mavend: keep only the stub floor in llmReplier (V-396)

The prompt, the call and the output parsing now live in internal/phraser. What is
left here is the one thing the daemon adds: a clarify, a model error and an
unusable generation all answer from voice.StubReplier, so a turn never breaks on
the model. The duplicated stripThink and parseResponseMood copies are gone;
capture.go uses phraser.StripThink.

cmd/mavend/capture.go

@@ -100,7 +100,7 @@ func (l llmCompleter) Complete(ctx context.Context, system, user string) (string
 // grammar, or a llama-server too old to honour one, gets the plain text it used
 // to get rather than an empty meeting summary.
 func unwrapSummary(raw string) string {
-	s := stripThink(strings.TrimSpace(raw))
+	s := phraser.StripThink(strings.TrimSpace(raw))
 	start := strings.Index(s, "{")
 	end := strings.LastIndex(s, "}")
 	if start < 0 || end <= start {

cmd/mavend/replier_llm.go

@@ -2,122 +2,33 @@ 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/phraser"
 	"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.
+// llmReplier is the daemon-side wiring around phraser.Replier: it owns the
+// deterministic floor, and nothing else. The phrasing itself, the prompt and the
+// output parsing live in internal/phraser so the eval can score them (#396).
 type llmReplier struct {
-	c    completer
+	p    *phraser.Replier
 	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}
+func newLLMReplier(c phraser.Completer, block func() string) *llmReplier {
+	return &llmReplier{p: phraser.NewReplier(c, block), stub: voice.NewStubReplier()}
 }
 
-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.`
-
+// Reply never fails: a clarify, a model error and an unusable generation all
+// answer from the stub, which is what keeps a turn from breaking on the model.
 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),
-		Grammar:       phraser.ResponseGrammar,
-		MaxTokens:     512,
-		RepeatPenalty: 1.3,
-	})
-	if err != nil {
+	out, err := r.p.PhraseReply(context.Background(), d)
+	if err != nil || out == "" {
 		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
-	}
+	return out
 }

cmd/mavend/replier_llm_test.go

@@ -5,28 +5,22 @@ import (
 	"testing"
 
 	"github.com/kami/maven/internal/llm"
-	"github.com/kami/maven/internal/phraser"
 	"github.com/kami/maven/internal/router"
 	"github.com/kami/maven/internal/voice"
 )
 
-type mockCompleter struct {
+// The phrasing itself is tested in internal/phraser. What is left here is the
+// only thing the daemon adds: the stub floor, on the three ways a reply can
+// fail to arrive.
+type stubCompleter struct {
 	out string
 	err error
 }
 
-func (m mockCompleter) Complete(_ context.Context, _ llm.Req) (string, error) { return m.out, m.err }
+func (s stubCompleter) Complete(_ context.Context, _ llm.Req) (string, error) { return s.out, s.err }
 
-func TestLLMReplierReturnsLLMReply(t *testing.T) {
-	r := newLLMReplier(mockCompleter{out: `{"response":"записала, кофе закончился","mood":"neutral"}`}, nil)
-	got := r.Reply(router.Decision{Intent: router.IntentNote, Slots: router.Slots{Text: "кофе закончился"}})
-	if got != "записала, кофе закончился" {
-		t.Errorf("got %q, want %q", got, "записала, кофе закончился")
-	}
-}
-
-func TestLLMReplierFallsBackToPlainText(t *testing.T) {
-	r := newLLMReplier(mockCompleter{out: "записала, кофе закончился"}, nil)
+func TestLLMReplierPassesTheModelReplyThrough(t *testing.T) {
+	r := newLLMReplier(stubCompleter{out: `{"response":"записала, кофе закончился","mood":"neutral"}`}, nil)
 	got := r.Reply(router.Decision{Intent: router.IntentNote, Slots: router.Slots{Text: "кофе закончился"}})
 	if got != "записала, кофе закончился" {
 		t.Errorf("got %q, want %q", got, "записала, кофе закончился")
@@ -34,54 +28,30 @@ func TestLLMReplierFallsBackToPlainText(t *testing.T) {
 }
 
 func TestLLMReplierFallsBackToStubOnError(t *testing.T) {
-	r := newLLMReplier(mockCompleter{err: errTestLLMDown}, nil)
-	noteDec := router.Decision{Intent: router.IntentNote}
-	got := r.Reply(noteDec)
-	want := voice.NewStubReplier().Reply(noteDec)
-	if got != want {
-		t.Errorf("on llm error: got %q, want stub %q", got, want)
-	}
+	r := newLLMReplier(stubCompleter{err: errReplierTest}, nil)
+	assertStub(t, r, router.Decision{Intent: router.IntentNote}, "llm error")
 }
 
 func TestLLMReplierFallsBackToStubOnEmpty(t *testing.T) {
-	r := newLLMReplier(mockCompleter{out: ""}, nil)
-	noteDec := router.Decision{Intent: router.IntentNote}
-	got := r.Reply(noteDec)
-	want := voice.NewStubReplier().Reply(noteDec)
-	if got != want {
-		t.Errorf("on empty llm: got %q, want stub %q", got, want)
-	}
+	r := newLLMReplier(stubCompleter{out: ""}, nil)
+	assertStub(t, r, router.Decision{Intent: router.IntentNote}, "empty llm")
 }
 
 func TestLLMReplierClarifyUsesStub(t *testing.T) {
-	r := newLLMReplier(mockCompleter{out: "я всё поняла"}, nil)
-	clarifyDec := router.Decision{Clarify: true}
-	got := r.Reply(clarifyDec)
-	want := voice.NewStubReplier().Reply(clarifyDec)
+	r := newLLMReplier(stubCompleter{out: "я всё поняла"}, nil)
+	assertStub(t, r, router.Decision{Clarify: true}, "clarify")
+}
+
+func assertStub(t *testing.T, r *llmReplier, d router.Decision, what string) {
+	t.Helper()
+	got, want := r.Reply(d), voice.NewStubReplier().Reply(d)
 	if got != want {
-		t.Errorf("on clarify: got %q, want stub %q", got, want)
+		t.Errorf("on %s: got %q, want stub %q", what, got, want)
 	}
 }
 
-var errTestLLMDown = errTest("llm down")
+var errReplierTest = errTest("llm down")
 
 type errTest string
 
 func (e errTest) Error() string { return string(e) }
-
-// grammarRecorder captures the request so the grammar can be asserted on.
-type grammarRecorder struct{ req llm.Req }
-
-func (g *grammarRecorder) Complete(_ context.Context, r llm.Req) (string, error) {
-	g.req = r
-	return `{"response":"записала","mood":"neutral"}`, nil
-}
-
-func TestLLMReplierCarriesTheResponseGrammar(t *testing.T) {
-	rec := &grammarRecorder{}
-	r := newLLMReplier(rec, nil)
-	r.Reply(router.Decision{Intent: router.IntentNote, Slots: router.Slots{Text: "кофе закончился"}})
-	if rec.req.Grammar != phraser.ResponseGrammar {
-		t.Errorf("grammar = %q, want phraser.ResponseGrammar", rec.req.Grammar)
-	}
-}