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.

Entity CRUD operation specification.

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

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.

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.

Authentication information required for API calls.

Configurations for authentication with API key.

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.

A snapshot of the app.

Defines the structure and metadata for a variable.

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.

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.

Configurations for authentication with a bearer token.

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.

The request message for Operations.CancelOperation.

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

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

Represents the persona property of a channel.

Message for configuration for the web widget.

Security settings for the web widget.

A chunk of content within a message.

Citations associated with the agent response.

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 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.

Settings to describe the conversation logging behaviors for the app.

All information about a single turn in the conversation.

Defines the root interface for all clients that generate credentials for calling Google APIs. All clients should implement this interface.

A DataStore resource in Vertex AI Search.

The connector config for the data store connection.

Data store related settings for the app.

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.

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.

Boost specification to boost certain documents.

Boost specification for a condition.

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

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.

Rewriter configuration.

Summarization configuration.

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

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); }

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..

Oauth 2.0 Authorization Code authentication configuration.

JWT Profile Oauth 2.0 Authorization Grant authentication configuration.

Threshold settings for metrics in an Evaluation.

Settings for golden evaluations.

Expectation level metrics thresholds.

Turn level metrics thresholds.

Event input.

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

Request message for ToolService.ExecuteTool.

Response message for ToolService.ExecuteTool.

Request message for AgentService.ExportApp.

Response message for 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.

Request message for WidgetService.GenerateChatToken.

Response message for WidgetService.GenerateChatToken.

Search suggestions from Google Search Tool.

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

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

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

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

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

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

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.

Safety setting.

Represents an image input or output in the conversation.

Request message for AgentService.ImportApp.

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

Response message for AgentService.ImportApp.

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

Language settings of the app.

Response message for AgentService.ListAgents.

Response message for AgentService.ListApps.

Response message for AgentService.ListAppVersions.

Response message for AgentService.ListChangelogs.

Response message for AgentService.ListConversations.

Response message for AgentService.ListDeployments.

Response message for AgentService.ListExamples.

Response message for AgentService.ListGuardrails.

The response message for Locations.ListLocations.

The response message for Operations.ListOperations.

Response message for AgentService.ListToolsets.

Response message for AgentService.ListTools.

A resource that represents a Google Cloud location.

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.

Represents an Omnichannel resource.

OmnichannelIntegrationConfig contains all App integration configs.

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.

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.

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

Represents the metadata of the long-running operation.

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

Additional options for ces#projectsLocationsAppsAgentsCreate.

Additional options for ces#projectsLocationsAppsAgentsDelete.

Additional options for ces#projectsLocationsAppsAgentsList.

Additional options for ces#projectsLocationsAppsAgentsPatch.

Additional options for ces#projectsLocationsAppsChangelogsList.

Additional options for ces#projectsLocationsAppsConversationsDelete.

Additional options for ces#projectsLocationsAppsConversationsGet.

Additional options for ces#projectsLocationsAppsConversationsList.

Additional options for ces#projectsLocationsAppsCreate.

Additional options for ces#projectsLocationsAppsDelete.

Additional options for ces#projectsLocationsAppsDeploymentsCreate.

Additional options for ces#projectsLocationsAppsDeploymentsDelete.

Additional options for ces#projectsLocationsAppsDeploymentsList.

Additional options for ces#projectsLocationsAppsDeploymentsPatch.

Additional options for ces#projectsLocationsAppsExamplesCreate.

Additional options for ces#projectsLocationsAppsExamplesDelete.

Additional options for ces#projectsLocationsAppsExamplesList.

Additional options for ces#projectsLocationsAppsExamplesPatch.

Additional options for ces#projectsLocationsAppsGuardrailsCreate.

Additional options for ces#projectsLocationsAppsGuardrailsDelete.

Additional options for ces#projectsLocationsAppsGuardrailsList.

Additional options for ces#projectsLocationsAppsGuardrailsPatch.

Additional options for ces#projectsLocationsAppsList.

Additional options for ces#projectsLocationsAppsPatch.

Additional options for ces#projectsLocationsAppsToolsCreate.

Additional options for ces#projectsLocationsAppsToolsDelete.

Additional options for ces#projectsLocationsAppsToolsetsCreate.

Additional options for ces#projectsLocationsAppsToolsetsDelete.

Additional options for ces#projectsLocationsAppsToolsetsList.

Additional options for ces#projectsLocationsAppsToolsetsPatch.

Additional options for ces#projectsLocationsAppsToolsList.

Additional options for ces#projectsLocationsAppsToolsPatch.

Additional options for ces#projectsLocationsAppsVersionsCreate.

Additional options for ces#projectsLocationsAppsVersionsDelete.

Additional options for ces#projectsLocationsAppsVersionsList.

Additional options for ces#projectsLocationsList.

Additional options for ces#projectsLocationsOperationsList.

Python code block to evaluate the condition.

A Python function tool.

Configuration to instruct how sensitive data should be handled.

Request message for AgentService.RestoreAppVersion

Request message for ToolService.RetrieveToolSchema.

Response message for ToolService.RetrieveToolSchema.

Request message for ToolService.RetrieveTools.

Response message for ToolService.RetrieveTools.

Request message for SessionService.RunSession.

Response message for SessionService.RunSession.

Represents a select subset of an OpenAPI 3.0 schema object.

Configurations for authentication using a custom service account.

Configurations for authentication with ID token generated from service agent.

Configuration for tools using Service Directory.

The configuration for the session.

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

Input for the session.

Output for the session.

Contains execution details during the processing.

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

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.

Configuration for how the agent response should be synthesized.

Pre-defined system tool.

TimeZone settings of the app.

The TLS configuration.

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.

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

Execution results for the requested tool calls from the client.

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

A tool that is created from a toolset.

Rule for transferring to a specific agent.

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.

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.

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

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.