Compare commits

...

3 Commits

Author SHA1 Message Date
kami 4282f6b9a9 Warn about vectors written before the marker existed 2026-07-31 13:44:29 +04:00
kami 7bb9f9be06 Merge the embedder marker 2026-07-31 13:42:40 +04:00
kami 1e47eaca5a Record which embedder wrote the stored vectors and warn on a swap (#378)
The embedder moved from paraphrase-multilingual-MiniLM-L12-v2 to
multilingual-e5-small. Both are 384-dimensional, so nothing in the code
noticed: cosine between an old stored vector and a new query vector is
noise, and recall degrades silently.

So the DB now records the embedder that wrote its vectors. One value for
the whole DB (migration #11, a small `meta` key/value table) rather than a
column on every vector row: the backfill re-embeds every note and fact in
one pass, so a per-row marker would hold the same string in every row and
cost a column on two tables for nothing.

The identity comes from the embedder itself via a new optional ID() method
("multilingual-e5-small@384", model file name plus dimension), so pointing
the config at another model changes the string without anyone editing a
constant. mavend logs a loud WARNING at startup naming both the stored and
the configured embedder when they differ.

Detection only — recall behaviour is unchanged. TODO(#378) in
store.CheckEmbedder marks where the backfill will hook in.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 13:42:07 +04:00
7 changed files with 295 additions and 0 deletions
+25
View File
@@ -171,6 +171,7 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
emb = router.NewHashEmbedder(1024)
}
w.embedder = emb
checkStoredEmbedder(dataStore, emb)
// ----- tool executor (the enabled act allowlist, store-backed) -----
// Config tools are the declarative bootstrap: seed them into the store as
@@ -1767,3 +1768,27 @@ func jsonStringImpl(s string) string {
b = append(b, '"')
return string(b)
}
// checkStoredEmbedder compares the embedder we just loaded with the one that
// wrote the vectors already in the DB (Vikunja #378).
//
// The two models we have both make 384-dim vectors, so a size check catches
// nothing: after a swap, recall silently compares vectors from different
// spaces and the scores are noise. So we say it out loud. Nothing is changed
// here — recall keeps running exactly as before until the backfill lands.
func checkStoredEmbedder(dataStore *store.Store, emb router.Embedder) {
if dataStore == nil {
return
}
current := router.EmbedderID(emb)
stored, mismatch, err := dataStore.CheckEmbedder(context.Background(), current)
if err != nil {
log.Printf("voice: embedder marker check failed: %v", err)
return
}
if mismatch {
log.Printf("voice: WARNING embedder MISMATCH — stored vectors were written by %q but the configured embedder is %q; recall scores are noise until the notes and facts are re-embedded (Vikunja #378)", stored, current)
return
}
log.Printf("voice: embedder marker ok (%s)", current)
}
+23
View File
@@ -2,6 +2,7 @@ package router
import (
"context"
"fmt"
"math"
"unicode"
)
@@ -19,6 +20,24 @@ type Embedder interface {
Close() error
}
// IdentifiedEmbedder — an embedder that can name itself. The name goes into
// the DB next to the vectors it wrote, so a later model swap is caught instead
// of silently returning nonsense scores (Vikunja #378).
type IdentifiedEmbedder interface {
Embedder
ID() string
}
// EmbedderID is the stable string stored alongside the vectors. It comes from
// the embedder itself — nobody hand-types a model name twice — and changes
// whenever the model or its dimension changes.
func EmbedderID(e Embedder) string {
if i, ok := e.(IdentifiedEmbedder); ok {
return i.ID()
}
return fmt.Sprintf("unknown@%d", e.Dim())
}
// AsymmetricEmbedder — an embedder that wants to know whether a text is a
// search query or a stored passage. Recall is asymmetric: a short question
// goes in, a longer note comes out. The e5 family is trained for exactly that
@@ -70,6 +89,10 @@ func NewHashEmbedder(dim int) *HashEmbedder {
func (h *HashEmbedder) Dim() int { return h.dim }
// ID names this embedder for the DB marker. The dimension is part of it
// because a HashEmbedder of another width is a different vector space.
func (h *HashEmbedder) ID() string { return fmt.Sprintf("hash@%d", h.dim) }
func (h *HashEmbedder) Close() error { return nil }
func (h *HashEmbedder) Embed(_ context.Context, text string) ([]float32, error) {
+24
View File
@@ -0,0 +1,24 @@
package router
import "testing"
func TestEmbedderIDFromModelPath(t *testing.T) {
got := modelIDFromPath("/opt/maven/models/embedder/multilingual-e5-small.onnx")
if got != "multilingual-e5-small@384" {
t.Fatalf("modelIDFromPath = %q", got)
}
// A different model file must produce a different id, even at 384 dim.
old := modelIDFromPath("/opt/maven/models/embedder/paraphrase-multilingual-MiniLM-L12-v2.onnx")
if old == got {
t.Fatal("two different models share one id")
}
}
func TestEmbedderIDIncludesDim(t *testing.T) {
if id := EmbedderID(NewHashEmbedder(1024)); id != "hash@1024" {
t.Fatalf("EmbedderID = %q", id)
}
if EmbedderID(NewHashEmbedder(1024)) == EmbedderID(NewHashEmbedder(384)) {
t.Fatal("dimension not part of the id")
}
}
+21
View File
@@ -33,6 +33,7 @@ const (
type onnxEmbedder struct {
tokenizer *unigramTokenizer
session *ort.DynamicSession[int64, float32]
id string
}
func NewONNXEmbedder(modelPath, tokenizerPath, libPath string) (*onnxEmbedder, error) {
@@ -58,11 +59,31 @@ func NewONNXEmbedder(modelPath, tokenizerPath, libPath string) (*onnxEmbedder, e
return &onnxEmbedder{
tokenizer: tok,
session: session,
id: modelIDFromPath(modelPath),
}, nil
}
func (e *onnxEmbedder) Dim() int { return embedDim }
// ID names the loaded model for the DB marker (Vikunja #378): the model file's
// own name plus the dimension, so pointing the config at another model changes
// the string on its own.
func (e *onnxEmbedder) ID() string { return e.id }
// modelIDFromPath turns /opt/.../multilingual-e5-small.onnx into
// "multilingual-e5-small@384".
func modelIDFromPath(modelPath string) string {
name := modelPath
if i := strings.LastIndexAny(name, "/\\"); i >= 0 {
name = name[i+1:]
}
name = strings.TrimSuffix(name, ".onnx")
if name == "" {
name = "onnx"
}
return fmt.Sprintf("%s@%d", name, embedDim)
}
// Embed treats the text as a query. The classifier compares one short
// utterance to another short seed phrase, so both sides get the same prefix
// and the comparison stays fair. The recall path must call EmbedQuery and
+97
View File
@@ -0,0 +1,97 @@
package store
import (
"context"
"database/sql"
"errors"
"fmt"
)
// metaKeyEmbedderID names the embedder that wrote the stored vectors.
//
// Why one value for the whole DB and not a column on every vector row: the
// vectors are only ever rewritten all at once (one backfill re-embeds every
// note and fact together), so a per-row marker would hold the same string in
// every row and cost a column on two tables for nothing.
const metaKeyEmbedderID = "embedder_id"
// Meta reads a single value from the meta table. Missing key ⇒ empty string.
func (s *Store) Meta(ctx context.Context, key string) (string, error) {
var v string
err := s.db.QueryRowContext(ctx, `SELECT value FROM meta WHERE key = ?`, key).Scan(&v)
if errors.Is(err, sql.ErrNoRows) {
return "", nil
}
if err != nil {
return "", fmt.Errorf("read meta %s: %w", key, err)
}
return v, nil
}
// SetMeta writes (or overwrites) a single meta value.
func (s *Store) SetMeta(ctx context.Context, key, value string) error {
_, err := s.db.ExecContext(ctx,
`INSERT INTO meta (key, value) VALUES (?,?)
ON CONFLICT(key) DO UPDATE SET value = excluded.value`, key, value)
if err != nil {
return fmt.Errorf("write meta %s: %w", key, err)
}
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. 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.
func (s *Store) CheckEmbedder(ctx context.Context, currentID string) (stored string, mismatch bool, err error) {
stored, err = s.Meta(ctx, metaKeyEmbedderID)
if err != nil {
return "", false, err
}
if stored != "" {
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
}
+100
View File
@@ -0,0 +1,100 @@
package store
import (
"context"
"testing"
"time"
)
// A fresh DB has no marker yet, so the current embedder is recorded and
// nothing is flagged.
func TestCheckEmbedderFreshDBRecords(t *testing.T) {
s := newTestStore(t)
ctx := context.Background()
stored, mismatch, err := s.CheckEmbedder(ctx, "multilingual-e5-small@384")
if err != nil {
t.Fatalf("CheckEmbedder: %v", err)
}
if mismatch {
t.Fatal("fresh DB reported a mismatch")
}
if stored != "multilingual-e5-small@384" {
t.Fatalf("stored = %q", stored)
}
got, err := s.Meta(ctx, metaKeyEmbedderID)
if err != nil {
t.Fatalf("Meta: %v", err)
}
if got != "multilingual-e5-small@384" {
t.Fatalf("marker not persisted, got %q", got)
}
}
// 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)
ctx := context.Background()
if err := s.SetMeta(ctx, metaKeyEmbedderID, "paraphrase-multilingual-MiniLM-L12-v2@384"); err != nil {
t.Fatalf("SetMeta: %v", err)
}
stored, mismatch, err := s.CheckEmbedder(ctx, "multilingual-e5-small@384")
if err != nil {
t.Fatalf("CheckEmbedder: %v", err)
}
if !mismatch {
t.Fatal("different embedder not detected")
}
if stored != "paraphrase-multilingual-MiniLM-L12-v2@384" {
t.Fatalf("stored = %q", stored)
}
}
// The same embedder must never raise a false alarm, including on re-check.
func TestCheckEmbedderSameModelNoAlarm(t *testing.T) {
s := newTestStore(t)
ctx := context.Background()
for i := 0; i < 2; i++ {
_, mismatch, err := s.CheckEmbedder(ctx, "multilingual-e5-small@384")
if err != nil {
t.Fatalf("CheckEmbedder: %v", err)
}
if mismatch {
t.Fatalf("false alarm on pass %d", i)
}
}
}
+5
View File
@@ -83,6 +83,11 @@ ALTER TABLE reminders ADD COLUMN next_fire_ts INTEGER;`, // #2
expires_ts INTEGER NOT NULL
);
CREATE INDEX IF NOT EXISTS idx_dialogue_sessions_expires ON dialogue_sessions (expires_ts);`, // #10 — the follow-up session survives a restart (Vikunja #363); small, TTL-pruned table, not a history log
`CREATE TABLE IF NOT EXISTS meta (
key TEXT PRIMARY KEY,
value TEXT NOT NULL
);`, // #11 — small key/value table for facts about the DB itself; first key is embedder_id (Vikunja #378)
}
// migrate applies every migration with a number greater than the DB's current