AbstractReadonly[Brand identifying this object as a BaseNode (see isBaseNode).
ReadonlydescriptionOptional ReadonlyinputOptional ReadonlyisolationReadonlynameOptional ReadonlyoutputOptional ReadonlypreparedThe retry config with its exception filter normalized once, up front (see prepareRetryConfig). Used by the node runner so the retry hot path never re-normalizes or throws on a malformed config mid-retry.
ReadonlyrerunOptional ReadonlyretryOptional ReadonlystateOptional ReadonlytimeoutReadonlywaitWhether this node must wait for ALL of its predecessors to trigger before
it runs (fan-in barrier). Overridden by JoinNode.
Runs the node, normalizing every yielded item into an Event. This
is what the engine (and ctx.runNode()) consumes. Validates the input
against inputSchema once, up front (skipping genai Content, which nodes
coerce themselves).
ProtectedrunCore execution contract. Subclasses yield one of:
output is that value),null/undefined (skipped).Protected AbstractrunImplement node execution logic here. May yield Events, raw values, or
null (normalized by BaseNode.run).
ProtectedtoNormalizes a single yielded item into an Event (or null to skip).
Subclasses may override for richer coercion (e.g. FunctionNode).
ProtectedvalidateProtectedvalidateValidates node output against outputSchema (Content passes through). Only
enforced for Zod schemas; a genai Schema is left unvalidated (see
parseWithSchema).
A base class designed for subclassing. Implement runNodeImpl to provide node logic; subclasses inherit the schema/retry/timeout machinery of BaseNode.
Named
WorkflowNode(notNode) to read consistently withWorkflowandWorkflowConfig, and to avoid shadowing the DOM /@types/nodeNodeglobal in the flat@google/adknamespace. Thenode()factory remains the ergonomic way to wrap a function/tool/agent.Mirrors
google/adk-pythonworkflow/_node.py::Node. Theparallel_workercapability is added in Phase 6.