Maven/internal/router/question.go

package router

import (
	"strings"

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

// The three word sets this file tests against are closed classes, so they live
// complete in internal/lexicon rather than inline here (Vikunja #525). The
// inline lists were short: no "чем", no "чём", no "кем", no declined "какой",
// so "чем ты занята" carried no interrogative at all and read as a statement.
//
// interrogatives mark an utterance as asking rather than telling.
// narrativeRequests are "tell me about X", which asks for knowledge Maven does
// not hold about him and carries neither a question mark nor an interrogative —
// that is how "расскажи про битву при Ватерлоо" reached the fact store (#470).
// captureVerbs win over both, because "запиши что я пил воду" contains an
// interrogative and is still a capture: the word he said is "запиши".
//
// All three are matched over tokens, never as substrings: "что" inside "чтобы"
// and "как" inside "какао" are not questions.
var (
	interrogatives    = lexicon.Interrogatives()
	locativeQuestions = lexicon.LocativeInterrogatives()
	narrativeRequests = lexicon.NarrativeRequests()
	captureVerbs      = lexicon.CaptureVerbs()
)

// CarriesCaptureVerb reports whether text tells Maven to write something down.
// Sibling of IsQuestionShaped and matched over the same tokens, and the two do
// not overlap: IsQuestionShaped returns false for anything this returns true
// for, because "запиши что я пил воду" is a capture and not a question.
//
// Both exist together so a caller can ask "is this its own request?" — a
// clarify answer that asks a question or orders a capture is not an answer
// (Vikunja #554).
func CarriesCaptureVerb(text string) bool {
	toks := planTokens(strings.TrimSpace(text))
	for _, v := range captureVerbs {
		if hasTok(toks, v) {
			return true
		}
	}
	return false
}

// IsQuestionShaped reports whether text asks for something rather than
// records it. It is a deterministic offline test over tokens, so it costs
// nothing and never depends on the model that produced the routing decision.
//
// It exists because a mis-routed question used to be persisted as a fact
// about the owner, with the model's invented answer as the value (#470). The
// predicate is deliberately blunt: refusing to store a question is cheap and
// reversible, storing an invented fact about him is neither.
func IsQuestionShaped(text string) bool {
	t := strings.TrimSpace(text)
	if t == "" {
		return false
	}
	toks := planTokens(t)
	for _, v := range captureVerbs {
		if hasTok(toks, v) {
			return false
		}
	}
	if strings.HasSuffix(t, "?") {
		return true
	}
	return hasOpenQuestionTokens(toks)
}

// IsOpenQuestionShaped reports whether the words themselves ask for
// information: an interrogative ("где", "как", "which") or a narrative
// request ("расскажи", "explain"). A trailing question mark alone does not
// qualify. That distinction matters to recall: punctuation can turn an
// ordinary first-person proposition into a polar question, but it is not
// evidence that an unrelated stored note answers it.
//
// Capture verbs keep the same precedence as IsQuestionShaped, so "запиши что
// я пил" remains a write request even though it contains an interrogative.
func IsOpenQuestionShaped(text string) bool {
	t := strings.TrimSpace(text)
	if t == "" {
		return false
	}
	toks := planTokens(t)
	for _, v := range captureVerbs {
		if hasTok(toks, v) {
			return false
		}
	}
	return hasOpenQuestionTokens(toks)
}

// IsLocativeQuestionShaped reports the open-question frame whose answer must
// locate the object or event named by the user. Recall treats that named target
// as evidence: a high cosine to an unrelated single stored note is not enough
// to answer "where is my passport?" with the location of a spare key (V-719).
//
// The words are the complete locative subset of the interrogative lexicon,
// and capture verbs retain precedence exactly as in IsQuestionShaped.
func IsLocativeQuestionShaped(text string) bool {
	t := strings.TrimSpace(text)
	if t == "" {
		return false
	}
	toks := planTokens(t)
	for _, v := range captureVerbs {
		if hasTok(toks, v) {
			return false
		}
	}
	for _, w := range locativeQuestions {
		if hasTok(toks, w) {
			return true
		}
	}
	return false
}

func hasOpenQuestionTokens(toks []string) bool {
	for _, w := range interrogatives {
		if hasTok(toks, w) {
			return true
		}
	}
	for _, w := range narrativeRequests {
		if hasTok(toks, w) {
			return true
		}
	}
	return false
}