agents

Creates, updates, deletes, gets or lists an agents resource.

Overview

Name	agents
Type	Resource
Id	google.ces.agents

Fields

The following fields are returned by SELECT queries:

get

Name	Datatype	Description
name	string	Identifier. The unique identifier of the agent. Format: projects/{project}/locations/{location}/apps/{app}/agents/{agent}
afterAgentCallbacks	array	Optional. 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	array	Optional. 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	array	Optional. 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	array	Optional. 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	array	Optional. 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	array	Optional. 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	array	Optional. List of child agents in the agent tree. Format: projects/{project}/locations/{location}/apps/{app}/agents/{agent}
createTime	string (google-datetime)	Output only. Timestamp when the agent was created.
description	string	Optional. Human-readable description of the agent.
displayName	string	Required. Display name of the agent.
etag	string	Etag used to ensure the object hasn't changed during a read-modify-write operation. If the etag is empty, the update will overwrite any concurrent changes.
generatedSummary	string	Output only. If the agent is generated by the LLM assistant, this field contains a descriptive summary of the generation.
guardrails	array	Optional. List of guardrails for the agent. Format: projects/{project}/locations/{location}/apps/{app}/guardrails/{guardrail}
instruction	string	Optional. Instructions for the LLM model to guide the agent's behavior.
llmAgent	object	Optional. The default agent type. (id: AgentLlmAgent)
modelSettings	object	Optional. Configurations for the LLM model. (id: ModelSettings)
remoteDialogflowAgent	object	Optional. The remote Dialogflow agent to be used for the agent execution. If this field is set, all other agent level properties will be ignored. Note: If the Dialogflow agent is in a different project from the app, you should grant roles/dialogflow.client to the CES service agent service-@gcp-sa-ces.iam.gserviceaccount.com. (id: AgentRemoteDialogflowAgent)
tools	array	Optional. List of available tools for the agent. Format: projects/{project}/locations/{location}/apps/{app}/tools/{tool}
toolsets	array	Optional. List of toolsets for the agent.
transferRules	array	Optional. Agent transfer rules. If multiple rules match, the first one in the list will be used.
updateTime	string (google-datetime)	Output only. Timestamp when the agent was last updated.
validationErrors	array	Output only. Misconfigurations or errors in the agent that may affect agent quality.

list

Name	Datatype	Description
name	string	Identifier. The unique identifier of the agent. Format: projects/{project}/locations/{location}/apps/{app}/agents/{agent}
afterAgentCallbacks	array	Optional. 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	array	Optional. 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	array	Optional. 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	array	Optional. 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	array	Optional. 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	array	Optional. 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	array	Optional. List of child agents in the agent tree. Format: projects/{project}/locations/{location}/apps/{app}/agents/{agent}
createTime	string (google-datetime)	Output only. Timestamp when the agent was created.
description	string	Optional. Human-readable description of the agent.
displayName	string	Required. Display name of the agent.
etag	string	Etag used to ensure the object hasn't changed during a read-modify-write operation. If the etag is empty, the update will overwrite any concurrent changes.
generatedSummary	string	Output only. If the agent is generated by the LLM assistant, this field contains a descriptive summary of the generation.
guardrails	array	Optional. List of guardrails for the agent. Format: projects/{project}/locations/{location}/apps/{app}/guardrails/{guardrail}
instruction	string	Optional. Instructions for the LLM model to guide the agent's behavior.
llmAgent	object	Optional. The default agent type. (id: AgentLlmAgent)
modelSettings	object	Optional. Configurations for the LLM model. (id: ModelSettings)
remoteDialogflowAgent	object	Optional. The remote Dialogflow agent to be used for the agent execution. If this field is set, all other agent level properties will be ignored. Note: If the Dialogflow agent is in a different project from the app, you should grant roles/dialogflow.client to the CES service agent service-@gcp-sa-ces.iam.gserviceaccount.com. (id: AgentRemoteDialogflowAgent)
tools	array	Optional. List of available tools for the agent. Format: projects/{project}/locations/{location}/apps/{app}/tools/{tool}
toolsets	array	Optional. List of toolsets for the agent.
transferRules	array	Optional. Agent transfer rules. If multiple rules match, the first one in the list will be used.
updateTime	string (google-datetime)	Output only. Timestamp when the agent was last updated.
validationErrors	array	Output only. Misconfigurations or errors in the agent that may affect agent quality.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get	select	projectsId, locationsId, appsId, agentsId		Gets details of the specified agent.
list	select	projectsId, locationsId, appsId	filter, orderBy, pageSize, pageToken	Lists agents in the given app.
create	insert	projectsId, locationsId, appsId	agentId	Creates a new agent in the given app.
patch	update	projectsId, locationsId, appsId, agentsId	updateMask	Updates the specified agent.
delete	delete	projectsId, locationsId, appsId, agentsId	force, etag	Deletes the specified agent.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
agentsId	string
appsId	string
locationsId	string
projectsId	string
agentId	string
etag	string
filter	string
force	boolean
orderBy	string
pageSize	integer (int32)
pageToken	string
updateMask	string (google-fieldmask)

SELECT examples

get

Gets details of the specified agent.

SELECT
name,
afterAgentCallbacks,
afterModelCallbacks,
afterToolCallbacks,
beforeAgentCallbacks,
beforeModelCallbacks,
beforeToolCallbacks,
childAgents,
createTime,
description,
displayName,
etag,
generatedSummary,
guardrails,
instruction,
llmAgent,
modelSettings,
remoteDialogflowAgent,
tools,
toolsets,
transferRules,
updateTime,
validationErrors
FROM google.ces.agents
WHERE projectsId = '{{ projectsId }}' -- required
AND locationsId = '{{ locationsId }}' -- required
AND appsId = '{{ appsId }}' -- required
AND agentsId = '{{ agentsId }}' -- required
;

list

Lists agents in the given app.

SELECT
name,
afterAgentCallbacks,
afterModelCallbacks,
afterToolCallbacks,
beforeAgentCallbacks,
beforeModelCallbacks,
beforeToolCallbacks,
childAgents,
createTime,
description,
displayName,
etag,
generatedSummary,
guardrails,
instruction,
llmAgent,
modelSettings,
remoteDialogflowAgent,
tools,
toolsets,
transferRules,
updateTime,
validationErrors
FROM google.ces.agents
WHERE projectsId = '{{ projectsId }}' -- required
AND locationsId = '{{ locationsId }}' -- required
AND appsId = '{{ appsId }}' -- required
AND filter = '{{ filter }}'
AND orderBy = '{{ orderBy }}'
AND pageSize = '{{ pageSize }}'
AND pageToken = '{{ pageToken }}'
;

INSERT examples

create

Creates a new agent in the given app.

INSERT INTO google.ces.agents (
data__beforeToolCallbacks,
data__remoteDialogflowAgent,
data__description,
data__afterModelCallbacks,
data__instruction,
data__tools,
data__beforeAgentCallbacks,
data__etag,
data__guardrails,
data__name,
data__displayName,
data__beforeModelCallbacks,
data__childAgents,
data__afterToolCallbacks,
data__afterAgentCallbacks,
data__toolsets,
data__transferRules,
data__modelSettings,
data__llmAgent,
projectsId,
locationsId,
appsId,
agentId
)
SELECT 
'{{ beforeToolCallbacks }}',
'{{ remoteDialogflowAgent }}',
'{{ description }}',
'{{ afterModelCallbacks }}',
'{{ instruction }}',
'{{ tools }}',
'{{ beforeAgentCallbacks }}',
'{{ etag }}',
'{{ guardrails }}',
'{{ name }}',
'{{ displayName }}',
'{{ beforeModelCallbacks }}',
'{{ childAgents }}',
'{{ afterToolCallbacks }}',
'{{ afterAgentCallbacks }}',
'{{ toolsets }}',
'{{ transferRules }}',
'{{ modelSettings }}',
'{{ llmAgent }}',
'{{ projectsId }}',
'{{ locationsId }}',
'{{ appsId }}',
'{{ agentId }}'
RETURNING
name,
afterAgentCallbacks,
afterModelCallbacks,
afterToolCallbacks,
beforeAgentCallbacks,
beforeModelCallbacks,
beforeToolCallbacks,
childAgents,
createTime,
description,
displayName,
etag,
generatedSummary,
guardrails,
instruction,
llmAgent,
modelSettings,
remoteDialogflowAgent,
tools,
toolsets,
transferRules,
updateTime,
validationErrors
;

Manifest

# Description fields are for documentation purposes
- name: agents
props:
  - name: projectsId
    value: "{{ projectsId }}"
    description: Required parameter for the agents resource.
  - name: locationsId
    value: "{{ locationsId }}"
    description: Required parameter for the agents resource.
  - name: appsId
    value: "{{ appsId }}"
    description: Required parameter for the agents resource.
  - name: beforeToolCallbacks
    description: |
      Optional. 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.
    value:
      - pythonCode: "{{ pythonCode }}"
        disabled: {{ disabled }}
        description: "{{ description }}"
        proactiveExecutionEnabled: {{ proactiveExecutionEnabled }}
  - name: remoteDialogflowAgent
    description: |
      Optional. The remote [Dialogflow](https://cloud.google.com/dialogflow/cx/docs/concept/console-conversational-agents) agent to be used for the agent execution. If this field is set, all other agent level properties will be ignored. Note: If the Dialogflow agent is in a different project from the app, you should grant `roles/dialogflow.client` to the CES service agent `service-@gcp-sa-ces.iam.gserviceaccount.com`.
    value:
      environmentId: "{{ environmentId }}"
      inputVariableMapping: "{{ inputVariableMapping }}"
      outputVariableMapping: "{{ outputVariableMapping }}"
      languageCodeVariable: "{{ languageCodeVariable }}"
      flowId: "{{ flowId }}"
      agent: "{{ agent }}"
      respectResponseInterruptionSettings: {{ respectResponseInterruptionSettings }}
  - name: description
    value: "{{ description }}"
    description: |
      Optional. Human-readable description of the agent.
  - name: afterModelCallbacks
    description: |
      Optional. 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.
    value:
      - pythonCode: "{{ pythonCode }}"
        disabled: {{ disabled }}
        description: "{{ description }}"
        proactiveExecutionEnabled: {{ proactiveExecutionEnabled }}
  - name: instruction
    value: "{{ instruction }}"
    description: |
      Optional. Instructions for the LLM model to guide the agent's behavior.
  - name: tools
    value:
      - "{{ tools }}"
    description: |
      Optional. List of available tools for the agent. Format: `projects/{project}/locations/{location}/apps/{app}/tools/{tool}`
  - name: beforeAgentCallbacks
    description: |
      Optional. 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.
    value:
      - pythonCode: "{{ pythonCode }}"
        disabled: {{ disabled }}
        description: "{{ description }}"
        proactiveExecutionEnabled: {{ proactiveExecutionEnabled }}
  - name: etag
    value: "{{ etag }}"
    description: |
      Etag used to ensure the object hasn't changed during a read-modify-write operation. If the etag is empty, the update will overwrite any concurrent changes.
  - name: guardrails
    value:
      - "{{ guardrails }}"
    description: |
      Optional. List of guardrails for the agent. Format: `projects/{project}/locations/{location}/apps/{app}/guardrails/{guardrail}`
  - name: name
    value: "{{ name }}"
    description: |
      Identifier. The unique identifier of the agent. Format: `projects/{project}/locations/{location}/apps/{app}/agents/{agent}`
  - name: displayName
    value: "{{ displayName }}"
    description: |
      Required. Display name of the agent.
  - name: beforeModelCallbacks
    description: |
      Optional. 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.
    value:
      - pythonCode: "{{ pythonCode }}"
        disabled: {{ disabled }}
        description: "{{ description }}"
        proactiveExecutionEnabled: {{ proactiveExecutionEnabled }}
  - name: childAgents
    value:
      - "{{ childAgents }}"
    description: |
      Optional. List of child agents in the agent tree. Format: `projects/{project}/locations/{location}/apps/{app}/agents/{agent}`
  - name: afterToolCallbacks
    description: |
      Optional. 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.
    value:
      - pythonCode: "{{ pythonCode }}"
        disabled: {{ disabled }}
        description: "{{ description }}"
        proactiveExecutionEnabled: {{ proactiveExecutionEnabled }}
  - name: afterAgentCallbacks
    description: |
      Optional. 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.
    value:
      - pythonCode: "{{ pythonCode }}"
        disabled: {{ disabled }}
        description: "{{ description }}"
        proactiveExecutionEnabled: {{ proactiveExecutionEnabled }}
  - name: toolsets
    description: |
      Optional. List of toolsets for the agent.
    value:
      - toolset: "{{ toolset }}"
        toolIds: "{{ toolIds }}"
  - name: transferRules
    description: |
      Optional. Agent transfer rules. If multiple rules match, the first one in the list will be used.
    value:
      - disablePlannerTransfer:
          expressionCondition:
            expression: "{{ expression }}"
        deterministicTransfer:
          pythonCodeCondition:
            pythonCode: "{{ pythonCode }}"
          expressionCondition:
            expression: "{{ expression }}"
        childAgent: "{{ childAgent }}"
        direction: "{{ direction }}"
  - name: modelSettings
    description: |
      Optional. Configurations for the LLM model.
    value:
      model: "{{ model }}"
      temperature: {{ temperature }}
  - name: llmAgent
    value: "{{ llmAgent }}"
    description: |
      Optional. The default agent type.
  - name: agentId
    value: "{{ agentId }}"

UPDATE examples

patch

Updates the specified agent.

UPDATE google.ces.agents
SET 
data__beforeToolCallbacks = '{{ beforeToolCallbacks }}',
data__remoteDialogflowAgent = '{{ remoteDialogflowAgent }}',
data__description = '{{ description }}',
data__afterModelCallbacks = '{{ afterModelCallbacks }}',
data__instruction = '{{ instruction }}',
data__tools = '{{ tools }}',
data__beforeAgentCallbacks = '{{ beforeAgentCallbacks }}',
data__etag = '{{ etag }}',
data__guardrails = '{{ guardrails }}',
data__name = '{{ name }}',
data__displayName = '{{ displayName }}',
data__beforeModelCallbacks = '{{ beforeModelCallbacks }}',
data__childAgents = '{{ childAgents }}',
data__afterToolCallbacks = '{{ afterToolCallbacks }}',
data__afterAgentCallbacks = '{{ afterAgentCallbacks }}',
data__toolsets = '{{ toolsets }}',
data__transferRules = '{{ transferRules }}',
data__modelSettings = '{{ modelSettings }}',
data__llmAgent = '{{ llmAgent }}'
WHERE 
projectsId = '{{ projectsId }}' --required
AND locationsId = '{{ locationsId }}' --required
AND appsId = '{{ appsId }}' --required
AND agentsId = '{{ agentsId }}' --required
AND updateMask = '{{ updateMask}}'
RETURNING
name,
afterAgentCallbacks,
afterModelCallbacks,
afterToolCallbacks,
beforeAgentCallbacks,
beforeModelCallbacks,
beforeToolCallbacks,
childAgents,
createTime,
description,
displayName,
etag,
generatedSummary,
guardrails,
instruction,
llmAgent,
modelSettings,
remoteDialogflowAgent,
tools,
toolsets,
transferRules,
updateTime,
validationErrors;

DELETE examples

delete

Deletes the specified agent.

DELETE FROM google.ces.agents
WHERE projectsId = '{{ projectsId }}' --required
AND locationsId = '{{ locationsId }}' --required
AND appsId = '{{ appsId }}' --required
AND agentsId = '{{ agentsId }}' --required
AND force = '{{ force }}'
AND etag = '{{ etag }}'
;