Struct CodeActAgent 

pub struct CodeActAgent { /* private fields */ }

Available on crate features agents and codeact only.

A configured CodeAct agent.

Build one with CodeActAgent::builder, supplying a Llm and a CodeRuntime. The agent then drives the CodeAct loop: each turn the model writes one script, tools are exposed as callable functions, and the script returns a tagged ScriptOutput.

Example

use std::sync::Arc;
use adk_agent::codeact::CodeActAgent;

// `model` implements `adk_core::Llm`; `runtime` implements `CodeRuntime`
// (e.g. a Monty-backed Python interpreter).
let agent = CodeActAgent::builder()
    .name("analyst")
    .model(model)
    .runtime(runtime)
    .instruction("Prefer pandas-style transformations.")
    .tool(Arc::new(load_csv_tool))
    .output_key("report")
    .build()?;

Implementations

impl CodeActAgent

pub fn builder() -> CodeActAgentBuilder

Start building a CodeActAgent.

pub fn input_schema(&self) -> Option<&Value>

The JSON schema describing this agent’s input, if set.

Like LlmAgent, this is descriptive metadata (e.g. for exposing the agent as a tool); it is not enforced on the incoming user message.

Trait Implementations

impl Agent for CodeActAgent

fn name(&self) -> &str

Returns the unique name of this agent.

fn description(&self) -> &str

Returns a human-readable description of this agent’s purpose.

fn sub_agents(&self) -> &[Arc<dyn Agent>]

Returns the child agents managed by this agent.

fn capabilities(&self) -> AgentCapabilities

Declares the execution-plane capabilities this agent supports.

fn run<'life0, 'async_trait>( &'life0 self, ctx: Arc<dyn InvocationContext>, ) -> Pin<Box<dyn Future<Output = Result<Pin<Box<dyn Stream<Item = Result<Event, AdkError>> + Send>>, AdkError>> + Send + 'async_trait>>

where 'life0: 'async_trait, CodeActAgent: 'async_trait,

Executes the agent and returns a stream of events.

fn interaction_mode(&self) -> AgentInteractionMode

Returns the agent’s primary interaction pattern.

fn supports_agent_transfer(&self) -> bool

Whether this agent participates in LLM-driven agent transfer and may be resumed directly across conversation turns.

fn topology(&self) -> Option<AgentTopology>

Returns portable composition metadata when this agent owns an explicit topology.

fn configure_run(&self, _agent_name: &str, _config: &mut RunConfig)

Applies agent-composition policy to a run before the runtime creates the invocation context for agent_name.

fn transfer_targets_for(&self, _agent_name: &str) -> Option<Vec<String>>

Returns the exact handoff targets allowed for agent_name, when this agent owns an explicit transfer topology.

fn strict_transfer_policy(&self) -> bool

Whether transfer-policy violations should fail the run.

fn govern_transfer<'life0, 'life1, 'async_trait>( &'life0 self, _request: &'life1 AgentTransferRequest, ) -> Pin<Box<dyn Future<Output = Result<AgentTransferDecision, AdkError>> + Send + 'async_trait>>

where 'life0: 'async_trait, 'life1: 'async_trait, Self: 'async_trait,

Applies asynchronous policy to an otherwise valid transfer.

impl Debug for CodeActAgent

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.