mavend, recalleval: wire the topic veto into both recall sources (V-470)

queryMemory and queryNotes both gate on score alone, so both needed it. The
eval keeps its own copy of bestRecall — package main is not importable — and a
fixture that measures a weaker gate than the daemon runs flatters it, so the copy
moves in step and its test pins the new rule.

Measured on the held-out recall fixture with the real embedder: 17/32 cases pass
→ 22/32, false recall 1/5 → 0/5, answered after gate 18/27 → 17/27. The one true
recall lost is en-hard-024, an English question against a Russian note, where no
lexical test can help.
This commit is contained in:
2026-08-03 13:51:04 +04:00
parent aec94eb2e8
commit 62c2e92ec0
3 changed files with 40 additions and 11 deletions
+14
View File
@@ -434,6 +434,14 @@ func (h *reactiveHandler) queryMemory(ctx context.Context, t *queryTurn) (string
return "", false
}
text := hit.Meta["text"]
// The score cleared the gate and the topic still has to match (#470). A
// note about his slow network scored high enough to answer "почему небо
// синее?", because the right-note and must-be-silent score ranges overlap
// and no threshold sits between them.
if !memory.RecallAllowed(t.dec.Utterance, text) {
log.Printf("voice: recall %q rejected for %q: a world question and no shared topic word", text, t.dec.Utterance)
return "", false
}
// A note is phrased in Maven's voice; a fact is read back as it was
// stored.
if hit.Meta["type"] == "note" {
@@ -469,6 +477,12 @@ func (h *reactiveHandler) queryNotes(ctx context.Context, t *queryTurn) (string,
if !memory.ConfidentScores(noteScores, h.queryMinScore, h.queryMinMargin) {
return "", false
}
// Same topic veto as queryMemory above: the best note must be about what
// he asked, not merely the nearest vector in the index.
if !memory.RecallAllowed(t.dec.Utterance, notes[0].Text) {
log.Printf("voice: note %q rejected for %q: a world question and no shared topic word", notes[0].Text, t.dec.Utterance)
return "", false
}
texts := make([]string, len(notes))
for i, n := range notes {
texts[i] = n.Text
+11 -3
View File
@@ -378,7 +378,7 @@ func scoreCase(ctx context.Context, emb router.Embedder, newStore NewStore, minS
if len(hits) > 1 {
o.Margin = hits[0].Score - hits[1].Score
}
o.Recalled = bestRecall(hits, minScore, minMargin)
o.Recalled = bestRecall(c.Query, hits, minScore, minMargin)
}
for i, h := range hits {
if h.ID != c.Want {
@@ -424,11 +424,19 @@ func rankNote(inTop3 bool) string {
// is not importable; recalleval_test.go asserts the two agree in behaviour.
// The daemon returns the whole hit (a note and a fact are said differently);
// the harness only scores what came back, so it keeps returning the text.
func bestRecall(results []memory.Result, minScore, minMargin float64) string {
// bestRecall mirrors the daemon's gate in cmd/mavend/recall.go, including the
// topic veto added for #470: a score that clears the gate still has to be
// about what he asked. Keep the two in step — a fixture that measures a
// weaker gate than the daemon runs flatters it.
func bestRecall(query string, results []memory.Result, minScore, minMargin float64) string {
if !memory.Confident(results, minScore, minMargin) {
return ""
}
return results[0].Meta["text"]
text := results[0].Meta["text"]
if !memory.RecallAllowed(query, text) {
return ""
}
return text
}
func bump(m map[string]TagStat, key string, pass bool) {
+15 -8
View File
@@ -140,21 +140,22 @@ func words(s string) []string {
// TestBestRecallMatchesDaemon — the harness duplicates bestRecall from
// cmd/mavend/recall.go (package main is not importable). This pins the copy to
// the original's three rules: no hits, below the gate, or no text ⇒ silence.
// the original's rules: no hits, below the gate, no text, or no shared topic
// word ⇒ silence.
func TestBestRecallMatchesDaemon(t *testing.T) {
if got := bestRecall(nil, 0.55, 0); got != "" {
if got := bestRecall("чай", nil, 0.55, 0); got != "" {
t.Errorf("no hits: got %q, want silence", got)
}
low := []memory.Result{{ID: "a", Score: 0.4, Meta: map[string]string{"text": "чай"}}}
if got := bestRecall(low, 0.55, 0); got != "" {
if got := bestRecall("чай", low, 0.55, 0); got != "" {
t.Errorf("below gate: got %q, want silence", got)
}
noText := []memory.Result{{ID: "a", Score: 0.9, Meta: map[string]string{}}}
if got := bestRecall(noText, 0.55, 0); got != "" {
if got := bestRecall("чай", noText, 0.55, 0); got != "" {
t.Errorf("no text: got %q, want silence", got)
}
ok := []memory.Result{{ID: "a", Score: 0.9, Meta: map[string]string{"text": "чай"}}}
if got := bestRecall(ok, 0.55, 0); got != "чай" {
if got := bestRecall("чай", ok, 0.55, 0); got != "чай" {
t.Errorf("above gate: got %q, want %q", got, "чай")
}
// Margin: a close runner-up means the embedder cannot tell the two apart,
@@ -163,17 +164,23 @@ func TestBestRecallMatchesDaemon(t *testing.T) {
{ID: "a", Score: 0.86, Meta: map[string]string{"text": "чай"}},
{ID: "b", Score: 0.85, Meta: map[string]string{"text": "кофе"}},
}
if got := bestRecall(close, 0.55, 0.03); got != "" {
if got := bestRecall("чай", close, 0.55, 0.03); got != "" {
t.Errorf("thin margin: got %q, want silence", got)
}
if got := bestRecall(close, 0.55, 0); got != "чай" {
if got := bestRecall("чай", close, 0.55, 0); got != "чай" {
t.Errorf("margin off: got %q, want %q", got, "чай")
}
// The topic veto (#470): the score is fine and the note is about
// something else.
offTopic := []memory.Result{{ID: "a", Score: 0.9, Meta: map[string]string{"text": "сеть какая-то медленная"}}}
if got := bestRecall("почему небо синее", offTopic, 0.55, 0); got != "" {
t.Errorf("off topic: got %q, want silence", got)
}
clear := []memory.Result{
{ID: "a", Score: 0.86, Meta: map[string]string{"text": "чай"}},
{ID: "b", Score: 0.70, Meta: map[string]string{"text": "кофе"}},
}
if got := bestRecall(clear, 0.55, 0.03); got != "чай" {
if got := bestRecall("чай", clear, 0.55, 0.03); got != "чай" {
t.Errorf("wide margin: got %q, want %q", got, "чай")
}
}