a side query suspends the flow instead of ending it (V-561)

V-560 classified the side query correctly and then dropped the request behind
it, saying "Прошлую просьбу отпускаю." The owner rejected that on sight: he
asked about the weather in the middle of setting a reminder, and being told the
reminder was let go reports a loss he did not ask for. It had not been lost —
there was simply nowhere to put it.

There is now. ClarifyStore grew a bounded stack in V-559 and nothing called
Push; this is the caller it was built for. A side query leaves the question
parked exactly as it is, the words are answered as themselves, and the question
comes back on the end of the same reply — one utterance, two acts.

The resumed question is not the first one again. "Когда?" works in the same
breath as "напомни позвонить маме" and does not work after a turn about Rome, so
the deck has a second form per slot that names the request: "На какое время
поставить напоминание?". No attempt is spent, because he answered the side query
and not the parked question, and charging a retry for a turn that was never an
answer is the V-554 shape.

clarifyDropped stays for new_request and cancel, where something really does
die. Two things can now die at once, so TakeExpired reports a count instead of a
bool and the expiry notice has a plural wording — "прошлую просьбу" when two
were lost would be a lie about the number.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

cmd/mavend/clarify.go

@@ -6,6 +6,8 @@ import (
 	"math/rand"
 	"strings"
 	"time"
+	"unicode"
+	"unicode/utf8"
 
 	"github.com/kami/maven/internal/dialogue"
 	"github.com/kami/maven/internal/router"
@@ -65,8 +67,28 @@ var clarifyExpiredVariants = []string{
 	"Столько времени прошло, что я отпустила прошлую просьбу. Скажи заново, если она в силе.",
 }
 
-// clarifyExpiredLine picks one of them at random.
-func clarifyExpiredLine() string {
+// clarifyExpiredPluralVariants — the same notice when TWO parked requests died
+// together (Vikunja #561). Since a side query suspends the flow instead of
+// dropping it, the stack can hold both the flow and the thing he interrupted it
+// with, and TakeExpired drops the whole stack when the top times out. "Прошлую
+// просьбу" would then be a lie about the count: he loses two and hears about
+// one.
+//
+// Two phrasings only, against five for the singular. This fires when he walks
+// off in the middle of an interrupted exchange, which is rarer than walking off
+// in the middle of a plain one, so it repeats less and needs less variety.
+var clarifyExpiredPluralVariants = []string{
+	"Прости, я слишком долго ждала и отпустила обе прошлые просьбы. Если они ещё нужны, скажи заново.",
+	"Я не дождалась ответа и убрала обе прошлые просьбы. Повтори, если они всё ещё нужны.",
+}
+
+// clarifyExpiredLine picks one of them at random. n is how many requests died;
+// anything above one gets the plural wording, because the bound is two today and
+// a third would still be "обе" short of the truth only if MaxStackDepth grew.
+func clarifyExpiredLine(n int) string {
+	if n > 1 {
+		return clarifyExpiredPluralVariants[rand.Intn(len(clarifyExpiredPluralVariants))]
+	}
 	return clarifyExpiredVariants[rand.Intn(len(clarifyExpiredVariants))]
 }
 
@@ -74,23 +96,34 @@ func clarifyExpiredLine() string {
 // notice is glued in front of this turn's reply (see withNotice), so a caller
 // checking for it has to match a prefix, not the whole string.
 func isClarifyExpired(s string) bool {
-	for _, v := range clarifyExpiredVariants {
-		if strings.HasPrefix(s, v) {
-			return true
-		}
-	}
-	return false
+	_, ok := cutClarifyExpired(s)
+	return ok
 }
 
 // trimClarifyExpired strips a leading expiry notice, leaving this turn's actual
 // reply. "" ⇒ the notice was the whole thing.
 func trimClarifyExpired(s string) string {
-	for _, v := range clarifyExpiredVariants {
-		if strings.HasPrefix(s, v) {
-			return strings.TrimSpace(strings.TrimPrefix(s, v))
+	rest, ok := cutClarifyExpired(s)
+	if !ok {
+		return strings.TrimSpace(s)
+	}
+	return rest
+}
+
+// cutClarifyExpired matches either expiry deck as a prefix and returns what
+// follows it. Both decks, since V-561 added the plural line: a caller asking
+// "did she say a request timed out" means the fact, not which wording carried
+// it, and a helper that knew only the singular would read the two-request
+// notice as ordinary reply text.
+func cutClarifyExpired(s string) (string, bool) {
+	for _, deck := range [][]string{clarifyExpiredVariants, clarifyExpiredPluralVariants} {
+		for _, v := range deck {
+			if strings.HasPrefix(s, v) {
+				return strings.TrimSpace(strings.TrimPrefix(s, v)), true
+			}
 		}
 	}
-	return strings.TrimSpace(s)
+	return "", false
 }
 
 // clarifyExpiredNotice returns that line when a parked question had just timed
@@ -101,11 +134,12 @@ func (h *reactiveHandler) clarifyExpiredNotice(ctx context.Context) string {
 	if h.clarifyStore == nil {
 		return ""
 	}
-	if !h.clarifyStore.TakeExpired(dialogueIDOf(ctx), h.now()) {
+	n := h.clarifyStore.TakeExpired(dialogueIDOf(ctx), h.now())
+	if n == 0 {
 		return ""
 	}
-	log.Printf("voice: clarify — parked question expired, telling him and routing the words fresh")
-	return clarifyExpiredLine()
+	log.Printf("voice: clarify — %d parked question(s) expired, telling him and routing the words fresh", n)
+	return clarifyExpiredLine(n)
 }
 
 // withNotice glues the expiry notice in front of this turn's reply. One turn
@@ -121,6 +155,48 @@ func withNotice(notice, reply string) string {
 	return notice + " " + reply
 }
 
+// withResumed puts the resumed question on the END of this turn's reply, where
+// withNotice puts the expiry notice on the front (Vikunja #561).
+//
+// The order is the owner's: "в Риме сейчас ..., на какое время поставить
+// 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.
+//
+// A resume with no answer in front of it is just the question.
+func withResumed(reply, resumed string) string {
+	if resumed == "" {
+		return reply
+	}
+	reply = strings.TrimSpace(reply)
+	if reply == "" {
+		return resumed
+	}
+	if strings.HasSuffix(reply, "?") {
+		return reply + " " + resumed
+	}
+	if trimmed := strings.TrimRight(reply, ".!"); trimmed != "" {
+		reply = trimmed
+	}
+	return reply + ", " + lowerFirst(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
+}
+
 // missingFor returns the slots a decision still needs, most important first.
 // Empty ⇒ there is nothing identifiable to ask about.
 func missingFor(dec router.Decision) []dialogue.Slot {
@@ -161,7 +237,7 @@ func (h *reactiveHandler) askClarify(ctx context.Context, dec router.Decision) (
 		log.Printf("voice: clarify — act %q matched no capability; saying so instead of asking", dec.Utterance)
 		return actNotRecognized, true
 	}
-	h.clarifyStore.Put(dialogueIDOf(ctx), &dialogue.PendingQuestion{
+	q := &dialogue.PendingQuestion{
 		Intent:      dialogue.Intent(dec.Intent),
 		Slots:       toDialogueSlots(dec.Slots),
 		Missing:     []dialogue.Slot{slot},
@@ -170,7 +246,33 @@ func (h *reactiveHandler) askClarify(ctx context.Context, dec router.Decision) (
 		TTL:         clarifyTTL,
 		Attempts:    1, // this ask
 		MaxAttempts: h.clarifyMaxAttempts,
-	})
+	}
+	// Push, not Put, when this turn suspended a flow (Vikunja #561): the side
+	// query needs clarifying of ITS own, and Put would replace the top of the
+	// stack — which is the very question the side query was allowed to interrupt
+	// rather than kill. Push keeps both.
+	//
+	// Push returns whatever the depth bound forced out, and that one has to be
+	// spoken: MaxStackDepth is a promise that every level she keeps is a level
+	// she can name when it dies. It is glued in front, like every other notice
+	// about something let go.
+	rt := turnRouteFrom(ctx)
+	if rt != nil && rt.suspended {
+		if evicted := h.clarifyStore.Push(dialogueIDOf(ctx), q); evicted != nil {
+			log.Printf("voice: clarify — stack full at %d, letting go of the request behind %q", dialogue.MaxStackDepth, evicted.Utterance)
+			rt.dropped = withNotice(rt.dropped, clarifyDropped)
+		}
+		// One question per breath still holds. The side query turned out to need
+		// a question of its own, so THAT is the one she asks; resuming as well
+		// would put two questions in one reply, which is the interrogation
+		// askRemainingGap already refuses to run. The suspended flow keeps its
+		// place underneath and is not lost — if it is never reached it dies on
+		// the TTL, and the expiry notice (now plural-aware) says so.
+		rt.resume = ""
+		log.Printf("voice: clarify — asked about %s for intent=%s, stacked on a suspended flow", slot, dec.Intent)
+		return question, true
+	}
+	h.clarifyStore.Put(dialogueIDOf(ctx), q)
 	log.Printf("voice: clarify — asked about %s for intent=%s", slot, dec.Intent)
 	return question, true
 }
@@ -180,10 +282,17 @@ func (h *reactiveHandler) askClarify(ctx context.Context, dec router.Decision) (
 // self-reference ("отменила"), as everywhere.
 const clarifyCancelled = "Хорошо, отменила."
 
-// clarifyDropped — he asked for something else instead, so the parked request
+// clarifyDropped — he asked for something ELSE instead, so the parked request
 // is gone. Glued in front of the answer to what he actually asked, because
-// nothing may be dropped in silence. V-561 suspends and resumes it instead of
-// letting it go, and this line goes away with it.
+// nothing may be dropped in silence.
+//
+// Only new_request and cancel reach this since V-561. A side query used to as
+// well, and the owner rejected it on sight: he asks about the weather in the
+// middle of setting a reminder, and hearing "прошлую просьбу отпускаю" tells him
+// a thing he did not ask to lose has been lost. It had not been — there was
+// simply nowhere to put it. Now there is (ClarifyStore's stack), so a side query
+// suspends and resumes, and apologising for a drop that did not happen is worse
+// than saying nothing.
 const clarifyDropped = "Прошлую просьбу отпускаю."
 
 // resolveClarifyAnswer reads an utterance against the parked question and
@@ -227,7 +336,19 @@ func (h *reactiveHandler) resolveClarifyAnswer(ctx context.Context, text string)
 	case roleCancel:
 		h.clarifyStore.Delete(dialogueIDOf(ctx))
 		return clarifyCancelled, true
-	case roleSideQuery, roleNewRequest:
+	case roleSideQuery:
+		// He asked something of his own WITHOUT leaving the flow. The question
+		// stays exactly where it is — same slot, same attempt, same parked
+		// utterance — and these words go on to be answered as themselves. The
+		// resumed question is then glued onto the back of that answer, so one
+		// reply carries both acts (Vikunja #561).
+		//
+		// No attempt is spent. He answered the side query, not the parked
+		// question, and charging a retry for a turn that was never an answer is
+		// the V-554 shape.
+		h.noteSuspended(ctx, q)
+		return "", false
+	case roleNewRequest:
 		// He moved on. A parked question used to swallow whatever came next, so
 		// one act she could not fulfil ate the following three turns (Vikunja
 		// #554) and a world question set a reminder for a time nobody asked for
@@ -283,6 +404,35 @@ func (h *reactiveHandler) noteDropped(ctx context.Context) {
 	}
 }
 
+// noteSuspended keeps the parked question alive across a side query and records
+// the words that bring it back, so runTurn can put them after this turn's answer
+// (Vikunja #561).
+//
+// Two things happen to the question and neither is an attempt. Its clock is
+// restarted, because she is about to ask it again and the 90s TTL measures the
+// pause since she last spoke it — leaving Asked at the original ask would let a
+// flow he is actively working through die of a wait he did not take. And the
+// stack is left exactly as it is: the question is already on top, so suspending
+// it is not a write.
+//
+// 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.
+func (h *reactiveHandler) noteSuspended(ctx context.Context, q *dialogue.PendingQuestion) {
+	rt := turnRouteFrom(ctx)
+	if rt == nil || len(q.Missing) == 0 {
+		return
+	}
+	question, ok := clarifyResumedFor(q.Missing[0])
+	if !ok {
+		return
+	}
+	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])
+}
+
 // foldAnswerIntoUtterance appends an answered subject to the original words,
 // unless they already carry it. "напомни" + "позвонить маме" reads as the
 // request he would have made in one breath. Nothing is appended when the

cmd/mavend/clarifytemplates.go

@@ -50,6 +50,38 @@ var clarifyQuestionVariants = map[dialogue.Slot][]string{
 	},
 }
 
+// clarifyResumedVariants — the wording for a question coming BACK after a side
+// query took the turn away from it (Vikunja #561).
+//
+// It is not the first question again. "Когда?" works in the same breath as
+// "напомни позвонить маме", because the thing it is about was just said. After
+// a turn about the weather in Rome it does not: he has been thinking about
+// something else, and a bare "Когда?" asks him to remember what she is holding.
+// So the resumed form names the request — "напоминание", "заметка" — and the
+// first form stays short.
+//
+// One wording per slot, not a rotation and not an attempt ladder. A resume does
+// not spend an attempt (that is the point of suspending rather than re-asking),
+// so there is no attempt number to vary on, and this line is heard once per
+// interruption rather than repeatedly.
+//
+// Persona holds: infinitive, so no gender agreement, "ты" nowhere needed, no pet
+// names.
+var clarifyResumedVariants = map[dialogue.Slot]string{
+	dialogue.SlotTime: "На какое время поставить напоминание?",
+	dialogue.SlotText: "Так о чём напомнить?",
+	dialogue.SlotKey:  "Так что записать?",
+	dialogue.SlotFn:   "Так какое действие выполнить?",
+}
+
+// clarifyResumedFor gives the resumed wording for a slot. ("", false) when the
+// slot has none, and the caller then resumes nothing rather than inventing a
+// question — a flow it cannot re-ask is one it must not claim to be holding.
+func clarifyResumedFor(slot dialogue.Slot) (string, bool) {
+	q, ok := clarifyResumedVariants[slot]
+	return q, ok
+}
+
 // actNotRecognized is what an act she cannot run gets (Vikunja #556).
 //
 // The deck used to ask "Что сделать?" instead. That question has no answer he

cmd/mavend/turnroute.go

@@ -31,6 +31,17 @@ type turnRoute struct {
 	// dropped — what she let go of this turn and must say out loud. A parked
 	// request that dies without a word leaves him thinking it landed.
 	dropped string
+
+	// resume — the parked question, re-worded, to put AFTER this turn's answer
+	// (Vikunja #561). A side query does not end the flow it interrupted, so the
+	// reply carries two acts: the answer he asked for, then the question he
+	// still owes her. Empty ⇒ nothing was suspended.
+	resume string
+	// suspended — a flow is parked underneath this turn. askClarify reads it to
+	// decide between Put (replace the top) and Push (keep the flow and stack the
+	// new question on it), because a side query that needs clarifying of its own
+	// must not overwrite the thing it interrupted.
+	suspended bool
 }
 
 type turnRouteKey struct{}

cmd/mavend/voice.go

@@ -255,7 +255,7 @@ const (
 // path wraps it in stt/tts, the text path returns it as-is.
 //
 // The ordering is load-bearing — see the step comments.
-func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSource) string {
+func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSource) (reply string) {
 	// 0. the decision record (V-564). Installed here rather than in the IPC
 	// entry point, so the mic, telegram and the web all leave the same trail —
 	// a record only the web produced would be missing exactly the turns that
@@ -311,6 +311,14 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
 	// with — carried on the same notice, so every exit below keeps it.
 	expiredNotice = withNotice(expiredNotice, rt.dropped)
 
+	// 3b. and if it SUSPENDED a request instead of letting it go, the question
+	// comes back on the end of whatever these words are answered with (Vikunja
+	// #561). A deferred append rather than a call at each exit: there are eight
+	// returns between here and the replier, and the flow has to survive all of
+	// them — one that forgot would be a request parked for ever, waiting for an
+	// answer to a question he never heard asked.
+	defer func() { reply = withResumed(reply, rt.resume) }()
+
 	// 4. quiet-hours toggle — keyword match, not classifier-dependent.
 	// "тихий режим" / "quiet on" would route through the classifier
 	// unreliably (it's a command, not a free-form query), so we match it