Files
Maven/cmd/mavend/replier_llm.go
T
kami 6a5121657a feat: {response,mood} output contract + router removal, TTS piper plan
Daemon side of Decision B: parse {"response","mood"} across the 4 consumers
(replier, nudges, reminders, chat), fall back to legacy formats. Drop the
LLM router — the classifier handles routing; replier/phraser share one
llm.Client (timeout 20s->60s). llm.Client reads reasoning_content when
content is empty (thinking models).

Docs: TTS piper-student plan (OmniVoice teacher -> piper student, from
scratch, phoneme-first). CLAUDE.md training guide.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-11 22:51:50 +04:00

114 lines
3.6 KiB
Go

package main
import (
"context"
"encoding/json"
"strings"
"time"
"github.com/kami/maven/internal/llm"
"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 LFM. Stub is the
// floor on any error (offline-safe). Maven speaks as "she", feminine RU.
type llmReplier struct {
c completer
stub *voice.StubReplier
}
func newLLMReplier(c completer) *llmReplier {
return &llmReplier{c: c, stub: voice.NewStubReplier()}
}
const replySystem = `Ты — Maven, домашняя ассистентка (о себе — в женском роде). Подтверди действие РОВНО ОДНИМ коротким предложением (≤120 символов), тепло и по-русски. Не задавай вопросов, не повторяй слова, не добавляй ничего после точки. Respond ONLY with valid JSON: {"response": "...", "mood": "neutral"}.`
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: 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
}
}