createHarness method

Future<CreateHarnessResponse> createHarness({ required String executionRoleArn, required String harnessName, List<String>? allowedTools, AuthorizerConfiguration? authorizerConfiguration, String? clientToken, HarnessEnvironmentProviderRequest? environment, HarnessEnvironmentArtifact? environmentArtifact, Map<String, String>? environmentVariables, int? maxIterations, int? maxTokens, HarnessMemoryConfiguration? memory, HarnessModelConfiguration? model, List<HarnessSkill>? skills, List<HarnessSystemContentBlock>? systemPrompt, Map<String, String>? tags, int? timeoutSeconds, List<HarnessTool>? tools, HarnessTruncationConfiguration? truncation, })

Operation to create a Harness.

May throw AccessDeniedException. May throw ConflictException. May throw InternalServerException. May throw ServiceQuotaExceededException. May throw ThrottlingException. May throw ValidationException.

Parameter executionRoleArn : 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.

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

Parameter allowedTools : 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.

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

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

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

Parameter environmentVariables : Environment variables to set in the harness runtime environment.

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

Parameter maxTokens : The maximum total number of output tokens the agent can generate across all model calls within a single invocation.

Parameter memory : The AgentCore Memory configuration for persisting conversation context across sessions.

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

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

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

Parameter tags : Tags to apply to the harness resource.

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

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

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

Implementation

Future<CreateHarnessResponse> createHarness({
  required String executionRoleArn,
  required String harnessName,
  List<String>? allowedTools,
  AuthorizerConfiguration? authorizerConfiguration,
  String? clientToken,
  HarnessEnvironmentProviderRequest? environment,
  HarnessEnvironmentArtifact? environmentArtifact,
  Map<String, String>? environmentVariables,
  int? maxIterations,
  int? maxTokens,
  HarnessMemoryConfiguration? memory,
  HarnessModelConfiguration? model,
  List<HarnessSkill>? skills,
  List<HarnessSystemContentBlock>? systemPrompt,
  Map<String, String>? tags,
  int? timeoutSeconds,
  List<HarnessTool>? tools,
  HarnessTruncationConfiguration? truncation,
}) async {
  final $payload = <String, dynamic>{
    'executionRoleArn': executionRoleArn,
    'harnessName': harnessName,
    if (allowedTools != null) 'allowedTools': allowedTools,
    if (authorizerConfiguration != null)
      'authorizerConfiguration': authorizerConfiguration,
    'clientToken': clientToken ?? _s.generateIdempotencyToken(),
    if (environment != null) 'environment': environment,
    if (environmentArtifact != null)
      'environmentArtifact': environmentArtifact,
    if (environmentVariables != null)
      'environmentVariables': environmentVariables,
    if (maxIterations != null) 'maxIterations': maxIterations,
    if (maxTokens != null) 'maxTokens': maxTokens,
    if (memory != null) 'memory': memory,
    if (model != null) 'model': model,
    if (skills != null) 'skills': skills,
    if (systemPrompt != null) 'systemPrompt': systemPrompt,
    if (tags != null) 'tags': tags,
    if (timeoutSeconds != null) 'timeoutSeconds': timeoutSeconds,
    if (tools != null) 'tools': tools,
    if (truncation != null) 'truncation': truncation,
  };
  final response = await _protocol.send(
    payload: $payload,
    method: 'POST',
    requestUri: '/harnesses',
    exceptionFnMap: _exceptionFns,
  );
  return CreateHarnessResponse.fromJson(response);
}