fix(assets): refresh loader_path when re-ingesting an existing reference
Some checks are pending
Python Linting / Run Ruff (push) Waiting to run
Python Linting / Run Pylint (push) Waiting to run

upsert_reference only wrote loader_path on the INSERT branch, so
re-ingesting an existing reference (an output overwritten in place, or a
file re-registered after its loader_path derivation changed) kept the
stale or NULL value forever. Write it on the UPDATE branch too, with a
null-safe change guard so a loader_path difference alone is enough to
trigger the update, and identical values stay a no-op.
This commit is contained in:
Simon Pinfold 2026-07-07 08:59:46 +12:00
parent 09086138db
commit 72d0f86a1d
2 changed files with 36 additions and 2 deletions

View File

@ -688,13 +688,14 @@ def upsert_reference(
AssetReference.asset_id != asset_id,
AssetReference.mtime_ns.is_(None),
AssetReference.mtime_ns != int(mtime_ns),
AssetReference.loader_path.is_distinct_from(loader_path),
AssetReference.is_missing == True, # noqa: E712
AssetReference.deleted_at.isnot(None),
)
)
.values(
asset_id=asset_id, mtime_ns=int(mtime_ns), is_missing=False,
deleted_at=None, updated_at=now,
asset_id=asset_id, mtime_ns=int(mtime_ns), loader_path=loader_path,
is_missing=False, deleted_at=None, updated_at=now,
)
)
res2 = session.execute(upd)

View File

@ -176,6 +176,39 @@ class TestUpsertReference:
ref = session.query(AssetReference).filter_by(file_path=file_path).one()
assert ref.mtime_ns == final_mtime
def test_upsert_refreshes_loader_path_on_existing_reference(self, session: Session):
"""Re-ingesting an existing reference writes the loader_path computed
by that ingest, healing NULL or stale values even when nothing else
about the row changed."""
asset = _make_asset(session, "hash1")
file_path = "/models/checkpoints/sub/model.safetensors"
upsert_reference(
session, asset_id=asset.id, file_path=file_path, name="model",
mtime_ns=100, loader_path=None,
)
session.commit()
created, updated = upsert_reference(
session, asset_id=asset.id, file_path=file_path, name="model",
mtime_ns=100, loader_path="sub/model.safetensors",
)
session.commit()
assert created is False
assert updated is True
ref = session.query(AssetReference).filter_by(file_path=file_path).one()
assert ref.loader_path == "sub/model.safetensors"
# Identical loader_path is a no-op, not a spurious update.
created, updated = upsert_reference(
session, asset_id=asset.id, file_path=file_path, name="model",
mtime_ns=100, loader_path="sub/model.safetensors",
)
session.commit()
assert created is False
assert updated is False
def test_upsert_restores_missing_reference(self, session: Session):
"""Upserting a reference that was marked missing should restore it."""
asset = _make_asset(session, "hash1")