google/adk-python

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…

Quelltext ansehen

Verwendung

  1. Installationsbefehl kopieren und das Quellpaket vor der Installation in der eigenen Agentenumgebung prüfen.
  2. Benötigte Werkzeuge, Zugangsdaten und Hosts im Original prüfen.
  3. Eingabe und gewünschtes Ergebnis beschreiben und die Ausgabe mit den Quellen abgleichen.
npx skills add https://github.com/google/adk-python --skill adk-agent-builder

Vor dem Start

  • Die Installation umfasst weder Modellabo noch API-Kontingent oder Dateizugriffsrechte.
  • Sterne und Installationen zeigen Aktivität, keine unabhängige Qualitäts- oder Sicherheitsprüfung.
Originales Skill-Dokument

Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.

ADK Agent Builder

Read only the reference that matches the task. Loading the whole tree costs context and buries the part that matters.

Every API below was checked against google-adk 2.6.2. If a symbol is missing at runtime, read the source under src/google/adk/ rather than guessing a neighbouring name.

Start here

TaskReference
First agent, environment, adk CLIgetting-started.md
Which import path is the canonical oneimport-paths.md
The rules that cause most runtime failuresbest-practices.md

Building blocks

Google API toolsets, built-in tools, custom BaseTool and BaseToolset.

parameter resolution, generators, node_input typing rules.

workflow node: output types, instruction templates, output_schema, auto-wrapping behavior.

mode='single_turn' delegation with schema-validated input and output.

Graph orchestration

edges, dict routing maps, default routes, self-loops, revision loops.

JoinNode fan-in, parallel_worker=True list processing.

with ctx.run_node() and imperative workflow construction.

resume behavior, resumable vs replayed sessions.

retries, custom BaseNode subclasses, graph validation rules.

the deprecated SequentialAgent / LoopAgent / ParallelAgent shells that Workflow replaces.

Runtime and verification

Event fields, and how state flows between nodes.

artifacts, memory, and state key scoping.

agent callbacks and app-level plugins.

  • testing.md — pytest with InMemoryRunner, faking a

model, asserting on node output.