Filter soft-deleted and missing refs from visibility queries

list_references_by_asset_id and list_tags_with_usage were not filtering
out deleted_at/is_missing refs, allowing /view?filename=blake3:... to
serve files through hidden references and inflating tag usage counts.
Add list_all_file_paths_by_asset_id for orphan cleanup which
intentionally needs unfiltered access.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Luke Mino-Altherr
2026-03-12 14:43:06 -07:00
parent 23e458e549
commit d78c741ba2
4 changed files with 29 additions and 5 deletions

View File

@ -549,6 +549,8 @@ def list_references_by_asset_id(
session.execute(
select(AssetReference)
.where(AssetReference.asset_id == asset_id)
.where(AssetReference.is_missing == False) # noqa: E712
.where(AssetReference.deleted_at.is_(None))
.order_by(AssetReference.id.asc())
)
.scalars()
@ -556,6 +558,25 @@ def list_references_by_asset_id(
)
def list_all_file_paths_by_asset_id(
session: Session,
asset_id: str,
) -> list[str]:
"""Return every file_path for an asset, including soft-deleted/missing refs.
Used for orphan cleanup where all on-disk files must be removed.
"""
return list(
session.execute(
select(AssetReference.file_path)
.where(AssetReference.asset_id == asset_id)
.where(AssetReference.file_path.isnot(None))
)
.scalars()
.all()
)
def upsert_reference(
session: Session,
asset_id: str,