,27 +183,23 @@ def restore_images_task(self, *, source_backup_run_id: int) -> dict:
def prune_backups() -> dict:
"""Daily Beat. Per-kind retention from ImportSettings.
Returns {"db_deleted": N, "images_deleted": M, "media_deleted": L,
"restore_deleted": R, "reconcile_deleted": C, "test_deleted": T,
Returns {"db_deleted": N, "media_deleted": L, "restore_deleted": R, "reconcile_deleted": C, "test_deleted": T,
"files_unlinked": K}. Media, restore, reconcile and test runs leave no
files here; only their history is trimmed, to the latest MEDIA_RUNS_KEPT,
RESTORE_RUNS_KEPT, RECONCILE_RUNS_KEPT and TEST_RUNS_KEPT.
Tagged rows (tag IS NOT NULL) are never pruned.
Status='running' / 'restoring' rows are never pruned — the
recover_stalled_backup_runs sweep flips truly-stuck ones to
'error' first. (Earlier docstring claimed the FC-3i TaskRun sweep
handled those, but TaskRun cleanup never touched BackupRun rows.
Audit 2026-06-02 added the dedicated sweep.)
'error' first.
"""
SessionLocal = _sync_session_factory()
counts = {"db_deleted": 0, "images_deleted": 0, "media_deleted": 0,
counts = {"db_deleted": 0, "media_deleted": 0,
"restore_deleted": 0, "reconcile_deleted": 0, "test_deleted": 0,
"files_unlinked": 0}
with SessionLocal() as session:
s = ImportSettings.load_sync(session)
for kind, keep in (
("db", s.backup_db_keep_last_n),
("images", s.backup_images_keep_last_n),
("media", MEDIA_RUNS_KEPT),
("restore", RESTORE_RUNS_KEPT),
("reconcile", RECONCILE_RUNS_KEPT),
@@ -315,7 +216,6 @@ def prune_backups() -> dict:
for row in candidates:
result = backup_service.unlink_artifact_files(
sql_path=row.sql_path,
tar_path=row.tar_path,
manifest_path=(row.manifest or {}).get("manifest_path"),
)
counts["files_unlinked"] += sum(