IBedrockAgentRuntime Interface
Interface for Agent Runtime resources.
Properties
agentRuntimeArnstringagent_runtime_arnstragentRuntimeArnStringAgentRuntimeArnstringAgentRuntimeArn*string#The ARN of the agent runtime resource - Format `arn:${Partition}:bedrock-agentcore:${Region}:${Account}:runtime/${RuntimeId}`.
example
ts
"arn:aws:bedrock-agentcore:us-west-2:123456789012:runtime/runtime-abc123"
agentRuntimeIdstringagent_runtime_idstragentRuntimeIdStringAgentRuntimeIdstringAgentRuntimeId*string#The ID of the agent runtime.
example
ts
"runtime-abc123"
agentRuntimeNamestringagent_runtime_namestragentRuntimeNameStringAgentRuntimeNamestringAgentRuntimeName*string#The name of the agent runtime.
agentRuntimeVersionmay be undefinedstringagent_runtime_versionmay be undefinedstragentRuntimeVersionmay be undefinedStringAgentRuntimeVersionmay be undefinedstringAgentRuntimeVersionmay be undefined*string#The version of the agent runtime.
agentStatusmay be undefinedstringagent_statusmay be undefinedstragentStatusmay be undefinedStringAgentStatusmay be undefinedstringAgentStatusmay be undefined*string#The current status of the agent runtime.
applicationLogGroupILogGroupapplication_log_groupILogGroupapplicationLogGroupILogGroupApplicationLogGroupILogGroupApplicationLogGroupILogGroup#The CloudWatch Logs application log group for the default endpoint of this runtime, located at `/aws/bedrock-agentcore/runtimes/{agentRuntimeId}-DEFAULT`.
notes · example
Use this property to attach metric filters, subscription filters, or alarms to the log group without hardcoding its name.
The log group is created by the AgentCore service on the runtime's first invocation, not by CDK. Constructs that require the log group to exist at deploy time (such as MetricFilter) may race the first invocation; in that case, ensure at least one invocation has occurred before deploying the dependent resources, or pre-create the log group with a LogRetention custom resource using the same name.
ts
"/aws/bedrock-agentcore/runtimes/runtime-abc123-DEFAULT"
connectionsConnectionsconnectionsConnectionsconnectionsConnectionsConnectionsConnectionsConnectionsConnections#The network connections associated with this resource.
createdAtmay be undefinedstringcreated_atmay be undefinedstrcreatedAtmay be undefinedStringCreatedAtmay be undefinedstringCreatedAtmay be undefined*string#The time at which the runtime was created.
example
ts
"2024-01-15T10:30:00Z"
envResourceEnvironmentenvResourceEnvironmentenvResourceEnvironmentEnvResourceEnvironmentEnvResourceEnvironment#The environment this resource belongs to.
notes
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.
grantPrincipalIPrincipalgrant_principalIPrincipalgrantPrincipalIPrincipalGrantPrincipalIPrincipalGrantPrincipalIPrincipal#The principal to grant permissions to.
lastUpdatedAtmay be undefinedstringlast_updated_atmay be undefinedstrlastUpdatedAtmay be undefinedStringLastUpdatedAtmay be undefinedstringLastUpdatedAtmay be undefined*string#The time at which the runtime was last updated.
example
ts
"2024-01-15T14:45:00Z"
The IAM role that provides permissions for the agent runtime.
runtimeRefRuntimeReferenceruntime_refRuntimeReferenceruntimeRefRuntimeReferenceRuntimeRefRuntimeReferenceRuntimeRefRuntimeReference#A reference to a Runtime resource.
Methods
addToRolePolicy(statement: PolicyStatement): IBedrockAgentRuntime // chainabledef add_to_role_policy(self, statement: PolicyStatement) -> IBedrockAgentRuntimepublic IBedrockAgentRuntime addToRolePolicy(PolicyStatement statement)public IBedrockAgentRuntime AddToRolePolicy(PolicyStatement statement)func AddToRolePolicy(Statement PolicyStatement) IBedrockAgentRuntime#Adds a policy statement to the runtime's execution role.
1 parameter · returns
Parameters
statementstatementstatementstatementStatement— The IAM policy statement to add.
Returns: The runtime instance for chaining
applyRemovalPolicy(policy: RemovalPolicy): voiddef apply_removal_policy(self, policy: RemovalPolicy) -> Nonepublic void applyRemovalPolicy(RemovalPolicy policy)public void ApplyRemovalPolicy(RemovalPolicy policy)func ApplyRemovalPolicy(Policy RemovalPolicy)#Apply the given removal policy to this resource.
notes
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).
grant(actions: string[], resources: string[]): Grantdef grant(self, actions: typing.List[str], resources: typing.List[str]) -> Grantpublic Grant grant(List<String> actions, List<String> resources)public Grant Grant(string[] actions, string[] resources)func Grant(Actions *[]*string, Resources *[]*string) Grant#Grant the runtime specific actions on AWS resources.
2 parameters · returns
Parameters
actionsactionsactionsactionsActions— The actions to grant.resourcesresourcesresourcesresourcesResources— The resource ARNs to grant access to.
Returns: The Grant object for chaining
grantInvoke(grantee: IGrantable): Grantdef grant_invoke(self, grantee: IGrantable) -> Grantpublic Grant grantInvoke(IGrantable grantee)public Grant GrantInvoke(IGrantable grantee)func GrantInvoke(Grantee IGrantable) Grant#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.
1 parameter
Parameters
granteegranteegranteegranteeGrantee— The principal to grant access to.
grantInvokeRuntime(grantee: IGrantable): Grantdef grant_invoke_runtime(self, grantee: IGrantable) -> Grantpublic Grant grantInvokeRuntime(IGrantable grantee)public Grant GrantInvokeRuntime(IGrantable grantee)func GrantInvokeRuntime(Grantee IGrantable) Grant#Permits an IAM principal to invoke this runtime Grants the bedrock-agentcore:InvokeAgentRuntime permission.
1 parameter
Parameters
granteegranteegranteegranteeGrantee— The principal to grant access to.
grantInvokeRuntimeForUser(grantee: IGrantable): Grantdef grant_invoke_runtime_for_user(self, grantee: IGrantable) -> Grantpublic Grant grantInvokeRuntimeForUser(IGrantable grantee)public Grant GrantInvokeRuntimeForUser(IGrantable grantee)func GrantInvokeRuntimeForUser(Grantee IGrantable) Grant#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.
1 parameter
Parameters
granteegranteegranteegranteeGrantee— The principal to grant access to.
metric(metricName: string, props?: MetricOptions): Metricdef metric(self, metric_name: str, props: typing.Optional[MetricOptions] = None) -> Metricpublic Metric metric(String metricName, MetricOptions props)public Metric Metric(string metricName, MetricOptions? props = null)func Metric(MetricName *string, Props MetricOptions) Metric#Return the given named metric for this agent runtime.
metricInvocations(props?: MetricOptions): Metricdef metric_invocations(self, props: typing.Optional[MetricOptions] = None) -> Metricpublic Metric metricInvocations(MetricOptions props)public Metric MetricInvocations(MetricOptions? props = null)func MetricInvocations(Props MetricOptions) Metric#Return a metric containing the total number of invocations for this agent runtime.
metricInvocationsAggregated(props?: MetricOptions): Metricdef metric_invocations_aggregated(self, props: typing.Optional[MetricOptions] = None) -> Metricpublic Metric metricInvocationsAggregated(MetricOptions props)public Metric MetricInvocationsAggregated(MetricOptions? props = null)func MetricInvocationsAggregated(Props MetricOptions) Metric#Return a metric containing the total number of invocations across all resources.
metricLatency(props?: MetricOptions): Metricdef metric_latency(self, props: typing.Optional[MetricOptions] = None) -> Metricpublic Metric metricLatency(MetricOptions props)public Metric MetricLatency(MetricOptions? props = null)func MetricLatency(Props MetricOptions) Metric#Return a metric measuring the latency of requests for this agent runtime.
metricSessionCount(props?: MetricOptions): Metricdef metric_session_count(self, props: typing.Optional[MetricOptions] = None) -> Metricpublic Metric metricSessionCount(MetricOptions props)public Metric MetricSessionCount(MetricOptions? props = null)func MetricSessionCount(Props MetricOptions) Metric#Return a metric containing the number of agent sessions for this agent runtime.
metricSessionsAggregated(props?: MetricOptions): Metricdef metric_sessions_aggregated(self, props: typing.Optional[MetricOptions] = None) -> Metricpublic Metric metricSessionsAggregated(MetricOptions props)public Metric MetricSessionsAggregated(MetricOptions? props = null)func MetricSessionsAggregated(Props MetricOptions) Metric#Return a metric containing the total number of sessions across all resources.
metricSystemErrors(props?: MetricOptions): Metricdef metric_system_errors(self, props: typing.Optional[MetricOptions] = None) -> Metricpublic Metric metricSystemErrors(MetricOptions props)public Metric MetricSystemErrors(MetricOptions? props = null)func MetricSystemErrors(Props MetricOptions) Metric#Return a metric containing the number of system errors for this agent runtime.
metricThrottles(props?: MetricOptions): Metricdef metric_throttles(self, props: typing.Optional[MetricOptions] = None) -> Metricpublic Metric metricThrottles(MetricOptions props)public Metric MetricThrottles(MetricOptions? props = null)func MetricThrottles(Props MetricOptions) Metric#Return a metric containing the number of throttled requests for this agent runtime.
metricTotalErrors(props?: MetricOptions): Metricdef metric_total_errors(self, props: typing.Optional[MetricOptions] = None) -> Metricpublic Metric metricTotalErrors(MetricOptions props)public Metric MetricTotalErrors(MetricOptions? props = null)func MetricTotalErrors(Props MetricOptions) Metric#Return a metric containing the total number of errors (system + user) for this agent runtime.
metricUserErrors(props?: MetricOptions): Metricdef metric_user_errors(self, props: typing.Optional[MetricOptions] = None) -> Metricpublic Metric metricUserErrors(MetricOptions props)public Metric MetricUserErrors(MetricOptions? props = null)func MetricUserErrors(Props MetricOptions) Metric#Return a metric containing the number of user errors for this agent runtime.
with(...mixins: IMixin[]): IConstructdef with(self, mixins: IMixin) -> IConstructpublic IConstruct with(IMixin mixins)public IConstruct With(IMixin mixins)func With(Mixins IMixin) IConstruct#Applies one or more mixins to this construct.
Mixins are applied in order. The list of constructs is captured at the start of the call, so constructs added by a mixin will not be visited.
1 parameter · returns
Parameters
mixinsmixinsmixinsmixinsMixins— The mixins to apply.
Returns: This construct for chaining