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).
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-11
- Stars
- ★ 2.2w
- Forks
- 4.3k
01 前言 Front Matter
- name
- adk-architecture
- description
- 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).
02 资源文件 14
- 参考文档references/api-principles.md2.7 KB
- 参考文档references/architecture-checkpoint-resume.md2.6 KB
- 参考文档references/architecture-context.md4.2 KB
- 参考文档references/architecture-llm-context-orchestration.md1.9 KB
- 参考文档references/architecture-node-runner.md6.0 KB
- 参考文档references/architecture-observability.md4.0 KB
- 参考文档references/architecture-runner-roles.md452 B
- 参考文档references/architecture-workflow-resumability.md7.7 KB
- 参考文档references/interface-agent.md2.0 KB
- 参考文档references/interface-base-agent.md2.0 KB
- 参考文档references/interface-base-node.md4.9 KB
- 参考文档references/interface-event.md3.2 KB
- 参考文档references/interface-runner.md3.0 KB
- 参考文档references/interface-workflow.md21.1 KB
03 SKILL.md 正文
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, DynamicNodeState, DynamicNodeRun |
workflow/_dynamic_node_scheduler.py |
ReplayManager (resume scan) |
workflow/utils/_replay_manager.py |
check_interception (replay fast-forward) |
workflow/utils/_replay_interceptor.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 |
BaseLlmFlow, SingleFlow, AutoFlow, flows/llm_flows/ subpackages (context/, prompt/, tools/, extensions/, core/) |
flows/llm_flows/ |
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.
04 同仓库更多 Skills
bigquery-graph
Skill for Graph Query Language (GQL) or SQL/PGQ queries against a property graph. Includes path finding, multi-hop traversal, topological connection, shortest path, node reachability, edge connectivity, and semantic graph queries.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity, summarize content, translate language, evaluate models, filter by semantic conditions, measure the causal effect of an intervention, compute correlations between columns, detect change points or structural breaks, extract trend or seasonality components, or leverage generative AI capabilities in BigQuery. Do not use for general BigQuery dataset, table, or job management requests.
code-review-skill
Reviews code with feedback tailored to the developer's profile in session state.
weather-skill
A skill that provides weather information based on reference data.
weather-skill
A skill that provides weather information based on reference data and scripts.
weather-skill
A skill that provides weather information based on reference data.