feat(tags): 'Reset content tagging' admin action
CI / lint (push) Successful in 3s
CI / backend-lint-and-test (push) Successful in 11s
CI / frontend-build (push) Successful in 30s
CI / integration (push) Successful in 2m57s

Wipe every general + character tag so the operator can re-tag from scratch via
the Camie auto-suggest, while PRESERVING fandoms, series (+ series_page order),
and each image's stored tagger_predictions (so suggestions repopulate
immediately). One set-based DELETE FROM tag WHERE kind IN ('general','character')
— the five tag-referencing tables all cascade, so applications + aliases +
allowlist + rejections + centroids clear automatically; series tags aren't
deleted so series survive; Tag.fandom_id is SET NULL so fandoms are untouched.

Reuses the established dry-run-preview -> confirm pattern: cleanup_service.
reset_content_tagging() + POST /api/admin/tags/reset-content +
TagMaintenanceCard section with a backup-first warning and a red confirm
showing exact counts (tags by kind + image applications). Irreversible except
via DB backup restore; the wipe only fires when the operator confirms.

Tests: service dry-run counts + live delete preserves fandom/series/series_page
while content tags + their image_tag cascade away; API dry-run wiring.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-04 16:47:36 -04:00
parent 26e47a86cb
commit 91b0145bc8
6 changed files with 245 additions and 0 deletions
+60
View File
@@ -9,6 +9,7 @@ import pytest
from sqlalchemy import func, select
from backend.app.models import Artist, ImageRecord, Tag, TagKind
from backend.app.models.series_page import SeriesPage
from backend.app.models.tag import image_tag
from backend.app.services import cleanup_service
@@ -333,3 +334,62 @@ def test_prune_unused_tags_commit_deletes_them(db_sync, tmp_path):
surviving_names = db_sync.execute(select(Tag.name)).scalars().all()
assert "kept" in surviving_names
assert "bye" not in surviving_names
# --- reset_content_tagging ------------------------------------------
def test_reset_content_tagging_dry_run_counts_without_deleting(db_sync, tmp_path):
a = _make_artist(db_sync, slug="rc")
img = _make_image(
db_sync, artist=a, path=str(tmp_path / "r.jpg"), sha256="1" * 64,
)
g = _make_tag(db_sync, name="solo", kind=TagKind.general)
c = _make_tag(db_sync, name="naruto", kind=TagKind.character)
_make_tag(db_sync, name="Naruto", kind=TagKind.fandom)
_make_tag(db_sync, name="my-series", kind=TagKind.series)
db_sync.execute(image_tag.insert().values([
{"image_record_id": img.id, "tag_id": g.id},
{"image_record_id": img.id, "tag_id": c.id},
]))
db_sync.commit()
result = cleanup_service.reset_content_tagging(db_sync, dry_run=True)
assert result["count"] == 2
assert result["by_kind"] == {"general": 1, "character": 1}
assert result["applications"] == 2
# Nothing deleted — all 4 tags still present.
assert db_sync.execute(select(func.count(Tag.id))).scalar_one() == 4
def test_reset_content_tagging_deletes_content_keeps_fandom_series(db_sync, tmp_path):
a = _make_artist(db_sync, slug="rc2")
img = _make_image(
db_sync, artist=a, path=str(tmp_path / "r2.jpg"), sha256="2" * 64,
)
g = _make_tag(db_sync, name="solo", kind=TagKind.general)
c = _make_tag(db_sync, name="naruto", kind=TagKind.character)
_make_tag(db_sync, name="Naruto", kind=TagKind.fandom)
s = _make_tag(db_sync, name="my-series", kind=TagKind.series)
db_sync.execute(image_tag.insert().values([
{"image_record_id": img.id, "tag_id": g.id},
{"image_record_id": img.id, "tag_id": c.id},
{"image_record_id": img.id, "tag_id": s.id}, # series membership
]))
db_sync.add(SeriesPage(series_tag_id=s.id, image_id=img.id, page_number=1))
db_sync.commit()
result = cleanup_service.reset_content_tagging(db_sync, dry_run=False)
assert result["deleted"] == 2
# general + character gone; fandom + series kept.
kinds = db_sync.execute(select(Tag.kind)).scalars().all()
kind_vals = {k.value if hasattr(k, "value") else str(k) for k in kinds}
assert kind_vals == {"fandom", "series"}
# series_page ordering survived.
assert db_sync.execute(
select(func.count()).select_from(SeriesPage)
).scalar_one() == 1
# Only the series image_tag association survived (content ones cascaded).
remaining = db_sync.execute(select(image_tag.c.tag_id)).scalars().all()
assert remaining == [s.id]