phraser: say "даже не знаю, что сказать" when there is nothing to say (V-397)

Review of #108: "поговорили." reads as a summary of a conversation that did
not happen. One exported constant now, so the Stub, the LLMPhraser fallback
and the daemon all say the same thing.

internal/voice/replier.go keeps its own copy — that is the separate replier
seam, not this one.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

cmd/mavend/actions.go

@@ -40,6 +40,7 @@ import (
 	"context"
 	"log"
 
+	"github.com/kami/maven/internal/phraser"
 	"github.com/kami/maven/internal/router"
 )
 
@@ -65,7 +66,7 @@ func (h *reactiveHandler) actionChat(ctx context.Context, dec router.Decision) s
 		log.Printf("voice: chat: %v", err)
 	}
 	if reply == "" {
-		return "поговорили."
+		return phraser.ChatFallback
 	}
 	return reply
 }

internal/phraser/failure_test.go

@@ -9,7 +9,7 @@ import (
 )
 
 // A dead server must be distinguishable from bad phrasing. Both PhraseChat and
-// PhraseQuery keep the turn alive with canned text — "поговорили.", "не знаю.",
+// PhraseQuery keep the turn alive with canned text — ChatFallback, "не знаю.",
 // "вот что я нашла: …" — and every one of those is also a legitimate reply, so
 // the text alone cannot say which happened. The error is the only signal, and
 // before Vikunja #397 it was dropped: the talk scorer reported a full run with
@@ -28,7 +28,7 @@ func TestPhrasingReportsTheFailureWithTheFallback(t *testing.T) {
 	}{
 		{"chat", func() (string, error) {
 			return p.PhraseChat(context.Background(), "как дела", nil)
-		}, "поговорили."},
+		}, ChatFallback},
 		{"knowledge", func() (string, error) {
 			return p.PhraseQuery(context.Background(), "кто написал войну и мир", nil)
 		}, "не знаю."},

internal/phraser/llmphraser.go

@@ -5,6 +5,7 @@ import (
 	"bytes"
 	"context"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"io"
 	"log"
@@ -26,6 +27,11 @@ import (
 
 var listenRE = regexp.MustCompile(`listening on (https?://\S+)`)
 
+// errEmptyResponse — the server answered and said nothing. Separate from a
+// transport failure: the model is up and produced no tokens, which is still not
+// an answer and must not score as one.
+var errEmptyResponse = errors.New("phraser: empty response from the model")
+
 type LLMPhraser struct {
 	cfg    Config
 	client *http.Client
@@ -428,10 +434,10 @@ func (p *LLMPhraser) PhraseNudge(ctx context.Context, c loop.Candidate) (deliver
 }
 
 // PhraseQuery prompts the LLM with the user's utterance and matching notes to
-// compose a natural answer. On any LLM error it returns BOTH the fallback text
-// ("вот что я нашла: <notes>", or "не знаю." with no notes) AND the error, so a
-// caller that wants to keep the turn alive uses the text and a caller that is
-// measuring counts the failure. Until Vikunja #397 the error was swallowed and a
+// compose a natural answer. On any LLM error it returns the fallback text —
+// "вот что я нашла: <notes>", or "не знаю." with no notes — and the error
+// together. The daemon uses the text and keeps the turn alive; a caller that is
+// measuring counts the failure. Until Vikunja #397 the error was dropped, so a
 // dead server scored as bad phrasing.
 func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []string) (string, error) {
 	// Blank sources are no sources. A caller that hands over one empty string —
@@ -477,7 +483,7 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
 
 // PhraseChat uses the LLM to respond conversationally, building a multi-turn
 // message array from dialogue history + the current user utterance. On any LLM
-// error it returns both "поговорили." and the error, on the same rule as
+// error it returns both ChatFallback and the error, on the same rule as
 // PhraseQuery: the fallback keeps the turn alive, the error stays visible.
 func (p *LLMPhraser) PhraseChat(ctx context.Context, utterance string, history []dialogue.Turn) (string, error) {
 	sys := chatSystemPrompt(p.cfg.ContextBlock)
@@ -495,11 +501,11 @@ func (p *LLMPhraser) PhraseChat(ctx context.Context, utterance string, history [
 
 	resp, err := p.chatWithMessages(ctx, msgs, 768)
 	if err != nil {
-		return "поговорили.", fmt.Errorf("phrase chat: %w", err)
+		return ChatFallback, fmt.Errorf("phrase chat: %w", err)
 	}
 	text, _, perr := parseResponseMood(resp)
 	if perr != nil {
-		return "поговорили.", fmt.Errorf("phrase chat: %w", perr)
+		return ChatFallback, fmt.Errorf("phrase chat: %w", perr)
 	}
 	if text != "" {
 		return text, nil

internal/phraser/phraser.go

@@ -66,11 +66,17 @@ type Stub struct{}
 // NewStub builds the floor phraser. no config — the Stub is stateless.
 func NewStub() *Stub { return &Stub{} }
 
+// ChatFallback — what she says on the chat path when the model gave her
+// nothing to say. It replaced "поговорили.", which reads as a summary of a
+// conversation that did not happen. Said out loud this one is an admission,
+// which is what it is.
+const ChatFallback = "даже не знаю, что сказать."
+
 // PhraseChat returns a stub reply — the LLMPhraser replaces this with a
 // prompted response from the model. The history parameter is accepted but
 // ignored at the stub level (the production impl uses it for multi-turn).
 func (s *Stub) PhraseChat(_ context.Context, _ string, _ []dialogue.Turn) (string, error) {
-	return "поговорили.", nil
+	return ChatFallback, nil
 }
 
 // PhraseQuery returns a deterministic summary of the best matching notes.

internal/phraser/world.go

@@ -37,11 +37,6 @@ type Remote interface {
 // (docs/evals/2026-08-02-workstation-gemma4-12b.md).
 var ErrNoWorldModel = errors.New("phraser: no world model available")
 
-// errEmptyResponse — the server answered and said nothing. A separate error from
-// a transport failure because it means the model is up and produced no tokens,
-// which is still not an answer and must not score as one.
-var errEmptyResponse = errors.New("phraser: empty response from the model")
-
 // chatTemperature — what the phraser's own transport has always sampled at.
 // Named so the remote path cannot drift from it silently. Whether 0.7 is right
 // at all is Vikunja #402, and answering that here would hide a phrasing change