feat(cleanup): reclaim orphaned attachments — rows and store blobs (#3068)
CI / lint (push) Successful in 2s
CI / extension-version (push) Successful in 3s
CI / frontend-build (push) Successful in 24s
CI / backend-lint-and-test (push) Successful in 28s
CI / integration (push) Successful in 3m47s

PostAttachment's two FKs are both ON DELETE SET NULL, so a deleted post or
artist left the row behind rather than taking it. Nothing ever pruned those
rows, and nothing in the repo had ever unlinked a file under the attachment
store — so both rows and bytes accumulated permanently, invisible to every
existing diagnostic.

Why a disk->DB reconciliation rather than a row sweep: the store is
sha-addressed and idempotent, so ONE blob backs MANY rows. Deleting a row
does not free its blob, and since the artist cascade (#3066) now deletes
its attachment rows outright, a freed blob has no DB pointer left to find
it by. Walking the store and asking "does any row still reference this
sha?" catches orphans from every cause, including ones no future delete
path will think to report.

Preview and apply share `_orphan_attachment_conditions` (rule 93). The
dry-run derives its surviving-sha set by NEGATING that same predicate, so
it is honest about blobs the delete would free rather than counting them as
still-referenced — the one place this was easy to get backwards, so it has
its own parity test.

Guards, each with a reason:
- A blob is written before its row commits, so a just-stored file legitimately
  has no referencing row. Files under 6h are never judged — same guard and
  reasoning as ORPHAN_TEMP_MIN_AGE_HOURS.
- `.partial` staging files belong to cleanup_orphaned_temp_files; skipped
  rather than raced.
- The sha is parsed as the first 64 chars, not via Path.stem: store() takes
  the extension from the source filename, and a URL-encoded basename yields a
  multi-dot suffix that would make stem eat part of the sha.
- A 900s walk budget reports partial=True instead of running to the task's
  hard limit (rule 89).
- TASK_STUCK_THRESHOLD_MINUTES override at 30 (= time_limit 25 + 5). Without
  it a healthy 20-minute walk is phantom-flagged 'RecoverySweep' at the bare
  5-min default — the #883 failure class; its invariant test is mirrored here.

Defaults to the safe preview at both the task and the route, unlike the other
maintenance triggers: this apply unlinks files. Operator-triggered only,
never on a beat.

Ships with its UI (rule 27): AttachmentReclaimCard in Cleanup → Duplicates &
leftovers, built on the existing useMaintenanceTask/MaintenanceTile shapes, so
a run survives navigating away. Surfaces files_failed and partial explicitly,
since both change what the numbers mean.

Also promotes humanBytes to utils/bytes.js — it was byte-identical in
VideoDedupCard and GatedPurgeCard and this card would have been the third
copy. The three divergent `formatBytes` helpers are deliberately left alone.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-08-26 22:37:24 -04:00
co-authored by Claude Opus 5
parent 2ce467e347
commit 2e0f8f8c61
12 changed files with 572 additions and 18 deletions
+31
View File
@@ -677,3 +677,34 @@ async def test_reset_content_tagging_apply_requires_confirm_token(client, db):
)
assert resp.status_code == 200
assert (await resp.get_json())["deleted"] == 1
@pytest.mark.asyncio
async def test_trigger_reclaim_attachments_defaults_to_preview(client, monkeypatch):
"""Unlike the other maintenance triggers, this one's apply unlinks FILES —
so an empty body must mean preview, not apply."""
from backend.app.tasks import admin as admin_tasks
calls = []
monkeypatch.setattr(
admin_tasks.reclaim_orphaned_attachments_task, "delay", _fake_delay(calls)
)
resp = await client.post("/api/admin/maintenance/reclaim-attachments", json={})
assert resp.status_code == 202
assert (await resp.get_json())["task_id"] == "task-xyz"
assert calls[0][1] == {"dry_run": True}
@pytest.mark.asyncio
async def test_trigger_reclaim_attachments_threads_apply(client, monkeypatch):
from backend.app.tasks import admin as admin_tasks
calls = []
monkeypatch.setattr(
admin_tasks.reclaim_orphaned_attachments_task, "delay", _fake_delay(calls)
)
resp = await client.post(
"/api/admin/maintenance/reclaim-attachments", json={"dry_run": False},
)
assert resp.status_code == 202
assert calls[0][1] == {"dry_run": False}
+174
View File
@@ -5,6 +5,7 @@ side effects use tmp_path. Assertions on mutated rows use COLUMN
SELECTS per reference_async_coredml_test_assertions — never
re-read ORM attributes after a service mutates and re-fetches.
"""
import os
from datetime import UTC, datetime
import pytest
@@ -1081,3 +1082,176 @@ def test_reconcile_preserves_from_attachment_on_provenance_collision(db_sync, tm
.where(ImageProvenance.image_record_id == img_id)
).all()
assert rows == [(native_id, att_id)]
# --- reclaim_orphaned_attachments -----------------------------------
def _store_blob(root, sha, *, ext=".pdf", age_hours=48, data=b"blob"):
"""Write a file into the sha-addressed attachment store, aged past the
min-age guard by default."""
d = root / "attachments" / sha[:3]
d.mkdir(parents=True, exist_ok=True)
p = d / f"{sha}{ext}"
p.write_bytes(data)
old = datetime.now(UTC).timestamp() - age_hours * 3600
os.utime(p, (old, old))
return p
def _attachment(db_sync, *, sha, post=None, artist=None):
att = PostAttachment(
post_id=post.id if post else None,
artist_id=artist.id if artist else None,
sha256=sha, path=f"/store/{sha[:3]}/f.pdf",
original_filename="f.pdf", ext=".pdf", size_bytes=4,
)
db_sync.add(att)
db_sync.flush()
return att
def test_reclaim_attachments_dry_run_projects_without_mutating(db_sync, tmp_path):
a = _make_artist(db_sync, slug="recl-dry")
p = Post(artist_id=a.id, external_post_id="rd-1")
db_sync.add(p)
db_sync.flush()
kept_sha, orphan_sha = "aa11".ljust(64, "0"), "bb22".ljust(64, "0")
_attachment(db_sync, sha=kept_sha, post=p, artist=a)
_attachment(db_sync, sha=orphan_sha) # both FKs NULL → orphan
db_sync.commit()
kept_blob = _store_blob(tmp_path, kept_sha)
orphan_blob = _store_blob(tmp_path, orphan_sha)
result = cleanup_service.reclaim_orphaned_attachments(
db_sync, images_root=tmp_path, dry_run=True,
)
assert result["rows"] == 1
assert result["files"] == 1
assert result["bytes"] == orphan_blob.stat().st_size
# Nothing actually happened.
assert kept_blob.exists() and orphan_blob.exists()
assert db_sync.execute(
select(func.count(PostAttachment.id))
).scalar_one() == 2
def test_reclaim_attachments_apply_deletes_rows_and_unlinks_blobs(db_sync, tmp_path):
a = _make_artist(db_sync, slug="recl-apply")
p = Post(artist_id=a.id, external_post_id="ra-1")
db_sync.add(p)
db_sync.flush()
kept_sha, orphan_sha = "cc33".ljust(64, "0"), "dd44".ljust(64, "0")
_attachment(db_sync, sha=kept_sha, post=p, artist=a)
_attachment(db_sync, sha=orphan_sha)
db_sync.commit()
kept_blob = _store_blob(tmp_path, kept_sha)
orphan_blob = _store_blob(tmp_path, orphan_sha)
result = cleanup_service.reclaim_orphaned_attachments(
db_sync, images_root=tmp_path, dry_run=False,
)
assert result["rows"] == 1
assert result["files"] == 1
assert kept_blob.exists() # still referenced
assert not orphan_blob.exists() # nothing points at it any more
surviving = db_sync.execute(select(PostAttachment.sha256)).scalars().all()
assert surviving == [kept_sha]
def test_reclaim_attachments_preview_matches_apply(db_sync, tmp_path):
"""Rule 93 — the dry-run's numbers are what the apply does. The projection
has to negate the orphan predicate to be honest about blobs the delete is
about to free, so this is the assertion that catches getting that backwards.
"""
orphan_sha = "ee55".ljust(64, "0")
_attachment(db_sync, sha=orphan_sha)
db_sync.commit()
_store_blob(tmp_path, orphan_sha)
projected = cleanup_service.reclaim_orphaned_attachments(
db_sync, images_root=tmp_path, dry_run=True,
)
applied = cleanup_service.reclaim_orphaned_attachments(
db_sync, images_root=tmp_path, dry_run=False,
)
for key in ("rows", "files", "bytes"):
assert projected[key] == applied[key], key
assert applied["rows"] == 1 and applied["files"] == 1
def test_reclaim_attachments_keeps_shared_blob_while_any_row_remains(db_sync, tmp_path):
"""The refcount case this whole sweep exists for: one sha-addressed blob
backs several rows, so deleting SOME of them must not free the file."""
a = _make_artist(db_sync, slug="recl-shared")
p = Post(artist_id=a.id, external_post_id="rs-1")
db_sync.add(p)
db_sync.flush()
sha = "ff66".ljust(64, "0")
_attachment(db_sync, sha=sha, post=p, artist=a) # attributed — survives
_attachment(db_sync, sha=sha) # orphan — deleted
db_sync.commit()
blob = _store_blob(tmp_path, sha)
result = cleanup_service.reclaim_orphaned_attachments(
db_sync, images_root=tmp_path, dry_run=False,
)
assert result["rows"] == 1 # the orphan row went
assert result["files"] == 0 # the blob did NOT
assert blob.exists()
def test_reclaim_attachments_spares_filesystem_import_rows(db_sync, tmp_path):
"""post_id NULL with an artist_id is the deliberate filesystem-import shape
(importer._capture_attachment), not an orphan — it is still attributed."""
a = _make_artist(db_sync, slug="recl-fsimport")
sha = "1177".ljust(64, "0")
_attachment(db_sync, sha=sha, artist=a) # post NULL, artist set
db_sync.commit()
blob = _store_blob(tmp_path, sha)
result = cleanup_service.reclaim_orphaned_attachments(
db_sync, images_root=tmp_path, dry_run=False,
)
assert result["rows"] == 0
assert result["files"] == 0
assert blob.exists()
assert db_sync.execute(
select(func.count(PostAttachment.id))
).scalar_one() == 1
def test_reclaim_attachments_skips_recent_and_staging_files(db_sync, tmp_path):
"""A blob is written BEFORE its row commits, so a just-stored file with no
row is in-flight, not orphaned. `.partial` staging files belong to
cleanup_orphaned_temp_files and must be left alone either way."""
fresh_sha, staged_sha = "2288".ljust(64, "0"), "3399".ljust(64, "0")
fresh = _store_blob(tmp_path, fresh_sha, age_hours=0)
staged = _store_blob(tmp_path, staged_sha, ext=".pdf.partial")
db_sync.commit()
result = cleanup_service.reclaim_orphaned_attachments(
db_sync, images_root=tmp_path, dry_run=False,
)
assert result["files"] == 0
assert result["skipped_recent"] == 1
assert fresh.exists() and staged.exists()
def test_reclaim_attachments_ignores_non_sha_named_files(db_sync, tmp_path):
"""The walk must only judge files it can identify as store blobs — anything
else under the root is none of its business."""
d = tmp_path / "attachments" / "zzz"
d.mkdir(parents=True)
stray = d / "notes.txt"
stray.write_text("not a blob")
old = datetime.now(UTC).timestamp() - 48 * 3600
os.utime(stray, (old, old))
result = cleanup_service.reclaim_orphaned_attachments(
db_sync, images_root=tmp_path, dry_run=False,
)
assert result["files"] == 0
assert stray.exists()
+14
View File
@@ -778,3 +778,17 @@ def test_vacuum_analyze_runs_over_high_churn_tables():
result = vacuum_analyze.apply().get()
assert result["vacuumed"] == list(VACUUM_TABLES)
def test_reclaim_attachments_stuck_threshold_exceeds_hard_time_limit():
"""#883's invariant, applied to the attachment reclaim: a task whose stall
threshold is under its own hard limit gets phantom-flagged 'RecoverySweep'
while it is still healthily running."""
from backend.app.tasks.admin import reclaim_orphaned_attachments_task
from backend.app.tasks.maintenance import TASK_STUCK_THRESHOLD_MINUTES
hard_minutes = reclaim_orphaned_attachments_task.time_limit / 60
override = TASK_STUCK_THRESHOLD_MINUTES[
"backend.app.tasks.admin.reclaim_orphaned_attachments_task"
]
assert override >= hard_minutes