.forgejo/workflows/baseline.yml

@@ -37,6 +37,10 @@ on:
         description: 'Commit/tag that still carries the full 0001..0087 chain'
         type: string
         default: '0a5bbe8'
+      mode:
+        description: 'chain = compare against this tree''s migrations; models = compare against a schema built from the MODELS'
+        type: string
+        default: 'chain'
 
 jobs:
   compare:
@@ -174,20 +178,44 @@ jobs:
           echo "candidate-bytes:  $(wc -c < "$F")"
           echo "candidate-b64-lines: $(echo "$B64" | wc -l)"
           set -x
+          mkdir -p /tmp/candidate
+          cp alembic/versions/*.py /tmp/candidate/
           # Put the tree back exactly as it was; this job never mutates state.
           rm -f alembic/versions/*.py
           mv /tmp/versions_held/*.py alembic/versions/ 2>/dev/null || true
 
-      # DB 2: whatever the CURRENT tree's alembic/versions produces. Before the
-      # squash that is the same 87 revisions and the diff is trivially clean —
-      # which is worth running once as a control, so a clean diff after the
-      # squash means something.
+      # DB 2: what the CURRENT tree produces.
+      #
+      # `mode: models` applies the candidate autogenerated from the MODELS
+      # instead, which is what answers "do the models describe the schema?" —
+      # the question #3275 exists because nobody had ever asked it. Under that
+      # mode a clean diff means autogenerate is trustworthy again.
+      #
+      # The two extensions are created by hand first. They are database
+      # objects, not table metadata, so no model can carry them and their
+      # absence is not a model defect — it is simply outside what this
+      # comparison is asking about.
       - name: Build the schema the CURRENT tree produces
+        env:
+          MODE: ${{ github.event.inputs.mode }}
         run: |
           set -eux
           docker exec "$PG_CONTAINER" createdb -U fabledcurator fc_base
-          ls alembic/versions/*.py | wc -l
-          DB_NAME=fc_base alembic upgrade head
+          if [ "${MODE:-chain}" = "models" ]; then
+            docker exec "$PG_CONTAINER" psql -U fabledcurator -d fc_base \
+              -c "CREATE EXTENSION IF NOT EXISTS vector" \
+              -c "CREATE EXTENSION IF NOT EXISTS tsm_system_rows"
+            mkdir -p /tmp/held
+            mv alembic/versions/*.py /tmp/held/
+            cp /tmp/candidate/*.py alembic/versions/
+            ls alembic/versions/*.py
+            DB_NAME=fc_base alembic upgrade head
+            rm -f alembic/versions/*.py
+            mv /tmp/held/*.py alembic/versions/
+          else
+            ls alembic/versions/*.py | wc -l
+            DB_NAME=fc_base alembic upgrade head
+          fi
           docker exec "$PG_CONTAINER" pg_dump -U fabledcurator --schema-only \
             --no-owner --no-privileges -d fc_base > baseline.sql
           wc -l baseline.sql

backend/app/models/image_record.py

@@ -33,6 +33,17 @@ class ImageRecord(Base):
 
 
     __table_args__ = (
+        # alembic 0036, and the last thing in this schema that lived only in a
+        # migration. SQLAlchemy CAN express an hnsw index with an operator
+        # class, so there is no reason for it to be invisible to the models —
+        # and its absence was the quietest failure of the lot: everything
+        # works, similarity search just silently stops using an index.
+        Index(
+            "ix_image_record_siglip_hnsw",
+            "siglip_embedding",
+            postgresql_using="hnsw",
+            postgresql_ops={"siglip_embedding": "vector_cosine_ops"},
+        ),
         # alembic 0035/0071: the date-ordered browse indexes (#3275).
         Index("ix_image_record_effective_date", text("effective_date DESC"), text("id DESC")),
         Index("ix_image_record_earliest_post_date", text("earliest_post_date DESC"), text("id DESC")),