create_harness¶
Operation¶
async
¶
create_harness(input: CreateHarnessInput, plugins: list[Plugin] | None = None) -> CreateHarnessOutput
Operation to create a harness.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
input
|
CreateHarnessInput
|
An instance of |
required |
plugins
|
list[Plugin] | None
|
A list of callables that modify the configuration dynamically. Changes made by these plugins only apply for the duration of the operation execution and will not affect any other operation invocations. |
None
|
Returns:
| Type | Description |
|---|---|
CreateHarnessOutput
|
An instance of |
Input¶
dataclass
¶
Dataclass for CreateHarnessInput structure.
Attributes¶
class-attribute
instance-attribute
¶
allowed_tools: list[str] | None = None
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.
class-attribute
instance-attribute
¶
authorizer_configuration: AuthorizerConfiguration | None = None
Represents inbound authorization configuration options used to authenticate incoming requests.
class-attribute
instance-attribute
¶
client_token: str | None = None
A unique, case-sensitive identifier to ensure idempotency of the request.
class-attribute
instance-attribute
¶
environment: HarnessEnvironmentProviderRequest | None = None
The compute environment configuration for the harness, including network and lifecycle settings.
class-attribute
instance-attribute
¶
environment_artifact: HarnessEnvironmentArtifact | None = None
The environment artifact for the harness, such as a custom container image containing additional dependencies.
class-attribute
instance-attribute
¶
environment_variables: dict[str, str] | None = field(repr=False, default=None)
Environment variables to set in the harness runtime environment.
class-attribute
instance-attribute
¶
execution_role_arn: str | None = None
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.
class-attribute
instance-attribute
¶
harness_name: str | None = None
The name of the harness. Must start with a letter and contain only alphanumeric characters and underscores.
class-attribute
instance-attribute
¶
max_iterations: int | None = None
The maximum number of iterations the agent loop can execute per invocation.
class-attribute
instance-attribute
¶
max_tokens: int | None = None
The maximum total number of output tokens the agent can generate across all model calls within a single invocation.
class-attribute
instance-attribute
¶
memory: HarnessMemoryConfiguration | None = None
The AgentCore Memory configuration for persisting conversation context across sessions.
class-attribute
instance-attribute
¶
model: HarnessModelConfiguration | None = None
The model configuration for the harness. Supports Amazon Bedrock, OpenAI, and Google Gemini model providers.
class-attribute
instance-attribute
¶
skills: list[HarnessSkill] | None = None
The skills available to the agent. Skills are bundles of files that the agent can pull into its context on demand.
class-attribute
instance-attribute
¶
system_prompt: list[HarnessSystemContentBlock] | None = None
The system prompt that defines the agent's behavior and instructions.
class-attribute
instance-attribute
¶
tags: dict[str, str] | None = None
Tags to apply to the harness resource.
class-attribute
instance-attribute
¶
timeout_seconds: int | None = None
The maximum duration in seconds for the agent loop execution per invocation.
class-attribute
instance-attribute
¶
tools: list[HarnessTool] | None = None
The tools available to the agent, such as remote MCP servers, AgentCore Gateway, AgentCore Browser, Code Interpreter, or inline functions.
class-attribute
instance-attribute
¶
truncation: HarnessTruncationConfiguration | None = None
The truncation configuration for managing conversation context when it exceeds model limits.