Merge pull request 'Bug: a transient complaint is stored as a durable fact at confidence 1.00' (#132) from task/481-bug-a-transient-complaint-is-stored-as-a into master

cmd/mavend/actions.go

@@ -57,6 +57,9 @@ var actionHandlers = map[router.Intent]func(*reactiveHandler, context.Context, r
 func (h *reactiveHandler) actionChat(ctx context.Context, dec router.Decision) string {
 	// Conversational: build history from dialogue session (prior user turns)
 	// and let the LLM respond from general knowledge + context.
+	if h.phraser == nil {
+		return "поговорили."
+	}
 	history := h.chatHistory()
 	reply, err := h.phraser.PhraseChat(ctx, dec.Utterance, history)
 	if err != nil {

cmd/mavend/actions_fact.go

@@ -38,6 +38,21 @@ func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) s
 		q.Slots.Value = ""
 		return h.actionQuery(ctx, q)
 	}
+	// A complaint is not a fact either (#481). "сеть какая-то медленная" and
+	// "интернет не работает" were stored as `self` rows at confidence 1.00, and
+	// recall reads a self row back later as if it were still true — the same
+	// class of row that outranked live search in #470. The sentence describes a
+	// moment, so she answers it and stores nothing. An explicit "запомни ..."
+	// and anything about him are both left alone by the test.
+	if router.IsTransientComplaint(dec.Utterance) {
+		log.Printf("voice: fact write refused, utterance is a passing complaint: %q (key %q) — answering as chat",
+			dec.Utterance, dec.Slots.Key)
+		c := dec
+		c.Intent = router.IntentChat
+		c.Slots.Key, c.Slots.HasKey = "", false
+		c.Slots.Value = ""
+		return h.actionChat(ctx, c)
+	}
 	now := h.now()
 	req := ipc.WriteFactReq{
 		Ts:     now,

cmd/mavend/factgate_test.go

@@ -123,3 +123,48 @@ func mustEmbedPassage(t *testing.T, h *reactiveHandler, text string) []float32 {
 	}
 	return vec
 }
+
+// The write half of #481: a complaint about a thing is a state of the
+// afternoon, not a fact about him. Stored as a `self` row at confidence 1.00
+// it comes back on recall as if the network were still down.
+func TestActionFact_ComplaintIsNotWritten(t *testing.T) {
+	ctx := context.Background()
+	h, api := newFactGateHandler(t, time.Now())
+
+	reply := h.actionFact(ctx, router.Decision{
+		Intent:    router.IntentFact,
+		Utterance: "сеть какая-то медленная",
+		Slots:     router.Slots{Key: "network_speed", HasKey: true, Value: "медленная"},
+	})
+
+	if _, err := api.LatestFact(ctx, "network_speed"); err == nil {
+		t.Fatal("a passing complaint was stored as a fact about him")
+	}
+	hits, err := h.memStore.Search(ctx, mustEmbedPassage(t, h, "сеть какая-то медленная"), 3)
+	if err != nil {
+		t.Fatalf("memory search: %v", err)
+	}
+	if len(hits) != 0 {
+		t.Fatalf("the complaint was indexed for recall: %+v", hits)
+	}
+	if reply == "" {
+		t.Fatal("the turn was neither stored nor answered")
+	}
+}
+
+// And the complaint he asked her to keep: the capture verb wins, as it does
+// over the question gate.
+func TestActionFact_AskedToRememberAComplaintStillWrites(t *testing.T) {
+	ctx := context.Background()
+	h, api := newFactGateHandler(t, time.Now())
+
+	h.actionFact(ctx, router.Decision{
+		Intent:    router.IntentFact,
+		Utterance: "запомни что интернет не работает",
+		Slots:     router.Slots{Key: "internet", HasKey: true, Value: "не работает"},
+	})
+
+	if _, err := api.LatestFact(ctx, "internet"); err != nil {
+		t.Fatalf("an explicit capture was refused: %v", err)
+	}
+}

internal/router/complaint.go

@@ -0,0 +1,79 @@
+package router
+
+import "strings"
+
+// transientStems — the states a thing is in for an afternoon. Compared as
+// prefixes because Russian inflects the ending: "медленн" covers "медленная",
+// "медленный" and "медленно" without listing them.
+var transientStems = []string{
+	"медленн", "тормоз", "лаг", "завис", "виснет", "глюч", "барахл",
+	"отвал", "падает", "упал", "сдох", "греется", "перегре",
+	"slow", "laggy", "stuck", "frozen", "flaky", "broken", "down",
+}
+
+// brokenVerbs — what "не ..." is denying when the sentence is a complaint.
+// "не работает", "не грузит", "не открывается". Prefixes again.
+var brokenVerbs = []string{
+	"работ", "пашет", "груз", "открыва", "включа", "коннект", "подключ",
+	"work", "load", "connect", "respond",
+}
+
+// selfMarkers — the words that make a sentence about him rather than about a
+// thing. Their presence turns the test off, because losing a fact he meant to
+// store is worse than keeping a complaint: "я сломал руку" is durable, and
+// "интернет не работает" is not.
+var selfMarkers = []string{"я", "мне", "меня", "мной", "i", "me", "my"}
+
+// IsTransientComplaint reports whether text observes a passing state of some
+// thing rather than recording a fact.
+//
+// It exists because "сеть какая-то медленная" and "интернет не работает" were
+// written to the fact store as `self` rows at confidence 1.00 (Vikunja #481),
+// where recall reads them back later as if they were still true. A complaint
+// describes a moment; the fact store describes him.
+//
+// Deterministic, offline, and shaped exactly like IsQuestionShaped: an
+// explicit capture verb wins over everything, because "запомни что интернет
+// не работает" is an instruction and not a passing remark. A first-person
+// marker also turns it off — the test is meant to catch a sentence about a
+// thing, and it errs toward storing.
+func IsTransientComplaint(text string) bool {
+	t := strings.TrimSpace(text)
+	if t == "" {
+		return false
+	}
+	toks := planTokens(strings.ToLower(t))
+	for _, v := range captureVerbs {
+		if hasTok(toks, v) {
+			return false
+		}
+	}
+	for _, m := range selfMarkers {
+		if hasTok(toks, m) {
+			return false
+		}
+	}
+	for _, tok := range toks {
+		for _, stem := range transientStems {
+			if strings.HasPrefix(tok, stem) {
+				return true
+			}
+		}
+	}
+	// "не" plus a verb of working, in either order of the two tokens that
+	// follow it — "не работает" and "не очень работает" both deny the same
+	// thing.
+	for i, tok := range toks {
+		if tok != "не" && tok != "not" && tok != "isn" {
+			continue
+		}
+		for j := i + 1; j < len(toks) && j <= i+2; j++ {
+			for _, v := range brokenVerbs {
+				if strings.HasPrefix(toks[j], v) {
+					return true
+				}
+			}
+		}
+	}
+	return false
+}

internal/router/complaint_test.go

@@ -0,0 +1,35 @@
+package router
+
+import "testing"
+
+func TestIsTransientComplaint(t *testing.T) {
+	for _, tc := range []struct {
+		text string
+		want bool
+	}{
+		// The two rows from the QA run that named this bug.
+		{"сеть какая-то медленная", true},
+		{"интернет не работает", true},
+		{"вайфай тормозит", true},
+		{"сервер завис", true},
+		{"the wifi is slow", true},
+
+		// An instruction wins: he asked for it to be written down.
+		{"запомни что интернет не работает", false},
+		{"запиши что сеть медленная", false},
+
+		// About him, so it stays a fact even when it sounds like a complaint.
+		{"я сломал руку", false},
+		{"мне медленно думается", false},
+
+		// Ordinary captures must not be touched.
+		{"поужинал", false},
+		{"выпил воды", false},
+		{"машина на парковке", false},
+		{"", false},
+	} {
+		if got := IsTransientComplaint(tc.text); got != tc.want {
+			t.Errorf("IsTransientComplaint(%q) = %v, want %v", tc.text, got, tc.want)
+		}
+	}
+}