From 4282f6b9a98fcc0e2fb75a91666f87b1abfa4e40 Mon Sep 17 00:00:00 2001
From: kami <kami@kvmx.ru>
Date: Fri, 31 Jul 2026 13:44:29 +0400
Subject: [PATCH] Warn about vectors written before the marker existed

---
 internal/store/meta.go      | 48 ++++++++++++++++++++++++++++++-------
 internal/store/meta_test.go | 33 +++++++++++++++++++++++++
 2 files changed, 73 insertions(+), 8 deletions(-)

diff --git a/internal/store/meta.go b/internal/store/meta.go
index fc88905..8edd0e3 100644
--- a/internal/store/meta.go
+++ b/internal/store/meta.go
@@ -39,17 +39,27 @@ func (s *Store) SetMeta(ctx context.Context, key, value string) error {
 	return nil
 }
 
+// EmbedderUnknown is the stored id reported for a DB that already holds
+// vectors but never recorded who wrote them.
+const EmbedderUnknown = "unknown (written before this marker existed)"
+
 // CheckEmbedder compares the embedder now configured against the one that
-// wrote the stored vectors.
-//
-// A DB that has never recorded one is claimed for the current embedder: either
-// it is fresh (nothing stored yet, nothing to fix) or it predates this marker.
-// Returns the stored id and whether it differs from the current one.
+// wrote the stored vectors. Returns the stored id and whether it differs.
 //
 // Vectors from two different models live in different spaces, so cosine
 // between them is noise rather than a low score — and both of our models are
 // 384-dimensional, so nothing else catches it.
 //
+// Three cases, and the middle one is the one that actually matters:
+//
+//   - marker present ⇒ compare the two ids.
+//   - marker absent but vectors already stored ⇒ this is a DB from before the
+//     marker, so we cannot know who wrote them. Report a mismatch. This is the
+//     real case on the deployed box: those vectors came from the old embedder,
+//     and claiming them for the current one would hide the exact problem the
+//     marker was added to catch.
+//   - marker absent and no vectors ⇒ fresh DB, claim it, nothing to fix.
+//
 // TODO(#378): on a mismatch, run the one-shot backfill here — re-embed every
 // stored note and fact text with the current embedder (EmbedPassage side),
 // write the vectors back, then SetMeta the current id.
@@ -58,8 +68,30 @@ func (s *Store) CheckEmbedder(ctx context.Context, currentID string) (stored str
 	if err != nil {
 		return "", false, err
 	}
-	if stored == "" {
-		return currentID, false, s.SetMeta(ctx, metaKeyEmbedderID, currentID)
+	if stored != "" {
+		return stored, stored != currentID, nil
 	}
-	return stored, stored != currentID, nil
+	n, err := s.countVectors(ctx)
+	if err != nil {
+		return "", false, err
+	}
+	if n > 0 {
+		return EmbedderUnknown, true, nil
+	}
+	return currentID, false, s.SetMeta(ctx, metaKeyEmbedderID, currentID)
+}
+
+// countVectors — how many stored rows carry an embedding. Used only to tell a
+// fresh DB apart from one that predates the marker.
+func (s *Store) countVectors(ctx context.Context) (int, error) {
+	var notes, vecs int
+	if err := s.db.QueryRowContext(ctx,
+		`SELECT count(*) FROM notes WHERE embedding IS NOT NULL`).Scan(&notes); err != nil {
+		return 0, fmt.Errorf("count note vectors: %w", err)
+	}
+	if err := s.db.QueryRowContext(ctx,
+		`SELECT count(*) FROM memory_vectors`).Scan(&vecs); err != nil {
+		return 0, fmt.Errorf("count memory vectors: %w", err)
+	}
+	return notes + vecs, nil
 }
diff --git a/internal/store/meta_test.go b/internal/store/meta_test.go
index 173db56..e63f07d 100644
--- a/internal/store/meta_test.go
+++ b/internal/store/meta_test.go
@@ -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)