Namespace Google.Apis.CustomerEngagementSuite.v1beta.Data

Classes

Action

Configuration of an Action for the tool to use. Note: This can be either an Action or an Operation. See https://cloud.google.com/integration-connectors/docs/entities-operation-action for details.

Agent

An agent acts as the fundamental building block that provides instructions to the Large Language Model (LLM) for executing specific tasks.

AgentAgentToolset

A toolset with a selection of its tools.

AgentLlmAgent

Default agent type. The agent uses instructions and callbacks specified in the agent to perform the task using a large language model.

The agent which will transfer execution to a remote Dialogflow CX agent. The Dialogflow agent will process subsequent user queries until the session ends or flow ends, and the control is transferred back to the parent CES agent.

AgentTransfer

Represents an event indicating the transfer of a conversation to a different agent.

AggregatedMetrics

Aggregated metrics for an evaluation or evaluation dataset.

AggregatedMetricsHallucinationMetrics

Metrics for hallucination results.

AggregatedMetricsMetricsByAppVersion

Metrics aggregated per app version.

AggregatedMetricsMetricsByTurn

Metrics aggregated per turn.

AggregatedMetricsSemanticSimilarityMetrics

Metrics for semantic similarity results.

AggregatedMetricsToolCallLatencyMetrics

Metrics for tool call latency.

AggregatedMetricsToolMetrics

Metrics for a single tool.

AggregatedMetricsTurnLatencyMetrics

Metrics for turn latency.

AmbientSoundConfig

Configuration for the ambient sound to be played with the synthesized agent response, to enhance the naturalness of the conversation.

ApiAuthentication

Authentication information required for API calls.

ApiKeyConfig

Configurations for authentication with API key.

App

An app serves as a top-level container for a group of agents, including the root agent and its sub-agents, along with their associated configurations. These agents work together to achieve specific goals within the app's context.

AppSnapshot

A snapshot of the app.

AppVariableDeclaration

Defines the structure and metadata for a variable.

AppVersion

In Customer Engagement Suite (CES), an app version is a snapshot of the app at a specific point in time. It is immutable and cannot be modified once created.

AudioProcessingConfig

Configuration for how the input and output audio should be processed and delivered.

AudioRecordingConfig

Configuration for how the audio interactions should be recorded.

BargeInConfig

Configuration for how the user barge-in activities should be handled.

BatchDeleteConversationsRequest

Request message for AgentService.BatchDeleteConversations.

BatchDeleteConversationsResponse

Response message for AgentService.BatchDeleteConversations.

BearerTokenConfig

Configurations for authentication with a bearer token.

BigQueryExportSettings

Settings to describe the BigQuery export behaviors for the app.

Blob

Represents a blob input or output in the conversation.

Callback

A callback defines the custom logic to be executed at various stages of agent interaction.

CancelOperationRequest

The request message for Operations.CancelOperation.

Changelog

Changelogs represent a change made to the app or to an resource within the app.

ChannelProfile

A ChannelProfile configures the agent's behavior for a specific communication channel, such as web UI or telephony.

ChannelProfilePersonaProperty

Represents the persona property of a channel.

ChannelProfileWebWidgetConfig

Message for configuration for the web widget.

ChannelProfileWebWidgetConfigSecuritySettings

Security settings for the web widget.

Chunk

A chunk of content within a message.

Citations

Citations associated with the agent response.

CitationsCitedChunk

Piece of cited information.

ClientCertificateSettings

Settings for custom client certificates.

ClientFunction

Represents a client-side function that the agent can invoke. When the tool is chosen by the agent, control is handed off to the client. The client is responsible for executing the function and returning the result as a ToolResponse to continue the interaction with the agent.

CloudLoggingSettings

Settings to describe the Cloud Logging behaviors for the app.

CodeBlock

A code block to be executed instead of a real tool call.

ConnectorTool

A ConnectorTool allows connections to different integrations. See: https://cloud.google.com/integration-connectors/docs/overview.

ConnectorToolset

A toolset that generates tools from an Integration Connectors Connection.

Conversation

A conversation represents an interaction between an end user and the CES app.

ConversationLoggingSettings

Settings to describe the conversation logging behaviors for the app.

ConversationTurn

All information about a single turn in the conversation.

DataStore

A DataStore resource in Vertex AI Search.

DataStoreConnectorConfig

The connector config for the data store connection.

DataStoreSettings

Data store related settings for the app.

DataStoreSettingsEngine

An engine to which the data stores are connected. See Vertex AI Search: https://cloud.google.com/generative-ai-app-builder/docs/enterprise-search-introduction.

DataStoreTool

Tool to retrieve from Vertex AI Search datastore or engine for grounding. Accepts either a datastore or an engine, but not both. See Vertex AI Search: https://cloud.google.com/generative-ai-app-builder/docs/enterprise-search-introduction.

DataStoreToolBoostSpec

Boost specification to boost certain documents.

DataStoreToolBoostSpecConditionBoostSpec

Boost specification for a condition.

DataStoreToolBoostSpecConditionBoostSpecBoostControlSpec

Specification for custom ranking based on customer specified attribute value. It provides more controls for customized ranking than the simple (condition, boost) combination above.

DataStoreToolBoostSpecConditionBoostSpecBoostControlSpecControlPoint

The control points used to define the curve. The curve defined through these control points can only be monotonically increasing or decreasing(constant values are acceptable).

DataStoreToolBoostSpecs

Boost specifications to boost certain documents. For more information, please refer to https://cloud.google.com/generative-ai-app-builder/docs/boosting.

DataStoreToolDataStoreSource

Configuration for searching within a specific DataStore.

DataStoreToolEngineSource

Configuration for searching within an Engine, potentially targeting specific DataStores.

DataStoreToolGroundingConfig

Grounding configuration.

DataStoreToolModalityConfig

If specified, will apply the given configuration for the specified modality.

DataStoreToolRewriterConfig

Rewriter configuration.

DataStoreToolSummarizationConfig

Summarization configuration.

DeleteEvaluationRunOperationMetadata

Operation metadata for EvaluationService.DeleteEvaluationRun.

Deployment

A deployment represents an immutable, queryable version of the app. It is used to deploy an app version with a specific channel profile.

Empty

A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }

EndSession

Indicates the session has terminated, due to either successful completion (e.g. user says "Good bye!" ) or an agent escalation. The agent will not process any further inputs after session is terminated and the client should half-close and disconnect after receiving all remaining responses from the agent.

EndUserAuthConfig

End-user authentication configuration used for Connection calls. The field values must be the names of context variables in the format $context.variables..

EndUserAuthConfigOauth2AuthCodeConfig

Oauth 2.0 Authorization Code authentication configuration.

EndUserAuthConfigOauth2JwtBearerConfig

JWT Profile Oauth 2.0 Authorization Grant authentication configuration.

Evaluation

An evaluation represents all of the information needed to simulate and evaluate an agent.

EvaluationConfig

EvaluationConfig configures settings for running the evaluation.

EvaluationDataset

An evaluation dataset represents a set of evaluations that are grouped together basaed on shared tags.

EvaluationErrorInfo

Information about an error encountered during an evaluation execution.

EvaluationExpectation

An evaluation expectation represents a specific criteria to evaluate against.

EvaluationExpectationLlmCriteria

Configuration for LLM-based evaluation criteria.

EvaluationGolden

The steps required to replay a golden conversation.

EvaluationGoldenExpectation

Represents a single, checkable requirement.

EvaluationGoldenTurn

A golden turn defines a single turn in a golden conversation.

EvaluationMetricsThresholds

Threshold settings for metrics in an Evaluation.

EvaluationMetricsThresholdsGoldenEvaluationMetricsThresholds

Settings for golden evaluations.

EvaluationMetricsThresholdsGoldenEvaluationMetricsThresholdsExpectationLevelMetricsThresholds

Expectation level metrics thresholds.

EvaluationMetricsThresholdsGoldenEvaluationMetricsThresholdsTurnLevelMetricsThresholds

Turn level metrics thresholds.

EvaluationPersona

A persona represents an end user in an evaluation.

EvaluationPersonaSpeechConfig

Configuration for Text-to-Speech generation.

EvaluationResult

An evaluation result represents the output of running an Evaluation.

EvaluationResultEvaluationExpectationResult

The result of a single evaluation expectation.

EvaluationResultGoldenExpectationOutcome

Specifies the expectation and the result of that expectation.

EvaluationResultGoldenExpectationOutcomeToolInvocationResult

The result of the tool invocation check.

EvaluationResultGoldenResult

The result of a golden evaluation.

EvaluationResultGoldenResultTurnReplayResult

The result of running a single turn of the golden conversation.

EvaluationResultHallucinationResult

The result of the hallucination check for a single turn.

EvaluationResultOverallToolInvocationResult

The result of the overall tool invocation check.

EvaluationResultScenarioExpectationOutcome

The outcome of a scenario expectation.

EvaluationResultScenarioExpectationOutcomeObservedToolCall

The observed tool call and response.

EvaluationResultScenarioResult

The outcome of a scenario evaluation.

EvaluationResultScenarioRubricOutcome

The outcome of the evaluation against the rubric.

EvaluationResultSemanticSimilarityResult

The result of the semantic similarity check.

EvaluationResultSpanLatency

The latency of a span execution.

EvaluationResultTaskCompletionResult

The result of the task completion check for the conversation.

EvaluationResultToolCallLatency

The latency of a tool call execution.

EvaluationResultUserGoalSatisfactionResult

The result of a user goal satisfaction check for a conversation.

EvaluationRun

An evaluation run represents an all the evaluation results from an evaluation execution.

EvaluationRunEvaluationRunSummary

Contains the summary of passed and failed result counts for a specific evaluation in an evaluation run.

EvaluationRunProgress

The progress of the evaluation run.

EvaluationScenario

The config for a scenario

EvaluationScenarioExpectation

The expectation to evaluate the conversation produced by the simulation.

EvaluationScenarioExpectationToolExpectation

The tool call and response pair to be evaluated.

EvaluationScenarioUserFact

Facts about the user as a key value pair.

EvaluationSettings

Settings for evaluation.

EvaluationStep

A step defines a singular action to happen during the evaluation.

Event

Event input.

Example

An example represents a sample conversation between the user and the agent(s).

ExecuteToolRequest

Request message for ToolService.ExecuteTool.

ExecuteToolResponse

Response message for ToolService.ExecuteTool.

ExportAppRequest

Request message for AgentService.ExportApp.

ExportAppResponse

Response message for AgentService.ExportApp.

ExpressionCondition

Expression condition based on session state.

FileSearchTool

The file search tool allows the agent to search across the files uploaded by the app/agent developer. It has presets to give relatively good quality search over the uploaded files and summarization of the retrieved results.

GenerateAppResourceResponse

Response message for AgentService.GenerateAppResource.

GenerateAppResourceResponseAppResources

The list of app resources generated by the LLM assistant.

GenerateAppResourceResponseEvaluations

The list of evaluations generated by the LLM assistant.

GenerateAppResourceResponseGenerateResultInfo

This provides additional information about the generated result.

GenerateAppResourceResponseTools

The list of tools generated by the LLM assistant.

GenerateChatTokenRequest

Request message for WidgetService.GenerateChatToken.

GenerateChatTokenResponse

Response message for WidgetService.GenerateChatToken.

GenerateEvaluationOperationMetadata

Operation metadata for EvaluationService.GenerateEvaluation.

GenerateEvaluationRequest

Request message for EvaluationService.GenerateEvaluation.

GoogleSearchSuggestions

Search suggestions from Google Search Tool.

GoogleSearchTool

Represents a tool to perform Google web searches for grounding. See https://cloud.google.com/customer-engagement-ai/conversational-agents/ps/tool#google-search.

GoogleSearchToolPromptConfig

Prompt settings used by the model when processing or summarizing the google search results.

Guardrail

Guardrail contains a list of checks and balances to keep the agents safe and secure.

GuardrailCodeCallback

Guardrail that blocks the conversation based on the code callbacks provided.

GuardrailContentFilter

Guardrail that bans certain content from being used in the conversation.

GuardrailLlmPolicy

Guardrail that blocks the conversation if the LLM response is considered violating the policy based on the LLM classification.

GuardrailLlmPromptSecurity

Guardrail that blocks the conversation if the input is considered unsafe based on the LLM classification.

GuardrailLlmPromptSecurityDefaultSecuritySettings

Configuration for default system security settings.

GuardrailModelSafety

Model safety settings overrides. When this is set, it will override the default settings and trigger the guardrail if the response is considered unsafe.

GuardrailModelSafetySafetySetting

Safety setting.

Image

Represents an image input or output in the conversation.

ImportAppRequest

Request message for AgentService.ImportApp.

ImportAppRequestImportOptions

Configuration options for the app import process. These options control how the import behaves, particularly when conflicts arise with existing app data.

ImportAppResponse

Response message for AgentService.ImportApp.

ImportEvaluationsOperationMetadata

Represents the metadata of the long-running operation for EvaluationService.ImportEvaluations.

ImportEvaluationsRequest

Request message for EvaluationService.ImportEvaluations.

ImportEvaluationsRequestConversationList

A list of conversation resource names.

ImportEvaluationsRequestImportOptions

Configuration options for the evaluation import process. These options control how the import behaves, particularly when conflicts arise with existing evaluations data.

ImportEvaluationsResponse

Response message for EvaluationService.ImportEvaluations.

InputAudioConfig

InputAudioConfig configures how the CES agent should interpret the incoming audio data.

LanguageSettings

Language settings of the app.

LatencyReport

Latency report for the evaluation run.

LatencyReportCallbackLatency

Latency metrics for a single callback.

LatencyReportGuardrailLatency

Latency metrics for a single guardrail.

LatencyReportLatencyMetrics

Latency metrics for a component.

LatencyReportLlmCallLatency

Latency metrics for a single LLM call.

LatencyReportToolLatency

Latency metrics for a single tool.

ListAgentsResponse

Response message for AgentService.ListAgents.

ListAppVersionsResponse

Response message for AgentService.ListAppVersions.

ListAppsResponse

Response message for AgentService.ListApps.

ListChangelogsResponse

Response message for AgentService.ListChangelogs.

ListConversationsResponse

Response message for AgentService.ListConversations.

ListDeploymentsResponse

Response message for AgentService.ListDeployments.

ListEvaluationDatasetsResponse

Response message for EvaluationService.ListEvaluationDatasets.

ListEvaluationExpectationsResponse

Response message for EvaluationService.ListEvaluationExpectations.

ListEvaluationResultsResponse

Response message for EvaluationService.ListEvaluationResults.

ListEvaluationRunsResponse

Response message for EvaluationService.ListEvaluationRuns.

ListEvaluationsResponse

Response message for EvaluationService.ListEvaluations.

ListExamplesResponse

Response message for AgentService.ListExamples.

ListGuardrailsResponse

Response message for AgentService.ListGuardrails.

ListLocationsResponse

The response message for Locations.ListLocations.

ListOperationsResponse

The response message for Operations.ListOperations.

ListScheduledEvaluationRunsResponse

Response message for EvaluationService.ListScheduledEvaluationRuns.

ListToolsResponse

Response message for AgentService.ListTools.

ListToolsetsResponse

Response message for AgentService.ListToolsets.

Location

A resource that represents a Google Cloud location.

LoggingSettings

Settings to describe the logging behaviors for the app.

McpTool

An MCP tool. See https://modelcontextprotocol.io/specification/2025-06-18/server/tools for more details.

McpToolset

A toolset that contains a list of tools that are offered by the MCP server.

Message

A message within a conversation.

MetricAnalysisSettings

Settings to describe the conversation data collection behaviors for LLM analysis metrics pipeline.

ModelSettings

Model settings contains various configurations for the LLM model.

OAuthConfig

Configurations for authentication with OAuth.

Omnichannel

Represents an Omnichannel resource.

OmnichannelIntegrationConfig

OmnichannelIntegrationConfig contains all App integration configs.

OmnichannelIntegrationConfigCesAppConfig

Configs for CES app.

OmnichannelIntegrationConfigChannelConfig

ChannelConfig contains config for various of app integration.

OmnichannelIntegrationConfigRoutingConfig

Routing config specify how/who to route app events to a subscriber.

OmnichannelIntegrationConfigSubscriberConfig

Configs of subscribers.

OmnichannelIntegrationConfigWhatsappConfig

How Omnichannel should receive/reply events from WhatsApp.

OmnichannelOperationMetadata

Represents the metadata of the long-running operation.

OpenApiTool

A remote API tool defined by an OpenAPI schema.

OpenApiToolset

A toolset that contains a list of tools that are defined by an OpenAPI schema.

Operation

This resource represents a long-running operation that is the result of a network API call.

OperationMetadata

Represents the metadata of the long-running operation.

OptimizationConfig

Configuration for running the optimization step after the evaluation run.

OutputAudioConfig

OutputAudioConfig configures how the CES agent should synthesize outgoing audio responses.

PersonaRunConfig

Configuration for running an evaluation for a specific persona.

PythonCodeCondition

Python code block to evaluate the condition.

PythonFunction

A Python function tool.

RedactionConfig

Configuration to instruct how sensitive data should be handled.

RestoreAppVersionRequest

Request message for AgentService.RestoreAppVersion

RetrieveToolSchemaRequest

Request message for ToolService.RetrieveToolSchema.

RetrieveToolSchemaResponse

Response message for ToolService.RetrieveToolSchema.

RetrieveToolsRequest

Request message for ToolService.RetrieveTools.

RetrieveToolsResponse

Response message for ToolService.RetrieveTools.

RunEvaluationRequest

Request message for EvaluationService.RunEvaluation.

RunSessionRequest

Request message for SessionService.RunSession.

RunSessionResponse

Response message for SessionService.RunSession.

ScheduledEvaluationRun

Represents a scheduled evaluation run configuration.

ScheduledEvaluationRunSchedulingConfig

Eval scheduling configuration details

Schema

Represents a select subset of an OpenAPI 3.0 schema object.

ServiceAccountAuthConfig

Configurations for authentication using a custom service account.

ServiceAgentIdTokenAuthConfig

Configurations for authentication with ID token generated from service agent.

ServiceDirectoryConfig

Configuration for tools using Service Directory.

SessionConfig

The configuration for the session.

SessionConfigRemoteDialogflowQueryParameters

QueryParameters to send to the remote Dialogflow agent when the session control is transferred to the remote agent.

SessionInput

Input for the session.

SessionOutput

Output for the session.

SessionOutputDiagnosticInfo

Contains execution details during the processing.

Span

A span is a unit of work or a single operation during the request processing.

Status

The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC. Each Status message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the API Design Guide.

SynthesizeSpeechConfig

Configuration for how the agent response should be synthesized.

SystemTool

Pre-defined system tool.

TestPersonaVoiceRequest

Request message for EvaluationService.TestPersonaVoice.

TestPersonaVoiceResponse

Response message for EvaluationService.TestPersonaVoice.

TimeZoneSettings

TimeZone settings of the app.

TlsConfig

The TLS configuration.

TlsConfigCaCert

The CA certificate.

Tool

A tool represents an action that the CES agent can take to achieve certain goals.

ToolCall

Request for the client or the agent to execute the specified tool.

ToolCalls

Request for the client to execute the tools and return the execution results before continuing the session.

ToolFakeConfig

Configuration for tool behavior in fake mode.

ToolResponse

The execution result of a specific tool from the client or the agent.

ToolResponses

Execution results for the requested tool calls from the client.

Toolset

A toolset represents a group of dynamically managed tools that can be used by the agent.

ToolsetTool

A tool that is created from a toolset.

TransferRule

Rule for transferring to a specific agent.

TransferRuleDeterministicTransfer

Deterministic transfer rule. When the condition evaluates to true, the transfer occurs.

TransferRuleDisablePlannerTransfer

A rule that prevents the planner from transferring to the target agent.

TriggerAction

Action that is taken when a certain precondition is met.

TriggerActionGenerativeAnswer

The agent will immediately respond with a generative answer.

TriggerActionRespondImmediately

The agent will immediately respond with a preconfigured response.

TriggerActionResponse

Represents a response from the agent.

TriggerActionTransferAgent

The agent will transfer the conversation to a different agent.

WebSearchQuery

Represents a single web search query and its associated search uri.

WidgetTool

Represents a widget tool that the agent can invoke. When the tool is chosen by the agent, agent will return the widget to the client. The client is responsible for processing the widget and generating the next user query to continue the interaction with the agent.