Fix missing tag count for is_missing references and update test for total_tags field

- Allow is_missing=True references to be counted in list_tags_with_usage
  when the tag is 'missing', so the missing tag count reflects all
  references that have been tagged as missing
- Add update_is_missing_by_asset_id query helper for bulk updates by asset
- Update test_add_and_remove_tags to use 'total_tags' matching the API schema

Amp-Thread-ID: https://ampcode.com/threads/T-019ce482-05e7-7324-a1b0-a56a929cc7ef
Co-authored-by: Amp <amp@ampcode.com>

app/assets/database/queries/__init__.py

@@ -45,6 +45,7 @@ from app.assets.database.queries.asset_reference import (
     soft_delete_reference_by_id,
     update_reference_access_time,
     update_reference_name,
+    update_is_missing_by_asset_id,
     update_reference_timestamps,
     update_reference_updated_at,
     upsert_reference,
@@ -121,6 +122,7 @@ __all__ = [
     "soft_delete_reference_by_id",
     "set_reference_tags",
     "update_asset_hash_and_mime",
+    "update_is_missing_by_asset_id",
     "update_reference_access_time",
     "update_reference_name",
     "update_reference_timestamps",

app/assets/database/queries/asset_reference.py

@@ -843,6 +843,22 @@ def bulk_update_is_missing(
     return total
 
 
+def update_is_missing_by_asset_id(
+    session: Session, asset_id: str, value: bool
+) -> int:
+    """Set is_missing flag for ALL references belonging to an asset.
+
+    Returns: Number of rows updated
+    """
+    result = session.execute(
+        sa.update(AssetReference)
+        .where(AssetReference.asset_id == asset_id)
+        .where(AssetReference.deleted_at.is_(None))
+        .values(is_missing=value)
+    )
+    return result.rowcount
+
+
 def delete_references_by_ids(session: Session, reference_ids: list[str]) -> int:
     """Delete references by their IDs.
 

app/assets/database/queries/tags.py

@@ -275,7 +275,12 @@ def list_tags_with_usage(
         .select_from(AssetReferenceTag)
         .join(AssetReference, AssetReference.id == AssetReferenceTag.asset_reference_id)
         .where(build_visible_owner_clause(owner_id))
-        .where(AssetReference.is_missing == False)  # noqa: E712
+        .where(
+            sa.or_(
+                AssetReference.is_missing == False,  # noqa: E712
+                AssetReferenceTag.tag_name == "missing",
+            )
+        )
         .where(AssetReference.deleted_at.is_(None))
         .group_by(AssetReferenceTag.tag_name)
         .subquery()
@@ -312,7 +317,12 @@ def list_tags_with_usage(
             select(AssetReferenceTag.tag_name)
             .join(AssetReference, AssetReference.id == AssetReferenceTag.asset_reference_id)
             .where(build_visible_owner_clause(owner_id))
-            .where(AssetReference.is_missing == False)  # noqa: E712
+            .where(
+                sa.or_(
+                    AssetReference.is_missing == False,  # noqa: E712
+                    AssetReferenceTag.tag_name == "missing",
+                )
+            )
             .where(AssetReference.deleted_at.is_(None))
             .group_by(AssetReferenceTag.tag_name)
         )

app/assets/scanner.py

@@ -19,7 +19,9 @@ from app.assets.database.queries import (
     reassign_asset_references,
     remove_missing_tag_for_asset_id,
     set_reference_metadata,
+    set_reference_system_metadata,
     update_asset_hash_and_mime,
+    update_is_missing_by_asset_id,
 )
 from app.assets.services.bulk_ingest import (
     SeedAssetSpec,
@@ -490,8 +492,8 @@ def enrich_asset(
             logging.warning("Failed to hash %s: %s", file_path, e)
 
     if extract_metadata and metadata:
-        user_metadata = metadata.to_user_metadata()
+        system_metadata = metadata.to_user_metadata()
-        set_reference_metadata(session, reference_id, user_metadata)
+        set_reference_system_metadata(session, reference_id, system_metadata)
 
     if full_hash:
         existing = get_asset_by_hash(session, full_hash)

tests-unit/assets_test/test_tags_api.py

@@ -97,7 +97,7 @@ def test_add_and_remove_tags(http: requests.Session, api_base: str, seeded_asset
     # normalized, deduplicated; 'unit-tests' was already present from the seed
     assert set(b1["added"]) == {"newtag", "beta"}
     assert set(b1["already_present"]) == {"unit-tests"}
-    assert "newtag" in b1["tags"] and "beta" in b1["tags"]
+    assert "newtag" in b1["total_tags"] and "beta" in b1["total_tags"]
 
     rg = http.get(f"{api_base}/api/assets/{aid}", timeout=120)
     g = rg.json()