Package software.amazon.awssdk.services.bedrockagentcore.model
package software.amazon.awssdk.services.bedrockagentcore.model
-
ClassDescriptionThe A2A (Agent-to-Agent) descriptor configuration for a registry record.The evaluation configuration for an A/B test, specifying which online evaluation configurations to use for measuring variant performance.The statistical results of an A/B test.Summary information about an A/B test.The exception that occurs when you do not have sufficient permissions to perform an action.Contains summary information about an actor in an AgentCore Memory resource.The agent card definition for A2A descriptors, including the schema version and inline content that describes the agent's capabilities.The agent skills descriptor configuration for a registry record.The configuration specifying where to read agent traces from for recommendation analysis.The configuration for a stream that enables programmatic control of a browser session in Amazon Bedrock AgentCore.Contains information about an update to an automation stream.Configuration for HTTP Basic Authentication using credentials stored in Amazon Web Services Secrets Manager.Summary representation for list responsesContains information about a branch in an AgentCore Memory resource.Contains filter criteria for branches when listing events.The browser action to perform.The result of a browser action execution.The status of a browser action execution.Browser enterprise policy configuration.The type of browser enterprise policy.Browser extension configuration.The configuration for a browser profile in Amazon Bedrock AgentCore.The collection of streams associated with a browser session in Amazon Bedrock AgentCore.A condensed representation of a browser session in Amazon Bedrock AgentCore.A certificate to install in the browser or code interpreter session.The location from which to retrieve a certificate.Filter configuration for narrowing down CloudWatch Logs sessions for evaluation.A filter for narrowing down agent traces from CloudWatch Logs based on key-value comparisons.A rule configuration for filtering agent traces from CloudWatch Logs.The configuration for reading agent traces from CloudWatch Logs.Configuration for reading agent traces from CloudWatch Logs for recommendation analysis.CloudWatch Logs destination for batch evaluation resultsThe output produced by executing code in a code interpreter session in Amazon Bedrock AgentCore.A condensed representation of a code interpreter session in Amazon Bedrock AgentCore.Base interface for all event types in CodeInterpreterStreamOutput.The known possible types of events for
CodeInterpreterStreamOutput.A confidence interval for a statistical measurement.A reference to a specific version of a configuration bundle.Maps a tool name to its JSON path within a configuration bundle.The exception that occurs when the request conflicts with the current state of the resource.Contains the content of a memory item.A block of content in a response.An event that contains incremental output from a command execution.An event that signals the start of content streaming from a command execution.An event that signals the completion of a command execution.The contextual information associated with an evaluation, including span context details that identify the specific traces and sessions being evaluated within the agent's execution flow.Statistics for the control variant in an A/B test.Contains conversational content for an event payload.A custom descriptor configuration for a registry record.Where to pull session spans fromContains the descriptor configuration for a registry record.The type of descriptor associated with a registry record.An exception thrown when attempting to create a resource with an identifier that already exists.A content block for ground truth data in evaluation reference inputs.The expected tool call trajectory for trajectory-based evaluation.The input data structure containing agent session spans in OpenTelemetry format.Aggregated results from a batch evaluation, including session completion counts and evaluator score summaries.Metadata for the evaluation, including session-specific ground truth data.A reference input containing ground truth data for evaluation, scoped to a specific context level (session or trace) through its span context.The comprehensive result of an evaluation containing the score, explanation, evaluator metadata, and execution details.The specification of which trace or span IDs to evaluate within the provided input data.An evaluator to run against sessionsStatistical metrics for a single evaluator comparing control and treatment variants.Aggregated statistics for an evaluator.Summary statistics for a single evaluator within a batch evaluation.Contains information about an event in an AgentCore Memory resource.The condition to use for filtering sessions by events.Filter expression for retrieving events based on metadata associated with an event.Configuration for a customer-managed external proxy server.Represents the metadata of a memory extraction job such as the message identifiers that compose this job.Filters for querying memory extraction jobs based on various criteria.The list of messages that compose this extraction job.Metadata information associated with this extraction job.Contains filter criteria for listing events.A value used in filter comparisons, supporting different data types.A filter to restrict which gateway target paths are included in the A/B test.Where to pull ground truth fromGround truth data for a single conversation turn.The input for a ground truth conversation turn.Configuration for AgentCore Browser.Configuration for AgentCore Code Interpreter.Configuration for AgentCore Gateway.Configuration for an Amazon Bedrock model provider.A content block within a message.A delta update to a content block.Event containing a delta update to a content block.The start payload for a content block.Event indicating the start of a content block.Event indicating the end of a content block.Authentication method for calling a Gateway.Configuration for a Google Gemini model provider.Configuration for an inline function tool.A message in the conversation.Event indicating the start of a message.Event indicating the end of a message.Token usage and latency metrics for the invocation.Specification of which model to use.Configuration for an OpenAI model provider.Reasoning content from the model.A delta update to a reasoning content block.A block of reasoning text from the model.Configuration for connecting to a remote MCP server.A skill available to the agent.Latency metrics for the invocation.A content block in the system prompt.Token usage counts for the invocation.A tool available to the agent loop.Configuration union for different tool types.The result of a tool execution.A delta update to a tool result content block.Start payload for a tool result content block.A content block within a tool result.A tool use request from the model.Delta payload for tool use input.Start payload for a tool use content block.Inline ground truth data containing assertions, expected trajectories, and per-turn expected responses.A block of input content.The exception that occurs when the service encounters an unexpected internal error.The input fails to satisfy the constraints specified by AgentCore.Request for InvokeAgentRuntimeCommand operation.The request body structure for theInvokeAgentRuntimeCommandoperation, containing the command to execute and optional configuration parameters.Response for InvokeAgentRuntimeCommand operation.Response handler for the InvokeAgentRuntimeCommand API.Builder forInvokeAgentRuntimeCommandResponseHandler.Visitor for subtypes ofInvokeAgentRuntimeCommandStreamOutput.Builder forInvokeAgentRuntimeCommandResponseHandler.Visitor.Base interface for all event types in InvokeAgentRuntimeCommandStreamOutput.The known possible types of events forInvokeAgentRuntimeCommandStreamOutput.Request for the InvokeBrowser operation.Response for the InvokeBrowser operation.Response handler for the InvokeCodeInterpreter API.Builder forInvokeCodeInterpreterResponseHandler.Visitor for subtypes ofCodeInterpreterStreamOutput.Builder forInvokeCodeInterpreterResponseHandler.Visitor.Response handler for the InvokeHarness API.Builder forInvokeHarnessResponseHandler.Visitor for subtypes ofInvokeHarnessStreamOutput.Builder forInvokeHarnessResponseHandler.Visitor.Base interface for all event types in InvokeHarnessStreamOutput.The known possible types of events forInvokeHarnessStreamOutput.Arguments for a key press action.The result of a key press action.Arguments for a key shortcut action.The result of a key shortcut action.Arguments for a key type action.The result of a key type action.Left expression of the event metadata filter.The configuration for a stream that provides a visual representation of a browser session in Amazon Bedrock AgentCore.The MCP (Model Context Protocol) descriptor configuration for a registry record.Contains the content of a memory record.Filters to apply to metadata associated with a memory.Contains information about a memory record in an AgentCore Memory resource.Input structure to create a new memory record.Input structure to delete an existing memory record.The left-hand side of a memory record metadata filter expression.The value of a memory record metadata entry.Output information returned after processing a memory record operation.The right-hand side of a memory record metadata filter expression.Contains summary information about a memory record.Input structure to update an existing memory record.Metadata information associated with this message.Value associated with theeventMetadatakey.The mouse button to use for a browser mouse action.Arguments for a mouse click action.The result of a mouse click action.Arguments for a mouse drag action.The result of a mouse drag action.Arguments for a mouse move action.The result of a mouse move action.Arguments for a mouse scroll action.The result of a mouse scroll action.Configuration for an OAuth 2.0 credential provider used to authenticate tool calls.Output destination configurationContains the payload content for an event.An online evaluation configuration associated with a specific A/B test variant.Union type representing different proxy configurations.Configuration for domains that should bypass all proxies and connect directly to the internet.Configuration for routing browser traffic through customer-managed proxy servers.Union type representing different proxy authentication methods.The configuration for a recommendation, varying by recommendation type.The evaluation configuration for assessing recommendation quality.A reference to an evaluator used for recommendation assessment.The result of a recommendation, containing the optimized output.A configuration bundle reference in a recommendation result.Summary information about a recommendation.The status of a registry record in its lifecycle.Summary information about a registry record.Contains information about resource content.The location of the browser extension.The exception that occurs when the specified resource does not exist.A structure representing a response chunk that contains exactly one of the possible event types:contentStart,contentDelta, orcontentStop.The exception that occurs when there is a retryable conflict performing an operation.Right expression of theeventMetadatafilter.The exception that occurs when there is an error in the runtime client.The Amazon S3 location configuration of a resource.Arguments for a screenshot action.The image format for a browser screenshot.The result of a screenshot action.Contains search criteria for retrieving memory records.The Amazon Web Services Secrets Manager location configuration.The MCP server definition with a schema version and inline content.The service encountered an internal error.The exception that occurs when the request would cause a service quota to be exceeded.Contains filter criteria for listing sessions.A time range filter for selecting sessions.Metadata for a specific session in a batch evaluation, including ground truth data and test scenario identifiers.Contains summary information about a session in an AgentCore Memory resource.The structured skill definition with a schema version and inline content.The skill markdown definition for agent skills descriptors.The contextual information that uniquely identifies a span within the distributed tracing system.Contains information about an update to a stream.The system prompt input, either as inline text or from a configuration bundle.A system prompt sourced from a configuration bundle version.Configuration for generating system prompt optimization recommendations.The result of a system prompt recommendation, containing the optimized prompt.A reference to a gateway target.The request was denied due to request throttling.The exception that occurs when the request was denied due to request throttling.The token consumption statistics for language model operations during evaluation.The collection of arguments that specify the operation to perform and its parameters when invoking a tool in Amazon Bedrock AgentCore.The tool description content.Tool descriptions sourced from a configuration bundle version.A tool description input containing the tool name and its current description.The output for a single tool description recommendation.Configuration for generating tool description optimization recommendations.The result of a tool description recommendation, containing optimized descriptions.The source of tool descriptions, either inline text or from a configuration bundle.Inline tool description input containing a list of tools.Contains structured content from a tool result.The MCP tools definition with a protocol version and inline content.This exception is thrown when the JWT bearer token is invalid or not found for OAuth bearer token based accessThe 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.The exception that occurs when the input fails to satisfy the constraints specified by the service.Stores information about a field passed inside a request that resulted in an exception.A variant in an A/B test, representing either the control (C) or treatment (T1) configuration.The configuration for an A/B test variant.Statistical results for a treatment variant compared against the control.The configuration that defines the dimensions of a browser viewport in a browser session.