Merge pull request 'Bug: a question writes invented knowledge into memory as a self fact, and recall then serves it back for unrelated questions' (#99) from task/470-bug-a-question-writes-invented-knowledge into master

Reviewed-on: #99

cmd/mavend/actions_fact.go

@@ -15,14 +15,41 @@ func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) s
 	if !dec.Slots.HasKey {
 		return "не разобрала, что записать — попробуй иначе."
 	}
+	// A question is never a fact about him (#470). "какая последняя версия
+	// языка Go?" used to land here, and the value stored was whatever the
+	// model invented for it, at confidence 1.00, indexed for recall under the
+	// question's own text. Two such rows then claimed seven unrelated world
+	// questions through recall and silently disabled world answering.
+	//
+	// The routing error itself is not fixed here — the answer is to answer.
+	// Sending the turn down the query chain is what he asked for anyway, and
+	// it costs a mis-routed capture nothing: an explicit "запиши ..." is not
+	// question-shaped, so it never takes this branch.
+	if router.IsQuestionShaped(dec.Utterance) {
+		log.Printf("voice: fact write refused, utterance is a question: %q (key %q) — answering as a query",
+			dec.Utterance, dec.Slots.Key)
+		q := dec
+		q.Intent = router.IntentQuery
+		// The key the model extracted is its guess at what to store, not a
+		// fact he has. Left in place, queryFactByKey would read it back and
+		// claim the turn before any real source ran.
+		q.Slots.Key, q.Slots.HasKey = "", false
+		q.Slots.Value = ""
+		return h.actionQuery(ctx, q)
+	}
 	now := h.now()
 	req := ipc.WriteFactReq{
-		Ts:         now,
-		Kind:       "self",
-		Key:        dec.Slots.Key,
-		Value:      dec.Slots.Value,
-		Source:     "tap:voice",
-		Confidence: 1.0,
+		Ts:     now,
+		Kind:   "self",
+		Key:    dec.Slots.Key,
+		Value:  dec.Slots.Value,
+		Source: "tap:voice",
+		// Not 1.00 unconditionally any more (#470). A value he said is
+		// evidence; a value the model supplied for words he never said is a
+		// guess, and writing a guess at full confidence is the same mistake
+		// the act path already refuses under "LLM output is not
+		// authorization".
+		Confidence: factConfidence(dec.Utterance, dec.Slots.Value),
 		// Subject: the key doubles as the entity-resolution candidate —
 		// a voice-tapped fact's key is usually the thing/person it's
 		// about ("espresso_machine", "kate"), so queueing it for Nexus

cmd/mavend/actions_query.go

@@ -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

cmd/mavend/factgate.go

@@ -0,0 +1,82 @@
+package main
+
+import (
+	"log"
+	"strings"
+	"unicode"
+)
+
+// ungroundedConfidence — what a self fact is worth when its value appears
+// nowhere in what he said. Below `query_min_score` is not the point (recall
+// gates on vector distance, not on this number); the point is that
+// `/history` and every future reader can tell a value he said from a value
+// the model supplied.
+const ungroundedConfidence = 0.6
+
+// factConfidence scores a self fact by whether its value is grounded in the
+// utterance it came from. Grounded stays 1.00, which is what a tapped fact
+// has always been worth. Ungrounded drops, and says so in the log.
+//
+// An empty value is grounded by definition: the key alone carries the fact
+// ("поужинал"), and there is nothing for the model to have invented.
+func factConfidence(utterance, value string) float64 {
+	if strings.TrimSpace(value) == "" {
+		return 1.0
+	}
+	if valueGrounded(utterance, value) {
+		return 1.0
+	}
+	log.Printf("voice: fact value %q is not in %q — writing at confidence %.2f",
+		value, utterance, ungroundedConfidence)
+	return ungroundedConfidence
+}
+
+// valueGrounded reports whether every word of value traces back to a word he
+// actually said. The comparison is on a 4-rune prefix, so the model's
+// normalization survives ("пил воду" → "вода") while an invented value
+// ("1.20" for a question about Go) does not.
+func valueGrounded(utterance, value string) bool {
+	said := factTokens(utterance)
+	words := factTokens(value)
+	if len(words) == 0 {
+		return true
+	}
+	for _, w := range words {
+		if !anyTokenMatches(said, w) {
+			return false
+		}
+	}
+	return true
+}
+
+func anyTokenMatches(said []string, w string) bool {
+	for _, s := range said {
+		if s == w || sameStem(s, w) {
+			return true
+		}
+	}
+	return false
+}
+
+// sameStem is inflection tolerance and nothing more: it compares all but the
+// last rune of the shorter word, and never fewer than three. Russian marks
+// case on the ending, so "пил воду" and the stored "вода" are the same word he
+// said, while "1.20" and "версия" are not. A word of three runes or fewer must
+// match outright, where a shorter prefix would match half the language.
+func sameStem(a, b string) bool {
+	ar, br := []rune(a), []rune(b)
+	shorter := min(len(ar), len(br))
+	n := shorter - 1
+	if n < 3 || len(ar) < n || len(br) < n {
+		return false
+	}
+	return string(ar[:n]) == string(br[:n])
+}
+
+// factTokens lowercases and splits on everything that is not a letter or a
+// digit, the same shape planTokens uses in the router.
+func factTokens(s string) []string {
+	return strings.FieldsFunc(strings.ToLower(s), func(r rune) bool {
+		return !unicode.IsLetter(r) && !unicode.IsDigit(r)
+	})
+}

cmd/mavend/factgate_test.go

@@ -0,0 +1,109 @@
+package main
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/kami/maven/internal/ipc"
+	"github.com/kami/maven/internal/memory"
+	"github.com/kami/maven/internal/router"
+	"github.com/kami/maven/internal/tool"
+	"github.com/kami/maven/internal/voice"
+)
+
+func newFactGateHandler(t *testing.T, now time.Time) (*reactiveHandler, ipc.CoreAPI) {
+	t.Helper()
+	st := newTestStore(t)
+	api := ipc.NewStoreAPI(st)
+	emb := router.NewHashEmbedder(1024)
+	h := &reactiveHandler{
+		api:       api,
+		embedder:  emb,
+		router:    buildRouter(emb, tool.NewMatcher(api), 0.55, nil),
+		replier:   voice.NewStubReplier(),
+		now:       func() time.Time { return now },
+		memStore:  memory.NewInMemoryStore(),
+		dataStore: st,
+	}
+	return h, api
+}
+
+// The write half of #470: a question routed to IntentFact must not become a
+// fact about him, and must not leave a vector behind for recall to serve.
+func TestActionFact_QuestionIsNotWritten(t *testing.T) {
+	ctx := context.Background()
+	h, api := newFactGateHandler(t, time.Now())
+
+	reply := h.actionFact(ctx, router.Decision{
+		Intent:    router.IntentFact,
+		Utterance: "какая последняя версия языка Go?",
+		Slots:     router.Slots{Key: "go_version", HasKey: true, Value: `"1.20"`},
+	})
+
+	if _, err := api.LatestFact(ctx, "go_version"); err == nil {
+		t.Fatal("a question was stored as a fact about him")
+	}
+	hits, err := h.memStore.Search(ctx, mustEmbedPassage(t, h, "какая последняя версия языка Go?"), 3)
+	if err != nil {
+		t.Fatalf("memory search: %v", err)
+	}
+	if len(hits) != 0 {
+		t.Fatalf("the question was indexed for recall: %+v", hits)
+	}
+	// It went down the query chain instead. Nothing is configured to answer a
+	// world question in this harness, so "не знаю." is the honest outcome —
+	// what matters is that the turn was answered, not stored.
+	if reply == "" {
+		t.Fatal("the turn was neither stored nor answered")
+	}
+}
+
+// The capture that must survive the gate: an explicit instruction to record,
+// even though it contains an interrogative.
+func TestActionFact_ExplicitCaptureStillWrites(t *testing.T) {
+	ctx := context.Background()
+	h, api := newFactGateHandler(t, time.Now())
+
+	h.actionFact(ctx, router.Decision{
+		Intent:    router.IntentFact,
+		Utterance: "запиши что я пил воду",
+		Slots:     router.Slots{Key: "water", HasKey: true, Value: `"вода"`},
+	})
+
+	f, err := api.LatestFact(ctx, "water")
+	if err != nil {
+		t.Fatalf("an explicit capture was refused: %v", err)
+	}
+	if f.Confidence != 1.0 {
+		t.Errorf("confidence = %v, want 1.0 for a value he said", f.Confidence)
+	}
+}
+
+func TestFactConfidence(t *testing.T) {
+	cases := []struct {
+		utterance, value string
+		want             float64
+	}{
+		{"запиши что я пил воду", `"вода"`, 1.0},
+		{"я выпил кофе", `"кофе"`, 1.0},
+		{"поужинал", "", 1.0},
+		{"отметь что я полил кактус", `"полил кактус"`, 1.0},
+		{"какая последняя версия языка Go", `"1.20"`, ungroundedConfidence},
+		{"кто премьер Японии", `"Тонио Озаки"`, ungroundedConfidence},
+	}
+	for _, c := range cases {
+		if got := factConfidence(c.utterance, c.value); got != c.want {
+			t.Errorf("factConfidence(%q, %q) = %v, want %v", c.utterance, c.value, got, c.want)
+		}
+	}
+}
+
+func mustEmbedPassage(t *testing.T, h *reactiveHandler, text string) []float32 {
+	t.Helper()
+	vec, err := router.EmbedQuery(context.Background(), h.embedder, text)
+	if err != nil {
+		t.Fatalf("embed %q: %v", text, err)
+	}
+	return vec
+}

internal/memory/lexical.go

@@ -0,0 +1,126 @@
+package memory
+
+import (
+	"strings"
+	"unicode"
+)
+
+// stopwords — words that carry no topic. A question and a note that share only
+// these share nothing: "почему небо синее" and "сеть какая-то медленная" both
+// contain "какая"-shaped filler and are about different worlds.
+var stopwords = map[string]bool{
+	// interrogatives and demonstratives
+	"что": true, "чего": true, "какой": true, "какая": true, "какое": true,
+	"какие": true, "каких": true, "кто": true, "кого": true, "кому": true,
+	"почему": true, "зачем": true, "где": true, "куда": true, "откуда": true,
+	"когда": true, "сколько": true, "как": true, "то": true, "это": true,
+	"этот": true, "тот": true, "там": true, "тут": true, "такой": true,
+	// pronouns — every sentence he says is about him, so "я" is not a topic
+	"я": true, "меня": true, "мне": true, "мой": true, "моя": true, "мои": true,
+	"ты": true, "тебя": true, "тебе": true, "твой": true, "он": true, "она": true,
+	"они": true, "мы": true, "себя": true, "свой": true,
+	// prepositions, conjunctions, particles, copulas
+	"в": true, "во": true, "на": true, "с": true, "со": true, "у": true,
+	"о": true, "об": true, "про": true, "за": true, "из": true, "по": true,
+	"до": true, "от": true, "для": true, "над": true, "под": true, "при": true,
+	"и": true, "а": true, "но": true, "или": true, "же": true, "ли": true,
+	"не": true, "ни": true, "бы": true, "был": true, "была": true, "было": true,
+	"быть": true, "есть": true, "был-ли": true, "уже": true, "ещё": true,
+	"еще": true, "так": true, "вот": true, "там-же": true,
+	// English filler, for the mixed utterances he does say
+	"the": true, "a": true, "an": true, "is": true, "are": true, "was": true,
+	"were": true, "be": true, "of": true, "in": true, "on": true, "at": true,
+	"to": true, "for": true, "about": true, "and": true, "or": true, "not": true,
+	"what": true, "who": true, "why": true, "when": true, "where": true,
+	"which": true, "how": true, "i": true, "my": true, "me": true, "it": true,
+	"this": true, "that": true,
+}
+
+// firstPerson — the words that make an utterance a question about his own
+// life. Not possession only: "как я восстановил конфиги" owns nothing and is
+// still about him.
+var firstPerson = map[string]bool{
+	"я": true, "меня": true, "мне": true, "мной": true, "мой": true,
+	"моя": true, "моё": true, "мое": true, "мои": true, "моего": true,
+	"моей": true, "моих": true, "моим": true, "себя": true, "свой": true,
+	"своя": true, "свои": true, "своего": true, "мною": true,
+	"i": true, "me": true, "my": true, "mine": true, "myself": true,
+}
+
+// RecallAllowed is the second half of the recall gate (#470). A hit that
+// cleared the score and margin gate may still be about something else
+// entirely: the held-out fixture puts the right note at 0.791-0.890 and the
+// must-be-silent cases at 0.795-0.835, so no threshold sits between them, and
+// a note about his slow network answered "почему небо синее?".
+//
+// The veto applies only to a question that mentions nothing of his. That
+// restriction is what keeps the fix from costing more than it saves: recall
+// exists to find the note whose words he no longer remembers, and demanding a
+// shared word of every recall silenced four true recalls on the fixture to
+// kill one false one. A question about his own life keeps the embedder alone
+// as its judge. A question about the world has to name something the memory
+// actually mentions.
+func RecallAllowed(query, text string) bool {
+	if mentionsHim(query) {
+		return true
+	}
+	return SharesContentWord(query, text)
+}
+
+func mentionsHim(query string) bool {
+	for _, w := range strings.FieldsFunc(strings.ToLower(query), func(r rune) bool {
+		return !unicode.IsLetter(r) && !unicode.IsDigit(r)
+	}) {
+		if firstPerson[w] {
+			return true
+		}
+	}
+	return false
+}
+
+// SharesContentWord reports whether query and text have at least one topic
+// word in common, after dropping the words that carry no topic. Stems are
+// compared, so the note and the question do not have to inflect alike.
+func SharesContentWord(query, text string) bool {
+	q := contentWords(query)
+	if len(q) == 0 {
+		// Nothing to compare — a question made entirely of filler. The score
+		// gate is then the only judge it can have.
+		return true
+	}
+	t := contentWords(text)
+	for _, a := range q {
+		for _, b := range t {
+			if a == b || sameStem(a, b) {
+				return true
+			}
+		}
+	}
+	return false
+}
+
+func contentWords(s string) []string {
+	var out []string
+	for _, w := range strings.FieldsFunc(strings.ToLower(s), func(r rune) bool {
+		return !unicode.IsLetter(r) && !unicode.IsDigit(r)
+	}) {
+		if !stopwords[w] {
+			out = append(out, w)
+		}
+	}
+	return out
+}
+
+// sameStem is inflection and derivation tolerance: Russian marks case and
+// tense on the ending, and the note and the question rarely use the same form.
+// "воду" and "вода" are the same water, "кормить" and "корм" the same feeding.
+// All but the last rune of the shorter word must match, and never fewer than
+// three, which is what keeps "сеть" clear of "сеанс".
+func sameStem(a, b string) bool {
+	ar, br := []rune(a), []rune(b)
+	n := min(len(ar), len(br)) - 1
+	if n < 3 {
+		return false
+	}
+	return string(ar[:n]) == string(br[:n])
+}

internal/memory/lexical_test.go

@@ -0,0 +1,40 @@
+package memory
+
+import "testing"
+
+func TestRecallAllowed(t *testing.T) {
+	cases := []struct {
+		name        string
+		query, text string
+		want        bool
+	}{
+		// The #470 shape: a world question and a note about his box.
+		{"world question, unrelated note", "почему небо синее", "сеть какая-то медленная", false},
+		{"world question, unrelated fact", "какая столица Франции", "какая последняя версия языка Go", false},
+		{"silent fixture case", "во сколько отходит поезд", "бэкап запускается в три ночи", false},
+
+		// A world question that does name the topic keeps its answer.
+		{"world question, same topic", "какой поезд идёт в Минск", "поезда в Минск ходят утром", true},
+
+		// A question about his own life is judged by the embedder alone,
+		// because recall exists for words he no longer remembers.
+		{"about him, no shared word", "во сколько я обычно засыпаю", "ложусь около одиннадцати", true},
+		{"about him, english", "which colour scheme do i like", "тёмная тема везде", true},
+
+		// Inflection must not break a match.
+		{"inflected", "чем кормить кота", "корм для кота в шкафу", true},
+	}
+	for _, c := range cases {
+		if got := RecallAllowed(c.query, c.text); got != c.want {
+			t.Errorf("%s: RecallAllowed(%q, %q) = %v, want %v", c.name, c.query, c.text, got, c.want)
+		}
+	}
+}
+
+// A question made only of filler has no topic word to match on, and the score
+// gate is then the only judge it can have.
+func TestRecallAllowedFallsBackWhenNothingToCompare(t *testing.T) {
+	if !RecallAllowed("что это", "сеть какая-то медленная") {
+		t.Error("a question with no content word must not be vetoed")
+	}
+}

internal/memory/recalleval/recalleval.go

@@ -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) {

internal/memory/recalleval/recalleval_test.go

@@ -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")
 	}
 }

internal/router/question.go

@@ -0,0 +1,64 @@
+package router
+
+import "strings"
+
+// interrogatives — the question words that mark an utterance as asking rather
+// than telling. Tokenized, never substring: "что" inside "чтобы" and "как"
+// inside "какао" are not questions.
+var interrogatives = []string{
+	"что", "чего", "какой", "какая", "какое", "какие", "каких",
+	"кто", "кого", "кому", "чей", "почему", "зачем", "отчего",
+	"где", "куда", "откуда", "когда", "сколько", "как",
+	"what", "who", "whom", "why", "when", "where", "which", "how",
+}
+
+// narrativeRequests — "tell me about X" asks for knowledge Maven does not
+// hold about him. It carries no question mark and no interrogative, which is
+// how "расскажи про битву при Ватерлоо" reached the fact store (#470).
+var narrativeRequests = []string{
+	"расскажи", "объясни", "опиши", "перечисли",
+	"tell", "explain", "describe",
+}
+
+// captureVerbs — an explicit instruction to record something. These win over
+// every test below, because "запиши что я пил воду" contains an interrogative
+// and is still a capture: the word he said is "запиши".
+var captureVerbs = []string{
+	"запиши", "запомни", "отметь", "заметь", "добавь", "сохрани",
+	"note", "remember", "log", "save",
+}
+
+// IsQuestionShaped reports whether text asks for something rather than
+// records it. It is a deterministic offline test over tokens, so it costs
+// nothing and never depends on the model that produced the routing decision.
+//
+// It exists because a mis-routed question used to be persisted as a fact
+// about the owner, with the model's invented answer as the value (#470). The
+// predicate is deliberately blunt: refusing to store a question is cheap and
+// reversible, storing an invented fact about him is neither.
+func IsQuestionShaped(text string) bool {
+	t := strings.TrimSpace(text)
+	if t == "" {
+		return false
+	}
+	toks := planTokens(t)
+	for _, v := range captureVerbs {
+		if hasTok(toks, v) {
+			return false
+		}
+	}
+	if strings.HasSuffix(t, "?") {
+		return true
+	}
+	for _, w := range interrogatives {
+		if hasTok(toks, w) {
+			return true
+		}
+	}
+	for _, w := range narrativeRequests {
+		if hasTok(toks, w) {
+			return true
+		}
+	}
+	return false
+}

internal/router/question_test.go

@@ -0,0 +1,48 @@
+package router
+
+import "testing"
+
+func TestIsQuestionShaped(t *testing.T) {
+	// The seven utterances #470 recorded, plus the captures that must keep
+	// working. A capture misread as a question loses a fact; a question
+	// misread as a capture poisons recall, so the captures are the ones worth
+	// pinning here.
+	cases := []struct {
+		text string
+		want bool
+	}{
+		{"какая последняя версия языка Go?", true},
+		{"что дальше?", true},
+		{"расскажи про битву при Ватерлоо", true},
+		{"почему небо синее?", true},
+		{"какая столица Австралии?", true},
+		{"кто такой Никола Тесла?", true},
+		{"сколько стоит доллар", true},
+		{"who is the premier of Japan", true},
+		{"объясни линии Фраунгофера", true},
+
+		{"запиши что я пил воду", false},
+		{"запомни какая у меня машина", false},
+		{"отметь что я поужинал", false},
+		{"поужинал", false},
+		{"я выпил кофе", false},
+		{"вода", false},
+		{"привет", false},
+		{"", false},
+	}
+	for _, c := range cases {
+		if got := IsQuestionShaped(c.text); got != c.want {
+			t.Errorf("IsQuestionShaped(%q) = %v, want %v", c.text, got, c.want)
+		}
+	}
+}
+
+// Substring matching is what made the day-plan predicates wrong before, and
+// this predicate gates a write, so it gets the same guard.
+func TestIsQuestionShapedIsTokenized(t *testing.T) {
+	for _, text := range []string{"чтобы не забыть, я полил кактус", "какао выпил"} {
+		if IsQuestionShaped(text) {
+			t.Errorf("IsQuestionShaped(%q) = true; a question word inside a longer word is not a question", text)
+		}
+	}
+}

internal/store/facts.go

@@ -6,6 +6,7 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"log"
 	"strings"
 	"time"
 
@@ -332,6 +333,20 @@ func (s *Store) VoidLatestFact(ctx context.Context, key, source string, ts time.
 	if err != nil {
 		return 0, 0, fmt.Errorf("void: last insert id: %w", err)
 	}
+	// The other half of the repair (#470). A fact reaches recall through a
+	// vector keyed `fact:<key>:<unix>`, holding the utterance that wrote it.
+	// Voiding the row alone left that vector answering questions, so revert
+	// reported success on a box that stayed broken. Deleting every vector for
+	// the key covers the earlier rows too: their values are superseded, and a
+	// superseded value has no business claiming a turn.
+	//
+	// Best-effort by design: the audit trail is already committed, and a fact
+	// that is voided but still recallable is better than a void that failed.
+	if n, derr := s.VectorMemory().DeletePrefix(ctx, "fact:"+key+":"); derr != nil {
+		log.Printf("store: void %q: memory vectors survive: %v", key, derr)
+	} else if n > 0 {
+		log.Printf("store: void %q: dropped %d memory vector(s)", key, n)
+	}
 	return oldID, newID, nil
 }
 

internal/store/memory.go

@@ -148,6 +148,27 @@ func (m *MemoryStore) Delete(ctx context.Context, id string) error {
 	return nil
 }
 
+// DeletePrefix removes every vector whose id starts with prefix and returns
+// how many went. Same escaping as ByPrefix, so a key containing % or _ cannot
+// widen the delete.
+//
+// It exists for the repair half of a revert (#470). Voiding a fact row left
+// its vector in the index, so recall kept serving the voided fact's utterance
+// and the documented repair did not repair.
+func (m *MemoryStore) DeletePrefix(ctx context.Context, prefix string) (int64, error) {
+	pattern := escapeLike(prefix) + "%"
+	res, err := m.db.ExecContext(ctx,
+		`DELETE FROM memory_vectors WHERE id LIKE ? ESCAPE '\'`, pattern)
+	if err != nil {
+		return 0, fmt.Errorf("memory: delete prefix %q: %w", prefix, err)
+	}
+	n, err := res.RowsAffected()
+	if err != nil {
+		return 0, fmt.Errorf("memory: delete prefix %q: rows affected: %w", prefix, err)
+	}
+	return n, nil
+}
+
 // escapeLike neutralises the LIKE wildcards in a literal prefix.
 func escapeLike(s string) string {
 	r := strings.NewReplacer(`\`, `\\`, `%`, `\%`, `_`, `\_`)

internal/store/voidvectors_test.go

@@ -0,0 +1,64 @@
+package store
+
+import (
+	"context"
+	"database/sql"
+	"testing"
+	"time"
+)
+
+// Stage 3 of #470: reverting a fact reported success and left the vector that
+// was answering questions, so the documented repair did not repair.
+func TestVoidLatestFactDropsMemoryVectors(t *testing.T) {
+	ctx := context.Background()
+	s := newTestStore(t)
+	now := time.Now()
+	mem := s.VectorMemory()
+
+	if _, err := s.WriteFact(ctx, now, KindSelf, "go_version", `"1.20"`, "tap:voice", 1.0, sql.NullInt64{}); err != nil {
+		t.Fatalf("WriteFact: %v", err)
+	}
+	// The id shape actionFact writes: fact:<key>:<unix>.
+	if err := mem.Insert(ctx, "fact:go_version:1", []float32{1, 0, 0}, map[string]string{
+		"type": "fact", "text": "какая последняя версия языка Go?",
+	}); err != nil {
+		t.Fatalf("Insert: %v", err)
+	}
+	// A vector for another key must survive the void.
+	if err := mem.Insert(ctx, "fact:water:1", []float32{0, 1, 0}, map[string]string{
+		"type": "fact", "text": "запиши что я пил воду",
+	}); err != nil {
+		t.Fatalf("Insert: %v", err)
+	}
+
+	if _, _, err := s.VoidLatestFact(ctx, "go_version", "feedback", now.Add(time.Minute)); err != nil {
+		t.Fatalf("VoidLatestFact: %v", err)
+	}
+
+	got, err := mem.ByPrefix(ctx, "fact:")
+	if err != nil {
+		t.Fatalf("ByPrefix: %v", err)
+	}
+	if len(got) != 1 || got[0].ID != "fact:water:1" {
+		t.Fatalf("after the void the index holds %+v; want only fact:water:1", got)
+	}
+}
+
+func TestDeletePrefixDoesNotWidenOnWildcards(t *testing.T) {
+	ctx := context.Background()
+	s := newTestStore(t)
+	mem := s.VectorMemory()
+
+	for _, id := range []string{"fact:a_b:1", "fact:axb:1"} {
+		if err := mem.Insert(ctx, id, []float32{1, 0}, map[string]string{"type": "fact"}); err != nil {
+			t.Fatalf("Insert %q: %v", id, err)
+		}
+	}
+	n, err := mem.DeletePrefix(ctx, "fact:a_b:")
+	if err != nil {
+		t.Fatalf("DeletePrefix: %v", err)
+	}
+	if n != 1 {
+		t.Fatalf("deleted %d rows; the _ in the key must not match x", n)
+	}
+}