refactor(ml): remove the dead per-tag centroid subsystem (#1189)
The v2 pivot replaced per-tag SigLIP centroids with learned heads + CCIP. Centroids were still recomputed (on every tag merge + a daily beat) but NOTHING read them — suggestions come from heads+CCIP and apply_allowlist_tags applies via Camie predictions, not centroids. Pure dead wiring; remove it. Removed: CentroidService, recompute_centroid/recompute_centroids tasks, the daily beat, POST /api/ml/recompute-centroids, the recompute-on-merge trigger, the tag_reference_embedding table + model, the centroid_similarity_threshold + min_reference_images settings (migration 0066), the CentroidRecomputeCard + its store action + MaintenancePanel tile, and the centroid slider in MLThresholdSliders. _keep_as_alias drops its vestigial has-centroid branch (the allowlist branch already covers "could re-emit"); tag merge no longer clears a table that no longer exists. NOT touched (still live, parallel to heads): the Camie tagger, ImagePrediction, and the allowlist bulk-apply — accepting a suggestion still allowlists + applies it across the library. The tag-eval "centroid" baseline metric is unrelated (in-memory) and stays. (image_record.centroid_scores JSON column also remains — separate legacy field, its own micro-cleanup.) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
This commit is contained in:
+5
-58
@@ -1,9 +1,9 @@
|
||||
"""ML Celery tasks: per-image inference, backfill discovery, centroid
|
||||
recompute, allowlist auto-apply, model self-heal.
|
||||
"""ML Celery tasks: per-image inference, backfill discovery, head training,
|
||||
allowlist auto-apply, model self-heal.
|
||||
|
||||
All run on the ml-worker (queue 'ml') except recompute_centroids and
|
||||
apply_allowlist_tags sweeps which are 'maintenance' lane. Sync sessions
|
||||
(Celery workers are sync processes), same pattern as FC-2a tasks.
|
||||
All run on the ml-worker (queue 'ml') except apply_allowlist_tags sweeps which
|
||||
are 'maintenance' lane. Sync sessions (Celery workers are sync processes), same
|
||||
pattern as FC-2a tasks.
|
||||
"""
|
||||
|
||||
import logging
|
||||
@@ -487,59 +487,6 @@ def _confidence_for_tag(session, tag, preds: dict) -> float | None:
|
||||
return best
|
||||
|
||||
|
||||
@celery.task(name="backend.app.tasks.ml.recompute_centroid", bind=True)
|
||||
def recompute_centroid(self, tag_id: int) -> bool:
|
||||
import asyncio
|
||||
|
||||
from ..services.ml.centroids import CentroidService
|
||||
from ._async_session import async_session_factory
|
||||
|
||||
async def _run() -> bool:
|
||||
# Per-task NullPool engine bound to THIS asyncio.run loop — the shared
|
||||
# process-wide engine reuses connections across loops and raises
|
||||
# "Future attached to a different loop" on every call after the first.
|
||||
async_factory, async_engine = async_session_factory()
|
||||
try:
|
||||
async with async_factory() as session:
|
||||
svc = CentroidService(session)
|
||||
result = await svc.recompute_for_tag(tag_id)
|
||||
await session.commit()
|
||||
return result
|
||||
finally:
|
||||
await async_engine.dispose()
|
||||
|
||||
return asyncio.run(_run())
|
||||
|
||||
|
||||
@celery.task(
|
||||
name="backend.app.tasks.ml.recompute_centroids",
|
||||
bind=True,
|
||||
# Audit 2026-06-02 — drifted-centroid rebuild over potentially
|
||||
# hundreds of tags.
|
||||
soft_time_limit=1800, time_limit=2100,
|
||||
)
|
||||
def recompute_centroids(self) -> int:
|
||||
"""Daily: find drifted centroids, enqueue recompute_centroid for each."""
|
||||
import asyncio
|
||||
|
||||
from ..services.ml.centroids import CentroidService
|
||||
from ._async_session import async_session_factory
|
||||
|
||||
async def _list() -> list[int]:
|
||||
# Per-task NullPool engine bound to this loop (see recompute_centroid).
|
||||
async_factory, async_engine = async_session_factory()
|
||||
try:
|
||||
async with async_factory() as session:
|
||||
return await CentroidService(session).list_drifted()
|
||||
finally:
|
||||
await async_engine.dispose()
|
||||
|
||||
drifted = asyncio.run(_list())
|
||||
for tid in drifted:
|
||||
recompute_centroid.delay(tid)
|
||||
return len(drifted)
|
||||
|
||||
|
||||
@celery.task(
|
||||
name="backend.app.tasks.ml.tag_eval_run",
|
||||
bind=True,
|
||||
|
||||
Reference in New Issue
Block a user