feat(tags): 'Reset content tagging' admin action
CI / backend-lint-and-test (push) Successful in 11s
CI / lint (push) Successful in 3s
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
+21
View File
@@ -224,6 +224,27 @@ async def tags_purge_legacy():
return jsonify(result)
@admin_bp.route("/tags/reset-content", methods=["POST"])
async def tags_reset_content():
"""Tier-A: delete ALL general + character tags (the Camie-suggestable
content vocabulary) so the operator can re-tag from scratch via
auto-suggest. fandom + series tags + series_page ordering are preserved,
and image tagger_predictions are untouched so suggestions repopulate.
dry-run preview returns per-kind counts + applications + a sample so the
UI shows exactly what'll go before the operator confirms (dry_run=false).
Irreversible except via DB backup restore."""
from ..services.cleanup_service import reset_content_tagging
body = await request.get_json(silent=True) or {}
dry_run = bool(body.get("dry_run", False))
async with get_session() as session:
result = await session.run_sync(
lambda sync_sess: reset_content_tagging(sync_sess, dry_run=dry_run)
)
return jsonify(result)
@admin_bp.route("/maintenance/db-stats", methods=["GET"])
async def db_stats():
"""Per-table bloat readout (pg_stat_user_tables) for the high-churn tables
+56
View File
@@ -455,6 +455,62 @@ def purge_legacy_tags(session: Session, *, dry_run: bool = False) -> dict:
return result
# The Camie-suggestable CONTENT vocabulary. "Reset content tagging" wipes
# these so the operator can re-tag from scratch via auto-suggest. fandom +
# series (and series_page ordering) are deliberately NOT here — they're kept.
RESETTABLE_TAG_KINDS = ("general", "character")
def reset_content_tagging(session: Session, *, dry_run: bool = False) -> dict:
"""Count (dry_run) or DELETE every general + character tag so the operator
can re-tag from scratch via the Camie auto-suggest.
PRESERVED: fandom + series tags and their series_page ordering, plus every
image's image_record.tagger_predictions (untouched) so suggestions
repopulate immediately. CASCADE on image_tag / tag_alias / tag_allowlist /
tag_reference_embedding / tag_suggestion_rejection clears each deleted
tag's applications + metadata. Tag.fandom_id is SET NULL, so deleting
character tags never touches the fandom rows. Irreversible except via DB
backup restore.
Returns:
{"by_kind": {"general": N, "character": M},
"count": total tags,
"applications": image_tag rows that will be / were removed,
"sample_names": [first 50],
and on live runs "deleted": total}
"""
predicate = Tag.kind.in_(RESETTABLE_TAG_KINDS)
rows = session.execute(
select(Tag.id, Tag.name, Tag.kind).where(predicate)
).all()
by_kind: dict[str, int] = {}
for _id, _name, kind in rows:
key = kind.value if hasattr(kind, "value") else str(kind)
by_kind[key] = by_kind.get(key, 0) + 1
# Headline impact: applications (image_tag rows) that vanish via cascade.
applications = session.execute(
select(func.count())
.select_from(image_tag)
.where(image_tag.c.tag_id.in_(select(Tag.id).where(predicate)))
).scalar_one()
sample = [name for _id, name, _kind in rows[:50]]
total = len(rows)
result = {
"by_kind": by_kind,
"count": total,
"applications": applications,
"sample_names": sample,
}
if dry_run:
return result
if total:
session.execute(Tag.__table__.delete().where(predicate))
session.commit()
result["deleted"] = total
return result
# ---------------------------------------------------------------------------
# FC-Cleanup additions (2026-05-26): retroactive audit of import-filter rules.
# ---------------------------------------------------------------------------