store, mavend: a fact is indexed as the fact, not as the utterance (V-493)

queryMemory returns a fact's stored text verbatim, so the text the write path
indexed is what he hears. It was the utterance, which made recall of any
voice-tapped fact answer with the sentence he said: go_version = 1.20 was
indexed as "какая последняя версия языка Go?", and that question came back.

FactRecallText renders the fact instead, and the utterance stays in meta as
provenance. Correcting a value now drops the key's vectors the way voiding one
does, since the superseded value was still answering.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
2026-08-03 22:36:34 +04:00
parent b9371dcac6
commit dbdab2d570
3 changed files with 80 additions and 8 deletions
+17 -8
View File
@@ -7,6 +7,7 @@ import (
"github.com/kami/maven/internal/ipc"
"github.com/kami/maven/internal/router"
"github.com/kami/maven/internal/store"
)
// actionFact handles router.IntentFact: persist a tapped self-fact, index
@@ -63,17 +64,25 @@ func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) s
log.Printf("voice: write fact: %v", err)
return "не получилось сохранить факт."
}
// Index the fact utterance in long-term memory (best-effort, must not
// fail the fact write). Facts aren't in the notes table, so this is the
// only recall path for them — "когда я пил воду?" reads back from here.
// Index the fact in long-term memory (best-effort, must not fail the fact
// write). Facts aren't in the notes table, so this is the only recall path
// for them — "когда я пил воду?" reads back from here.
//
// The indexed text is the fact, not the utterance (#493). queryMemory
// returns a fact's stored text verbatim, so what goes in here is what he
// hears; storing the utterance meant recall answered with his own sentence
// rather than the value. The utterance stays alongside as provenance —
// readable on /trace, never the answer and never embedded.
if h.memStore != nil {
if vec, err := router.EmbedPassage(ctx, h.embedder, dec.Utterance); err != nil {
text := store.FactRecallText(dec.Slots.Key, dec.Slots.Value)
if vec, err := router.EmbedPassage(ctx, h.embedder, text); err != nil {
log.Printf("voice: embed fact for memory: %v", err)
} else if err := h.memStore.Insert(ctx, "fact:"+dec.Slots.Key+":"+strconv.FormatInt(now.Unix(), 10), vec, map[string]string{
"source": "voice",
"type": "fact",
"text": dec.Utterance,
"ts": strconv.FormatInt(now.Unix(), 10),
"source": "voice",
"type": "fact",
"text": text,
"utterance": dec.Utterance,
"ts": strconv.FormatInt(now.Unix(), 10),
}); err != nil {
log.Printf("voice: memory insert fact: %v", err)
}
+16
View File
@@ -78,6 +78,22 @@ func TestActionFact_ExplicitCaptureStillWrites(t *testing.T) {
if f.Confidence != 1.0 {
t.Errorf("confidence = %v, want 1.0 for a value he said", f.Confidence)
}
// #493: what recall reads back is the fact, not the sentence he said.
// queryMemory returns a fact's text verbatim, so the utterance sitting here
// meant "запиши что я пил воду" was the answer to "когда я пил воду?".
hits, err := h.memStore.Search(ctx, mustEmbedPassage(t, h, "вода"), 3)
if err != nil {
t.Fatalf("memory search: %v", err)
}
if len(hits) != 1 {
t.Fatalf("the fact was not indexed once: %+v", hits)
}
if got := hits[0].Meta["text"]; got != "water — вода" {
t.Errorf("indexed text = %q, want the fact", got)
}
if got := hits[0].Meta["utterance"]; got != "запиши что я пил воду" {
t.Errorf("utterance provenance = %q, want it kept alongside", got)
}
}
func TestFactConfidence(t *testing.T) {
+47
View File
@@ -47,6 +47,39 @@ func (s *Store) WriteFact(ctx context.Context, ts time.Time, kind FactKind, key,
return id, nil
}
// FactRecallText is the text a fact is indexed under and read back as (#493).
//
// It used to be the utterance that wrote the fact, so recall of ANY
// voice-tapped fact answered with the sentence he said instead of the value
// stored: `go_version = 1.20` was indexed as "какая последняя версия языка
// Go?", and that question is what came back. The poisoned rows made the defect
// visible; the shape was wrong for legitimate facts too.
//
// The key is spoken with its underscores dropped, because a key is written for
// the store and this string is read out loud.
func FactRecallText(key, value string) string {
spoken := strings.TrimSpace(strings.ReplaceAll(key, "_", " "))
v := strings.TrimSpace(DecodeFactValue(value))
switch {
case v == "":
return spoken
case spoken == "":
return v
}
return spoken + " — " + v
}
// DecodeFactValue unwraps a stored value for reading. The column holds raw json
// when the writer serialized one (SetValue, CorrectValue) and a plain string
// when it did not (a voice tap), so a reader that wants the text handles both.
func DecodeFactValue(value string) string {
var s string
if err := json.Unmarshal([]byte(value), &s); err == nil {
return s
}
return value
}
// LatestFact returns the latest non-voided fact for key, or ErrNoFact.
// "Non-voided" = no later row has voids_id pointing at it. We resolve this by
// taking the newest row whose id is not referenced by any voids_id.
@@ -291,6 +324,20 @@ func (s *Store) CorrectValue(ctx context.Context, key, source string, value any,
if err != nil {
return 0, fmt.Errorf("last insert id: %w", err)
}
// The same repair a void needs, for the same reason (#493). A correction
// supersedes the value, and the vector still holds the old one, so recall
// kept answering with the value he had just corrected. Dropping it costs
// the key its recall vector until the fact is tapped again: this layer has
// no embedder, and a missing vector loses a question while a stale one
// answers it wrongly.
//
// Best-effort: the corrected row is committed, and a correction that lands
// beats one that fails on cleanup.
if n, derr := s.VectorMemory().DeletePrefix(ctx, "fact:"+key+":"); derr != nil {
log.Printf("store: correct %q: memory vectors survive: %v", key, derr)
} else if n > 0 {
log.Printf("store: correct %q: dropped %d superseded memory vector(s)", key, n)
}
return newID, nil
}