AgentState class

Input properties used for looking up and filtering Agent resources.

Constructors

AgentState({Input<List<AgentAfterAgentCallback>?>? afterAgentCallbacks, Input<List<AgentAfterModelCallback>?>? afterModelCallbacks, Input<List<AgentAfterToolCallback>?>? afterToolCallbacks, Input<String?>? agentId, Input<String?>? app, Input<List<AgentBeforeAgentCallback>?>? beforeAgentCallbacks, Input<List<AgentBeforeModelCallback>?>? beforeModelCallbacks, Input<List<AgentBeforeToolCallback>?>? beforeToolCallbacks, Input<List<String>?>? childAgents, Input<String?>? createTime, Input<String?>? deletionPolicy, Input<String?>? description, Input<String?>? displayName, Input<String?>? etag, Input<String?>? generatedSummary, Input<List<String>?>? guardrails, Input<String?>? instruction, Input<Map<String, dynamic>?>? llmAgent, Input<String?>? location, Input<AgentModelSettings?>? modelSettings, Input<String?>? name, Input<String?>? project, Input<AgentRemoteDialogflowAgent?>? remoteDialogflowAgent, Input<List<String>?>? tools, Input<List<AgentToolset>?>? toolsets, Input<String?>? updateTime})
Creates a new AgentState. afterAgentCallbacks The callbacks to execute after the agent is called. afterModelCallbacks The callbacks to execute after the model is called. If there are multiple afterToolCallbacks The callbacks to execute after the tool is invoked. If there are multiple agentId The ID to use for the agent, which will become the final component of app Resource ID segment making up resource name. It identifies the resource within its parent collection as described in https://google.aip.dev/122. beforeAgentCallbacks The callbacks to execute before the agent is called. beforeModelCallbacks The callbacks to execute before the model is called. If there are multiple beforeToolCallbacks The callbacks to execute before the tool is invoked. If there are multiple childAgents List of child agents in the agent tree. createTime Timestamp when the agent was created. deletionPolicy Whether Terraform will be prevented from destroying the resource. Defaults to DELETE. description Human-readable description of the agent. displayName Display name of the agent. etag Etag used to ensure the object hasn't changed during a read-modify-write generatedSummary If the agent is generated by the LLM assistant, this field contains a guardrails List of guardrails for the agent. instruction Instructions for the LLM model to guide the agent's behavior. llmAgent Default agent type. The agent uses instructions and callbacks specified in location Resource ID segment making up resource name. It identifies the resource within its parent collection as described in https://google.aip.dev/122. modelSettings Model settings contains various configurations for the LLM model. name Identifier. The unique identifier of the agent. project The ID of the project in which the resource belongs. remoteDialogflowAgent The agent which will transfer execution to an existing remote tools List of available tools for the agent. toolsets List of toolsets for the agent. updateTime Timestamp when the agent was last updated.
const
AgentState.fromMap(Map<String, dynamic> map)
factory

Properties

afterAgentCallbacks → Input<List<AgentAfterAgentCallback>?>?
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. Structure is documented below.
final
afterModelCallbacks → Input<List<AgentAfterModelCallback>?>?
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. Structure is documented below.
final
afterToolCallbacks → Input<List<AgentAfterToolCallback>?>?
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. Structure is documented below.
final
agentId → Input<String?>?
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.
final
app → Input<String?>?
Resource ID segment making up resource name. It identifies the resource within its parent collection as described in https://google.aip.dev/122.
final
beforeAgentCallbacks → Input<List<AgentBeforeAgentCallback>?>?
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. Structure is documented below.
final
beforeModelCallbacks → Input<List<AgentBeforeModelCallback>?>?
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. Structure is documented below.
final
beforeToolCallbacks → Input<List<AgentBeforeToolCallback>?>?
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. Structure is documented below.
final
childAgents → Input<List<String>?>?
List of child agents in the agent tree. Format: projects/{project}/locations/{location}/apps/{app}/agents/{agent}
final
createTime → Input<String?>?
Timestamp when the agent was created.
final
deletionPolicy → Input<String?>?
Whether Terraform will be prevented from destroying the resource. Defaults to DELETE. When a 'terraform destroy' or 'pulumi up' would delete the resource, the command will fail if this field is set to "PREVENT" in Terraform state. When set to "ABANDON", the command will remove the resource from Terraform management without updating or deleting the resource in the API. When set to "DELETE", deleting the resource is allowed.
final
description → Input<String?>?
Human-readable description of the agent.
final
displayName → Input<String?>?
Display name of the agent.
final
etag → Input<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.
final
generatedSummary → Input<String?>?
If the agent is generated by the LLM assistant, this field contains a descriptive summary of the generation.
final
guardrails → Input<List<String>?>?
List of guardrails for the agent. Format: projects/{project}/locations/{location}/apps/{app}/guardrails/{guardrail}
final
hashCode → int
The hash code for this object.
no setterinherited
instruction → Input<String?>?
Instructions for the LLM model to guide the agent's behavior.
final
llmAgent → Input<Map<String, dynamic>?>?
Default agent type. The agent uses instructions and callbacks specified in the agent to perform the task using a large language model.
final
location → Input<String?>?
Resource ID segment making up resource name. It identifies the resource within its parent collection as described in https://google.aip.dev/122.
final
modelSettings → Input<AgentModelSettings?>?
Model settings contains various configurations for the LLM model. Structure is documented below.
final
name → Input<String?>?
Identifier. The unique identifier of the agent. Format: projects/{project}/locations/{location}/apps/{app}/agents/{agent}
final
project → Input<String?>?
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
final
remoteDialogflowAgent → Input<AgentRemoteDialogflowAgent?>?
The agent which will transfer execution to an existing remote Dialogflow agent flow. The corresponding 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. Structure is documented below.
final
runtimeType → Type
A representation of the runtime type of the object.
no setterinherited
tools → Input<List<String>?>?
List of available tools for the agent. Format: projects/{project}/locations/{location}/apps/{app}/tools/{tool}
final
toolsets → Input<List<AgentToolset>?>?
List of toolsets for the agent. Structure is documented below.
final
updateTime → Input<String?>?
Timestamp when the agent was last updated.
final

Methods

noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
toMap() → Map<String, dynamic>
toString() → String
A string representation of this object.
inherited

Operators

operator ==(Object other) → bool
The equality operator.
inherited