Maven/cmd/mavend/quiet_toggle.go

// Quiet-mode toggle recognition — the pre-route keyword check that lets
// "тихий режим" flip the daemon-wide quiet_hours config without going through
// the router. Moved out of voice.go unchanged (Vikunja #321); the tests live in
// quiet_toggle_test.go.
package main

import (
	"context"
	"log"
	"strings"
	"unicode"

	"github.com/kami/maven/internal/ipc"
	"github.com/kami/maven/internal/morph"
	"github.com/kami/maven/internal/phraser"
)

// 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.
//
// src is the channel the utterance arrived on, and it is written straight into
// the fact. Every toggle used to be stored as "tap:voice", including the ones
// typed into the web UI, which left the facts table claiming a microphone flipped
// a setting nobody spoke to. This is the one function where that matters most:
// when he goes looking at why quiet mode is on, provenance is the first column
// he reads.
func (h *reactiveHandler) resolveQuietToggle(ctx context.Context, text string, src turnSource) (string, bool) {
	on, off := classifyQuietToggle(text)
	if !on && !off {
		return "", false
	}
	val := "false"
	reply := phraser.Ack(phraser.AckQuietOff, nil)
	if on {
		val = "true"
		reply = phraser.Ack(phraser.AckQuietOn, nil)
	}
	if _, err := h.api.WriteFact(ctx, ipc.WriteFactReq{
		Ts:         h.now(),
		Kind:       "config",
		Key:        "quiet_hours",
		Value:      val,
		Source:     string(src),
		Confidence: 1.0,
	}); err != nil {
		log.Printf("voice: write quiet_hours: %v", err)
		return phraser.Ack(phraser.FailQuiet, nil), true
	}
	return reply, true
}

// quietStem reports whether tok is one of the words a vocabulary slot accepts.
// A slot is written as alternatives joined by "|", and an alternative comes in
// two flavours:
//
//   - a dictionary form, matched through the dictionary, so every case and
//     gender of it counts. This is what the nouns and adjectives want: "тихий",
//     "тихом", "тихо" and "тише" are one word.
//   - a form prefixed with "=", matched as the exact token. This is what the
//     VERBS want, and it is not a shortcut. A command is an imperative, and the
//     dictionary quite correctly files "говори" and "говорил" under one lemma —
//     so lemma-matching a verb slot read "он говорил тихим голосом весь вечер",
//     a remark about his evening, as an order to go quiet. Aspect pairs are two
//     separate verbs, which is why several imperatives are listed by hand.
//
// 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.
//
// The comparison is a dictionary lookup, not a stem plus a list of 36 endings
// (Vikunja #526). The distinction the old comment described is exactly the one a
// dictionary makes: "тихий", "тихом", "тихо" and "тише" are one word inflected,
// while "тихонько" and "потихоньку" are different words — and the dictionary
// knows that without anybody deciding that "онько" is not an ending.
func quietStem(tok, slot string) bool {
	for _, form := range strings.Split(slot, "|") {
		if exact, ok := strings.CutPrefix(form, "="); ok {
			if tok == exact {
				return true
			}
			continue
		}
		if morph.SameWord(tok, form) {
			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 sequences of
// dictionary forms. They used to be truncated stems ("тих", "выключ"), which is
// what the ending list existed to complete; a dictionary form needs no
// completing (Vikunja #526).
//
// Note what is NOT here any more: the OFF list used to carry {"не", "тих"} and
// the ON list {"не", "шум"} / {"не", "беспоко"}. Both were adjacency patterns,
// and negation is not an adjacency phenomenon. "не надо тихий режим" put two
// tokens between "не" and "тих", so the OFF pattern missed, the ON pattern
// {"тих","режим"} matched, and asking for quiet mode to stop turned it on.
// Negation is handled by quietNegators below, over the whole utterance.
var (
	quietOffPhrases = [][]string{
		{"quiet", "off"}, {"quiet", "end"},
		{"громкий", "режим"}, {"шумный", "режим"},
		{"=отмени|=отменяй|=отменить", "тихий"},
		{"=выключи|=выключай|=выключить", "тихий"},
	}
	quietOnPhrases = [][]string{
		{"quiet", "on"}, {"quiet", "mode"},
		{"тихий", "режим"}, {"не", "=шуми|=шумите"}, {"не", "=беспокой|=беспокоить"},
		// The noun form and the comparative. "режим тишины" is how the
		// setting is named half the time, and "сделай потише" is how it is
		// actually asked for out loud. Both used to fall through to the
		// router, which has no quiet intent, so the command did nothing.
		{"режим", "тишина"}, {"=сделай", "тихий"}, {"=сделай", "потише"},
		{"=говори", "тихий"}, {"=будь", "потише"},
		{"тихий"}, {"потише"},
	}
)

// quietWordStems — every word that names the setting. Used by the
// negated-but-unmatched fallback in classifyQuietToggle, which has to
// recognise "хватит тишины" without an ON phrase having matched.
var quietWordStems = []string{"тихий", "тишина", "потише"}

// quietNegatorWords — negators that are whole words with no useful stem.
var quietNegatorWords = map[string]bool{
	"не": true, "нет": true, "хватит": true, "no": true, "not": true, "off": true,
}

// quietNegatorStems — negators that inflect. Imperatives, matched exactly for
// the reason quietStem gives: "выключи" is a command and "выключил" is a report
// about earlier, and one lemma covers both. "выключатель" was never a negator
// and is not one now.
var quietNegatorStems = []string{
	"=выключи|=выключай|=выключить", "=отмени|=отменяй|=отменить",
	"=прекрати|=прекращай|=прекратить", "=убери|=убирай|=убрать",
	"stop", "cancel", "disable",
}

// quietNegated reports whether the utterance carries a negator. Two ON phrases
// are themselves built on "не" — "не шуми", "не беспокой" — and those are
// requests FOR quiet, so they are excluded before the scan: a negator only
// counts when it is not part of the phrase that matched.
func quietNegated(tokens []string, matched []string) bool {
	if len(matched) > 0 && matched[0] == "не" {
		return false
	}
	for _, t := range tokens {
		if quietNegatorWords[t] {
			return true
		}
		for _, stem := range quietNegatorStems {
			if quietStem(t, stem) {
				return true
			}
		}
	}
	return false
}

// classifyQuietToggle reads an utterance as a quiet-mode command.
//
// Explicit OFF phrases resolve first, for the same reason classifyConfirm
// checks negatives first: they are built out of the ON words ("выключи тихий"
// contains "тихий"), so scanning ON first would shadow them. An ON phrase that
// matches is then checked for negation across the whole utterance, so any way
// of saying "not quiet mode" turns it off rather than on.
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) {
			if quietNegated(tokens, p) {
				return false, true
			}
			return true, false
		}
	}
	// No ON phrase matched, but he negated a quiet word: "не тихо", "хватит
	// тихого режима". The ON vocabulary cannot see these — bare "тих" only
	// matches a one-token utterance, by design, so the negator pushes the token
	// count past it — and reading them as "no command" would leave quiet mode
	// on after he asked for it to stop.
	if quietNegated(tokens, nil) {
		for _, t := range tokens {
			for _, stem := range quietWordStems {
				if quietStem(t, stem) {
					return false, true
				}
			}
		}
	}
	return false, false
}