adk-architecture

Explains how the ADK runtime fits together: the node and graph execution model, Context and Event flow, checkpoint and resume, tracing, and the rules governing the public API surface. Use when answering "how does X work" about ADK internals, tracing where an event or a piece of state comes from, deciding where a new capability belongs, reviewing a change to BaseNode, Workflow, Runner, Agent, Event or Context, working out why a node re-ran or stayed waiting after a resume, or judging whether a change breaks the public API. Don't use for assembling an agent from existing pieces (use adk-agent-builder), diagnosing one failing run or test (use adk-debug), or formatting and naming conventions (use adk-style).

Jump to install

Repository: google/adk-python
Last source activity: August 13, 2026 at 00:03
Detected SKILL.md language: English
Stars: 21,148
Forks: 3,843

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/google/adk-python --skill adk-architecture

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

15 files

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

adk-sample-creator

Creates a new sample agent in the ADK Python repository — the sample directory, its `agent.py`, and its `README.md` — following the conventions the existing samples already use. Use when the user wants to add a sample or example demonstrating a feature or agent pattern (dynamic nodes, fan-out/fan-in, a standalone tool-using agent), asks where a new sample belongs under `contributing/samples/`, or wants an existing sample's README brought up to the standard structure. Don't use for building a real working agent for the user's own project (use `adk-agent-builder`), or for checking whether the Python blocks in a Markdown file run (use `adk-verify-snippets`).

2026-08-14

adk-agent-builder

Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between agents, human-in-the-loop pauses, and pytest coverage for all of it. Use when asked to create an agent or a workflow, add a tool to one, branch or loop between nodes, run steps in parallel, pause for user approval, or test an agent. Don't use for explaining how ADK works internally or designing its core components (use `adk-architecture`), for an agent that already runs but misbehaves (use `adk-debug`), for authoring a sample under `contributing/` (use `adk-sample-creator`), or for naming, typing, and formatting conventions (use `adk-style`).

2026-08-13

adk-debug

Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model. Covers the `adk run` CLI and the `adk web` dev server with its session, trace, and debug HTTP endpoints. Use when an agent returns the wrong answer, ignores a tool or swallows a tool error, hangs, loops, emits raw JSON instead of calling tools, is not discovered by `adk web`, when a sub-agent cannot see the parent conversation, or when you need the LLM request/response, token counts, or logs for a run. Don't use for how ADK is designed internally (use `adk-architecture`), for building a new agent or workflow (use `adk-agent-builder`), for environment or dependency setup failures (use `adk-setup`), or for lint and style nits (use `adk-style`).

2026-08-13

View all from this repository

ADK Architecture

The runtime is a graph of nodes. BaseNode is the unit of execution. Workflow is a node that schedules other nodes along declared edges. NodeRunner executes exactly one node. Runner owns the invocation and the session. Agents are nodes too — BaseAgent extends BaseNode.

A node communicates with its parent through a per-execution Context, and with the session through Events it yields. Those are two separate channels: ctx carries the result upward, events carry persistence and streaming.

Read the source before relying on any signature here. These notes drift; the code does not. Paths below are relative to src/google/adk/.

Pick a reference

Question

Reference

What must a node implement? What may it yield? Which config fields exist?

BaseNode

How does the graph schedule nodes, dedup dynamic children, propagate interrupts?

Workflow

How does a caller start an invocation?

Runner

What is Agent, and which methods do I call on it?

Agent

I am subclassing an agent — what do I override?

BaseAgent

What is on an Event, and what may I assume about its lifetime?

Event

What does a node read and write on ctx?

Context

Who creates the child Context, stamps events, retries, catches errors?

NodeRunner

Why are Runner, NodeRunner and Workflow three separate things?

Runner roles

How does a human-in-the-loop pause and resume work for one node?

Checkpoint and resume

How does a whole workflow survive a pause, and what does is_resumable change?

Workflow resumability

How are spans created, and what attributes do they carry?

Observability

Why does the model not see the raw event log?

LLM context orchestration

Is this change a breaking change? Where does a new export belong?

API principles

Where the code lives

Concept

Module

BaseNode, START

workflow/_base_node.py

Workflow, _LoopState

workflow/_workflow.py

Graph, edge compilation

workflow/_graph.py

NodeRunner

workflow/_node_runner.py

DynamicNodeScheduler

workflow/_dynamic_node_scheduler.py

ReplayManager (resume scan)

workflow/utils/_replay_manager.py

NodeInterruptedError, NodeTimeoutError

workflow/_errors.py

Context, ctx.run_node()

agents/context.py

ReadonlyContext

agents/readonly_context.py

InvocationContext

agents/invocation_context.py

BaseAgent, LlmAgent (aliased Agent)

agents/base_agent.py, agents/llm_agent.py

Event, NodeInfo

events/event.py

EventActions

events/event_actions.py

Branch paths (parent.child@1)

events/_branch_path.py

Node paths (wf@1/child@2)

events/_node_path_builder.py

Runner, InMemoryRunner

runners.py

Node spans, TelemetryContext

Everything under workflow/ is a leading-underscore module. Treat those names as internal — they can change without a major version bump, so a change there is not automatically a breaking change.