Skip to main content

@swamp/gcp/ces

v2026.04.23.2

Google Cloud ces infrastructure models

Repository

https://github.com/systeminit/swamp-extensions

Labels

gcpgoogle-cloudcescloudinfrastructure

Contents

Quality score

Verified by Swamp

How well-documented and verifiable this extension is.

100%

Grade A

  • Has README or module doc2/2earned
  • README has a code example1/1earned
  • README is substantive1/1earned
  • Most symbols documented1/1earned
  • No slow types1/1earned
  • Has description1/1earned
  • At least one platform tag (or universal)1/1earned
  • Two or more platform tags (or universal)1/1earned
  • License declared1/1earned
  • Verified public repository2/2earned

Install

$ swamp extension pull @swamp/gcp/ces

Release Notes

  • Updated: apps, apps_deployments, apps_tools, apps_versions

@swamp/gcp/ces/appsv2026.04.23.2apps.ts

Global Arguments

ArgumentTypeDescription
audioProcessingConfig?objectConfiguration for how the input and output audio should be processed and delivered.
clientCertificateSettings?objectSettings for custom client certificates.
dataStoreSettings?objectData store related settings for the app.
defaultChannelProfile?objectA ChannelProfile configures the agent's behavior for a specific communication channel, such as web UI or telephony.
description?stringOptional. Human-readable description of the app.
displayName?stringRequired. Display name of the app.
errorHandlingSettings?objectSettings to describe how errors should be handled in the app.
evaluationMetricsThresholds?objectThreshold settings for metrics in an Evaluation.
globalInstruction?stringOptional. Instructions for all the agents in the app. You can use this instruction to set up a stable identity or personality across all the agents.
guardrails?arrayOptional. List of guardrails for the app. Format: `projects/{project}/locations/{location}/apps/{app}/guardrails/{guardrail}`
languageSettings?objectLanguage settings of the app.
locked?booleanOptional. Indicates whether the app is locked for changes. If the app is locked, modifications to the app resources will be rejected.
loggingSettings?objectSettings to describe the logging behaviors for the app.
metadata?recordOptional. Metadata about the app. This field can be used to store additional information relevant to the app's details or intended usages.
modelSettings?objectModel settings contains various configurations for the LLM model.
name?stringIdentifier. The unique identifier of the app. Format: `projects/{project}/locations/{location}/apps/{app}`
pinned?booleanOptional. Whether the app is pinned in the app list.
rootAgent?stringOptional. The root agent is the entry point of the app. Format: `projects/{project}/locations/{location}/apps/{app}/agents/{agent}`
timeZoneSettings?objectTimeZone settings of the app.
toolExecutionMode?enumOptional. The tool execution mode for the app. If not provided, will default to PARALLEL.
variableDeclarations?arrayOptional. The declarations of the variables.
appId?stringOptional. The ID to use for the app, which will become the final component of the app's resource name. If not provided, a unique ID will be automatically assigned for the app.
location?stringThe location for this resource (e.g., 'us', 'us-central1', 'europe-west1')
createCreate a apps
getGet a apps
ArgumentTypeDescription
identifierstringThe name of the apps
updateUpdate apps attributes
deleteDelete the apps
ArgumentTypeDescription
identifierstringThe name of the apps
syncSync apps state from GCP
execute_toolexecute tool
ArgumentTypeDescription
args?any
context?any
mockConfig?any
tool?any
toolsetTool?any
variables?any
export_appexport app
ArgumentTypeDescription
appVersion?any
exportFormat?any
gcsUri?any
import_appimport app
ArgumentTypeDescription
appContent?any
appId?any
displayName?any
gcsUri?any
ignoreAppLock?any
importOptions?any
retrieve_tool_schemaretrieve tool schema
ArgumentTypeDescription
tool?any
toolsetTool?any

Resources

state(infinite)— An app serves as a top-level container for a group of agents, including the r...
@swamp/gcp/ces/apps-agentsv2026.04.23.1apps_agents.ts

Global Arguments

ArgumentTypeDescription
afterAgentCallbacks?arrayOptional. The callbacks to execute after the agent is called. The provided callbacks are executed sequentially in the exact order they are given in the list. If a callback returns an overridden response, execution stops and any remaining callbacks are skipped.
afterModelCallbacks?arrayOptional. The callbacks to execute after the model is called. If there are multiple calls to the model, the callback will be executed multiple times. The provided callbacks are executed sequentially in the exact order they are given in the list. If a callback returns an overridden response, execution stops and any remaining callbacks are skipped.
afterToolCallbacks?arrayOptional. The callbacks to execute after the tool is invoked. If there are multiple tool invocations, the callback will be executed multiple times. The provided callbacks are executed sequentially in the exact order they are given in the list. If a callback returns an overridden response, execution stops and any remaining callbacks are skipped.
beforeAgentCallbacks?arrayOptional. The callbacks to execute before the agent is called. The provided callbacks are executed sequentially in the exact order they are given in the list. If a callback returns an overridden response, execution stops and any remaining callbacks are skipped.
beforeModelCallbacks?arrayOptional. The callbacks to execute before the model is called. If there are multiple calls to the model, the callback will be executed multiple times. The provided callbacks are executed sequentially in the exact order they are given in the list. If a callback returns an overridden response, execution stops and any remaining callbacks are skipped.
beforeToolCallbacks?arrayOptional. The callbacks to execute before the tool is invoked. If there are multiple tool invocations, the callback will be executed multiple times. The provided callbacks are executed sequentially in the exact order they are given in the list. If a callback returns an overridden response, execution stops and any remaining callbacks are skipped.
childAgents?arrayOptional. List of child agents in the agent tree. Format: `projects/{project}/locations/{location}/apps/{app}/agents/{agent}`
description?stringOptional. Human-readable description of the agent.
displayName?stringRequired. Display name of the agent.
guardrails?arrayOptional. List of guardrails for the agent. Format: `projects/{project}/locations/{location}/apps/{app}/guardrails/{guardrail}`
instruction?stringOptional. Instructions for the LLM model to guide the agent's behavior.
llmAgent?objectDefault agent type. The agent uses instructions and callbacks specified in the agent to perform the task using a large language model.
modelSettings?objectModel settings contains various configurations for the LLM model.
name?stringIdentifier. The unique identifier of the agent. Format: `projects/{project}/locations/{location}/apps/{app}/agents/{agent}`
remoteDialogflowAgent?objectThe agent which will transfer execution to a remote [Dialogflow CX](https://docs.cloud.google.com/dialogflow/cx/docs/concept/agent) 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.
tools?arrayOptional. List of available tools for the agent. Format: `projects/{project}/locations/{location}/apps/{app}/tools/{tool}`
toolsets?arrayOptional. List of toolsets for the agent.
transferRules?arrayOptional. Agent transfer rules. If multiple rules match, the first one in the list will be used.
agentId?stringOptional. The ID to use for the agent, which will become the final component of the agent's resource name. If not provided, a unique ID will be automatically assigned for the agent.
location?stringThe location for this resource (e.g., 'us', 'us-central1', 'europe-west1')
createCreate a agents
getGet a agents
ArgumentTypeDescription
identifierstringThe name of the agents
updateUpdate agents attributes
deleteDelete the agents
ArgumentTypeDescription
identifierstringThe name of the agents
syncSync agents state from GCP

Resources

state(infinite)— An agent acts as the fundamental building block that provides instructions to...
@swamp/gcp/ces/apps-changelogsv2026.04.23.1apps_changelogs.ts

Global Arguments

ArgumentTypeDescription
namestringInstance name for this resource (used as the unique identifier in the factory pattern)
location?stringThe location for this resource (e.g., 'us', 'us-central1', 'europe-west1')
getGet a changelogs
ArgumentTypeDescription
identifierstringThe name of the changelogs
syncSync changelogs state from GCP

Resources

state(infinite)— Changelogs represent a change made to the app or to an resource within the app.
@swamp/gcp/ces/apps-conversationsv2026.04.23.1apps_conversations.ts

Global Arguments

ArgumentTypeDescription
namestringInstance name for this resource (used as the unique identifier in the factory pattern)
location?stringThe location for this resource (e.g., 'us', 'us-central1', 'europe-west1')
getGet a conversations
ArgumentTypeDescription
identifierstringThe name of the conversations
deleteDelete the conversations
ArgumentTypeDescription
identifierstringThe name of the conversations
syncSync conversations state from GCP
batch_deletebatch delete
ArgumentTypeDescription
conversations?any

Resources

state(infinite)— A conversation represents an interaction between an end user and the CES app.
@swamp/gcp/ces/apps-deploymentsv2026.04.23.2apps_deployments.ts

Global Arguments

ArgumentTypeDescription
appVersion?stringOptional. The resource name of the app version to deploy. Format: `projects/{project}/locations/{location}/apps/{app}/versions/{version}` Use `projects/{project}/locations/{location}/apps/{app}/versions/-` to use the draft app.
channelProfile?objectA ChannelProfile configures the agent's behavior for a specific communication channel, such as web UI or telephony.
displayName?stringRequired. Display name of the deployment.
experimentConfig?objectExperiment for the deployment.
name?stringIdentifier. The resource name of the deployment. Format: `projects/{project}/locations/{location}/apps/{app}/deployments/{deployment}`
deploymentId?stringOptional. The ID to use for the deployment, which will become the final component of the deployment's resource name. If not provided, a unique ID will be automatically assigned for the deployment.
location?stringThe location for this resource (e.g., 'us', 'us-central1', 'europe-west1')
createCreate a deployments
getGet a deployments
ArgumentTypeDescription
identifierstringThe name of the deployments
updateUpdate deployments attributes
deleteDelete the deployments
ArgumentTypeDescription
identifierstringThe name of the deployments
syncSync deployments state from GCP

Resources

state(infinite)— A deployment represents an immutable, queryable version of the app. It is use...
@swamp/gcp/ces/apps-examplesv2026.04.23.1apps_examples.ts

Global Arguments

ArgumentTypeDescription
description?stringOptional. Human-readable description of the example.
displayName?stringRequired. Display name of the example.
entryAgent?stringOptional. The agent that initially handles the conversation. If not specified, the example represents a conversation that is handled by the root agent. Format: `projects/{project}/locations/{location}/apps/{app}/agents/{agent}`
messages?arrayOptional. The collection of messages that make up the conversation.
name?stringIdentifier. The unique identifier of the example. Format: `projects/{project}/locations/{location}/apps/{app}/examples/{example}`
exampleId?stringOptional. The ID to use for the example, which will become the final component of the example's resource name. If not provided, a unique ID will be automatically assigned for the example.
location?stringThe location for this resource (e.g., 'us', 'us-central1', 'europe-west1')
createCreate a examples
getGet a examples
ArgumentTypeDescription
identifierstringThe name of the examples
updateUpdate examples attributes
deleteDelete the examples
ArgumentTypeDescription
identifierstringThe name of the examples
syncSync examples state from GCP

Resources

state(infinite)— An example represents a sample conversation between the user and the agent(s).
@swamp/gcp/ces/apps-guardrailsv2026.04.23.1apps_guardrails.ts

Global Arguments

ArgumentTypeDescription
action?objectAction that is taken when a certain precondition is met.
codeCallback?objectGuardrail that blocks the conversation based on the code callbacks provided.
contentFilter?objectGuardrail that bans certain content from being used in the conversation.
description?stringOptional. Description of the guardrail.
displayName?stringRequired. Display name of the guardrail.
enabled?booleanOptional. Whether the guardrail is enabled.
llmPolicy?objectGuardrail that blocks the conversation if the LLM response is considered violating the policy based on the LLM classification.
llmPromptSecurity?objectGuardrail that blocks the conversation if the input is considered unsafe based on the LLM classification.
modelSafety?objectModel safety settings overrides. When this is set, it will override the default settings and trigger the guardrail if the response is considered unsafe.
name?stringIdentifier. The unique identifier of the guardrail. Format: `projects/{project}/locations/{location}/apps/{app}/guardrails/{guardrail}`
guardrailId?stringOptional. The ID to use for the guardrail, which will become the final component of the guardrail's resource name. If not provided, a unique ID will be automatically assigned for the guardrail.
location?stringThe location for this resource (e.g., 'us', 'us-central1', 'europe-west1')
createCreate a guardrails
getGet a guardrails
ArgumentTypeDescription
identifierstringThe name of the guardrails
updateUpdate guardrails attributes
deleteDelete the guardrails
ArgumentTypeDescription
identifierstringThe name of the guardrails
syncSync guardrails state from GCP

Resources

state(infinite)— Guardrail contains a list of checks and balances to keep the agents safe and ...
@swamp/gcp/ces/apps-toolsv2026.04.23.2apps_tools.ts

Global Arguments

ArgumentTypeDescription
agentTool?objectRepresents a tool that allows the agent to call another agent.
clientFunction?objectRepresents 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.
connectorTool?objectA ConnectorTool allows connections to different integrations. See: https://cloud.google.com/integration-connectors/docs/overview.
dataStoreTool?objectTool 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.
executionType?enumOptional. The execution type of the tool.
fileSearchTool?objectThe 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.
googleSearchTool?objectRepresents a tool to perform Google web searches for grounding. See https://cloud.google.com/customer-engagement-ai/conversational-agents/ps/tool#google-search.
mcpTool?objectAn MCP tool. See https://modelcontextprotocol.io/specification/2025-06-18/server/tools for more details.
name?stringIdentifier. The resource name of the tool. Format: * `projects/{project}/locations/{location}/apps/{app}/tools/{tool}` for standalone tools. * `projects/{project}/locations/{location}/apps/{app}/toolsets/{toolset}/tools/{tool}` for tools retrieved from a toolset. These tools are dynamic and output-only; they cannot be referenced directly where a tool is expected.
openApiTool?objectA remote API tool defined by an OpenAPI schema.
pythonFunction?objectA Python function tool.
systemTool?objectPre-defined system tool.
toolFakeConfig?objectConfiguration for tool behavior in fake mode.
widgetTool?objectRepresents 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.
toolId?stringOptional. The ID to use for the tool, which will become the final component of the tool's resource name. If not provided, a unique ID will be automatically assigned for the tool.
location?stringThe location for this resource (e.g., 'us', 'us-central1', 'europe-west1')
createCreate a tools
getGet a tools
ArgumentTypeDescription
identifierstringThe name of the tools
updateUpdate tools attributes
deleteDelete the tools
ArgumentTypeDescription
identifierstringThe name of the tools
syncSync tools state from GCP

Resources

state(infinite)— A tool represents an action that the CES agent can take to achieve certain go...
@swamp/gcp/ces/apps-toolsetsv2026.04.23.1apps_toolsets.ts

Global Arguments

ArgumentTypeDescription
connectorToolset?objectA toolset that generates tools from an Integration Connectors Connection.
description?stringOptional. The description of the toolset.
displayName?stringOptional. The display name of the toolset. Must be unique within the same app.
executionType?enumOptional. The execution type of the tools in the toolset.
mcpToolset?objectA toolset that contains a list of tools that are offered by the MCP server.
name?stringIdentifier. The unique identifier of the toolset. Format: `projects/{project}/locations/{location}/apps/{app}/toolsets/{toolset}`
openApiToolset?objectA toolset that contains a list of tools that are defined by an OpenAPI schema.
toolFakeConfig?objectConfiguration for tool behavior in fake mode.
toolsetId?stringOptional. The ID to use for the toolset, which will become the final component of the toolset's resource name. If not provided, a unique ID will be automatically assigned for the toolset.
location?stringThe location for this resource (e.g., 'us', 'us-central1', 'europe-west1')
createCreate a toolsets
getGet a toolsets
ArgumentTypeDescription
identifierstringThe name of the toolsets
updateUpdate toolsets attributes
deleteDelete the toolsets
ArgumentTypeDescription
identifierstringThe name of the toolsets
syncSync toolsets state from GCP
retrieve_toolsretrieve tools
ArgumentTypeDescription
toolIds?any

Resources

state(infinite)— A toolset represents a group of dynamically managed tools that can be used by...
@swamp/gcp/ces/apps-versionsv2026.04.23.2apps_versions.ts

Global Arguments

ArgumentTypeDescription
description?stringOptional. The description of the app version.
displayName?stringOptional. The display name of the app version.
name?stringIdentifier. The unique identifier of the app version. Format: `projects/{project}/locations/{location}/apps/{app}/versions/{version}`
snapshot?objectA snapshot of the app.
appVersionId?stringOptional. The ID to use for the app version, which will become the final component of the app version's resource name. If not provided, a unique ID will be automatically assigned for the app version.
location?stringThe location for this resource (e.g., 'us', 'us-central1', 'europe-west1')
createCreate a versions
getGet a versions
ArgumentTypeDescription
identifierstringThe name of the versions
deleteDelete the versions
ArgumentTypeDescription
identifierstringThe name of the versions
syncSync versions state from GCP
restorerestore

Resources

state(infinite)— In Customer Engagement Suite (CES), an app version is a snapshot of the app a...
@swamp/gcp/ces/locationsv2026.04.23.1locations.ts

Global Arguments

ArgumentTypeDescription
namestringInstance name for this resource (used as the unique identifier in the factory pattern)
getGet a locations
ArgumentTypeDescription
identifierstringThe name of the locations
syncSync locations state from GCP

Resources

state(infinite)— A resource that represents a Google Cloud location.