fix(kb): stop DROP INDEX killing HNSW via Ladybug ghost catalog

Ladybug 0.19 DROP INDEX leaves `_0_Leaf_vec_UPPER` / `0_id_docs` in catalog so
CREATE fails while SHOW_INDEXES omits the index; create_fts_and_vector used to
swallow that. Never drop FTS/VECTOR; ensure_indexes after upserts; rebuild =
delete kb.lbug. Add compose.edelweiss.yml + regression tests.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
2026-08-12 16:05:14 +01:00
co-authored by Cursor
parent 1d1f6a90ff
commit b73b4d4f97
11 changed files with 356 additions and 45 deletions
+4 -15
View File
@@ -22,7 +22,7 @@ ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(ROOT / "bin" / "tools"))
from kblib import ( # noqa: E402
connect, create_fts_and_vector, init_schema, upsert_leaf,
connect, ensure_indexes, init_schema, upsert_leaf,
open_readonly, stats,
)
from mdleaves import read_markdown, to_all, walk_markdown # noqa: E402
@@ -116,13 +116,11 @@ def main(argv: list[str]) -> int:
db, conn = connect(DB_PATH, read_only=False)
init_schema(conn)
# Keep the FTS/VECTOR indexes in place across incremental runs: ladybug's
# DROP INDEX leaves the backing tables registered on migrated DBs, so a
# drop+recreate silently kills the vector index. Only create when missing.
# Never DROP FTS/VECTOR (ghost catalog). Write leafs, then ensure indexes.
# --rebuild already deleted kb.lbug above, so CREATE runs on a clean DB.
embed = embedder()
done, total = index_leafs(conn, leafs, embed, a.limit)
if a.rebuild or not _has_indexes(conn):
create_fts_and_vector(conn, force=True)
ensure_indexes(conn)
s = stats(conn)
conn.close()
db.close()
@@ -132,14 +130,5 @@ def main(argv: list[str]) -> int:
return 0
def _has_indexes(conn) -> bool:
try:
rows = conn.execute("CALL SHOW_INDEXES() RETURN *").get_all()
names = {row[1] for row in rows if row[0] == "Leaf"}
return "id" in names and "Leaf_vec" in names
except Exception:
return False
if __name__ == "__main__":
sys.exit(main(sys.argv[1:]))