mavend: a question is never a fact about him (V-470)

IntentFact used to persist whatever the model invented for a question-shaped
utterance, at confidence 1.00, and index it for recall under the question's own
text. Two such rows then claimed seven unrelated world questions and silently
disabled world answering.

A question now goes down the query chain, which is what he asked for. The second
half is confidence: a value grounded in what he said stays 1.00, a value the model
supplied for words he never said drops to 0.60 and says so in the log. Same
reasoning as 'LLM output is not authorization' on the act path.

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/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
+}