From adk
Explains ADK Dev Console UI at localhost:3001 during adk dev, including tabs (Chat, Observe), Agent Steps hierarchy, traces, and navigation.
npx claudepluginhub botpress/skills --plugin adkThis skill uses the workspace's default tool permissions.
The Dev Console is a local app served at port `3001` (by default, but can be customized) during `adk dev`. It gives developers real-time visibility into their agent's behavior — conversations, execution traces, data, integrations, and configuration.
Debugs ADK agents by reading traces, analyzing logs, diagnosing common failures like tool errors, workflow issues, and LLM misbehavior, plus guiding the 8-step debug loop.
Guides Claude Agent SDK development in TypeScript/Python: auth, sessions, custom tools, permissions, prompts, tracking via docs-management delegation.
Engineers production-ready ADK agents and multi-agent systems in Python/Java/Go with clean structure, tests, safe tools, and deployment automation.
Share bugs, ideas, or general feedback.
The Dev Console is a local app served at port 3001 (by default, but can be customized) during adk dev. It gives developers real-time visibility into their agent's behavior — conversations, execution traces, data, integrations, and configuration.
Activate when users ask about:
localhost:3001, "dev console", "Dev Console", or specific tab names (Chat, Build, Components, Data, Test, Observe, Config)| File | Contents |
|---|---|
references/agent-steps.md | Agent Steps visualization — turns, iterations, tools, messages, state mutations, cost tracking, status indicators |
references/pages.md | Every page/tab in the Dev Console — what it shows, key features, layout |
Match depth to the question:
| 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 |
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
Status indicators: ✓ green = ok, ✗ red = error, ⟳ blue spinning = running
AI metrics per iteration: model name, input/output tokens, cost (USD)
| Path | Page |
|---|---|
/chat | Chat + Agent Steps |
/actions | Actions browser |
/workflows | Workflows + run history |
/search | RAG search testing |
/evals | Eval definitions + runs |
/knowledge | Knowledge base management |
/tables | Table data management |
/traces | Full trace viewer |
/conversations | Conversation history |
/logs | Runtime logs |
/settings | Agent configuration |
/integrations | Integration management |