A pending clarify has no way out: neither answering it nor dismissing it registers #198

Merged
claude merged 2 commits from task/654-a-pending-clarify-has-no-way-out-neither into master 2026-08-07 10:24:40 +02:00
4 changed files with 211 additions and 22 deletions
Showing only changes of commit 4fdecf9a25 - Show all commits
+42 -22
View File
@@ -6,7 +6,6 @@ import (
"math/rand"
"strings"
"time"
"unicode"
"unicode/utf8"
"github.com/kami/maven/internal/dialogue"
@@ -162,12 +161,13 @@ func withNotice(notice, reply string) string {
// напоминание?" — answer first, then the open question. A question in front of
// its own answer would read as ignoring what he asked.
//
// A statement's full stop is folded into a comma, so the two acts read as one
// sentence — that is the owner's own punctuation, "в Риме сейчас ..., на какое
// время поставить напоминание?". An answer that is ITSELF a question keeps its
// mark and the resume starts a new sentence: she sometimes answers a side query
// by asking him to say it again, and "переформулировать?, на какое время" folds
// two questions into one unreadable line.
// Two sentences, not one (V-654). This used to fold the answer's full stop into
// a comma, on the strength of the owner having written it that way once. Spliced
// onto a real answer it reads as one run-on thought — "вот что я нашла: вайфай
// пароль лежит в ящике стола, на какое время поставить напоминание?" — and the
// question disappears into the tail of a sentence about something else. A reply
// with no terminator of its own is given one, so the join never depends on how
// the phraser chose to end.
//
// A resume with no answer in front of it is just the question.
func withResumed(reply, resumed string) string {
@@ -178,23 +178,17 @@ func withResumed(reply, resumed string) string {
if reply == "" {
return resumed
}
if strings.HasSuffix(reply, "?") {
return reply + " " + resumed
if !endsSentence(reply) {
reply += "."
}
if trimmed := strings.TrimRight(reply, ".!"); trimmed != "" {
reply = trimmed
}
return reply + ", " + lowerFirst(resumed)
return reply + " " + resumed
}
// lowerFirst lowercases the opening rune, so a deck line written as a standalone
// sentence reads as the second half of one. Only the first rune: "На какое
// время" must become "на какое время" and nothing else in it may move.
func lowerFirst(s string) string {
for i, r := range s {
return string(unicode.ToLower(r)) + s[i+utf8.RuneLen(r):]
}
return s
// endsSentence reports whether s already closes itself. The ellipsis counts: a
// trailing "…" is a deliberate end, and a full stop after it reads as a typo.
func endsSentence(s string) bool {
r, _ := utf8.DecodeLastRuneInString(s)
return strings.ContainsRune(".!?…", r)
}
// missingFor returns the slots a decision still needs, most important first.
@@ -381,6 +375,14 @@ func (h *reactiveHandler) resolveClarifyAnswer(ctx context.Context, text string)
return "", false
}
// He is answering, so the run of step-asides is over (V-654). Reset here
// rather than where a gap is FILLED: "позвонить маме" against a question
// about the time gives her nothing she asked for and still means he is in
// the exchange, and the retry it costs is bound enough on its own. The
// counter is for the case the bounds miss — he asked for other things and
// never came back.
q.Suspends = 0
merged := q.Answer(text, toDialogueSlots(answer))
// Fold a newly answered subject into the raw utterance. Downstream actions
// phrase from Utterance, not from the text slot — actionReminder stores it
@@ -467,6 +469,14 @@ func (h *reactiveHandler) noteDropped(ctx context.Context) {
//
// A slot with no resumed wording (clarifyResumedFor says so) resumes nothing and
// says nothing. She must not claim to be holding a question she cannot re-ask.
//
// Suspension is bounded, since V-654. Neither of the two things above is a
// limit: no attempt is spent, and restarting the clock means the TTL cannot
// arrive while he keeps talking. So the count is the only thing that ends it,
// and past MaxSuspends she lets the request go and says so with the same line
// every other drop uses. The rule is unchanged — a question ends by being
// answered or by being let go out loud — this only recognises three unrelated
// requests in a row as the second of those.
func (h *reactiveHandler) noteSuspended(ctx context.Context, q *dialogue.PendingQuestion) {
rt := turnRouteFrom(ctx)
if rt == nil || len(q.Missing) == 0 {
@@ -476,11 +486,18 @@ func (h *reactiveHandler) noteSuspended(ctx context.Context, q *dialogue.Pending
if !ok {
return
}
if !q.CanResume() {
h.clarifyStore.Delete(dialogueIDOf(ctx))
h.noteDropped(ctx)
log.Printf("voice: clarify — the question about %s stepped aside %d times; letting the request go", q.Missing[0], q.Suspends)
return
}
q.Suspends++
q.Asked = h.now()
h.clarifyStore.Put(dialogueIDOf(ctx), q)
rt.resume = question
rt.suspended = true
log.Printf("voice: clarify — is its own request; suspending the question about %s and resuming it in the same reply", q.Missing[0])
log.Printf("voice: clarify — is its own request; suspending the question about %s and resuming it in the same reply (suspend %d of %d)", q.Missing[0], q.Suspends, dialogue.MaxSuspends)
}
// foldAnswerIntoUtterance appends an answered subject to the original words,
@@ -520,6 +537,9 @@ func (h *reactiveHandler) askRemainingGap(ctx context.Context, q *dialogue.Pendi
if !ok || !q.CanAsk() {
return "", false
}
// Suspends is not carried, and by this point it is already zero: the answer
// path resets it (V-654). Left off the literal so the zero is stated where
// the struct is built, rather than inherited from a field nobody names.
h.clarifyStore.Put(dialogueIDOf(ctx), &dialogue.PendingQuestion{
Intent: q.Intent,
Slots: merged,
+50
View File
@@ -740,3 +740,53 @@ func TestACompleteTurnStillDoesNotAsk(t *testing.T) {
}
}
}
// TestTheResumedQuestionIsItsOwnSentence — V-654. The re-ask used to be spliced
// onto the answer with a comma, so a real answer and an unrelated open question
// read as one run-on thought and the question vanished into its tail.
func TestTheResumedQuestionIsItsOwnSentence(t *testing.T) {
const resumed = "На какое время поставить напоминание?"
cases := []struct {
name string
reply string
want string
}{
{
// The measured line, shortened. Two sentences, and the question keeps
// its capital.
name: "a statement keeps its full stop",
reply: "Вайфай пароль лежит в ящике стола.",
want: "Вайфай пароль лежит в ящике стола. " + resumed,
},
{
name: "a reply with no terminator is given one",
reply: "Вайфай пароль лежит в ящике стола",
want: "Вайфай пароль лежит в ящике стола. " + resumed,
},
{
// She sometimes answers a side query by asking him to say it again.
// Two questions, and neither may swallow the other.
name: "a question keeps its mark",
reply: "Можешь переформулировать?",
want: "Можешь переформулировать? " + resumed,
},
{
name: "an ellipsis is already an ending",
reply: "Не уверена…",
want: "Не уверена… " + resumed,
},
{
name: "a resume with no answer in front of it is just the question",
reply: "",
want: resumed,
},
}
for _, tc := range cases {
if got := withResumed(tc.reply, resumed); got != tc.want {
t.Errorf("%s: withResumed(%q) = %q, want %q", tc.name, tc.reply, got, tc.want)
}
}
if got := withResumed("Готово.", ""); got != "Готово." {
t.Errorf("nothing to resume must leave the reply alone, got %q", got)
}
}
+94
View File
@@ -279,3 +279,97 @@ func TestTheTurnIsRoutedOnce(t *testing.T) {
t.Fatalf("the pipeline routed again and got something else: %+v vs %+v", second, first)
}
}
// TestASuspendedQuestionDoesNotRideForever — V-654, the measured failure of
// 2026-08-07 (docs/evals/2026-08-07-week-of-usage-transcript.md, t=51 to t=58).
//
// A side query suspends the parked question, spends no attempt and restarts the
// TTL. Nothing else bounded it, so one unfilled time slot came back on the end
// of six consecutive unrelated replies and stopped only when a seventh turn
// happened to read as a failed answer. Three step-asides, then she lets it go
// and says so.
func TestASuspendedQuestionDoesNotRideForever(t *testing.T) {
ctx := context.Background()
h, st := newRoutingClarifyHandler(t)
id := dialogueIDFor(sourceText, "web")
resumed, _ := clarifyResumedFor(dialogue.SlotTime)
if reply := h.handleText(ctx, "web", "напомни позвонить маме"); !strings.Contains(reply, "?") {
t.Fatalf("expected the time question, got %q", reply)
}
// Three questions of his own. Each one is answered as itself and each one
// brings the open question back, exactly as V-561 asks.
asides := []string{
"о чём мы вчера говорили?",
"какие у меня напоминания?",
"сколько времени?",
}
for i, text := range asides {
reply := h.handleText(ctx, "web", text)
if !strings.HasSuffix(reply, resumed) {
t.Fatalf("side query %d: the question must come back, got %q", i+1, reply)
}
if strings.Contains(reply, clarifyDropped) {
t.Fatalf("side query %d: nothing was let go yet, so nothing may say so: %q", i+1, reply)
}
q := h.clarifyStore.Get(id, h.now())
if q == nil {
t.Fatalf("side query %d: the question was dropped early", i+1)
}
if q.Attempts != 1 {
t.Fatalf("side query %d: a step-aside spent an attempt: %d", i+1, q.Attempts)
}
if q.Suspends != i+1 {
t.Fatalf("side query %d: suspends = %d, want %d", i+1, q.Suspends, i+1)
}
}
// The fourth. She has stepped aside as often as she is willing to, so the
// request goes — out loud, and without the question on the tail.
reply := h.handleText(ctx, "web", "что у меня сегодня?")
if !strings.Contains(reply, clarifyDropped) {
t.Fatalf("the request was let go in silence: %q", reply)
}
if strings.HasSuffix(reply, resumed) {
t.Fatalf("a question she has let go must not be asked again: %q", reply)
}
if h.clarifyStore.Get(id, h.now()) != nil {
t.Fatal("the question must be gone once she has said she let it go")
}
if reminders, err := st.DueReminders(ctx, h.now().Add(48*time.Hour)); err != nil || len(reminders) != 0 {
t.Fatalf("a reminder was invented for a time nobody gave: %v err=%v", reminders, err)
}
}
// TestAnAnsweredGapResetsTheSuspendBudget — the counter measures CONSECUTIVE
// step-asides. He filled a gap, so the run is broken and the next question
// starts with its full allowance: a long exchange he is engaged with must not
// run out of patience on his behalf.
func TestAnAnsweredGapResetsTheSuspendBudget(t *testing.T) {
ctx := context.Background()
h, _ := newRoutingClarifyHandler(t)
id := dialogueIDFor(sourceText, "web")
// A bare "напомни" is missing both halves, so answering the subject re-parks
// the request with a question about the time.
if reply := h.handleText(ctx, "web", "напомни"); !strings.Contains(reply, "?") {
t.Fatalf("expected a question, got %q", reply)
}
if reply := h.handleText(ctx, "web", "какие у меня напоминания?"); reply == "" {
t.Fatal("the side query must be answered as itself")
}
if q := h.clarifyStore.Get(id, h.now()); q == nil || q.Suspends != 1 {
t.Fatalf("the side query was not counted: %+v", q)
}
if reply := h.handleText(ctx, "web", "позвонить маме"); reply == "" {
t.Fatal("the answer must be consumed")
}
q := h.clarifyStore.Get(id, h.now())
if q == nil {
t.Fatal("a reminder still needs its time, so a question must be parked")
}
if q.Suspends != 0 {
t.Fatalf("answering a gap must reset the suspend budget: suspends = %d", q.Suspends)
}
}
+25
View File
@@ -41,8 +41,33 @@ type PendingQuestion struct {
Attempts int // questions already asked
// MaxAttempts caps Attempts. 0 ⇒ DefaultMaxAttempts.
MaxAttempts int
// Suspends counts how many times this question has stepped aside for
// something he asked instead, and come back on the end of the answer. It is
// deliberately NOT an attempt: a side query is not a failed answer, and
// charging it a retry is the V-554 shape. See CanResume for why it is
// counted at all.
Suspends int
}
// MaxSuspends — how many times one question may step aside and come back before
// she lets the request go (V-654).
//
// It exists because suspension had no bound of any kind. A side query spends no
// attempt, so MaxAttempts never applies to it, and it restarts the 90s clock, so
// the TTL never arrives either. Measured on 2026-08-07: one unfilled time slot
// rode the end of six consecutive unrelated replies and stopped only when a
// seventh turn happened to read as a failed answer.
//
// Three, matching DefaultMaxAttempts, and for the same reason. Once he has
// asked for three other things without touching the question, the likely truth
// is that he has moved on and has not said so.
const MaxSuspends = 3
// CanResume reports whether this question may step aside once more. False ⇒ the
// caller lets the request go and says so; it must never simply stop resuming,
// because a question dropped in silence reads as one that was answered.
func (q *PendingQuestion) CanResume() bool { return q.Suspends < MaxSuspends }
// Action reads the parked question as the typed action it is assembling
// (pending.go). Derived rather than stored: the question's fields stay the one
// copy of the truth, so a caller that fills them the old way cannot end up with