provider/llamaswap/audio.go

@@ -63,7 +63,7 @@ func (m *speechModel) Speak(ctx context.Context, req audio.SpeechRequest, opts .
 	if err != nil {
 		return nil, fmt.Errorf("llama-swap: encode speech request: %w", err)
 	}
-	audioBytes, contentType, err := m.p.doRaw(ctx, http.MethodPost, "/v1/audio/speech", m.id, "application/json", bytes.NewReader(body))
+	audioBytes, contentType, err := m.p.doRaw(ctx, http.MethodPost, "/v1/audio/speech", m.id, "application/json", bytes.NewReader(body), maxResponseBytes)
 	if err != nil {
 		return nil, err
 	}
@@ -140,7 +140,7 @@ func (m *transcriptionModel) Transcribe(ctx context.Context, req audio.Transcrip
 		return nil, fmt.Errorf("llama-swap: build transcription form: %w", err)
 	}
 
-	raw, _, err := m.p.doRaw(ctx, http.MethodPost, "/v1/audio/transcriptions", m.id, w.FormDataContentType(), &buf)
+	raw, _, err := m.p.doRaw(ctx, http.MethodPost, "/v1/audio/transcriptions", m.id, w.FormDataContentType(), &buf, maxResponseBytes)
 	if err != nil {
 		return nil, err
 	}
@@ -201,7 +201,7 @@ func (p *Provider) ListVoices(ctx context.Context, model string) ([]string, erro
 	if model == "" {
 		return nil, fmt.Errorf("llama-swap: ListVoices requires a model id")
 	}
-	raw, _, err := p.doRaw(ctx, http.MethodGet, "/v1/audio/voices?model="+url.QueryEscape(model), model, "", nil)
+	raw, _, err := p.doRaw(ctx, http.MethodGet, "/v1/audio/voices?model="+url.QueryEscape(model), model, "", nil, maxResponseBytes)
 	if err != nil {
 		return nil, err
 	}
@@ -256,10 +256,10 @@ func parseVoices(raw []byte) ([]string, error) {
 
 // doRaw performs a request to a llama-swap endpoint and returns the raw
 // response body and its Content-Type — the sibling of doJSON for endpoints
-// whose success payload is not JSON (audio bytes) or whose shape varies.
-// contentType sets the request Content-Type when body is non-nil. A response
-// larger than maxResponseBytes is an error, never a silent truncation.
-func (p *Provider) doRaw(ctx context.Context, method, path, model, contentType string, body io.Reader) ([]byte, string, error) {
+// whose success payload is not JSON (audio/video bytes) or whose shape
+// varies. contentType sets the request Content-Type when body is non-nil.
+// A response larger than maxBytes is an error, never a silent truncation.
+func (p *Provider) doRaw(ctx context.Context, method, path, model, contentType string, body io.Reader, maxBytes int64) ([]byte, string, error) {
 	if err := p.requireBaseURL(); err != nil {
 		return nil, "", err
 	}
@@ -275,12 +275,12 @@ func (p *Provider) doRaw(ctx context.Context, method, path, model, contentType s
 	if resp.StatusCode/100 != 2 {
 		return nil, "", p.apiError(resp, model)
 	}
-	data, err := io.ReadAll(io.LimitReader(resp.Body, maxResponseBytes+1))
+	data, err := io.ReadAll(io.LimitReader(resp.Body, maxBytes+1))
 	if err != nil {
 		return nil, "", fmt.Errorf("llama-swap: read response: %w", err)
 	}
-	if len(data) > maxResponseBytes {
-		return nil, "", fmt.Errorf("llama-swap: response exceeds %d bytes", maxResponseBytes)
+	if int64(len(data)) > maxBytes {
+		return nil, "", fmt.Errorf("llama-swap: response exceeds %d bytes", maxBytes)
 	}
 	return data, resp.Header.Get("Content-Type"), nil
 }

provider/llamaswap/llamaswap.go

@@ -47,6 +47,12 @@ const DefaultName = "llama-swap"
 // can't make a decode allocate without limit.
 const maxResponseBytes = 64 << 20
 
+// maxVideoResponseBytes caps the /v1/videos/sync body — the response IS an
+// encoded clip, which legitimately dwarfs any JSON/audio payload (a long
+// high-bitrate generation can pass 64MB). Still bounded so a buggy upstream
+// can't allocate without limit.
+const maxVideoResponseBytes = 512 << 20
+
 // Provider is a llama-swap client. It satisfies llm.Provider (chat, delegated
 // to provider/openai) and imagegen.Provider (image generation), and exposes
 // llama-swap's management endpoints as concrete methods.

provider/llamaswap/video.go

@@ -96,7 +96,7 @@ func (m *videoModel) Generate(ctx context.Context, req videogen.Request, opts ..
 		return nil, fmt.Errorf("llama-swap: build video form: %w", err)
 	}
 
-	videoBytes, contentType, err := m.p.doRaw(ctx, http.MethodPost, "/v1/videos/sync", m.id, w.FormDataContentType(), &buf)
+	videoBytes, contentType, err := m.p.doRaw(ctx, http.MethodPost, "/v1/videos/sync", m.id, w.FormDataContentType(), &buf, maxVideoResponseBytes)
 	if err != nil {
 		return nil, err
 	}
@@ -145,7 +145,7 @@ func initImageFilename(mimeType string) string {
 		return "frame.jpg"
 	case "image/webp":
 		return "frame.webp"
-	default: // stable-diffusion outputs and unknowns: PNG is the safe hint
+	default: // unknown MIME — PNG is the safe hint
 		return "frame.png"
 	}
 }

provider/llamaswap/video_test.go

@@ -23,6 +23,7 @@ func TestVideoGenerate(t *testing.T) {
 		gotContentType = r.Header.Get("Content-Type")
 		if err := r.ParseMultipartForm(32 << 20); err != nil {
 			t.Errorf("parse form: %v", err)
+			return
 		}
 		gotForm = map[string]string{}
 		for k, v := range r.MultipartForm.Value {