Files

T

Shangjie Chen 199d954815 feat: expose max_parallel_workers parameter on workflow.node decorator and Node class

Expose `max_parallel_workers` on the `@workflow.node` decorator and `Node` class when `parallel_worker=True`. This allows throttling the concurrency limit when executing parallel workers.

Co-authored-by: Shangjie Chen <deanchen@google.com>
PiperOrigin-RevId: 940663519

2026-06-30 14:34:30 -07:00

agents/llm_agent

docs: add unit guides for task mode

2026-06-12 16:19:07 -07:00

events

docs: add unit guides for event.py, request_input.py and update adk-unit-guide skill

2026-06-12 14:55:34 -07:00

workflow

feat: expose max_parallel_workers parameter on workflow.node decorator and Node class

2026-06-30 14:34:30 -07:00

README.md

docs(workflow): Add and update workflow developer guides

2026-06-17 16:15:57 -07:00

README.md

ADK Developer Guides

This directory contains specific developer guides for the ADK Python implementation. For the official ADK documentation, visit adk.dev.

Index

Agents

LlmAgent Single-Turn Mode - Guide on using LlmAgent in single-turn mode.
LlmAgent Task Mode - Guide on using LlmAgent in task mode.

Events

Event and NodeInfo - Understanding Event and NodeInfo in workflows.
RequestInput - How to use RequestInput for human-in-the-loop interactions.

Workflows

Workflow - Graph-based orchestration of complex, multi-step agent interactions.
Workflow Graphs - Understanding nodes, edges, and graph structures in workflows.
Function Nodes - Wrapping Python functions and generators as workflow nodes.
JoinNode - Synchronizing parallel execution paths in workflows.
RetryConfig - Configuring retry policies for resilient workflow nodes.
ParallelWorker - Processing lists of items concurrently in workflows.
Dynamic Nodes - Scheduling and executing nodes dynamically at runtime.