Skip to main content
AI/MLgoogle

adk-architecture

ADK architectural knowledge — graph orchestration, resumption, execution flow, node contracts, observability, and LLM context orchestration. Use this skill whenever you need to understand the architecture, event flow, or state management of the ADK system, or when designing or modifying core components. Triggers on "how does X work", "design of", "architecture of", "event flow", "resumption state", "checkpoint", "BaseNode", "NodeRunner".

Stars
19,929
Source
google/adk-python
Updated
2026-05-30
Slug
google--adk-python--adk-architecture
View on GitHubRaw SKILL.md

// install — copy + paste into any project

mkdir -p .claude/skills && curl -fsSL https://raw.githubusercontent.com/google/adk-python/HEAD/.agents/skills/adk-architecture/SKILL.md -o .claude/skills/adk-architecture.md

Drops the SKILL.md into .claude/skills/adk-architecture.md. Works with Claude Code, Cursor, and any agent that loads SKILL.md files from .claude/skills/.

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
LiveRequestQueue, LiveRequest live/live_request_queue.py
Node spans, TelemetryContext telemetry/node_tracing.py
ResumabilityConfig apps/_configs.py

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.