eval: score the reply path, the fourth phrasing path (V-396)

Nine reply cases and a fourth column in the talk report. The reply path is a
separate object from the phraser in the daemon, so Pair joins a Talker and a
Confirmer for a run that covers everything Maven says.

Cases carry intent/key/value because the replier is phrased from the decision the
router resolved, not from the raw utterance. Three of them are baits the other
paths cannot produce: a masculine verb about himself that she must not copy onto
herself, a polite plural input that must still come back на ты, and an unresolved
note that invites a question a confirmation is not allowed to ask.

Not scored against a model here — this box has no llama-server, and the baseline
test is opt-in on MAVEN_LLM_URL.

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."
     }
   ]
 }