fix(vector): re-sync a note's vectors by replacing them; roll back a failed insert (#68)

The vectors table is a vec0 virtual table, where INSERT OR REPLACE does not replace, so syncing a note that already had vectors failed with a UNIQUE constraint error and the edit never reached the index. AddDocuments also shadowed err inside its loop, so a failed insert left the write transaction open and later writes failed with 'database is locked'.

Add Client.ReplaceDocuments (delete and insert in one transaction) and use it from SyncObservation and SyncSummary. The shared write function has a named result, so every failed return rolls back. Fixes #66.

Co-authored-by: Claude Sonnet 5.5 <[email protected]>
This commit is contained in:
Holger Reinhardt
2026-10-04 23:15:46 +01:00
committed by GitHub
co-authored by Claude Sonnet 5.5
parent eba3136fff
commit 67de0f0c84
4 changed files with 158 additions and 25 deletions
+64
View File
@@ -2152,3 +2152,67 @@ func TestGetOrComputeEmbedding_ContextCancelDuringSingleflight(t *testing.T) {
// Wait for first call to finish
<-firstDone
}
func TestClient_AddDocuments_FailedBatchIsRolledBackAndDoesNotLockTheDatabase(t *testing.T) {
db, dbCleanup := testDB(t)
defer dbCleanup()
embedSvc, embedCleanup := testEmbeddingService(t)
defer embedCleanup()
client, err := NewClient(Config{DB: db}, embedSvc)
require.NoError(t, err)
doc := func(id string, sqliteID int64) Document {
return Document{ID: id, Content: "text of " + id, Metadata: map[string]any{
"sqlite_id": sqliteID, "doc_type": "observation", "field_type": "narrative", "project": "alpha", "scope": "project",
}}
}
require.NoError(t, client.AddDocuments(context.Background(), []Document{doc("obs_1_narrative", 1)}))
// The second document of the batch exists already, so the batch fails after the first was inserted.
err = client.AddDocuments(context.Background(), []Document{doc("obs_2_narrative", 2), doc("obs_1_narrative", 1)})
require.Error(t, err)
var n int
require.NoError(t, db.QueryRow("SELECT COUNT(*) FROM vectors WHERE doc_id = 'obs_2_narrative'").Scan(&n))
assert.Zero(t, n, "nothing of the failed batch is kept")
// With the transaction left open, this would wait for the lock until the context ends.
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
require.NoError(t, client.AddDocuments(ctx, []Document{doc("obs_3_narrative", 3)}), "a write after a failed one goes through")
}
func TestClient_ReplaceDocuments_ReplacesOnlyTheDocumentsOfThatNote(t *testing.T) {
db, dbCleanup := testDB(t)
defer dbCleanup()
embedSvc, embedCleanup := testEmbeddingService(t)
defer embedCleanup()
client, err := NewClient(Config{DB: db}, embedSvc)
require.NoError(t, err)
ctx := context.Background()
doc := func(id string, sqliteID int64, docType, scope string) Document {
return Document{ID: id, Content: "text of " + id, Metadata: map[string]any{
"sqlite_id": sqliteID, "doc_type": docType, "field_type": "narrative", "project": "alpha", "scope": scope,
}}
}
require.NoError(t, client.AddDocuments(ctx, []Document{
doc("obs_1_narrative", 1, "observation", "global"), doc("obs_1_fact_0", 1, "observation", "global"),
doc("obs_2_narrative", 2, "observation", "global"),
doc("summary_1_request", 1, "session_summary", ""), // the same sqlite id, another kind of document
}))
require.NoError(t, client.ReplaceDocuments(ctx, "observation", 1, []Document{doc("obs_1_narrative", 1, "observation", "project")}))
count := func(where string, args ...any) (n int) {
require.NoError(t, db.QueryRow("SELECT COUNT(*) FROM vectors WHERE "+where, args...).Scan(&n))
return n
}
assert.Equal(t, 1, count("doc_type = 'observation' AND sqlite_id = 1"), "the fact document is gone")
assert.Equal(t, 1, count("doc_id = 'obs_1_narrative' AND scope = 'project'"), "and the narrative carries the new scope")
assert.Equal(t, 1, count("doc_id = 'obs_2_narrative' AND scope = 'global'"), "another note is untouched")
assert.Equal(t, 1, count("doc_id = 'summary_1_request'"), "so is a summary with the same id")
require.NoError(t, client.ReplaceDocuments(ctx, "observation", 1, nil), "no documents left: only the old ones are deleted")
assert.Zero(t, count("doc_type = 'observation' AND sqlite_id = 1"))
}