router: a deterministic test for question-shaped text (V-470)

The predicate a fact write needs before it trusts a routing decision. Tokenized,
not substring: 'что' inside 'чтобы' is not a question. Capture verbs win over
every question signal, because 'запиши что я пил воду' contains an interrogative
and is still a capture.

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)
+		}
+	}
+}