Move the quiet-toggle and pattern-extraction slices out of voice.go (#321)

Continues the decomposition PR #50 started. voice.go 542 -> 365: quiet_toggle.go 144 resolveQuietToggle, quietInflections, quietStem, quietTokens, quietPhrase, quietOn/OffPhrases, classifyQuietToggle (quiet_toggle_test.go already existed for these) patterns.go +44 detectPattern, next to detectAndPropose which it calls and which patterns.go's own header already pointed at What is left in voice.go is the handler: reactiveHandler, HandlePushToTalk, handleText, runTurn, applyAction, replySystem, chatHistory, reply. Move-only: all 133 distinct non-blank lines removed from voice.go were matched in the two destination files, zero lines added to voice.go. The only non-move edits are import lists (log added to patterns.go, unicode and internal/pattern dropped from voice.go) and two comments that pointed at voice.go for code that is no longer there.
2026-08-01 01:30:06 +04:00
parent 9190f897a3
commit c5317eb2b4
3 changed files with 191 additions and 178 deletions
@@ -0,0 +1,144 @@
+// 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"
+)
+
+// 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
+}