phraser: the reminder summary is cut in runes, and silence is an error (V-620)

Three defects in internal/phraser, all of the shape "reports done when
nothing happened".

The reminder summary was cut in bytes: `len(s) > 60` and `s[:57]`, in two
copies (Stub.PhraseReminder and LLMPhraser.PhraseReminder). On Russian a
letter is two bytes, so the cut fell at about 28 letters instead of 60 and
landed inside a letter about half the time. Sendable.Summary is what
voicesink hands to piper and what the telegram sink posts, so the half rune
was spoken and sent. One rune-counting helper now, shared by both. The test
that covered this was ASCII, which is what let the arithmetic stand.

The evidence branch of PhraseQuery and the bare-prose tail of PhraseChat
both returned ("", nil) when the server answered and the model wrote no
tokens. The knowledge branch has guarded that with errEmptyResponse since it
was written; these two did not. The daemon's callers check for the empty
string and paper over it, so the visible cost was the eval, which scored a
silent model as bad phrasing rather than as a failure, and a log line that
never appeared.

Stub.PhraseReminder set no Mood. Its sibling PhraseNudge sets "neutral" and
says in a comment why: the Stub is a production fallback and owes the output
contract a value. The zero value is not one of the five moods.

No prompt and no spoken wording changed, so the phrasing eval is unmoved.

internal/phraser/failure_test.go

@@ -78,3 +78,36 @@ func TestEmptyKnowledgeAnswerIsAnError(t *testing.T) {
 		t.Errorf("error = %v; want it to name the empty response", err)
 	}
 }
+
+// The other two paths, which had no such guard. The evidence branch of
+// PhraseQuery and PhraseChat both returned ("", nil) off a server that produced
+// no tokens — an empty answer reported as a successful phrasing. The daemon's
+// callers check for the empty string and paper over it; the eval does not, and
+// scored a silent model as bad phrasing rather than as a failure.
+func TestEmptyAnswerIsAnErrorOnEveryPath(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		w.Write([]byte(`{"choices":[{"message":{"content":""}}]}`))
+	}))
+	t.Cleanup(srv.Close)
+	p := NewLLMPhraserAt(srv.URL, Config{})
+
+	t.Run("evidence", func(t *testing.T) {
+		got, err := p.PhraseQuery(context.Background(), "сколько воды я выпил", []string{"два литра"})
+		if err == nil {
+			t.Fatal("an empty response scored as an answer")
+		}
+		if !isFallback(t, fbQuerySources, "два литра", got) {
+			t.Errorf("fallback text = %q, want a %q variant", got, fbQuerySources)
+		}
+	})
+	t.Run("chat", func(t *testing.T) {
+		got, err := p.PhraseChat(context.Background(), "как дела", nil)
+		if err == nil {
+			t.Fatal("an empty response scored as an answer")
+		}
+		if !isFallback(t, fbChat, "", got) {
+			t.Errorf("fallback text = %q, want a %q variant", got, fbChat)
+		}
+	})
+}