feat(ml): image_prediction table + backfill + dual-write (#768 step 1)

Normalize tagger predictions out of the image_record.tagger_predictions JSON
blob into a queryable per-prediction table. Step 1 of the cutover (expand):
additive + low-risk — reads still use the JSON, this just adds the table and
keeps it populated.

- ImagePrediction(image_record_id, raw_name, category, score) — stores the
  RAW tagger vocab name (not tag_id) so read-time alias→canonical resolution
  is unchanged. Indexed for per-image reads + by (raw_name, score).
- Migration 0045: create table + set-based backfill from the JSON via
  json_each (fast post-#764-prune). The old column stays (vestigial) and is
  dropped in a later follow-up — DROP needs an ACCESS EXCLUSIVE lock on the
  hot image_record table, so it waits for a quiesced-worker window.
- tag_and_embed dual-writes the rows (delete-then-insert, idempotent);
  tagger_store_floor already applied in infer().

Next: switch suggestion + allowlist reads to the table, then drop the JSON
write. Plan-task #768.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

backend/app/tasks/ml.py

@@ -10,11 +10,11 @@ import logging
 from pathlib import Path
 
 from celery.exceptions import SoftTimeLimitExceeded
-from sqlalchemy import select
+from sqlalchemy import delete, select
 from sqlalchemy.exc import DBAPIError, OperationalError
 
 from ..celery_app import celery
-from ..models import ImageRecord, MLSettings
+from ..models import ImagePrediction, ImageRecord, MLSettings
 from ._sync_engine import sync_session_factory as _sync_session_factory
 
 log = logging.getLogger(__name__)
@@ -162,6 +162,23 @@ def tag_and_embed(self, image_id: int) -> dict:
             record.siglip_embedding = embedding.tolist()
             record.siglip_model_version = settings.embedder_model_version
             session.add(record)
+            # Write the normalized image_prediction rows (#768). Delete-then-
+            # insert keeps a re-tag idempotent. tagger_store_floor was already
+            # applied in tagger.infer, so preds is the >=floor set. (Transitional
+            # dual-write alongside the JSON column until the read cutover lands.)
+            session.execute(
+                delete(ImagePrediction).where(
+                    ImagePrediction.image_record_id == image_id
+                )
+            )
+            session.add_all([
+                ImagePrediction(
+                    image_record_id=image_id, raw_name=name,
+                    category=p.get("category", "general"),
+                    score=float(p.get("confidence", 0.0)),
+                )
+                for name, p in preds.items()
+            ])
             session.commit()
     except SoftTimeLimitExceeded:
         log.error(