feat(sandbox): update sandbox status messages and improve loading feedback

- Modified Docker run commands in CI workflows to include the `-direct` flag for enhanced server operation.
- Removed outdated loading status message during sandbox preparation and added new messages for improved user feedback.
- Introduced a loading message for waiting on AI responses, enhancing the user experience during sandbox execution.
- Refactored identity handling in stream processing to streamline message management.

Made-with: Cursor

.github/workflows/pr-test.yml

@@ -1142,7 +1142,7 @@ jobs:
             -v /tmp/kubeconfig-tai-k8s.yml:/etc/tai/kubeconfig.yml:ro \
             -e TAI_K8S_UPSTREAM="tcp://${K3D_IP}:6443" \
             -e TAI_KUBECONFIG=/etc/tai/kubeconfig.yml \
-            yaoapp/tai:latest server \
+            yaoapp/tai:latest server -direct \
             -grpc 0.0.0.0:19100 -http 0.0.0.0:8099 -vnc 0.0.0.0:16080 -k8s 0.0.0.0:16443
 
           for i in $(seq 1 30); do

.github/workflows/unit-test.yml

@@ -853,7 +853,7 @@ jobs:
             -v /tmp/kubeconfig-tai-k8s.yml:/etc/tai/kubeconfig.yml:ro \
             -e TAI_K8S_UPSTREAM="tcp://${K3D_IP}:6443" \
             -e TAI_KUBECONFIG=/etc/tai/kubeconfig.yml \
-            yaoapp/tai:latest server \
+            yaoapp/tai:latest server -direct \
             -grpc 0.0.0.0:19100 -http 0.0.0.0:8099 -vnc 0.0.0.0:16080 -k8s 0.0.0.0:16443
 
           for i in $(seq 1 30); do

agent/assistant/handlers/stream.go

@@ -227,32 +227,30 @@ func (s *streamState) handleToolCall(data []byte) int {
 		tc := toolCallArray[0]
 		props = map[string]interface{}{}
 
-		hasStaticFields := false
+		hasIdentity := false
 		if id, ok := tc["id"].(string); ok {
 			props["id"] = id
-			hasStaticFields = true
+			hasIdentity = true
 		}
 		if typ, ok := tc["type"].(string); ok {
 			props["type"] = typ
-			hasStaticFields = true
+			hasIdentity = true
 		}
 		if index, ok := tc["index"].(float64); ok {
 			props["index"] = int(index)
-			hasStaticFields = true
 		}
 		if fn, ok := tc["function"].(map[string]interface{}); ok {
 			if name, ok := fn["name"].(string); ok {
 				props["name"] = name
-				hasStaticFields = true
+				hasIdentity = true
 			}
 			if args, ok := fn["arguments"].(string); ok {
 				props["arguments"] = args
 			}
 		}
 
-		if hasStaticFields {
+		if hasIdentity {
 			// First chunk with id/name/type: merge so all fields are applied.
-			// arguments="" is included but that's fine — subsequent appends build on it.
 			deltaAction = "merge"
 		} else if _, ok := props["arguments"]; ok {
 			// Subsequent chunk with only arguments fragment: append to arguments.

agent/assistant/sandbox_v2.go

@@ -116,7 +116,6 @@ func (ast *Assistant) initSandboxV2(ctx *context.Context, opts *context.Options)
 	}
 
 	// 7. Runner.Prepare (standard context).
-	updateLoadingV2(ctx, loadingMsgID, "sandbox.configuring")
 	err = runner.Prepare(stdCtx, &sandboxTypes.PrepareRequest{
 		Computer:   computer,
 		Config:     cfg,

agent/i18n/builtin.go

@@ -100,14 +100,14 @@ func init() {
 			"kb.chat.description": "Auto-created knowledge base collection for chat sessions",
 
 			// Sandbox: assistant/sandbox.go - Sandbox status messages
-			"sandbox.preparing":     "Preparing sandbox environment",
-			"sandbox.ready":         "Sandbox ready",
-			"sandbox.working":       "Working on your request",
-			"sandbox.completed":     "Completed",
-			"sandbox.failed":        "Execution failed",
-			"sandbox.starting":      "Starting sandbox environment",
-			"sandbox.configuring":   "Configuring runtime environment",
-			"sandbox.pulling_image": "Pulling container image",
+			"sandbox.preparing":        "Getting things ready...",
+			"sandbox.ready":            "Sandbox ready",
+			"sandbox.working":          "Working on your request",
+			"sandbox.completed":        "Completed",
+			"sandbox.failed":           "Execution failed",
+			"sandbox.starting":         "Setting up workspace...",
+			"sandbox.pulling_image":    "Preparing environment (first time may take a moment)",
+			"sandbox.waiting_response": "Waiting for AI response...",
 
 			// Sandbox: claude/executor.go - Tool execution messages
 			"sandbox.tool.read":          "Reading file",
@@ -227,14 +227,14 @@ func init() {
 			"kb.chat.description": "自动为聊天会话创建的知识库集合",
 
 			// Sandbox: assistant/sandbox.go - Sandbox status messages
-			"sandbox.preparing":     "正在准备沙箱环境",
-			"sandbox.ready":         "沙箱环境就绪",
-			"sandbox.working":       "正在处理您的请求",
-			"sandbox.completed":     "处理完成",
-			"sandbox.failed":        "执行失败",
-			"sandbox.starting":      "正在启动沙箱环境",
-			"sandbox.configuring":   "正在配置运行环境",
-			"sandbox.pulling_image": "正在拉取容器镜像",
+			"sandbox.preparing":        "正在准备...",
+			"sandbox.ready":            "就绪",
+			"sandbox.working":          "正在处理您的请求",
+			"sandbox.completed":        "处理完成",
+			"sandbox.failed":           "执行失败",
+			"sandbox.starting":         "正在启动工作区...",
+			"sandbox.pulling_image":    "正在准备运行环境（首次可能需要一点时间）",
+			"sandbox.waiting_response": "等待 AI 响应...",
 
 			// Sandbox: claude/executor.go - Tool execution messages
 			"sandbox.tool.read":          "正在读取文件",
@@ -382,14 +382,14 @@ func init() {
 			"kb.chat.description": "自动为聊天会话创建的知识库集合",
 
 			// Sandbox: assistant/sandbox.go - Sandbox status messages
-			"sandbox.preparing":     "正在准备沙箱环境",
-			"sandbox.ready":         "沙箱环境就绪",
-			"sandbox.working":       "正在处理您的请求",
-			"sandbox.completed":     "处理完成",
-			"sandbox.failed":        "执行失败",
-			"sandbox.starting":      "正在启动沙箱环境",
-			"sandbox.configuring":   "正在配置运行环境",
-			"sandbox.pulling_image": "正在拉取容器镜像",
+			"sandbox.preparing":        "正在准备...",
+			"sandbox.ready":            "就绪",
+			"sandbox.working":          "正在处理您的请求",
+			"sandbox.completed":        "处理完成",
+			"sandbox.failed":           "执行失败",
+			"sandbox.starting":         "正在启动工作区...",
+			"sandbox.pulling_image":    "正在准备运行环境（首次可能需要一点时间）",
+			"sandbox.waiting_response": "等待 AI 响应...",
 
 			// Sandbox: claude/executor.go - Tool execution messages
 			"sandbox.tool.read":          "正在读取文件",

agent/sandbox/v2/claude/parse.go

@@ -78,6 +78,10 @@ func parseStreamJSON(_ context.Context, stdout io.ReadCloser, handler message.St
 						toolIndex++
 
 						if handler != nil {
+							if messageStarted {
+								handler(message.ChunkMessageEnd, nil)
+								messageStarted = false
+							}
 							if !toolBlockActive {
 								startData := message.EventMessageStartData{
 									MessageID: fmt.Sprintf("sandbox-tool-%d", time.Now().UnixNano()),
@@ -119,6 +123,7 @@ func parseStreamJSON(_ context.Context, stdout io.ReadCloser, handler message.St
 								if toolBlockActive {
 									handler(message.ChunkMessageEnd, nil)
 									toolBlockActive = false
+									messageStarted = false
 								}
 								if !messageStarted {
 									startData := message.EventMessageStartData{

agent/sandbox/v2/stream.go

@@ -8,6 +8,7 @@ import (
 	"time"
 
 	agentContext "github.com/yaoapp/yao/agent/context"
+	"github.com/yaoapp/yao/agent/i18n"
 	"github.com/yaoapp/yao/agent/output/message"
 	"github.com/yaoapp/yao/agent/sandbox/v2/types"
 	infra "github.com/yaoapp/yao/sandbox/v2"
@@ -106,6 +107,19 @@ func ExecuteSandboxStream(
 		}
 	}()
 
+	if req.LoadingMsgID != "" {
+		waitMsg := &message.Message{
+			MessageID:   req.LoadingMsgID,
+			Delta:       true,
+			DeltaAction: message.DeltaReplace,
+			Type:        message.TypeLoading,
+			Props: map[string]any{
+				"message": i18n.T(ctx.Locale, "sandbox.waiting_response"),
+			},
+		}
+		ctx.Send(waitMsg)
+	}
+
 	var textContent []byte
 	loadingClosed := false
 	wrappedHandler := func(chunkType message.StreamChunkType, data []byte) int {