Merge branch 'fix/g09' into fix/integrated

internal/store/memory.go

@@ -64,11 +64,17 @@ func (m *MemoryStore) Insert(ctx context.Context, id string, vec []float32, meta
 
 // Search returns the topK nearest rows by cosine similarity. A full scan; see
 // the type doc for why that's fine at this scale.
+//
+// Rows under memory.NonRecallPrefix are excluded in SQL. They are speaker
+// voiceprints sharing this table, and note recall must not rank them; see that
+// constant for why the previous arrangement only appeared to do this.
 func (m *MemoryStore) Search(ctx context.Context, vec []float32, topK int) ([]memory.Result, error) {
 	if topK <= 0 {
 		topK = 10
 	}
-	rows, err := m.db.QueryContext(ctx, `SELECT id, vec, meta FROM memory_vectors`)
+	rows, err := m.db.QueryContext(ctx,
+		`SELECT id, vec, meta FROM memory_vectors WHERE id NOT LIKE ? ESCAPE '\'`,
+		escapeLike(memory.NonRecallPrefix)+"%")
 	if err != nil {
 		return nil, fmt.Errorf("memory: scan: %w", err)
 	}

internal/store/memory_test.go

@@ -3,7 +3,10 @@ package store
 import (
 	"context"
 	"path/filepath"
+	"strings"
 	"testing"
+
+	"github.com/kami/maven/internal/memory"
 )
 
 func newMemTestStore(t *testing.T) *Store {
@@ -101,3 +104,38 @@ func TestMemoryStorePersistsAcrossReopen(t *testing.T) {
 		t.Fatalf("memory did not survive reopen: %v", got)
 	}
 }
+
+// A voiceprint sharing the vector table must never rank as a note hit. The
+// dimensions match here on purpose: what used to hide these rows was cosine
+// returning 0 on a width mismatch, which is a property of two model choices and
+// not of the store.
+func TestMemoryStoreSearchSkipsVoiceprints(t *testing.T) {
+	ctx := context.Background()
+	m := newMemTestStore(t).VectorMemory()
+
+	if err := m.Insert(ctx, "note:1", []float32{0, 1, 0}, map[string]string{"text": "заметка"}); err != nil {
+		t.Fatal(err)
+	}
+	if err := m.Insert(ctx, memory.NonRecallPrefix+"kami", []float32{1, 0, 0}, map[string]string{"name": "Ками"}); err != nil {
+		t.Fatal(err)
+	}
+
+	got, err := m.Search(ctx, []float32{1, 0, 0}, 10)
+	if err != nil {
+		t.Fatalf("Search: %v", err)
+	}
+	for _, r := range got {
+		if strings.HasPrefix(r.ID, memory.NonRecallPrefix) {
+			t.Fatalf("recall returned a voiceprint: %+v", r)
+		}
+	}
+	if len(got) != 1 || got[0].ID != "note:1" {
+		t.Fatalf("Search = %+v, want just the note", got)
+	}
+
+	// The row is still there for the speaker code that owns it.
+	recs, err := m.ByPrefix(ctx, memory.NonRecallPrefix)
+	if err != nil || len(recs) != 1 {
+		t.Fatalf("ByPrefix = %+v, %v; want the voiceprint", recs, err)
+	}
+}