Maven/cmd/mavend/voice.go

// Package main is mavend's voice wiring + reactive handler.
//
// Two responsibilities for the audio path:
//
//  1. CONSTRUCTION: read cfg.Voice, build the stt/tts/transcribers (Stub
//     in-process by default, Remote via worker socket when configured),
//     the router (stage-0 grammar + HashEmbedder classifier seeded with
//     floor examples — production swaps in the ONNX multilingual model
//     later), the voice TCP listener, the sessions registry, the
//     voicesink, and wire the voicesink into the dispatcher's Voice slot.
//
//  2. HANDLER: a concrete voice.Handler that processes PushToTalk
//     requests: stt → router → action → replier → tts → reply. The
//     handler is what makes the audio round-trip "live". It wires to the
//     CoreAPI in-process (the daemon already has it as ipc.NewStoreAPI(st)
//     for module-IPC — the reactive path uses the same CoreAPI off the
//     same store; both are the "core = the only key-holder" path through
//     the daemon-embedded adapter).
//
// The "actions" handled today (per spec order; some deferred):
//
//   - IntentFact: WriteFact via CoreAPI. The router's Slots.Key/Value feed
//     the write; Source = "tap:voice" (the voice path is a tap, value=1.0
//     confidence — the user said it out loud, maven trusts the capture).
//   - IntentReminder: CreateReminder via CoreAPI. The router already
//     resolved relative→absolute at capture ("in 4h" → fire_ts); the
//     CoreAPI stores it as-is.
//   - IntentAct: the tool executor runs the matched fn against the store's
//     ENABLED allowlist (internal/tool). A verb not on it is scaffolded as a
//     'proposed' tool a human enables on the authed mavweb surface (never
//     voice). Destructive tools run only after a spoken confirm turn.
//   - IntentNote: chroma/vector-store deferred. The handler replies
//     "saved" without persisting — a stub on the way to chroma.
//   - IntentQuery: RAG-over-chroma deferred. The handler replies "I'll
//     look that up later" — same shape as the other deferred slots.
//   - Clarify: the router's stage-3 confidence gate fired; reply "didn't
//     catch that, can you rephrase?"
//
// The Replier (voice.StubReplier today) renders the reply TEXT across all
// these branches. The TTS synthesiser (tts.Stub today) renders that text
// to audio. The PushToTalkResp carries BOTH so the client can play (audio)
// AND log (text) for tests asserting the round-trip.
package main

import (
	"context"
	"errors"
	"fmt"
	"log"
	"strings"
	"sync"
	"time"
	"unicode"

	"github.com/kami/maven/internal/audio"
	"github.com/kami/maven/internal/dialogue"
	"github.com/kami/maven/internal/ipc"
	"github.com/kami/maven/internal/memory"
	"github.com/kami/maven/internal/pattern"
	"github.com/kami/maven/internal/phraser"
	"github.com/kami/maven/internal/router"
	"github.com/kami/maven/internal/store"
	"github.com/kami/maven/internal/stt"
	"github.com/kami/maven/internal/tool"
	"github.com/kami/maven/internal/tts"
	"github.com/kami/maven/internal/ttsnorm"
	"github.com/kami/maven/internal/voice"
	"github.com/kami/maven/internal/weather"
)

// reactiveHandler — voice.Handler implementation. One method: turn a
// PushToTalkReq into a reply (audio + text). The handler is concurrency-
// safe (the wired stt/tts/router/api all are); called from per-conn
// goroutines on the voice.Server.
type reactiveHandler struct {
	stt      stt.Transcriber
	tts      tts.Synthesizer
	router   *router.Router
	embedder router.Embedder // reused for note write/query (same model as the classifier)
	api      ipc.CoreAPI
	tools    *tool.Executor
	matcher  *tool.Matcher
	phraser  phraser.Phraser
	replier  voice.Replier
	now      func() time.Time

	weatherProvider weather.Provider
	weatherLocation string // default location for weather queries

	memStore  memory.Store
	dataStore *store.Store // direct store access for event extraction + pattern detection

	// queryMinScore — the note-recall confidence gate. Top cosine below this ⇒
	// "I don't know" instead of a guess. Tuned for the ONNX embedder; a knob, not
	// load-bearing math (same posture as the presence thresholds). Set by
	// wireVoice from VoiceConfig; default 0.55.
	queryMinScore float64
	// queryMinMargin — the second half of that gate: how far the top hit must
	// beat the runner-up. 0 ⇒ margin off.
	queryMinMargin float64

	// timeParser — used as a fallback for stage-0 reminder grammar matches
	// (where the extractor didn't run). Shared with the router's extractor.
	// The production dateparser will replace StubDateTimeParser here too.
	timeParser router.DateTimeParser

	// dialogueSessions carries slots across turns for follow-ups (single-user
	// 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

	// clarifyMaxAttempts — questions per request before she gives up out loud.
	// 0 ⇒ dialogue.DefaultMaxAttempts (3). Set from VoiceConfig.
	clarifyMaxAttempts int

	// 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
	// while one waits overwrites it (last-asked wins); expires after confirmTTL.
	mu             sync.Mutex
	pending        *pendingAct
	pendingRoutine *pendingRoutineConfirm // routine proposal awaiting y/n
	pendingHexis   *pendingHexisExec      // mutating Hexis capability awaiting y/n

	ecosystem *ecosystemWiring // nexus + hexis + praxis clients
}

// HandlePushToTalk — the full reactive round-trip. Each step's failure
// surfaces as a short reply text + empty audio OR an error; the voice
// server translates an error into a wire RpcError. Today the handler
// prefers a canned error-reply over an error return (a user-facing "didn't
// catch that" is better than a wire error the client surfaces as
// "internal"); the only error returned is a synthesizer fault (no audio
// to ship back).
func (h *reactiveHandler) HandlePushToTalk(ctx context.Context, req voice.PushToTalkReq, _ uint64) (voice.PushToTalkResp, error) {
	// 1. stt — transcribe the audio.
	text, _, err := h.stt.Transcribe(ctx, req.Audio)
	if err != nil {
		log.Printf("voice: stt error: %v", err)
		return h.reply(ctx, "не получилось разобрать речь — попробуй ещё раз.", nil)
	}
	if text == "" {
		return h.reply(ctx, "ничего не услышала — попробуй ещё раз.", nil)
	}
	log.Printf("voice: stt → %q", text)

	// 2-5. the shared turn pipeline (confirm → clarify → route → dialogue →
	// action → replier), identical to the text path.
	replyText := h.runTurn(ctx, text)

	// 6. tts — synthesise the reply text; return to the voice server which
	// ships it back on the conn.
	return h.reply(ctx, replyText, nil)
}

// handleText — the core reactive path without stt/tts. Used by the IPC Chat
// endpoint (and eventually by telegram). Splits out the audio bookends from
// HandlePushToTalk so text channels share the same routing logic.
func (h *reactiveHandler) handleText(ctx context.Context, text string) string {
	log.Printf("voice: handleText: %q", text)
	return h.runTurn(ctx, text)
}

// runTurn — the reactive turn pipeline shared by the voice and text entry
// points: confirm answer → expired-clarify notice → clarify answer → quiet
// toggle → route → dialogue merge → clarify question → action → replier.
// Takes the already-transcribed utterance, returns the reply text; the voice
// 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) string {
	// 1. confirm turn — if a destructive act is parked, this utterance is its
	// y/n answer, not a fresh command. Handled before routing so "да" doesn't
	// get classified as some other intent.
	if reply, handled := h.resolveConfirm(ctx, text); handled {
		return reply
	}

	// 2. expired clarify — a question was parked but its TTL ran out, so the
	// request behind it is gone. Say that out loud (see clarify.go) and carry
	// on: these words are still routed as a fresh utterance below, with the
	// notice glued in front of whatever the fresh routing answers. Checked
	// BEFORE the answer path: reading a parked question drops an expired one.
	expiredNotice := h.clarifyExpiredNotice()

	// 3. clarify answer — if she asked a live 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 reply
	}

	// 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
	// before routing. Same pattern as the confirm turn above.
	if reply, handled := h.resolveQuietToggle(ctx, text); handled {
		return withNotice(expiredNotice, reply)
	}

	// 5. router — classify the utterance.
	dec, err := h.router.Route(ctx, text, h.now())
	if err != nil {
		// ErrNoIntents ⇒ classifier unseeded (cold boot). reply with a
		// "still warming up" rather than a wire error.
		if errors.Is(err, router.ErrNoIntents) {
			return withNotice(expiredNotice, "я ещё не понимаю свободную речь — скоро научусь.")
		}
		log.Printf("voice: router error: %v", err)
		return withNotice(expiredNotice, "не получилось разобрать команду.")
	}
	log.Printf("voice: route result: intent=%s slots=%+v", dec.Intent, dec.Slots)

	// 6. dialogue — fill this turn's missing slots from a prior same-intent
	// turn (follow-ups like «напомни завтра» → «…позвонить маме»), then remember
	// this turn for the next follow-up. Only same-intent, non-expired, non-
	// clarify turns carry (see followUpMerge). Best-effort: nil store ⇒ skipped.
	if h.dialogueSessions != nil {
		now := h.now()
		prev := h.dialogueSessions.Get(voiceDialogueID, now)
		dec = followUpMerge(prev, dec, now)
		if !dec.Clarify {
			h.rememberTurn(prev, dec, now)
		}
	}

	// 7. 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 withNotice(expiredNotice, question)
		}
	}

	// 8. action — execute the decision's intent. errors here surface as
	// short reply text (the user wants to know the action didn't land);
	// the round-trip stays alive.
	replyText := h.applyAction(ctx, dec)
	log.Printf("voice: applyAction returned: %q", replyText)

	// 9. replier — phrase the reply across the router decision.
	if replyText == "" {
		replyText = h.replier.Reply(dec)
	}
	return withNotice(expiredNotice, replyText)
}

// applyAction — executes the router's Decision. Intent-by-intent:
//
//   - IntentFact: WriteFact via CoreAPI. Source = "tap:voice" (a voice
//     capture is a tap; confidence 1.0).
//   - IntentReminder: CreateReminder via CoreAPI.
//   - IntentAct: tool-executor deferred (no-op today; the reply says so).
//   - IntentNote / IntentQuery: chroma/RAG deferred (no-op; reply says so).
//   - Clarify: the router's stage-3 fired; no action.
//
// Returns "" when the Replier should phrase the reply (the default path);
// returns a non-empty string when the action path wants to OVERRIDE the
// reply text (e.g. an action error the user should hear SPECIFICALLY, not
// a generic "ok"). Errors surface as a short reply text the user hears.
func (h *reactiveHandler) applyAction(ctx context.Context, dec router.Decision) string {
	if dec.Clarify {
		return "" // the Replier phrases clarify
	}
	if handler, ok := actionHandlers[dec.Intent]; ok {
		return handler(h, ctx, dec)
	}
	return ""
}

// detectPattern extracts an event from the written fact and runs the pattern
// detector. If a stable recurring pattern is found and no proposed routine
// exists for this action+object yet, one is created and the user is prompted
// to confirm via the park() mechanism. Returns the suggestion phrase when a
// new proposal was created and parked; "" otherwise.
func (h *reactiveHandler) detectPattern(ctx context.Context, factID int64, key, value string, ts time.Time) string {
	ev := pattern.Extract(factID, key, value, ts)
	if ev == nil {
		return "" // not an actionable event
	}
	if _, err := h.dataStore.CreateEvent(ctx, factID, ev.Action, ev.Object, ts); err != nil {
		log.Printf("voice: create event: %v", err)
		return ""
	}
	// Detect+propose (Vikunja #43) is shared with the digestion tick's
	// proactive scan — see patterns.go. Event *extraction* above stays here,
	// tied to this fact write; detection over the accumulated history does
	// not need to happen right now for the voice path to have already done
	// its job — it's dedupe-safe to also let the next tick find the same
	// pattern independently.
	r, id, err := detectAndPropose(ctx, h.dataStore, ev.Action, ev.Object, ts)
	if err != nil {
		log.Printf("voice: detect pattern %s/%s: %v", ev.Action, ev.Object, err)
		return ""
	}
	if r == nil {
		return "" // not enough data, too irregular, or already proposed/decided
	}
	log.Printf("voice: proposed routine: %s/%s every %.1f days", r.Action, r.Object, r.IntervalDays)

	// Park the proposal for voice confirmation.
	phrase := pattern.PhraseRoutine(r)
	h.mu.Lock()
	h.pendingRoutine = &pendingRoutineConfirm{
		routineID: id,
		action:    r.Action,
		object:    r.Object,
		interval:  r.IntervalDays,
		phrase:    phrase,
		expiry:    ts.Add(confirmTTL),
	}
	h.mu.Unlock()
	return phrase
}

// resolveQuietToggle — pre-route keyword check. Returns (reply, true) when
// the utterance is a quiet-on/off command; ("", false) otherwise. Called from
// runTurn BEFORE the router so a classifier miscue can't drop it — which means
// both the voice path and the text path (mavweb /api/chat, telegram) reach it,
// so a false positive here is a network-reachable way to flip a daemon-wide
// setting. See classifyQuietToggle for the matching rule.
func (h *reactiveHandler) resolveQuietToggle(ctx context.Context, text string) (string, bool) {
	on, off := classifyQuietToggle(text)
	if !on && !off {
		return "", false
	}
	val := "false"
	reply := "тихий режим выключен."
	if on {
		val = "true"
		reply = "тихий режим включён. буду реже напоминать."
	}
	if _, err := h.api.WriteFact(ctx, ipc.WriteFactReq{
		Ts:         h.now(),
		Kind:       "config",
		Key:        "quiet_hours",
		Value:      val,
		Source:     "tap:voice",
		Confidence: 1.0,
	}); err != nil {
		log.Printf("voice: write quiet_hours: %v", err)
		return "не получилось переключить тихий режим.", true
	}
	return reply, true
}

// quietInflections — the inflectional endings a stem may carry and still be
// the same word. Adjective/adverb/noun/verb endings, all ≤3 letters. This is
// what separates "тихий"/"тихом"/"тихо" (stem "тих" + a real ending) from
// "тихонько"/"потихоньку", which are different words: "онько" is not an
// ending, and "потихоньку" doesn't start with the stem at all.
var quietInflections = []string{
	"", "а", "е", "и", "й", "о", "у", "ы", "ю", "я",
	"ая", "ее", "ей", "ем", "ие", "ий", "им", "их", "ия", "ию", "ое", "ой", "ом", "ую", "ые", "ый", "ым", "ых", "ья",
	"ами", "ого", "ому", "ыми", "ать", "ить", "ять",
}

// quietStem reports whether tok is the given stem carrying at most one
// inflectional ending. Word boundaries come from tokenisation (see
// quietTokens), not from a regexp — Go's \b is ASCII-oriented and treats every
// Cyrillic letter as a non-word character, so `\bтих\b` would happily match
// inside "тихонько". Comparing whole tokens sidesteps that entirely.
func quietStem(tok, stem string) bool {
	if !strings.HasPrefix(tok, stem) {
		return false
	}
	suffix := tok[len(stem):]
	for _, e := range quietInflections {
		if suffix == e {
			return true
		}
	}
	return false
}

// quietTokens splits an utterance into lowercase word tokens, dropping
// punctuation and spacing. Unicode-aware, so Cyrillic words tokenise the same
// way ASCII ones do.
func quietTokens(text string) []string {
	return strings.FieldsFunc(strings.ToLower(strings.TrimSpace(text)), func(r rune) bool {
		return !unicode.IsLetter(r) && !unicode.IsDigit(r)
	})
}

// quietPhrase matches a pattern (a sequence of stems) against the token list.
// Multi-word patterns match any contiguous run of tokens — "включи тихий
// режим" carries "тихий режим". Single-word patterns match ONLY when they are
// the whole utterance: bare "тихо" is a command, but "в комнате тихо" is a
// remark about the room and must not flip a daemon-wide setting.
func quietPhrase(tokens, pattern []string) bool {
	if len(pattern) == 0 || len(tokens) < len(pattern) {
		return false
	}
	if len(pattern) == 1 {
		return len(tokens) == 1 && quietStem(tokens[0], pattern[0])
	}
	for i := 0; i+len(pattern) <= len(tokens); i++ {
		hit := true
		for j, stem := range pattern {
			if !quietStem(tokens[i+j], stem) {
				hit = false
				break
			}
		}
		if hit {
			return true
		}
	}
	return false
}

// quietOffPhrases / quietOnPhrases — the toggle vocabulary, as stem sequences.
var (
	quietOffPhrases = [][]string{
		{"quiet", "off"}, {"quiet", "end"},
		{"громк", "режим"}, {"шумн", "режим"},
		{"отмен", "тих"}, {"выключ", "тих"}, {"не", "тих"},
	}
	quietOnPhrases = [][]string{
		{"quiet", "on"}, {"quiet", "mode"},
		{"тих", "режим"}, {"не", "шум"}, {"не", "беспоко"},
		{"тих"},
	}
)

// classifyQuietToggle reads an utterance as a quiet-mode command. OFF is
// resolved before ON for the same reason classifyConfirm checks negatives
// first: the OFF phrases are built out of the ON words ("выключи тихий"
// contains "тихий"), so scanning ON first would shadow them and "выключи
// тихий режим" would turn quiet mode on. Negation wins.
func classifyQuietToggle(text string) (on, off bool) {
	tokens := quietTokens(text)
	for _, p := range quietOffPhrases {
		if quietPhrase(tokens, p) {
			return false, true
		}
	}
	for _, p := range quietOnPhrases {
		if quietPhrase(tokens, p) {
			return true, false
		}
	}
	return false, false
}

// replySystem answers system-observable queries using the handler's clock
// and (in future) system interfaces. The decision's utterance is parsed
// for keywords to determine what the user is asking about.
func (h *reactiveHandler) replySystem(ctx context.Context, dec router.Decision) string {
	u := strings.ToLower(dec.Utterance)
	now := h.now()

	// stage-0 grammars catch the exact time/date patterns, but duration
	// queries ("сколько времени прошло") bypass the grammar's build filter
	// and can reach replySystem via the classifier path. Guard against them.
	if hasDurationWords(u) {
		return "пока не умею отвечать на этот вопрос."
	}

	switch {
	case strings.Contains(u, "час") || strings.Contains(u, "врем"):
		// "который час в киеве" — she keeps one clock, so any named place gets
		// the honest answer. Never local time dressed up as the city's.
		if mentionsUnknownPlace(u) {
			return onlyLocalTimeReply
		}
		return "сейчас " + ruClock(now)
	case strings.Contains(u, "день") || strings.Contains(u, "числ"):
		// "какое число завтра" — answer for the day the user asked about,
		// not today. Reuses the router's calendar day-word parser.
		day := now
		prefix := "сегодня"
		if d, ok := router.ParseCalendarDate(u, now); ok {
			day = d
			prefix = dayPrefix(now, d)
		} else if mentionsUnknownDay(u) {
			// He named a day she cannot work out ("в пятницу", "через неделю").
			// Answering today's date here would be the same silent wrong answer
			// this arm was fixed for, so say what she can do instead.
			return onlyNearDaysReply
		}
		dow := ruWeekdays[day.Weekday()]
		month := ruMonths[day.Month()-1]
		return fmt.Sprintf("%s %s, %d %s %d года", prefix, dow, day.Day(), month, day.Year())
	case strings.Contains(u, "кто дома") || strings.Contains(u, "человек дома"):
		return "присутствие пока не подключено к голосовому запросу."
	case strings.Contains(u, "памят") || strings.Contains(u, "процессор") || strings.Contains(u, "загрузк") || strings.Contains(u, "статус") || strings.Contains(u, "работа") || strings.Contains(u, "сервис") || strings.Contains(u, "диск") || strings.Contains(u, "ip") || strings.Contains(u, "аптайм") || strings.Contains(u, "трафик") || strings.Contains(u, "интернет"):
		return "системная статистика пока не подключена."
	default:
		return "пока не умею отвечать на этот вопрос."
	}
}

// chatHistory collects dialogue turns from the session store for the current
// conversation. Returns prior user utterances (newest last) up to a depth of
// 4 turns. Returns nil when there's no session or no history.
func (h *reactiveHandler) chatHistory() []dialogue.Turn {
	if h.dialogueSessions == nil {
		return nil
	}
	now := h.now()
	prev := h.dialogueSessions.Get(voiceDialogueID, now)
	if prev == nil {
		return nil
	}
	// History already includes the immediate prior turn (set by the dialogue
	// merge at lines 373-395), plus up to 3 more from deeper history.
	out := make([]dialogue.Turn, 0, 1+len(prev.History))
	out = append(out, dialogue.Turn{
		Intent: prev.Intent,
		Slots:  prev.Slots,
		Text:   prev.Slots.Text,
	})
	out = append(out, prev.History...)
	return out
}

// reply wraps a text reply through TTS to produce a PushToTalkResp. If TTS
// fails, the response carries an empty audio + the text — the client can
// still display text if it can't play. The routedChannels field is
// reserved for a future "the dispatcher also forwarded to ntfy/telegram"
// reply (today the reactive path doesn't dispatch nudges; that's the loop
// tick's job).
func (h *reactiveHandler) reply(ctx context.Context, text string, _ []string) (voice.PushToTalkResp, error) {
	spoken := ttsnorm.Speakable(text)
	log.Printf("voice: reply → %q", text)
	audioOut, err := h.tts.Synthesize(ctx, spoken)
	if err != nil {
		log.Printf("voice: tts error: %v", err)
		return voice.PushToTalkResp{ReplyText: text, ReplyAudio: audio.Audio{}}, nil
	}
	return voice.PushToTalkResp{ReplyText: text, ReplyAudio: audioOut}, nil
}