internal/phraser/replier.go

@@ -0,0 +1,112 @@
+// phraser/replier.go — reactive reply phrasing, the confirmation he hears
+// after every fact, note and reminder.
+//
+// It lived in cmd/mavend as package main until Vikunja #396, which meant the
+// most frequently heard sentence Maven says was the one path the phrasing eval
+// could not import, let alone score. Nothing here talks to the daemon: the
+// caller supplies the completer and the context block, and cmd/mavend keeps the
+// stub fallback so a model error still answers.
+package phraser
+
+import (
+	"context"
+	"strings"
+	"time"
+
+	"github.com/kami/maven/internal/llm"
+	"github.com/kami/maven/internal/persona"
+	"github.com/kami/maven/internal/router"
+)
+
+// Completer is the model seam for the replier, a subset of router.Completer.
+// *llm.Client satisfies it.
+type Completer interface {
+	Complete(ctx context.Context, r llm.Req) (string, error)
+}
+
+// replyTimeout bounds one reply. Generous because the resident model on the CPU
+// floor is slow and the caller has a deterministic fallback anyway.
+const replyTimeout = 60 * time.Second
+
+// ReplySystemPrompt — the reactive confirmation contract: one short Russian
+// sentence, feminine self-reference, informal address, no question.
+const ReplySystemPrompt = `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.`
+
+// Replier phrases reactive confirmations with the resident model. It has no
+// fallback of its own: an error is returned, and the daemon answers from the
+// deterministic stub. That is also what makes it scorable — a dead server shows
+// up as an error rather than as bad phrasing.
+type Replier struct {
+	c Completer
+
+	// block renders the shared context block per turn (who he is, the time).
+	// nil ⇒ the prompt stands alone.
+	block func() string
+}
+
+// NewReplier builds a replier over c. block may be nil.
+func NewReplier(c Completer, block func() string) *Replier {
+	return &Replier{c: c, block: block}
+}
+
+// PhraseReply returns the confirmation for one decision. An empty string with a
+// nil error means the model produced nothing usable, which the caller must
+// treat exactly like an error.
+func (r *Replier) PhraseReply(ctx context.Context, d router.Decision) (string, error) {
+	ctx, cancel := context.WithTimeout(ctx, replyTimeout)
+	defer cancel()
+	out, err := r.c.Complete(ctx, llm.Req{
+		System:        persona.Prepend(r.block, ReplySystemPrompt),
+		User:          replyContext(d),
+		Grammar:       ResponseGrammar,
+		MaxTokens:     512,
+		RepeatPenalty: 1.3,
+	})
+	if err != nil {
+		return "", err
+	}
+	out = stripThink(out)
+	if response, _, perr := parseResponseMood(out); perr != nil {
+		return "", perr
+	} else if response != "" {
+		return response, nil
+	}
+	// fallback: the model answered in bare prose, which is fine here.
+	return firstSentence(out), nil
+}
+
+// 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.
+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)
+}
+
+// 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
+	}
+}
+
+// StripThink removes the <think> block a Thinking-variant model emits before its
+// answer. Exported for the daemon's own model callers, which parse output that
+// never passes through a phraser method.
+func StripThink(s string) string { return stripThink(s) }

internal/phraser/replier_test.go

@@ -0,0 +1,90 @@
+package phraser
+
+import (
+	"context"
+	"testing"
+
+	"github.com/kami/maven/internal/llm"
+	"github.com/kami/maven/internal/router"
+)
+
+type mockCompleter struct {
+	out string
+	err error
+}
+
+func (m mockCompleter) Complete(_ context.Context, _ llm.Req) (string, error) { return m.out, m.err }
+
+func TestReplierReturnsLLMReply(t *testing.T) {
+	r := NewReplier(mockCompleter{out: `{"response":"записала, кофе закончился","mood":"neutral"}`}, nil)
+	got, err := r.PhraseReply(context.Background(), noteDecision())
+	if err != nil || got != "записала, кофе закончился" {
+		t.Errorf("got %q, %v, want %q, nil", got, err, "записала, кофе закончился")
+	}
+}
+
+func TestReplierFallsBackToPlainText(t *testing.T) {
+	r := NewReplier(mockCompleter{out: "записала, кофе закончился"}, nil)
+	got, err := r.PhraseReply(context.Background(), noteDecision())
+	if err != nil || got != "записала, кофе закончился" {
+		t.Errorf("got %q, %v, want %q, nil", got, err, "записала, кофе закончился")
+	}
+}
+
+func TestReplierReportsTheModelError(t *testing.T) {
+	r := NewReplier(mockCompleter{err: errTestLLMDown}, nil)
+	got, err := r.PhraseReply(context.Background(), noteDecision())
+	if err == nil {
+		t.Errorf("got %q, nil error — a dead model must be reported, not phrased around", got)
+	}
+}
+
+// A fragment the grammar left half-open is a failed generation. It must come
+// back as an error so the daemon reaches its stub, not as a reply.
+func TestReplierRejectsBrokenJSON(t *testing.T) {
+	r := NewReplier(mockCompleter{out: `{"response":"запис`}, nil)
+	got, err := r.PhraseReply(context.Background(), noteDecision())
+	if err == nil || got != "" {
+		t.Errorf("got %q, %v, want empty and an error", got, err)
+	}
+}
+
+func TestReplierEmptyOutputIsEmpty(t *testing.T) {
+	r := NewReplier(mockCompleter{out: ""}, nil)
+	got, err := r.PhraseReply(context.Background(), noteDecision())
+	if err != nil || got != "" {
+		t.Errorf("got %q, %v, want empty and no error", got, err)
+	}
+}
+
+// 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 TestReplierCarriesTheResponseGrammar(t *testing.T) {
+	rec := &grammarRecorder{}
+	r := NewReplier(rec, nil)
+	if _, err := r.PhraseReply(context.Background(), noteDecision()); err != nil {
+		t.Fatalf("PhraseReply: %v", err)
+	}
+	if rec.req.Grammar != ResponseGrammar {
+		t.Errorf("grammar = %q, want ResponseGrammar", rec.req.Grammar)
+	}
+	if rec.req.System != ReplySystemPrompt {
+		t.Errorf("system prompt = %q, want ReplySystemPrompt", rec.req.System)
+	}
+}
+
+func noteDecision() router.Decision {
+	return router.Decision{Intent: router.IntentNote, Slots: router.Slots{Text: "кофе закончился"}}
+}
+
+var errTestLLMDown = errTest("llm down")
+
+type errTest string
+
+func (e errTest) Error() string { return string(e) }