The data for displaying an Agent.
JSON representation |
---|
{ "name" : string , "displayName" : string , "description" : string , "icon" : { object ( |
name
string
Resource name of the agent. Format: projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/assistants/{assistant}/agents/{agent}
displayName
string
Required. Display name of the agent. The language of this is either Agent.language_code
, or ListAvailableAgentViewsRequest.language_code
if translations are enabled.
description
string
Required. Human-readable description of the agent. This might be used by an LLM to automatically select an agent to respond to a user query and to generate the first version of the steps for the agent that can be modified by the user. The language of this is either Agent.language_code
, or ListAvailableAgentViewsRequest.language_code
if translations are enabled.
icon
object (
Image
)
Optional. The icon that represents the agent on the UI.
agentType
enum (
AgentType
)
Output only. The type of the agent.
agentOrigin
enum (
AgentOrigin
)
Immutable. The origin of the Agent.
state
enum (
State
)
Output only. The state of the Agent.
suggestedPrompts[]
object (
SuggestedPrompt
)
Optional. The suggested prompts for the agent, to be shown on the agent landing page.
customPlaceholderText
string
The custom placeholder text that appears in the text box before the user enters any text.
agent_state_reason
. The reason why the agent is in its current state. agent_state_reason
can be only one of the following:suspensionReason
string
The reason why the agent was suspended. Only set if the state is SUSPENDED.
rejectionReason
string
The reason why the agent was rejected. Only set if the state is PRIVATE, and got there via rejection.
deploymentFailureReason
string
The reason why the agent deployment failed. Only set if the state is DEPLOYMENT_FAILED.
AgentType
The type of the agent.
Enums | |
---|---|
AGENT_TYPE_UNSPECIFIED
|
The agent type is unspecified. |
NO_CODE
|
No-code agent. |
HTTP
|
HTTP agent. |
ADK
|
ADK agent. |
MANAGED
|
Google managed agent. |
A2A
|
A2A agent. |
DIALOGFLOW
|
Dialogflow agent. |
LOW_CODE
|
Low-code agent. |
UserPermissions
The permissions of the user on an Agent.
JSON representation |
---|
{ "canRun" : boolean , "canView" : boolean , "canEdit" : boolean , "canWithdraw" : boolean , "canRequestReview" : boolean , "canDelete" : boolean } |
Fields | |
---|---|
canRun
|
If the user can run this Agent. |
canView
|
If the user can view the source of this Agent. |
canEdit
|
If the user can edit this Agent. |
canWithdraw
|
If the user can withdraw this Agent. |
canRequestReview
|
If the user can request a review for this Agent. |
canDelete
|
If the user can delete this Agent. |
SuggestedPrompt
A suggested prompt for the agent, to be shown on the agent landing page.
JSON representation |
---|
{ "text" : string } |
Fields | |
---|---|
text
|
Required. The text of the suggested prompt. The language of this is either |