feat: write leafs incrementally without rebuilding the graph. (#29)
Tests / Test (push) Failing after 4s
Tests / Release (semver) (push) Skipped

Ladybug 0.19 stays FTS/HNSW queryable on MERGE of new ids; DROP INDEX
was the fatal path. bin/brain/add.go and POST /ingest land facts+info
in one transaction so watch/mail/git can become leafs now (Gitea #14).
This commit is contained in:
2026-08-14 10:46:59 +01:00
committed by GitHub
co-authored by GitHub
parent 8b5be9b659
commit 9d1a3f3c70
21 changed files with 487 additions and 55 deletions
+45 -1
View File
@@ -4,7 +4,7 @@ Single embedded graph `var/kb.lbug`. Two roots: facts (assertions backed by
>=2 independent sources) and info (narrative leafs). Hybrid retrieval: BM25
(FTS extension) + HNSW cosine (VECTOR extension) + Cypher graph hops.
All access is read-only unless `--rebuild` is passed to kb/index.
All access is read-only unless `--rebuild` (kb/index) or `kb/add`.
"""
from __future__ import annotations
@@ -118,6 +118,50 @@ def upsert_leaf(conn: ladybug.Connection, *, text: str, root: str, confidence: s
return lid
def add_leafs(conn: ladybug.Connection, leafs: list[dict]) -> list[str]:
"""Write facts+info leafs in one transaction. Safe while FTS/HNSW exist.
Each leaf dict: text, source, optional root/confidence/source_rev/how/loc/type/embedding.
Does not delete the database file. Measured on Ladybug 0.19: MERGE of new
ids (and updates) stays FTS+HNSW queryable; DROP INDEX is the fatal path.
"""
if not leafs:
return []
started = False
try:
conn.execute("BEGIN TRANSACTION")
started = True
except Exception:
started = False
ids: list[str] = []
try:
for lf in leafs:
ids.append(
upsert_leaf(
conn,
text=str(lf["text"]),
root=str(lf.get("root") or ROOT_INFO),
confidence=str(lf.get("confidence") or CONF_CONFIRMED),
source=str(lf["source"]),
source_rev=str(lf.get("source_rev") or "working-tree"),
how=str(lf.get("how") or "brain/add"),
loc=str(lf.get("loc") or lf.get("source") or ""),
type_=str(lf.get("type") or lf.get("type_") or "reference"),
embedding=lf.get("embedding"),
)
)
if started:
conn.execute("COMMIT")
except Exception:
if started:
try:
conn.execute("ROLLBACK")
except Exception:
pass
raise
return ids
def leaf_index_names(conn: ladybug.Connection) -> set[str]:
"""Return index names on the Leaf table (e.g. {'id', 'Leaf_vec', '_PK'})."""
rows = conn.execute("CALL SHOW_INDEXES() RETURN *").get_all()