Maven/cmd/mavend/actions_query.go

package main

import (
	"context"
	"errors"
	"fmt"
	"log"
	"time"

	"github.com/kami/maven/internal/ipc"
	"github.com/kami/maven/internal/memory"
	"github.com/kami/maven/internal/router"
	"github.com/kami/maven/internal/weather"
)

// queryTurn is the per-turn scratch a chain of query sources shares: the
// decision being answered plus the work an earlier source already paid for
// (the query embedding, the notes it pulled). Sources read and fill it in
// order, so a later source never re-embeds.
type queryTurn struct {
	dec   router.Decision
	vec   []float32
	notes []ipc.Note
}

// querySource — one answer source in the chain actionQuery walks. answer
// returns (reply, true) when this source claims the question, ("", false)
// when it passes to the next one. name is for reading the table, not logged.
//
// A struct of one func rather than an interface: every source is a plain
// method on *reactiveHandler with no state of its own (what state a turn has
// lives in queryTurn), so an interface would mean one empty type per source
// to satisfy it — ceremony for nothing. Same reasoning as confirmResolver in
// confirm.go, and the table then reads like actionHandlers: a flat list of
// method expressions you extend with one line.
type querySource struct {
	name   string
	answer func(*reactiveHandler, context.Context, *queryTurn) (string, bool)
}

// querySources is the ordered chain actionQuery walks; first source to claim
// answers the turn. THE ORDER IS LOAD-BEARING — see the memory-before-notes
// comment on queryMemory: running the notes-only pass first was #373, and the
// gate was never the bug. Adding a source (Kiwix, RSS, crawler, email) is one
// line here plus its method; where you put the line is the whole decision.
var querySources = []querySource{
	{"fact-by-key", (*reactiveHandler).queryFactByKey},
	{"calendar", (*reactiveHandler).queryCalendar},
	{"weather", (*reactiveHandler).queryWeather},
	{"embed", (*reactiveHandler).queryEmbed},
	{"memory", (*reactiveHandler).queryMemory},
	{"notes", (*reactiveHandler).queryNotes},
	{"general-knowledge", (*reactiveHandler).queryGeneral},
}

func (h *reactiveHandler) actionQuery(ctx context.Context, dec router.Decision) string {
	t := &queryTurn{dec: dec}
	for _, src := range querySources {
		if reply, ok := src.answer(h, ctx, t); ok {
			return reply
		}
	}
	return "не знаю."
}

// queryFactByKey — when the dialogue layer resolved an anaphoric reference to
// a prior fact's key (e.g. "когда я это сделал?" after "запиши что я пил
// воду"), look up the fact's value directly.
func (h *reactiveHandler) queryFactByKey(ctx context.Context, t *queryTurn) (string, bool) {
	dec := t.dec
	if !dec.Slots.HasKey || dec.Slots.Key == "" {
		return "", false
	}
	f, err := h.api.LatestFact(ctx, dec.Slots.Key)
	if err != nil {
		return "", false
	}
	if dec.Slots.HasTime {
		// The query asks about timing — the fact's own timestamp is the
		// answer it's looking for. Format as a natural reply.
		return fmt.Sprintf("я записала это %s", formatTime(f.Ts)), true
	}
	// General fact reference: describe what we know.
	if dec.Utterance == "" {
		return fmt.Sprintf("вот что я знаю: %s — %s", dec.Slots.Key, f.Value), true
	}
	// The utterance still carries the question; fall through to normal RAG
	// with the resolved key in context.
	return "", false
}

// queryCalendar — "что у меня сегодня?", "планы на завтра?"
// h.now(), not time.Now(): the handler's clock is the injected one, so this
// source can be tested at a fixed time like the rest.
func (h *reactiveHandler) queryCalendar(ctx context.Context, t *queryTurn) (string, bool) {
	date, ok := router.ParseCalendarDate(t.dec.Utterance, h.now())
	if !ok {
		return "", false
	}
	events, err := h.api.CalendarEvents(ctx, date, date.Add(24*time.Hour))
	if err != nil {
		log.Printf("voice: calendar events: %v", err)
		return "не получилось проверить календарь.", true
	}
	// Provenance travels with each event. A work meeting relayed off a phone
	// notification (source ambient:notif, #126) is stored below full confidence
	// and gets hedged; a CalDAV read is recited plainly.
	entries := make([]router.CalendarEntry, len(events))
	for i, e := range events {
		entries[i] = router.CalendarEntry{Text: e.Value, Uncertain: e.Confidence < 1.0}
	}
	var f router.CalendarEventFormatter
	return f.FormatEntries(entries, date), true
}

func (h *reactiveHandler) queryWeather(ctx context.Context, t *queryTurn) (string, bool) {
	if !isWeatherQuery(t.dec.Utterance) {
		return "", false
	}
	loc := extractWeatherLocation(t.dec.Utterance, h.weatherLocation)
	ctxWT, cancel := context.WithTimeout(ctx, 5*time.Second)
	defer cancel()
	w, err := h.weatherProvider.CurrentWeather(ctxWT, loc)
	if errors.Is(err, weather.ErrNotConfigured) {
		return "погода не настроена.", true
	}
	if err != nil {
		log.Printf("voice: weather: %v", err)
		return "не получилось узнать погоду.", true
	}
	return fmt.Sprintf("в %s сейчас %.0f градусов, %s.", w.Location, w.Temperature, w.Condition), true
}

// queryEmbed isn't an answer source — it's the shared cost the two recall
// sources below both need, run once, in the position it always ran in. It
// only claims the turn when the embedder fails.
func (h *reactiveHandler) queryEmbed(ctx context.Context, t *queryTurn) (string, bool) {
	vec, err := router.EmbedQuery(ctx, h.embedder, t.dec.Utterance)
	if err != nil {
		log.Printf("voice: embed query: %v", err)
		return "не получилось найти ответ.", true
	}
	t.vec = vec
	return "", false
}

// queryMemory — long-term memory first: ONE search over everything Maven
// remembers (notes and facts share this index) and ONE confidence gate, so
// the memory that is clearly the best match answers — a note just as much as
// a fact.
//
// This used to run only after the notes-only source below had already
// rejected the same note at the same score, which no note could ever survive
// a second time: the branch could only return a fact (#373). Order, not the
// gate, was the bug — the set of questions Maven answers is unchanged, only
// which memory gets to answer them.
func (h *reactiveHandler) queryMemory(ctx context.Context, t *queryTurn) (string, bool) {
	if h.memStore == nil {
		return "", false
	}
	hits, herr := h.memStore.Search(ctx, t.vec, 3)
	if herr != nil {
		log.Printf("voice: memory search: %v", herr)
		return "", false
	}
	hit, ok := bestRecall(hits, h.queryMinScore, h.queryMinMargin)
	if !ok {
		return "", false
	}
	text := hit.Meta["text"]
	// A note is phrased in Maven's voice; a fact is read back as it was
	// stored.
	if hit.Meta["type"] == "note" {
		if reply, perr := h.phraser.PhraseQuery(ctx, t.dec.Utterance, []string{text}); perr == nil && reply != "" {
			return reply, true
		}
	}
	return text, true
}

// queryNotes — notes-only pass, for notes the vector index above does not
// hold (an older note written before it existed). Same gate, notes-only
// candidates.
//
// Confidence gate: below it, say "I don't know" rather than read back the
// least-unrelated note — a confident wrong recall is worse than a gap (spec's
// "not a guesser-of-truth"). Same instinct as the loop's since(key)==null →
// don't fire. Two parts: an absolute cosine floor, and a margin over the
// runner-up, which is the part that works with the e5 embedder's narrow score
// band. See memory.Confident. Failing the gate passes the turn on to general
// knowledge, which is what "don't read back the runner-up" means here.
func (h *reactiveHandler) queryNotes(ctx context.Context, t *queryTurn) (string, bool) {
	notes, err := h.api.QueryNotes(ctx, t.vec, 5)
	if err != nil {
		log.Printf("voice: query notes: %v", err)
		return "не получилось найти ответ.", true
	}
	t.notes = notes
	noteScores := make([]float64, len(notes))
	for i, n := range notes {
		noteScores[i] = n.Score
	}
	if !memory.ConfidentScores(noteScores, h.queryMinScore, h.queryMinMargin) {
		return "", false
	}
	texts := make([]string, len(notes))
	for i, n := range notes {
		texts[i] = n.Text
	}
	reply, err := h.phraser.PhraseQuery(ctx, t.dec.Utterance, texts)
	if err != nil {
		log.Printf("voice: phrase query: %v", err)
	}
	if reply == "" {
		reply = "вот что я нашла: " + texts[0]
	}
	return reply, true
}

// queryGeneral — general knowledge from the phraser, the last source before
// giving up. It always claims: either the model answers or Maven says she
// doesn't know.
func (h *reactiveHandler) queryGeneral(ctx context.Context, t *queryTurn) (string, bool) {
	reply, err := h.phraser.PhraseQuery(ctx, t.dec.Utterance, nil)
	if err != nil || reply == "" {
		return "не знаю.", true
	}
	return reply, true
}