feat(ml): drop image_record.tagger_predictions — image_prediction is sole store (#768 step 3)

Read cutover verified in prod (suggestions + allowlist read image_prediction;
backfill complete at 908k rows / 51k images). Removes the old JSON column and
everything that fed it:

- ImageRecord.tagger_predictions column removed; migration 0046 DROPs it.
  tagger_model_version kept as the "tagged / current?" signal the backfill
  sweep reads (needs-tagging check switched to tagger_model_version IS NULL).
- tag_and_embed no longer dual-writes the JSON — image_prediction is the only
  write path.
- importer re-import reset drops the JSON line (image_prediction rows are
  already deleted on re-import).
- Retired the one-time #768 backfill task + the #764 prune task, their admin
  endpoints, and their Maintenance cards (Backfill/PrunePredictionsCard).
- Tests seed/assert via image_prediction; stale column refs removed.

Disk reclaim is NOT automatic: DROP COLUMN is a catalog change. Run
`VACUUM FULL image_record` off-hours afterward to return the ~100 GB to the OS
so DB backups go small (#739). image_prediction (~90 MB) stays in pg_dump — it's
the source of truth now.

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

backend/app/tasks/ml.py

@@ -157,15 +157,15 @@ def tag_and_embed(self, image_id: int) -> dict:
                 )
 
             phase = "persist"
-            record.tagger_predictions = preds
             record.tagger_model_version = settings.tagger_model_version
             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.)
+            # Write the normalized image_prediction rows (#768) — the sole home
+            # for predictions now (image_record.tagger_predictions was dropped in
+            # migration 0046). Delete-then-insert keeps a re-tag idempotent;
+            # tagger_store_floor was already applied in tagger.infer, so preds is
+            # the >=floor set.
             session.execute(
                 delete(ImagePrediction).where(
                     ImagePrediction.image_record_id == image_id
@@ -282,7 +282,7 @@ def backfill(self) -> int:
                 select(ImageRecord.id)
                 .where(ImageRecord.id > last_id)
                 .where(
-                    (ImageRecord.tagger_predictions.is_(None))
+                    (ImageRecord.tagger_model_version.is_(None))
                     | (
                         ImageRecord.tagger_model_version
                         != settings.tagger_model_version