Maven/cmd/mavend/replier_llm.go

package main

import (
	"context"
	"encoding/json"
	"strings"
	"time"

	"github.com/kami/maven/internal/llm"
	"github.com/kami/maven/internal/persona"
	"github.com/kami/maven/internal/router"
	"github.com/kami/maven/internal/voice"
)

// completer is the LLM seam for the replier (subset of router.Completer).
// *llm.Client satisfies it.
type completer interface {
	Complete(ctx context.Context, r llm.Req) (string, error)
}

// llmReplier phrases reactive confirmations with the resident model
// (Qwen3-1.7B). Stub is the
// floor on any error (offline-safe). Maven speaks as "she", feminine RU.
type llmReplier struct {
	c    completer
	stub *voice.StubReplier

	// block renders the shared context block per turn (who he is, the time).
	// nil ⇒ the prompt stands alone.
	block func() string
}

func newLLMReplier(c completer, block func() string) *llmReplier {
	return &llmReplier{c: c, stub: voice.NewStubReplier(), block: block}
}

const replySystem = `Ты — Maven, домашняя ассистентка (о себе — в женском роде). Владелец — мужчина, говоришь с ним на "ты", в единственном числе; никогда не "вы"/"ваш" и не "он"/"его". Подтверди действие РОВНО ОДНИМ коротким предложением (≤120 символов), по-русски, спокойно и без официальных формулировок. Не задавай вопросов, не повторяй слова, не добавляй ничего после точки. Отвечай ТОЛЬКО одним объектом JSON с полями "response" (текст) и "mood" (ровно одно из: neutral, happy, thinking, tired, confused).
Пример: {"response": "Записала, что ты выпил стакан воды.", "mood": "neutral"}
Никогда не пиши "..." в поле response.`

func (r *llmReplier) Reply(d router.Decision) string {
	if d.Clarify {
		return r.stub.Reply(d)
	}
	ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
	defer cancel()
	out, err := r.c.Complete(ctx, llm.Req{
		System:        persona.Prepend(r.block, replySystem),
		User:          replyContext(d),
		MaxTokens:     512,
		RepeatPenalty: 1.3,
	})
	if err != nil {
		return r.stub.Reply(d)
	}
	out = stripThink(out)
	if response, _ := parseResponseMood(out); response != "" {
		return response
	}
	// fallback: try plain-text parsing
	if out = firstSentence(out); out != "" {
		return out
	}
	return r.stub.Reply(d)
}

// firstSentence trims the model's output to a single clean confirmation: first
// line, first sentence, whitespace-normalized — the last-line defense against a
// small model that rambles past the first period despite the prompt + stop.
// stripThink removes the <think> block that Thinking-variant models emit.
func stripThink(s string) string {
	if i := strings.LastIndex(s, "</think>"); i >= 0 {
		s = strings.TrimSpace(s[i+8:])
	}
	return s
}

func firstSentence(s string) string {
	s = strings.TrimSpace(s)
	if i := strings.IndexByte(s, '\n'); i >= 0 {
		s = s[:i]
	}
	// keep up to and including the first sentence-ending punctuation.
	if i := strings.IndexAny(s, ".!?"); i >= 0 {
		s = s[:i+1]
	}
	return strings.TrimSpace(s)
}

// parseResponseMood extracts {"response","mood"} from LLM output, tolerant
// of thinking tokens and extra text before/after the JSON block.
func parseResponseMood(raw string) (response, mood string) {
	cleaned := strings.TrimSpace(raw)
	start := strings.Index(cleaned, "{")
	end := strings.LastIndex(cleaned, "}")
	if start < 0 || end < 0 || end <= start {
		return "", ""
	}
	var parsed struct {
		Response string `json:"response"`
		Mood     string `json:"mood"`
	}
	if err := json.Unmarshal([]byte(cleaned[start:end+1]), &parsed); err != nil {
		return "", ""
	}
	return parsed.Response, parsed.Mood
}

// replyContext renders the decision into a compact RU description for the model.
func replyContext(d router.Decision) string {
	switch d.Intent {
	case router.IntentFact:
		return "записала факт: " + d.Slots.Key + " " + d.Slots.Value
	case router.IntentNote:
		return "сохранила заметку: " + d.Slots.Text
	case router.IntentReminder:
		return "поставила напоминание: " + d.Slots.Text
	default:
		return string(d.Intent) + ": " + d.Slots.Text
	}
}