adk-dev-console
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseADK Dev Console
ADK Dev Console
The Dev Console is a local app served at port (by default, but can be customized) during . It gives developers real-time visibility into their agent's behavior — conversations, execution traces, data, integrations, and configuration.
3001adk devDev Console是在运行期间，默认在端口（可自定义）提供服务的本地应用。它能让开发者实时查看Agent的行为——对话内容、执行追踪、数据、集成以及配置信息。
adk dev3001When to Use This Skill
何时使用此技能
Activate when users ask about:
- UI concepts — "What are Agent Steps?", "What does the Observe tab show?", "What is a turn?"
- Dev Console navigation — "What tabs are available?", "Where do I find traces?", "How do I test RAG?"
- Reading execution data — "What do the steps mean?", "Why is my step red?", "What's the cost shown?"
- Specific pages — "How do I use the evals page?", "Where do I configure integrations?", "How do I search knowledge?"
- Comparing UI vs CLI — "Should I use the Dev Console or CLI for debugging?"
- Mentions of , "dev console", "Dev Console", or specific tab names (Chat, Build, Components, Data, Test, Observe, Config)
localhost:3001
当用户询问以下内容时启用：
- UI概念——"什么是Agent Steps？"、"Observe标签页展示什么内容？"、"什么是turn？"
- Dev Console导航——"有哪些可用标签页？"、"在哪里查看追踪信息？"、"如何测试RAG？"
- 解读执行数据——"这些步骤是什么意思？"、"为什么我的步骤显示红色？"、"显示的成本是什么？"
- 特定页面——"如何使用evals页面？"、"在哪里配置集成？"、"如何搜索知识库？"
- UI与CLI对比——"调试时应该用Dev Console还是CLI？"
- 提及、"dev console"、"Dev Console"或特定标签页名称（Chat、Build、Components、Data、Test、Observe、Config）
localhost:3001
Available Documentation
可用文档
| File | Contents |
|---|---|
| Agent Steps visualization — turns, iterations, tools, messages, state mutations, cost tracking, status indicators |
| Every page/tab in the Dev Console — what it shows, key features, layout |
| 文件 | 内容 |
|---|---|
| Agent Steps可视化——turns、迭代、工具、消息、状态变更、成本追踪、状态指示器 |
| Dev Console中的每个页面/标签页——展示内容、关键功能、布局 |
How to Answer
回答方式
Match depth to the question:
- "What is X?" (e.g., "What are Agent Steps?") → One sentence definition + what the user sees. Don't dump the full data model.
- "Where do I find X?" → Name the tab group and page, give the URL path.
- "How do I read X?" → Explain the visual hierarchy and what each element means.
- "What does this mean?" (pointing at something in the UI) → Identify the component, explain its meaning.
根据问题的深度匹配回答：
- "X是什么？"（例如："什么是Agent Steps？"）→ 一句话定义+用户能看到的内容。不要罗列完整的数据模型。
- "在哪里找到X？" → 说明标签组和页面名称，给出URL路径。
- "如何解读X？" → 解释视觉层级以及每个元素的含义。
- "这是什么意思？"（指向UI中的某个元素）→ 识别组件，解释其含义。
Quick Reference
快速参考
Tab Groups
标签组
| Group | Pages | Purpose |
|---|---|---|
| Chat | Chat | Test the agent via webchat + see Agent Steps |
| Build | Story | Visual agent flow graph (feature-flagged) |
| Components | Actions, Workflows, Triggers | Browse and test bot primitives |
| Test | RAG Search, Evals | Test knowledge search and run automated evals |
| Data | Knowledge, Tables, Files | Manage knowledge bases, tables, and files |
| Observe | Conversations, Traces, Logs | View conversation history, execution traces, runtime logs |
| Config | Settings, Integrations | Agent config, secrets, LLM settings, integration management |
| 组 | 页面 | 用途 |
|---|---|---|
| Chat | Chat | 通过网页聊天测试Agent + 查看Agent Steps |
| Build | Story | Agent流程可视化图（功能标记控制） |
| Components | Actions、Workflows、Triggers | 浏览并测试机器人基础组件 |
| Test | RAG Search、Evals | 测试知识库搜索并运行自动化评估 |
| Data | Knowledge、Tables、Files | 管理知识库、表格和文件 |
| Observe | Conversations、Traces、Logs | 查看对话历史、执行追踪、运行时日志 |
| Config | Settings、Integrations | Agent配置、密钥、LLM设置、集成管理 |
Agent Steps (Chat Page)
Agent Steps（Chat页面）
The right panel of the Chat page shows Agent Steps — a real-time visualization of what the agent did to process each message.
Hierarchy: Turn → Iterations → Tools / Messages / State Mutations
- Turn = one conversation exchange (user message → agent processing → response)
- Iteration = one loop of the autonomous agent (think → decide → act)
- Tool = a tool call within an iteration (violet card)
- Message = a bot message sent (blue card)
- State Mutation = a state change (teal card, shows before/after)
Status indicators: ✓ green = ok, ✗ red = error, ⟳ blue spinning = running
AI metrics per iteration: model name, input/output tokens, cost (USD)
Chat页面的右侧面板展示Agent Steps——实时可视化Agent处理每条消息的过程。
层级结构： Turn → Iterations → Tools / Messages / State Mutations
- Turn = 一次对话交互（用户消息→Agent处理→回复）
- Iteration = 自主Agent的一次循环（思考→决策→行动）
- Tool = 迭代中的工具调用（紫色卡片）
- Message = 发送的机器人消息（蓝色卡片）
- State Mutation = 状态变更（蓝绿色卡片，显示变更前后状态）
状态指示器： ✓ 绿色=正常，✗ 红色=错误，⟳ 蓝色旋转=运行中
每轮迭代的AI指标： 模型名称、输入/输出token数量、成本（美元）
Key URLs
关键URL
| Path | Page |
|---|---|
| Chat + Agent Steps |
| Actions browser |
| Workflows + run history |
| RAG search testing |
| Eval definitions + runs |
| Knowledge base management |
| Table data management |
| Full trace viewer |
| Conversation history |
| Runtime logs |
| Agent configuration |
| Integration management |
| 路径 | 页面 |
|---|---|
| Chat + Agent Steps |
| Actions浏览器 |
| Workflows + 运行历史 |
| RAG搜索测试 |
| 评估定义 + 运行记录 |
| 知识库管理 |
| 表格数据管理 |
| 完整追踪查看器 |
| 对话历史 |
| 运行时日志 |
| Agent配置 |
| 集成管理 |