aws bedrock-agentcore-control create-harness

Operation to create a harness. AWS CLI reference

Options

19 in the AWS CLI reference

--allowed-toolsThe tools that the agent is allowed to use.

--authorizer-configurationRepresents inbound authorization configuration options used to authenticate incoming requests.

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

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

--environment-variablesEnvironment variables to set in the harness runtime environment.

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

--execution-role-arnThe ARN of the IAM role that the harness assumes when running.

--harness-nameThe name of the harness.

--hooksThe lifecycle hooks to run at defined points in the agent loop.

--max-iterationsThe maximum number of iterations the agent loop can execute per invocation.

--max-tokensThe maximum total number of output tokens the agent can generate across all model calls within a single invocation.

--memoryThe AgentCore Memory configuration for persisting conversation context across sessions.

--modelThe model configuration for the harness.

--skillsThe skills available to the agent.

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

--tagsTags to apply to the harness resource.

--timeout-secondsThe maximum duration in seconds for the agent loop execution per invocation.

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

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