Package-level declarations

Types

Link copied to clipboard

This exception is thrown when a request is denied per access permissions

Link copied to clipboard
Link copied to clipboard

Contains information about an agent runtime. An agent runtime is the execution environment for a Amazon Bedrock Agent.

Link copied to clipboard

The artifact of the agent.

Link copied to clipboard

Contains information about an agent runtime endpoint. An endpoint provides a way to connect to and interact with an agent runtime.

Link copied to clipboard
Link copied to clipboard
sealed class AgentRuntimeStatus
Link copied to clipboard

The configuration for an Amazon API Gateway target.

Link copied to clipboard

The configuration for defining REST API tool filters and overrides for the gateway target.

Link copied to clipboard

Specifies which operations from an API Gateway REST API are exposed as tools. Tool names and descriptions are derived from the operationId and description fields in the API's exported OpenAPI specification.

Link copied to clipboard

Settings to override configurations for a tool.

Link copied to clipboard
Link copied to clipboard

Contains information about an API key credential provider.

Link copied to clipboard

Configuration for API schema.

Link copied to clipboard

Configuration settings for connecting to Atlassian services using OAuth2 authentication. This includes the client credentials required to authenticate with Atlassian's OAuth2 authorization server.

Link copied to clipboard

The configuration details returned for an Atlassian OAuth2 provider, including the client ID and OAuth2 discovery information.

Link copied to clipboard

Represents inbound authorization configuration options used to authenticate incoming requests.

Link copied to clipboard
sealed class AuthorizerType
Link copied to clipboard

Defines the value or values to match for and the relationship of the match.

Link copied to clipboard

Base class for all service related exceptions thrown by the BedrockAgentCoreControl client

Link copied to clipboard

The configuration for using Amazon Bedrock models in evaluator assessments, including model selection and inference parameters.

Link copied to clipboard

The network configuration for a browser. This structure defines how the browser connects to the network.

Link copied to clipboard
sealed class BrowserNetworkMode
Link copied to clipboard

Configuration for enabling browser signing capabilities that allow agents to cryptographically identify themselves to websites using HTTP message signatures.

Link copied to clipboard

The current browser signing configuration that shows whether cryptographic agent identification is enabled for web bot authentication.

Link copied to clipboard
sealed class BrowserStatus
Link copied to clipboard

Contains summary information about a browser. A browser enables Amazon Bedrock Agent to interact with web content.

Link copied to clipboard

The definition of a categorical rating scale option that provides a named category with its description for evaluation scoring.

Link copied to clipboard

Represents a Cedar policy statement within the AgentCore Policy system. Cedar is a policy language designed for authorization that provides human-readable, analyzable, and high-performance policy evaluation for controlling agent behavior and access decisions.

Link copied to clipboard
Link copied to clipboard
sealed class ClaimMatchValueType

The value or values to match for.

Link copied to clipboard

The configuration for reading agent traces from CloudWatch logs as input for online evaluation.

Link copied to clipboard

The configuration for writing evaluation results to CloudWatch logs with embedded metric format (EMF) for monitoring.

Link copied to clipboard
sealed class Code

The source code configuration that specifies the location and details of the code to be executed.

Link copied to clipboard

The configuration for the source code that defines how the agent runtime code should be executed, including the code location, runtime environment, and entry point.

Link copied to clipboard

The network configuration for a code interpreter. This structure defines how the code interpreter connects to the network.

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard

Contains summary information about a code interpreter. A code interpreter enables Amazon Bedrock Agent to execute code.

Link copied to clipboard

Exception thrown when a resource is modified concurrently by multiple requests.

Link copied to clipboard

This exception is thrown when there is a conflict performing an operation

Link copied to clipboard

Contains consolidation configuration information for a memory strategy.

Link copied to clipboard

Representation of a container configuration.

Link copied to clipboard
sealed class Content

Represents content input for policy generation operations. This structure encapsulates the natural language descriptions or other content formats that are used as input for AI-powered policy generation.

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
sealed class CredentialProvider

A credential provider for gateway authentication. This structure contains the configuration for authenticating with the target endpoint.

Link copied to clipboard

The configuration for a credential provider. This structure defines how the gateway authenticates with the target endpoint.

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard

Defines the name of a custom claim field and rules for finding matches to authenticate its value.

Link copied to clipboard

Input for custom configuration of a memory strategy.

Link copied to clipboard

Contains custom consolidation configuration information.

Link copied to clipboard

Input for a custom consolidation configuration.

Link copied to clipboard

Contains custom extraction configuration information.

Link copied to clipboard

Input for a custom extraction configuration.

Link copied to clipboard

Configuration for inbound JWT-based authorization, specifying how incoming requests should be authenticated.

Link copied to clipboard

Input for creating a custom memory strategy.

Link copied to clipboard

Input configuration for a custom OAuth2 provider.

Link copied to clipboard

Output configuration for a custom OAuth2 provider.

Link copied to clipboard

Contains configurations for a custom reflection strategy.

Link copied to clipboard

Input for a custom reflection configuration.

Link copied to clipboard
sealed class DataSourceConfig

The configuration that specifies where to read agent traces for online evaluation.

Link copied to clipboard

Exception thrown when decryption of a secret fails.

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard

Input for deleting a memory strategy.

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard

Exception thrown when encryption of a secret fails.

Link copied to clipboard

Contains configurations to override the default consolidation step for the episodic memory strategy.

Link copied to clipboard

Contains configurations to override the default extraction step for the episodic memory strategy.

Link copied to clipboard

Input for creating an episodic memory strategy.

Link copied to clipboard

Input for the configuration to override the episodic memory strategy.

Configurations for overriding the consolidation step of the episodic memory strategy.

Configurations for overriding the extraction step of the episodic memory strategy.

Configurations for overriding the reflection step of the episodic memory strategy.

Link copied to clipboard

The configuration for the reflections created with the episodic memory strategy.

Link copied to clipboard

An episodic reflection configuration input.

Link copied to clipboard

Contains configurations to override the default reflection step for the episodic memory strategy.

Link copied to clipboard
sealed class EvaluatorConfig

The configuration that defines how an evaluator assesses agent performance, including the evaluation method and parameters.

Link copied to clipboard
sealed class EvaluatorLevel
Link copied to clipboard

The model configuration that specifies which foundation model to use for evaluation and how to configure it.

Link copied to clipboard
sealed class EvaluatorReference

The reference to an evaluator used in online evaluation configurations, containing the evaluator identifier.

Link copied to clipboard
sealed class EvaluatorStatus
Link copied to clipboard

The summary information about an evaluator, including basic metadata and status information.

Link copied to clipboard
sealed class EvaluatorType
Link copied to clipboard
sealed class ExceptionLevel
Link copied to clipboard

Contains extraction configuration information for a memory strategy.

Link copied to clipboard
class Filter

The filter that applies conditions to agent traces during online evaluation to determine which traces should be evaluated.

Link copied to clipboard
sealed class FilterOperator
Link copied to clipboard
sealed class FilterValue

The value used in filter comparisons, supporting different data types for flexible filtering criteria.

Link copied to clipboard
class Finding

Represents a finding or issue discovered during policy generation or validation. Findings provide insights about potential problems, recommendations, or validation results from policy analysis operations. Finding types include: VALID (policy is ready to use), INVALID (policy has validation errors that must be fixed), NOT_TRANSLATABLE (input couldn't be converted to policy), ALLOW_ALL (policy would allow all actions, potential security risk), ALLOW_NONE (policy would allow no actions, unusable), DENY_ALL (policy would deny all actions, may be too restrictive), and DENY_NONE (policy would deny no actions, ineffective). Review all findings before creating policies from generated assets to ensure they match your security requirements.

Link copied to clipboard
sealed class FindingType
Link copied to clipboard

An API key credential provider for gateway authentication. This structure contains the configuration for authenticating with the target endpoint using an API key.

Link copied to clipboard
Link copied to clipboard

The configuration for an interceptor on a gateway. This structure defines settings for an interceptor that will be invoked during the invocation of the gateway.

Link copied to clipboard

The configuration for a policy engine associated with a gateway. A policy engine is a collection of policies that evaluates and authorizes agent tool calls. When associated with a gateway, the policy engine intercepts all agent requests and determines whether to allow or deny each action based on the defined policies.

Link copied to clipboard
Link copied to clipboard

The configuration for a gateway protocol. This structure defines how the gateway communicates with external services.

Link copied to clipboard
sealed class GatewayProtocolType
Link copied to clipboard
sealed class GatewayStatus
Link copied to clipboard

Contains summary information about a gateway.

Link copied to clipboard

The gateway target.

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard

Input configuration for a GitHub OAuth2 provider.

Link copied to clipboard

Output configuration for a GitHub OAuth2 provider.

Link copied to clipboard

Input configuration for a Google OAuth2 provider.

Link copied to clipboard

Output configuration for a Google OAuth2 provider.

Link copied to clipboard
Link copied to clipboard

Configuration settings for connecting to a supported OAuth2 provider. This includes client credentials and OAuth2 discovery information for providers that have built-in support.

Link copied to clipboard

The configuration details returned for a supported OAuth2 provider, including client credentials and OAuth2 discovery information.

Link copied to clipboard

The configuration parameters that control how the foundation model behaves during evaluation, including response generation settings.

Link copied to clipboard

The interceptor configuration.

Link copied to clipboard

The input configuration of the interceptor.

Link copied to clipboard

This exception is thrown if there was an unexpected error during processing of request

Link copied to clipboard

The configuration to invoke a self-managed memory processing pipeline with.

Link copied to clipboard

The configuration to invoke a self-managed memory processing pipeline with.

Link copied to clipboard
sealed class KeyType
Link copied to clipboard

Contains the KMS configuration for a resource.

Link copied to clipboard

The lambda configuration for the interceptor

Link copied to clipboard

LifecycleConfiguration lets you manage the lifecycle of runtime sessions and resources in AgentCore Runtime. This configuration helps optimize resource utilization by automatically cleaning up idle sessions and preventing long-running instances from consuming resources indefinitely.

Link copied to clipboard

Configuration settings for connecting to LinkedIn services using OAuth2 authentication. This includes the client credentials required to authenticate with LinkedIn's OAuth2 authorization server.

Link copied to clipboard

The configuration details returned for a LinkedIn OAuth2 provider, including the client ID and OAuth2 discovery information.

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard

The configuration for LLM-as-a-Judge evaluation that uses a language model to assess agent performance based on custom instructions and rating scales.

Link copied to clipboard

The configuration for a Model Context Protocol (MCP) gateway. This structure defines how the gateway implements the MCP protocol.

Link copied to clipboard

The Lambda configuration for a Model Context Protocol target. This structure defines how the gateway uses a Lambda function to communicate with the target.

Link copied to clipboard

The target configuration for the MCP server.

Link copied to clipboard

The Model Context Protocol (MCP) configuration for a target. This structure defines how the gateway uses MCP to communicate with the target.

Link copied to clipboard
class Memory

Contains information about a memory resource.

Link copied to clipboard
sealed class MemoryStatus
Link copied to clipboard

Contains information about a memory strategy.

Link copied to clipboard
sealed class MemoryStrategyInput

Contains input information for creating a memory strategy.

Link copied to clipboard
Link copied to clipboard
sealed class MemoryStrategyType
Link copied to clipboard

Contains summary information about a memory resource.

Link copied to clipboard

The trigger configuration based on a message.

Link copied to clipboard

The trigger configuration based on a message.

Link copied to clipboard

Input configuration for a Microsoft OAuth2 provider.

Link copied to clipboard

Output configuration for a Microsoft OAuth2 provider.

Link copied to clipboard

Contains information for modifying a consolidation configuration.

Link copied to clipboard

Contains information for modifying an extraction configuration.

Link copied to clipboard

The configuration for updating invocation settings.

Link copied to clipboard

Contains information for modifying memory strategies.

Link copied to clipboard

Input for modifying a memory strategy.

Link copied to clipboard

Contains information for modifying a reflection configuration.

Link copied to clipboard

The configuration for updating the self-managed memory strategy.

Link copied to clipboard

Contains information for modifying a strategy configuration.

Link copied to clipboard

SecurityConfig for the Agent.

Link copied to clipboard
sealed class NetworkMode
Link copied to clipboard

The definition of a numerical rating scale option that provides a numeric value with its description for evaluation scoring.

Link copied to clipboard

Contains the authorization server metadata for an OAuth2 provider.

Link copied to clipboard

Contains information about an OAuth2 credential provider.

Link copied to clipboard
sealed class Oauth2Discovery

Contains the discovery information for an OAuth2 provider.

Link copied to clipboard

Contains the input configuration for an OAuth2 provider.

Link copied to clipboard

Contains the output configuration for an OAuth2 provider.

Link copied to clipboard

An OAuth credential provider for gateway authentication. This structure contains the configuration for authenticating with the target endpoint using OAuth.

Link copied to clipboard
sealed class OAuthGrantType
Link copied to clipboard
Link copied to clipboard

The summary information about an online evaluation configuration, including basic metadata and execution status.

Link copied to clipboard

The configuration that specifies where evaluation results should be written for monitoring and analysis.

Link copied to clipboard
sealed class OverrideType
Link copied to clipboard
class Policy

Represents a complete policy resource within the AgentCore Policy system. Policies are ARN-able resources that contain Cedar policy statements and associated metadata for controlling agent behavior and access decisions. Each policy belongs to a policy engine and defines fine-grained authorization rules that are evaluated in real-time as agents interact with tools through Gateway. Policies use the Cedar policy language to specify who (principals based on OAuth claims like username, role, or scope) can perform what actions (tool calls) on which resources (Gateways), with optional conditions for attribute-based access control. Multiple policies can apply to a single request, with Cedar's forbid-wins semantics ensuring that security restrictions are never accidentally overridden.

Link copied to clipboard
sealed class PolicyDefinition

Represents the definition structure for policies within the AgentCore Policy system. This structure encapsulates different policy formats and languages that can be used to define access control rules.

Link copied to clipboard

Represents a policy engine resource within the AgentCore Policy system. Policy engines serve as containers for grouping related policies and provide the execution context for policy evaluation and management. Each policy engine can be associated with one Gateway (one engine per Gateway), where it intercepts all agent tool calls and evaluates them against the contained policies before allowing tools to execute. The policy engine maintains the Cedar schema generated from the Gateway's tool manifest, ensuring that policies are validated against the actual tools and parameters available. Policy engines support two enforcement modes that can be configured when associating with a Gateway: log-only mode for testing (evaluates decisions without blocking) and enforce mode for production (actively allows or denies based on policy evaluation).

Link copied to clipboard
sealed class PolicyEngineStatus
Link copied to clipboard

Represents a policy generation request within the AgentCore Policy system. Tracks the AI-powered conversion of natural language descriptions into Cedar policy statements, enabling users to author policies by describing authorization requirements in plain English. The generation process analyzes the natural language input along with the Gateway's tool context and Cedar schema to produce one or more validated policy options. Each generation request tracks the status of the conversion process and maintains findings about the generated policies, including validation results and potential issues. Generated policy assets remain available for one week after successful generation, allowing time to review and create policies from the generated options.

Link copied to clipboard

Represents a generated policy asset from the AI-powered policy generation process within the AgentCore Policy system. Each asset contains a Cedar policy statement generated from natural language input, along with associated metadata and analysis findings to help users evaluate and select the most appropriate policy option.

Link copied to clipboard
Link copied to clipboard
sealed class PolicyStatus
Link copied to clipboard
Link copied to clipboard

The protocol configuration for an agent runtime. This structure defines how the agent runtime communicates with clients.

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
sealed class RatingScale

The rating scale that defines how evaluators should score agent performance, supporting both numerical and categorical scales.

Link copied to clipboard

The recording configuration for a browser. This structure defines how browser sessions are recorded.

Link copied to clipboard

Contains reflection configuration information for a memory strategy.

Link copied to clipboard

Configuration for HTTP request headers that will be passed through to the runtime.

Link copied to clipboard
sealed class Resource

Represents a resource within the AgentCore Policy system. Resources are the targets of policy evaluation. Currently, only AgentCore Gateways are supported as resources for policy enforcement.

Link copied to clipboard

Exception thrown when a resource limit is exceeded.

Link copied to clipboard

This exception is thrown when a resource referenced by the operation does not exist

Link copied to clipboard
sealed class ResourceType
Link copied to clipboard
sealed class RestApiMethod
Link copied to clipboard
class Rule

The evaluation rule that defines sampling configuration, filtering criteria, and session detection settings for online evaluation.

Link copied to clipboard

The Amazon S3 configuration for a gateway. This structure defines how the gateway accesses files in Amazon S3.

Link copied to clipboard

The Amazon S3 location for storing data. This structure defines where in Amazon S3 data is stored.

Link copied to clipboard

Input configuration for a Salesforce OAuth2 provider.

Link copied to clipboard

Output configuration for a Salesforce OAuth2 provider.

Link copied to clipboard

The configuration that controls what percentage of agent traces are sampled for evaluation to manage evaluation volume and costs.

Link copied to clipboard

A schema definition for a gateway target. This structure defines the structure of the API that the target exposes.

Link copied to clipboard
sealed class SchemaType
Link copied to clipboard
sealed class SearchType
Link copied to clipboard
class Secret

Contains information about a secret in AWS Secrets Manager.

Link copied to clipboard

A configuration for a self-managed memory strategy.

Link copied to clipboard

Input configuration for a self-managed memory strategy.

Link copied to clipboard

Contains semantic consolidation override configuration.

Link copied to clipboard

Contains semantic extraction override configuration.

Link copied to clipboard

Input for creating a semantic memory strategy.

Link copied to clipboard

Input for semantic override configuration in a memory strategy.

Input for semantic override consolidation configuration in a memory strategy.

Input for semantic override extraction configuration in a memory strategy.

Link copied to clipboard
sealed class ServerProtocol
Link copied to clipboard

An internal error occurred.

Link copied to clipboard

This exception is thrown when a request is made beyond the service quota

Link copied to clipboard

The configuration that defines how agent sessions are detected and when they are considered complete for evaluation.

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard

Input configuration for a Slack OAuth2 provider.

Link copied to clipboard

Output configuration for a Slack OAuth2 provider.

Link copied to clipboard

Contains configuration information for a memory strategy.

Link copied to clipboard

Contains summary consolidation override configuration.

Link copied to clipboard

Input for creating a summary memory strategy.

Link copied to clipboard

Input for summary override configuration in a memory strategy.

Input for summary override consolidation configuration in a memory strategy.

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
sealed class TargetConfiguration

The configuration for a gateway target. This structure defines how the gateway connects to and interacts with the target endpoint.

Link copied to clipboard
sealed class TargetStatus
Link copied to clipboard

Contains summary information about a gateway target. A target represents an endpoint that the gateway can connect to.

Link copied to clipboard

API rate limit has been exceeded.

Link copied to clipboard

This exception is thrown when the number of requests exceeds the limit

Link copied to clipboard

Trigger configuration based on time.

Link copied to clipboard

Trigger configuration based on time.

Link copied to clipboard

Trigger configuration based on tokens.

Link copied to clipboard

Trigger configuration based on tokens.

Link copied to clipboard

A tool definition for a gateway target. This structure defines a tool that the target exposes through the Model Context Protocol.

Link copied to clipboard
sealed class ToolSchema

A tool schema for a gateway target. This structure defines the schema for a tool that the target exposes through the Model Context Protocol.

Link copied to clipboard
sealed class TriggerCondition

Condition that triggers memory processing.

Link copied to clipboard

Condition that triggers memory processing.

Link copied to clipboard

This exception is thrown when the JWT bearer token is invalid or not found for OAuth bearer token based access

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard

Contains user preference consolidation override configuration.

Link copied to clipboard

Contains user preference extraction override configuration.

Link copied to clipboard

Input for creating a user preference memory strategy.

Link copied to clipboard

Input for user preference override configuration in a memory strategy.

Input for user preference override consolidation configuration in a memory strategy.

Input for user preference override extraction configuration in a memory strategy.

Link copied to clipboard

The input fails to satisfy the constraints specified by the service.

Link copied to clipboard

Stores information about a field passed inside a request that resulted in an exception.

Link copied to clipboard
Link copied to clipboard
class VpcConfig

VpcConfig for the Agent.

Link copied to clipboard

The information about the workload identity.

Link copied to clipboard

Contains information about a workload identity.