docs: update serverless deployment docs (#248)

Author: Sodawyx

README.md

@@ -421,6 +421,22 @@ agentscope-registry.ap-southeast-1.cr.aliyuncs.com/agentscope/runtime-sandbox-ba
 
 ---
 
+#### Serverless Sandbox Deployment
+
+AgentScope Runtime also supports serverless deployment, which is suitable for running sandboxes in a serverless environment,
+[Alibaba Cloud Function Compute (FC)](https://help.aliyun.com/zh/functioncompute/fc/) or [Alibaba Cloud AgentRun](https://docs.agent.run/).
+
+First, please refer to the [documentation](https://runtime.agentscope.io/en/sandbox/advanced.html#optional-function-compute-fc-settings) to configure the serverless environment variables.
+Make `CONTAINER_DEPLOYMENT` to `fc` or `agentrun` to enable serverless deployment.
+
+Then, start a sandbox server, use the `--config` option to specify a serverless environment setup:
+
+```bash
+# This command will load the settings defined in the `custom.env` file
+runtime-sandbox-server --config fc.env
+```
+After the server starts, you can access the sandbox server at baseurl `http://localhost:8000` and invoke sandbox tools described above.
+
 ## 📚 Cookbook
 
 - **[📖 Cookbook](https://runtime.agentscope.io/en/intro.html)**: Comprehensive tutorials
@@ -471,6 +487,40 @@ response = client.responses.create(
 print(response)
 ```
 
+Besides, `DeployManager` also supports serverless deployments, such as deploying your agent app
+to [ModelStudio](https://bailian.console.aliyun.com/?admin=1&tab=doc#/doc/?type=app&url=2983030)
+or [AgentRun](https://docs.agent.run/).
+
+```python
+from agentscope_runtime.engine.deployers import ModelStudioDeployManager
+# Create deployment manager
+deployer = ModelstudioDeployManager(
+    oss_config=OSSConfig(
+        access_key_id=os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_ID"),
+        access_key_secret=os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_SECRET"),
+    ),
+    modelstudio_config=ModelstudioConfig(
+        workspace_id=os.environ.get("MODELSTUDIO_WORKSPACE_ID"),
+        access_key_id=os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_ID"),
+        access_key_secret=os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_SECRET"),
+        dashscope_api_key=os.environ.get("DASHSCOPE_API_KEY"),
+    ),
+)
+
+# Deploy to ModelStudio
+result = await app.deploy(
+    deployer,
+    deploy_name="agent-app-example",
+    telemetry_enabled=True,
+    requirements=["agentscope", "fastapi", "uvicorn"],
+    environment={
+        "PYTHONPATH": "/app",
+        "DASHSCOPE_API_KEY": os.environ.get("DASHSCOPE_API_KEY"),
+    },
+)
+```
+
+For more advanced serverless deployment guides, please refer to the [documentation](https://runtime.agentscope.io/en/advanced_deployment.html#method-4-modelstudio-deployment).
 
 ---
 

README_zh.md

@@ -422,7 +422,22 @@ export RUNTIME_SANDBOX_IMAGE_TAG="preview"
 agentscope-registry.ap-southeast-1.cr.aliyuncs.com/myteam/runtime-sandbox-base:preview
 ```
 
+---
+
+#### Serverless 沙箱部署
+
+AgentScope Runtime 同样支持 serverless 部署，适用于在无服务器环境中运行沙箱，例如 [阿里云函数计算（FC）](https://help.aliyun.com/zh/functioncompute/fc/)或[阿里云 AgentRun](https://docs.agent.run/)。
+
+首先，请参考[文档](https://runtime.agentscope.io/zh/sandbox/advanced.html#optional-function-compute-fc-settings)配置 serverless 环境变量。
+将 `CONTAINER_DEPLOYMENT` 设置为 `fc` 或 `agentrun` 以启用 serverless 部署。
 
+然后，启动沙箱服务器，使用 `--config` 选项指定 serverless 环境配置：
+
+```bash
+# 此命令将加载 `fc.env` 文件中定义的设置
+runtime-sandbox-server --config fc.env
+```
+服务器启动后，您可以通过URL `http://localhost:8000` 访问沙箱服务器，并调用上述描述的沙箱工具。
 
 ---
 
@@ -477,6 +492,41 @@ response = client.responses.create(
 print(response)
 ```
 
+此外，`DeployManager` 也支持 Serverless 部署，例如将您的 agent 应用部署到
+[ModelStudio](https://bailian.console.aliyun.com/?admin=1&tab=doc#/doc/?type=app&url=2983030)
+或 [AgentRun](https://docs.agent.run/)。
+
+```python
+from agentscope_runtime.engine.deployers import ModelStudioDeployManager
+# 创建部署管理器
+deployer = ModelstudioDeployManager(
+    oss_config=OSSConfig(
+        access_key_id=os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_ID"),
+        access_key_secret=os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_SECRET"),
+    ),
+    modelstudio_config=ModelstudioConfig(
+        workspace_id=os.environ.get("MODELSTUDIO_WORKSPACE_ID"),
+        access_key_id=os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_ID"),
+        access_key_secret=os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_SECRET"),
+        dashscope_api_key=os.environ.get("DASHSCOPE_API_KEY"),
+    ),
+)
+
+# 部署到 ModelStudio
+result = await app.deploy(
+    deployer,
+    deploy_name="agent-app-example",
+    telemetry_enabled=True,
+    requirements=["agentscope", "fastapi", "uvicorn"],
+    environment={
+        "PYTHONPATH": "/app",
+        "DASHSCOPE_API_KEY": os.environ.get("DASHSCOPE_API_KEY"),
+    },
+)
+```
+
+有关更高级的 serverless 部署指南，请参考[文档](https://runtime.agentscope.io/zh/advanced_deployment.html#method-4-modelstudio-deployment)。
+
 ---
 
 ## 🤝 贡献

cookbook/en/advanced_deployment.md

@@ -478,7 +478,7 @@ if __name__ == "__main__":
 - Can be scaled with `kubectl scale deployment`
 
 
-## Method 4: ModelStudio Deployment
+## Method 4: Serverless Deployment: ModelStudio
 
 **Best for**: Alibaba Cloud users requiring managed cloud deployment with built-in monitoring, scaling, and integration with Alibaba Cloud ecosystem.
 
@@ -561,7 +561,7 @@ if __name__ == "__main__":
 - Built-in monitoring and auto-scaling
 - Integrated with DashScope LLM services
 
-## Method 5: AgentRun Deployment
+## Method 5: Serverless Deployment: AgentRun
 
 **Best For**: Alibaba Cloud users who need to deploy agents to AgentRun service with automated build, upload, and deployment workflows.
 

cookbook/en/agent_app.md

@@ -510,3 +510,6 @@ await app.deploy(LocalDeployManager(host="0.0.0.0", port=8091))
 ```
 
 See {doc}`advanced_deployment` for additional deployers (Kubernetes, ModelStudio, AgentRun, etc.) and more configuration tips.
+
+AgentScope Runtime provides serverless deployment options, including deploying agents to ModelStudio(FC) and AgentRun.
+See {doc}`advanced_deployment` for more configuration details about ModelStudio and AgentRun.

cookbook/zh/advanced_deployment.md

@@ -473,7 +473,7 @@ if __name__ == "__main__":
 - 可使用 `kubectl scale deployment` 进行扩展
 
 
-## 方法4：ModelStudio部署
+## 方法4：Serverless部署：ModelStudio
 
 **最适合**：阿里云用户，需要托管云部署，具有内置监控、扩展和与阿里云生态系统集成。
 
@@ -556,7 +556,7 @@ if __name__ == "__main__":
 - 内置监控和自动扩展
 - 与 DashScope LLM 服务集成
 
-## 方法5：AgentRun 部署
+## 方法5：Serverless部署：AgentRun
 
 **最适合**：阿里云用户，需要将智能体部署到 AgentRun 服务，实现自动化的构建、上传和部署流程。
 

cookbook/zh/agent_app.md

@@ -516,3 +516,6 @@ await app.deploy(LocalDeployManager(host="0.0.0.0", port=8091))
 ```
 
 更多部署选项和详细说明，请参考 {doc}`advanced_deployment` 文档。
+
+AgentScope Runtime 提供了Serverless的部署方案，您可以将您的Agent部署到 ModelStudio(FC) 或 AgentRun 上。
+参考 {doc}`advanced_deployment` 文档，查看ModelStudio和AgentRun部署部分获取更多配置详情.

examples/deployments/agentrun_deploy/README.md

@@ -521,3 +521,4 @@ After successful deployment:
 
 This example provides a complete workflow for deploying AgentScope Runtime agents to Alibaba Cloud AgentRun with serverless, production-ready configurations.
 
+