Files
hyperguild/ingestion/internal/vectorstore/sync_test.go
Mathias 815739758e
All checks were successful
CI / Lint / Test / Vet (push) Successful in 11s
CI / Mirror to GitHub (push) Has been skipped
feat(vectorstore): re-embed on file mtime > store updated_at (#23)
Removes the TODO in Sync that left files static after their first embed.
Edits to brain/wiki/ and brain/knowledge/ now surface in subsequent
syncs without manual /backfill-embeddings calls.

Approach
- Store interface: KnownPaths → KnownPathsWithTime returning path →
  updated_at. Callers compare against file mtime to detect edits.
- PGStore: SELECT path, updated_at FROM brain_embeddings.
- Sync groups known chunks by parent path and tracks the EARLIEST
  updated_at per parent. A file is stale when its mtime is after that
  oldest chunk's timestamp — any chunk older than the file means at
  least one chunk hasn't been refreshed since the last edit.
- Stale-path rewrite: delete every old chunk for the parent (handles
  "file shrunk → fewer chunks → orphan rows at higher #NNNN" cleanly),
  then re-chunk + re-embed + re-upsert.

Tests
- New: TestSync_ReembedsFileWhenMtimeNewer — file mtime forced into the
  future vs store updated_at; Sync deletes old chunk + upserts fresh one.
- New: TestSync_SkipsFileWhenMtimeOlder — file mtime backdated; Sync is
  a no-op (no upserts, no deletes).
- Updated: stubStore.known is now map[string]time.Time. A zero value
  resolves to a far-future sentinel so existing "skip if already known"
  tests keep passing without per-test setup.
- pg_test renamed KnownPaths integration → KnownPathsWithTime; asserts
  updated_at is non-zero and within 5s of insert wall-clock.

Backward compat
- brain_embeddings rows pre-dating this change carry valid updated_at
  values (column was always populated via `DEFAULT now()` + ON CONFLICT
  `updated_at = now()`). No migration needed. Live pod will start
  re-embedding any file whose source has been edited since its chunks
  were originally written.

Closes gitea/mathias/hyperguild#23.
2026-05-20 09:50:45 +02:00

275 lines
8.9 KiB
Go

package vectorstore_test
import (
"context"
"errors"
"os"
"path/filepath"
"strings"
"testing"
"time"
"github.com/mathiasbq/hyperguild/ingestion/internal/vectorstore"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
type stubStore struct {
// known maps chunk-path → updated_at. Tests that don't care about
// re-embed-on-mtime use a far-future time so the Sync skip path
// always wins. Tests that do exercise the mtime path set the
// updated_at explicitly.
known map[string]time.Time
upserts map[string][]float32
deletes []string
failNext error
}
// farFuture is "newer than any file mtime", used as the default
// updated_at in stubs that don't care about re-embed behavior.
var farFuture = time.Now().Add(24 * time.Hour)
func (s *stubStore) KnownPathsWithTime(_ context.Context) (map[string]time.Time, error) {
out := make(map[string]time.Time, len(s.known))
for k, t := range s.known {
if t.IsZero() {
t = farFuture
}
out[k] = t
}
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]time.Time{}}
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#0001")
assert.Contains(t, store.upserts, "wiki/jepa-fx/facts/y.md#0001")
}
func TestSync_SkipsAlreadyKnown(t *testing.T) {
dir := t.TempDir()
writeNote(t, dir, "wiki/a/facts/x.md", "x")
store := &stubStore{known: map[string]time.Time{"wiki/a/facts/x.md#0001": {}}}
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]time.Time{"wiki/old/facts/ghost.md#0001": {}}}
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]time.Time{}}
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#0001")
}
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]time.Time{}}
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#0001")
assert.Contains(t, store.upserts, "knowledge/2026-05-19-koala-gpu-setup.md#0001")
}
func TestSync_ChunksLongFiles(t *testing.T) {
dir := t.TempDir()
// Build a file that's well over the chunk byte budget. Multi-section
// markdown so the chunker has heading boundaries to cut on.
body := "# Doc\n\nintro line.\n\n"
for i := 0; i < 10; i++ {
body += "## Section " + string(rune('A'+i)) + "\n\n"
body += strings.Repeat("This section has a fair amount of content. ", 50) + "\n\n"
}
writeNote(t, dir, "knowledge/long.md", body)
store := &stubStore{known: map[string]time.Time{}}
emb := stubEmbedder{vec: make([]float32, 768)}
res, err := vectorstore.Sync(context.Background(), dir, store, emb)
require.NoError(t, err)
assert.Greater(t, res.Added, 1, "long file should produce multiple chunk rows")
// Every upserted path for this file must be a chunk path.
chunkCount := 0
for p := range store.upserts {
if strings.HasPrefix(p, "knowledge/long.md#") {
chunkCount++
}
}
assert.Equal(t, res.Added, chunkCount, "all rows for long file should be chunk-suffixed")
// The bare parent path must NOT be upserted directly.
assert.NotContains(t, store.upserts, "knowledge/long.md")
}
func TestSync_ShortFileGetsSingleChunkRow(t *testing.T) {
dir := t.TempDir()
writeNote(t, dir, "wiki/short.md", "tiny body\n")
store := &stubStore{known: map[string]time.Time{}}
emb := stubEmbedder{vec: make([]float32, 768)}
res, err := vectorstore.Sync(context.Background(), dir, store, emb)
require.NoError(t, err)
assert.Equal(t, 1, res.Added)
assert.Contains(t, store.upserts, "wiki/short.md#0001")
}
func TestSync_SkipsFileIfAnyChunkAlreadyKnown(t *testing.T) {
dir := t.TempDir()
writeNote(t, dir, "wiki/foo.md", "body\n")
store := &stubStore{known: map[string]time.Time{
"wiki/foo.md#0001": {},
}}
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_DeletesAllChunksOfDisappearedFile(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki"), 0o755))
store := &stubStore{known: map[string]time.Time{
"wiki/ghost.md#0001": {},
"wiki/ghost.md#0002": {},
"wiki/ghost.md#0003": {},
}}
res, err := vectorstore.Sync(context.Background(), dir, store, stubEmbedder{vec: make([]float32, 768)})
require.NoError(t, err)
assert.Equal(t, 3, res.Deleted)
}
func TestSync_ReembedsFileWhenMtimeNewer(t *testing.T) {
dir := t.TempDir()
writeNote(t, dir, "wiki/edited.md", "original body\n")
// Force the file's mtime ahead of any plausible store updated_at.
future := time.Now().Add(1 * time.Hour)
require.NoError(t, os.Chtimes(filepath.Join(dir, "wiki/edited.md"), future, future))
store := &stubStore{
known: map[string]time.Time{
// Existing chunk row pre-dates the file's mtime.
"wiki/edited.md#0001": time.Now().Add(-1 * time.Hour),
},
}
emb := stubEmbedder{vec: make([]float32, 768)}
res, err := vectorstore.Sync(context.Background(), dir, store, emb)
require.NoError(t, err)
assert.Equal(t, 1, res.Added, "file with newer mtime should be re-embedded")
assert.Contains(t, store.upserts, "wiki/edited.md#0001")
// Old chunks of the same parent must be deleted before re-embed so
// shrunk files don't leave orphan rows at higher #NNNN indexes.
assert.Contains(t, store.deletes, "wiki/edited.md#0001")
}
func TestSync_SkipsFileWhenMtimeOlder(t *testing.T) {
dir := t.TempDir()
writeNote(t, dir, "wiki/stable.md", "body\n")
// Backdate mtime to before the store's recorded updated_at.
past := time.Now().Add(-2 * time.Hour)
require.NoError(t, os.Chtimes(filepath.Join(dir, "wiki/stable.md"), past, past))
store := &stubStore{
known: map[string]time.Time{
"wiki/stable.md#0001": time.Now(),
},
}
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)
assert.Empty(t, store.deletes)
}
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]time.Time{}}
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)
}