alembic/versions/0045_image_prediction_table.py

@@ -51,6 +51,10 @@ def upgrade() -> None:
     # Backfill from the JSON blob. json_each expands {name: {category,
     # confidence}} into one row per prediction. category defaults to 'general'
     # to mirror the suggestion read path; rows with no confidence are skipped.
+    # Filter to >= the store floor (ml_settings.tagger_store_floor, default
+    # 0.70) right here so this is self-sufficient — it does NOT depend on the
+    # #764 prune having run, and extracting only the >=floor tail keeps
+    # image_prediction small (~tens of rows/image) even from the full JSON.
     op.execute(
         """
         INSERT INTO image_prediction (image_record_id, raw_name, category, score)
@@ -62,6 +66,11 @@ def upgrade() -> None:
              json_each(ir.tagger_predictions) je
         WHERE ir.tagger_predictions IS NOT NULL
           AND je.value ->> 'confidence' IS NOT NULL
+          AND (je.value ->> 'confidence')::double precision
+              >= COALESCE(
+                  (SELECT tagger_store_floor FROM ml_settings WHERE id = 1),
+                  0.70
+              )
         ON CONFLICT (image_record_id, raw_name) DO NOTHING
         """
     )