Maven/cmd/mavend/actions.go

// actionTable dispatches applyAction's per-intent bodies. Each of the 7
// intents (fact, reminder, note, query, act, chat, system) has one handler
// here with the signature:
//
//	func(h *reactiveHandler, ctx context.Context, dec router.Decision) string
//
// same contract as applyAction itself: "" means "let the Replier phrase the
// reply", a non-empty string OVERRIDES it. This is a straight extraction of
// applyAction's old switch cases (formerly ~300 lines in voice.go) — no
// reordering of side effects, no new abstractions inside a handler.
//
// What does NOT belong in this table, because it is not per-intent:
//
//   - the dec.Clarify short-circuit ("" when the router's stage-3 fired) —
//     stays in applyAction, before dispatch, since it applies to every
//     intent identically.
//   - the destructive-act confirm gate (park / resolveConfirm / confirmTTL)
//     and the enabled-tool allowlist. Both live entirely inside
//     actionAct/handleAct below, exactly where they lived in the old
//     switch's IntentAct case — they are act-specific (a fact or a note
//     can't be destructive), not shared across intents, so they do not need
//     to move to a separate layer. The important invariant, preserved
//     as-is: applyAction runs identically whether dec came from a fresh
//     route or from a completed clarify answer (see finishClarified in
//     clarify.go and its comment "filling in an argument never grants
//     authority") — a handler must never special-case a clarify-completed
//     decision to skip the confirm gate or the allowlist.
//   - detectPattern and dialogue-session bookkeeping (rememberTurn,
//     followUpMerge) run in the callers (handleText, HandlePushToTalk,
//     finishClarified), not per-intent, and are untouched by this slice.
//
// Adding an intent: write its handler here, add one line to actionHandlers.
// Do not grow applyAction's switch back.
package main

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

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

// actionHandlers is the per-intent dispatch table used by applyAction.
var actionHandlers = map[router.Intent]func(*reactiveHandler, context.Context, router.Decision) string{
	router.IntentFact:     (*reactiveHandler).actionFact,
	router.IntentReminder: (*reactiveHandler).actionReminder,
	router.IntentAct:      (*reactiveHandler).actionAct,
	router.IntentChat:     (*reactiveHandler).actionChat,
	router.IntentSystem:   (*reactiveHandler).actionSystem,
	router.IntentNote:     (*reactiveHandler).actionNote,
	router.IntentQuery:    (*reactiveHandler).actionQuery,
}

func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) string {
	if !dec.Slots.HasKey {
		return "не разобрала, что записать — попробуй иначе."
	}
	now := h.now()
	req := ipc.WriteFactReq{
		Ts:         now,
		Kind:       "self",
		Key:        dec.Slots.Key,
		Value:      dec.Slots.Value,
		Source:     "tap:voice",
		Confidence: 1.0,
		// Subject: the key doubles as the entity-resolution candidate —
		// a voice-tapped fact's key is usually the thing/person it's
		// about ("espresso_machine", "kate"), so queueing it for Nexus
		// resolution costs one async lookup and is a no-op (not_found)
		// for the abstract self-state keys (mood, water) that aren't
		// entities at all.
		Subject: dec.Slots.Key,
	}
	factID, err := h.api.WriteFact(ctx, req)
	if err != nil {
		log.Printf("voice: write fact: %v", err)
		return "не получилось сохранить факт."
	}
	// Index the fact utterance in long-term memory (best-effort, must not
	// fail the fact write). Facts aren't in the notes table, so this is the
	// only recall path for them — "когда я пил воду?" reads back from here.
	if h.memStore != nil {
		if vec, err := router.EmbedPassage(ctx, h.embedder, dec.Utterance); err != nil {
			log.Printf("voice: embed fact for memory: %v", err)
		} else if err := h.memStore.Insert(ctx, "fact:"+dec.Slots.Key+":"+strconv.FormatInt(now.Unix(), 10), vec, map[string]string{
			"source": "voice",
			"type":   "fact",
			"text":   dec.Utterance,
			"ts":     strconv.FormatInt(now.Unix(), 10),
		}); err != nil {
			log.Printf("voice: memory insert fact: %v", err)
		}
	}
	// Event extraction + pattern detection (best-effort, must not fail the
	// fact write). If the fact describes a recognizable action, it becomes a
	// normalized event; if ≥3 events for the same action+object show stable
	// intervals, a proposed routine is created and parked for confirmation.
	if h.dataStore != nil {
		if phrase := h.detectPattern(ctx, factID, dec.Slots.Key, dec.Slots.Value, now); phrase != "" {
			return phrase // "ты заправляешь ... напоминать?"
		}
	}
	return "" // replier phrases the success reply
}

func (h *reactiveHandler) actionReminder(ctx context.Context, dec router.Decision) string {
	if !dec.Slots.HasTime {
		// Stage-0 (reminder-wakeword grammar) skips the extractor, so the
		// time wasn't parsed. Run the parser as a fallback.
		if dec.Stage == 0 && h.timeParser != nil {
			t, ok, err := h.timeParser.Parse(ctx, dec.Utterance, h.now())
			if err == nil && ok {
				dec.Slots.Time = t
				dec.Slots.HasTime = true
			}
		}
		if !dec.Slots.HasTime {
			return "не получилось разобрать время напоминания."
		}
	}
	payload := `{"text":` + jsonString(dec.Utterance) + `}`
	if _, err := h.api.CreateReminder(ctx, dec.Slots.Time, payload, ""); err != nil {
		log.Printf("voice: create reminder: %v", err)
		return "не получилось поставить напоминание."
	}
	return ""
}

func (h *reactiveHandler) actionAct(ctx context.Context, dec router.Decision) string {
	// tool executor: run the matched fn against the enabled allowlist.
	// HasFn=false ⇒ try the matcher (for LLM-routed acts where the verb
	// didn't go through the stage-0 act grammar).
	if !dec.Slots.HasFn && dec.Slots.Text != "" && h.matcher != nil {
		if fn, args, ok := h.matcher.Match(dec.Slots.Text); ok {
			dec.Slots.Fn, dec.Slots.Args, dec.Slots.HasFn = fn, args, true
		}
	}

	// Praxis ecosystem tools: intercept before the system command executor.
	if h.ecosystem != nil && h.ecosystem.praxis != nil && dec.Slots.HasFn {
		if reply := h.handlePraxisAct(ctx, dec); reply != "" {
			return reply
		}
	}

	// Hexis ecosystem action: if ecosystem is configured and we have a verb
	// + entity text, try to resolve the entity and execute via Hexis.
	if h.ecosystem != nil && h.ecosystem.hexis != nil && dec.Slots.Text != "" {
		if reply := h.handleHexisAct(ctx, dec); reply != "" {
			return reply
		}
	}

	// HasFn still false ⇒ no allowlist match: scaffold a 'proposed' tool
	// the user can enable on the authed surface ("earn the right to ask").
	if !dec.Slots.HasFn {
		return h.proposeGap(ctx, dec)
	}
	out, err := h.tools.Exec(ctx, dec.Slots.Fn, dec.Slots.Args, false)
	if err != nil {
		switch {
		case errors.Is(err, tool.ErrNeedsConfirm):
			// destructive: park it and ask. The next utterance answers.
			phrase := actPhrase(dec.Slots.Fn, dec.Slots.Args)
			h.park(dec.Slots.Fn, dec.Slots.Args, phrase)
			return "выполнить «" + phrase + "»? скажи «да» или «нет»."
		case errors.Is(err, tool.ErrNotEnabled):
			return h.proposeGap(ctx, dec)
		}
		log.Printf("voice: tool %s: %v", dec.Slots.Fn, err)
		if out != "" {
			return "не получилось выполнить команду: " + firstLine(out)
		}
		return "не получилось выполнить команду."
	}
	if out != "" {
		return "готово: " + firstLine(out)
	}
	return "готово."
}

func (h *reactiveHandler) actionChat(ctx context.Context, dec router.Decision) string {
	// Conversational: build history from dialogue session (prior user turns)
	// and let the LLM respond from general knowledge + context.
	history := h.chatHistory()
	reply, err := h.phraser.PhraseChat(ctx, dec.Utterance, history)
	if err != nil {
		log.Printf("voice: chat: %v", err)
		return "поговорили."
	}
	return reply
}

func (h *reactiveHandler) actionSystem(ctx context.Context, dec router.Decision) string {
	return h.replySystem(ctx, dec)
}

func (h *reactiveHandler) actionNote(ctx context.Context, dec router.Decision) string {
	// embed the note text with the same model the classifier uses, persist
	// via CoreAPI (source=tap:voice). Semantic recall lives in `notes`, not
	// facts — no predicate reads it (spec's two-memory split).
	vec, err := router.EmbedPassage(ctx, h.embedder, dec.Utterance)
	if err != nil {
		log.Printf("voice: embed note: %v", err)
		return "не получилось сохранить заметку."
	}
	noteTs := h.now()
	noteID, err := h.api.WriteNote(ctx, noteTs, dec.Utterance, vec, "tap:voice")
	if err != nil {
		log.Printf("voice: write note: %v", err)
		return "не получилось сохранить заметку."
	}
	// Insert into long-term memory (best-effort, must not fail the note write).
	// text/ts in the meta make a Search hit self-describing (see bestRecall).
	if h.memStore != nil {
		if err := h.memStore.Insert(ctx, "note:"+strconv.FormatInt(noteID, 10), vec, map[string]string{
			"source": "voice",
			"type":   "note",
			"text":   dec.Utterance,
			"ts":     strconv.FormatInt(noteTs.Unix(), 10),
		}); err != nil {
			log.Printf("voice: memory insert: %v", err)
		}
	}
	return "" // replier phrases the "saved" reply
}

func (h *reactiveHandler) actionQuery(ctx context.Context, dec router.Decision) string {
	// Fact-by-key lookup: 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.
	if dec.Slots.HasKey && dec.Slots.Key != "" {
		if f, err := h.api.LatestFact(ctx, dec.Slots.Key); err == nil {
			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.
				reply := fmt.Sprintf("я записала это %s", formatTime(f.Ts))
				return reply
			}
			// General fact reference: describe what we know.
			if dec.Utterance == "" {
				return fmt.Sprintf("вот что я знаю: %s — %s", dec.Slots.Key, f.Value)
			}
			// The utterance still carries the question; fall through to
			// normal RAG with the resolved key in context.
		}
	}

	// Calendar questions: "что у меня сегодня?", "планы на завтра?"
	// h.now(), not time.Now(): the handler's clock is the injected one, so
	// this arm can be tested at a fixed time like the rest.
	if date, ok := router.ParseCalendarDate(dec.Utterance, h.now()); ok {
		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."
		}
		values := make([]string, len(events))
		for i, e := range events {
			values[i] = e.Value
		}
		var f router.CalendarEventFormatter
		return f.Format(values, date)
	}

	// Weather questions
	if isWeatherQuery(dec.Utterance) {
		loc := extractWeatherLocation(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."
		}
		if err != nil {
			log.Printf("voice: weather: %v", err)
			return "не получилось узнать погоду."
		}
		return fmt.Sprintf("в %s сейчас %.0f градусов, %s.", w.Location, w.Temperature, w.Condition)
	}

	vec, err := router.EmbedQuery(ctx, h.embedder, dec.Utterance)
	if err != nil {
		log.Printf("voice: embed query: %v", err)
		return "не получилось найти ответ."
	}
	// 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 gate 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.
	if h.memStore != nil {
		if hits, herr := h.memStore.Search(ctx, vec, 3); herr == nil {
			if hit, ok := bestRecall(hits, h.queryMinScore, h.queryMinMargin); ok {
				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, dec.Utterance, []string{text}); perr == nil && reply != "" {
						return reply
					}
				}
				return text
			}
		} else {
			log.Printf("voice: memory search: %v", herr)
		}
	}

	notes, err := h.api.QueryNotes(ctx, vec, 5)
	if err != nil {
		log.Printf("voice: query notes: %v", err)
		return "не получилось найти ответ."
	}
	// 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.
	noteScores := make([]float64, len(notes))
	for i, n := range notes {
		noteScores[i] = n.Score
	}
	if !memory.ConfidentScores(noteScores, h.queryMinScore, h.queryMinMargin) {
		// Try general knowledge from the phraser before giving up
		reply, err := h.phraser.PhraseQuery(ctx, dec.Utterance, nil)
		if err != nil || reply == "" {
			return "не знаю."
		}
		return reply
	}
	texts := make([]string, len(notes))
	for i, n := range notes {
		texts[i] = n.Text
	}
	reply, err := h.phraser.PhraseQuery(ctx, dec.Utterance, texts)
	if err != nil {
		log.Printf("voice: phrase query: %v", err)
	}
	if reply == "" {
		reply = "вот что я нашла: " + texts[0]
	}
	return reply
}