Runtime

class aws_cdk.aws_bedrock_agentcore_alpha.Runtime(scope, id, *, agent_runtime_artifact, runtime_name, authorizer_configuration=None, description=None, environment_variables=None, execution_role=None, lifecycle_configuration=None, network_configuration=None, protocol_configuration=None, request_header_configuration=None, tags=None)

Bases: RuntimeBase

(experimental) Bedrock Agent Core Runtime Enables running containerized agents with specific network configurations, security settings, and runtime artifacts.

See:

https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime.html

Stability:

experimental

Resource:

AWS::BedrockAgentCore::Runtime

ExampleMetadata:

fixture=default infused

Example:

repository = ecr.Repository(self, "TestRepository",
    repository_name="test-agent-runtime"
)
agent_runtime_artifact = agentcore.AgentRuntimeArtifact.from_ecr_repository(repository, "v1.0.0")

runtime = agentcore.Runtime(self, "MyAgentRuntime",
    runtime_name="myAgent",
    agent_runtime_artifact=agent_runtime_artifact,
    authorizer_configuration=agentcore.RuntimeAuthorizerConfiguration.using_oAuth("https://github.com/.well-known/openid-configuration", "oauth_client_123")
)
Parameters:
  • scope (Construct)

  • id (str)

  • agent_runtime_artifact (AgentRuntimeArtifact) – (experimental) The artifact configuration for the agent runtime Contains the container configuration with ECR URI.

  • runtime_name (str) – (experimental) The name of the agent runtime Valid characters are a-z, A-Z, 0-9, _ (underscore) Must start with a letter and can be up to 48 characters long Pattern: ^[a-zA-Z][a-zA-Z0-9_]{0,47}$.

  • authorizer_configuration (Optional[RuntimeAuthorizerConfiguration]) – (experimental) Authorizer configuration for the agent runtime Use RuntimeAuthorizerConfiguration static methods to create the configuration. Default: - RuntimeAuthorizerConfiguration.iam() (IAM authentication)

  • description (Optional[str]) – (experimental) Optional description for the agent runtime. Default: - No description Length Minimum: 1 , Maximum: 1200

  • environment_variables (Optional[Mapping[str, str]]) – (experimental) Environment variables for the agent runtime - Maximum 50 environment variables - Key: Must be 1-100 characters, start with letter or underscore, contain only letters, numbers, and underscores - Value: Must be 0-2048 characters (per CloudFormation specification). Default: - No environment variables

  • execution_role (Optional[IRole]) – (experimental) The IAM role that provides permissions for the agent runtime If not provided, a role will be created automatically. Default: - A new role will be created

  • lifecycle_configuration (Union[LifecycleConfiguration, Dict[str, Any], None]) – (experimental) The life cycle configuration for the AgentCore Runtime. Default: - No lifecycle configuration

  • network_configuration (Optional[RuntimeNetworkConfiguration]) – (experimental) Network configuration for the agent runtime. Default: - RuntimeNetworkConfiguration.usingPublicNetwork()

  • protocol_configuration (Optional[ProtocolType]) – (experimental) Protocol configuration for the agent runtime. Default: - ProtocolType.HTTP

  • request_header_configuration (Union[RequestHeaderConfiguration, Dict[str, Any], None]) – (experimental) Configuration for HTTP request headers that will be passed through to the runtime. Default: - No request headers configured

  • tags (Optional[Mapping[str, str]]) – (experimental) Tags for the agent runtime A list of key:value pairs of tags to apply to this Runtime resource. Default: {} - no tags

Stability:

experimental

Methods

add_endpoint(endpoint_name, *, description=None, version=None)

(experimental) Add an endpoint to this runtime This is a convenience method that creates a RuntimeEndpoint associated with this runtime.

Parameters:
  • endpoint_name (str) – The name of the endpoint.

  • description (Optional[str]) – (experimental) Description for the endpoint, Must be between 1 and 1200 characters. Default: - No description

  • version (Optional[str]) – (experimental) Override the runtime version for this endpoint. Default: 1

Return type:

RuntimeEndpoint

Returns:

The created RuntimeEndpoint

Stability:

experimental

add_to_role_policy(statement)

(experimental) Adds a policy statement to the runtime’s execution role.

Parameters:

statement (PolicyStatement) – The IAM policy statement to add.

Return type:

IBedrockAgentRuntime

Returns:

The runtime instance for chaining

Stability:

experimental

apply_removal_policy(policy)

Apply the given removal policy to this resource.

The Removal Policy controls what happens to this resource when it stops being managed by CloudFormation, either because you’ve removed it from the CDK application or because you’ve made a change that requires the resource to be replaced.

The resource can be deleted (RemovalPolicy.DESTROY), or left in your AWS account for data recovery and cleanup later (RemovalPolicy.RETAIN).

Parameters:

policy (RemovalPolicy)

Return type:

None

grant(actions, resources)

(experimental) Grant the runtime specific actions on AWS resources.

Parameters:
  • actions (Sequence[str]) – The actions to grant.

  • resources (Sequence[str]) – The resource ARNs to grant access to.

Return type:

Grant

Returns:

The Grant object for chaining

Stability:

experimental

grant_invoke(grantee)

(experimental) Permits an IAM principal to invoke this runtime both directly and on behalf of users Grants both bedrock-agentcore:InvokeAgentRuntime and bedrock-agentcore:InvokeAgentRuntimeForUser permissions.

Parameters:

grantee (IGrantable) – The principal to grant access to.

Stability:

experimental

Return type:

Grant

grant_invoke_runtime(grantee)

(experimental) Permits an IAM principal to invoke this runtime Grants the bedrock-agentcore:InvokeAgentRuntime permission.

Parameters:

grantee (IGrantable) – The principal to grant access to.

Stability:

experimental

Return type:

Grant

grant_invoke_runtime_for_user(grantee)

(experimental) Permits an IAM principal to invoke this runtime on behalf of a user Grants the bedrock-agentcore:InvokeAgentRuntimeForUser permission Required when using the X-Amzn-Bedrock-AgentCore-Runtime-User-Id header.

Parameters:

grantee (IGrantable) – The principal to grant access to.

Stability:

experimental

Return type:

Grant

metric(metric_name, dimensions, *, account=None, color=None, dimensions_map=None, id=None, label=None, period=None, region=None, stack_account=None, stack_region=None, statistic=None, unit=None, visible=None)

(experimental) Return the given named metric for this agent runtime.

By default, the metric will be calculated as a sum over a period of 5 minutes. You can customize this by using the statistic and period properties.

Parameters:
  • metric_name (str)

  • dimensions (Mapping[str, str])

  • account (Optional[str]) – Account which this metric comes from. Default: - Deployment account.

  • color (Optional[str]) – The hex color code, prefixed with ‘#’ (e.g. ‘#00ff00’), to use when this metric is rendered on a graph. The Color class has a set of standard colors that can be used here. Default: - Automatic color

  • dimensions_map (Optional[Mapping[str, str]]) – Dimensions of the metric. Default: - No dimensions.

  • id (Optional[str]) – Unique identifier for this metric when used in dashboard widgets. The id can be used as a variable to represent this metric in math expressions. Valid characters are letters, numbers, and underscore. The first character must be a lowercase letter. Default: - No ID

  • label (Optional[str]) – Label for this metric when added to a Graph in a Dashboard. You can use dynamic labels to show summary information about the entire displayed time series in the legend. For example, if you use:: [max: ${MAX}] MyMetric As the metric label, the maximum value in the visible range will be shown next to the time series name in the graph’s legend. Default: - No label

  • period (Optional[Duration]) – The period over which the specified statistic is applied. Default: Duration.minutes(5)

  • region (Optional[str]) – Region which this metric comes from. Default: - Deployment region.

  • stack_account (Optional[str]) – Account of the stack this metric is attached to. Default: - Deployment account.

  • stack_region (Optional[str]) – Region of the stack this metric is attached to. Default: - Deployment region.

  • statistic (Optional[str]) – What function to use for aggregating. Use the aws_cloudwatch.Stats helper class to construct valid input strings. Can be one of the following: - “Minimum” | “min” - “Maximum” | “max” - “Average” | “avg” - “Sum” | “sum” - “SampleCount | “n” - “pNN.NN” - “tmNN.NN” | “tm(NN.NN%:NN.NN%)” - “iqm” - “wmNN.NN” | “wm(NN.NN%:NN.NN%)” - “tcNN.NN” | “tc(NN.NN%:NN.NN%)” - “tsNN.NN” | “ts(NN.NN%:NN.NN%)” Default: Average

  • unit (Optional[Unit]) – Unit used to filter the metric stream. Only refer to datums emitted to the metric stream with the given unit and ignore all others. Only useful when datums are being emitted to the same metric stream under different units. The default is to use all matric datums in the stream, regardless of unit, which is recommended in nearly all cases. CloudWatch does not honor this property for graphs. Default: - All metric datums in the given metric stream

  • visible (Optional[bool]) – Whether this metric should be visible in dashboard graphs. Setting this to false is useful when you want to hide raw metrics that are used in math expressions, and show only the expression results. Default: true

Stability:

experimental

Return type:

Metric

metric_invocations(*, account=None, color=None, dimensions_map=None, id=None, label=None, period=None, region=None, stack_account=None, stack_region=None, statistic=None, unit=None, visible=None)

(experimental) Return a metric containing the total number of invocations for this agent runtime.

Parameters:
  • account (Optional[str]) – Account which this metric comes from. Default: - Deployment account.

  • color (Optional[str]) – The hex color code, prefixed with ‘#’ (e.g. ‘#00ff00’), to use when this metric is rendered on a graph. The Color class has a set of standard colors that can be used here. Default: - Automatic color

  • dimensions_map (Optional[Mapping[str, str]]) – Dimensions of the metric. Default: - No dimensions.

  • id (Optional[str]) – Unique identifier for this metric when used in dashboard widgets. The id can be used as a variable to represent this metric in math expressions. Valid characters are letters, numbers, and underscore. The first character must be a lowercase letter. Default: - No ID

  • label (Optional[str]) –

    Label for this metric when added to a Graph in a Dashboard. You can use dynamic labels to show summary information about the entire displayed time series in the legend. For example, if you use:: [max: ${MAX}] MyMetric As the metric label, the maximum value in the visible range will be shown next to the time series name in the graph’s legend. Default: - No label

  • period (Optional[Duration]) – The period over which the specified statistic is applied. Default: Duration.minutes(5)

  • region (Optional[str]) – Region which this metric comes from. Default: - Deployment region.

  • stack_account (Optional[str]) – Account of the stack this metric is attached to. Default: - Deployment account.

  • stack_region (Optional[str]) – Region of the stack this metric is attached to. Default: - Deployment region.

  • statistic (Optional[str]) – What function to use for aggregating. Use the aws_cloudwatch.Stats helper class to construct valid input strings. Can be one of the following: - “Minimum” | “min” - “Maximum” | “max” - “Average” | “avg” - “Sum” | “sum” - “SampleCount | “n” - “pNN.NN” - “tmNN.NN” | “tm(NN.NN%:NN.NN%)” - “iqm” - “wmNN.NN” | “wm(NN.NN%:NN.NN%)” - “tcNN.NN” | “tc(NN.NN%:NN.NN%)” - “tsNN.NN” | “ts(NN.NN%:NN.NN%)” Default: Average

  • unit (Optional[Unit]) – Unit used to filter the metric stream. Only refer to datums emitted to the metric stream with the given unit and ignore all others. Only useful when datums are being emitted to the same metric stream under different units. The default is to use all matric datums in the stream, regardless of unit, which is recommended in nearly all cases. CloudWatch does not honor this property for graphs. Default: - All metric datums in the given metric stream

  • visible (Optional[bool]) – Whether this metric should be visible in dashboard graphs. Setting this to false is useful when you want to hide raw metrics that are used in math expressions, and show only the expression results. Default: true

Stability:

experimental

Return type:

Metric

metric_invocations_aggregated(*, account=None, color=None, dimensions_map=None, id=None, label=None, period=None, region=None, stack_account=None, stack_region=None, statistic=None, unit=None, visible=None)

(experimental) Return a metric containing the total number of invocations across all resources.

Parameters:
  • account (Optional[str]) – Account which this metric comes from. Default: - Deployment account.

  • color (Optional[str]) – The hex color code, prefixed with ‘#’ (e.g. ‘#00ff00’), to use when this metric is rendered on a graph. The Color class has a set of standard colors that can be used here. Default: - Automatic color

  • dimensions_map (Optional[Mapping[str, str]]) – Dimensions of the metric. Default: - No dimensions.

  • id (Optional[str]) – Unique identifier for this metric when used in dashboard widgets. The id can be used as a variable to represent this metric in math expressions. Valid characters are letters, numbers, and underscore. The first character must be a lowercase letter. Default: - No ID

  • label (Optional[str]) –

    Label for this metric when added to a Graph in a Dashboard. You can use dynamic labels to show summary information about the entire displayed time series in the legend. For example, if you use:: [max: ${MAX}] MyMetric As the metric label, the maximum value in the visible range will be shown next to the time series name in the graph’s legend. Default: - No label

  • period (Optional[Duration]) – The period over which the specified statistic is applied. Default: Duration.minutes(5)

  • region (Optional[str]) – Region which this metric comes from. Default: - Deployment region.

  • stack_account (Optional[str]) – Account of the stack this metric is attached to. Default: - Deployment account.

  • stack_region (Optional[str]) – Region of the stack this metric is attached to. Default: - Deployment region.

  • statistic (Optional[str]) – What function to use for aggregating. Use the aws_cloudwatch.Stats helper class to construct valid input strings. Can be one of the following: - “Minimum” | “min” - “Maximum” | “max” - “Average” | “avg” - “Sum” | “sum” - “SampleCount | “n” - “pNN.NN” - “tmNN.NN” | “tm(NN.NN%:NN.NN%)” - “iqm” - “wmNN.NN” | “wm(NN.NN%:NN.NN%)” - “tcNN.NN” | “tc(NN.NN%:NN.NN%)” - “tsNN.NN” | “ts(NN.NN%:NN.NN%)” Default: Average

  • unit (Optional[Unit]) – Unit used to filter the metric stream. Only refer to datums emitted to the metric stream with the given unit and ignore all others. Only useful when datums are being emitted to the same metric stream under different units. The default is to use all matric datums in the stream, regardless of unit, which is recommended in nearly all cases. CloudWatch does not honor this property for graphs. Default: - All metric datums in the given metric stream

  • visible (Optional[bool]) – Whether this metric should be visible in dashboard graphs. Setting this to false is useful when you want to hide raw metrics that are used in math expressions, and show only the expression results. Default: true

Stability:

experimental

Return type:

Metric

metric_latency(*, account=None, color=None, dimensions_map=None, id=None, label=None, period=None, region=None, stack_account=None, stack_region=None, statistic=None, unit=None, visible=None)

(experimental) Return a metric measuring the latency of requests for this agent runtime.

The latency metric represents the total time elapsed between receiving the request and sending the final response token, representing complete end-to-end processing time.

Parameters:
  • account (Optional[str]) – Account which this metric comes from. Default: - Deployment account.

  • color (Optional[str]) – The hex color code, prefixed with ‘#’ (e.g. ‘#00ff00’), to use when this metric is rendered on a graph. The Color class has a set of standard colors that can be used here. Default: - Automatic color

  • dimensions_map (Optional[Mapping[str, str]]) – Dimensions of the metric. Default: - No dimensions.

  • id (Optional[str]) – Unique identifier for this metric when used in dashboard widgets. The id can be used as a variable to represent this metric in math expressions. Valid characters are letters, numbers, and underscore. The first character must be a lowercase letter. Default: - No ID

  • label (Optional[str]) –

    Label for this metric when added to a Graph in a Dashboard. You can use dynamic labels to show summary information about the entire displayed time series in the legend. For example, if you use:: [max: ${MAX}] MyMetric As the metric label, the maximum value in the visible range will be shown next to the time series name in the graph’s legend. Default: - No label

  • period (Optional[Duration]) – The period over which the specified statistic is applied. Default: Duration.minutes(5)

  • region (Optional[str]) – Region which this metric comes from. Default: - Deployment region.

  • stack_account (Optional[str]) – Account of the stack this metric is attached to. Default: - Deployment account.

  • stack_region (Optional[str]) – Region of the stack this metric is attached to. Default: - Deployment region.

  • statistic (Optional[str]) – What function to use for aggregating. Use the aws_cloudwatch.Stats helper class to construct valid input strings. Can be one of the following: - “Minimum” | “min” - “Maximum” | “max” - “Average” | “avg” - “Sum” | “sum” - “SampleCount | “n” - “pNN.NN” - “tmNN.NN” | “tm(NN.NN%:NN.NN%)” - “iqm” - “wmNN.NN” | “wm(NN.NN%:NN.NN%)” - “tcNN.NN” | “tc(NN.NN%:NN.NN%)” - “tsNN.NN” | “ts(NN.NN%:NN.NN%)” Default: Average

  • unit (Optional[Unit]) – Unit used to filter the metric stream. Only refer to datums emitted to the metric stream with the given unit and ignore all others. Only useful when datums are being emitted to the same metric stream under different units. The default is to use all matric datums in the stream, regardless of unit, which is recommended in nearly all cases. CloudWatch does not honor this property for graphs. Default: - All metric datums in the given metric stream

  • visible (Optional[bool]) – Whether this metric should be visible in dashboard graphs. Setting this to false is useful when you want to hide raw metrics that are used in math expressions, and show only the expression results. Default: true

Stability:

experimental

Return type:

Metric

metric_session_count(*, account=None, color=None, dimensions_map=None, id=None, label=None, period=None, region=None, stack_account=None, stack_region=None, statistic=None, unit=None, visible=None)

(experimental) Return a metric containing the number of agent sessions for this agent runtime.

Parameters:
  • account (Optional[str]) – Account which this metric comes from. Default: - Deployment account.

  • color (Optional[str]) – The hex color code, prefixed with ‘#’ (e.g. ‘#00ff00’), to use when this metric is rendered on a graph. The Color class has a set of standard colors that can be used here. Default: - Automatic color

  • dimensions_map (Optional[Mapping[str, str]]) – Dimensions of the metric. Default: - No dimensions.

  • id (Optional[str]) – Unique identifier for this metric when used in dashboard widgets. The id can be used as a variable to represent this metric in math expressions. Valid characters are letters, numbers, and underscore. The first character must be a lowercase letter. Default: - No ID

  • label (Optional[str]) –

    Label for this metric when added to a Graph in a Dashboard. You can use dynamic labels to show summary information about the entire displayed time series in the legend. For example, if you use:: [max: ${MAX}] MyMetric As the metric label, the maximum value in the visible range will be shown next to the time series name in the graph’s legend. Default: - No label

  • period (Optional[Duration]) – The period over which the specified statistic is applied. Default: Duration.minutes(5)

  • region (Optional[str]) – Region which this metric comes from. Default: - Deployment region.

  • stack_account (Optional[str]) – Account of the stack this metric is attached to. Default: - Deployment account.

  • stack_region (Optional[str]) – Region of the stack this metric is attached to. Default: - Deployment region.

  • statistic (Optional[str]) – What function to use for aggregating. Use the aws_cloudwatch.Stats helper class to construct valid input strings. Can be one of the following: - “Minimum” | “min” - “Maximum” | “max” - “Average” | “avg” - “Sum” | “sum” - “SampleCount | “n” - “pNN.NN” - “tmNN.NN” | “tm(NN.NN%:NN.NN%)” - “iqm” - “wmNN.NN” | “wm(NN.NN%:NN.NN%)” - “tcNN.NN” | “tc(NN.NN%:NN.NN%)” - “tsNN.NN” | “ts(NN.NN%:NN.NN%)” Default: Average

  • unit (Optional[Unit]) – Unit used to filter the metric stream. Only refer to datums emitted to the metric stream with the given unit and ignore all others. Only useful when datums are being emitted to the same metric stream under different units. The default is to use all matric datums in the stream, regardless of unit, which is recommended in nearly all cases. CloudWatch does not honor this property for graphs. Default: - All metric datums in the given metric stream

  • visible (Optional[bool]) – Whether this metric should be visible in dashboard graphs. Setting this to false is useful when you want to hide raw metrics that are used in math expressions, and show only the expression results. Default: true

Stability:

experimental

Return type:

Metric

metric_sessions_aggregated(*, account=None, color=None, dimensions_map=None, id=None, label=None, period=None, region=None, stack_account=None, stack_region=None, statistic=None, unit=None, visible=None)

(experimental) Return a metric containing the total number of sessions across all resources.

Parameters:
  • account (Optional[str]) – Account which this metric comes from. Default: - Deployment account.

  • color (Optional[str]) – The hex color code, prefixed with ‘#’ (e.g. ‘#00ff00’), to use when this metric is rendered on a graph. The Color class has a set of standard colors that can be used here. Default: - Automatic color

  • dimensions_map (Optional[Mapping[str, str]]) – Dimensions of the metric. Default: - No dimensions.

  • id (Optional[str]) – Unique identifier for this metric when used in dashboard widgets. The id can be used as a variable to represent this metric in math expressions. Valid characters are letters, numbers, and underscore. The first character must be a lowercase letter. Default: - No ID

  • label (Optional[str]) –

    Label for this metric when added to a Graph in a Dashboard. You can use dynamic labels to show summary information about the entire displayed time series in the legend. For example, if you use:: [max: ${MAX}] MyMetric As the metric label, the maximum value in the visible range will be shown next to the time series name in the graph’s legend. Default: - No label

  • period (Optional[Duration]) – The period over which the specified statistic is applied. Default: Duration.minutes(5)

  • region (Optional[str]) – Region which this metric comes from. Default: - Deployment region.

  • stack_account (Optional[str]) – Account of the stack this metric is attached to. Default: - Deployment account.

  • stack_region (Optional[str]) – Region of the stack this metric is attached to. Default: - Deployment region.

  • statistic (Optional[str]) – What function to use for aggregating. Use the aws_cloudwatch.Stats helper class to construct valid input strings. Can be one of the following: - “Minimum” | “min” - “Maximum” | “max” - “Average” | “avg” - “Sum” | “sum” - “SampleCount | “n” - “pNN.NN” - “tmNN.NN” | “tm(NN.NN%:NN.NN%)” - “iqm” - “wmNN.NN” | “wm(NN.NN%:NN.NN%)” - “tcNN.NN” | “tc(NN.NN%:NN.NN%)” - “tsNN.NN” | “ts(NN.NN%:NN.NN%)” Default: Average

  • unit (Optional[Unit]) – Unit used to filter the metric stream. Only refer to datums emitted to the metric stream with the given unit and ignore all others. Only useful when datums are being emitted to the same metric stream under different units. The default is to use all matric datums in the stream, regardless of unit, which is recommended in nearly all cases. CloudWatch does not honor this property for graphs. Default: - All metric datums in the given metric stream

  • visible (Optional[bool]) – Whether this metric should be visible in dashboard graphs. Setting this to false is useful when you want to hide raw metrics that are used in math expressions, and show only the expression results. Default: true

Stability:

experimental

Return type:

Metric

metric_system_errors(*, account=None, color=None, dimensions_map=None, id=None, label=None, period=None, region=None, stack_account=None, stack_region=None, statistic=None, unit=None, visible=None)

(experimental) Return a metric containing the number of system errors for this agent runtime.

Parameters:
  • account (Optional[str]) – Account which this metric comes from. Default: - Deployment account.

  • color (Optional[str]) – The hex color code, prefixed with ‘#’ (e.g. ‘#00ff00’), to use when this metric is rendered on a graph. The Color class has a set of standard colors that can be used here. Default: - Automatic color

  • dimensions_map (Optional[Mapping[str, str]]) – Dimensions of the metric. Default: - No dimensions.

  • id (Optional[str]) – Unique identifier for this metric when used in dashboard widgets. The id can be used as a variable to represent this metric in math expressions. Valid characters are letters, numbers, and underscore. The first character must be a lowercase letter. Default: - No ID

  • label (Optional[str]) –

    Label for this metric when added to a Graph in a Dashboard. You can use dynamic labels to show summary information about the entire displayed time series in the legend. For example, if you use:: [max: ${MAX}] MyMetric As the metric label, the maximum value in the visible range will be shown next to the time series name in the graph’s legend. Default: - No label

  • period (Optional[Duration]) – The period over which the specified statistic is applied. Default: Duration.minutes(5)

  • region (Optional[str]) – Region which this metric comes from. Default: - Deployment region.

  • stack_account (Optional[str]) – Account of the stack this metric is attached to. Default: - Deployment account.

  • stack_region (Optional[str]) – Region of the stack this metric is attached to. Default: - Deployment region.

  • statistic (Optional[str]) – What function to use for aggregating. Use the aws_cloudwatch.Stats helper class to construct valid input strings. Can be one of the following: - “Minimum” | “min” - “Maximum” | “max” - “Average” | “avg” - “Sum” | “sum” - “SampleCount | “n” - “pNN.NN” - “tmNN.NN” | “tm(NN.NN%:NN.NN%)” - “iqm” - “wmNN.NN” | “wm(NN.NN%:NN.NN%)” - “tcNN.NN” | “tc(NN.NN%:NN.NN%)” - “tsNN.NN” | “ts(NN.NN%:NN.NN%)” Default: Average

  • unit (Optional[Unit]) – Unit used to filter the metric stream. Only refer to datums emitted to the metric stream with the given unit and ignore all others. Only useful when datums are being emitted to the same metric stream under different units. The default is to use all matric datums in the stream, regardless of unit, which is recommended in nearly all cases. CloudWatch does not honor this property for graphs. Default: - All metric datums in the given metric stream

  • visible (Optional[bool]) – Whether this metric should be visible in dashboard graphs. Setting this to false is useful when you want to hide raw metrics that are used in math expressions, and show only the expression results. Default: true

Stability:

experimental

Return type:

Metric

metric_throttles(*, account=None, color=None, dimensions_map=None, id=None, label=None, period=None, region=None, stack_account=None, stack_region=None, statistic=None, unit=None, visible=None)

(experimental) Return a metric containing the number of throttled requests for this agent runtime.

Parameters:
  • account (Optional[str]) – Account which this metric comes from. Default: - Deployment account.

  • color (Optional[str]) – The hex color code, prefixed with ‘#’ (e.g. ‘#00ff00’), to use when this metric is rendered on a graph. The Color class has a set of standard colors that can be used here. Default: - Automatic color

  • dimensions_map (Optional[Mapping[str, str]]) – Dimensions of the metric. Default: - No dimensions.

  • id (Optional[str]) – Unique identifier for this metric when used in dashboard widgets. The id can be used as a variable to represent this metric in math expressions. Valid characters are letters, numbers, and underscore. The first character must be a lowercase letter. Default: - No ID

  • label (Optional[str]) –

    Label for this metric when added to a Graph in a Dashboard. You can use dynamic labels to show summary information about the entire displayed time series in the legend. For example, if you use:: [max: ${MAX}] MyMetric As the metric label, the maximum value in the visible range will be shown next to the time series name in the graph’s legend. Default: - No label

  • period (Optional[Duration]) – The period over which the specified statistic is applied. Default: Duration.minutes(5)

  • region (Optional[str]) – Region which this metric comes from. Default: - Deployment region.

  • stack_account (Optional[str]) – Account of the stack this metric is attached to. Default: - Deployment account.

  • stack_region (Optional[str]) – Region of the stack this metric is attached to. Default: - Deployment region.

  • statistic (Optional[str]) – What function to use for aggregating. Use the aws_cloudwatch.Stats helper class to construct valid input strings. Can be one of the following: - “Minimum” | “min” - “Maximum” | “max” - “Average” | “avg” - “Sum” | “sum” - “SampleCount | “n” - “pNN.NN” - “tmNN.NN” | “tm(NN.NN%:NN.NN%)” - “iqm” - “wmNN.NN” | “wm(NN.NN%:NN.NN%)” - “tcNN.NN” | “tc(NN.NN%:NN.NN%)” - “tsNN.NN” | “ts(NN.NN%:NN.NN%)” Default: Average

  • unit (Optional[Unit]) – Unit used to filter the metric stream. Only refer to datums emitted to the metric stream with the given unit and ignore all others. Only useful when datums are being emitted to the same metric stream under different units. The default is to use all matric datums in the stream, regardless of unit, which is recommended in nearly all cases. CloudWatch does not honor this property for graphs. Default: - All metric datums in the given metric stream

  • visible (Optional[bool]) – Whether this metric should be visible in dashboard graphs. Setting this to false is useful when you want to hide raw metrics that are used in math expressions, and show only the expression results. Default: true

Stability:

experimental

Return type:

Metric

metric_total_errors(*, account=None, color=None, dimensions_map=None, id=None, label=None, period=None, region=None, stack_account=None, stack_region=None, statistic=None, unit=None, visible=None)

(experimental) Return a metric containing the total number of errors (system + user) for this agent runtime.

Parameters:
  • account (Optional[str]) – Account which this metric comes from. Default: - Deployment account.

  • color (Optional[str]) – The hex color code, prefixed with ‘#’ (e.g. ‘#00ff00’), to use when this metric is rendered on a graph. The Color class has a set of standard colors that can be used here. Default: - Automatic color

  • dimensions_map (Optional[Mapping[str, str]]) – Dimensions of the metric. Default: - No dimensions.

  • id (Optional[str]) – Unique identifier for this metric when used in dashboard widgets. The id can be used as a variable to represent this metric in math expressions. Valid characters are letters, numbers, and underscore. The first character must be a lowercase letter. Default: - No ID

  • label (Optional[str]) –

    Label for this metric when added to a Graph in a Dashboard. You can use dynamic labels to show summary information about the entire displayed time series in the legend. For example, if you use:: [max: ${MAX}] MyMetric As the metric label, the maximum value in the visible range will be shown next to the time series name in the graph’s legend. Default: - No label

  • period (Optional[Duration]) – The period over which the specified statistic is applied. Default: Duration.minutes(5)

  • region (Optional[str]) – Region which this metric comes from. Default: - Deployment region.

  • stack_account (Optional[str]) – Account of the stack this metric is attached to. Default: - Deployment account.

  • stack_region (Optional[str]) – Region of the stack this metric is attached to. Default: - Deployment region.

  • statistic (Optional[str]) – What function to use for aggregating. Use the aws_cloudwatch.Stats helper class to construct valid input strings. Can be one of the following: - “Minimum” | “min” - “Maximum” | “max” - “Average” | “avg” - “Sum” | “sum” - “SampleCount | “n” - “pNN.NN” - “tmNN.NN” | “tm(NN.NN%:NN.NN%)” - “iqm” - “wmNN.NN” | “wm(NN.NN%:NN.NN%)” - “tcNN.NN” | “tc(NN.NN%:NN.NN%)” - “tsNN.NN” | “ts(NN.NN%:NN.NN%)” Default: Average

  • unit (Optional[Unit]) – Unit used to filter the metric stream. Only refer to datums emitted to the metric stream with the given unit and ignore all others. Only useful when datums are being emitted to the same metric stream under different units. The default is to use all matric datums in the stream, regardless of unit, which is recommended in nearly all cases. CloudWatch does not honor this property for graphs. Default: - All metric datums in the given metric stream

  • visible (Optional[bool]) – Whether this metric should be visible in dashboard graphs. Setting this to false is useful when you want to hide raw metrics that are used in math expressions, and show only the expression results. Default: true

Stability:

experimental

Return type:

Metric

metric_user_errors(*, account=None, color=None, dimensions_map=None, id=None, label=None, period=None, region=None, stack_account=None, stack_region=None, statistic=None, unit=None, visible=None)

(experimental) Return a metric containing the number of user errors for this agent runtime.

Parameters:
  • account (Optional[str]) – Account which this metric comes from. Default: - Deployment account.

  • color (Optional[str]) – The hex color code, prefixed with ‘#’ (e.g. ‘#00ff00’), to use when this metric is rendered on a graph. The Color class has a set of standard colors that can be used here. Default: - Automatic color

  • dimensions_map (Optional[Mapping[str, str]]) – Dimensions of the metric. Default: - No dimensions.

  • id (Optional[str]) – Unique identifier for this metric when used in dashboard widgets. The id can be used as a variable to represent this metric in math expressions. Valid characters are letters, numbers, and underscore. The first character must be a lowercase letter. Default: - No ID

  • label (Optional[str]) –

    Label for this metric when added to a Graph in a Dashboard. You can use dynamic labels to show summary information about the entire displayed time series in the legend. For example, if you use:: [max: ${MAX}] MyMetric As the metric label, the maximum value in the visible range will be shown next to the time series name in the graph’s legend. Default: - No label

  • period (Optional[Duration]) – The period over which the specified statistic is applied. Default: Duration.minutes(5)

  • region (Optional[str]) – Region which this metric comes from. Default: - Deployment region.

  • stack_account (Optional[str]) – Account of the stack this metric is attached to. Default: - Deployment account.

  • stack_region (Optional[str]) – Region of the stack this metric is attached to. Default: - Deployment region.

  • statistic (Optional[str]) – What function to use for aggregating. Use the aws_cloudwatch.Stats helper class to construct valid input strings. Can be one of the following: - “Minimum” | “min” - “Maximum” | “max” - “Average” | “avg” - “Sum” | “sum” - “SampleCount | “n” - “pNN.NN” - “tmNN.NN” | “tm(NN.NN%:NN.NN%)” - “iqm” - “wmNN.NN” | “wm(NN.NN%:NN.NN%)” - “tcNN.NN” | “tc(NN.NN%:NN.NN%)” - “tsNN.NN” | “ts(NN.NN%:NN.NN%)” Default: Average

  • unit (Optional[Unit]) – Unit used to filter the metric stream. Only refer to datums emitted to the metric stream with the given unit and ignore all others. Only useful when datums are being emitted to the same metric stream under different units. The default is to use all matric datums in the stream, regardless of unit, which is recommended in nearly all cases. CloudWatch does not honor this property for graphs. Default: - All metric datums in the given metric stream

  • visible (Optional[bool]) – Whether this metric should be visible in dashboard graphs. Setting this to false is useful when you want to hide raw metrics that are used in math expressions, and show only the expression results. Default: true

Stability:

experimental

Return type:

Metric

to_string()

Returns a string representation of this construct.

Return type:

str

Attributes

PROPERTY_INJECTION_ID = '@aws-cdk.aws-bedrock-agentcore-alpha.Runtime'
agent_runtime_arn

(experimental) The ARN of the agent runtime.

Returns:

a token representing the ARN of this agent runtime

Stability:

experimental

Attribute:

true

agent_runtime_artifact

(experimental) The artifact configuration for the agent runtime.

Stability:

experimental

agent_runtime_id

(experimental) The unique identifier of the agent runtime.

Returns:

a token representing the ID of this agent runtime

Stability:

experimental

Attribute:

true

agent_runtime_name

(experimental) The name of the agent runtime.

Returns:

a token representing the name of this agent runtime

Stability:

experimental

Attribute:

true

agent_runtime_version

(experimental) The version of the agent runtime.

Returns:

a token representing the version of this agent runtime

Stability:

experimental

Attribute:

true

agent_status

(experimental) The status of the agent runtime.

Returns:

a token representing the status of this agent runtime

Stability:

experimental

Attribute:

true

connections

(experimental) An accessor for the Connections object that will fail if this Runtime does not have a VPC configured.

Stability:

experimental

created_at

(experimental) The timestamp when the agent runtime was created.

Returns:

a token representing the creation timestamp of this agent runtime

Stability:

experimental

Attribute:

true

description

(experimental) Optional description for the agent runtime.

Stability:

experimental

env

The environment this resource belongs to.

For resources that are created and managed in a Stack (those created by creating new class instances like new Role(), new Bucket(), etc.), this is always the same as the environment of the stack they belong to.

For referenced resources (those obtained from referencing methods like Role.fromRoleArn(), Bucket.fromBucketName(), etc.), they might be different than the stack they were imported into.

grant_principal

(experimental) The principal to grant permissions to.

Stability:

experimental

last_updated_at

(experimental) The timestamp when the agent runtime was last updated.

Returns:

a token representing the last update timestamp of this agent runtime

Stability:

experimental

Attribute:

true

node

The tree node.

role

(experimental) The IAM role that provides permissions for the agent runtime.

Stability:

experimental

stack

The stack in which this resource is defined.

Static Methods

classmethod from_agent_runtime_attributes(scope, id, *, agent_runtime_arn, agent_runtime_id, agent_runtime_name, role_arn, agent_runtime_version=None, agent_status=None, created_at=None, description=None, last_updated_at=None, security_groups=None)

(experimental) Import an existing Agent Runtime using attributes This allows you to reference an Agent Runtime that was created outside of CDK.

Parameters:
  • scope (Construct) – The construct scope.

  • id (str) – The construct id.

  • agent_runtime_arn (str) – (experimental) The ARN of the agent runtime.

  • agent_runtime_id (str) – (experimental) The ID of the agent runtime.

  • agent_runtime_name (str) – (experimental) The name of the agent runtime.

  • role_arn (str) – (experimental) The IAM role ARN.

  • agent_runtime_version (Optional[str]) – (experimental) The version of the agent runtime When importing a runtime and this is not specified or undefined, endpoints created on this runtime will point to version “1” unless explicitly overridden. Default: - undefined

  • agent_status (Optional[str]) – (experimental) The current status of the agent runtime. Default: - Status not available

  • created_at (Optional[str]) – (experimental) The time at which the runtime was created. Default: - Creation time not available

  • description (Optional[str]) – (experimental) The description of the agent runtime. Default: - No description

  • last_updated_at (Optional[str]) – (experimental) The time at which the runtime was last updated. Default: - Last update time not available

  • security_groups (Optional[Sequence[ISecurityGroup]]) – (experimental) The security groups for this runtime, if in a VPC. Default: - By default, the runtime is not in a VPC.

Return type:

IBedrockAgentRuntime

Returns:

An IBedrockAgentRuntime instance representing the imported runtime

Stability:

experimental

classmethod is_construct(x)

Checks if x is a construct.

Use this method instead of instanceof to properly detect Construct instances, even when the construct library is symlinked.

Explanation: in JavaScript, multiple copies of the constructs library on disk are seen as independent, completely different libraries. As a consequence, the class Construct in each copy of the constructs library is seen as a different class, and an instance of one class will not test as instanceof the other class. npm install will not create installations like this, but users may manually symlink construct libraries together or use a monorepo tool: in those cases, multiple copies of the constructs library can be accidentally installed, and instanceof will behave unpredictably. It is safest to avoid using instanceof, and using this type-testing method instead.

Parameters:

x (Any) – Any object.

Return type:

bool

Returns:

true if x is an object created from a class which extends Construct.

classmethod is_owned_resource(construct)

Returns true if the construct was created by CDK, and false otherwise.

Parameters:

construct (IConstruct)

Return type:

bool

classmethod is_resource(construct)

Check whether the given construct is a Resource.

Parameters:

construct (IConstruct)

Return type:

bool