Merge the clarify wiring

# Conflicts:
#	internal/dialogue/clarify.go
#	internal/dialogue/clarify_test.go
This commit is contained in:
kami
2026-07-31 02:30:59 +04:00
3 changed files with 461 additions and 53 deletions
+43 -53
View File
@@ -228,6 +228,8 @@ 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())
@@ -252,8 +254,10 @@ 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,
}
@@ -306,6 +310,14 @@ 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
@@ -380,6 +392,13 @@ 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
@@ -409,34 +428,16 @@ 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)
}
}
@@ -467,6 +468,11 @@ 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 {
@@ -484,30 +490,14 @@ 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
}
}