Files
hyperguild/ingestion/internal/vectorstore/sync_test.go
Mathias 078ec029da
All checks were successful
CI / Lint / Test / Vet (push) Successful in 11s
CI / Mirror to GitHub (push) Has been skipped
fix(ingestion): embed sync also scans brain/knowledge/ + logs per-item errors
The embed sync goroutine only walked brain/wiki/. brain/knowledge/ (112
curated entries, per CLAUDE.md the most-important brain content) had zero
coverage in brain_embeddings — vector retrieval was blind to it. Hybrid
BM25 + pgvector retrieval would never surface a curated knowledge entry
via the vector arm.

Extract the per-root walk into a loop over a small subdir list and add
"knowledge" alongside "wiki". scanDirs is package-level so it stays a
single source of truth for what gets embedded.

Also log each failing item's path + error string from StartSync.
Previously only the aggregate count was logged, so a persistent
`errors=1` per cycle was opaque. With per-item warnings, the actual
ollama "input length exceeds the context length" surface immediately.

Refs gitea/mathias/infra#37 (this commit covers the knowledge/ scan
bug; the long-file chunking bug is a separate change.)
2026-05-19 21:27:15 +02:00

152 lines
4.5 KiB
Go

package vectorstore_test
import (
"context"
"errors"
"os"
"path/filepath"
"testing"
"github.com/mathiasbq/hyperguild/ingestion/internal/vectorstore"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
type stubStore struct {
known map[string]struct{}
upserts map[string][]float32
deletes []string
failNext error
}
func (s *stubStore) KnownPaths(_ context.Context) (map[string]struct{}, error) {
out := make(map[string]struct{}, len(s.known))
for k := range s.known {
out[k] = struct{}{}
}
return out, nil
}
func (s *stubStore) Upsert(_ context.Context, path string, v []float32) error {
if s.failNext != nil {
err := s.failNext
s.failNext = nil
return err
}
if s.upserts == nil {
s.upserts = make(map[string][]float32)
}
s.upserts[path] = v
return nil
}
func (s *stubStore) Delete(_ context.Context, path string) error {
s.deletes = append(s.deletes, path)
return nil
}
type stubEmbedder struct {
vec []float32
err error
}
func (e stubEmbedder) Embed(_ context.Context, _ string) ([]float32, error) {
return e.vec, e.err
}
func writeNote(t *testing.T, dir, rel, body string) {
t.Helper()
full := filepath.Join(dir, rel)
require.NoError(t, os.MkdirAll(filepath.Dir(full), 0o755))
require.NoError(t, os.WriteFile(full, []byte(body), 0o644))
}
func TestSync_AddsNewFiles(t *testing.T) {
dir := t.TempDir()
writeNote(t, dir, "wiki/jepa-fx/facts/x.md", "body of x")
writeNote(t, dir, "wiki/jepa-fx/facts/y.md", "body of y")
store := &stubStore{known: map[string]struct{}{}}
emb := stubEmbedder{vec: make([]float32, 768)}
res, err := vectorstore.Sync(context.Background(), dir, store, emb)
require.NoError(t, err)
assert.Equal(t, 2, res.Added)
assert.Empty(t, res.Deleted)
assert.Contains(t, store.upserts, "wiki/jepa-fx/facts/x.md")
assert.Contains(t, store.upserts, "wiki/jepa-fx/facts/y.md")
}
func TestSync_SkipsAlreadyKnown(t *testing.T) {
dir := t.TempDir()
writeNote(t, dir, "wiki/a/facts/x.md", "x")
store := &stubStore{known: map[string]struct{}{"wiki/a/facts/x.md": {}}}
emb := stubEmbedder{vec: make([]float32, 768)}
res, err := vectorstore.Sync(context.Background(), dir, store, emb)
require.NoError(t, err)
assert.Equal(t, 0, res.Added)
assert.Empty(t, store.upserts)
}
func TestSync_DeletesDisappearedFiles(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki"), 0o755))
// store has a path that doesn't exist on disk anymore
store := &stubStore{known: map[string]struct{}{"wiki/old/facts/ghost.md": {}}}
res, err := vectorstore.Sync(context.Background(), dir, &stubStoreWithDelete{stubStore: store}, stubEmbedder{vec: make([]float32, 768)})
require.NoError(t, err)
assert.Equal(t, 1, res.Deleted)
}
// stubStoreWithDelete is a thin wrapper to capture Delete calls;
// stubStore already implements Delete but we need the wrapper to mix
// store interfaces with sync-specific expectations.
type stubStoreWithDelete struct {
*stubStore
}
func TestSync_SkipsIndexFiles(t *testing.T) {
dir := t.TempDir()
writeNote(t, dir, "wiki/a/_index.md", "moc")
writeNote(t, dir, "wiki/a/facts/real.md", "body")
store := &stubStore{known: map[string]struct{}{}}
res, err := vectorstore.Sync(context.Background(), dir, store, stubEmbedder{vec: make([]float32, 768)})
require.NoError(t, err)
assert.Equal(t, 1, res.Added)
assert.NotContains(t, store.upserts, "wiki/a/_index.md")
}
func TestSync_ScansKnowledgeDir(t *testing.T) {
dir := t.TempDir()
writeNote(t, dir, "wiki/a/facts/x.md", "x")
writeNote(t, dir, "knowledge/2026-05-19-koala-gpu-setup.md", "knowledge body")
store := &stubStore{known: map[string]struct{}{}}
emb := stubEmbedder{vec: make([]float32, 768)}
res, err := vectorstore.Sync(context.Background(), dir, store, emb)
require.NoError(t, err)
assert.Equal(t, 2, res.Added)
assert.Contains(t, store.upserts, "wiki/a/facts/x.md")
assert.Contains(t, store.upserts, "knowledge/2026-05-19-koala-gpu-setup.md")
}
func TestSync_NoOpWhenComponentsNil(t *testing.T) {
dir := t.TempDir()
writeNote(t, dir, "wiki/a/facts/x.md", "x")
res, err := vectorstore.Sync(context.Background(), dir, nil, nil)
require.NoError(t, err)
assert.Equal(t, 0, res.Added)
}
func TestSync_CollectsEmbedderErrors(t *testing.T) {
dir := t.TempDir()
writeNote(t, dir, "wiki/a/facts/x.md", "x")
store := &stubStore{known: map[string]struct{}{}}
emb := stubEmbedder{err: errors.New("upstream down")}
res, err := vectorstore.Sync(context.Background(), dir, store, emb)
require.NoError(t, err)
assert.Equal(t, 0, res.Added)
assert.Len(t, res.Errors, 1)
}