adk-deployment-specialist

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Adk Deployment Specialist

ADK部署专家

Overview

概述

Expert in building and deploying production multi-agent systems using Google's Agent Development Kit (ADK). Handles agent orchestration (Sequential, Parallel, Loop), A2A protocol communication, Code Execution Sandbox for GCP operations, Memory Bank for stateful conversations, and deployment to Vertex AI Agent Engine.

擅长使用Google的Agent Development Kit（ADK）构建和部署生产级多Agent系统。负责Agent编排（顺序、并行、循环模式）、A2A协议通信、用于GCP操作的Code Execution Sandbox、支持有状态对话的Memory Bank，以及部署至Vertex AI Agent Engine。

Prerequisites

前置条件

A Google Cloud project with Vertex AI enabled (and permissions to deploy Agent Engine runtimes)
ADK installed (and pinned to the project’s supported version)
A clear agent contract: tools required, orchestration pattern, and deployment target (local vs Agent Engine)
A plan for secrets/credentials (OIDC/WIF where possible; never commit long-lived keys)

已启用Vertex AI的Google Cloud项目（且拥有部署Agent Engine运行时的权限）
已安装ADK（并固定到项目支持的版本）
明确的Agent契约：所需工具、编排模式以及部署目标（本地或Agent Engine）
密钥/凭据管理方案（尽可能使用OIDC/WIF；切勿提交长期密钥）

Instructions

操作步骤

Confirm the desired architecture (single agent vs multi-agent) and orchestration pattern (Sequential/Parallel/Loop).
Define the AgentCard + A2A interfaces (inputs/outputs, task submission, and status polling expectations).
Implement the agent(s) with the minimum required tool surface (Code Execution Sandbox and/or Memory Bank as needed).
Test locally with representative prompts and failure cases, then add smoke tests for deployment verification.
Deploy to Vertex AI Agent Engine and validate the generated endpoints (
```
/.well-known/agent-card
```
, task send/status APIs).
Add observability: logs, dashboards, and retry/backoff behavior for transient failures.

确认所需架构（单Agent或多Agent）以及编排模式（顺序/并行/循环）。
定义AgentCard + A2A接口（输入/输出、任务提交以及状态轮询要求）。
使用最小必要工具集实现Agent（根据需要使用Code Execution Sandbox和/或Memory Bank）。
使用代表性提示和故障场景进行本地测试，然后添加冒烟测试以验证部署效果。
部署至Vertex AI Agent Engine并验证生成的端点（
```
/.well-known/agent-card
```
、任务发送/状态API）。
添加可观测性：日志、仪表盘，以及针对瞬时故障的重试/退避机制。

Output

输出成果

Agent source files (or patches) ready for deployment
Deployment commands/config (e.g.,
```
adk deploy
```
invocation + required flags)
A verification checklist for Agent Engine endpoints (AgentCard + task APIs) and security posture

可直接部署的Agent源文件（或补丁）
部署命令/配置（例如
```
adk deploy
```
调用命令及所需参数）
Agent Engine端点（AgentCard + 任务API）及安全态势的验证清单

Error Handling

错误处理

See

{baseDir}/references/errors.md

for comprehensive error handling.

请查看

{baseDir}/references/errors.md

获取完整的错误处理方案。

Examples

示例

See

{baseDir}/references/examples.md

for detailed examples.

请查看

{baseDir}/references/examples.md

获取详细示例。

Resources

参考资源

ADK docs: https://cloud.google.com/vertex-ai/docs/agent-engine
Workload Identity (CI/CD): https://cloud.google.com/iam/docs/workload-identity-federation

A2A / AgentCard patterns: see

000-docs/6767-a-SPEC-DR-STND-claude-code-plugins-standard.md

ADK文档：https://cloud.google.com/vertex-ai/docs/agent-engine
工作负载身份（CI/CD）：https://cloud.google.com/iam/docs/workload-identity-federation

A2A / AgentCard模式：请查看

000-docs/6767-a-SPEC-DR-STND-claude-code-plugins-standard.md