cmd/mavend/clarify.go

@@ -1,6 +1,8 @@
 package main
 
 import (
+	"context"
+	"log"
 	"time"
 
 	"github.com/kami/maven/internal/dialogue"
@@ -64,3 +66,115 @@ func clarifyQuestion(dec router.Decision) (dialogue.Slot, string, bool) {
 	}
 	return missing[0], q, true
 }
+
+// askClarify parks the request and returns the question to ask instead of the
+// canned "не поняла". Returns ("", false) when there is nothing to ask about, so
+// the caller falls back to the canned reply.
+func (h *reactiveHandler) askClarify(dec router.Decision) (string, bool) {
+	if h.clarifyStore == nil {
+		return "", false
+	}
+	slot, question, ok := clarifyQuestion(dec)
+	if !ok {
+		return "", false
+	}
+	h.clarifyStore.Put(voiceDialogueID, &dialogue.PendingQuestion{
+		Intent:    dialogue.Intent(dec.Intent),
+		Slots:     toDialogueSlots(dec.Slots),
+		Missing:   []dialogue.Slot{slot},
+		Utterance: dec.Utterance,
+		Asked:     h.now(),
+		TTL:       clarifyTTL,
+		Attempts:  1, // asked once; MaxAttempts is 1, so there is no second ask
+	})
+	log.Printf("voice: clarify — asked about %s for intent=%s", slot, dec.Intent)
+	return question, true
+}
+
+// resolveClarifyAnswer reads an utterance as the answer to a parked question.
+// Returns ("", false) when no live question is parked (or it expired), so the
+// caller routes the utterance normally as a fresh request. Sibling of
+// resolveConfirm and checked in the same place.
+//
+// The answer is parsed with the same extractor the router uses, for the intent
+// she parked — no second parser. If it still does not fill the gap the request
+// is dropped: she does not ask again.
+func (h *reactiveHandler) resolveClarifyAnswer(ctx context.Context, text string) (string, bool) {
+	if h.clarifyStore == nil {
+		return "", false
+	}
+	q := h.clarifyStore.Get(voiceDialogueID, h.now())
+	if q == nil {
+		return "", false
+	}
+	// One shot either way: the question is consumed whether or not the answer
+	// works, so a failed answer can't leave the question armed.
+	h.clarifyStore.Delete(voiceDialogueID)
+
+	intent := router.Intent(q.Intent)
+	answer := h.extractor.Extract(ctx, intent, text, h.now())
+	merged := q.Answer(text, toDialogueSlots(answer))
+	if len(dialogue.StillMissing(q.Missing, merged)) > 0 {
+		log.Printf("voice: clarify — answer %q did not fill %v, dropping", text, q.Missing)
+		return clarifyDropped, true
+	}
+
+	// Rebuild the decision as if it had routed cleanly, then run it down the
+	// normal path. Clarify is deliberately false and the intent is unchanged:
+	// filling in an argument never grants authority, so the completed decision
+	// still meets the allowlist and the destructive-act confirm gate in
+	// applyAction exactly like any other decision.
+	dec := router.Decision{
+		Utterance: q.Utterance,
+		Stage:     2,
+		Intent:    intent,
+		Slots:     applyDialogueSlots(answer, merged),
+	}
+	return h.finishClarified(ctx, dec), true
+}
+
+// finishClarified runs a completed decision through the same steps a freshly
+// routed one takes: remember the turn, act, then phrase.
+func (h *reactiveHandler) finishClarified(ctx context.Context, dec router.Decision) string {
+	if h.dialogueSessions != nil {
+		now := h.now()
+		prev := h.dialogueSessions.Get(voiceDialogueID, now)
+		dec = followUpMerge(prev, dec, now)
+		h.rememberTurn(prev, dec, now)
+	}
+	reply := h.applyAction(ctx, dec)
+	if reply == "" {
+		reply = h.replier.Reply(dec)
+	}
+	return reply
+}
+
+// rememberTurn stores this turn as the dialogue session the next follow-up
+// inherits from, carrying up to 4 prior turns of history for anaphora. Capped so
+// one long conversation can't grow the session unboundedly.
+func (h *reactiveHandler) rememberTurn(prev *dialogue.Session, dec router.Decision, now time.Time) {
+	var history []dialogue.Turn
+	if prev != nil {
+		history = append(history, dialogue.Turn{
+			Intent: prev.Intent,
+			Slots:  prev.Slots,
+			Text:   prev.Slots.Text,
+		})
+		maxHist := len(prev.History)
+		if maxHist > 3 {
+			maxHist = 3
+		}
+		history = append(history, prev.History[:maxHist]...)
+	}
+	ttl := time.Duration(0) // use the store default (2 min)
+	if dec.Intent == router.IntentChat {
+		ttl = 15 * time.Minute // conversational turns should last longer
+	}
+	h.dialogueSessions.Put(voiceDialogueID, &dialogue.Session{
+		Intent:    dialogue.Intent(dec.Intent),
+		Slots:     toDialogueSlots(dec.Slots),
+		Timestamp: now,
+		TTL:       ttl,
+		History:   history,
+	})
+}

cmd/mavend/voice.go

@@ -226,6 +226,8 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
 
 	// ----- dialogue (multi-turn slot carry-over; 2-min follow-up window) -----
 	dialogueSessions := dialogue.NewSessionStore(2 * time.Minute)
+	clarifyStore := dialogue.NewClarifyStore(clarifyTTL)
+	timeParser := router.NewPythonDateParser()
 
 	// ----- replier (LLM-backed when the engine is on, Stub floor otherwise) -----
 	replier := voice.Replier(voice.NewStubReplier())
@@ -250,8 +252,10 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
 		memStore:         memStore,
 		dataStore:        dataStore,
 		dialogueSessions: dialogueSessions,
+		clarifyStore:     clarifyStore,
+		extractor:        router.Extractor{Time: timeParser, Acts: matcher, Facts: router.DefaultFactParser{}},
 		queryMinScore:    cfg.Voice.QueryMinScore,
-		timeParser:       router.NewPythonDateParser(),
+		timeParser:       timeParser,
 		ecosystem:        eco,
 	}
 
@@ -304,6 +308,14 @@ type reactiveHandler struct {
 	// box → one session slot, keyed voiceDialogueID). nil ⇒ no carry-over.
 	dialogueSessions *dialogue.SessionStore
 
+	// clarifyStore parks the request behind an open question she asked (see
+	// clarify.go). nil ⇒ she falls back to the canned "не поняла" reply.
+	clarifyStore *dialogue.ClarifyStore
+
+	// extractor parses the answer to an open question, with the same parsers
+	// the router's own stage-2 uses.
+	extractor router.Extractor
+
 	// pending destructive-act confirmation. A destructive act replies with a
 	// "выполнить X? да/нет" prompt and parks here; the NEXT utterance is read as
 	// the y/n answer. ponytail: single slot, single-user box — a second act
@@ -378,6 +390,13 @@ func (h *reactiveHandler) HandlePushToTalk(ctx context.Context, req voice.PushTo
 		return h.reply(ctx, reply, nil)
 	}
 
+	// 1b2. clarify answer — if she asked a question last turn, this utterance is
+	// its answer, not a fresh command. After the confirm check: a y/n gate is
+	// armed by her own prompt and is the narrower claim on the utterance.
+	if reply, handled := h.resolveClarifyAnswer(ctx, text); handled {
+		return h.reply(ctx, reply, nil)
+	}
+
 	// 1c. 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
@@ -407,34 +426,16 @@ func (h *reactiveHandler) HandlePushToTalk(ctx context.Context, req voice.PushTo
 		prev := h.dialogueSessions.Get(voiceDialogueID, now)
 		dec = followUpMerge(prev, dec, now)
 		if !dec.Clarify {
-			// Build history: carry over up to 4 prior turns for cross-intent
-			// reference. The most recent prior turn is prepended to history.
-			var history []dialogue.Turn
-			if prev != nil {
-				history = append(history, dialogue.Turn{
-					Intent: prev.Intent,
-					Slots:  prev.Slots,
-					Text:   prev.Slots.Text, // the prior turn's utterance
-				})
-				// Cap history depth so one long conversation can't grow
-				// the session unboundedly.
-				maxHist := len(prev.History)
-				if maxHist > 3 {
-					maxHist = 3
-				}
-				history = append(history, prev.History[:maxHist]...)
-			}
-			ttl := time.Duration(0) // use default (2 min)
-			if dec.Intent == router.IntentChat {
-				ttl = 15 * time.Minute // conversational turns should last longer
-			}
-			h.dialogueSessions.Put(voiceDialogueID, &dialogue.Session{
-				Intent:    dialogue.Intent(dec.Intent),
-				Slots:     toDialogueSlots(dec.Slots),
-				Timestamp: now,
-				TTL:       ttl,
-				History:   history,
-			})
+			h.rememberTurn(prev, dec, now)
+		}
+	}
+
+	// 2c. clarify — she is not sure. If one named thing is missing, ask about it
+	// and park the request (clarify.go); otherwise the replier's canned reply
+	// stands.
+	if dec.Clarify {
+		if question, asked := h.askClarify(dec); asked {
+			return h.reply(ctx, question, nil)
 		}
 	}
 
@@ -465,6 +466,11 @@ func (h *reactiveHandler) handleText(ctx context.Context, text string) string {
 		return reply
 	}
 
+	// 1b2. clarify answer — same check as HandlePushToTalk.
+	if reply, handled := h.resolveClarifyAnswer(ctx, text); handled {
+		return reply
+	}
+
 	// 2. router — classify the utterance.
 	dec, err := h.router.Route(ctx, text, h.now())
 	if err != nil {
@@ -482,30 +488,14 @@ func (h *reactiveHandler) handleText(ctx context.Context, text string) string {
 		prev := h.dialogueSessions.Get(voiceDialogueID, now)
 		dec = followUpMerge(prev, dec, now)
 		if !dec.Clarify {
-			var history []dialogue.Turn
-			if prev != nil {
-				history = append(history, dialogue.Turn{
-					Intent: prev.Intent,
-					Slots:  prev.Slots,
-					Text:   prev.Slots.Text,
-				})
-				maxHist := len(prev.History)
-				if maxHist > 3 {
-					maxHist = 3
-				}
-				history = append(history, prev.History[:maxHist]...)
-			}
-			ttl := time.Duration(0)
-			if dec.Intent == router.IntentChat {
-				ttl = 15 * time.Minute
-			}
-			h.dialogueSessions.Put(voiceDialogueID, &dialogue.Session{
-				Intent:    dialogue.Intent(dec.Intent),
-				Slots:     toDialogueSlots(dec.Slots),
-				Timestamp: now,
-				TTL:       ttl,
-				History:   history,
-			})
+			h.rememberTurn(prev, dec, now)
+		}
+	}
+
+	// 2c. clarify — same as HandlePushToTalk: ask about the one missing thing.
+	if dec.Clarify {
+		if question, asked := h.askClarify(dec); asked {
+			return question
 		}
 	}