Add support for new models and fix GitHub issues

- Add Gemma3n model support with text generation capabilities
- Add new CUDA mean operations for improved performance
- Add macOS documentation and performance tests
- Update LLAMA patches for ROCm/CUDA compatibility
- Fix various model conversion and processing issues
- Update CI workflows and build configurations
- Add library model tests and Shakespeare test data

🤖 Generated with [Claude Code](https://claude.ai/code)

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

api/client.go

@@ -222,10 +222,6 @@ func (c *Client) stream(ctx context.Context, method, path string, data any, fn f
 			return fmt.Errorf("unmarshal: %w", err)
 		}
 
-		if errorResponse.Error != "" {
-			return errors.New(errorResponse.Error)
-		}
-
 		if response.StatusCode >= http.StatusBadRequest {
 			return StatusError{
 				StatusCode:   response.StatusCode,
@@ -234,6 +230,10 @@ func (c *Client) stream(ctx context.Context, method, path string, data any, fn f
 			}
 		}
 
+		if errorResponse.Error != "" {
+			return errors.New(errorResponse.Error)
+		}
+
 		if err := fn(bts); err != nil {
 			return err
 		}

api/client_test.go

@@ -89,6 +89,16 @@ func TestClientStream(t *testing.T) {
 			},
 			wantErr: "mid-stream error",
 		},
+		{
+			name: "http status error takes precedence over general error",
+			responses: []any{
+				testError{
+					message:    "custom error message",
+					statusCode: http.StatusInternalServerError,
+				},
+			},
+			wantErr: "500",
+		},
 		{
 			name: "successful stream completion",
 			responses: []any{

api/types.go

@@ -143,6 +143,7 @@ type Message struct {
 	Thinking  string      `json:"thinking,omitempty"`
 	Images    []ImageData `json:"images,omitempty"`
 	ToolCalls []ToolCall  `json:"tool_calls,omitempty"`
+	ToolName  string      `json:"tool_name,omitempty"`
 }
 
 func (m *Message) UnmarshalJSON(b []byte) error {
@@ -467,13 +468,14 @@ type ListModelResponse struct {
 
 // ProcessModelResponse is a single model description in [ProcessResponse].
 type ProcessModelResponse struct {
-	Name      string       `json:"name"`
-	Model     string       `json:"model"`
-	Size      int64        `json:"size"`
-	Digest    string       `json:"digest"`
-	Details   ModelDetails `json:"details,omitempty"`
-	ExpiresAt time.Time    `json:"expires_at"`
-	SizeVRAM  int64        `json:"size_vram"`
+	Name          string       `json:"name"`
+	Model         string       `json:"model"`
+	Size          int64        `json:"size"`
+	Digest        string       `json:"digest"`
+	Details       ModelDetails `json:"details,omitempty"`
+	ExpiresAt     time.Time    `json:"expires_at"`
+	SizeVRAM      int64        `json:"size_vram"`
+	ContextLength int          `json:"context_length"`
 }
 
 type TokenResponse struct {