CreateHarnessRequest

Types

Link copied to clipboard
class Builder
Link copied to clipboard
object Companion

Properties

Link copied to clipboard

The tools that the agent is allowed to use. Supports glob patterns such as * for all tools, @builtin for all built-in tools, or @serverName/toolName for specific MCP server tools.

Link copied to clipboard

Represents inbound authorization configuration options used to authenticate incoming requests.

Link copied to clipboard

A unique, case-sensitive identifier to ensure idempotency of the request.

Link copied to clipboard

The compute environment configuration for the harness, including network and lifecycle settings.

Link copied to clipboard

The environment artifact for the harness, such as a custom container image containing additional dependencies.

Link copied to clipboard

Environment variables to set in the harness runtime environment.

Link copied to clipboard

The ARN of the IAM role that the harness assumes when running. This role must have permissions for the services the agent needs to access, such as Amazon Bedrock for model invocation.

Link copied to clipboard

The name of the harness. Must start with a letter and contain only alphanumeric characters and underscores.

Link copied to clipboard

The maximum number of iterations the agent loop can execute per invocation.

Link copied to clipboard

The maximum number of tokens the agent can generate per iteration.

Link copied to clipboard

The AgentCore Memory configuration for persisting conversation context across sessions.

Link copied to clipboard

The model configuration for the harness. Supports Amazon Bedrock, OpenAI, and Google Gemini model providers.

Link copied to clipboard

The skills available to the agent. Skills are bundles of files that the agent can pull into its context on demand.

Link copied to clipboard

The system prompt that defines the agent's behavior and instructions.

Link copied to clipboard

Tags to apply to the harness resource.

Link copied to clipboard

The maximum duration in seconds for the agent loop execution per invocation.

Link copied to clipboard

The tools available to the agent, such as remote MCP servers, AgentCore Gateway, AgentCore Browser, Code Interpreter, or inline functions.

Link copied to clipboard

The truncation configuration for managing conversation context when it exceeds model limits.

Functions

Link copied to clipboard
Link copied to clipboard
open operator override fun equals(other: Any?): Boolean
Link copied to clipboard
open override fun hashCode(): Int
Link copied to clipboard
open override fun toString(): String