Class: Aws::BedrockAgentCore::Client

Inherits:
Seahorse::Client::Base show all
Includes:
ClientStubs
Defined in:
gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb

Overview

An API client for BedrockAgentCore. To construct a client, you need to configure a :region and :credentials.

client = Aws::BedrockAgentCore::Client.new(
  region: region_name,
  credentials: credentials,
  # ...
)

For details on configuring region and credentials see the developer guide.

See #initialize for a full list of supported configuration options.

Instance Attribute Summary

Attributes inherited from Seahorse::Client::Base

#config, #handlers

API Operations collapse

Instance Method Summary collapse

Methods included from ClientStubs

#api_requests, #stub_data, #stub_responses

Methods inherited from Seahorse::Client::Base

add_plugin, api, clear_plugins, define, new, #operation_names, plugins, remove_plugin, set_api, set_plugins

Methods included from Seahorse::Client::HandlerBuilder

#handle, #handle_request, #handle_response

Constructor Details

#initialize(options) ⇒ Client

Returns a new instance of Client.

Parameters:

  • options (Hash)

Options Hash (options):

  • :plugins (Array<Seahorse::Client::Plugin>) — default: []] —

    A list of plugins to apply to the client. Each plugin is either a class name or an instance of a plugin class.

  • :credentials (required, Aws::CredentialProvider) —

    Your AWS credentials used for authentication. This can be any class that includes and implements Aws::CredentialProvider, or instance of any one of the following classes:

    • Aws::Credentials - Used for configuring static, non-refreshing credentials.

    • Aws::SharedCredentials - Used for loading static credentials from a shared file, such as ~/.aws/config.

    • Aws::AssumeRoleCredentials - Used when you need to assume a role.

    • Aws::AssumeRoleWebIdentityCredentials - Used when you need to assume a role after providing credentials via the web.

    • Aws::SSOCredentials - Used for loading credentials from AWS SSO using an access token generated from aws login.

    • Aws::ProcessCredentials - Used for loading credentials from a process that outputs to stdout.

    • Aws::InstanceProfileCredentials - Used for loading credentials from an EC2 IMDS on an EC2 instance.

    • Aws::ECSCredentials - Used for loading credentials from instances running in ECS.

    • Aws::CognitoIdentityCredentials - Used for loading credentials from the Cognito Identity service.

    When :credentials are not configured directly, the following locations will be searched for credentials:

    • Aws.config[:credentials]

    • The :access_key_id, :secret_access_key, :session_token, and :account_id options.

    • ENV['AWS_ACCESS_KEY_ID'], ENV['AWS_SECRET_ACCESS_KEY'], ENV['AWS_SESSION_TOKEN'], and ENV['AWS_ACCOUNT_ID'].

    • ~/.aws/credentials

    • ~/.aws/config

    • EC2/ECS IMDS instance profile - When used by default, the timeouts are very aggressive. Construct and pass an instance of Aws::InstanceProfileCredentials or Aws::ECSCredentials to enable retries and extended timeouts. Instance profile credential fetching can be disabled by setting ENV['AWS_EC2_METADATA_DISABLED'] to true.

  • :region (required, String) —

    The AWS region to connect to. The configured :region is used to determine the service :endpoint. When not passed, a default :region is searched for in the following locations:

    • Aws.config[:region]
    • ENV['AWS_REGION']
    • ENV['AMAZON_REGION']
    • ENV['AWS_DEFAULT_REGION']
    • ~/.aws/credentials
    • ~/.aws/config
  • :access_key_id (String)
  • :account_id (String)
  • :active_endpoint_cache (Boolean) — default: false —

    When set to true, a thread polling for endpoints will be running in the background every 60 secs (default). Defaults to false.

  • :adaptive_retry_wait_to_fill (Boolean) — default: true —

    Used only in adaptive retry mode. When true, the request will sleep until there is sufficent client side capacity to retry the request. When false, the request will raise a RetryCapacityNotAvailableError and will not retry instead of sleeping.

  • :auth_scheme_preference (Array<String>) —

    A list of preferred authentication schemes to use when making a request. Supported values are: sigv4, sigv4a, httpBearerAuth, and noAuth. When set using ENV['AWS_AUTH_SCHEME_PREFERENCE'] or in shared config as auth_scheme_preference, the value should be a comma-separated list.

  • :client_side_monitoring (Boolean) — default: false —

    When true, client-side metrics will be collected for all API requests from this client.

  • :client_side_monitoring_client_id (String) — default: "" —

    Allows you to provide an identifier for this client which will be attached to all generated client side metrics. Defaults to an empty string.

  • :client_side_monitoring_host (String) — default: "127.0.0.1" —

    Allows you to specify the DNS hostname or IPv4 or IPv6 address that the client side monitoring agent is running on, where client metrics will be published via UDP.

  • :client_side_monitoring_port (Integer) — default: 31000 —

    Required for publishing client metrics. The port that the client side monitoring agent is running on, where client metrics will be published via UDP.

  • :client_side_monitoring_publisher (Aws::ClientSideMonitoring::Publisher) — default: Aws::ClientSideMonitoring::Publisher —

    Allows you to provide a custom client-side monitoring publisher class. By default, will use the Client Side Monitoring Agent Publisher.

  • :convert_params (Boolean) — default: true —

    When true, an attempt is made to coerce request parameters into the required types.

  • :correct_clock_skew (Boolean) — default: true —

    Used only in standard and adaptive retry modes. Specifies whether to apply a clock skew correction and retry requests with skewed client clocks.

  • :defaults_mode (String) — default: "legacy" —

    See DefaultsModeConfiguration for a list of the accepted modes and the configuration defaults that are included.

  • :disable_host_prefix_injection (Boolean) — default: false —

    When true, the SDK will not prepend the modeled host prefix to the endpoint.

  • :disable_request_compression (Boolean) — default: false —

    When set to 'true' the request body will not be compressed for supported operations.

  • :endpoint (String, URI::HTTPS, URI::HTTP) —

    Normally you should not configure the :endpoint option directly. This is normally constructed from the :region option. Configuring :endpoint is normally reserved for connecting to test or custom endpoints. The endpoint should be a URI formatted like:

    'http://example.com'
'https://example.com'
'http://example.com:123'
  • :endpoint_cache_max_entries (Integer) — default: 1000 —

    Used for the maximum size limit of the LRU cache storing endpoints data for endpoint discovery enabled operations. Defaults to 1000.

  • :endpoint_cache_max_threads (Integer) — default: 10 —

    Used for the maximum threads in use for polling endpoints to be cached, defaults to 10.

  • :endpoint_cache_poll_interval (Integer) — default: 60 —

    When :endpoint_discovery and :active_endpoint_cache is enabled, Use this option to config the time interval in seconds for making requests fetching endpoints information. Defaults to 60 sec.

  • :endpoint_discovery (Boolean) — default: false —

    When set to true, endpoint discovery will be enabled for operations when available.

  • :event_stream_handler (Proc) —

    When an EventStream or Proc object is provided, it will be used as callback for each chunk of event stream response received along the way.

  • :ignore_configured_endpoint_urls (Boolean) —

    Setting to true disables use of endpoint URLs provided via environment variables and the shared configuration file.

  • :input_event_stream_handler (Proc) —

    When an EventStream or Proc object is provided, it can be used for sending events for the event stream.

  • :log_formatter (Aws::Log::Formatter) — default: Aws::Log::Formatter.default —

    The log formatter.

  • :log_level (Symbol) — default: :info —

    The log level to send messages to the :logger at.

  • :logger (Logger) —

    The Logger instance to send log messages to. If this option is not set, logging will be disabled.

  • :max_attempts (Integer) — default: 3 —

    An integer representing the maximum number attempts that will be made for a single request, including the initial attempt. For example, setting this value to 5 will result in a request being retried up to 4 times. Used in standard and adaptive retry modes.

  • :output_event_stream_handler (Proc) —

    When an EventStream or Proc object is provided, it will be used as callback for each chunk of event stream response received along the way.

  • :profile (String) — default: "default" —

    Used when loading credentials from the shared credentials file at HOME/.aws/credentials. When not specified, 'default' is used.

  • :request_checksum_calculation (String) — default: "when_supported" —

    Determines when a checksum will be calculated for request payloads. Values are:

    • when_supported - (default) When set, a checksum will be calculated for all request payloads of operations modeled with the httpChecksum trait where requestChecksumRequired is true and/or a requestAlgorithmMember is modeled.
    • when_required - When set, a checksum will only be calculated for request payloads of operations modeled with the httpChecksum trait where requestChecksumRequired is true or where a requestAlgorithmMember is modeled and supplied.
  • :request_min_compression_size_bytes (Integer) — default: 10240 —

    The minimum size in bytes that triggers compression for request bodies. The value must be non-negative integer value between 0 and 10485780 bytes inclusive.

  • :response_checksum_validation (String) — default: "when_supported" —

    Determines when checksum validation will be performed on response payloads. Values are:

    • when_supported - (default) When set, checksum validation is performed on all response payloads of operations modeled with the httpChecksum trait where responseAlgorithms is modeled, except when no modeled checksum algorithms are supported.
    • when_required - When set, checksum validation is not performed on response payloads of operations unless the checksum algorithm is supported and the requestValidationModeMember member is set to ENABLED.
  • :retry_backoff (Proc) —

    A proc or lambda used for backoff. Defaults to 2**retries * retry_base_delay. This option is only used in the legacy retry mode.

  • :retry_base_delay (Float) — default: 0.3 —

    The base delay in seconds used by the default backoff function. This option is only used in the legacy retry mode.

  • :retry_jitter (Symbol) — default: :none —

    A delay randomiser function used by the default backoff function. Some predefined functions can be referenced by name - :none, :equal, :full, otherwise a Proc that takes and returns a number. This option is only used in the legacy retry mode.

    @see https://www.awsarchitectureblog.com/2015/03/backoff.html

  • :retry_limit (Integer) — default: 3 —

    The maximum number of times to retry failed requests. Only ~ 500 level server errors and certain ~ 400 level client errors are retried. Generally, these are throttling errors, data checksum errors, networking errors, timeout errors, auth errors, endpoint discovery, and errors from expired credentials. This option is only used in the legacy retry mode.

  • :retry_max_delay (Integer) — default: 0 —

    The maximum number of seconds to delay between retries (0 for no limit) used by the default backoff function. This option is only used in the legacy retry mode.

  • :retry_mode (String) — default: "legacy" —

    Specifies which retry algorithm to use. Values are:

    • legacy - The pre-existing retry behavior. This is the default value if no retry mode is provided.

    • standard - A standardized set of retry rules across the AWS SDKs. This includes support for retry quotas, which limit the number of unsuccessful retries a client can make.

    • adaptive - A retry mode that includes all the functionality of standard mode along with automatic client side throttling.

  • :sdk_ua_app_id (String) —

    A unique and opaque application ID that is appended to the User-Agent header as app/sdk_ua_app_id. It should have a maximum length of 50. This variable is sourced from environment variable AWS_SDK_UA_APP_ID or the shared config profile attribute sdk_ua_app_id.

  • :secret_access_key (String)
  • :session_token (String)
  • :sigv4a_signing_region_set (Array) —

    A list of regions that should be signed with SigV4a signing. When not passed, a default :sigv4a_signing_region_set is searched for in the following locations:

    • Aws.config[:sigv4a_signing_region_set]
    • ENV['AWS_SIGV4A_SIGNING_REGION_SET']
    • ~/.aws/config
  • :stub_responses (Boolean) — default: false —

    Causes the client to return stubbed responses. By default fake responses are generated and returned. You can specify the response data to return or errors to raise by calling ClientStubs#stub_responses. See ClientStubs for more information.

    Please note When response stubbing is enabled, no HTTP requests are made, and retries are disabled.

  • :telemetry_provider (Aws::Telemetry::TelemetryProviderBase) — default: Aws::Telemetry::NoOpTelemetryProvider —

    Allows you to provide a telemetry provider, which is used to emit telemetry data. By default, uses NoOpTelemetryProvider which will not record or emit any telemetry data. The SDK supports the following telemetry providers:

    • OpenTelemetry (OTel) - To use the OTel provider, install and require the opentelemetry-sdk gem and then, pass in an instance of a Aws::Telemetry::OTelProvider for telemetry provider.
  • :token_provider (Aws::TokenProvider) —

    Your Bearer token used for authentication. This can be any class that includes and implements Aws::TokenProvider, or instance of any one of the following classes:

    • Aws::StaticTokenProvider - Used for configuring static, non-refreshing tokens.

    • Aws::SSOTokenProvider - Used for loading tokens from AWS SSO using an access token generated from aws login.

    When :token_provider is not configured directly, the Aws::TokenProviderChain will be used to search for tokens configured for your profile in shared configuration files.

  • :use_dualstack_endpoint (Boolean) —

    When set to true, dualstack enabled endpoints (with .aws TLD) will be used if available.

  • :use_fips_endpoint (Boolean) —

    When set to true, fips compatible endpoints will be used if available. When a fips region is used, the region is normalized and this config is set to true.

  • :validate_params (Boolean) — default: true —

    When true, request parameters are validated before sending the request.

  • :endpoint_provider (Aws::BedrockAgentCore::EndpointProvider) —

    The endpoint provider used to resolve endpoints. Any object that responds to #resolve_endpoint(parameters) where parameters is a Struct similar to Aws::BedrockAgentCore::EndpointParameters.

  • :http_continue_timeout (Float) — default: 1 —

    The number of seconds to wait for a 100-continue response before sending the request body. This option has no effect unless the request has "Expect" header set to "100-continue". Defaults to nil which disables this behaviour. This value can safely be set per request on the session.

  • :http_idle_timeout (Float) — default: 5 —

    The number of seconds a connection is allowed to sit idle before it is considered stale. Stale connections are closed and removed from the pool before making a request.

  • :http_open_timeout (Float) — default: 15 —

    The default number of seconds to wait for response data. This value can safely be set per-request on the session.

  • :http_proxy (URI::HTTP, String) —

    A proxy to send requests through. Formatted like 'http://proxy.com:123'.

  • :http_read_timeout (Float) — default: 60 —

    The default number of seconds to wait for response data. This value can safely be set per-request on the session.

  • :http_wire_trace (Boolean) — default: false —

    When true, HTTP debug output will be sent to the :logger.

  • :on_chunk_received (Proc) —

    When a Proc object is provided, it will be used as callback when each chunk of the response body is received. It provides three arguments: the chunk, the number of bytes received, and the total number of bytes in the response (or nil if the server did not send a content-length).

  • :on_chunk_sent (Proc) —

    When a Proc object is provided, it will be used as callback when each chunk of the request body is sent. It provides three arguments: the chunk, the number of bytes read from the body, and the total number of bytes in the body.

  • :raise_response_errors (Boolean) — default: true —

    When true, response errors are raised.

  • :ssl_ca_bundle (String) —

    Full path to the SSL certificate authority bundle file that should be used when verifying peer certificates. If you do not pass :ssl_ca_bundle or :ssl_ca_directory the the system default will be used if available.

  • :ssl_ca_directory (String) —

    Full path of the directory that contains the unbundled SSL certificate authority files for verifying peer certificates. If you do not pass :ssl_ca_bundle or :ssl_ca_directory the the system default will be used if available.

  • :ssl_ca_store (String) —

    Sets the X509::Store to verify peer certificate.

  • :ssl_cert (OpenSSL::X509::Certificate) —

    Sets a client certificate when creating http connections.

  • :ssl_key (OpenSSL::PKey) —

    Sets a client key when creating http connections.

  • :ssl_timeout (Float) —

    Sets the SSL timeout in seconds

  • :ssl_verify_peer (Boolean) — default: true —

    When true, SSL peer certificates are verified when establishing a connection.



482
483
484
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 482

def initialize(*args)
  super
end

Instance Method Details

#batch_create_memory_records(params = {}) ⇒ Types::BatchCreateMemoryRecordsOutput

Creates multiple memory records in a single batch operation for the specified memory with custom content.

Examples:

Request syntax with placeholder values


resp = client.batch_create_memory_records({
  memory_id: "MemoryId", # required
  records: [ # required
    {
      request_identifier: "RequestIdentifier", # required
      namespaces: ["Namespace"], # required
      content: { # required
        text: "MemoryContentTextString",
      },
      timestamp: Time.now, # required
      memory_strategy_id: "MemoryStrategyId",
      metadata: {
        "MetadataKey" => {
          string_value: "StringValue",
          string_list_value: ["StringListMemberValue"],
          number_value: 1.0,
          date_time_value: Time.now,
        },
      },
    },
  ],
  client_token: "String",
})

Response structure


resp.successful_records #=> Array
resp.successful_records[0].memory_record_id #=> String
resp.successful_records[0].status #=> String, one of "SUCCEEDED", "FAILED"
resp.successful_records[0].request_identifier #=> String
resp.successful_records[0].error_code #=> Integer
resp.successful_records[0].error_message #=> String
resp.failed_records #=> Array
resp.failed_records[0].memory_record_id #=> String
resp.failed_records[0].status #=> String, one of "SUCCEEDED", "FAILED"
resp.failed_records[0].request_identifier #=> String
resp.failed_records[0].error_code #=> Integer
resp.failed_records[0].error_message #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The unique ID of the memory resource where records will be created.

  • :records (required, Array<Types::MemoryRecordCreateInput>) —

    A list of memory record creation inputs to be processed in the batch operation.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure idempotent processing of the batch request.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

Returns:

See Also:



555
556
557
558
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 555

def batch_create_memory_records(params = {}, options = {})
  req = build_request(:batch_create_memory_records, params)
  req.send_request(options)
end

#batch_delete_memory_records(params = {}) ⇒ Types::BatchDeleteMemoryRecordsOutput

Deletes multiple memory records in a single batch operation from the specified memory.

Examples:

Request syntax with placeholder values


resp = client.batch_delete_memory_records({
  memory_id: "MemoryId", # required
  records: [ # required
    {
      memory_record_id: "MemoryRecordId", # required
    },
  ],
})

Response structure


resp.successful_records #=> Array
resp.successful_records[0].memory_record_id #=> String
resp.successful_records[0].status #=> String, one of "SUCCEEDED", "FAILED"
resp.successful_records[0].request_identifier #=> String
resp.successful_records[0].error_code #=> Integer
resp.successful_records[0].error_message #=> String
resp.failed_records #=> Array
resp.failed_records[0].memory_record_id #=> String
resp.failed_records[0].status #=> String, one of "SUCCEEDED", "FAILED"
resp.failed_records[0].request_identifier #=> String
resp.failed_records[0].error_code #=> Integer
resp.failed_records[0].error_message #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The unique ID of the memory resource where records will be deleted.

  • :records (required, Array<Types::MemoryRecordDeleteInput>) —

    A list of memory record deletion inputs to be processed in the batch operation.

Returns:

See Also:



605
606
607
608
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 605

def batch_delete_memory_records(params = {}, options = {})
  req = build_request(:batch_delete_memory_records, params)
  req.send_request(options)
end

#batch_update_memory_records(params = {}) ⇒ Types::BatchUpdateMemoryRecordsOutput

Updates multiple memory records with custom content in a single batch operation within the specified memory.

Examples:

Request syntax with placeholder values


resp = client.batch_update_memory_records({
  memory_id: "MemoryId", # required
  records: [ # required
    {
      memory_record_id: "MemoryRecordId", # required
      timestamp: Time.now, # required
      content: {
        text: "MemoryContentTextString",
      },
      namespaces: ["Namespace"],
      memory_strategy_id: "MemoryStrategyId",
      metadata: {
        "MetadataKey" => {
          string_value: "StringValue",
          string_list_value: ["StringListMemberValue"],
          number_value: 1.0,
          date_time_value: Time.now,
        },
      },
    },
  ],
})

Response structure


resp.successful_records #=> Array
resp.successful_records[0].memory_record_id #=> String
resp.successful_records[0].status #=> String, one of "SUCCEEDED", "FAILED"
resp.successful_records[0].request_identifier #=> String
resp.successful_records[0].error_code #=> Integer
resp.successful_records[0].error_message #=> String
resp.failed_records #=> Array
resp.failed_records[0].memory_record_id #=> String
resp.failed_records[0].status #=> String, one of "SUCCEEDED", "FAILED"
resp.failed_records[0].request_identifier #=> String
resp.failed_records[0].error_code #=> Integer
resp.failed_records[0].error_message #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The unique ID of the memory resource where records will be updated.

  • :records (required, Array<Types::MemoryRecordUpdateInput>) —

    A list of memory record update inputs to be processed in the batch operation.

Returns:

See Also:



669
670
671
672
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 669

def batch_update_memory_records(params = {}, options = {})
  req = build_request(:batch_update_memory_records, params)
  req.send_request(options)
end

#complete_resource_token_auth(params = {}) ⇒ Struct

Confirms the user authentication session for obtaining OAuth2.0 tokens for a resource.

Examples:

Request syntax with placeholder values


resp = client.complete_resource_token_auth({
  user_identifier: { # required
    user_token: "UserTokenType",
    user_id: "UserIdType",
  },
  session_uri: "RequestUri", # required
})

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :user_identifier (required, Types::UserIdentifier) —

    The OAuth2.0 token or user ID that was used to generate the workload access token used for initiating the user authorization flow to retrieve OAuth2.0 tokens.

  • :session_uri (required, String) —

    Unique identifier for the user's authentication session for retrieving OAuth2 tokens. This ID tracks the authorization flow state across multiple requests and responses during the OAuth2 authentication process.

Returns:

  • (Struct) —

    Returns an empty response.

See Also:



704
705
706
707
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 704

def complete_resource_token_auth(params = {}, options = {})
  req = build_request(:complete_resource_token_auth, params)
  req.send_request(options)
end

#create_ab_test(params = {}) ⇒ Types::CreateABTestResponse

Creates an A/B test for comparing agent configurations. A/B tests split traffic between a control variant and a treatment variant through a gateway, then evaluate performance using online evaluation configurations to determine which variant performs better.

Examples:

Request syntax with placeholder values


resp = client.create_ab_test({
  name: "ABTestName", # required
  description: "ABTestDescription",
  gateway_arn: "GatewayArn", # required
  variants: [ # required
    {
      name: "VariantName", # required
      weight: 1, # required
      variant_configuration: { # required
        configuration_bundle: {
          bundle_arn: "ConfigurationBundleArn", # required
          bundle_version: "ConfigurationBundleVersion", # required
        },
        target: {
          name: "TargetName", # required
        },
      },
    },
  ],
  gateway_filter: {
    target_paths: ["PathPattern"],
  },
  evaluation_config: { # required
    online_evaluation_config_arn: "OnlineEvaluationConfigArn",
    per_variant_online_evaluation_config: [
      {
        name: "VariantName", # required
        online_evaluation_config_arn: "OnlineEvaluationConfigArn", # required
      },
    ],
  },
  role_arn: "RoleArn", # required
  enable_on_create: false,
  client_token: "ClientToken",
  tags: {
    "TagKey" => "TagValue",
  },
})

Response structure


resp.ab_test_id #=> String
resp.ab_test_arn #=> String
resp.name #=> String
resp.status #=> String, one of "CREATING", "ACTIVE", "CREATE_FAILED", "UPDATING", "UPDATE_FAILED", "DELETING", "DELETE_FAILED", "FAILED"
resp.execution_status #=> String, one of "PAUSED", "RUNNING", "STOPPED", "NOT_STARTED"
resp.created_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :name (required, String) —

    The name of the A/B test. Must be unique within your account.

  • :description (String) —

    The description of the A/B test.

  • :gateway_arn (required, String) —

    The Amazon Resource Name (ARN) of the gateway to use for traffic splitting.

  • :variants (required, Array<Types::Variant>) —

    The list of variants for the A/B test. Must contain exactly two variants: a control (C) and a treatment (T1), each with a configuration bundle or target reference and a traffic weight.

  • :gateway_filter (Types::GatewayFilter) —

    Optional filter to restrict which gateway target paths are included in the A/B test.

  • :evaluation_config (required, Types::ABTestEvaluationConfig) —

    The evaluation configuration specifying which online evaluation configurations to use for measuring variant performance.

  • :role_arn (required, String) —

    The IAM role ARN that grants permissions for the A/B test to access gateway and evaluation resources.

  • :enable_on_create (Boolean) —

    Whether to enable the A/B test immediately upon creation. If true, traffic splitting begins automatically.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, the service ignores the request, but does not return an error.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :tags (Hash<String,String>) —

    A map of tag keys and values to associate with the A/B test.

Returns:

See Also:



820
821
822
823
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 820

def create_ab_test(params = {}, options = {})
  req = build_request(:create_ab_test, params)
  req.send_request(options)
end

#create_event(params = {}) ⇒ Types::CreateEventOutput

Creates an event in an AgentCore Memory resource. Events represent interactions or activities that occur within a session and are associated with specific actors.

To use this operation, you must have the bedrock-agentcore:CreateEvent permission.

This operation is subject to request rate limiting.

Examples:

Request syntax with placeholder values


resp = client.create_event({
  memory_id: "MemoryId", # required
  actor_id: "ActorId", # required
  session_id: "SessionId",
  event_timestamp: Time.now, # required
  payload: [ # required
    {
      conversational: {
        content: { # required
          text: "ContentTextString",
        },
        role: "ASSISTANT", # required, accepts ASSISTANT, USER, TOOL, OTHER
      },
      blob: {
      },
    },
  ],
  branch: {
    root_event_id: "EventId",
    name: "BranchName", # required
  },
  client_token: "String",
  metadata: {
    "MetadataKey" => {
      string_value: "MetadataValueStringValueString",
    },
  },
  extraction_mode: "SKIP", # accepts SKIP
})

Response structure


resp.event.memory_id #=> String
resp.event.actor_id #=> String
resp.event.session_id #=> String
resp.event.event_id #=> String
resp.event.event_timestamp #=> Time
resp.event.payload #=> Array
resp.event.payload[0].conversational.content.text #=> String
resp.event.payload[0].conversational.role #=> String, one of "ASSISTANT", "USER", "TOOL", "OTHER"
resp.event.branch.root_event_id #=> String
resp.event.branch.name #=> String
resp.event.metadata #=> Hash
resp.event.metadata["MetadataKey"].string_value #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The identifier of the AgentCore Memory resource in which to create the event.

  • :actor_id (required, String) —

    The identifier of the actor associated with this event. An actor represents an entity that participates in sessions and generates events.

  • :session_id (String) —

    The identifier of the session in which this event occurs. A session represents a sequence of related events.

  • :event_timestamp (required, Time, DateTime, Date, Integer, String) —

    The timestamp when the event occurred. If not specified, the current time is used.

  • :payload (required, Array<Types::PayloadType>) —

    The content payload of the event. This can include conversational data or binary content.

  • :branch (Types::Branch) —

    The branch information for this event. Branches allow for organizing events into different conversation threads or paths.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the operation completes no more than one time. If this token matches a previous request, AgentCore ignores the request, but does not return an error.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :metadata (Hash<String,Types::MetadataValue>) —

    The key-value metadata to attach to the event.

  • :extraction_mode (String) —

    Controls long-term memory extraction for this event. When set to SKIP, the event is stored in short-term memory but is excluded from long-term memory extraction. If not specified, the event is processed for extraction as usual.

Returns:

See Also:



931
932
933
934
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 931

def create_event(params = {}, options = {})
  req = build_request(:create_event, params)
  req.send_request(options)
end

#create_payment_instrument(params = {}) ⇒ Types::CreatePaymentInstrumentResponse

Create a new payment instrument for a connector.

Examples:

Request syntax with placeholder values


resp = client.create_payment_instrument({
  user_id: "UserId",
  agent_name: "PaymentAgentName",
  payment_manager_arn: "PaymentManagerArn", # required
  payment_connector_id: "PaymentConnectorId", # required
  payment_instrument_type: "EMBEDDED_CRYPTO_WALLET", # required, accepts EMBEDDED_CRYPTO_WALLET
  payment_instrument_details: { # required
    embedded_crypto_wallet: {
      network: "ETHEREUM", # required, accepts ETHEREUM, SOLANA
      linked_accounts: [ # required
        {
          email: {
            email_address: "Email", # required
          },
          sms: {
            phone_number: "PhoneNumber", # required
          },
          developer_jwt: {
            kid: "JwtKeyId", # required
            sub: "LinkedAccountDeveloperJwtSubString", # required
          },
          o_auth_2: {
            google: {
              sub: "OAuth2AuthenticationSubString", # required
              email_address: "Email",
              name: "OAuth2AuthenticationNameString",
              username: "OAuth2AuthenticationUsernameString",
            },
            apple: {
              sub: "OAuth2AuthenticationSubString", # required
              email_address: "Email",
              name: "OAuth2AuthenticationNameString",
              username: "OAuth2AuthenticationUsernameString",
            },
            x: {
              sub: "OAuth2AuthenticationSubString", # required
              email_address: "Email",
              name: "OAuth2AuthenticationNameString",
              username: "OAuth2AuthenticationUsernameString",
            },
            telegram: {
              sub: "OAuth2AuthenticationSubString", # required
              email_address: "Email",
              name: "OAuth2AuthenticationNameString",
              username: "OAuth2AuthenticationUsernameString",
            },
            github: {
              sub: "OAuth2AuthenticationSubString", # required
              email_address: "Email",
              name: "OAuth2AuthenticationNameString",
              username: "OAuth2AuthenticationUsernameString",
            },
          },
        },
      ],
      wallet_address: "String",
      redirect_url: "EmbeddedCryptoWalletRedirectUrlString",
    },
  },
  client_token: "ClientToken",
})

Response structure


resp.payment_instrument.payment_instrument_id #=> String
resp.payment_instrument.payment_manager_arn #=> String
resp.payment_instrument.payment_connector_id #=> String
resp.payment_instrument.user_id #=> String
resp.payment_instrument.payment_instrument_type #=> String, one of "EMBEDDED_CRYPTO_WALLET"
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.network #=> String, one of "ETHEREUM", "SOLANA"
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts #=> Array
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].email.email_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].sms.phone_number #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].developer_jwt.kid #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].developer_jwt.sub #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.google.sub #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.google.email_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.google.name #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.google.username #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.apple.sub #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.apple.email_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.apple.name #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.apple.username #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.x.sub #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.x.email_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.x.name #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.x.username #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.telegram.sub #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.telegram.email_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.telegram.name #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.telegram.username #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.github.sub #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.github.email_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.github.name #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.github.username #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.wallet_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.redirect_url #=> String
resp.payment_instrument.created_at #=> Time
resp.payment_instrument.status #=> String, one of "INITIATED", "ACTIVE", "FAILED", "DELETED"
resp.payment_instrument.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :user_id (String) —

    The user ID associated with this payment instrument.

  • :agent_name (String) —

    The agent name associated with this request, used for observability.

  • :payment_manager_arn (required, String) —

    The ARN of the payment manager that owns this payment instrument.

  • :payment_connector_id (required, String) —

    The ID of the payment connector to use for this instrument.

  • :payment_instrument_type (required, String) —

    The type of payment instrument being created.

  • :payment_instrument_details (required, Types::PaymentInstrumentDetails) —

    The details of the payment instrument.

  • :client_token (String) —

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

    A suitable default value is auto-generated. You should normally not need to pass this option.**

Returns:

See Also:



1074
1075
1076
1077
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1074

def create_payment_instrument(params = {}, options = {})
  req = build_request(:create_payment_instrument, params)
  req.send_request(options)
end

#create_payment_session(params = {}) ⇒ Types::CreatePaymentSessionResponse

Create a new payment session.

Examples:

Request syntax with placeholder values


resp = client.create_payment_session({
  user_id: "UserId",
  agent_name: "PaymentAgentName",
  payment_manager_arn: "PaymentManagerArn", # required
  limits: {
    max_spend_amount: { # required
      value: "String", # required
      currency: "USD", # required, accepts USD
    },
  },
  expiry_time_in_minutes: 1, # required
  client_token: "ClientToken",
})

Response structure


resp.payment_session.payment_session_id #=> String
resp.payment_session.payment_manager_arn #=> String
resp.payment_session.limits.max_spend_amount.value #=> String
resp.payment_session.limits.max_spend_amount.currency #=> String, one of "USD"
resp.payment_session.user_id #=> String
resp.payment_session.expiry_time_in_minutes #=> Integer
resp.payment_session.created_at #=> Time
resp.payment_session.available_limits.available_spend_amount.value #=> String
resp.payment_session.available_limits.available_spend_amount.currency #=> String, one of "USD"
resp.payment_session.available_limits.updated_at #=> Time
resp.payment_session.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :user_id (String) —

    The user ID associated with this payment session.

  • :agent_name (String) —

    The agent name associated with this request, used for observability.

  • :payment_manager_arn (required, String) —

    The ARN of the payment manager that owns this session.

  • :limits (Types::SessionLimits) —

    The spending limits for this payment session.

  • :expiry_time_in_minutes (required, Integer) —

    The session expiry time in minutes. Must be between 15 and 480 minutes.

  • :client_token (String) —

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

    A suitable default value is auto-generated. You should normally not need to pass this option.**

Returns:

See Also:



1142
1143
1144
1145
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1142

def create_payment_session(params = {}, options = {})
  req = build_request(:create_payment_session, params)
  req.send_request(options)
end

#delete_ab_test(params = {}) ⇒ Types::DeleteABTestResponse

Deletes an A/B test and its associated gateway rules.

Examples:

Request syntax with placeholder values


resp = client.delete_ab_test({
  ab_test_id: "ABTestId", # required
})

Response structure


resp.ab_test_id #=> String
resp.ab_test_arn #=> String
resp.status #=> String, one of "CREATING", "ACTIVE", "CREATE_FAILED", "UPDATING", "UPDATE_FAILED", "DELETING", "DELETE_FAILED", "FAILED"

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :ab_test_id (required, String) —

    The unique identifier of the A/B test to delete.

Returns:

See Also:



1174
1175
1176
1177
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1174

def delete_ab_test(params = {}, options = {})
  req = build_request(:delete_ab_test, params)
  req.send_request(options)
end

#delete_batch_evaluation(params = {}) ⇒ Types::DeleteBatchEvaluationResponse

Deletes a batch evaluation and its associated results.

Examples:

Request syntax with placeholder values


resp = client.delete_batch_evaluation({
  batch_evaluation_id: "BatchEvaluationId", # required
})

Response structure


resp.batch_evaluation_id #=> String
resp.batch_evaluation_arn #=> String
resp.status #=> String, one of "PENDING", "IN_PROGRESS", "COMPLETED", "COMPLETED_WITH_ERRORS", "FAILED", "STOPPING", "STOPPED", "DELETING"

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :batch_evaluation_id (required, String) —

    The unique identifier of the batch evaluation to delete.

Returns:

See Also:



1206
1207
1208
1209
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1206

def delete_batch_evaluation(params = {}, options = {})
  req = build_request(:delete_batch_evaluation, params)
  req.send_request(options)
end

#delete_event(params = {}) ⇒ Types::DeleteEventOutput

Deletes an event from an AgentCore Memory resource. When you delete an event, it is permanently removed.

To use this operation, you must have the bedrock-agentcore:DeleteEvent permission.

Examples:

Request syntax with placeholder values


resp = client.delete_event({
  memory_id: "MemoryId", # required
  session_id: "SessionId", # required
  event_id: "EventId", # required
  actor_id: "ActorId", # required
})

Response structure


resp.event_id #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The identifier of the AgentCore Memory resource from which to delete the event.

  • :session_id (required, String) —

    The identifier of the session containing the event to delete.

  • :event_id (required, String) —

    The identifier of the event to delete.

  • :actor_id (required, String) —

    The identifier of the actor associated with the event to delete.

Returns:

See Also:



1251
1252
1253
1254
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1251

def delete_event(params = {}, options = {})
  req = build_request(:delete_event, params)
  req.send_request(options)
end

#delete_memory_record(params = {}) ⇒ Types::DeleteMemoryRecordOutput

Deletes a memory record from an AgentCore Memory resource. When you delete a memory record, it is permanently removed.

To use this operation, you must have the bedrock-agentcore:DeleteMemoryRecord permission.

Examples:

Request syntax with placeholder values


resp = client.delete_memory_record({
  memory_id: "MemoryId", # required
  memory_record_id: "MemoryRecordId", # required
})

Response structure


resp.memory_record_id #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The identifier of the AgentCore Memory resource from which to delete the memory record.

  • :memory_record_id (required, String) —

    The identifier of the memory record to delete.

Returns:

See Also:



1288
1289
1290
1291
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1288

def delete_memory_record(params = {}, options = {})
  req = build_request(:delete_memory_record, params)
  req.send_request(options)
end

#delete_payment_instrument(params = {}) ⇒ Types::DeletePaymentInstrumentResponse

Deletes a payment instrument. This is a soft delete operation that preserves the record for audit and compliance purposes.

Examples:

Request syntax with placeholder values


resp = client.delete_payment_instrument({
  user_id: "UserId",
  payment_manager_arn: "PaymentManagerArn", # required
  payment_connector_id: "PaymentConnectorId", # required
  payment_instrument_id: "PaymentInstrumentId", # required
})

Response structure


resp.status #=> String, one of "INITIATED", "ACTIVE", "FAILED", "DELETED"

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :user_id (String) —

    The user ID making the delete request. Must match the instrument's userId.

  • :payment_manager_arn (required, String) —

    The payment manager ARN. Must match the instrument's paymentManagerArn.

  • :payment_connector_id (required, String) —

    The payment connector ID. Must match the instrument's paymentConnectorId.

  • :payment_instrument_id (required, String) —

    The payment instrument ID to delete.

Returns:

See Also:



1332
1333
1334
1335
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1332

def delete_payment_instrument(params = {}, options = {})
  req = build_request(:delete_payment_instrument, params)
  req.send_request(options)
end

#delete_payment_session(params = {}) ⇒ Types::DeletePaymentSessionResponse

Deletes a payment session. This permanently removes the payment session record.

Examples:

Request syntax with placeholder values


resp = client.delete_payment_session({
  user_id: "UserId",
  payment_manager_arn: "PaymentManagerArn", # required
  payment_session_id: "PaymentSessionId", # required
})

Response structure


resp.status #=> String, one of "ACTIVE", "EXPIRED", "DELETED"

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :user_id (String) —

    The user ID making the delete request. Must match the session's userId.

  • :payment_manager_arn (required, String) —

    The payment manager ARN. Must match the session's paymentManagerArn.

  • :payment_session_id (required, String) —

    The payment session ID to delete.

Returns:

See Also:



1370
1371
1372
1373
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1370

def delete_payment_session(params = {}, options = {})
  req = build_request(:delete_payment_session, params)
  req.send_request(options)
end

#delete_recommendation(params = {}) ⇒ Types::DeleteRecommendationResponse

Deletes a recommendation and its associated results.

Examples:

Request syntax with placeholder values


resp = client.delete_recommendation({
  recommendation_id: "RecommendationId", # required
})

Response structure


resp.recommendation_id #=> String
resp.status #=> String, one of "PENDING", "IN_PROGRESS", "COMPLETED", "FAILED", "DELETING"

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :recommendation_id (required, String) —

    The unique identifier of the recommendation to delete.

Returns:

See Also:



1400
1401
1402
1403
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1400

def delete_recommendation(params = {}, options = {})
  req = build_request(:delete_recommendation, params)
  req.send_request(options)
end

#evaluate(params = {}) ⇒ Types::EvaluateResponse

Performs on-demand evaluation of agent traces using a specified evaluator. This synchronous API accepts traces in OpenTelemetry format and returns immediate scoring results with detailed explanations.

Examples:

Request syntax with placeholder values


resp = client.evaluate({
  evaluator_id: "EvaluatorId", # required
  evaluation_input: { # required
    session_spans: [
      {
      },
    ],
  },
  evaluation_target: {
    span_ids: ["SpanId"],
    trace_ids: ["TraceId"],
  },
  evaluation_reference_inputs: [
    {
      context: { # required
        span_context: {
          session_id: "String", # required
          trace_id: "String",
          span_id: "String",
        },
      },
      expected_response: {
        text: "EvaluationContentTextString",
      },
      assertions: [
        {
          text: "EvaluationContentTextString",
        },
      ],
      expected_trajectory: {
        tool_names: ["EvaluationToolName"],
      },
    },
  ],
})

Response structure


resp.evaluation_results #=> Array
resp.evaluation_results[0].evaluator_arn #=> String
resp.evaluation_results[0].evaluator_id #=> String
resp.evaluation_results[0].evaluator_name #=> String
resp.evaluation_results[0].explanation #=> String
resp.evaluation_results[0].context.span_context.session_id #=> String
resp.evaluation_results[0].context.span_context.trace_id #=> String
resp.evaluation_results[0].context.span_context.span_id #=> String
resp.evaluation_results[0].value #=> Float
resp.evaluation_results[0].label #=> String
resp.evaluation_results[0].token_usage.input_tokens #=> Integer
resp.evaluation_results[0].token_usage.output_tokens #=> Integer
resp.evaluation_results[0].token_usage.total_tokens #=> Integer
resp.evaluation_results[0].error_message #=> String
resp.evaluation_results[0].error_code #=> String
resp.evaluation_results[0].ignored_reference_input_fields #=> Array
resp.evaluation_results[0].ignored_reference_input_fields[0] #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :evaluator_id (required, String) —

    The unique identifier of the evaluator to use for scoring. Can be a built-in evaluator (e.g., Builtin.Helpfulness, Builtin.Correctness) or a custom evaluator Id created through the control plane API.

  • :evaluation_input (required, Types::EvaluationInput) —

    The input data containing agent session spans to be evaluated. Includes a list of spans in OpenTelemetry format from supported frameworks like Strands (AgentCore Runtime) or LangGraph with OpenInference instrumentation.

  • :evaluation_target (Types::EvaluationTarget) —

    The specific trace or span IDs to evaluate within the provided input. Allows targeting evaluation at different levels: individual tool calls, single request-response interactions (traces), or entire conversation sessions.

  • :evaluation_reference_inputs (Array<Types::EvaluationReferenceInput>) —

    Ground truth data to compare against agent responses during evaluation. Allows to provide expected responses, assertions, and expected tool trajectories at different evaluation levels. Session-level reference inputs apply to the entire conversation, while trace-level reference inputs target specific request-response interactions identified by trace ID.

Returns:

See Also:



1501
1502
1503
1504
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1501

def evaluate(params = {}, options = {})
  req = build_request(:evaluate, params)
  req.send_request(options)
end

#get_ab_test(params = {}) ⇒ Types::GetABTestResponse

Retrieves detailed information about an A/B test, including its configuration, status, and statistical results.

Examples:

Request syntax with placeholder values


resp = client.get_ab_test({
  ab_test_id: "ABTestId", # required
})

Response structure


resp.ab_test_id #=> String
resp.ab_test_arn #=> String
resp.name #=> String
resp.description #=> String
resp.status #=> String, one of "CREATING", "ACTIVE", "CREATE_FAILED", "UPDATING", "UPDATE_FAILED", "DELETING", "DELETE_FAILED", "FAILED"
resp.execution_status #=> String, one of "PAUSED", "RUNNING", "STOPPED", "NOT_STARTED"
resp.gateway_arn #=> String
resp.variants #=> Array
resp.variants[0].name #=> String
resp.variants[0].weight #=> Integer
resp.variants[0].variant_configuration.configuration_bundle.bundle_arn #=> String
resp.variants[0].variant_configuration.configuration_bundle.bundle_version #=> String
resp.variants[0].variant_configuration.target.name #=> String
resp.gateway_filter.target_paths #=> Array
resp.gateway_filter.target_paths[0] #=> String
resp.evaluation_config.online_evaluation_config_arn #=> String
resp.evaluation_config.per_variant_online_evaluation_config #=> Array
resp.evaluation_config.per_variant_online_evaluation_config[0].name #=> String
resp.evaluation_config.per_variant_online_evaluation_config[0].online_evaluation_config_arn #=> String
resp.role_arn #=> String
resp.current_run_id #=> String
resp.error_details #=> Array
resp.error_details[0] #=> String
resp.started_at #=> Time
resp.stopped_at #=> Time
resp.max_duration_expires_at #=> Time
resp.created_at #=> Time
resp.updated_at #=> Time
resp.results.analysis_timestamp #=> Time
resp.results.evaluator_metrics #=> Array
resp.results.evaluator_metrics[0].evaluator_arn #=> String
resp.results.evaluator_metrics[0].control_stats.variant_name #=> String
resp.results.evaluator_metrics[0].control_stats.sample_size #=> Integer
resp.results.evaluator_metrics[0].control_stats.mean #=> Float
resp.results.evaluator_metrics[0].variant_results #=> Array
resp.results.evaluator_metrics[0].variant_results[0].variant_name #=> String
resp.results.evaluator_metrics[0].variant_results[0].sample_size #=> Integer
resp.results.evaluator_metrics[0].variant_results[0].mean #=> Float
resp.results.evaluator_metrics[0].variant_results[0].absolute_change #=> Float
resp.results.evaluator_metrics[0].variant_results[0].percent_change #=> Float
resp.results.evaluator_metrics[0].variant_results[0].p_value #=> Float
resp.results.evaluator_metrics[0].variant_results[0].confidence_interval.lower #=> Float
resp.results.evaluator_metrics[0].variant_results[0].confidence_interval.upper #=> Float
resp.results.evaluator_metrics[0].variant_results[0].is_significant #=> Boolean

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :ab_test_id (required, String) —

    The unique identifier of the A/B test to retrieve.

Returns:

See Also:



1591
1592
1593
1594
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1591

def get_ab_test(params = {}, options = {})
  req = build_request(:get_ab_test, params)
  req.send_request(options)
end

#get_agent_card(params = {}) ⇒ Types::GetAgentCardResponse

Retrieves the A2A agent card associated with an AgentCore Runtime agent.

Examples:

Request syntax with placeholder values


resp = client.get_agent_card({
  runtime_session_id: "SessionType",
  agent_runtime_arn: "String", # required
  qualifier: "String",
})

Response structure


resp.runtime_session_id #=> String
resp.status_code #=> Integer

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :runtime_session_id (String) —

    The session ID that the AgentCore Runtime agent is using.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :agent_runtime_arn (required, String) —

    The ARN of the AgentCore Runtime agent for which you want to get the A2A agent card.

  • :qualifier (String) —

    Optional qualifier to specify an agent alias, such as prodcode> or dev. If you don't provide a value, the DEFAULT alias is used.

Returns:

See Also:



1636
1637
1638
1639
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1636

def get_agent_card(params = {}, options = {})
  req = build_request(:get_agent_card, params)
  req.send_request(options)
end

#get_batch_evaluation(params = {}) ⇒ Types::GetBatchEvaluationResponse

Retrieves detailed information about a batch evaluation, including its status, configuration, results, and any error details.

Examples:

Request syntax with placeholder values


resp = client.get_batch_evaluation({
  batch_evaluation_id: "BatchEvaluationId", # required
})

Response structure


resp.batch_evaluation_id #=> String
resp.batch_evaluation_arn #=> String
resp.batch_evaluation_name #=> String
resp.status #=> String, one of "PENDING", "IN_PROGRESS", "COMPLETED", "COMPLETED_WITH_ERRORS", "FAILED", "STOPPING", "STOPPED", "DELETING"
resp.created_at #=> Time
resp.evaluators #=> Array
resp.evaluators[0].evaluator_id #=> String
resp.insights #=> Array
resp.insights[0].insight_id #=> String
resp.data_source_config.cloud_watch_logs.service_names #=> Array
resp.data_source_config.cloud_watch_logs.service_names[0] #=> String
resp.data_source_config.cloud_watch_logs.log_group_names #=> Array
resp.data_source_config.cloud_watch_logs.log_group_names[0] #=> String
resp.data_source_config.cloud_watch_logs.filter_config.session_ids #=> Array
resp.data_source_config.cloud_watch_logs.filter_config.session_ids[0] #=> String
resp.data_source_config.cloud_watch_logs.filter_config.time_range.start_time #=> Time
resp.data_source_config.cloud_watch_logs.filter_config.time_range.end_time #=> Time
resp.data_source_config.online_evaluation_config_source.online_evaluation_config_arn #=> String
resp.data_source_config.online_evaluation_config_source.time_range.start_time #=> Time
resp.data_source_config.online_evaluation_config_source.time_range.end_time #=> Time
resp.output_config.cloud_watch_config.log_group_name #=> String
resp.output_config.cloud_watch_config.log_stream_name #=> String
resp.evaluation_results.number_of_sessions_completed #=> Integer
resp.evaluation_results.number_of_sessions_in_progress #=> Integer
resp.evaluation_results.number_of_sessions_failed #=> Integer
resp.evaluation_results.total_number_of_sessions #=> Integer
resp.evaluation_results.number_of_sessions_ignored #=> Integer
resp.evaluation_results.evaluator_summaries #=> Array
resp.evaluation_results.evaluator_summaries[0].evaluator_id #=> String
resp.evaluation_results.evaluator_summaries[0].statistics.average_score #=> Float
resp.evaluation_results.evaluator_summaries[0].total_evaluated #=> Integer
resp.evaluation_results.evaluator_summaries[0].total_failed #=> Integer
resp.failure_analysis_result.failures #=> Array
resp.failure_analysis_result.failures[0].cluster_id #=> Integer
resp.failure_analysis_result.failures[0].name #=> String
resp.failure_analysis_result.failures[0].description #=> String
resp.failure_analysis_result.failures[0].affected_session_count #=> Integer
resp.failure_analysis_result.failures[0].sub_categories #=> Array
resp.failure_analysis_result.failures[0].sub_categories[0].cluster_id #=> Integer
resp.failure_analysis_result.failures[0].sub_categories[0].name #=> String
resp.failure_analysis_result.failures[0].sub_categories[0].description #=> String
resp.failure_analysis_result.failures[0].sub_categories[0].affected_session_count #=> Integer
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes #=> Array
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].cluster_id #=> Integer
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].name #=> String
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].root_cause #=> String
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].recommendation #=> String
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_session_count #=> Integer
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_sessions #=> Array
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_sessions[0].session_id #=> String
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_sessions[0].explanation #=> String
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_sessions[0].fix_type #=> String
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_sessions[0].recommendation #=> String
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_sessions[0].failure_spans #=> Array
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_sessions[0].failure_spans[0].span_id #=> String
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_sessions[0].failure_spans[0].trace_id #=> String
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_sessions[0].failure_spans[0].signals #=> Array
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_sessions[0].failure_spans[0].signals[0].category #=> String, one of "execution-error-category-authentication", "execution-error-category-resource-not-found", "execution-error-category-service-errors", "execution-error-category-rate-limiting", "execution-error-category-formatting", "execution-error-category-timeout", "execution-error-category-resource-exhaustion", "execution-error-category-environment", "execution-error-category-tool-schema", "task-instruction-category-non-compliance", "task-instruction-category-problem-id", "incorrect-actions-category-tool-selection", "incorrect-actions-category-poor-information-retrieval", "incorrect-actions-category-clarification", "incorrect-actions-category-inappropriate-info-request", "context-handling-error-category-context-handling-failures", "hallucination-category-hall-capabilities", "hallucination-category-hall-misunderstand", "hallucination-category-hall-usage", "hallucination-category-hall-history", "hallucination-category-hall-params", "hallucination-category-fabricate-tool-outputs", "repetitive-behavior-category-repetition-tool", "repetitive-behavior-category-repetition-info", "repetitive-behavior-category-step-repetition", "orchestration-related-errors-category-reasoning-mismatch", "orchestration-related-errors-category-goal-deviation", "orchestration-related-errors-category-premature-termination", "orchestration-related-errors-category-unaware-termination", "llm-output-category-nonsensical", "configuration-mismatch-category-tool-definition", "coding-use-case-specific-failure-types-category-edge-case-oversights", "coding-use-case-specific-failure-types-category-dependency-issues", "other"
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_sessions[0].failure_spans[0].signals[0].evidence #=> String
resp.failure_analysis_result.failures[0].sub_categories[0].root_causes[0].affected_sessions[0].failure_spans[0].signals[0].confidence #=> Float
resp.user_intent_result.user_intents #=> Array
resp.user_intent_result.user_intents[0].cluster_id #=> Integer
resp.user_intent_result.user_intents[0].name #=> String
resp.user_intent_result.user_intents[0].description #=> String
resp.user_intent_result.user_intents[0].affected_session_count #=> Integer
resp.user_intent_result.user_intents[0].affected_sessions #=> Array
resp.user_intent_result.user_intents[0].affected_sessions[0].session_id #=> String
resp.user_intent_result.user_intents[0].affected_sessions[0].user_messages #=> Array
resp.user_intent_result.user_intents[0].affected_sessions[0].user_messages[0] #=> String
resp.execution_summary_result.execution_summaries #=> Array
resp.execution_summary_result.execution_summaries[0].cluster_id #=> Integer
resp.execution_summary_result.execution_summaries[0].name #=> String
resp.execution_summary_result.execution_summaries[0].description #=> String
resp.execution_summary_result.execution_summaries[0].affected_session_count #=> Integer
resp.execution_summary_result.execution_summaries[0].affected_sessions #=> Array
resp.execution_summary_result.execution_summaries[0].affected_sessions[0].session_id #=> String
resp.execution_summary_result.execution_summaries[0].affected_sessions[0].approach_taken #=> String
resp.execution_summary_result.execution_summaries[0].affected_sessions[0].final_outcome #=> String
resp.error_details #=> Array
resp.error_details[0] #=> String
resp.description #=> String
resp.updated_at #=> Time
resp.kms_key_arn #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :batch_evaluation_id (required, String) —

    The unique identifier of the batch evaluation to retrieve.

Returns:

See Also:



1763
1764
1765
1766
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1763

def get_batch_evaluation(params = {}, options = {})
  req = build_request(:get_batch_evaluation, params)
  req.send_request(options)
end

#get_browser_session(params = {}) ⇒ Types::GetBrowserSessionResponse

Retrieves detailed information about a specific browser session in Amazon Bedrock AgentCore. This operation returns the session's configuration, current status, associated streams, and metadata.

To get a browser session, you must specify both the browser identifier and the session ID. The response includes information about the session's viewport configuration, timeout settings, and stream endpoints.

The following operations are related to GetBrowserSession:

Examples:

Request syntax with placeholder values


resp = client.get_browser_session({
  browser_identifier: "String", # required
  session_id: "BrowserSessionId", # required
})

Response structure


resp.browser_identifier #=> String
resp.session_id #=> String
resp.name #=> String
resp.created_at #=> Time
resp.view_port.width #=> Integer
resp.view_port.height #=> Integer
resp.extensions #=> Array
resp.extensions[0].location.s3.bucket #=> String
resp.extensions[0].location.s3.prefix #=> String
resp.extensions[0].location.s3.version_id #=> String
resp.enterprise_policies #=> Array
resp.enterprise_policies[0].location.s3.bucket #=> String
resp.enterprise_policies[0].location.s3.prefix #=> String
resp.enterprise_policies[0].location.s3.version_id #=> String
resp.enterprise_policies[0].type #=> String, one of "MANAGED", "RECOMMENDED"
resp.profile_configuration.profile_identifier #=> String
resp.session_timeout_seconds #=> Integer
resp.status #=> String, one of "READY", "TERMINATED"
resp.streams.automation_stream.stream_endpoint #=> String
resp.streams.automation_stream.stream_status #=> String, one of "ENABLED", "DISABLED"
resp.streams.live_view_stream.stream_endpoint #=> String
resp.proxy_configuration.proxies #=> Array
resp.proxy_configuration.proxies[0].external_proxy.server #=> String
resp.proxy_configuration.proxies[0].external_proxy.port #=> Integer
resp.proxy_configuration.proxies[0].external_proxy.domain_patterns #=> Array
resp.proxy_configuration.proxies[0].external_proxy.domain_patterns[0] #=> String
resp.proxy_configuration.proxies[0].external_proxy.credentials.basic_auth.secret_arn #=> String
resp.proxy_configuration.bypass.domain_patterns #=> Array
resp.proxy_configuration.bypass.domain_patterns[0] #=> String
resp.certificates #=> Array
resp.certificates[0].location.secrets_manager.secret_arn #=> String
resp.filesystem_configurations #=> Array
resp.filesystem_configurations[0].s3_files_configuration.access_point_arn #=> String
resp.filesystem_configurations[0].s3_files_configuration.mount_path #=> String
resp.filesystem_configurations[0].s3_files_configuration.file_system_arn #=> String
resp.filesystem_configurations[0].efs_configuration.access_point_arn #=> String
resp.filesystem_configurations[0].efs_configuration.mount_path #=> String
resp.filesystem_configurations[0].efs_configuration.file_system_arn #=> String
resp.session_replay_artifact #=> String
resp.last_updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :browser_identifier (required, String) —

    The unique identifier of the browser associated with the session.

  • :session_id (required, String) —

    The unique identifier of the browser session to retrieve.

Returns:

See Also:



1870
1871
1872
1873
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1870

def get_browser_session(params = {}, options = {})
  req = build_request(:get_browser_session, params)
  req.send_request(options)
end

#get_code_interpreter_session(params = {}) ⇒ Types::GetCodeInterpreterSessionResponse

Retrieves detailed information about a specific code interpreter session in Amazon Bedrock AgentCore. This operation returns the session's configuration, current status, and metadata.

To get a code interpreter session, you must specify both the code interpreter identifier and the session ID. The response includes information about the session's timeout settings and current status.

The following operations are related to GetCodeInterpreterSession:

Examples:

Request syntax with placeholder values


resp = client.get_code_interpreter_session({
  code_interpreter_identifier: "String", # required
  session_id: "CodeInterpreterSessionId", # required
})

Response structure


resp.code_interpreter_identifier #=> String
resp.session_id #=> String
resp.name #=> String
resp.created_at #=> Time
resp.session_timeout_seconds #=> Integer
resp.status #=> String, one of "READY", "TERMINATED"
resp.certificates #=> Array
resp.certificates[0].location.secrets_manager.secret_arn #=> String
resp.filesystem_configurations #=> Array
resp.filesystem_configurations[0].s3_files_configuration.access_point_arn #=> String
resp.filesystem_configurations[0].s3_files_configuration.mount_path #=> String
resp.filesystem_configurations[0].s3_files_configuration.file_system_arn #=> String
resp.filesystem_configurations[0].efs_configuration.access_point_arn #=> String
resp.filesystem_configurations[0].efs_configuration.mount_path #=> String
resp.filesystem_configurations[0].efs_configuration.file_system_arn #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :code_interpreter_identifier (required, String) —

    The unique identifier of the code interpreter associated with the session.

  • :session_id (required, String) —

    The unique identifier of the code interpreter session to retrieve.

Returns:

See Also:



1944
1945
1946
1947
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1944

def get_code_interpreter_session(params = {}, options = {})
  req = build_request(:get_code_interpreter_session, params)
  req.send_request(options)
end

#get_event(params = {}) ⇒ Types::GetEventOutput

Retrieves information about a specific event in an AgentCore Memory resource.

To use this operation, you must have the bedrock-agentcore:GetEvent permission.

Examples:

Request syntax with placeholder values


resp = client.get_event({
  memory_id: "MemoryId", # required
  session_id: "SessionId", # required
  actor_id: "ActorId", # required
  event_id: "EventId", # required
})

Response structure


resp.event.memory_id #=> String
resp.event.actor_id #=> String
resp.event.session_id #=> String
resp.event.event_id #=> String
resp.event.event_timestamp #=> Time
resp.event.payload #=> Array
resp.event.payload[0].conversational.content.text #=> String
resp.event.payload[0].conversational.role #=> String, one of "ASSISTANT", "USER", "TOOL", "OTHER"
resp.event.branch.root_event_id #=> String
resp.event.branch.name #=> String
resp.event.metadata #=> Hash
resp.event.metadata["MetadataKey"].string_value #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The identifier of the AgentCore Memory resource containing the event.

  • :session_id (required, String) —

    The identifier of the session containing the event.

  • :actor_id (required, String) —

    The identifier of the actor associated with the event.

  • :event_id (required, String) —

    The identifier of the event to retrieve.

Returns:

See Also:



1999
2000
2001
2002
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 1999

def get_event(params = {}, options = {})
  req = build_request(:get_event, params)
  req.send_request(options)
end

#get_memory_record(params = {}) ⇒ Types::GetMemoryRecordOutput

Retrieves a specific memory record from an AgentCore Memory resource.

To use this operation, you must have the bedrock-agentcore:GetMemoryRecord permission.

Examples:

Request syntax with placeholder values


resp = client.get_memory_record({
  memory_id: "MemoryId", # required
  memory_record_id: "MemoryRecordId", # required
})

Response structure


resp.memory_record.memory_record_id #=> String
resp.memory_record.content.text #=> String
resp.memory_record.memory_strategy_id #=> String
resp.memory_record.namespaces #=> Array
resp.memory_record.namespaces[0] #=> String
resp.memory_record.created_at #=> Time
resp.memory_record.metadata #=> Hash
resp.memory_record.metadata["MetadataKey"].string_value #=> String
resp.memory_record.metadata["MetadataKey"].string_list_value #=> Array
resp.memory_record.metadata["MetadataKey"].string_list_value[0] #=> String
resp.memory_record.metadata["MetadataKey"].number_value #=> Float
resp.memory_record.metadata["MetadataKey"].date_time_value #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The identifier of the AgentCore Memory resource containing the memory record.

  • :memory_record_id (required, String) —

    The identifier of the memory record to retrieve.

Returns:

See Also:



2046
2047
2048
2049
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 2046

def get_memory_record(params = {}, options = {})
  req = build_request(:get_memory_record, params)
  req.send_request(options)
end

#get_payment_instrument(params = {}) ⇒ Types::GetPaymentInstrumentResponse

Get a payment instrument by ID.

Examples:

Request syntax with placeholder values


resp = client.get_payment_instrument({
  user_id: "UserId",
  agent_name: "PaymentAgentName",
  payment_manager_arn: "PaymentManagerArn", # required
  payment_connector_id: "PaymentConnectorId",
  payment_instrument_id: "PaymentInstrumentId", # required
})

Response structure


resp.payment_instrument.payment_instrument_id #=> String
resp.payment_instrument.payment_manager_arn #=> String
resp.payment_instrument.payment_connector_id #=> String
resp.payment_instrument.user_id #=> String
resp.payment_instrument.payment_instrument_type #=> String, one of "EMBEDDED_CRYPTO_WALLET"
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.network #=> String, one of "ETHEREUM", "SOLANA"
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts #=> Array
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].email.email_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].sms.phone_number #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].developer_jwt.kid #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].developer_jwt.sub #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.google.sub #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.google.email_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.google.name #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.google.username #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.apple.sub #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.apple.email_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.apple.name #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.apple.username #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.x.sub #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.x.email_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.x.name #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.x.username #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.telegram.sub #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.telegram.email_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.telegram.name #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.telegram.username #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.github.sub #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.github.email_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.github.name #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.linked_accounts[0].o_auth_2.github.username #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.wallet_address #=> String
resp.payment_instrument.payment_instrument_details.embedded_crypto_wallet.redirect_url #=> String
resp.payment_instrument.created_at #=> Time
resp.payment_instrument.status #=> String, one of "INITIATED", "ACTIVE", "FAILED", "DELETED"
resp.payment_instrument.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :user_id (String) —

    The user ID associated with this payment instrument.

  • :agent_name (String) —

    The agent name associated with this request, used for observability.

  • :payment_manager_arn (required, String) —

    The ARN of the payment manager that owns this payment instrument.

  • :payment_connector_id (String) —

    The ID of the payment connector.

  • :payment_instrument_id (required, String) —

    The ID of the payment instrument to retrieve.

Returns:

See Also:



2125
2126
2127
2128
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 2125

def get_payment_instrument(params = {}, options = {})
  req = build_request(:get_payment_instrument, params)
  req.send_request(options)
end

#get_payment_instrument_balance(params = {}) ⇒ Types::GetPaymentInstrumentBalanceResponse

Get the balance of a payment instrument.

Examples:

Request syntax with placeholder values


resp = client.get_payment_instrument_balance({
  user_id: "UserId",
  agent_name: "PaymentAgentName",
  payment_manager_arn: "PaymentManagerArn", # required
  payment_connector_id: "PaymentConnectorId", # required
  payment_instrument_id: "PaymentInstrumentId", # required
  chain: "BASE", # required, accepts BASE, BASE_SEPOLIA, ETHEREUM, SOLANA, SOLANA_DEVNET
  token: "USDC", # required, accepts USDC
})

Response structure


resp.payment_instrument_id #=> String
resp.token_balance.amount #=> String
resp.token_balance.decimals #=> Integer
resp.token_balance.token #=> String, one of "USDC"
resp.token_balance.network #=> String, one of "ETHEREUM", "SOLANA"
resp.token_balance.chain #=> String, one of "BASE", "BASE_SEPOLIA", "ETHEREUM", "SOLANA", "SOLANA_DEVNET"

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :user_id (String) —

    The user ID associated with this payment instrument.

  • :agent_name (String) —

    The agent name associated with this request, used for observability.

  • :payment_manager_arn (required, String) —

    The ARN of the payment manager that owns this payment instrument.

  • :payment_connector_id (required, String) —

    The ID of the payment connector associated with this instrument.

  • :payment_instrument_id (required, String) —

    The ID of the payment instrument to query balance for.

  • :chain (required, String) —

    The specific blockchain chain to query balance on. Required because balances are chain-specific.

  • :token (required, String) —

    The token to query balance for. Only tokens supported for X402 payments are returned.

Returns:

See Also:



2185
2186
2187
2188
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 2185

def get_payment_instrument_balance(params = {}, options = {})
  req = build_request(:get_payment_instrument_balance, params)
  req.send_request(options)
end

#get_payment_session(params = {}) ⇒ Types::GetPaymentSessionResponse

Get a payment session.

Examples:

Request syntax with placeholder values


resp = client.get_payment_session({
  user_id: "UserId",
  agent_name: "PaymentAgentName",
  payment_manager_arn: "PaymentManagerArn", # required
  payment_session_id: "PaymentSessionId", # required
})

Response structure


resp.payment_session.payment_session_id #=> String
resp.payment_session.payment_manager_arn #=> String
resp.payment_session.limits.max_spend_amount.value #=> String
resp.payment_session.limits.max_spend_amount.currency #=> String, one of "USD"
resp.payment_session.user_id #=> String
resp.payment_session.expiry_time_in_minutes #=> Integer
resp.payment_session.created_at #=> Time
resp.payment_session.available_limits.available_spend_amount.value #=> String
resp.payment_session.available_limits.available_spend_amount.currency #=> String, one of "USD"
resp.payment_session.available_limits.updated_at #=> Time
resp.payment_session.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :user_id (String) —

    The user ID associated with this payment session.

  • :agent_name (String) —

    The agent name associated with this request, used for observability.

  • :payment_manager_arn (required, String) —

    The ARN of the payment manager that owns this session.

  • :payment_session_id (required, String) —

    The ID of the payment session to retrieve.

Returns:

See Also:



2235
2236
2237
2238
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 2235

def get_payment_session(params = {}, options = {})
  req = build_request(:get_payment_session, params)
  req.send_request(options)
end

#get_recommendation(params = {}) ⇒ Types::GetRecommendationResponse

Retrieves detailed information about a recommendation, including its configuration, status, and results.

Examples:

Request syntax with placeholder values


resp = client.get_recommendation({
  recommendation_id: "RecommendationId", # required
})

Response structure


resp.recommendation_id #=> String
resp.recommendation_arn #=> String
resp.name #=> String
resp.description #=> String
resp.type #=> String, one of "SYSTEM_PROMPT_RECOMMENDATION", "TOOL_DESCRIPTION_RECOMMENDATION"
resp.recommendation_config.system_prompt_recommendation_config.system_prompt.text #=> String
resp.recommendation_config.system_prompt_recommendation_config.system_prompt.configuration_bundle.bundle_arn #=> String
resp.recommendation_config.system_prompt_recommendation_config.system_prompt.configuration_bundle.version_id #=> String
resp.recommendation_config.system_prompt_recommendation_config.system_prompt.configuration_bundle.system_prompt_json_path #=> String
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.session_spans #=> Array
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.log_group_arns #=> Array
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.log_group_arns[0] #=> String
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.service_names #=> Array
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.service_names[0] #=> String
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.start_time #=> Time
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.end_time #=> Time
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.rule.filters #=> Array
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].key #=> String
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].operator #=> String, one of "Equals", "NotEquals", "GreaterThan", "LessThan", "GreaterThanOrEqual", "LessThanOrEqual", "Contains", "NotContains"
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].value.string_value #=> String
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].value.double_value #=> Float
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].value.boolean_value #=> Boolean
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.batch_evaluation.batch_evaluation_arn #=> String
resp.recommendation_config.system_prompt_recommendation_config.evaluation_config.evaluators #=> Array
resp.recommendation_config.system_prompt_recommendation_config.evaluation_config.evaluators[0].evaluator_arn #=> String
resp.recommendation_config.tool_description_recommendation_config.tool_description.tool_description_text.tools #=> Array
resp.recommendation_config.tool_description_recommendation_config.tool_description.tool_description_text.tools[0].tool_name #=> String
resp.recommendation_config.tool_description_recommendation_config.tool_description.tool_description_text.tools[0].tool_description.text #=> String
resp.recommendation_config.tool_description_recommendation_config.tool_description.configuration_bundle.bundle_arn #=> String
resp.recommendation_config.tool_description_recommendation_config.tool_description.configuration_bundle.version_id #=> String
resp.recommendation_config.tool_description_recommendation_config.tool_description.configuration_bundle.tools #=> Array
resp.recommendation_config.tool_description_recommendation_config.tool_description.configuration_bundle.tools[0].tool_name #=> String
resp.recommendation_config.tool_description_recommendation_config.tool_description.configuration_bundle.tools[0].tool_description_json_path #=> String
resp.recommendation_config.tool_description_recommendation_config.agent_traces.session_spans #=> Array
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.log_group_arns #=> Array
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.log_group_arns[0] #=> String
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.service_names #=> Array
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.service_names[0] #=> String
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.start_time #=> Time
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.end_time #=> Time
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.rule.filters #=> Array
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].key #=> String
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].operator #=> String, one of "Equals", "NotEquals", "GreaterThan", "LessThan", "GreaterThanOrEqual", "LessThanOrEqual", "Contains", "NotContains"
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].value.string_value #=> String
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].value.double_value #=> Float
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].value.boolean_value #=> Boolean
resp.recommendation_config.tool_description_recommendation_config.agent_traces.batch_evaluation.batch_evaluation_arn #=> String
resp.status #=> String, one of "PENDING", "IN_PROGRESS", "COMPLETED", "FAILED", "DELETING"
resp.created_at #=> Time
resp.updated_at #=> Time
resp.recommendation_result.system_prompt_recommendation_result.recommended_system_prompt #=> String
resp.recommendation_result.system_prompt_recommendation_result.configuration_bundle.bundle_arn #=> String
resp.recommendation_result.system_prompt_recommendation_result.configuration_bundle.version_id #=> String
resp.recommendation_result.system_prompt_recommendation_result.explanation #=> String
resp.recommendation_result.system_prompt_recommendation_result.error_code #=> String
resp.recommendation_result.system_prompt_recommendation_result.error_message #=> String
resp.recommendation_result.tool_description_recommendation_result.tools #=> Array
resp.recommendation_result.tool_description_recommendation_result.tools[0].tool_name #=> String
resp.recommendation_result.tool_description_recommendation_result.tools[0].recommended_tool_description #=> String
resp.recommendation_result.tool_description_recommendation_result.tools[0].explanation #=> String
resp.recommendation_result.tool_description_recommendation_result.configuration_bundle.bundle_arn #=> String
resp.recommendation_result.tool_description_recommendation_result.configuration_bundle.version_id #=> String
resp.recommendation_result.tool_description_recommendation_result.error_code #=> String
resp.recommendation_result.tool_description_recommendation_result.error_message #=> String
resp.kms_key_arn #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :recommendation_id (required, String) —

    The unique identifier of the recommendation to retrieve.

Returns:

See Also:



2338
2339
2340
2341
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 2338

def get_recommendation(params = {}, options = {})
  req = build_request(:get_recommendation, params)
  req.send_request(options)
end

#get_resource_api_key(params = {}) ⇒ Types::GetResourceApiKeyResponse

Retrieves the API key associated with an API key credential provider.

Examples:

Request syntax with placeholder values


resp = client.get_resource_api_key({
  workload_identity_token: "WorkloadIdentityTokenType", # required
  resource_credential_provider_name: "CredentialProviderName", # required
})

Response structure


resp.api_key #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :workload_identity_token (required, String) —

    The identity token of the workload from which you want to retrieve the API key.

  • :resource_credential_provider_name (required, String) —

    The credential provider name for the resource from which you are retrieving the API key.

Returns:

See Also:



2372
2373
2374
2375
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 2372

def get_resource_api_key(params = {}, options = {})
  req = build_request(:get_resource_api_key, params)
  req.send_request(options)
end

#get_resource_oauth_2_token(params = {}) ⇒ Types::GetResourceOauth2TokenResponse

Returns the OAuth 2.0 token of the provided resource.

Examples:

Request syntax with placeholder values


resp = client.get_resource_oauth_2_token({
  workload_identity_token: "WorkloadIdentityTokenType", # required
  resource_credential_provider_name: "CredentialProviderName", # required
  scopes: ["ScopeType"], # required
  oauth2_flow: "USER_FEDERATION", # required, accepts USER_FEDERATION, M2M, ON_BEHALF_OF_TOKEN_EXCHANGE
  session_uri: "RequestUri",
  resource_oauth_2_return_url: "ResourceOauth2ReturnUrlType",
  force_authentication: false,
  custom_parameters: {
    "CustomRequestKeyType" => "CustomRequestValueType",
  },
  custom_state: "State",
  resources: ["ResourceType"],
  audiences: ["AudienceType"],
})

Response structure


resp.authorization_url #=> String
resp.access_token #=> String
resp.session_uri #=> String
resp.session_status #=> String, one of "IN_PROGRESS", "FAILED"

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :workload_identity_token (required, String) —

    The identity token of the workload from which you want to retrieve the OAuth2 token.

  • :resource_credential_provider_name (required, String) —

    The name of the resource's credential provider.

  • :scopes (required, Array<String>) —

    The OAuth scopes being requested.

  • :oauth2_flow (required, String) —

    The type of flow to be performed.

  • :session_uri (String) —

    Unique identifier for the user's authentication session for retrieving OAuth2 tokens. This ID tracks the authorization flow state across multiple requests and responses during the OAuth2 authentication process.

  • :resource_oauth_2_return_url (String) —

    The callback URL to redirect to after the OAuth 2.0 token retrieval is complete. This URL must be one of the provided URLs configured for the workload identity.

  • :force_authentication (Boolean) —

    Indicates whether to always initiate a new three-legged OAuth (3LO) flow, regardless of any existing session.

  • :custom_parameters (Hash<String,String>) —

    A map of custom parameters to include in the authorization request to the resource credential provider. These parameters are in addition to the standard OAuth 2.0 flow parameters, and will not override them.

  • :custom_state (String) —

    An opaque string that will be sent back to the callback URL provided in resourceOauth2ReturnUrl. This state should be used to protect the callback URL of your application against CSRF attacks by ensuring the response corresponds to the original request.

  • :resources (Array<String>) —

    The resources to include in the token request. These are used to specify the target resources for which the OAuth2 token is being requested.

  • :audiences (Array<String>) —

    The audiences to include in the token request. These are used to specify the intended recipients of the OAuth2 token.

Returns:

See Also:



2463
2464
2465
2466
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 2463

def get_resource_oauth_2_token(params = {}, options = {})
  req = build_request(:get_resource_oauth_2_token, params)
  req.send_request(options)
end

#get_resource_payment_token(params = {}) ⇒ Types::GetResourcePaymentTokenResponse

Generates authentication tokens for payment providers that use vendor-specific authentication mechanisms.

Examples:

Request syntax with placeholder values


resp = client.get_resource_payment_token({
  workload_identity_token: "WorkloadIdentityTokenType", # required
  resource_credential_provider_name: "CredentialProviderName", # required
  payment_token_request: { # required
    coinbase_cdp_token_request: {
      request_method: "GET", # required, accepts GET, POST, PUT, DELETE, PATCH
      request_host: "PaymentRequestHostType",
      request_path: "PaymentRequestPathType", # required
      include_wallet_auth_token: false,
      request_body: "CoinbaseCdpPaymentRequestBodyType",
    },
    stripe_privy_token_request: {
      request_host: "StripePrivyRequestHostType",
      request_path: "StripePrivyRequestPathType", # required
      request_body: "StripePrivyRequestBodyType", # required
      include_authorization_signature: false,
    },
  },
})

Response structure


resp.payment_token_response.coinbase_cdp_token_response.bearer_token #=> String
resp.payment_token_response.coinbase_cdp_token_response.wallet_auth_token #=> String
resp.payment_token_response.stripe_privy_token_response.authorization_signature #=> String
resp.payment_token_response.stripe_privy_token_response.request_expiry #=> Integer
resp.payment_token_response.stripe_privy_token_response.app_id #=> String
resp.payment_token_response.stripe_privy_token_response.basic_auth_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :workload_identity_token (required, String) —

    Workload access token for authorization.

  • :resource_credential_provider_name (required, String) —

    Name of the payment credential provider to use.

  • :payment_token_request (required, Types::PaymentTokenRequestInput) —

    Vendor-specific token request input. Contains all request parameters in a type-safe, vendor-specific structure.

Returns:

See Also:



2520
2521
2522
2523
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 2520

def get_resource_payment_token(params = {}, options = {})
  req = build_request(:get_resource_payment_token, params)
  req.send_request(options)
end

#get_workload_access_token(params = {}) ⇒ Types::GetWorkloadAccessTokenResponse

Obtains a workload access token for agentic workloads not acting on behalf of a user.

Examples:

Request syntax with placeholder values


resp = client.get_workload_access_token({
  workload_name: "WorkloadIdentityNameType", # required
})

Response structure


resp.workload_access_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :workload_name (required, String) —

    The unique identifier for the registered workload.

Returns:

See Also:



2549
2550
2551
2552
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 2549

def get_workload_access_token(params = {}, options = {})
  req = build_request(:get_workload_access_token, params)
  req.send_request(options)
end

#get_workload_access_token_for_jwt(params = {}) ⇒ Types::GetWorkloadAccessTokenForJWTResponse

Obtains a workload access token for agentic workloads acting on behalf of a user, using a JWT token.

Examples:

Request syntax with placeholder values


resp = client.get_workload_access_token_for_jwt({
  workload_name: "WorkloadIdentityNameType", # required
  user_token: "UserTokenType", # required
})

Response structure


resp.workload_access_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :workload_name (required, String) —

    The unique identifier for the registered workload.

  • :user_token (required, String) —

    The OAuth 2.0 token issued by the user's identity provider.

Returns:

See Also:



2582
2583
2584
2585
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 2582

def get_workload_access_token_for_jwt(params = {}, options = {})
  req = build_request(:get_workload_access_token_for_jwt, params)
  req.send_request(options)
end

#get_workload_access_token_for_user_id(params = {}) ⇒ Types::GetWorkloadAccessTokenForUserIdResponse

Obtains a workload access token for agentic workloads acting on behalf of a user, using the user's ID.

Examples:

Request syntax with placeholder values


resp = client.get_workload_access_token_for_user_id({
  workload_name: "WorkloadIdentityNameType", # required
  user_id: "UserIdType", # required
})

Response structure


resp.workload_access_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :workload_name (required, String) —

    The name of the workload from which you want to retrieve the access token.

  • :user_id (required, String) —

    The ID of the user for whom you are retrieving the access token.

Returns:

See Also:



2616
2617
2618
2619
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 2616

def get_workload_access_token_for_user_id(params = {}, options = {})
  req = build_request(:get_workload_access_token_for_user_id, params)
  req.send_request(options)
end

#invoke_agent_runtime(params = {}) ⇒ Types::InvokeAgentRuntimeResponse

Sends a request to an agent or tool hosted in an Amazon Bedrock AgentCore Runtime and receives responses in real-time.

To invoke an agent, you can specify either the AgentCore Runtime ARN or the agent ID with an account ID, and provide a payload containing your request. When you use the agent ID instead of the full ARN, you don't need to URL-encode the identifier. You can optionally specify a qualifier to target a specific endpoint of the agent.

This operation supports streaming responses, allowing you to receive partial responses as they become available. We recommend using pagination to ensure that the operation returns quickly and successfully when processing large responses.

For example code, see Invoke an AgentCore Runtime agent.

If you're integrating your agent with OAuth, you can't use the Amazon Web Services SDK to call InvokeAgentRuntime. Instead, make a HTTPS request to InvokeAgentRuntime. For an example, see Authenticate and authorize with Inbound Auth and Outbound Auth.

To use this operation, you must have the bedrock-agentcore:InvokeAgentRuntime permission. If you are making a call to InvokeAgentRuntime on behalf of a user ID with the X-Amzn-Bedrock-AgentCore-Runtime-User-Id header, You require permissions to both actions (bedrock-agentcore:InvokeAgentRuntime and bedrock-agentcore:InvokeAgentRuntimeForUser).

Examples:

Request syntax with placeholder values


resp = client.invoke_agent_runtime({
  content_type: "MimeType",
  accept: "MimeType",
  mcp_session_id: "StringType",
  runtime_session_id: "SessionType",
  mcp_protocol_version: "StringType",
  mcp_method: "StringType",
  mcp_name: "StringType",
  runtime_user_id: "StringType",
  trace_id: "InvokeAgentRuntimeRequestTraceIdString",
  trace_parent: "InvokeAgentRuntimeRequestTraceParentString",
  trace_state: "InvokeAgentRuntimeRequestTraceStateString",
  baggage: "InvokeAgentRuntimeRequestBaggageString",
  agent_runtime_arn: "String", # required
  qualifier: "String",
  account_id: "InvokeAgentRuntimeRequestAccountIdString",
  payload: "data", # required
})

Response structure


resp.runtime_session_id #=> String
resp.mcp_session_id #=> String
resp.mcp_protocol_version #=> String
resp.trace_id #=> String
resp.trace_parent #=> String
resp.trace_state #=> String
resp.baggage #=> String
resp.content_type #=> String
resp.response #=> IO
resp.status_code #=> Integer

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :content_type (String) —

    The MIME type of the input data in the payload. This tells the agent runtime how to interpret the payload data. Common values include application/json for JSON data.

  • :accept (String) —

    The desired MIME type for the response from the agent runtime. This tells the agent runtime what format to use for the response data. Common values include application/json for JSON data.

  • :mcp_session_id (String) —

    The identifier of the MCP session.

  • :runtime_session_id (String) —

    The identifier of the runtime session.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :mcp_protocol_version (String) —

    The version of the MCP protocol being used.

  • :mcp_method (String) —

    The MCP method being invoked. For example, tools/call, resources/read, or prompts/get.

  • :mcp_name (String) —

    The name of the MCP resource, tool, or prompt being accessed. The value depends on the method:

    • tools/call – The tool name.

    • resources/read – The resource URI.

    • prompts/get – The prompt name.

  • :runtime_user_id (String) —

    The identifier of the runtime user.

  • :trace_id (String) —

    The trace identifier for request tracking.

  • :trace_parent (String) —

    The parent trace information for distributed tracing.

  • :trace_state (String) —

    The trace state information for distributed tracing.

  • :baggage (String) —

    Additional context information for distributed tracing.

  • :agent_runtime_arn (required, String) —

    The identifier of the agent runtime to invoke. You can specify either the full Amazon Web Services Resource Name (ARN) or the agent ID. If you use the agent ID, you must also provide the accountId query parameter.

  • :qualifier (String) —

    The qualifier to use for the agent runtime. This is an endpoint name that points to a specific version. If not specified, Amazon Bedrock AgentCore uses the default endpoint of the agent runtime.

  • :account_id (String) —

    The identifier of the Amazon Web Services account for the agent runtime resource. This parameter is required when you specify an agent ID instead of the full ARN for agentRuntimeArn.

  • :payload (required, String, StringIO, File) —

    The input data to send to the agent runtime. The format of this data depends on the specific agent configuration and must match the specified content type. For most agents, this is a JSON object containing the user's request.

Returns:

See Also:



2778
2779
2780
2781
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 2778

def invoke_agent_runtime(params = {}, options = {}, &block)
  req = build_request(:invoke_agent_runtime, params)
  req.send_request(options, &block)
end

#invoke_agent_runtime_command(params = {}) ⇒ Types::InvokeAgentRuntimeCommandResponse

Executes a command in a runtime session container and streams the output back to the caller. This operation allows you to run shell commands within the agent runtime environment and receive real-time streaming responses including standard output and standard error.

To invoke a command, you must specify the agent runtime ARN and a runtime session ID. The command execution supports streaming responses, allowing you to receive output as it becomes available through contentStart, contentDelta, and contentStop events.

To use this operation, you must have the bedrock-agentcore:InvokeAgentRuntimeCommand permission.

Examples:

EventStream Operation Example


# You can process the event once it arrives immediately, or wait until the
# full response is complete and iterate through the eventstream enumerator.

# To interact with event immediately, you need to register invoke_agent_runtime_command
# with callbacks. Callbacks can be registered for specific events or for all
# events, including error events.

# Callbacks can be passed into the `:event_stream_handler` option or within a
# block statement attached to the #invoke_agent_runtime_command call directly. Hybrid
# pattern of both is also supported.

# `:event_stream_handler` option takes in either a Proc object or
# Aws::BedrockAgentCore::EventStreams::InvokeAgentRuntimeCommandStreamOutput object.

# Usage pattern a): Callbacks with a block attached to #invoke_agent_runtime_command
# Example for registering callbacks for all event types and an error event
client.invoke_agent_runtime_command(
  # params input
) do |stream|
  stream.on_error_event do |event|
    # catch unmodeled error event in the stream
    raise event
    # => Aws::Errors::EventError
    # event.event_type => :error
    # event.error_code => String
    # event.error_message => String
  end

  stream.on_event do |event|
    # process all events arrive
    puts event.event_type
    # ...
  end
end

# Usage pattern b): Pass in `:event_stream_handler` for #invoke_agent_runtime_command
#  1) Create a Aws::BedrockAgentCore::EventStreams::InvokeAgentRuntimeCommandStreamOutput object
#  Example for registering callbacks with specific events

handler = Aws::BedrockAgentCore::EventStreams::InvokeAgentRuntimeCommandStreamOutput.new
handler.on_chunk_event do |event|
  event # => Aws::BedrockAgentCore::Types::chunk
end
handler.on_access_denied_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::accessDeniedException
end
handler.on_internal_server_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::internalServerException
end
handler.on_resource_not_found_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::resourceNotFoundException
end
handler.on_service_quota_exceeded_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::serviceQuotaExceededException
end
handler.on_throttling_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::throttlingException
end
handler.on_validation_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::validationException
end
handler.on_runtime_client_error_event do |event|
  event # => Aws::BedrockAgentCore::Types::runtimeClientError
end

client.invoke_agent_runtime_command(
  # params inputs
  event_stream_handler: handler
)

#  2) Use a Ruby Proc object
#  Example for registering callbacks with specific events
handler = Proc.new do |stream|
  stream.on_chunk_event do |event|
    event # => Aws::BedrockAgentCore::Types::chunk
  end
  stream.on_access_denied_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::accessDeniedException
  end
  stream.on_internal_server_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::internalServerException
  end
  stream.on_resource_not_found_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::resourceNotFoundException
  end
  stream.on_service_quota_exceeded_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::serviceQuotaExceededException
  end
  stream.on_throttling_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::throttlingException
  end
  stream.on_validation_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::validationException
  end
  stream.on_runtime_client_error_event do |event|
    event # => Aws::BedrockAgentCore::Types::runtimeClientError
  end
end

client.invoke_agent_runtime_command(
  # params inputs
  event_stream_handler: handler
)

#  Usage pattern c): Hybrid pattern of a) and b)
handler = Aws::BedrockAgentCore::EventStreams::InvokeAgentRuntimeCommandStreamOutput.new
handler.on_chunk_event do |event|
  event # => Aws::BedrockAgentCore::Types::chunk
end
handler.on_access_denied_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::accessDeniedException
end
handler.on_internal_server_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::internalServerException
end
handler.on_resource_not_found_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::resourceNotFoundException
end
handler.on_service_quota_exceeded_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::serviceQuotaExceededException
end
handler.on_throttling_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::throttlingException
end
handler.on_validation_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::validationException
end
handler.on_runtime_client_error_event do |event|
  event # => Aws::BedrockAgentCore::Types::runtimeClientError
end

client.invoke_agent_runtime_command(
  # params input
  event_stream_handler: handler
) do |stream|
  stream.on_error_event do |event|
    # catch unmodeled error event in the stream
    raise event
    # => Aws::Errors::EventError
    # event.event_type => :error
    # event.error_code => String
    # event.error_message => String
  end
end

# You can also iterate through events after the response complete.
# Events are available at
resp.stream # => Enumerator
# For parameter input example, please refer to following request syntax.

Request syntax with placeholder values


resp = client.invoke_agent_runtime_command({
  content_type: "MimeType",
  accept: "MimeType",
  runtime_session_id: "SessionType",
  trace_id: "InvokeAgentRuntimeCommandRequestTraceIdString",
  trace_parent: "InvokeAgentRuntimeCommandRequestTraceParentString",
  trace_state: "InvokeAgentRuntimeCommandRequestTraceStateString",
  baggage: "InvokeAgentRuntimeCommandRequestBaggageString",
  agent_runtime_arn: "String", # required
  qualifier: "String",
  account_id: "InvokeAgentRuntimeCommandRequestAccountIdString",
  body: { # required
    command: "InvokeAgentRuntimeCommandRequestBodyCommandString", # required
    timeout: 1,
  },
})

Response structure


resp.runtime_session_id #=> String
resp.trace_id #=> String
resp.trace_parent #=> String
resp.trace_state #=> String
resp.baggage #=> String
resp.content_type #=> String
resp.status_code #=> Integer
# All events are available at resp.stream:
resp.stream #=> Enumerator
resp.stream.event_types #=> [:chunk, :access_denied_exception, :internal_server_exception, :resource_not_found_exception, :service_quota_exceeded_exception, :throttling_exception, :validation_exception, :runtime_client_error]

# For :chunk event available at #on_chunk_event callback and response eventstream enumerator:
event.content_delta.stdout #=> String
event.content_delta.stderr #=> String
event.content_stop.exit_code #=> Integer
event.content_stop.status #=> String, one of "COMPLETED", "TIMED_OUT"

# For :access_denied_exception event available at #on_access_denied_exception_event callback and response eventstream enumerator:
event.message #=> String

# For :internal_server_exception event available at #on_internal_server_exception_event callback and response eventstream enumerator:
event.message #=> String

# For :resource_not_found_exception event available at #on_resource_not_found_exception_event callback and response eventstream enumerator:
event.message #=> String

# For :service_quota_exceeded_exception event available at #on_service_quota_exceeded_exception_event callback and response eventstream enumerator:
event.message #=> String

# For :throttling_exception event available at #on_throttling_exception_event callback and response eventstream enumerator:
event.message #=> String

# For :validation_exception event available at #on_validation_exception_event callback and response eventstream enumerator:
event.message #=> String
event.reason #=> String, one of "CannotParse", "FieldValidationFailed", "IdempotentParameterMismatchException", "EventInOtherSession", "ResourceConflict"
event.field_list #=> Array
event.field_list[0].name #=> String
event.field_list[0].message #=> String

# For :runtime_client_error event available at #on_runtime_client_error_event callback and response eventstream enumerator:
event.message #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :content_type (String) —

    The MIME type of the input data in the request payload. This tells the agent runtime how to interpret the payload data. Common values include application/json for JSON data.

  • :accept (String) —

    The desired MIME type for the response from the agent runtime command. This tells the agent runtime what format to use for the response data. Common values include application/json for JSON data.

  • :runtime_session_id (String) —

    The unique identifier of the runtime session in which to execute the command. This session ID is used to maintain state and context across multiple command invocations.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :trace_id (String) —

    The trace identifier for request tracking.

  • :trace_parent (String) —

    The parent trace information for distributed tracing.

  • :trace_state (String) —

    The trace state information for distributed tracing.

  • :baggage (String) —

    Additional context information for distributed tracing.

  • :agent_runtime_arn (required, String) —

    The Amazon Resource Name (ARN) of the agent runtime on which to execute the command. This identifies the specific agent runtime environment where the command will run.

  • :qualifier (String) —

    The qualifier to use for the agent runtime. This is an endpoint name that points to a specific version. If not specified, Amazon Bedrock AgentCore uses the default endpoint of the agent runtime.

  • :account_id (String) —

    The identifier of the Amazon Web Services account for the agent runtime resource. This parameter is required when you specify an agent ID instead of the full ARN for agentRuntimeArn.

  • :body (required, Types::InvokeAgentRuntimeCommandRequestBody) —

    The request body containing the command to execute and optional configuration parameters such as timeout settings.

Yields:

  • (event_stream_handler)

Returns:

See Also:



3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 3075

def invoke_agent_runtime_command(params = {}, options = {}, &block)
  params = params.dup
  event_stream_handler = case handler = params.delete(:event_stream_handler)
    when EventStreams::InvokeAgentRuntimeCommandStreamOutput then handler
    when Proc then EventStreams::InvokeAgentRuntimeCommandStreamOutput.new.tap(&handler)
    when nil then EventStreams::InvokeAgentRuntimeCommandStreamOutput.new
    else
      msg = "expected :event_stream_handler to be a block or "\
            "instance of Aws::BedrockAgentCore::EventStreams::InvokeAgentRuntimeCommandStreamOutput"\
            ", got `#{handler.inspect}` instead"
      raise ArgumentError, msg
    end

  yield(event_stream_handler) if block_given?

  req = build_request(:invoke_agent_runtime_command, params)

  req.context[:event_stream_handler] = event_stream_handler
  req.handlers.add(Aws::Binary::DecodeHandler, priority: 95)

  req.send_request(options, &block)
end

#invoke_browser(params = {}) ⇒ Types::InvokeBrowserResponse

Invokes an operating system-level action on a browser session in Amazon Bedrock AgentCore. This operation provides direct OS-level control over browser sessions, enabling mouse actions, keyboard input, and screenshots that the WebSocket-based Chrome DevTools Protocol (CDP) cannot handle — such as interacting with print dialogs, context menus, and JavaScript alerts.

You send a request with exactly one action in the BrowserAction union, and receive a corresponding result in the BrowserActionResult union.

The following operations are related to InvokeBrowser:

Examples:

Request syntax with placeholder values


resp = client.invoke_browser({
  browser_identifier: "String", # required
  session_id: "BrowserSessionId", # required
  action: { # required
    mouse_click: {
      x: 1, # required
      y: 1, # required
      button: "LEFT", # accepts LEFT, RIGHT, MIDDLE
      click_count: 1,
    },
    mouse_move: {
      x: 1, # required
      y: 1, # required
    },
    mouse_drag: {
      end_x: 1, # required
      end_y: 1, # required
      start_x: 1, # required
      start_y: 1, # required
      button: "LEFT", # accepts LEFT, RIGHT, MIDDLE
    },
    mouse_scroll: {
      x: 1, # required
      y: 1, # required
      delta_x: 1,
      delta_y: 1,
    },
    key_type: {
      text: "KeyTypeArgumentsTextString", # required
    },
    key_press: {
      key: "String", # required
      presses: 1,
    },
    key_shortcut: {
      keys: ["String"], # required
    },
    screenshot: {
      format: "PNG", # accepts PNG
    },
  },
})

Response structure


resp.result.mouse_click.status #=> String, one of "SUCCESS", "FAILED"
resp.result.mouse_click.error #=> String
resp.result.mouse_move.status #=> String, one of "SUCCESS", "FAILED"
resp.result.mouse_move.error #=> String
resp.result.mouse_drag.status #=> String, one of "SUCCESS", "FAILED"
resp.result.mouse_drag.error #=> String
resp.result.mouse_scroll.status #=> String, one of "SUCCESS", "FAILED"
resp.result.mouse_scroll.error #=> String
resp.result.key_type.status #=> String, one of "SUCCESS", "FAILED"
resp.result.key_type.error #=> String
resp.result.key_press.status #=> String, one of "SUCCESS", "FAILED"
resp.result.key_press.error #=> String
resp.result.key_shortcut.status #=> String, one of "SUCCESS", "FAILED"
resp.result.key_shortcut.error #=> String
resp.result.screenshot.status #=> String, one of "SUCCESS", "FAILED"
resp.result.screenshot.error #=> String
resp.result.screenshot.data #=> String
resp.session_id #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :browser_identifier (required, String) —

    The unique identifier of the browser associated with the session. This must match the identifier used when creating the session with StartBrowserSession.

  • :session_id (required, String) —

    The unique identifier of the browser session on which to perform the action. This must be an active session created with StartBrowserSession.

  • :action (required, Types::BrowserAction) —

    The browser action to perform. Exactly one member of the BrowserAction union must be set per request.

Returns:

See Also:



3212
3213
3214
3215
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 3212

def invoke_browser(params = {}, options = {})
  req = build_request(:invoke_browser, params)
  req.send_request(options)
end

#invoke_code_interpreter(params = {}) ⇒ Types::InvokeCodeInterpreterResponse

Executes code within an active code interpreter session in Amazon Bedrock AgentCore. This operation processes the provided code, runs it in a secure environment, and returns the execution results including output, errors, and generated visualizations.

To execute code, you must specify the code interpreter identifier, session ID, and the code to run in the arguments parameter. The operation returns a stream containing the execution results, which can include text output, error messages, and data visualizations.

This operation is subject to request rate limiting based on your account's service quotas.

The following operations are related to InvokeCodeInterpreter:

Examples:

EventStream Operation Example


# You can process the event once it arrives immediately, or wait until the
# full response is complete and iterate through the eventstream enumerator.

# To interact with event immediately, you need to register invoke_code_interpreter
# with callbacks. Callbacks can be registered for specific events or for all
# events, including error events.

# Callbacks can be passed into the `:event_stream_handler` option or within a
# block statement attached to the #invoke_code_interpreter call directly. Hybrid
# pattern of both is also supported.

# `:event_stream_handler` option takes in either a Proc object or
# Aws::BedrockAgentCore::EventStreams::CodeInterpreterStreamOutput object.

# Usage pattern a): Callbacks with a block attached to #invoke_code_interpreter
# Example for registering callbacks for all event types and an error event
client.invoke_code_interpreter(
  # params input
) do |stream|
  stream.on_error_event do |event|
    # catch unmodeled error event in the stream
    raise event
    # => Aws::Errors::EventError
    # event.event_type => :error
    # event.error_code => String
    # event.error_message => String
  end

  stream.on_event do |event|
    # process all events arrive
    puts event.event_type
    # ...
  end
end

# Usage pattern b): Pass in `:event_stream_handler` for #invoke_code_interpreter
#  1) Create a Aws::BedrockAgentCore::EventStreams::CodeInterpreterStreamOutput object
#  Example for registering callbacks with specific events

handler = Aws::BedrockAgentCore::EventStreams::CodeInterpreterStreamOutput.new
handler.on_result_event do |event|
  event # => Aws::BedrockAgentCore::Types::result
end
handler.on_access_denied_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::accessDeniedException
end
handler.on_conflict_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::conflictException
end
handler.on_internal_server_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::internalServerException
end
handler.on_resource_not_found_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::resourceNotFoundException
end
handler.on_service_quota_exceeded_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::serviceQuotaExceededException
end
handler.on_throttling_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::throttlingException
end
handler.on_validation_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::validationException
end

client.invoke_code_interpreter(
  # params inputs
  event_stream_handler: handler
)

#  2) Use a Ruby Proc object
#  Example for registering callbacks with specific events
handler = Proc.new do |stream|
  stream.on_result_event do |event|
    event # => Aws::BedrockAgentCore::Types::result
  end
  stream.on_access_denied_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::accessDeniedException
  end
  stream.on_conflict_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::conflictException
  end
  stream.on_internal_server_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::internalServerException
  end
  stream.on_resource_not_found_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::resourceNotFoundException
  end
  stream.on_service_quota_exceeded_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::serviceQuotaExceededException
  end
  stream.on_throttling_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::throttlingException
  end
  stream.on_validation_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::validationException
  end
end

client.invoke_code_interpreter(
  # params inputs
  event_stream_handler: handler
)

#  Usage pattern c): Hybrid pattern of a) and b)
handler = Aws::BedrockAgentCore::EventStreams::CodeInterpreterStreamOutput.new
handler.on_result_event do |event|
  event # => Aws::BedrockAgentCore::Types::result
end
handler.on_access_denied_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::accessDeniedException
end
handler.on_conflict_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::conflictException
end
handler.on_internal_server_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::internalServerException
end
handler.on_resource_not_found_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::resourceNotFoundException
end
handler.on_service_quota_exceeded_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::serviceQuotaExceededException
end
handler.on_throttling_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::throttlingException
end
handler.on_validation_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::validationException
end

client.invoke_code_interpreter(
  # params input
  event_stream_handler: handler
) do |stream|
  stream.on_error_event do |event|
    # catch unmodeled error event in the stream
    raise event
    # => Aws::Errors::EventError
    # event.event_type => :error
    # event.error_code => String
    # event.error_message => String
  end
end

# You can also iterate through events after the response complete.
# Events are available at
resp.stream # => Enumerator
# For parameter input example, please refer to following request syntax.

Request syntax with placeholder values


resp = client.invoke_code_interpreter({
  code_interpreter_identifier: "String", # required
  session_id: "CodeInterpreterSessionId",
  trace_id: "InvokeCodeInterpreterRequestTraceIdString",
  trace_parent: "InvokeCodeInterpreterRequestTraceParentString",
  name: "executeCode", # required, accepts executeCode, executeCommand, readFiles, listFiles, removeFiles, writeFiles, startCommandExecution, getTask, stopTask
  arguments: {
    code: "MaxLenString",
    language: "python", # accepts python, javascript, typescript
    clear_context: false,
    command: "MaxLenString",
    path: "MaxLenString",
    paths: ["MaxLenString"],
    content: [
      {
        path: "MaxLenString", # required
        text: "MaxLenString",
        blob: "data",
      },
    ],
    directory_path: "MaxLenString",
    task_id: "MaxLenString",
    runtime: "nodejs", # accepts nodejs, deno, python
  },
})

Response structure


resp.session_id #=> String
# All events are available at resp.stream:
resp.stream #=> Enumerator
resp.stream.event_types #=> [:result, :access_denied_exception, :conflict_exception, :internal_server_exception, :resource_not_found_exception, :service_quota_exceeded_exception, :throttling_exception, :validation_exception]

# For :result event available at #on_result_event callback and response eventstream enumerator:
event.content #=> Array
event.content[0].type #=> String, one of "text", "image", "resource", "resource_link"
event.content[0].text #=> String
event.content[0].data #=> String
event.content[0].mime_type #=> String
event.content[0].uri #=> String
event.content[0].name #=> String
event.content[0].description #=> String
event.content[0].size #=> Integer
event.content[0].resource.type #=> String, one of "text", "blob"
event.content[0].resource.uri #=> String
event.content[0].resource.mime_type #=> String
event.content[0].resource.text #=> String
event.content[0].resource.blob #=> String
event.structured_content.task_id #=> String
event.structured_content.task_status #=> String, one of "submitted", "working", "completed", "canceled", "failed"
event.structured_content.stdout #=> String
event.structured_content.stderr #=> String
event.structured_content.exit_code #=> Integer
event.structured_content.execution_time #=> Float
event.is_error #=> Boolean

# For :access_denied_exception event available at #on_access_denied_exception_event callback and response eventstream enumerator:
event.message #=> String

# For :conflict_exception event available at #on_conflict_exception_event callback and response eventstream enumerator:
event.message #=> String

# For :internal_server_exception event available at #on_internal_server_exception_event callback and response eventstream enumerator:
event.message #=> String

# For :resource_not_found_exception event available at #on_resource_not_found_exception_event callback and response eventstream enumerator:
event.message #=> String

# For :service_quota_exceeded_exception event available at #on_service_quota_exceeded_exception_event callback and response eventstream enumerator:
event.message #=> String

# For :throttling_exception event available at #on_throttling_exception_event callback and response eventstream enumerator:
event.message #=> String

# For :validation_exception event available at #on_validation_exception_event callback and response eventstream enumerator:
event.message #=> String
event.reason #=> String, one of "CannotParse", "FieldValidationFailed", "IdempotentParameterMismatchException", "EventInOtherSession", "ResourceConflict"
event.field_list #=> Array
event.field_list[0].name #=> String
event.field_list[0].message #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :code_interpreter_identifier (required, String) —

    The unique identifier of the code interpreter associated with the session. This must match the identifier used when creating the session with StartCodeInterpreterSession.

  • :session_id (String) —

    The unique identifier of the code interpreter session to use. This must be an active session created with StartCodeInterpreterSession. If the session has expired or been stopped, the request will fail.

  • :trace_id (String) —

    The trace identifier for request tracking.

  • :trace_parent (String) —

    The parent trace information for distributed tracing.

  • :name (required, String) —

    The name of the code interpreter to invoke.

  • :arguments (Types::ToolArguments) —

    The arguments for the code interpreter. This includes the code to execute and any additional parameters such as the programming language, whether to clear the execution context, and other execution options. The structure of this parameter depends on the specific code interpreter being used.

Yields:

  • (event_stream_handler)

Returns:

See Also:



3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 3511

def invoke_code_interpreter(params = {}, options = {}, &block)
  params = params.dup
  event_stream_handler = case handler = params.delete(:event_stream_handler)
    when EventStreams::CodeInterpreterStreamOutput then handler
    when Proc then EventStreams::CodeInterpreterStreamOutput.new.tap(&handler)
    when nil then EventStreams::CodeInterpreterStreamOutput.new
    else
      msg = "expected :event_stream_handler to be a block or "\
            "instance of Aws::BedrockAgentCore::EventStreams::CodeInterpreterStreamOutput"\
            ", got `#{handler.inspect}` instead"
      raise ArgumentError, msg
    end

  yield(event_stream_handler) if block_given?

  req = build_request(:invoke_code_interpreter, params)

  req.context[:event_stream_handler] = event_stream_handler
  req.handlers.add(Aws::Binary::DecodeHandler, priority: 95)

  req.send_request(options, &block)
end

#invoke_harness(params = {}) ⇒ Types::InvokeHarnessResponse

Operation to invoke a Harness.

Examples:

EventStream Operation Example


# You can process the event once it arrives immediately, or wait until the
# full response is complete and iterate through the eventstream enumerator.

# To interact with event immediately, you need to register invoke_harness
# with callbacks. Callbacks can be registered for specific events or for all
# events, including error events.

# Callbacks can be passed into the `:event_stream_handler` option or within a
# block statement attached to the #invoke_harness call directly. Hybrid
# pattern of both is also supported.

# `:event_stream_handler` option takes in either a Proc object or
# Aws::BedrockAgentCore::EventStreams::InvokeHarnessStreamOutput object.

# Usage pattern a): Callbacks with a block attached to #invoke_harness
# Example for registering callbacks for all event types and an error event
client.invoke_harness(
  # params input
) do |stream|
  stream.on_error_event do |event|
    # catch unmodeled error event in the stream
    raise event
    # => Aws::Errors::EventError
    # event.event_type => :error
    # event.error_code => String
    # event.error_message => String
  end

  stream.on_event do |event|
    # process all events arrive
    puts event.event_type
    # ...
  end
end

# Usage pattern b): Pass in `:event_stream_handler` for #invoke_harness
#  1) Create a Aws::BedrockAgentCore::EventStreams::InvokeHarnessStreamOutput object
#  Example for registering callbacks with specific events

handler = Aws::BedrockAgentCore::EventStreams::InvokeHarnessStreamOutput.new
handler.on_message_start_event do |event|
  event # => Aws::BedrockAgentCore::Types::messageStart
end
handler.on_content_block_start_event do |event|
  event # => Aws::BedrockAgentCore::Types::contentBlockStart
end
handler.on_content_block_delta_event do |event|
  event # => Aws::BedrockAgentCore::Types::contentBlockDelta
end
handler.on_content_block_stop_event do |event|
  event # => Aws::BedrockAgentCore::Types::contentBlockStop
end
handler.on_message_stop_event do |event|
  event # => Aws::BedrockAgentCore::Types::messageStop
end
handler.on_metadata_event do |event|
  event # => Aws::BedrockAgentCore::Types::metadata
end
handler.on_internal_server_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::internalServerException
end
handler.on_validation_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::validationException
end
handler.on_runtime_client_error_event do |event|
  event # => Aws::BedrockAgentCore::Types::runtimeClientError
end

client.invoke_harness(
  # params inputs
  event_stream_handler: handler
)

#  2) Use a Ruby Proc object
#  Example for registering callbacks with specific events
handler = Proc.new do |stream|
  stream.on_message_start_event do |event|
    event # => Aws::BedrockAgentCore::Types::messageStart
  end
  stream.on_content_block_start_event do |event|
    event # => Aws::BedrockAgentCore::Types::contentBlockStart
  end
  stream.on_content_block_delta_event do |event|
    event # => Aws::BedrockAgentCore::Types::contentBlockDelta
  end
  stream.on_content_block_stop_event do |event|
    event # => Aws::BedrockAgentCore::Types::contentBlockStop
  end
  stream.on_message_stop_event do |event|
    event # => Aws::BedrockAgentCore::Types::messageStop
  end
  stream.on_metadata_event do |event|
    event # => Aws::BedrockAgentCore::Types::metadata
  end
  stream.on_internal_server_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::internalServerException
  end
  stream.on_validation_exception_event do |event|
    event # => Aws::BedrockAgentCore::Types::validationException
  end
  stream.on_runtime_client_error_event do |event|
    event # => Aws::BedrockAgentCore::Types::runtimeClientError
  end
end

client.invoke_harness(
  # params inputs
  event_stream_handler: handler
)

#  Usage pattern c): Hybrid pattern of a) and b)
handler = Aws::BedrockAgentCore::EventStreams::InvokeHarnessStreamOutput.new
handler.on_message_start_event do |event|
  event # => Aws::BedrockAgentCore::Types::messageStart
end
handler.on_content_block_start_event do |event|
  event # => Aws::BedrockAgentCore::Types::contentBlockStart
end
handler.on_content_block_delta_event do |event|
  event # => Aws::BedrockAgentCore::Types::contentBlockDelta
end
handler.on_content_block_stop_event do |event|
  event # => Aws::BedrockAgentCore::Types::contentBlockStop
end
handler.on_message_stop_event do |event|
  event # => Aws::BedrockAgentCore::Types::messageStop
end
handler.on_metadata_event do |event|
  event # => Aws::BedrockAgentCore::Types::metadata
end
handler.on_internal_server_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::internalServerException
end
handler.on_validation_exception_event do |event|
  event # => Aws::BedrockAgentCore::Types::validationException
end
handler.on_runtime_client_error_event do |event|
  event # => Aws::BedrockAgentCore::Types::runtimeClientError
end

client.invoke_harness(
  # params input
  event_stream_handler: handler
) do |stream|
  stream.on_error_event do |event|
    # catch unmodeled error event in the stream
    raise event
    # => Aws::Errors::EventError
    # event.event_type => :error
    # event.error_code => String
    # event.error_message => String
  end
end

# You can also iterate through events after the response complete.
# Events are available at
resp.stream # => Enumerator
# For parameter input example, please refer to following request syntax.

Request syntax with placeholder values


resp = client.invoke_harness({
  harness_arn: "HarnessArn", # required
  qualifier: "HarnessEndpointName",
  runtime_session_id: "InvokeHarnessRequestRuntimeSessionIdString", # required
  runtime_user_id: "String",
  trace_parent: "InvokeHarnessRequestTraceParentString",
  trace_state: "InvokeHarnessRequestTraceStateString",
  trace_id: "InvokeHarnessRequestTraceIdString",
  baggage: "InvokeHarnessRequestBaggageString",
  messages: [ # required
    {
      role: "user", # required, accepts user, assistant
      content: [ # required
        {
          text: "SensitiveText",
          tool_use: {
            name: "HarnessToolName", # required
            tool_use_id: "HarnessToolUseId", # required
            input: { # required
            },
            type: "tool_use", # accepts tool_use, server_tool_use, mcp_tool_use
            server_name: "String",
          },
          tool_result: {
            tool_use_id: "HarnessToolUseId", # required
            content: [ # required
              {
                text: "SensitiveText",
                json: {
                },
              },
            ],
            status: "success", # accepts success, error
            type: "tool_use", # accepts tool_use, server_tool_use, mcp_tool_use
          },
          reasoning_content: {
            reasoning_text: {
              text: "String", # required
              signature: "String",
            },
            redacted_content: "data",
          },
        },
      ],
    },
  ],
  model: {
    bedrock_model_config: {
      model_id: "ModelId", # required
      max_tokens: 1,
      temperature: 1.0,
      top_p: 1.0,
      api_format: "converse_stream", # accepts converse_stream, responses, chat_completions
      additional_params: {
      },
    },
    open_ai_model_config: {
      model_id: "ModelId", # required
      api_key_arn: "ApiKeyArn", # required
      max_tokens: 1,
      temperature: 1.0,
      top_p: 1.0,
      api_format: "chat_completions", # accepts chat_completions, responses
      additional_params: {
      },
    },
    gemini_model_config: {
      model_id: "ModelId", # required
      api_key_arn: "ApiKeyArn", # required
      max_tokens: 1,
      temperature: 1.0,
      top_p: 1.0,
      top_k: 1,
      additional_params: {
      },
    },
    lite_llm_model_config: {
      model_id: "ModelId", # required
      api_key_arn: "ApiKeyArn",
      api_base: "HarnessLiteLlmApiBase",
      max_tokens: 1,
      temperature: 1.0,
      top_p: 1.0,
      additional_params: {
      },
    },
  },
  system_prompt: [
    {
      text: "SensitiveText",
    },
  ],
  tools: [
    {
      type: "remote_mcp", # required, accepts remote_mcp, agentcore_browser, agentcore_gateway, inline_function, agentcore_code_interpreter
      name: "HarnessToolName",
      config: {
        remote_mcp: {
          url: "HarnessRemoteMcpUrl", # required
          headers: {
            "HttpHeaderKey" => "HttpHeaderValue",
          },
        },
        agent_core_browser: {
          browser_arn: "HarnessBrowserArn",
        },
        agent_core_gateway: {
          gateway_arn: "GatewayArn", # required
          outbound_auth: {
            aws_iam: {
            },
            none: {
            },
            oauth: {
              provider_arn: "OAuthCredentialProviderArn", # required
              scopes: ["OAuthScope"], # required
              custom_parameters: {
                "OAuthCustomParametersKey" => "OAuthCustomParametersValue",
              },
              grant_type: "CLIENT_CREDENTIALS", # accepts CLIENT_CREDENTIALS, AUTHORIZATION_CODE, TOKEN_EXCHANGE
              default_return_url: "OAuthDefaultReturnUrl",
            },
          },
        },
        inline_function: {
          description: "HarnessInlineFunctionDescription", # required
          input_schema: { # required
          },
        },
        agent_core_code_interpreter: {
          code_interpreter_arn: "HarnessCodeInterpreterArn",
        },
      },
    },
  ],
  skills: [
    {
      path: "HarnessSkillPath",
      s3: {
        uri: "HarnessSkillS3Uri", # required
      },
      git: {
        url: "HarnessSkillGitUrl", # required
        path: "String",
        auth: {
          credential_arn: "ApiKeyArn", # required
          username: "String",
        },
      },
      aws_skills: {
        paths: ["HarnessAwsSkillPath"],
      },
    },
  ],
  allowed_tools: ["HarnessAllowedTool"],
  max_iterations: 1,
  max_tokens: 1,
  timeout_seconds: 1,
  actor_id: "String",
})

Response structure


# All events are available at resp.stream:
resp.stream #=> Enumerator
resp.stream.event_types #=> [:message_start, :content_block_start, :content_block_delta, :content_block_stop, :message_stop, :metadata, :internal_server_exception, :validation_exception, :runtime_client_error]

# For :message_start event available at #on_message_start_event callback and response eventstream enumerator:
event.role #=> String, one of "user", "assistant"

# For :content_block_start event available at #on_content_block_start_event callback and response eventstream enumerator:
event.content_block_index #=> Integer
event.start.tool_use.tool_use_id #=> String
event.start.tool_use.name #=> String
event.start.tool_use.type #=> String, one of "tool_use", "server_tool_use", "mcp_tool_use"
event.start.tool_use.server_name #=> String
event.start.tool_result.tool_use_id #=> String
event.start.tool_result.status #=> String, one of "success", "error"

# For :content_block_delta event available at #on_content_block_delta_event callback and response eventstream enumerator:
event.content_block_index #=> Integer
event.delta.text #=> String
event.delta.tool_use.input #=> String
event.delta.tool_result #=> Array
event.delta.tool_result[0].text #=> String
event.delta.reasoning_content.text #=> String
event.delta.reasoning_content.redacted_content #=> String
event.delta.reasoning_content.signature #=> String
event.delta.tool_result_metadata.metadata #=> String

# For :content_block_stop event available at #on_content_block_stop_event callback and response eventstream enumerator:
event.content_block_index #=> Integer

# For :message_stop event available at #on_message_stop_event callback and response eventstream enumerator:
event.stop_reason #=> String, one of "end_turn", "tool_use", "tool_result", "max_tokens", "stop_sequence", "content_filtered", "malformed_model_output", "malformed_tool_use", "interrupted", "partial_turn", "model_context_window_exceeded", "max_iterations_exceeded", "max_output_tokens_exceeded", "timeout_exceeded"

# For :metadata event available at #on_metadata_event callback and response eventstream enumerator:
event.usage.input_tokens #=> Integer
event.usage.output_tokens #=> Integer
event.usage.total_tokens #=> Integer
event.usage.cache_read_input_tokens #=> Integer
event.usage.cache_write_input_tokens #=> Integer
event.metrics.latency_ms #=> Integer

# For :internal_server_exception event available at #on_internal_server_exception_event callback and response eventstream enumerator:
event.message #=> String

# For :validation_exception event available at #on_validation_exception_event callback and response eventstream enumerator:
event.message #=> String
event.reason #=> String, one of "CannotParse", "FieldValidationFailed", "IdempotentParameterMismatchException", "EventInOtherSession", "ResourceConflict"
event.field_list #=> Array
event.field_list[0].name #=> String
event.field_list[0].message #=> String

# For :runtime_client_error event available at #on_runtime_client_error_event callback and response eventstream enumerator:
event.message #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :harness_arn (required, String) —

    The ARN of the harness to invoke.

  • :qualifier (String) —

    The endpoint name to invoke. If omitted, the DEFAULT endpoint is used.

  • :runtime_session_id (required, String) —

    The session ID for the invocation. Use the same session ID across requests to continue a conversation.

  • :runtime_user_id (String) —

    An identifier for the end user making the request. This value is passed through to the runtime container.

  • :trace_parent (String) —

    W3C trace context parent header containing version, trace ID, parent span ID, and trace flags.

  • :trace_state (String) —

    W3C trace context state header for vendor-specific trace information.

  • :trace_id (String) —

    Trace ID for maintaining observability through the operation.

  • :baggage (String) —

    W3C Baggage header for user-defined context propagation. Format: key1=value1,key2=value2

  • :messages (required, Array<Types::HarnessMessage>) —

    The messages to send to the agent.

  • :model (Types::HarnessModelConfiguration) —

    The model configuration to use for this invocation. If specified, overrides the harness default.

  • :system_prompt (Array<Types::HarnessSystemContentBlock>) —

    The system prompt to use for this invocation. If specified, overrides the harness default.

  • :tools (Array<Types::HarnessTool>) —

    The tools available to the agent for this invocation. If specified, overrides the harness default.

  • :skills (Array<Types::HarnessSkill>) —

    The skills available to the agent for this invocation. If specified, overrides the harness default.

  • :allowed_tools (Array<String>) —

    The tools that the agent is allowed to use for this invocation. If specified, overrides the harness default.

  • :max_iterations (Integer) —

    The maximum number of iterations the agent loop can execute. If specified, overrides the harness default.

  • :max_tokens (Integer) —

    The maximum number of tokens the agent can generate per iteration. If specified, overrides the harness default.

  • :timeout_seconds (Integer) —

    The maximum duration in seconds for the agent loop execution. If specified, overrides the harness default.

  • :actor_id (String) —

    The actor ID for memory operations. Overrides the actor ID configured on the harness.

Yields:

  • (event_stream_handler)

Returns:

See Also:



3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 3991

def invoke_harness(params = {}, options = {}, &block)
  params = params.dup
  event_stream_handler = case handler = params.delete(:event_stream_handler)
    when EventStreams::InvokeHarnessStreamOutput then handler
    when Proc then EventStreams::InvokeHarnessStreamOutput.new.tap(&handler)
    when nil then EventStreams::InvokeHarnessStreamOutput.new
    else
      msg = "expected :event_stream_handler to be a block or "\
            "instance of Aws::BedrockAgentCore::EventStreams::InvokeHarnessStreamOutput"\
            ", got `#{handler.inspect}` instead"
      raise ArgumentError, msg
    end

  yield(event_stream_handler) if block_given?

  req = build_request(:invoke_harness, params)

  req.context[:event_stream_handler] = event_stream_handler
  req.handlers.add(Aws::Binary::DecodeHandler, priority: 95)

  req.send_request(options, &block)
end

#list_ab_tests(params = {}) ⇒ Types::ListABTestsResponse

Lists all A/B tests in the account.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_ab_tests({
  max_results: 1,
  next_token: "String",
})

Response structure


resp.ab_tests #=> Array
resp.ab_tests[0].ab_test_id #=> String
resp.ab_tests[0].ab_test_arn #=> String
resp.ab_tests[0].name #=> String
resp.ab_tests[0].status #=> String, one of "CREATING", "ACTIVE", "CREATE_FAILED", "UPDATING", "UPDATE_FAILED", "DELETING", "DELETE_FAILED", "FAILED"
resp.ab_tests[0].execution_status #=> String, one of "PAUSED", "RUNNING", "STOPPED", "NOT_STARTED"
resp.ab_tests[0].description #=> String
resp.ab_tests[0].gateway_arn #=> String
resp.ab_tests[0].created_at #=> Time
resp.ab_tests[0].updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :max_results (Integer) —

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

  • :next_token (String) —

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

Returns:

See Also:



4060
4061
4062
4063
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4060

def list_ab_tests(params = {}, options = {})
  req = build_request(:list_ab_tests, params)
  req.send_request(options)
end

#list_actors(params = {}) ⇒ Types::ListActorsOutput

Lists all actors in an AgentCore Memory resource. We recommend using pagination to ensure that the operation returns quickly and successfully.

To use this operation, you must have the bedrock-agentcore:ListActors permission.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_actors({
  memory_id: "MemoryId", # required
  max_results: 1,
  next_token: "PaginationToken",
})

Response structure


resp.actor_summaries #=> Array
resp.actor_summaries[0].actor_id #=> String
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The identifier of the AgentCore Memory resource for which to list actors.

  • :max_results (Integer) —

    The maximum number of results to return in a single call. The default value is 20.

  • :next_token (String) —

    The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.

Returns:

See Also:



4110
4111
4112
4113
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4110

def list_actors(params = {}, options = {})
  req = build_request(:list_actors, params)
  req.send_request(options)
end

#list_batch_evaluations(params = {}) ⇒ Types::ListBatchEvaluationsResponse

Lists all batch evaluations in the account, providing summary information about each evaluation's status and configuration.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_batch_evaluations({
  max_results: 1,
  next_token: "String",
})

Response structure


resp.batch_evaluations #=> Array
resp.batch_evaluations[0].batch_evaluation_id #=> String
resp.batch_evaluations[0].batch_evaluation_arn #=> String
resp.batch_evaluations[0].batch_evaluation_name #=> String
resp.batch_evaluations[0].status #=> String, one of "PENDING", "IN_PROGRESS", "COMPLETED", "COMPLETED_WITH_ERRORS", "FAILED", "STOPPING", "STOPPED", "DELETING"
resp.batch_evaluations[0].created_at #=> Time
resp.batch_evaluations[0].description #=> String
resp.batch_evaluations[0].evaluators #=> Array
resp.batch_evaluations[0].evaluators[0].evaluator_id #=> String
resp.batch_evaluations[0].insights #=> Array
resp.batch_evaluations[0].insights[0].insight_id #=> String
resp.batch_evaluations[0].evaluation_results.number_of_sessions_completed #=> Integer
resp.batch_evaluations[0].evaluation_results.number_of_sessions_in_progress #=> Integer
resp.batch_evaluations[0].evaluation_results.number_of_sessions_failed #=> Integer
resp.batch_evaluations[0].evaluation_results.total_number_of_sessions #=> Integer
resp.batch_evaluations[0].evaluation_results.number_of_sessions_ignored #=> Integer
resp.batch_evaluations[0].evaluation_results.evaluator_summaries #=> Array
resp.batch_evaluations[0].evaluation_results.evaluator_summaries[0].evaluator_id #=> String
resp.batch_evaluations[0].evaluation_results.evaluator_summaries[0].statistics.average_score #=> Float
resp.batch_evaluations[0].evaluation_results.evaluator_summaries[0].total_evaluated #=> Integer
resp.batch_evaluations[0].evaluation_results.evaluator_summaries[0].total_failed #=> Integer
resp.batch_evaluations[0].error_details #=> Array
resp.batch_evaluations[0].error_details[0] #=> String
resp.batch_evaluations[0].kms_key_arn #=> String
resp.batch_evaluations[0].updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :max_results (Integer) —

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

  • :next_token (String) —

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

Returns:

See Also:



4177
4178
4179
4180
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4177

def list_batch_evaluations(params = {}, options = {})
  req = build_request(:list_batch_evaluations, params)
  req.send_request(options)
end

#list_browser_sessions(params = {}) ⇒ Types::ListBrowserSessionsResponse

Retrieves a list of browser sessions in Amazon Bedrock AgentCore that match the specified criteria. This operation returns summary information about each session, including identifiers, status, and timestamps.

You can filter the results by browser identifier and session status. The operation supports pagination to handle large result sets efficiently.

We recommend using pagination to ensure that the operation returns quickly and successfully when retrieving large numbers of sessions.

The following operations are related to ListBrowserSessions:

Examples:

Request syntax with placeholder values


resp = client.list_browser_sessions({
  browser_identifier: "String", # required
  max_results: 1,
  next_token: "NextToken",
  status: "READY", # accepts READY, TERMINATED
})

Response structure


resp.items #=> Array
resp.items[0].browser_identifier #=> String
resp.items[0].session_id #=> String
resp.items[0].name #=> String
resp.items[0].status #=> String, one of "READY", "TERMINATED"
resp.items[0].created_at #=> Time
resp.items[0].last_updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :browser_identifier (required, String) —

    The unique identifier of the browser to list sessions for. If specified, only sessions for this browser are returned. If not specified, sessions for all browsers are returned.

  • :max_results (Integer) —

    The maximum number of results to return in a single call. The default value is 10. Valid values range from 1 to 100. To retrieve the remaining results, make another call with the returned nextToken value.

  • :next_token (String) —

    The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results. If not specified, Amazon Bedrock AgentCore returns the first page of results.

  • :status (String) —

    The status of the browser sessions to list. Valid values include ACTIVE, STOPPING, and STOPPED. If not specified, sessions with any status are returned.

Returns:

See Also:



4256
4257
4258
4259
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4256

def list_browser_sessions(params = {}, options = {})
  req = build_request(:list_browser_sessions, params)
  req.send_request(options)
end

#list_code_interpreter_sessions(params = {}) ⇒ Types::ListCodeInterpreterSessionsResponse

Retrieves a list of code interpreter sessions in Amazon Bedrock AgentCore that match the specified criteria. This operation returns summary information about each session, including identifiers, status, and timestamps.

You can filter the results by code interpreter identifier and session status. The operation supports pagination to handle large result sets efficiently.

We recommend using pagination to ensure that the operation returns quickly and successfully when retrieving large numbers of sessions.

The following operations are related to ListCodeInterpreterSessions:

Examples:

Request syntax with placeholder values


resp = client.list_code_interpreter_sessions({
  code_interpreter_identifier: "String", # required
  max_results: 1,
  next_token: "NextToken",
  status: "READY", # accepts READY, TERMINATED
})

Response structure


resp.items #=> Array
resp.items[0].code_interpreter_identifier #=> String
resp.items[0].session_id #=> String
resp.items[0].name #=> String
resp.items[0].status #=> String, one of "READY", "TERMINATED"
resp.items[0].created_at #=> Time
resp.items[0].last_updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :code_interpreter_identifier (required, String) —

    The unique identifier of the code interpreter to list sessions for. If specified, only sessions for this code interpreter are returned. If not specified, sessions for all code interpreters are returned.

  • :max_results (Integer) —

    The maximum number of results to return in a single call. The default value is 10. Valid values range from 1 to 100. To retrieve the remaining results, make another call with the returned nextToken value.

  • :next_token (String) —

    The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results. If not specified, Amazon Bedrock AgentCore returns the first page of results.

  • :status (String) —

    The status of the code interpreter sessions to list. Valid values include ACTIVE, STOPPING, and STOPPED. If not specified, sessions with any status are returned.

Returns:

See Also:



4335
4336
4337
4338
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4335

def list_code_interpreter_sessions(params = {}, options = {})
  req = build_request(:list_code_interpreter_sessions, params)
  req.send_request(options)
end

#list_events(params = {}) ⇒ Types::ListEventsOutput

Lists events in an AgentCore Memory resource based on specified criteria. We recommend using pagination to ensure that the operation returns quickly and successfully.

To use this operation, you must have the bedrock-agentcore:ListEvents permission.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_events({
  memory_id: "MemoryId", # required
  session_id: "SessionId", # required
  actor_id: "ActorId", # required
  include_payloads: false,
  filter: {
    branch: {
      name: "BranchName", # required
      include_parent_branches: false,
    },
    event_metadata: [
      {
        left: { # required
          metadata_key: "MetadataKey",
        },
        operator: "EQUALS_TO", # required, accepts EQUALS_TO, EXISTS, NOT_EXISTS
        right: {
          metadata_value: {
            string_value: "MetadataValueStringValueString",
          },
        },
      },
    ],
  },
  max_results: 1,
  next_token: "PaginationToken",
})

Response structure


resp.events #=> Array
resp.events[0].memory_id #=> String
resp.events[0].actor_id #=> String
resp.events[0].session_id #=> String
resp.events[0].event_id #=> String
resp.events[0].event_timestamp #=> Time
resp.events[0].payload #=> Array
resp.events[0].payload[0].conversational.content.text #=> String
resp.events[0].payload[0].conversational.role #=> String, one of "ASSISTANT", "USER", "TOOL", "OTHER"
resp.events[0].branch.root_event_id #=> String
resp.events[0].branch.name #=> String
resp.events[0].metadata #=> Hash
resp.events[0].metadata["MetadataKey"].string_value #=> String
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The identifier of the AgentCore Memory resource for which to list events.

  • :session_id (required, String) —

    The identifier of the session for which to list events.

  • :actor_id (required, String) —

    The identifier of the actor for which to list events.

  • :include_payloads (Boolean) —

    Specifies whether to include event payloads in the response. Set to true to include payloads, or false to exclude them.

  • :filter (Types::FilterInput) —

    Filter criteria to apply when listing events.

  • :max_results (Integer) —

    The maximum number of results to return in a single call. The default value is 20.

  • :next_token (String) —

    The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.

Returns:

See Also:



4431
4432
4433
4434
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4431

def list_events(params = {}, options = {})
  req = build_request(:list_events, params)
  req.send_request(options)
end

#list_memory_extraction_jobs(params = {}) ⇒ Types::ListMemoryExtractionJobsOutput

Lists all long-term memory extraction jobs that are eligible to be started with optional filtering.

To use this operation, you must have the bedrock-agentcore:ListMemoryExtractionJobs permission.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_memory_extraction_jobs({
  memory_id: "MemoryId", # required
  max_results: 1,
  filter: {
    strategy_id: "String",
    session_id: "String",
    actor_id: "String",
    status: "FAILED", # accepts FAILED
  },
  next_token: "PaginationToken",
})

Response structure


resp.jobs #=> Array
resp.jobs[0].job_id #=> String
resp.jobs[0].messages.messages_list #=> Array
resp.jobs[0].messages.messages_list[0].event_id #=> String
resp.jobs[0].messages.messages_list[0].message_index #=> Integer
resp.jobs[0].status #=> String, one of "FAILED"
resp.jobs[0].failure_reason #=> String
resp.jobs[0].strategy_id #=> String
resp.jobs[0].session_id #=> String
resp.jobs[0].actor_id #=> String
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The unique identifier of the memory to list extraction jobs for.

  • :max_results (Integer) —

    The maximum number of results to return in a single call. The default value is 20.

  • :filter (Types::ExtractionJobFilterInput) —

    Filter criteria to apply when listing extraction jobs.

  • :next_token (String) —

    The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.

Returns:

See Also:



4496
4497
4498
4499
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4496

def list_memory_extraction_jobs(params = {}, options = {})
  req = build_request(:list_memory_extraction_jobs, params)
  req.send_request(options)
end

#list_memory_records(params = {}) ⇒ Types::ListMemoryRecordsOutput

Lists memory records in an AgentCore Memory resource based on specified criteria. We recommend using pagination to ensure that the operation returns quickly and successfully.

To use this operation, you must have the bedrock-agentcore:ListMemoryRecords permission.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_memory_records({
  memory_id: "MemoryId", # required
  namespace: "Namespace",
  namespace_path: "Namespace",
  memory_strategy_id: "MemoryStrategyId",
  max_results: 1,
  next_token: "PaginationToken",
  metadata_filters: [
    {
      left: { # required
        metadata_key: "MetadataKey",
      },
      operator: "EQUALS_TO", # required, accepts EQUALS_TO, EXISTS, NOT_EXISTS, BEFORE, AFTER, CONTAINS, GREATER_THAN, GREATER_THAN_OR_EQUALS, LESS_THAN, LESS_THAN_OR_EQUALS
      right: {
        metadata_value: {
          string_value: "StringValue",
          string_list_value: ["StringListMemberValue"],
          number_value: 1.0,
          date_time_value: Time.now,
        },
      },
    },
  ],
})

Response structure


resp.memory_record_summaries #=> Array
resp.memory_record_summaries[0].memory_record_id #=> String
resp.memory_record_summaries[0].content.text #=> String
resp.memory_record_summaries[0].memory_strategy_id #=> String
resp.memory_record_summaries[0].namespaces #=> Array
resp.memory_record_summaries[0].namespaces[0] #=> String
resp.memory_record_summaries[0].created_at #=> Time
resp.memory_record_summaries[0].score #=> Float
resp.memory_record_summaries[0].metadata #=> Hash
resp.memory_record_summaries[0].metadata["MetadataKey"].string_value #=> String
resp.memory_record_summaries[0].metadata["MetadataKey"].string_list_value #=> Array
resp.memory_record_summaries[0].metadata["MetadataKey"].string_list_value[0] #=> String
resp.memory_record_summaries[0].metadata["MetadataKey"].number_value #=> Float
resp.memory_record_summaries[0].metadata["MetadataKey"].date_time_value #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The identifier of the AgentCore Memory resource for which to list memory records.

  • :namespace (String) —

    The namespace prefix to filter memory records by. Returns all memory records in namespaces that start with the provided prefix. Either namespace or namespacePath is required.

  • :namespace_path (String) —

    Use namespacePath for hierarchical retrievals. Return all memory records where namespace falls under the same parent hierarchy. Either namespace or namespacePath is required.

  • :memory_strategy_id (String) —

    The memory strategy identifier to filter memory records by. If specified, only memory records with this strategy ID are returned.

  • :max_results (Integer) —

    The maximum number of results to return in a single call. The default value is 20.

  • :next_token (String) —

    The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.

  • :metadata_filters (Array<Types::MemoryMetadataFilterExpression>) —

    A list of metadata filter expressions to scope the returned memory records.

Returns:

See Also:



4595
4596
4597
4598
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4595

def list_memory_records(params = {}, options = {})
  req = build_request(:list_memory_records, params)
  req.send_request(options)
end

#list_payment_instruments(params = {}) ⇒ Types::ListPaymentInstrumentsResponse

List payment instruments for a manager.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_payment_instruments({
  user_id: "UserId",
  agent_name: "PaymentAgentName",
  payment_manager_arn: "PaymentManagerArn", # required
  payment_connector_id: "PaymentConnectorId",
  next_token: "NextToken",
  max_results: 1,
})

Response structure


resp.payment_instruments #=> Array
resp.payment_instruments[0].payment_instrument_id #=> String
resp.payment_instruments[0].payment_manager_arn #=> String
resp.payment_instruments[0].payment_connector_id #=> String
resp.payment_instruments[0].user_id #=> String
resp.payment_instruments[0].payment_instrument_type #=> String, one of "EMBEDDED_CRYPTO_WALLET"
resp.payment_instruments[0].status #=> String, one of "INITIATED", "ACTIVE", "FAILED", "DELETED"
resp.payment_instruments[0].created_at #=> Time
resp.payment_instruments[0].updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :user_id (String) —

    The user ID associated with the payment instruments.

  • :agent_name (String) —

    The agent name associated with this request, used for observability.

  • :payment_manager_arn (required, String) —

    The ARN of the payment manager that owns the payment instruments.

  • :payment_connector_id (String) —

    The ID of the payment connector to filter by.

  • :next_token (String) —

    Token for pagination to retrieve the next set of results.

  • :max_results (Integer) —

    Maximum number of results to return in a single response.

Returns:

See Also:



4655
4656
4657
4658
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4655

def list_payment_instruments(params = {}, options = {})
  req = build_request(:list_payment_instruments, params)
  req.send_request(options)
end

#list_payment_sessions(params = {}) ⇒ Types::ListPaymentSessionsResponse

List payment sessions.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_payment_sessions({
  user_id: "UserId",
  agent_name: "PaymentAgentName",
  payment_manager_arn: "PaymentManagerArn", # required
  next_token: "NextToken",
  max_results: 1,
})

Response structure


resp.payment_sessions #=> Array
resp.payment_sessions[0].payment_session_id #=> String
resp.payment_sessions[0].payment_manager_arn #=> String
resp.payment_sessions[0].user_id #=> String
resp.payment_sessions[0].expiry_time_in_minutes #=> Integer
resp.payment_sessions[0].created_at #=> Time
resp.payment_sessions[0].updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :user_id (String) —

    The user ID associated with the payment sessions.

  • :agent_name (String) —

    The agent name associated with this request, used for observability.

  • :payment_manager_arn (required, String) —

    The ARN of the payment manager that owns the sessions.

  • :next_token (String) —

    Token for pagination to retrieve the next set of results.

  • :max_results (Integer) —

    Maximum number of results to return in a single response.

Returns:

See Also:



4709
4710
4711
4712
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4709

def list_payment_sessions(params = {}, options = {})
  req = build_request(:list_payment_sessions, params)
  req.send_request(options)
end

#list_recommendations(params = {}) ⇒ Types::ListRecommendationsResponse

Lists all recommendations in the account, with optional filtering by status.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_recommendations({
  max_results: 1,
  next_token: "NextToken",
  status_filter: "PENDING", # accepts PENDING, IN_PROGRESS, COMPLETED, FAILED, DELETING
})

Response structure


resp.recommendation_summaries #=> Array
resp.recommendation_summaries[0].recommendation_id #=> String
resp.recommendation_summaries[0].recommendation_arn #=> String
resp.recommendation_summaries[0].name #=> String
resp.recommendation_summaries[0].description #=> String
resp.recommendation_summaries[0].type #=> String, one of "SYSTEM_PROMPT_RECOMMENDATION", "TOOL_DESCRIPTION_RECOMMENDATION"
resp.recommendation_summaries[0].status #=> String, one of "PENDING", "IN_PROGRESS", "COMPLETED", "FAILED", "DELETING"
resp.recommendation_summaries[0].created_at #=> Time
resp.recommendation_summaries[0].updated_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :max_results (Integer) —

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

  • :next_token (String) —

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

  • :status_filter (String) —

    Optional filter to return only recommendations with the specified status.

Returns:

See Also:



4765
4766
4767
4768
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4765

def list_recommendations(params = {}, options = {})
  req = build_request(:list_recommendations, params)
  req.send_request(options)
end

#list_sessions(params = {}) ⇒ Types::ListSessionsOutput

Lists sessions in an AgentCore Memory resource based on specified criteria. We recommend using pagination to ensure that the operation returns quickly and successfully.

Empty sessions are automatically deleted after one day.

To use this operation, you must have the bedrock-agentcore:ListSessions permission.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.list_sessions({
  memory_id: "MemoryId", # required
  actor_id: "ActorId", # required
  max_results: 1,
  next_token: "PaginationToken",
  filter: {
    event_filter: "HAS_EVENTS", # accepts HAS_EVENTS
  },
})

Response structure


resp.session_summaries #=> Array
resp.session_summaries[0].session_id #=> String
resp.session_summaries[0].actor_id #=> String
resp.session_summaries[0].created_at #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The identifier of the AgentCore Memory resource for which to list sessions.

  • :actor_id (required, String) —

    The identifier of the actor for which to list sessions.

  • :max_results (Integer) —

    The maximum number of results to return in a single call. The default value is 20.

  • :next_token (String) —

    The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.

  • :filter (Types::SessionFilter) —

    Filter criteria to apply when listing sessions.

Returns:

See Also:



4829
4830
4831
4832
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4829

def list_sessions(params = {}, options = {})
  req = build_request(:list_sessions, params)
  req.send_request(options)
end

#process_payment(params = {}) ⇒ Types::ProcessPaymentResponse

Processes a payment using a payment instrument within a payment session.

Examples:

Request syntax with placeholder values


resp = client.process_payment({
  user_id: "UserId",
  agent_name: "PaymentAgentName",
  payment_manager_arn: "PaymentManagerArn", # required
  payment_session_id: "PaymentSessionId", # required
  payment_instrument_id: "PaymentInstrumentId", # required
  payment_type: "CRYPTO_X402", # required, accepts CRYPTO_X402
  payment_input: { # required
    crypto_x402: {
      version: "String", # required
      payload: { # required
      },
    },
  },
  client_token: "ClientToken",
})

Response structure


resp.process_payment_id #=> String
resp.payment_manager_arn #=> String
resp.payment_session_id #=> String
resp.payment_instrument_id #=> String
resp.payment_type #=> String, one of "CRYPTO_X402"
resp.status #=> String, one of "PROOF_GENERATED"
resp.payment_output.crypto_x402.version #=> String
resp.created_at #=> Time
resp.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :user_id (String) —

    The user ID associated with this payment.

  • :agent_name (String) —

    The agent name associated with this request, used for observability.

  • :payment_manager_arn (required, String) —

    The ARN of the payment manager.

  • :payment_session_id (required, String) —

    The ID of the payment session.

  • :payment_instrument_id (required, String) —

    The ID of the payment instrument to use.

  • :payment_type (required, String) —

    The type of payment to process.

  • :payment_input (required, Types::PaymentInput) —

    The payment input details specific to the payment type.

  • :client_token (String) —

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

    A suitable default value is auto-generated. You should normally not need to pass this option.**

Returns:

See Also:



4912
4913
4914
4915
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 4912

def process_payment(params = {}, options = {})
  req = build_request(:process_payment, params)
  req.send_request(options)
end

#retrieve_memory_records(params = {}) ⇒ Types::RetrieveMemoryRecordsOutput

Searches for and retrieves memory records from an AgentCore Memory resource based on specified search criteria. We recommend using pagination to ensure that the operation returns quickly and successfully.

To use this operation, you must have the bedrock-agentcore:RetrieveMemoryRecords permission.

The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.

Examples:

Request syntax with placeholder values


resp = client.retrieve_memory_records({
  memory_id: "MemoryId", # required
  namespace: "Namespace",
  namespace_path: "Namespace",
  search_criteria: { # required
    search_query: "SearchCriteriaSearchQueryString", # required
    memory_strategy_id: "MemoryStrategyId",
    top_k: 1,
    metadata_filters: [
      {
        left: { # required
          metadata_key: "MetadataKey",
        },
        operator: "EQUALS_TO", # required, accepts EQUALS_TO, EXISTS, NOT_EXISTS, BEFORE, AFTER, CONTAINS, GREATER_THAN, GREATER_THAN_OR_EQUALS, LESS_THAN, LESS_THAN_OR_EQUALS
        right: {
          metadata_value: {
            string_value: "StringValue",
            string_list_value: ["StringListMemberValue"],
            number_value: 1.0,
            date_time_value: Time.now,
          },
        },
      },
    ],
  },
  next_token: "PaginationToken",
  max_results: 1,
})

Response structure


resp.memory_record_summaries #=> Array
resp.memory_record_summaries[0].memory_record_id #=> String
resp.memory_record_summaries[0].content.text #=> String
resp.memory_record_summaries[0].memory_strategy_id #=> String
resp.memory_record_summaries[0].namespaces #=> Array
resp.memory_record_summaries[0].namespaces[0] #=> String
resp.memory_record_summaries[0].created_at #=> Time
resp.memory_record_summaries[0].score #=> Float
resp.memory_record_summaries[0].metadata #=> Hash
resp.memory_record_summaries[0].metadata["MetadataKey"].string_value #=> String
resp.memory_record_summaries[0].metadata["MetadataKey"].string_list_value #=> Array
resp.memory_record_summaries[0].metadata["MetadataKey"].string_list_value[0] #=> String
resp.memory_record_summaries[0].metadata["MetadataKey"].number_value #=> Float
resp.memory_record_summaries[0].metadata["MetadataKey"].date_time_value #=> Time
resp.next_token #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The identifier of the AgentCore Memory resource from which to retrieve memory records.

  • :namespace (String) —

    The namespace prefix to filter memory records by. Searches for memory records in namespaces that start with the provided prefix. Either namespace or namespacePath is required.

  • :namespace_path (String) —

    Use namespacePath for hierarchical retrievals. Return all memory records where namespace falls under the same parent hierarchy. Either namespace or namespacePath is required.

  • :search_criteria (required, Types::SearchCriteria) —

    The search criteria to use for finding relevant memory records. This includes the search query, memory strategy ID, and other search parameters.

  • :next_token (String) —

    The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.

  • :max_results (Integer) —

    The maximum number of results to return in a single call. The default value is 20.

Returns:

See Also:



5013
5014
5015
5016
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 5013

def retrieve_memory_records(params = {}, options = {})
  req = build_request(:retrieve_memory_records, params)
  req.send_request(options)
end

#save_browser_session_profile(params = {}) ⇒ Types::SaveBrowserSessionProfileResponse

Saves the current state of a browser session as a reusable profile in Amazon Bedrock AgentCore. A browser profile captures persistent browser data such as cookies and local storage from an active session, enabling you to reuse this data in future browser sessions.

To save a browser session profile, you must specify the profile identifier, browser identifier, and session ID. The session must be active when saving the profile. Once saved, the profile can be used with the StartBrowserSession operation to initialize new sessions with the stored browser state.

Browser profiles are useful for scenarios that require persistent authentication, maintaining user preferences across sessions, or continuing tasks that depend on previously stored browser data.

The following operations are related to SaveBrowserSessionProfile:

Examples:

Request syntax with placeholder values


resp = client.save_browser_session_profile({
  trace_id: "SaveBrowserSessionProfileRequestTraceIdString",
  trace_parent: "SaveBrowserSessionProfileRequestTraceParentString",
  profile_identifier: "BrowserProfileId", # required
  browser_identifier: "String", # required
  session_id: "BrowserSessionId", # required
  client_token: "ClientToken",
})

Response structure


resp.profile_identifier #=> String
resp.browser_identifier #=> String
resp.session_id #=> String
resp.last_updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :trace_id (String) —

    The trace identifier for request tracking.

  • :trace_parent (String) —

    The parent trace information for distributed tracing.

  • :profile_identifier (required, String) —

    The unique identifier for the browser profile. This identifier is used to reference the profile when starting new browser sessions. The identifier must follow the pattern of an alphanumeric name (up to 48 characters) followed by a hyphen and a 10-character alphanumeric suffix.

  • :browser_identifier (required, String) —

    The unique identifier of the browser associated with the session from which to save the profile.

  • :session_id (required, String) —

    The unique identifier of the browser session from which to save the profile. The session must be active when saving the profile.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock AgentCore ignores the request, but does not return an error.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

Returns:

See Also:



5103
5104
5105
5106
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 5103

def save_browser_session_profile(params = {}, options = {})
  req = build_request(:save_browser_session_profile, params)
  req.send_request(options)
end

#search_registry_records(params = {}) ⇒ Types::SearchRegistryRecordsResponse

Searches for registry records using semantic, lexical, or hybrid queries. Returns metadata for matching records ordered by relevance within the specified registry.

Examples:

Request syntax with placeholder values


resp = client.search_registry_records({
  search_query: "SearchRegistryRecordsRequestSearchQueryString", # required
  registry_ids: ["RegistryIdentifier"], # required
  max_results: 1,
  filters: {
  },
})

Response structure


resp.registry_records #=> Array
resp.registry_records[0].registry_arn #=> String
resp.registry_records[0].record_arn #=> String
resp.registry_records[0].record_id #=> String
resp.registry_records[0].name #=> String
resp.registry_records[0].description #=> String
resp.registry_records[0].descriptor_type #=> String, one of "MCP", "A2A", "CUSTOM", "AGENT_SKILLS"
resp.registry_records[0].descriptors.mcp.server.schema_version #=> String
resp.registry_records[0].descriptors.mcp.server.inline_content #=> String
resp.registry_records[0].descriptors.mcp.tools.protocol_version #=> String
resp.registry_records[0].descriptors.mcp.tools.inline_content #=> String
resp.registry_records[0].descriptors.a2a.agent_card.schema_version #=> String
resp.registry_records[0].descriptors.a2a.agent_card.inline_content #=> String
resp.registry_records[0].descriptors.custom.inline_content #=> String
resp.registry_records[0].descriptors.agent_skills.skill_md.inline_content #=> String
resp.registry_records[0].descriptors.agent_skills.skill_definition.schema_version #=> String
resp.registry_records[0].descriptors.agent_skills.skill_definition.inline_content #=> String
resp.registry_records[0].version #=> String
resp.registry_records[0].status #=> String, one of "DRAFT", "PENDING_APPROVAL", "APPROVED", "REJECTED", "DEPRECATED"
resp.registry_records[0].created_at #=> Time
resp.registry_records[0].updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :search_query (required, String) —

    The search query to find matching registry records.

  • :registry_ids (required, Array<String>) —

    The list of registry identifiers to search within. Currently, you can specify exactly one registry identifier. You can provide either the full Amazon Web Services Resource Name (ARN) or the 12-character alphanumeric registry ID.

  • :max_results (Integer) —

    The maximum number of records to return in a single call. Valid values are 1 through 20. The default value is 10.

  • :filters (Hash, Array, String, Numeric, Boolean) —

    A metadata filter expression to narrow search results. Uses structured JSON operators including field-level operators ($eq, $ne, $in) and logical operators ($and, $or) on filterable fields (name, descriptorType, version). For example, to filter by descriptor type: {"descriptorType": {"$eq": "MCP"}}. To combine filters: {"$and": [{"descriptorType": {"$eq": "MCP"}}, {"name": {"$eq": "my-tool"}}]}.

    Document type used to carry open content (Hash,Array,String,Numeric,Boolean). A document type value is serialized using the same format as its surroundings and requires no additional encoding or escaping.

Returns:

See Also:



5181
5182
5183
5184
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 5181

def search_registry_records(params = {}, options = {})
  req = build_request(:search_registry_records, params)
  req.send_request(options)
end

#start_batch_evaluation(params = {}) ⇒ Types::StartBatchEvaluationResponse

Starts a batch evaluation job that evaluates agent performance across multiple sessions. Batch evaluations pull agent traces from CloudWatch Logs or an existing online evaluation configuration and run specified evaluators and insights against them.

Examples:

Request syntax with placeholder values


resp = client.start_batch_evaluation({
  batch_evaluation_name: "BatchEvaluationName", # required
  evaluators: [
    {
      evaluator_id: "EvaluatorId", # required
    },
  ],
  insights: [
    {
      insight_id: "InsightId", # required
    },
  ],
  data_source_config: { # required
    cloud_watch_logs: {
      service_names: ["String"], # required
      log_group_names: ["String"], # required
      filter_config: {
        session_ids: ["String"],
        time_range: {
          start_time: Time.now,
          end_time: Time.now,
        },
      },
    },
    online_evaluation_config_source: {
      online_evaluation_config_arn: "OnlineEvaluationConfigArn", # required
      time_range: {
        start_time: Time.now,
        end_time: Time.now,
      },
    },
  },
  client_token: "ClientToken",
  evaluation_metadata: {
    session_metadata: [
      {
        session_id: "String", # required
        test_scenario_id: "String",
        ground_truth: {
          inline: {
            assertions: [
              {
                text: "EvaluationContentTextString",
              },
            ],
            expected_trajectory: {
              tool_names: ["EvaluationToolName"],
            },
            turns: [
              {
                input: {
                  prompt: "GroundTruthTurnInputPromptString",
                },
                expected_response: {
                  text: "EvaluationContentTextString",
                },
              },
            ],
          },
        },
        metadata: {
          "String" => "String",
        },
      },
    ],
  },
  tags: {
    "TagKey" => "TagValue",
  },
  kms_key_arn: "KmsKeyArn",
  description: "BatchEvaluationDescription",
})

Response structure


resp.batch_evaluation_id #=> String
resp.batch_evaluation_arn #=> String
resp.batch_evaluation_name #=> String
resp.evaluators #=> Array
resp.evaluators[0].evaluator_id #=> String
resp.insights #=> Array
resp.insights[0].insight_id #=> String
resp.status #=> String, one of "PENDING", "IN_PROGRESS", "COMPLETED", "COMPLETED_WITH_ERRORS", "FAILED", "STOPPING", "STOPPED", "DELETING"
resp.created_at #=> Time
resp.output_config.cloud_watch_config.log_group_name #=> String
resp.output_config.cloud_watch_config.log_stream_name #=> String
resp.tags #=> Hash
resp.tags["TagKey"] #=> String
resp.kms_key_arn #=> String
resp.description #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :batch_evaluation_name (required, String) —

    The name of the batch evaluation. Must be unique within your account.

  • :evaluators (Array<Types::Evaluator>) —

    The list of evaluators to apply during the batch evaluation. Can include both built-in evaluators and custom evaluators. Maximum of 10 evaluators.

  • :insights (Array<Types::Insight>) —

    The list of insight analyses to run against sessions during the batch evaluation. Maximum of 10 insights.

  • :data_source_config (required, Types::DataSourceConfig) —

    The data source configuration that specifies where to pull agent session traces from for evaluation.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, the service ignores the request, but does not return an error.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :evaluation_metadata (Types::EvaluationMetadata) —

    Optional metadata for the evaluation, including session-specific ground truth data and test scenario identifiers.

  • :tags (Hash<String,String>) —

    A map of tag keys and values to associate with the batch evaluation.

  • :kms_key_arn (String) —

    The ARN of the KMS key used to encrypt evaluation data. If provided, customer data is encrypted at rest with the specified key.

  • :description (String) —

    The description of the batch evaluation.

Returns:

See Also:



5341
5342
5343
5344
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 5341

def start_batch_evaluation(params = {}, options = {})
  req = build_request(:start_batch_evaluation, params)
  req.send_request(options)
end

#start_browser_session(params = {}) ⇒ Types::StartBrowserSessionResponse

Creates and initializes a browser session in Amazon Bedrock AgentCore. The session enables agents to navigate and interact with web content, extract information from websites, and perform web-based tasks as part of their response generation.

To create a session, you must specify a browser identifier and a name. You can also configure the viewport dimensions to control the visible area of web content. The session remains active until it times out or you explicitly stop it using the StopBrowserSession operation.

The following operations are related to StartBrowserSession:

Examples:

Request syntax with placeholder values


resp = client.start_browser_session({
  trace_id: "StartBrowserSessionRequestTraceIdString",
  trace_parent: "StartBrowserSessionRequestTraceParentString",
  browser_identifier: "String", # required
  name: "Name",
  session_timeout_seconds: 1,
  view_port: {
    width: 1, # required
    height: 1, # required
  },
  extensions: [
    {
      location: { # required
        s3: {
          bucket: "S3LocationBucketString", # required
          prefix: "S3LocationPrefixString", # required
          version_id: "S3LocationVersionIdString",
        },
      },
    },
  ],
  profile_configuration: {
    profile_identifier: "BrowserProfileId", # required
  },
  proxy_configuration: {
    proxies: [ # required
      {
        external_proxy: {
          server: "HostName", # required
          port: 1, # required
          domain_patterns: ["DomainPattern"],
          credentials: {
            basic_auth: {
              secret_arn: "SecretArn", # required
            },
          },
        },
      },
    ],
    bypass: {
      domain_patterns: ["DomainPattern"],
    },
  },
  enterprise_policies: [
    {
      location: { # required
        s3: {
          bucket: "S3LocationBucketString", # required
          prefix: "S3LocationPrefixString", # required
          version_id: "S3LocationVersionIdString",
        },
      },
      type: "MANAGED", # accepts MANAGED, RECOMMENDED
    },
  ],
  certificates: [
    {
      location: { # required
        secrets_manager: {
          secret_arn: "SecretArn", # required
        },
      },
    },
  ],
  filesystem_configurations: [
    {
      s3_files_configuration: {
        access_point_arn: "S3FilesAccessPointArn", # required
        mount_path: "MountPath", # required
        file_system_arn: "S3FilesFileSystemArn", # required
      },
      efs_configuration: {
        access_point_arn: "EfsAccessPointArn", # required
        mount_path: "MountPath", # required
        file_system_arn: "EfsFileSystemArn", # required
      },
    },
  ],
  client_token: "ClientToken",
})

Response structure


resp.browser_identifier #=> String
resp.session_id #=> String
resp.created_at #=> Time
resp.streams.automation_stream.stream_endpoint #=> String
resp.streams.automation_stream.stream_status #=> String, one of "ENABLED", "DISABLED"
resp.streams.live_view_stream.stream_endpoint #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :trace_id (String) —

    The trace identifier for request tracking.

  • :trace_parent (String) —

    The parent trace information for distributed tracing.

  • :browser_identifier (required, String) —

    The unique identifier of the browser to use for this session. This identifier specifies which browser environment to initialize for the session.

  • :name (String) —

    The name of the browser session. This name helps you identify and manage the session. The name does not need to be unique.

  • :session_timeout_seconds (Integer) —

    The duration in seconds (time-to-live) after which the session automatically terminates, regardless of ongoing activity. Defaults to 3600 seconds (1 hour). Recommended minimum: 60 seconds. Maximum allowed: 28,800 seconds (8 hours).

  • :view_port (Types::ViewPort) —

    The dimensions of the browser viewport for this session. This determines the visible area of the web content and affects how web pages are rendered. If not specified, Amazon Bedrock AgentCore uses a default viewport size.

  • :extensions (Array<Types::BrowserExtension>) —

    A list of browser extensions to load into the browser session.

  • :profile_configuration (Types::BrowserProfileConfiguration) —

    The browser profile configuration to use for this session. A browser profile contains persistent data such as cookies and local storage that can be reused across multiple browser sessions. If specified, the session initializes with the profile's stored data, enabling continuity for tasks that require authentication or personalized settings.

  • :proxy_configuration (Types::ProxyConfiguration) —

    Optional proxy configuration for routing browser traffic through customer-specified proxy servers. When provided, enables HTTP Basic authentication via Amazon Web Services Secrets Manager and domain-based routing rules. Requires secretsmanager:GetSecretValue IAM permission for the specified secret ARNs.

  • :enterprise_policies (Array<Types::BrowserEnterprisePolicy>) —

    A list of files containing enterprise policies for the browser.

  • :certificates (Array<Types::Certificate>) —

    A list of certificates to install in the browser session.

  • :filesystem_configurations (Array<Types::ToolsFileSystemConfiguration>) —

    The file system configurations to mount into the browser session. Use these configurations to mount your own Amazon Simple Storage Service (Amazon S3) Files or Amazon Elastic File System (Amazon EFS) access points. Your session can then read and write your data. If you don't specify this field, no additional file systems are mounted.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock AgentCore ignores the request, but does not return an error. This parameter helps prevent the creation of duplicate sessions if there are temporary network issues.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

Returns:

See Also:



5547
5548
5549
5550
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 5547

def start_browser_session(params = {}, options = {})
  req = build_request(:start_browser_session, params)
  req.send_request(options)
end

#start_code_interpreter_session(params = {}) ⇒ Types::StartCodeInterpreterSessionResponse

Creates and initializes a code interpreter session in Amazon Bedrock AgentCore. The session enables agents to execute code as part of their response generation, supporting programming languages such as Python for data analysis, visualization, and computation tasks.

To create a session, you must specify a code interpreter identifier and a name. The session remains active until it times out or you explicitly stop it using the StopCodeInterpreterSession operation.

The following operations are related to StartCodeInterpreterSession:

Examples:

Request syntax with placeholder values


resp = client.start_code_interpreter_session({
  trace_id: "StartCodeInterpreterSessionRequestTraceIdString",
  trace_parent: "StartCodeInterpreterSessionRequestTraceParentString",
  code_interpreter_identifier: "String", # required
  name: "Name",
  session_timeout_seconds: 1,
  certificates: [
    {
      location: { # required
        secrets_manager: {
          secret_arn: "SecretArn", # required
        },
      },
    },
  ],
  filesystem_configurations: [
    {
      s3_files_configuration: {
        access_point_arn: "S3FilesAccessPointArn", # required
        mount_path: "MountPath", # required
        file_system_arn: "S3FilesFileSystemArn", # required
      },
      efs_configuration: {
        access_point_arn: "EfsAccessPointArn", # required
        mount_path: "MountPath", # required
        file_system_arn: "EfsFileSystemArn", # required
      },
    },
  ],
  client_token: "ClientToken",
})

Response structure


resp.code_interpreter_identifier #=> String
resp.session_id #=> String
resp.created_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :trace_id (String) —

    The trace identifier for request tracking.

  • :trace_parent (String) —

    The parent trace information for distributed tracing.

  • :code_interpreter_identifier (required, String) —

    The unique identifier of the code interpreter to use for this session. This identifier specifies which code interpreter environment to initialize for the session.

  • :name (String) —

    The name of the code interpreter session. This name helps you identify and manage the session. The name does not need to be unique.

  • :session_timeout_seconds (Integer) —

    The duration in seconds (time-to-live) after which the session automatically terminates, regardless of ongoing activity. Defaults to 900 seconds (15 minutes). Recommended minimum: 60 seconds. Maximum allowed: 28,800 seconds (8 hours).

  • :certificates (Array<Types::Certificate>) —

    A list of certificates to install in the code interpreter session.

  • :filesystem_configurations (Array<Types::ToolsFileSystemConfiguration>) —

    The file system configurations to mount into the code interpreter session. Use these configurations to mount your own Amazon Simple Storage Service (Amazon S3) Files or Amazon Elastic File System (Amazon EFS) access points. Your session can then read and write your data. If you don't specify this field, no additional file systems are mounted.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock AgentCore ignores the request, but does not return an error. This parameter helps prevent the creation of duplicate sessions if there are temporary network issues.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

Returns:

See Also:



5667
5668
5669
5670
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 5667

def start_code_interpreter_session(params = {}, options = {})
  req = build_request(:start_code_interpreter_session, params)
  req.send_request(options)
end

#start_memory_extraction_job(params = {}) ⇒ Types::StartMemoryExtractionJobOutput

Starts a memory extraction job that processes events that failed extraction previously in an AgentCore Memory resource and produces structured memory records. When earlier extraction attempts have left events unprocessed, this job will pick up and extract those as well.

To use this operation, you must have the bedrock-agentcore:StartMemoryExtractionJob permission.

Examples:

Request syntax with placeholder values


resp = client.start_memory_extraction_job({
  memory_id: "MemoryId", # required
  extraction_job: { # required
    job_id: "String", # required
  },
  client_token: "String",
})

Response structure


resp.job_id #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :memory_id (required, String) —

    The unique identifier of the memory for which to start extraction jobs.

  • :extraction_job (required, Types::ExtractionJob) —

    Extraction job to start in this operation.

  • :client_token (String) —

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

    A suitable default value is auto-generated. You should normally not need to pass this option.**

Returns:

See Also:



5716
5717
5718
5719
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 5716

def start_memory_extraction_job(params = {}, options = {})
  req = build_request(:start_memory_extraction_job, params)
  req.send_request(options)
end

#start_recommendation(params = {}) ⇒ Types::StartRecommendationResponse

Starts a recommendation job that analyzes agent traces and generates optimization suggestions for system prompts or tool descriptions to improve agent performance.

Examples:

Request syntax with placeholder values


resp = client.start_recommendation({
  name: "RecommendationName", # required
  description: "RecommendationDescription",
  type: "SYSTEM_PROMPT_RECOMMENDATION", # required, accepts SYSTEM_PROMPT_RECOMMENDATION, TOOL_DESCRIPTION_RECOMMENDATION
  recommendation_config: { # required
    system_prompt_recommendation_config: {
      system_prompt: { # required
        text: "SystemPromptText",
        configuration_bundle: {
          bundle_arn: "ConfigurationBundleArn", # required
          version_id: "ConfigurationBundleVersionId", # required
          system_prompt_json_path: "String", # required
        },
      },
      agent_traces: { # required
        session_spans: [
          {
          },
        ],
        cloudwatch_logs: {
          log_group_arns: ["String"], # required
          service_names: ["ServiceName"], # required
          start_time: Time.now, # required
          end_time: Time.now, # required
          rule: {
            filters: [
              {
                key: "CloudWatchLogsFilterKeyString", # required
                operator: "Equals", # required, accepts Equals, NotEquals, GreaterThan, LessThan, GreaterThanOrEqual, LessThanOrEqual, Contains, NotContains
                value: { # required
                  string_value: "FilterStringValue",
                  double_value: 1.0,
                  boolean_value: false,
                },
              },
            ],
          },
        },
        batch_evaluation: {
          batch_evaluation_arn: "BatchEvaluationArn", # required
        },
      },
      evaluation_config: {
        evaluators: [ # required
          {
            evaluator_arn: "EvaluatorArn", # required
          },
        ],
      },
    },
    tool_description_recommendation_config: {
      tool_description: { # required
        tool_description_text: {
          tools: [ # required
            {
              tool_name: "RecommendationToolName", # required
              tool_description: { # required
                text: "ToolDescriptionText",
              },
            },
          ],
        },
        configuration_bundle: {
          bundle_arn: "ConfigurationBundleArn", # required
          version_id: "ConfigurationBundleVersionId", # required
          tools: [ # required
            {
              tool_name: "RecommendationToolName", # required
              tool_description_json_path: "String", # required
            },
          ],
        },
      },
      agent_traces: { # required
        session_spans: [
          {
          },
        ],
        cloudwatch_logs: {
          log_group_arns: ["String"], # required
          service_names: ["ServiceName"], # required
          start_time: Time.now, # required
          end_time: Time.now, # required
          rule: {
            filters: [
              {
                key: "CloudWatchLogsFilterKeyString", # required
                operator: "Equals", # required, accepts Equals, NotEquals, GreaterThan, LessThan, GreaterThanOrEqual, LessThanOrEqual, Contains, NotContains
                value: { # required
                  string_value: "FilterStringValue",
                  double_value: 1.0,
                  boolean_value: false,
                },
              },
            ],
          },
        },
        batch_evaluation: {
          batch_evaluation_arn: "BatchEvaluationArn", # required
        },
      },
    },
  },
  kms_key_arn: "KmsKeyArn",
  client_token: "ClientToken",
  tags: {
    "TagKey" => "TagValue",
  },
})

Response structure


resp.recommendation_id #=> String
resp.recommendation_arn #=> String
resp.name #=> String
resp.description #=> String
resp.type #=> String, one of "SYSTEM_PROMPT_RECOMMENDATION", "TOOL_DESCRIPTION_RECOMMENDATION"
resp.recommendation_config.system_prompt_recommendation_config.system_prompt.text #=> String
resp.recommendation_config.system_prompt_recommendation_config.system_prompt.configuration_bundle.bundle_arn #=> String
resp.recommendation_config.system_prompt_recommendation_config.system_prompt.configuration_bundle.version_id #=> String
resp.recommendation_config.system_prompt_recommendation_config.system_prompt.configuration_bundle.system_prompt_json_path #=> String
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.session_spans #=> Array
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.log_group_arns #=> Array
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.log_group_arns[0] #=> String
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.service_names #=> Array
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.service_names[0] #=> String
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.start_time #=> Time
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.end_time #=> Time
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.rule.filters #=> Array
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].key #=> String
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].operator #=> String, one of "Equals", "NotEquals", "GreaterThan", "LessThan", "GreaterThanOrEqual", "LessThanOrEqual", "Contains", "NotContains"
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].value.string_value #=> String
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].value.double_value #=> Float
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].value.boolean_value #=> Boolean
resp.recommendation_config.system_prompt_recommendation_config.agent_traces.batch_evaluation.batch_evaluation_arn #=> String
resp.recommendation_config.system_prompt_recommendation_config.evaluation_config.evaluators #=> Array
resp.recommendation_config.system_prompt_recommendation_config.evaluation_config.evaluators[0].evaluator_arn #=> String
resp.recommendation_config.tool_description_recommendation_config.tool_description.tool_description_text.tools #=> Array
resp.recommendation_config.tool_description_recommendation_config.tool_description.tool_description_text.tools[0].tool_name #=> String
resp.recommendation_config.tool_description_recommendation_config.tool_description.tool_description_text.tools[0].tool_description.text #=> String
resp.recommendation_config.tool_description_recommendation_config.tool_description.configuration_bundle.bundle_arn #=> String
resp.recommendation_config.tool_description_recommendation_config.tool_description.configuration_bundle.version_id #=> String
resp.recommendation_config.tool_description_recommendation_config.tool_description.configuration_bundle.tools #=> Array
resp.recommendation_config.tool_description_recommendation_config.tool_description.configuration_bundle.tools[0].tool_name #=> String
resp.recommendation_config.tool_description_recommendation_config.tool_description.configuration_bundle.tools[0].tool_description_json_path #=> String
resp.recommendation_config.tool_description_recommendation_config.agent_traces.session_spans #=> Array
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.log_group_arns #=> Array
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.log_group_arns[0] #=> String
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.service_names #=> Array
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.service_names[0] #=> String
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.start_time #=> Time
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.end_time #=> Time
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.rule.filters #=> Array
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].key #=> String
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].operator #=> String, one of "Equals", "NotEquals", "GreaterThan", "LessThan", "GreaterThanOrEqual", "LessThanOrEqual", "Contains", "NotContains"
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].value.string_value #=> String
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].value.double_value #=> Float
resp.recommendation_config.tool_description_recommendation_config.agent_traces.cloudwatch_logs.rule.filters[0].value.boolean_value #=> Boolean
resp.recommendation_config.tool_description_recommendation_config.agent_traces.batch_evaluation.batch_evaluation_arn #=> String
resp.status #=> String, one of "PENDING", "IN_PROGRESS", "COMPLETED", "FAILED", "DELETING"
resp.created_at #=> Time
resp.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :name (required, String) —

    The name of the recommendation. Must be unique within your account.

  • :description (String) —

    The description of the recommendation.

  • :type (required, String) —

    The type of recommendation to generate. Valid values are SYSTEM_PROMPT_RECOMMENDATION for system prompt optimization or TOOL_DESCRIPTION_RECOMMENDATION for tool description optimization.

  • :recommendation_config (required, Types::RecommendationConfig) —

    The configuration for the recommendation, including the input to optimize, agent traces to analyze, and evaluation settings.

  • :kms_key_arn (String) —

    The ARN of the KMS key used to encrypt recommendation data. If provided, customer data is encrypted at rest with the specified key.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, the service ignores the request, but does not return an error.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :tags (Hash<String,String>) —

    A map of tag keys and values to associate with the recommendation.

Returns:

See Also:



5937
5938
5939
5940
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 5937

def start_recommendation(params = {}, options = {})
  req = build_request(:start_recommendation, params)
  req.send_request(options)
end

#stop_batch_evaluation(params = {}) ⇒ Types::StopBatchEvaluationResponse

Stops a running batch evaluation. Sessions that have already been evaluated retain their results.

Examples:

Request syntax with placeholder values


resp = client.stop_batch_evaluation({
  batch_evaluation_id: "BatchEvaluationId", # required
})

Response structure


resp.batch_evaluation_id #=> String
resp.batch_evaluation_arn #=> String
resp.status #=> String, one of "PENDING", "IN_PROGRESS", "COMPLETED", "COMPLETED_WITH_ERRORS", "FAILED", "STOPPING", "STOPPED", "DELETING"
resp.description #=> String

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :batch_evaluation_id (required, String) —

    The unique identifier of the batch evaluation to stop.

Returns:

See Also:



5972
5973
5974
5975
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 5972

def stop_batch_evaluation(params = {}, options = {})
  req = build_request(:stop_batch_evaluation, params)
  req.send_request(options)
end

#stop_browser_session(params = {}) ⇒ Types::StopBrowserSessionResponse

Terminates an active browser session in Amazon Bedrock AgentCore. This operation stops the session, releases associated resources, and makes the session unavailable for further use.

To stop a browser session, you must specify both the browser identifier and the session ID. Once stopped, a session cannot be restarted; you must create a new session using StartBrowserSession.

The following operations are related to StopBrowserSession:

Examples:

Request syntax with placeholder values


resp = client.stop_browser_session({
  trace_id: "StopBrowserSessionRequestTraceIdString",
  trace_parent: "StopBrowserSessionRequestTraceParentString",
  browser_identifier: "String", # required
  session_id: "BrowserSessionId", # required
  client_token: "ClientToken",
})

Response structure


resp.browser_identifier #=> String
resp.session_id #=> String
resp.last_updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :trace_id (String) —

    The trace identifier for request tracking.

  • :trace_parent (String) —

    The parent trace information for distributed tracing.

  • :browser_identifier (required, String) —

    The unique identifier of the browser associated with the session.

  • :session_id (required, String) —

    The unique identifier of the browser session to stop.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock AgentCore ignores the request, but does not return an error.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

Returns:

See Also:



6043
6044
6045
6046
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 6043

def stop_browser_session(params = {}, options = {})
  req = build_request(:stop_browser_session, params)
  req.send_request(options)
end

#stop_code_interpreter_session(params = {}) ⇒ Types::StopCodeInterpreterSessionResponse

Terminates an active code interpreter session in Amazon Bedrock AgentCore. This operation stops the session, releases associated resources, and makes the session unavailable for further use.

To stop a code interpreter session, you must specify both the code interpreter identifier and the session ID. Once stopped, a session cannot be restarted; you must create a new session using StartCodeInterpreterSession.

The following operations are related to StopCodeInterpreterSession:

Examples:

Request syntax with placeholder values


resp = client.stop_code_interpreter_session({
  trace_id: "StopCodeInterpreterSessionRequestTraceIdString",
  trace_parent: "StopCodeInterpreterSessionRequestTraceParentString",
  code_interpreter_identifier: "String", # required
  session_id: "CodeInterpreterSessionId", # required
  client_token: "ClientToken",
})

Response structure


resp.code_interpreter_identifier #=> String
resp.session_id #=> String
resp.last_updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :trace_id (String) —

    The trace identifier for request tracking.

  • :trace_parent (String) —

    The parent trace information for distributed tracing.

  • :code_interpreter_identifier (required, String) —

    The unique identifier of the code interpreter associated with the session.

  • :session_id (required, String) —

    The unique identifier of the code interpreter session to stop.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock AgentCore ignores the request, but does not return an error.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

Returns:

See Also:



6116
6117
6118
6119
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 6116

def stop_code_interpreter_session(params = {}, options = {})
  req = build_request(:stop_code_interpreter_session, params)
  req.send_request(options)
end

#stop_runtime_session(params = {}) ⇒ Types::StopRuntimeSessionResponse

Stops a session that is running in an running AgentCore Runtime agent.

Examples:

Request syntax with placeholder values


resp = client.stop_runtime_session({
  runtime_session_id: "SessionType", # required
  agent_runtime_arn: "String", # required
  qualifier: "String",
  client_token: "ClientToken",
})

Response structure


resp.runtime_session_id #=> String
resp.status_code #=> Integer

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :runtime_session_id (required, String) —

    The ID of the session that you want to stop.

  • :agent_runtime_arn (required, String) —

    The ARN of the agent that contains the session that you want to stop.

  • :qualifier (String) —

    Optional qualifier to specify an agent alias, such as prodcode> or dev. If you don't provide a value, the DEFAULT alias is used.

  • :client_token (String) —

    Idempotent token used to identify the request. If you use the same token with multiple requests, the same response is returned. Use ClientToken to prevent the same request from being processed more than once.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

Returns:

See Also:



6165
6166
6167
6168
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 6165

def stop_runtime_session(params = {}, options = {})
  req = build_request(:stop_runtime_session, params)
  req.send_request(options)
end

#update_ab_test(params = {}) ⇒ Types::UpdateABTestResponse

Updates an A/B test's configuration, including variants, traffic allocation, evaluation settings, or execution status.

Examples:

Request syntax with placeholder values


resp = client.update_ab_test({
  ab_test_id: "ABTestId", # required
  client_token: "ClientToken",
  name: "ABTestName",
  description: "ABTestDescription",
  variants: [
    {
      name: "VariantName", # required
      weight: 1, # required
      variant_configuration: { # required
        configuration_bundle: {
          bundle_arn: "ConfigurationBundleArn", # required
          bundle_version: "ConfigurationBundleVersion", # required
        },
        target: {
          name: "TargetName", # required
        },
      },
    },
  ],
  gateway_filter: {
    target_paths: ["PathPattern"],
  },
  evaluation_config: {
    online_evaluation_config_arn: "OnlineEvaluationConfigArn",
    per_variant_online_evaluation_config: [
      {
        name: "VariantName", # required
        online_evaluation_config_arn: "OnlineEvaluationConfigArn", # required
      },
    ],
  },
  role_arn: "RoleArn",
  execution_status: "PAUSED", # accepts PAUSED, RUNNING, STOPPED, NOT_STARTED
})

Response structure


resp.ab_test_id #=> String
resp.ab_test_arn #=> String
resp.status #=> String, one of "CREATING", "ACTIVE", "CREATE_FAILED", "UPDATING", "UPDATE_FAILED", "DELETING", "DELETE_FAILED", "FAILED"
resp.execution_status #=> String, one of "PAUSED", "RUNNING", "STOPPED", "NOT_STARTED"
resp.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :ab_test_id (required, String) —

    The unique identifier of the A/B test to update.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, the service ignores the request, but does not return an error.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

  • :name (String) —

    The updated name of the A/B test.

  • :description (String) —

    The updated description of the A/B test.

  • :variants (Array<Types::Variant>) —

    The updated list of variants.

  • :gateway_filter (Types::GatewayFilter) —

    The updated gateway filter.

  • :evaluation_config (Types::ABTestEvaluationConfig) —

    The updated evaluation configuration.

  • :role_arn (String) —

    The updated IAM role ARN.

  • :execution_status (String) —

    The updated execution status to enable or disable the A/B test.

Returns:

See Also:



6264
6265
6266
6267
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 6264

def update_ab_test(params = {}, options = {})
  req = build_request(:update_ab_test, params)
  req.send_request(options)
end

#update_browser_stream(params = {}) ⇒ Types::UpdateBrowserStreamResponse

Updates a browser stream. To use this operation, you must have permissions to perform the bedrock:UpdateBrowserStream action.

Examples:

Request syntax with placeholder values


resp = client.update_browser_stream({
  browser_identifier: "String", # required
  session_id: "BrowserSessionId", # required
  stream_update: { # required
    automation_stream_update: {
      stream_status: "ENABLED", # accepts ENABLED, DISABLED
    },
  },
  client_token: "ClientToken",
})

Response structure


resp.browser_identifier #=> String
resp.session_id #=> String
resp.streams.automation_stream.stream_endpoint #=> String
resp.streams.automation_stream.stream_status #=> String, one of "ENABLED", "DISABLED"
resp.streams.live_view_stream.stream_endpoint #=> String
resp.updated_at #=> Time

Parameters:

  • params (Hash) (defaults to: {}) —

    ({})

Options Hash (params):

  • :browser_identifier (required, String) —

    The identifier of the browser.

  • :session_id (required, String) —

    The identifier of the browser session.

  • :stream_update (required, Types::StreamUpdate) —

    The update to apply to the browser stream.

  • :client_token (String) —

    A unique, case-sensitive identifier to ensure that the operation completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error.

    A suitable default value is auto-generated. You should normally not need to pass this option.**

Returns:

See Also:



6323
6324
6325
6326
 
# File 'gems/aws-sdk-bedrockagentcore/lib/aws-sdk-bedrockagentcore/client.rb', line 6323

def update_browser_stream(params = {}, options = {})
  req = build_request(:update_browser_stream, params)
  req.send_request(options)
end