Warn about vectors written before the marker existed
This commit is contained in:
@@ -3,6 +3,7 @@ package store
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// A fresh DB has no marker yet, so the current embedder is recorded and
|
||||
@@ -30,6 +31,38 @@ func TestCheckEmbedderFreshDBRecords(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// The deployed box: notes were written by the old embedder, before the marker
|
||||
// existed. Claiming them for the current one would hide exactly the problem
|
||||
// the marker is for, so an unmarked DB that already holds vectors is a
|
||||
// mismatch.
|
||||
func TestCheckEmbedderUnmarkedDBWithVectorsIsMismatch(t *testing.T) {
|
||||
s := newTestStore(t)
|
||||
ctx := context.Background()
|
||||
|
||||
if _, err := s.WriteNote(ctx, time.Now(), "молоко в холодильнике", []float32{0.1, 0.2}, "voice"); err != nil {
|
||||
t.Fatalf("WriteNote: %v", err)
|
||||
}
|
||||
|
||||
stored, mismatch, err := s.CheckEmbedder(ctx, "multilingual-e5-small@384")
|
||||
if err != nil {
|
||||
t.Fatalf("CheckEmbedder: %v", err)
|
||||
}
|
||||
if !mismatch {
|
||||
t.Fatal("an unmarked DB with stored vectors should report a mismatch")
|
||||
}
|
||||
if stored != EmbedderUnknown {
|
||||
t.Fatalf("stored = %q, want %q", stored, EmbedderUnknown)
|
||||
}
|
||||
// It must NOT claim the DB — that would silence the warning on restart.
|
||||
got, err := s.Meta(ctx, metaKeyEmbedderID)
|
||||
if err != nil {
|
||||
t.Fatalf("Meta: %v", err)
|
||||
}
|
||||
if got != "" {
|
||||
t.Fatalf("marker written despite unknown provenance: %q", got)
|
||||
}
|
||||
}
|
||||
|
||||
// Both models are 384-dim, so this is the only thing that catches the swap.
|
||||
func TestCheckEmbedderDifferentModelMismatch(t *testing.T) {
|
||||
s := newTestStore(t)
|
||||
|
||||
Reference in New Issue
Block a user