chore: retire ml-backfill-daily beat + the spent purge-legacy action (operator-approved)

- ml-backfill-daily: the CPU tag_and_embed backfill raced the GPU agent's
  daily embed backfill for the same NULL-embedding images at ~100x the cost
  (B1 audit verdict, milestone #124). The backfill TASK stays — the manual
  /api/ml/backfill button remains the deliberate CPU fallback pending B3.
- purge-legacy: one-time IR-migration cleanup, dry-run verified 0 targets on
  the live library before removal (A2 audit, milestone #123). Fully retired
  per rule 22: tile, store action, route, service fn, tests.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
This commit is contained in:
2026-07-02 11:24:08 -04:00
parent 95d2ae1d58
commit 1f27189b8f
6 changed files with 1 additions and 203 deletions
+1 -15
View File
@@ -1,13 +1,12 @@
"""FC-3k: /api/admin — destructive admin actions.
Five action surfaces:
Action surfaces:
POST /api/admin/artists/<slug>/cascade-delete (Tier C)
POST /api/admin/images/bulk-delete (Tier C)
DELETE /api/admin/tags/<int:tag_id> (Tier B)
POST /api/admin/tags/<int:dest_id>/merge (Tier B)
POST /api/admin/tags/prune-unused (Tier A)
POST /api/admin/posts/prune-bare (Tier A)
POST /api/admin/tags/purge-legacy (Tier A)
GET /api/admin/tags/<int:tag_id>/usage-count (helper)
Tier-C ops take a dry_run body flag (returns projection inline,
@@ -277,19 +276,6 @@ async def posts_reconcile_duplicates():
return await _run_dry_run_op(reconcile_duplicate_posts, source_id=source_id)
@admin_bp.route("/tags/purge-legacy", methods=["POST"])
async def tags_purge_legacy():
"""Tier-A: delete legacy IR-migration tags — archive/post/artist
kinds (e.g. `BlenderKnight:Hannah_BJ_Loops`) PLUS general tags with
a legacy name prefix (`source:*`, from IR's source kind that fell
back to general). dry-run preview returns per-kind + per-prefix
counts + a sample so the UI shows exactly what'll go before the
operator confirms with dry_run=false."""
from ..services.cleanup_service import purge_legacy_tags
return await _run_dry_run_op(purge_legacy_tags)
@admin_bp.route("/tags/reset-content", methods=["POST"])
async def tags_reset_content():
"""Tier-A: delete ALL general + character tags (the Camie-suggestable
-4
View File
@@ -97,10 +97,6 @@ def make_celery() -> Celery:
"task": "backend.app.tasks.maintenance.cleanup_old_tasks",
"schedule": 86400.0, # daily
},
"ml-backfill-daily": {
"task": "backend.app.tasks.ml.backfill",
"schedule": 86400.0,
},
"train-heads-nightly": {
"task": "backend.app.tasks.ml.scheduled_train_heads",
"schedule": 86400.0, # passive cadence; manual retrain stays available
-65
View File
@@ -718,71 +718,6 @@ def reconcile_duplicate_posts(
return {"groups": len(groups), "merged": losers_total, "sample": sample}
# Legacy tags FC no longer uses, in two shapes:
# (1) kinds the tag input never produces — archive/post/artist.
# provenance (post grouping) + archive membership are their own
# systems now, and artists are first-class Artist/Source rows.
# meta/rating were already hard-deleted by alembic 0023.
# (2) name prefixes from IR kinds FC never adopted — `source:*`.
# ImageRepo had a `source` kind; FC's enum doesn't, so ir_ingest
# fell those back to `general` (kind=general, name="source:patreon"
# etc.). They can't be caught by kind, so we match the name prefix.
PURGEABLE_TAG_KINDS = ("archive", "post", "artist")
LEGACY_NAME_PREFIXES = ("source:",)
def _legacy_tag_predicate():
name_clauses = [Tag.name.like(f"{p}%") for p in LEGACY_NAME_PREFIXES]
return or_(Tag.kind.in_(PURGEABLE_TAG_KINDS), *name_clauses)
def purge_legacy_tags(session: Session, *, dry_run: bool = False) -> dict:
"""Count (dry_run) or delete legacy IR-migration tags: archive/post/
artist-kind tags PLUS general tags whose name matches a legacy
prefix (source:*).
CASCADE on image_tag / tag_alias / tag_suggestion_rejection / series_page
clears the related rows on the parent DELETE.
Returns:
{"by_kind": {kind: count, ...}, # kind-matched rows
"by_prefix": {"source:*": count}, # name-prefix-matched rows
"count": total, "sample_names": [first 50],
and on live runs "deleted": total}
"""
predicate = _legacy_tag_predicate()
rows = session.execute(
select(Tag.id, Tag.name, Tag.kind).where(predicate)
).all()
by_kind: dict[str, int] = {}
by_prefix: dict[str, int] = {}
for _id, name, kind in rows:
# Classify by name-prefix first so a source:* row counts once,
# under the prefix bucket, regardless of its (general) kind.
matched_prefix = next(
(p for p in LEGACY_NAME_PREFIXES if name.startswith(p)), None,
)
if matched_prefix is not None:
label = f"{matched_prefix}*"
by_prefix[label] = by_prefix.get(label, 0) + 1
else:
key = kind.value if hasattr(kind, "value") else str(kind)
by_kind[key] = by_kind.get(key, 0) + 1
sample = [name for _id, name, _kind in rows[:50]]
total = len(rows)
result = {
"by_kind": by_kind, "by_prefix": by_prefix,
"count": total, "sample_names": sample,
}
if dry_run:
return result
if total:
session.execute(Tag.__table__.delete().where(predicate))
session.commit()
result["deleted"] = total
return result
# The CONTENT vocabulary. "Reset content tagging" wipes these so the operator
# can re-tag from scratch. fandom + series (and series_page ordering) are
# deliberately NOT here — they're kept.
@@ -42,53 +42,6 @@
</div>
</MaintenanceTile>
<MaintenanceTile
icon="mdi-tag-off"
title="Legacy migration tags"
blurb="Purge retired archive/post/artist + source:* tags."
destructive
>
<p class="fc-muted text-body-2 mb-3">
Purge legacy IR-migration tags FC no longer uses: retired/system
kinds (<code>archive</code>, <code>post</code>, <code>artist</code> e.g.
<code>BlenderKnight:Hannah_BJ_Loops</code>) plus <code>source:*</code> tags
(ImageRepo's old <code>source</code> kind, migrated to <code>general</code>).
Provenance and artists are their own systems now, so these are pure noise.
Removes them from every image.
</p>
<v-btn
color="accent" variant="flat" rounded="pill"
prepend-icon="mdi-magnify"
:loading="loadingKindPreview"
class="mb-3"
@click="onKindPreview"
>Preview legacy tags</v-btn>
<div v-if="kindPreview">
<p class="text-body-2 mb-2">
<strong>{{ kindPreview.count }}</strong> legacy tag(s).
<span v-for="(n, k) in kindPreview.by_kind" :key="k" class="fc-muted">
{{ k }}: {{ n }}&nbsp;&nbsp;
</span>
<span v-for="(n, p) in kindPreview.by_prefix" :key="p" class="fc-muted">
{{ p }}: {{ n }}&nbsp;&nbsp;
</span>
</p>
<SampleNameGrid
v-if="kindPreview.sample_names?.length"
:names="kindPreview.sample_names" class="mb-3"
/>
<v-btn
color="error" variant="flat" rounded="pill"
prepend-icon="mdi-delete-sweep"
:disabled="!kindPreview.count"
:loading="kindCommitting"
@click="onKindCommit"
>Delete {{ kindPreview.count }} legacy tag(s)</v-btn>
</div>
</MaintenanceTile>
<MaintenanceTile
icon="mdi-tag-multiple"
title="Reset content tagging"
@@ -216,16 +169,6 @@ const {
emptyPreview: (r) => ({ count: 0, sample_names: r.sample_names || [] }),
})
// Legacy migration-tag purge.
const {
previewData: kindPreview, previewing: loadingKindPreview,
committing: kindCommitting, runPreview: onKindPreview, runCommit: onKindCommit,
} = usePreviewCommit({
preview: () => store.purgeLegacyTags({ dryRun: true }),
commit: () => store.purgeLegacyTags({ dryRun: false }),
emptyPreview: { count: 0, by_kind: {}, by_prefix: {}, sample_names: [] },
})
// Reset content tagging (general + character).
const {
previewData: resetPreview, previewing: loadingResetPreview,
-5
View File
@@ -101,10 +101,6 @@ export const useAdminStore = defineStore('admin', () => {
})
}
function purgeLegacyTags(opts = {}) {
return _dryRunPost('/api/admin/tags/purge-legacy', opts)
}
// Destructive: deletes ALL general + character tags so the operator can
// re-tag from scratch via auto-suggest. fandom + series preserved.
function resetContentTagging(opts = {}) {
@@ -154,7 +150,6 @@ export const useAdminStore = defineStore('admin', () => {
pruneUnusedTags,
pruneBarePosts,
reconcileDuplicatePosts,
purgeLegacyTags,
resetContentTagging,
normalizeTags,
pollTaskUntilDone,
-57
View File
@@ -390,63 +390,6 @@ async def test_prune_unused_commit_deletes_and_returns_count(client, db):
assert "byebye" in body["sample_names"]
@pytest.mark.asyncio
async def test_purge_legacy_dry_run_counts_by_kind_and_prefix(client, db):
db.add_all([
Tag(name="BlenderKnight:Hannah_BJ_Loops", kind=TagKind.archive),
Tag(name="BlenderKnight:May Animation", kind=TagKind.post),
Tag(name="SomeArtist", kind=TagKind.artist),
# IR `source` kind fell back to general during migration —
# caught by the source:* name prefix, not by kind.
Tag(name="source:patreon", kind=TagKind.general),
Tag(name="blonde hair", kind=TagKind.general), # must survive
])
await db.commit()
resp = await client.post(
"/api/admin/tags/purge-legacy", json={"dry_run": True},
)
body = await resp.get_json()
assert body["count"] == 4
assert body["by_kind"] == {"archive": 1, "post": 1, "artist": 1}
assert body["by_prefix"] == {"source:*": 1}
assert "blonde hair" not in body["sample_names"]
assert "source:patreon" in body["sample_names"]
@pytest.mark.asyncio
async def test_purge_legacy_commit_deletes_only_legacy(client, db):
from sqlalchemy import func, select
db.add_all([
Tag(name="arch1", kind=TagKind.archive),
Tag(name="source:fanbox", kind=TagKind.general),
Tag(name="keepme", kind=TagKind.general),
Tag(name="char1", kind=TagKind.character),
])
await db.commit()
resp = await client.post(
"/api/admin/tags/purge-legacy", json={"dry_run": False},
)
body = await resp.get_json()
assert body["deleted"] == 2 # arch1 + source:fanbox
# The plain general + character tags survive.
keep = (await db.execute(
select(Tag.name).where(Tag.name.in_(["keepme", "char1"]))
)).scalars().all()
assert set(keep) == {"keepme", "char1"}
# No archive/post/artist or source:* left.
gone = (await db.execute(
select(func.count()).select_from(Tag).where(
(Tag.kind.in_([TagKind.archive, TagKind.post, TagKind.artist]))
| (Tag.name.like("source:%"))
)
)).scalar_one()
assert gone == 0
# --- Tier-A: POST /posts/prune-bare + /posts/reconcile-duplicates ---
# These two routes share _run_dry_run_op with the tag prunes (DRY pass,
# task #753); cover their apply path + reconcile's source_id passthrough so