Maven/internal/router/stage0.go

package router

import (
	"regexp"
	"strings"
)

// Grammar — one stage-0 exact-match pattern. Wake-word + known command grammar
// hits the allowlist directly, skips the classifier (lowest latency — the vosk
// command path). Boring high-frequency acts for free.
//
// A Grammar returns a fully-formed Decision (intent + slots) at confidence 1.0
// when its pattern matches AND its Build returns ok=true; the router stops the
// cascade. Grammar rules are code, not config — same boundary as rules-as-code
// in the loop. The tool registry populates the verb set at daemon wiring time.
type Grammar struct {
	Name    string
	Pattern *regexp.Regexp // matched against the raw utterance
	Build   func(match []string) (Decision, bool)
}

// wakeWordAct — "maven, restart nginx" / "maven restart nginx" → the remainder
// is matched against the act allowlist. A non-match returns ok=false so the
// cascade falls through to the classifier (a wakeword prefix alone doesn't
// guarantee a known command — "maven, i'm tired" is a fact, not an act).
var wakeWordAct = regexp.MustCompile(`(?i)^\s*(?:maven|мэйвен|мейвен|майвен|мавена?|мэвен)[,:.!\s]+(.+)$`)

// wakeToken matches a leading wake-word token in any script the STT commonly
// produces for "Maven" — Latin "maven" or a Cyrillic phonetic rendering. The
// STT is a Russian model, so it transcribes the spoken wake word phonetically
// almost every time; matching only the Latin spelling meant stage-0 grammars
// (time/date/reminder) silently missed nearly every wake-worded utterance and
// fell through to the classifier, which misroutes time queries into the
// reminder intent (dense time-vocab centroid, see SystemTimeDateGrammars).
var wakeToken = regexp.MustCompile(`(?i)^\s*(?:maven|мэйвен|мейвен|майвен|мавена?|мэвен)[,:.!\s]*`)

// StripWakeToken removes a leading wake-word token (any script/spelling seen
// in wakeToken) and reports whether one was found.
func StripWakeToken(u string) (string, bool) {
	loc := wakeToken.FindStringIndex(u)
	if loc == nil {
		return u, false
	}
	rest := strings.TrimSpace(u[loc[1]:])
	if rest == "" {
		return u, false
	}
	return rest, true
}

// DefaultGrammars — the wake-word act fast path. The ActMatcher is the same
// allowlist stage-2 act extraction uses (single source of truth for the fn
// list). Returns nil grammars if no matcher is wired (the daemon always wires
// one — the guard is for tests that only exercise the classifier).
func DefaultGrammars(actMatcher ActMatcher) []Grammar {
	if actMatcher == nil {
		return nil
	}
	return []Grammar{
		{
			Name:    "wakeword-act",
			Pattern: wakeWordAct,
			Build: func(m []string) (Decision, bool) {
				rest := strings.TrimSpace(m[1])
				fn, args, ok := actMatcher.Match(rest)
				if !ok {
					return Decision{}, false // fall through to classifier
				}
				return Decision{
					Stage:      0,
					Intent:     IntentAct,
					Confidence: 1.0,
					Slots:      Slots{Fn: fn, Args: args, HasFn: true, Text: rest},
				}, true
			},
		},
	}
}

// --- напомни / remind me stage-0 grammar ---
//
// "напомни через час выпить воды" / "remind me in 30 minutes to water plants"
// routes directly to IntentReminder, bypassing the classifier entirely.
// Without this grammar the reminder centroid (dense with time-lexicon) pulls
// non-reminder time queries toward it, and the verb+action overlap pushes
// actual reminders toward fact — a double contamination. Stage 0 fixes both.
//
// The grammar captures the part after "напомни"/"remind me" into Slots.Text
// so the daemon's time parser can extract the fire time from it. The grammar
// itself does NOT parse time — that's the extractor's job (stage 2), but
// stage 0 skips the extractor. The daemon's applyAction fallback calls the
// time parser for stage-0 reminders that arrive without HasTime.
func ReminderGrammar() Grammar {
	return Grammar{
		Name:    "reminder-wakeword",
		Pattern: regexp.MustCompile(`(?i)^\s*(?:напомни|remind me)[\s,:]+(.+)$`),
		Build: func(m []string) (Decision, bool) {
			rest := strings.TrimSpace(m[1])
			if rest == "" {
				return Decision{}, false
			}
			return Decision{
				Stage:      0,
				Intent:     IntentReminder,
				Confidence: 1.0,
				Slots:      Slots{Text: rest},
			}, true
		},
	}
}

// SystemTimeDateGrammars — stage-0 grammars for high-frequency system queries
// that replySystem handles deterministically (time, date, day-of-week).
// "сколько времени" is seeded in BOTH system.txt and query.txt (a centroid
// collision), and the reminder centroid contaminates any utterance with time
// vocabulary. These grammars route directly to IntentSystem, skipping the
// classifier entirely — the answer is always deterministic.
//
// The time-query grammar uses a broad pattern (prefix match) with a Build
// filter: utterances containing "прошло"/"осталось" or starting with "до"
// after the time expression are elapsed/duration queries that belong to the
// classifier, not to replySystem's "what time is it" handler.
func SystemTimeDateGrammars() []Grammar {
	return []Grammar{
		{
			Name:    "time-query",
			Pattern: regexp.MustCompile(`(?i)^\s*сколько\s+(сейчас\s+)?времени(.*)$`),
			Build:   timeQueryBuild,
		},
		{
			Name:    "clock-query",
			Pattern: regexp.MustCompile(`(?i)^\s*который\s+(сейчас\s+)?час(\s+у\s+нас|\s+в\s+\w+)?\s*[?!.]?\s*$`),
			Build:   timeDateBuild,
		},
		{
			Name:    "date-query",
			Pattern: regexp.MustCompile(`(?i)^\s*(?:какой\s+сегодня\s+(?:день|день\s+недели|число)|какое\s+сегодня\s+число)\s*[?!.]?\s*$`),
			Build:   timeDateBuild,
		},
	}
}

// AgendaQueryGrammars — stage-0 grammars for "what have I got on" questions,
// routed to IntentQuery so they reach the query chain (queryDayPlan,
// queryCalendar) instead of replySystem.
//
// This exists because the model puts them in IntentSystem. Measured on the
// deployed daemon 01-08-2026: "что у меня сегодня" and "что у меня в календаре
// сегодня" both routed system, and replySystem has no agenda arm, so both
// answered "пока не умею". The fixture has said query since ru-query-019 was
// written ("the clock/date system rule must not swallow it"); the daemon
// disagreed with the fixture and the daemon was wrong.
//
// Routing, not answering. These set the intent and nothing else — which source
// in the query chain claims the turn stays the chain's decision, and a
// question with no date still falls through queryCalendar to recall.
//
// Deliberately not folded into SystemTimeDateGrammars: those exist to send
// utterances TO system, these exist to keep utterances OUT of it, and one
// function returning both would read as a list of clock rules.
func AgendaQueryGrammars() []Grammar {
	return []Grammar{
		{
			// An explicit calendar noun is unambiguous wherever it appears:
			// "что в календаре на завтра", "покажи расписание на среду".
			Name:    "calendar-query",
			Pattern: regexp.MustCompile(`(?i)(календар|расписани|повестк)`),
			Build:   agendaQueryBuild,
		},
		{
			// The agenda phrasing with no calendar noun. Anchored at the start
			// and requiring the possessive, so it reads as a question about his
			// day: "что у меня сегодня", "что у меня стоит на послезавтра".
			// "у меня кончилась вода" is a fact and does not match.
			Name: "agenda-query",
			// (\s|[?!.]|$) rather than \b: Go's \b is ASCII-only, so it does
			// not see a boundary after a Cyrillic letter and the pattern
			// silently never fires.
			// "во сколько у меня встреча" is the same agenda question with a
			// clock word in front, and the clock word is what sent it to
			// system (fixture ru-query-013).
			Pattern: regexp.MustCompile(`(?i)^\s*(что|чего|какие|сколько|во\s+сколько|когда)\s+у\s+меня(\s|[?!.]|$)`),
			Build:   agendaQueryBuild,
		},
		{
			// A plan noun aimed at a named day, with no possessive to anchor
			// on: "какие планы на завтра", "что по делам в среду". The rule
			// above wants "у меня" and this phrasing never has it, so
			// "какие планы на завтра" answered "пока не умею" while "какие
			// планы на сегодня" worked (Vikunja #471). The day word is what
			// makes it an agenda question rather than a topic.
			Name: "plan-day-query",
			// Only "план" and "дел". A verb stem like "встреч" would take
			// "встречаемся в среду", which is him telling her something, not
			// asking.
			Pattern: regexp.MustCompile(`(?i)(^|\s)(план|дел)[а-я]*\s+(на|в|во|по)\s+` + dayWordPattern + `(\s|[?!.]|$)`),
			Build:   agendaQueryBuild,
		},
		{
			// "что дальше?" — the rest of the day, with no possessive and no
			// plan word for the rules above to anchor on, so neither claimed
			// it and the model called it a fact (Vikunja #498). The predicate
			// for the same utterance already exists as IsRestOfDayQuery, one
			// layer down in the query chain; this is what gets the turn there.
			//
			// "и что там дальше" and "что потом дальше" are the same question,
			// and "what's next" splits into two tokens, hence the optional
			// middles rather than plain adjacency.
			Name:    "rest-of-day-query",
			Pattern: regexp.MustCompile(`(?i)^\s*(и\s+)?(что|чего|what'?s?)\s+(там\s+|ещё\s+|еще\s+|потом\s+|у\s+меня\s+)?(дальше|next)(\s|[?!.]|$)`),
			Build:   agendaQueryBuild,
		},
		{
			// A named event with no calendar word at all: "когда планёрка?",
			// "во сколько созвон". He is asking when something on his calendar
			// happens, and the noun is the only signal. Closed list, so "когда
			// битва при Ватерлоо" is still a world question.
			Name:    "event-time-query",
			Pattern: regexp.MustCompile(`(?i)^\s*(когда|во\s+сколько|в\s+котором\s+часу)\s+(будет\s+|у\s+нас\s+)?(планёрк|планерк|встреч|созвон|митинг|совещани|звонок|созвон|приём|прием|интервью|собеседовани|тренировк|урок|занятие|пара)[а-я]*(\s|[?!.]|$)`),
			Build:   agendaQueryBuild,
		},
	}
}

// chatNarrativeTopics — the things "расскажи X" asks for that are not
// questions about the world. She is being asked to entertain or to describe
// herself, and the query chain has no source for either.
var chatNarrativeTopics = regexp.MustCompile(`(?i)(анекдот|шутк|сказк|истори[юи]\s+на\s+ночь|о\s+себе|про\s+себя|о\s+нас|про\s+нас)`)

// NarrativeQueryGrammar — stage-0 rule for "расскажи про X", "объясни X",
// "опиши X", routed to IntentQuery.
//
// It carries no question mark and no interrogative, so the model called
// "расскажи про битву при Ватерлоо" a fact and tried to store the answer it
// invented (Vikunja #470, point 1). The write is contained now — actions_fact
// refuses a question-shaped write and re-runs the turn as a query — but every
// such utterance still paid a model round trip to reach a decision one regex
// can make, and the fixture still scored the routing as wrong (Vikunja #498).
//
// The lexicon is narrativeRequests in question.go, which IsQuestionShaped
// already uses. One list, two callers: a word that marks an utterance as
// asking must not mark it here and not there.
//
// Routing, not answering. Which source claims the turn is still the query
// chain's decision, and the personal boundary still sits where it sat.
func NarrativeQueryGrammar() Grammar {
	return Grammar{
		Name: "narrative-query",
		// (\s|[?!.]|$) rather than \b: Go's \b is ASCII-only and never fires
		// after a Cyrillic letter, so the pattern would silently never match.
		Pattern: regexp.MustCompile(`(?is)^\s*(` + strings.Join(narrativeRequests, "|") + `)(?:\s+(?:мне|нам|us|me))?(?:\s+(?:про|о|об|about))?(\s+.+)$`),
		Build: func(m []string) (Decision, bool) {
			topic := strings.TrimSpace(m[2])
			// "расскажи" with nothing after it is a conversational opener,
			// and there is no topic to look up.
			if topic == "" {
				return Decision{}, false
			}
			// Against the whole utterance, not the topic: "о себе" has its
			// preposition eaten by the pattern, leaving a bare "себе".
			if chatNarrativeTopics.MatchString(m[0]) {
				return Decision{}, false
			}
			return Decision{
				Stage:      0,
				Intent:     IntentQuery,
				Confidence: 1.0,
				Slots:      Slots{Text: topic},
			}, true
		},
	}
}

// FeedQueryGrammar — stage-0 rule for "что нового в лентах?", routed to
// IntentQuery so it reaches queryFeeds.
//
// Same shape of defect as the agenda grammars: the model calls it system, and
// replySystem has no feeds arm, so the documented utterance of task 258 step 1
// answered "пока не умею отвечать на этот вопрос." while the same question
// worded with "новостях" worked (Vikunja #474).
//
// An ask word at the front and a feed noun after it are both required, which
// is the same pair ParseFeedQuery wants. "что нового?" on its own is a greeting
// — the most common opener in the language — and vagueNouns in feeds.go exists
// to keep it out of the feed reader; routing it to query here would put it
// back. "у меня новая лента в инстаграме" carries the noun without the ask and
// stays the statement it is.
func FeedQueryGrammar() Grammar {
	return Grammar{
		Name: "feed-query",
		// (\s|[?!.]|$) rather than \b, which is ASCII-only and never fires next
		// to a Cyrillic letter.
		Pattern: regexp.MustCompile(`(?i)^\s*(что|какие|расскажи|покажи|почитай|прочитай)\s+.*(лент|новостн)[а-я]*(\s|[?!.]|$)`),
		Build:   agendaQueryBuild,
	}
}

// dayWordPattern — the day words an agenda question can name. Weekdays appear
// in the accusative and prepositional forms the questions actually use ("в
// среду", "на среде"), which is why the stems carry an inflection tail rather
// than a fixed ending.
const dayWordPattern = `(сегодня|завтра|послезавтра|выходн[а-я]+|недел[а-я]+|понедельник[а-я]*|вторник[а-я]*|сред[ауые][а-я]*|четверг[а-я]*|пятниц[ауые][а-я]*|суббот[ауые][а-я]*|воскресень[ея][а-я]*)`

// agendaQueryBuild — shared Build for the agenda grammars and the feed one,
// which all do the same single thing: keep the utterance out of IntentSystem
// and let the query chain decide who answers it. Confidence 1.0 on
// the intent only: the utterance travels intact and the query chain's own
// matchers decide the rest.
func agendaQueryBuild(m []string) (Decision, bool) {
	return Decision{
		Stage:      0,
		Intent:     IntentQuery,
		Confidence: 1.0,
	}, true
}

// timeQueryBuild — Build for the time-query grammar. Returns ok=false for
// elapsed/duration queries ("сколько времени прошло", "сколько времени
// осталось", "сколько времени до") so they fall through to the classifier.
// The classifier handles them as query intent (notes RAG), not system.
func timeQueryBuild(m []string) (Decision, bool) {
	suffix := strings.TrimSpace(m[2])
	if suffix != "" && !strings.HasPrefix(suffix, "?") {
		lower := strings.ToLower(suffix)
		// If the first word after "времени" is a duration marker, this is an
		// elapsed-time query, not a "what time is it" query.
		firstWord := strings.Fields(lower)
		if len(firstWord) > 0 {
			switch firstWord[0] {
			case "прошло", "осталось", "до", "пройдет", "минуло", "проходит":
				return Decision{}, false
			}
		}
	}
	return Decision{
		Stage:      0,
		Intent:     IntentSystem,
		Confidence: 1.0,
	}, true
}

// timeDateBuild — shared Build for clock-query and date-query grammars. Returns a
// Decision routed to IntentSystem with the original utterance intact, so the
// daemon's replySystem handler can keyword-match and answer it.
func timeDateBuild(m []string) (Decision, bool) {
	return Decision{
		Stage:      0,
		Intent:     IntentSystem,
		Confidence: 1.0,
	}, true
}