cmd/mavend/actions.go

@@ -58,9 +58,13 @@ func (h *reactiveHandler) actionChat(ctx context.Context, dec router.Decision) s
 	// Conversational: build history from dialogue session (prior user turns)
 	// and let the LLM respond from general knowledge + context.
 	history := h.chatHistory()
+	// The phraser hands back its own fallback text alongside the error, so the
+	// turn survives a dead server and the failure still reaches the log.
 	reply, err := h.phraser.PhraseChat(ctx, dec.Utterance, history)
 	if err != nil {
 		log.Printf("voice: chat: %v", err)
+	}
+	if reply == "" {
 		return "поговорили."
 	}
 	return reply

cmd/mavend/actions_query.go

@@ -445,7 +445,13 @@ func (h *reactiveHandler) queryMemory(ctx context.Context, t *queryTurn) (string
 	// A note is phrased in Maven's voice; a fact is read back as it was
 	// stored.
 	if hit.Meta["type"] == "note" {
-		if reply, perr := h.phraser.PhraseQuery(ctx, t.dec.Utterance, []string{text}); perr == nil && reply != "" {
+		reply, perr := h.phraser.PhraseQuery(ctx, t.dec.Utterance, []string{text})
+		switch {
+		case perr != nil:
+			// Reading the note back verbatim beats the phraser's own fallback,
+			// which only wraps the same text in "вот что я нашла:".
+			log.Printf("voice: recall phrase: %v", perr)
+		case reply != "":
 			return reply, true
 		}
 	}

cmd/mavend/worldmodel.go

@@ -54,7 +54,11 @@ func (h *reactiveHandler) phraseSource(ctx context.Context, name, utterance stri
 		log.Printf("voice: %s: no world model, reading the source back instead", name)
 		return ""
 	case err != nil:
+		// The resident phraser answers this call with its fallback text and the
+		// error together. Drop the text: these callers hold the passage itself
+		// and read it back better than "вот что я нашла: <passage>" does.
 		log.Printf("voice: %s: phrase: %v", name, err)
+		return ""
 	}
 	return reply
 }

internal/phraser/eval/talk.go

@@ -78,6 +78,12 @@ type TalkCase struct {
 	Note      string   `json:"note,omitempty"`
 }
 
+// TalkSchemaVersion — the version this loader understands. Separate from the
+// nudge fixture's SchemaVersion: the two fixtures have different shapes and
+// change on different days, and one shared constant would force a bump on the
+// fixture that did not move.
+const TalkSchemaVersion = 1
+
 // TalkFixture — the versioned envelope, same gating as Fixture.
 type TalkFixture struct {
 	SchemaVersion int        `json:"schema_version"`
@@ -92,8 +98,8 @@ func LoadTalk() (TalkFixture, error) {
 	if err := json.Unmarshal(talkFixtureJSON, &f); err != nil {
 		return TalkFixture{}, fmt.Errorf("parse talk fixture: %w", err)
 	}
-	if f.SchemaVersion != SchemaVersion {
-		return TalkFixture{}, fmt.Errorf("talk fixture schema_version %d, want %d", f.SchemaVersion, SchemaVersion)
+	if f.SchemaVersion != TalkSchemaVersion {
+		return TalkFixture{}, fmt.Errorf("talk fixture schema_version %d, want %d", f.SchemaVersion, TalkSchemaVersion)
 	}
 	if len(f.Cases) == 0 {
 		return TalkFixture{}, fmt.Errorf("talk fixture has no cases")

internal/phraser/eval/talk_test.go

@@ -142,19 +142,13 @@ func TestLLMTalkBaseline(t *testing.T) {
 	p := phraser.NewLLMPhraserAt(base, cfg)
 	defer p.Close()
 
-	// Unreachable server is fatal here, not a logged warning, and that differs
-	// from the nudge test on purpose. PhraseNudge returns its errors, so a dead
-	// server there shows up honestly in the Errors column. PhraseChat and
-	// PhraseQuery do NOT: they swallow every failure and return a canned string
-	// ("поговорили.", "не знаю.", "вот что я нашла: …"). So on these three paths
-	// a dead server produces a full report with 0 errors and a terrible score —
-	// a number that looks like bad phrasing and is really no phrasing at all.
-	// Refusing to score without a confirmed model is the only guard available
-	// until the phraser reports its failures (Vikunja #397).
+	// The model id names the run in the report. Since Vikunja #397 every path
+	// returns its errors, so a server that dies mid-run shows up in the Errors
+	// column instead of scoring as bad phrasing — the before-and-after probe that
+	// used to stand in for that is gone.
 	model, err := llm.ModelID(ctx, base)
 	if err != nil {
-		t.Fatalf("no model at %s: %v — refusing to score, these paths hide their errors "+
-			"and would report a plausible-looking result off a dead server", base, err)
+		t.Fatalf("no model at %s: %v", base, err)
 	}
 	t.Logf("scoring model %s at %s", model, base)
 
@@ -169,10 +163,11 @@ func TestLLMTalkBaseline(t *testing.T) {
 	}
 	t.Log("\n" + rep.String() + "\nreplies:\n" + rep.Replies() + "\nfailures:\n" + rep.Failures())
 
-	// And again afterwards: the run takes minutes, and a server that died or got
-	// OOM-killed halfway through would leave the first cases scored and the rest
-	// silently canned. Checking only at the start would not catch that.
-	if _, err := llm.ModelID(ctx, base); err != nil {
-		t.Fatalf("model at %s went away during the run: %v — the score above is not trustworthy", base, err)
+	// A run where nothing was phrased is not a low score, it is no measurement.
+	if rep.Errors == rep.Total {
+		t.Fatalf("every case errored — nothing was measured, the score above is not a phrasing result")
+	}
+	if rep.Errors > 0 {
+		t.Logf("%d/%d cases errored — those are model failures, not phrasing failures", rep.Errors, rep.Total)
 	}
 }