Maven/cmd/mavend/turnrole.go

package main

import (
	"strings"
	"unicode"

	"github.com/kami/maven/internal/dialogue"
	"github.com/kami/maven/internal/lexicon"
	"github.com/kami/maven/internal/router"
)

// turnRole — what this utterance IS, relative to the action Maven is in the
// middle of assembling. The five roles are the owner's vocabulary (Vikunja
// #558), plus the sixth answer a resolver is allowed to give: not_applicable,
// which hands the turn back to generic dispatch.
//
// It exists because the arbitration used to be ordering. The clarify resolver,
// the confirm gate, the follow-up merge and the repair marker all ran BEFORE
// the router, so the claimant holding conversational state decided what an
// utterance was without asking the one component whose job that is — and on
// 2026-08-05 "какая сейчас погода в Риме?" became the time of a reminder,
// because the extractor found "сейчас" in it and nothing looked at the rest.
//
// The rule that fixes that: a routed decision which stands on its own — its own
// intent, its own slots filled from its own words — is not an answer, whatever
// the extractor found inside it.
type turnRole string

const (
	roleAnswer        turnRole = "answer"         // it fills the slot she asked about
	roleCorrection    turnRole = "correction"     // it replaces a value she already had
	roleSideQuery     turnRole = "side_query"     // a question of its own, asked mid-flow
	roleNewRequest    turnRole = "new_request"    // a different request entirely
	roleAside         turnRole = "aside"          // something he stated, not an answer
	roleCancel        turnRole = "cancel"         // call the pending action off
	roleNotApplicable turnRole = "not_applicable" // nothing is pending; not our turn
)

// frameWords — the words that can stand around a bare slot value without adding
// a request. Every member is a closed class from internal/lexicon: the frame
// itself, the interrogatives, the parts of a spoken clock, the days and the
// months. Assembled once; the sets are copies, so this cannot edit them.
var frameWords = buildFrameWords()

func buildFrameWords() map[string]bool {
	out := make(map[string]bool)
	add := func(list []string) {
		for _, w := range list {
			out[strings.ToLower(w)] = true
		}
	}
	add(lexicon.SlotValueFrame())
	add(lexicon.Interrogatives())
	add(lexicon.PartsOfDay())
	add(lexicon.HalfHourWords())
	add(lexicon.DayOffsetWords())
	for i := 0; i < 7; i++ {
		out[lexicon.Weekday(i)] = true
	}
	for m := 1; m <= 12; m++ {
		out[lexicon.MonthGenitive(m)] = true
	}
	for hh := 0; hh <= 23; hh++ {
		add(strings.Fields(lexicon.HourSpoken(hh)))
	}
	return out
}

// cancelWords — the same, for the words that call the pending action off.
var cancelWords = buildCancelWords()

func buildCancelWords() map[string]bool {
	out := make(map[string]bool)
	for _, w := range lexicon.DialogueCancel() {
		out[strings.ToLower(w)] = true
	}
	return out
}

// turnTokens splits an utterance the way the router's own predicates do: over
// letters and digits, lowercased, so punctuation and a clock's colon fall out.
func turnTokens(text string) []string {
	return strings.FieldsFunc(strings.ToLower(text), func(r rune) bool {
		return !unicode.IsLetter(r) && !unicode.IsDigit(r)
	})
}

// ownContent lists the tokens of an utterance that are neither frame nor value:
// what it is about, over and above the thing she asked for. Numbers go out
// because a number is the commonest slot value there is, and the closed number
// and day lexicons go out with them.
//
// Empty ⇒ the utterance is a slot value and nothing else, however it is dressed
// up. That is the whole test, and it is what separates "а что если в 11:00" —
// which is a time, hedged — from "какая сейчас погода в Риме?", which leaves
// "погода" and "риме" behind and is therefore about something.
func ownContent(text string) []string {
	var out []string
	for _, tok := range turnTokens(text) {
		if frameWords[tok] || lexicon.IsFillerParticle(tok) {
			continue
		}
		if _, ok := lexicon.Cardinal(tok); ok {
			continue
		}
		if _, ok := lexicon.Ordinal(tok); ok {
			continue
		}
		if isNumeric(tok) {
			continue
		}
		out = append(out, tok)
	}
	return out
}

func isNumeric(tok string) bool {
	for _, r := range tok {
		if !unicode.IsDigit(r) {
			return false
		}
	}
	return tok != ""
}

// isCancel reports whether the utterance is nothing but a call-off. Every
// content token has to be a cancel word, so "забудь" ends the exchange and
// "забудь купить молоко" does not.
func isCancel(text string) bool {
	content := ownContent(text)
	if len(content) == 0 {
		return false
	}
	for _, tok := range content {
		if !cancelWords[tok] {
			return false
		}
	}
	return true
}

// carriesOwnRequest reads the ROUTED decision for the thing that decides this:
// does the utterance ask for something in its own right? Each intent is asked
// the question in its own terms, because "its own slots filled from its own
// words" means a different field for each of them.
//
// A query or a system question needs no further evidence — the router already
// read a question in these words. The write intents need the verb or the slot
// that names the request, so a bare value the router guessed a home for does
// not count as one.
func carriesOwnRequest(dec router.Decision, text string) bool {
	if dec.Clarify {
		// The router itself was unsure. An utterance she could not route is
		// not an utterance that outranks the question in front of it.
		return false
	}
	switch dec.Intent {
	case router.IntentQuery, router.IntentSystem:
		return true
	case router.IntentReminder:
		return carriesReminderVerb(text)
	case router.IntentFact, router.IntentNote:
		return router.CarriesCaptureVerb(text)
	case router.IntentAct:
		// An act that resolved to a capability is a command. One that did not
		// is words she cannot execute anyway, so it stays an answer and gets
		// re-asked — the same thing that happens to it today.
		return dec.Slots.HasFn
	default: // chat
		return false
	}
}

// carriesReminderVerb — "напомни" and its forms, matched over tokens. The
// reminder verbs are a closed lexicon and are not capture verbs, so
// CarriesCaptureVerb never sees them.
func carriesReminderVerb(text string) bool {
	toks := turnTokens(text)
	for _, v := range lexicon.ReminderVerbs() {
		for _, t := range toks {
			if t == strings.ToLower(v) {
				return true
			}
		}
	}
	return false
}

// isPleasantry matches the WHOLE utterance against lexicon.Pleasantries, after
// lowercasing and dropping the punctuation a greeting carries.
//
// Whole utterance and not tokens. Every token rule tried here was wrong on
// something: "вечер" answers "это утра или вечера?", "нет" answers a confirm,
// and "спокойной" alone is not an utterance at all. A greeting is a fixed
// phrase, so matching it as one costs nothing and claims nothing else.
func isPleasantry(text string) bool {
	t := strings.ToLower(strings.TrimSpace(text))
	t = strings.Trim(t, " .,!?…")
	t = strings.Join(strings.Fields(t), " ")
	if t == "" {
		return false
	}
	for _, p := range lexicon.Pleasantries() {
		if t == p {
			return true
		}
	}
	return false
}

// offlineOwnRequest is the shape half of the evidence: the offline token tests,
// which cost nothing and never depend on the model that produced the routing.
// It is also the whole answer when there is no route to read — the classifier
// is the failure floor and a turn must never break on the model.
func offlineOwnRequest(text string) bool {
	return router.IsQuestionShaped(text) || router.CarriesCaptureVerb(text) || carriesReminderVerb(text)
}

// classifyTurnRole decides what this utterance is against the pending action.
//
// The fast path is the first line and it is a fast path to the SAME answer, not
// a second decision procedure: an utterance with no content of its own can
// never be a request of its own, so it can never be anything but an answer, and
// the route below would spend a second on the resident model to say so. Every
// other utterance is routed first, and the role is read off the decision.
//
// `routed` is the turn's routing, already computed; ok is false when there was
// none to compute (no router wired, or the route failed). A failed route falls
// to the offline shape tests rather than breaking the turn.
func classifyTurnRole(q *dialogue.PendingQuestion, text string, answer dialogue.Slots, routed router.Decision, ok bool) turnRole {
	if isCancel(text) {
		return roleCancel
	}
	// Two pieces of evidence, and the content gate in front of both. The shape
	// tests are the floor and answer for free; the route is what sees a request
	// with no shape to it — "погода в риме" asks a question and carries neither
	// a question mark nor an interrogative, and only the router knows that.
	//
	// An utterance of pure frame gets one more chance, and V-577 is why. Every
	// token of "что у меня сегодня?" is frame, so the content gate called it an
	// answer, the parked reminder took "сегодня" for its time, and the question
	// he asked was answered nowhere. A routed intent beats a frame match,
	// because the frame is a hint and the route is a decision.
	//
	// The condition is that it fills nothing she asked about. That keeps the
	// hedged "а что если в 11:00" an answer, which is what it is: it carries the
	// hour, and no route saying "question" changes that. It works because the
	// extractor no longer reads a day word as the current clock, so a sentence
	// that names no hour now fills nothing to weigh.
	// A pleasantry is neither (V-663). "спасибо" and "привет" fell through to
	// roleAnswer, so a question about a reminder's DAY was re-asked at a man
	// saying thank you, and the retry it spent was one of the three bounds
	// meant to end the ride. It is an aside: answered as itself, the question
	// resumed on the tail, no attempt spent, one ride counted. Placed above the
	// content gate because "доброе утро" has content and states nothing, so
	// neither half of the evidence below can reach it.
	if q != nil && isPleasantry(text) {
		return roleAside
	}
	own := false
	if len(ownContent(text)) > 0 {
		own = offlineOwnRequest(text) || (ok && carriesOwnRequest(routed, text))
	} else if ok && fillsNothingAsked(q, answer) {
		own = carriesOwnRequest(routed, text)
	}
	if !own {
		if isAside(q, text, answer, routed, ok) {
			return roleAside
		}
		if replacesFilledSlot(q, answer) {
			return roleCorrection
		}
		return roleAnswer
	}
	if router.IsQuestionShaped(text) || (ok && (routed.Intent == router.IntentQuery || routed.Intent == router.IntentSystem)) {
		return roleSideQuery
	}
	return roleNewRequest
}

// isAside reports whether the utterance is something he STATED while she was
// waiting on a question (V-577 shape 2).
//
// "у меня новый ноутбук" said into a parked reminder was dropped in silence: it
// carries no capture verb, so it is not a request of its own, and it fills no
// slot, so it is not an answer either. Neither storing it nor saying it was
// ignored is the one behaviour that is wrong, and it was the behaviour.
//
// Three conditions, and all three are needed. The route has to call it a
// statement AND stand behind that, so a bare time is never an aside. It has to
// fill none of what she asked about, so an answer she can use stays an answer.
// And it has to say something, so a shrug is still a failed answer and still
// spends a retry.
func isAside(q *dialogue.PendingQuestion, text string, answer dialogue.Slots, routed router.Decision, ok bool) bool {
	if !ok || q == nil {
		return false
	}
	if !statesSomething(routed) {
		return false
	}
	if len(ownContent(text)) == 0 {
		return false
	}
	return fillsNothingAsked(q, answer)
}

// statesSomething reports whether the route is evidence that these words state
// a thing, rather than a guess she has to interrupt a flow over.
//
// Two kinds of evidence, and the second one exists because the classifier floor
// marks nearly everything Clarify. A parsed fact key comes from the
// deterministic fact parser and not from a similarity score, so "я выпил воды"
// is a statement on any engine. A confident note or fact is the other kind, and
// that is the one the resident model gives for "у меня новый ноутбук".
func statesSomething(routed router.Decision) bool {
	switch routed.Intent {
	case router.IntentFact:
		return routed.Slots.HasKey || !routed.Clarify
	case router.IntentNote:
		return !routed.Clarify
	}
	return false
}

// fillsNothingAsked reports whether the utterance gave her none of what she
// asked for. Nothing is pending counts as nothing filled.
func fillsNothingAsked(q *dialogue.PendingQuestion, answer dialogue.Slots) bool {
	if q == nil {
		return true
	}
	return len(dialogue.StillMissing(q.Missing, answer)) == len(q.Missing)
}

// replacesFilledSlot reports whether the utterance overwrites something the
// pending action already had, rather than filling the gap she asked about —
// "нет, на девять" while she is waiting for the subject. Both are handled the
// same way (dialogue.Answer already prefers the newer value), so this only
// names the turn honestly for the log and for the decision trace V-564 adds.
func replacesFilledSlot(q *dialogue.PendingQuestion, answer dialogue.Slots) bool {
	if q == nil {
		return false
	}
	asked := make(map[dialogue.Slot]bool, len(q.Missing))
	for _, s := range q.Missing {
		asked[s] = true
	}
	if answer.HasTime && q.Slots.HasTime && !asked[dialogue.SlotTime] && !answer.Time.Equal(q.Slots.Time) {
		return true
	}
	if answer.HasKey && q.Slots.HasKey && !asked[dialogue.SlotKey] && answer.Key != q.Slots.Key {
		return true
	}
	return false
}