Merge pull request 'The reply path can't be tested — llmReplier is stuck in package main' (#107) from task/396-the-reply-path-can-t-be-tested-llmreplie into master

Reviewed-on: #107

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)
-	}
-}

internal/phraser/eval/talk.go

@@ -26,20 +26,22 @@ import (
 	"time"
 
 	"github.com/kami/maven/internal/dialogue"
+	"github.com/kami/maven/internal/router"
 )
 
 //go:embed talk_v1.json
 var talkFixtureJSON []byte
 
-// The three phrasing paths under test. Values match the fixture's "path" field.
+// The phrasing paths under test. Values match the fixture's "path" field.
 const (
 	PathChat      = "chat"      // PhraseChat
 	PathQuery     = "query"     // PhraseQuery with notes
 	PathKnowledge = "knowledge" // PhraseQuery with no notes
+	PathReply     = "reply"     // PhraseReply, the reactive confirmation
 )
 
 // TalkPaths — report order.
-var TalkPaths = []string{PathChat, PathQuery, PathKnowledge}
+var TalkPaths = []string{PathChat, PathQuery, PathKnowledge, PathReply}
 
 // TalkCheckNames — the checks that apply to a free-form reply, in report order.
 // Deliberately a subset of CheckNames: length, mood and "no questions" are nudge
@@ -58,12 +60,19 @@ var TalkCheckNames = []string{
 // WantAny is the on-topic contract: at least one lowercased fragment must appear
 // in the reply. Fragments are stems ("пароль" → "парол") so declension does not
 // defeat them.
+//
+// Intent, Key and Value carry the reply path's decision: that path is phrased
+// from what the router already resolved, not from the raw utterance. Utterance
+// stays filled anyway, because it is what a human reads in the report.
 type TalkCase struct {
 	ID        string   `json:"id"`
 	Path      string   `json:"path"`
 	Utterance string   `json:"utterance"`
 	History   []string `json:"history,omitempty"`
 	Notes     []string `json:"notes,omitempty"`
+	Intent    string   `json:"intent,omitempty"`
+	Key       string   `json:"key,omitempty"`
+	Value     string   `json:"value,omitempty"`
 	WantAny   []string `json:"want_any"`
 	Tags      []string `json:"tags,omitempty"`
 	Note      string   `json:"note,omitempty"`
@@ -92,13 +101,27 @@ func LoadTalk() (TalkFixture, error) {
 	return f, nil
 }
 
-// Talker — the two methods a conversational path must have to be scorable.
-// *phraser.LLMPhraser satisfies it; same trick as Nudger.
+// Talker — the methods a conversational path must have to be scorable.
+// *phraser.LLMPhraser satisfies the first two; *phraser.Replier satisfies the
+// third, so a run that scores all four paths passes a Pair.
 type Talker interface {
 	PhraseChat(ctx context.Context, utterance string, history []dialogue.Turn) (string, error)
 	PhraseQuery(ctx context.Context, utterance string, notes []string) (string, error)
 }
 
+// Confirmer — the reply path. *phraser.Replier satisfies it.
+type Confirmer interface {
+	PhraseReply(ctx context.Context, d router.Decision) (string, error)
+}
+
+// Pair joins the two objects the daemon wires separately — the phraser and the
+// replier — so one ScoreTalk call covers every path Maven speaks through. A bare
+// Talker still works; its reply cases score as errors, which is honest.
+type Pair struct {
+	Talker
+	Confirmer
+}
+
 // TalkOutcome — one scored case.
 type TalkOutcome struct {
 	Case    TalkCase
@@ -194,10 +217,30 @@ func (c TalkCase) run(ctx context.Context, t Talker) (string, error) {
 		return t.PhraseQuery(ctx, c.Utterance, c.Notes)
 	case PathKnowledge:
 		return t.PhraseQuery(ctx, c.Utterance, nil)
+	case PathReply:
+		conf, ok := t.(Confirmer)
+		if !ok {
+			return "", fmt.Errorf("target cannot phrase replies — pass a Pair")
+		}
+		return conf.PhraseReply(ctx, c.decision())
 	}
 	return "", fmt.Errorf("unknown path %q", c.Path)
 }
 
+// decision rebuilds what the router would have handed the replier. Text is the
+// utterance for a note or a reminder, which is what the router puts there.
+func (c TalkCase) decision() router.Decision {
+	return router.Decision{
+		Intent: router.Intent(c.Intent),
+		Slots: router.Slots{
+			Key:    c.Key,
+			Value:  c.Value,
+			Text:   c.Utterance,
+			HasKey: c.Key != "",
+		},
+	}
+}
+
 func (c TalkCase) turns() []dialogue.Turn {
 	turns := make([]dialogue.Turn, 0, len(c.History))
 	for _, h := range c.History {

internal/phraser/eval/talk_test.go

@@ -11,6 +11,7 @@ import (
 	"github.com/kami/maven/internal/llm"
 	"github.com/kami/maven/internal/persona"
 	"github.com/kami/maven/internal/phraser"
+	"github.com/kami/maven/internal/router"
 )
 
 // perPathMinimum — the resolution floor. A per-path score built on a handful of
@@ -36,6 +37,10 @@ func TestTalkFixture(t *testing.T) {
 
 		switch c.Path {
 		case PathChat, PathQuery, PathKnowledge:
+		case PathReply:
+			if c.Intent == "" {
+				t.Errorf("%s: reply case has no intent — the replier is phrased from the decision", c.ID)
+			}
 		default:
 			t.Errorf("%s: unknown path %q", c.ID, c.Path)
 		}
@@ -69,10 +74,15 @@ type fakeTalker struct{ reply string }
 func (f fakeTalker) PhraseChat(context.Context, string, []dialogue.Turn) (string, error) {
 	return f.reply, nil
 }
+
 func (f fakeTalker) PhraseQuery(context.Context, string, []string) (string, error) {
 	return f.reply, nil
 }
 
+func (f fakeTalker) PhraseReply(context.Context, router.Decision) (string, error) {
+	return f.reply, nil
+}
+
 // TestScoreTalkCounts — a reply that fails on purpose must be counted on every
 // path, so a real run cannot report a hidden zero.
 func TestScoreTalkCounts(t *testing.T) {
@@ -104,7 +114,7 @@ func TestScoreTalkCounts(t *testing.T) {
 	}
 }
 
-// TestLLMTalkBaseline — the resident model on the three conversational paths.
+// TestLLMTalkBaseline — the resident model on all four phrasing paths.
 // Opt-in exactly like TestLLMPhrasingBaseline: CI has no model and a run costs
 // minutes on the CPU target.
 //
@@ -148,7 +158,12 @@ func TestLLMTalkBaseline(t *testing.T) {
 	}
 	t.Logf("scoring model %s at %s", model, base)
 
-	rep, err := ScoreTalk(ctx, "llm ("+model+", built-in persona)", p, f)
+	// The reply path is a separate object in the daemon too: the phraser owns its
+	// own llama-server, the replier is handed an llm.Client. Pair scores both.
+	block := func() string { return persona.Facts{}.Block(time.Now()) }
+	target := Pair{Talker: p, Confirmer: phraser.NewReplier(llm.New(base, cfg.Timeout), block)}
+
+	rep, err := ScoreTalk(ctx, "llm ("+model+", built-in persona)", target, f)
 	if err != nil {
 		t.Fatalf("ScoreTalk: %v", err)
 	}

internal/phraser/eval/talk_v1.json

@@ -222,6 +222,90 @@
       "utterance": "почему гром слышно позже молнии?",
       "want_any": ["звук", "све", "быстр", "гром", "молни"],
       "tags": ["general"]
+    },
+    {
+      "id": "reply-fact-coffee",
+      "path": "reply",
+      "intent": "fact",
+      "key": "кофе",
+      "value": "закончился",
+      "utterance": "кофе закончился",
+      "want_any": ["коф"],
+      "tags": ["fact"],
+      "note": "The plainest confirmation there is, and the sentence he hears most often."
+    },
+    {
+      "id": "reply-fact-weight",
+      "path": "reply",
+      "intent": "fact",
+      "key": "вес",
+      "value": "82",
+      "utterance": "мой вес 82",
+      "want_any": ["вес", "82"],
+      "tags": ["fact", "number"],
+      "note": "A number must survive into the confirmation; a paraphrase that drops it is useless."
+    },
+    {
+      "id": "reply-fact-pill",
+      "path": "reply",
+      "intent": "fact",
+      "key": "таблетки",
+      "value": "выпил",
+      "utterance": "таблетки выпил",
+      "want_any": ["таблетк"],
+      "tags": ["fact", "feminine"],
+      "note": "He says 'выпил', masculine and about himself. She must not copy the form onto herself."
+    },
+    {
+      "id": "reply-note-router",
+      "path": "reply",
+      "intent": "note",
+      "utterance": "роутер перезагружается сам по ночам",
+      "want_any": ["роутер"],
+      "tags": ["note"]
+    },
+    {
+      "id": "reply-note-long",
+      "path": "reply",
+      "intent": "note",
+      "utterance": "если диск снова отвалится, посмотреть кабель, а не контроллер, в прошлый раз был кабель",
+      "want_any": ["диск", "кабел"],
+      "tags": ["note", "length"],
+      "note": "A long note baits a long confirmation. One sentence is the contract."
+    },
+    {
+      "id": "reply-reminder-evening",
+      "path": "reply",
+      "intent": "reminder",
+      "utterance": "напомни вечером полить цветы",
+      "want_any": ["цвет", "полит", "вечер"],
+      "tags": ["reminder"]
+    },
+    {
+      "id": "reply-reminder-tomorrow",
+      "path": "reply",
+      "intent": "reminder",
+      "utterance": "напомни завтра позвонить в поликлинику",
+      "want_any": ["поликлиник", "позвон", "звон"],
+      "tags": ["reminder"]
+    },
+    {
+      "id": "reply-formality-bait",
+      "path": "reply",
+      "intent": "note",
+      "utterance": "запишите пожалуйста что счётчики я сдал",
+      "want_any": ["счётчик", "счетчик"],
+      "tags": ["note", "persona-bait", "address"],
+      "note": "Polite plural in the input. The confirmation must still be на ты."
+    },
+    {
+      "id": "reply-question-bait",
+      "path": "reply",
+      "intent": "note",
+      "utterance": "надо купить фильтр для воды, не помню какой",
+      "want_any": ["фильтр"],
+      "tags": ["note", "no-question"],
+      "note": "An unresolved note invites her to ask which filter. A confirmation does not ask."
     }
   ]
 }

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) }