Gemini Enterprise for Customer Experience v1 API - Namespace Google.Cloud.Ces.V1 (1.0.0-beta01)

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.

Container for nested types declared in the Action message type.

Entity CRUD operation specification.

Container for nested types declared in the EntityOperation message type.

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

Container for nested types declared in the Agent message type.

A toolset with a selection of its tools.

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.

Resource name for the Agent resource.

The service that manages agent-related resources in Gemini Enterprise for Customer Engagement (CES).

Base class for server-side implementations of AgentService

Client for AgentService

AgentService client wrapper, for convenient use.

Builder class for AgentServiceClient to provide simple configuration of credentials, endpoint etc.

AgentService client wrapper implementation, for convenient use.

Settings for AgentServiceClient instances.

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

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

Container for nested types declared in the AmbientSoundConfig message type.

Authentication information required for API calls.

Configurations for authentication with API key.

Container for nested types declared in the ApiKeyConfig message type.

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.

Container for nested types declared in the App message type.

Defines the structure and metadata for a variable.

Resource name for the App resource.

A snapshot of the app.

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.

Resource name for the AppVersion resource.

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

Configuration for how the audio interactions should be recorded.

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

Request message for [AgentService.BatchDeleteConversations][google.cloud.ces.v1.AgentService.BatchDeleteConversations].

Response message for [AgentService.BatchDeleteConversations][google.cloud.ces.v1.AgentService.BatchDeleteConversations].

Configurations for authentication with a bearer token.

The top-level message sent by the client for the [SessionService.BidiRunSession][google.cloud.ces.v1.SessionService.BidiRunSession] method.

The top-level message returned from [SessionService.BidiRunSession][google.cloud.ces.v1.SessionService.BidiRunSession] method.

Settings to describe the BigQuery export behaviors for the app.

Represents a blob input or output in the conversation.

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

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

Resource name for the Changelog resource.

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

Container for nested types declared in the ChannelProfile message type.

Represents the persona property of a channel.

Container for nested types declared in the PersonaProperty message type.

Message for configuration for the web widget.

Container for nested types declared in the WebWidgetConfig message type.

Security settings for the web widget.

A chunk of content within a message.

Citations associated with the agent response.

Container for nested types declared in the Citations message type.

Piece of cited information.

Settings for custom client certificates.

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][google.cloud.ces.v1.ToolResponse] to continue the interaction with the agent.

Settings to describe the Cloud Logging behaviors for the app.

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

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

A toolset that generates tools from an Integration Connectors Connection.

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

Container for nested types declared in the Conversation message type.

All information about a single turn in the conversation.

Settings to describe the conversation logging behaviors for the app.

Resource name for the Conversation resource.

Request message for [AgentService.CreateAgent][google.cloud.ces.v1.AgentService.CreateAgent].

Request message for [AgentService.CreateApp][google.cloud.ces.v1.AgentService.CreateApp].

Request message for [AgentService.CreateAppVersion][google.cloud.ces.v1.AgentService.CreateAppVersion]

Request message for [AgentService.CreateDeployment][google.cloud.ces.v1.AgentService.CreateDeployment].

Request message for [AgentService.CreateExample][google.cloud.ces.v1.AgentService.CreateExample].

Request message for [AgentService.CreateGuardrail][google.cloud.ces.v1.AgentService.CreateGuardrail].

Request message for [AgentService.CreateTool][google.cloud.ces.v1.AgentService.CreateTool].

Request message for [AgentService.CreateToolset][google.cloud.ces.v1.AgentService.CreateToolset].

A DataStore resource in Vertex AI Search.

Container for nested types declared in the DataStore message type.

The connector config for the data store connection.

Data store related settings for the app.

Container for nested types declared in the DataStoreSettings message type.

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 .

Container for nested types declared in the Engine message type.

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 .

Container for nested types declared in the DataStoreTool message type.

Boost specification to boost certain documents.

Container for nested types declared in the BoostSpec message type.

Boost specification for a condition.

Container for nested types declared in the ConditionBoostSpec message type.

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

Container for nested types declared in the BoostControlSpec message type.

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).

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

Configuration for searching within a specific DataStore.

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

Grounding configuration.

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

Container for nested types declared in the ModalityConfig message type.

Rewriter configuration.

Summarization configuration.

Resource name for the Dataset resource.

Resource name for the DeidentifyTemplate resource.

Request message for [AgentService.DeleteAgent][google.cloud.ces.v1.AgentService.DeleteAgent].

Request message for [AgentService.DeleteApp][google.cloud.ces.v1.AgentService.DeleteApp].

Request message for [AgentService.DeleteAppVersion][google.cloud.ces.v1.AgentService.DeleteAppVersion].

Request message for [AgentService.DeleteConversation][google.cloud.ces.v1.AgentService.DeleteConversation].

Request message for [AgentService.DeleteDeployment][google.cloud.ces.v1.AgentService.DeleteDeployment].

Request message for [AgentService.DeleteExample][google.cloud.ces.v1.AgentService.DeleteExample].

Request message for [AgentService.DeleteGuardrail][google.cloud.ces.v1.AgentService.DeleteGuardrail].

Request message for [AgentService.DeleteTool][google.cloud.ces.v1.AgentService.DeleteTool].

Request message for [AgentService.DeleteToolset][google.cloud.ces.v1.AgentService.DeleteToolset].

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

Resource name for the Deployment resource.

Resource name for the DialogflowAgent resource.

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.

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

Container for nested types declared in the EndUserAuthConfig message type.

Oauth 2.0 Authorization Code authentication configuration.

JWT Profile Oauth 2.0 Authorization Grant authentication configuration.

Resource name for the Engine resource.

Threshold settings for metrics in an Evaluation.

Container for nested types declared in the EvaluationMetricsThresholds message type.

Settings for golden evaluations.

Container for nested types declared in the GoldenEvaluationMetricsThresholds message type.

Expectation level metrics thresholds.

Turn level metrics thresholds.

Container for nested types declared in the TurnLevelMetricsThresholds message type.

Settings for matching tool calls.

Container for nested types declared in the ToolMatchingSettings message type.

Event input.

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

Resource name for the Example resource.

Request message for [ToolService.ExecuteTool][google.cloud.ces.v1.ToolService.ExecuteTool].

Response message for [ToolService.ExecuteTool][google.cloud.ces.v1.ToolService.ExecuteTool].

Request message for [AgentService.ExportApp][google.cloud.ces.v1.AgentService.ExportApp].

Container for nested types declared in the ExportAppRequest message type.

Response message for [AgentService.ExportApp][google.cloud.ces.v1.AgentService.ExportApp].

Expression condition based on session state.

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.

Container for nested types declared in the FileSearchTool message type.

Request message for [WidgetService.GenerateChatToken][google.cloud.ces.v1.WidgetService.GenerateChatToken].

Response message for [WidgetService.GenerateChatToken][google.cloud.ces.v1.WidgetService.GenerateChatToken].

Request message for [AgentService.GetAgent][google.cloud.ces.v1.AgentService.GetAgent].

Request message for [AgentService.GetApp][google.cloud.ces.v1.AgentService.GetApp].

Request message for [AgentService.GetAppVersion][google.cloud.ces.v1.AgentService.GetAppVersion].

Request message for [AgentService.GetChangelog][google.cloud.ces.v1.AgentService.GetChangelog].

Request message for [AgentService.GetConversation][google.cloud.ces.v1.AgentService.GetConversation].

Request message for [AgentService.GetDeployment][google.cloud.ces.v1.AgentService.GetDeployment].

Request message for [AgentService.GetExample][google.cloud.ces.v1.AgentService.GetExample].

Request message for [AgentService.GetGuardrail][google.cloud.ces.v1.AgentService.GetGuardrail].

Request message for [AgentService.GetTool][google.cloud.ces.v1.AgentService.GetTool].

Request message for [AgentService.GetToolset][google.cloud.ces.v1.AgentService.GetToolset].

Indicates that the server will disconnect soon and the client should half-close and restart the connection.

Search suggestions from [Google Search Tool][google.cloud.ces.v1.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 .

Container for nested types declared in the GoogleSearchTool message type.

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

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

Container for nested types declared in the Guardrail message type.

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

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

Container for nested types declared in the ContentFilter message type.

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

Container for nested types declared in the LlmPolicy message type.

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

Container for nested types declared in the LlmPromptSecurity message type.

Configuration for default system security settings.

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

Container for nested types declared in the ModelSafety message type.

Safety setting.

Resource name for the Guardrail resource.

Represents an image input or output in the conversation.

Request message for [AgentService.ImportApp][google.cloud.ces.v1.AgentService.ImportApp].

Container for nested types declared in the ImportAppRequest message type.

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

Container for nested types declared in the ImportOptions message type.

Response message for [AgentService.ImportApp][google.cloud.ces.v1.AgentService.ImportApp].

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

Resource name for the InspectTemplate resource.

Indicates the agent's audio response has been interrupted. The client should immediately stop any current audio playback (e.g., due to user barge-in or a new agent response being generated).

Language settings of the app.

Request message for [AgentService.ListAgents][google.cloud.ces.v1.AgentService.ListAgents].

Response message for [AgentService.ListAgents][google.cloud.ces.v1.AgentService.ListAgents].

Request message for [AgentService.ListAppVersions][google.cloud.ces.v1.AgentService.ListAppVersions].

Response message for [AgentService.ListAppVersions][google.cloud.ces.v1.AgentService.ListAppVersions].

Request message for [AgentService.ListApps][google.cloud.ces.v1.AgentService.ListApps].

Response message for [AgentService.ListApps][google.cloud.ces.v1.AgentService.ListApps].

Request message for [AgentService.ListChangelogs][google.cloud.ces.v1.AgentService.ListChangelogs].

Response message for [AgentService.ListChangelogs][google.cloud.ces.v1.AgentService.ListChangelogs].

Request message for [AgentService.ListConversations][google.cloud.ces.v1.AgentService.ListConversations].

Response message for [AgentService.ListConversations][google.cloud.ces.v1.AgentService.ListConversations].

Request message for [AgentService.ListDeployments][google.cloud.ces.v1.AgentService.ListDeployments].

Response message for [AgentService.ListDeployments][google.cloud.ces.v1.AgentService.ListDeployments].

Request message for [AgentService.ListExamples][google.cloud.ces.v1.AgentService.ListExamples].

Response message for [AgentService.ListExamples][google.cloud.ces.v1.AgentService.ListExamples].

Request message for [AgentService.ListGuardrails][google.cloud.ces.v1.AgentService.ListGuardrails].

Response message for [AgentService.ListGuardrails][google.cloud.ces.v1.AgentService.ListGuardrails].

Request message for [AgentService.ListTools][google.cloud.ces.v1.AgentService.ListTools].

Response message for [AgentService.ListTools][google.cloud.ces.v1.AgentService.ListTools].

Request message for [AgentService.ListToolsets][google.cloud.ces.v1.AgentService.ListToolsets].

Response message for [AgentService.ListToolsets][google.cloud.ces.v1.AgentService.ListToolsets].

Settings to describe the logging behaviors for the app.

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

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

A message within a conversation.

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

Model settings contains various configurations for the LLM model.

Configurations for authentication with OAuth.

Container for nested types declared in the OAuthConfig message type.

Represents an Omnichannel resource.

OmnichannelIntegrationConfig contains all App integration configs.

Container for nested types declared in the OmnichannelIntegrationConfig message type.

Configs for CES app.

ChannelConfig contains config for various of app integration.

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

Configs of subscribers.

How Omnichannel should receive/reply events from WhatsApp.

Resource name for the Omnichannel resource.

Represents the metadata of the long-running operation.

A remote API tool defined by an OpenAPI schema.

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

Represents the metadata of the long-running operation.

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

Python code block to evaluate the condition.

A Python function tool.

Speech recognition result for the audio input.

Configuration to instruct how sensitive data should be handled.

Request message for [AgentService.RestoreAppVersion][google.cloud.ces.v1.AgentService.RestoreAppVersion]

Response message for [AgentService.RestoreAppVersion][google.cloud.ces.v1.AgentService.RestoreAppVersion]

Request message for [ToolService.RetrieveToolSchema][google.cloud.ces.v1.ToolService.RetrieveToolSchema].

Response message for [ToolService.RetrieveToolSchema][google.cloud.ces.v1.ToolService.RetrieveToolSchema].

Request message for [ToolService.RetrieveTools][google.cloud.ces.v1.ToolService.RetrieveTools].

Response message for [ToolService.RetrieveTools][google.cloud.ces.v1.ToolService.RetrieveTools].

Request message for [SessionService.RunSession][google.cloud.ces.v1.SessionService.RunSession].

Response message for [SessionService.RunSession][google.cloud.ces.v1.SessionService.RunSession].

Represents a select subset of an OpenAPI 3.0 schema object.

Container for nested types declared in the Schema message type.

Resource name for the SecretVersion resource.

Configurations for authentication using a custom service account.

Configurations for authentication with ID token generated from service agent.

Configuration for tools using Service Directory.

Resource name for the Service resource.

The configuration for the session.

Container for nested types declared in the SessionConfig message type.

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

Input for the session.

Resource name for the Session resource.

Output for the session.

Container for nested types declared in the SessionOutput message type.

Contains execution details during the processing.

Session service provides APIs for interacting with CES agents.

Base class for server-side implementations of SessionService

Client for SessionService

SessionService client wrapper, for convenient use.

Bidirectional streaming methods for BidiRunSession(CallSettings, BidirectionalStreamingSettings) .

Builder class for SessionServiceClient to provide simple configuration of credentials, endpoint etc.

SessionService client wrapper implementation, for convenient use.

Settings for SessionServiceClient instances.

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

Configuration for how the agent response should be synthesized.

Pre-defined system tool.

TimeZone settings of the app.

The TLS configuration.

Container for nested types declared in the TlsConfig message type.

The CA certificate.

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

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

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

Configuration for tool behavior in fake mode.

Resource name for the Tool resource.

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

Execution results for the requested tool calls from the client.

Tool service provides APIs for interacting with CES tools.

Base class for server-side implementations of ToolService

Client for ToolService

ToolService client wrapper, for convenient use.

Builder class for ToolServiceClient to provide simple configuration of credentials, endpoint etc.

ToolService client wrapper implementation, for convenient use.

Settings for ToolServiceClient instances.

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

Resource name for the Toolset resource.

A tool that is created from a toolset.

Rule for transferring to a specific agent.

Container for nested types declared in the TransferRule message type.

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

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

Action that is taken when a certain precondition is met.

Container for nested types declared in the TriggerAction message type.

The agent will immediately respond with a generative answer.

The agent will immediately respond with a preconfigured response.

Represents a response from the agent.

The agent will transfer the conversation to a different agent.

Request message for [AgentService.UpdateAgent][google.cloud.ces.v1.AgentService.UpdateAgent].

Request message for [AgentService.UpdateApp][google.cloud.ces.v1.AgentService.UpdateApp].

Request message for [AgentService.UpdateDeployment][google.cloud.ces.v1.AgentService.UpdateDeployment].

Request message for [AgentService.UpdateExample][google.cloud.ces.v1.AgentService.UpdateExample].

Request message for [AgentService.UpdateGuardrail][google.cloud.ces.v1.AgentService.UpdateGuardrail].

Request message for [AgentService.UpdateTool][google.cloud.ces.v1.AgentService.UpdateTool].

Request message for [AgentService.UpdateToolset][google.cloud.ces.v1.AgentService.UpdateToolset].

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

Provides APIs for widgets to interact with CES APIs.

Base class for server-side implementations of WidgetService

Client for WidgetService

WidgetService client wrapper, for convenient use.

Builder class for WidgetServiceClient to provide simple configuration of credentials, endpoint etc.

WidgetService client wrapper implementation, for convenient use.

Settings for WidgetServiceClient instances.

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.

Container for nested types declared in the WidgetTool message type.

Enum of possible cases for the "action_spec" oneof.

The operation to perform on the entity.

Enum of possible cases for the "agent_type" oneof.

The possible contents of AgentName .

Enum of possible cases for the "source" oneof.

Prebuilt ambient noise.

Enum of possible cases for the "auth_config" oneof.

The location of the API key in the request.

Defines the tool execution behavior if there are multipletools being selected by the agent at the same time.

The possible contents of AppName .

The possible contents of AppVersionName .

AudioEncoding specifies the encoding format for audio data.

Enum of possible cases for the "message_type" oneof.

Enum of possible cases for the "message_type" oneof.

Enum of possible cases for the "callback" oneof.

The possible contents of ChangelogName .

The type of the channel profile.

The persona of the channel.

Modality of the web widget.

Theme of the web widget.

Enum of possible cases for the "data" oneof.

The channel type of the conversation.

Type of the input message.

The source of the conversation.

The possible contents of ConversationName .

The type of the data store.

The document processing mode of the data store.

The type of the engine. See the documentation available at https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/SolutionType and https://cloud.google.com/generative-ai-app-builder/docs/create-datastore-ingest .

Enum of possible cases for the "search_source" oneof.

The attribute(or function) for which the custom ranking is to be applied.

The interpolation type to be applied. Default will be linear (Piecewise Linear).

Filter parameter behavior.

The modality type.

The possible contents of DatasetName .

The possible contents of DeidentifyTemplateName .

The possible contents of DeploymentName .

The possible contents of DialogflowAgentName .

Enum of possible cases for the "auth_config" oneof.

The possible contents of EngineName .

Semantic similarity channel to use.

The hallucination metric behavior. Regardless of the behavior, the metric will always be calculated. The difference is that when disabled, the metric is not used to calculate the overall evaluation score.

Defines the behavior when an extra tool call is encountered. An extra tool call is a tool call that is present in the execution but does not match any tool call in the golden expectation.

The possible contents of ExampleName .

Enum of possible cases for the "tool_identifier" oneof.

Enum of possible cases for the "tool_identifier" oneof.

The execution type of the tool or toolset.

Export format for the app.

Enum of possible cases for the "app" oneof.

The type of the Vertex RAG corpus.

Enum of possible cases for the "guardrail_type" oneof.

Match type for the content filter.

Defines when to apply the policy check during the conversation.

Enum of possible cases for the "security_config" oneof.

Probability based thresholds levels for blocking.

Harm category.

The possible contents of GuardrailName .

Enum of possible cases for the "app" oneof.

Defines the strategy for handling conflicts when an app with the same ID already exists, or when imported resources (like Agents, Tools, etc.) have the same display names as existing resources within that app.

The possible contents of InspectTemplateName .

OAuth grant types. Only client credential grant is supported.

Enum of possible cases for the "channel_config" oneof.

Enum of possible cases for the "subscriber_config" oneof.

The possible contents of OmnichannelName .

Enum of possible cases for the "tool_identifier" oneof.

Enum of possible cases for the "tool_identifier" oneof.

OpenAPI data types.

The possible contents of SecretVersionName .

The possible contents of ServiceName .

Enum of possible cases for the "input_type" oneof.

The possible contents of SessionName .

Enum of possible cases for the "output_type" oneof.

Enum of possible cases for the "tool_type" oneof.

Enum of possible cases for the "tool_identifier" oneof.

Enum of possible cases for the "tool_response" oneof.

The possible contents of ToolName .

Enum of possible cases for the "tool_identifier" oneof.

Enum of possible cases for the "toolset_type" oneof.

The possible contents of ToolsetName .

Enum of possible cases for the "rule_type" oneof.

Enum of possible cases for the "condition_type" oneof.

The direction of the transfer.

Enum of possible cases for the "action" oneof.

Enum of possible cases for the "input" oneof.

All available widget types. New values may be added to this enum in the future.