fix: review findings — clone-route audio sniffing, zip caps, filename sanitization, WAV response caps

- speakWithReference now validates the response IS audio via the same
  audioResultMIME sniff the sfx/enhance surfaces use — a 2xx JSON soft
  error or HTML proxy page was previously wrapped up as audio/wav bytes.
- audioResultMIME moves to audio.go (next to speechMIME; it was defined
  in sfx.go but shared by enhance/clone) and learns the Ogg container
  normalization (application/ogg -> audio/ogg).
- Stems zip unpack gains entry-count (16) and total-decompressed (1GB)
  caps on top of the existing per-entry cap — the per-entry bound alone
  still let a many-entry bomb multiply up.
- sanitizeFilename drops NUL and both path separators too, so upload
  metadata can never smuggle directory structure to a file-writing shim.
- New maxAudioResponseBytes (256MB) for bodies that ARE one audio clip
  (clone, enhance, sfx): a long WAV legitimately passes the 64MB JSON
  cap.
- speakWithReference local renamed path -> upPath (naming parity with
  stems/enhance).

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01WWCQcYStWXBYUy5sZWnbLT

provider/llamaswap/clone_translate_test.go

@@ -2,12 +2,14 @@ package llamaswap
 
 import (
 	"context"
+	"errors"
 	"io"
 	"net/http"
 	"net/http/httptest"
 	"testing"
 
 	"gitea.stevedudenhoeffer.com/steve/majordomo/audio"
+	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
 )
 
 func TestSpeakWithReferenceUsesCloneRoute(t *testing.T) {
@@ -54,7 +56,7 @@ func TestSpeakWithReferenceUsesCloneRoute(t *testing.T) {
 	}
 }
 
-func TestSpeakWithReferenceDefaultsToWavMIME(t *testing.T) {
+func TestSpeakWithReferenceSniffsHeaderlessWav(t *testing.T) {
 	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		if err := r.ParseMultipartForm(1 << 20); err != nil {
 			t.Fatalf("parse multipart: %v", err)
@@ -65,7 +67,7 @@ func TestSpeakWithReferenceDefaultsToWavMIME(t *testing.T) {
 			}
 		}
 		w.Header()["Content-Type"] = nil // no declared type at all
-		_, _ = w.Write([]byte("RAWAUDIO"))
+		_, _ = w.Write(wavFixture())
 	}))
 	defer srv.Close()
 
@@ -77,9 +79,43 @@ func TestSpeakWithReferenceDefaultsToWavMIME(t *testing.T) {
 	if err != nil {
 		t.Fatalf("Speak: %v", err)
 	}
-	// The clone route's default container is wav, not the JSON route's mp3.
+	// Headerless RIFF sniffs audio/wave, normalized to the conventional wav.
 	if res.MIME != "audio/wav" {
-		t.Errorf("MIME = %q, want audio/wav fallback", res.MIME)
+		t.Errorf("MIME = %q, want sniffed audio/wav", res.MIME)
+	}
+}
+
+func TestSpeakWithReferenceRejectsNonAudioResponse(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		// A FastAPI-style 2xx soft error must not be wrapped up as audio.
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"detail":"reference audio too short"}`))
+	}))
+	defer srv.Close()
+
+	p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
+	sm, _ := p.SpeechModel("chatterbox")
+	_, err := sm.Speak(context.Background(),
+		audio.SpeechRequest{Input: "hi"},
+		audio.WithReferenceAudio([]byte("REF"), "audio/wav"))
+	var apiErr *llm.APIError
+	if !errors.As(err, &apiErr) {
+		t.Fatalf("err = %v, want APIError for non-audio clone body", err)
+	}
+}
+
+func TestSanitizeFilenameStripsPathAndControlBytes(t *testing.T) {
+	for in, want := range map[string]string{
+		"song.mp3":                "song.mp3",
+		"../../etc/passwd":        "....etcpasswd",
+		"a\r\nContent-Type: evil": "aContent-Type: evil",
+		"..\\..\\boot.ini":        "....boot.ini",
+		"nul\x00byte.wav":         "nulbyte.wav",
+		"  /  ":                   "",
+	} {
+		if got := sanitizeFilename(in); got != want {
+			t.Errorf("sanitizeFilename(%q) = %q, want %q", in, got, want)
+		}
 	}
 }