fix(retrieval): fail open on registry resolution errors

This commit is contained in:
2026-04-24 11:32:46 -04:00
parent ce6ffdbb63
commit 05c11fd4fb
7 changed files with 121 additions and 6 deletions

View File

@@ -163,6 +163,45 @@ def test_ingest_file_derives_project_id_from_registry_root(tmp_data_dir, tmp_pat
assert all(meta["project_id"] == "p04-gigabit" for meta in fake_store.metadatas)
def test_ingest_file_logs_and_fails_open_when_project_derivation_fails(
tmp_data_dir,
sample_markdown,
monkeypatch,
):
"""A broken registry should be visible but should not block ingestion."""
init_db()
warnings = []
class FakeVectorStore:
def __init__(self):
self.metadatas = []
def add(self, ids, documents, metadatas):
self.metadatas.extend(metadatas)
def delete(self, ids):
return None
fake_store = FakeVectorStore()
monkeypatch.setattr("atocore.ingestion.pipeline.get_vector_store", lambda: fake_store)
monkeypatch.setattr(
"atocore.projects.registry.derive_project_id_for_path",
lambda path: (_ for _ in ()).throw(ValueError("registry broken")),
)
monkeypatch.setattr(
"atocore.ingestion.pipeline.log.warning",
lambda event, **kwargs: warnings.append((event, kwargs)),
)
result = ingest_file(sample_markdown)
assert result["status"] == "ingested"
assert fake_store.metadatas
assert all(meta["project_id"] == "" for meta in fake_store.metadatas)
assert warnings[0][0] == "project_id_derivation_failed"
assert "registry broken" in warnings[0][1]["error"]
def test_ingest_project_folder_passes_project_id_to_files(tmp_data_dir, sample_folder, monkeypatch):
seen = []