API Reference

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Agents

Get Agent by ID

client.agents.retrieve(stringagentID, RequestOptionsoptions?): Agent { id, acp_type, created_at, 9 more }

GET/agents/{agent_id}

Delete Agent by ID

client.agents.delete(stringagentID, RequestOptionsoptions?): DeleteResponse { id, message }

DELETE/agents/{agent_id}

List Agents

client.agents.list(AgentListParams { agent_card_metadata, limit, order_by, 3 more } query?, RequestOptionsoptions?): AgentListResponse { id, acp_type, created_at, 9 more }

GET/agents

Handle Agent RPC by ID

client.agents.rpc(stringagentID, AgentRpcParams { method, params, id, jsonrpc } body, RequestOptionsoptions?): AgentRpcResponse { result, id, error, jsonrpc }

POST/agents/{agent_id}/rpc

Get Agent by Name

client.agents.retrieveByName(stringagentName, RequestOptionsoptions?): Agent { id, acp_type, created_at, 9 more }

GET/agents/name/{agent_name}

Delete Agent by Name

client.agents.deleteByName(stringagentName, RequestOptionsoptions?): DeleteResponse { id, message }

DELETE/agents/name/{agent_name}

Handle Agent RPC by Name

client.agents.rpcByName(stringagentName, AgentRpcByNameParams { method, params, id, jsonrpc } body, RequestOptionsoptions?): AgentRpcResponse { result, id, error, jsonrpc }

POST/agents/name/{agent_name}/rpc

Register Build

client.agents.registerBuild(AgentRegisterBuildParams { description, name, agent_input_type, registration_metadata } body, RequestOptionsoptions?): Agent { id, acp_type, created_at, 9 more }

POST/agents/register-build

ModelsExpand Collapse

AcpType = "sync" | "async" | "agentic"

One of the following:

"sync"

"async"

"agentic"

Agent { id, acp_type, created_at, 9 more }

id: string

The unique identifier of the agent.

acp_type: AcpType

The type of the ACP Server (Either sync or async)

One of the following:

"sync"

"async"

"agentic"

created_at: string

The timestamp when the agent was created

formatdate-time

description: string

The description of the action.

name: string

The unique name of the agent.

updated_at: string

The timestamp when the agent was last updated

formatdate-time

agent_input_type?: "text" | "json" | null

The type of input the agent expects.

One of the following:

"text"

"json"

production_deployment_id?: string | null

ID of the current production deployment.

registered_at?: string | null

The timestamp when the agent was last registered

formatdate-time

registration_metadata?: Record<string, unknown> | null

The metadata for the agent’s registration.

status?: "Ready" | "Failed" | "Unknown" | 3 more

The status of the action, indicating if it’s building, ready, failed, etc.

One of the following:

"Ready"

"Failed"

"Unknown"

"Deleted"

"Unhealthy"

"BuildOnly"

status_reason?: string | null

The reason for the status of the action.

AgentRpcRequest { method, params, id, jsonrpc }

method: "event/send" | "task/create" | "message/send" | 2 more

One of the following:

"event/send"

"task/create"

"message/send"

"task/cancel"

"task/interrupt"

params: CreateTaskRequest { name, params, task_metadata } | CancelTaskRequest { task_id, task_name } | InterruptTaskRequest { task_id, task_name } | 2 more

The parameters for the agent RPC request

One of the following:

CreateTaskRequest { name, params, task_metadata }

name?: string | null

Optional human-readable name for the task. When set it must be globally unique. task/create is get-or-create by name: reusing an existing name returns the existing task (with its prior history) instead of creating a new one, so omit name (or make it unique, e.g. by appending a UUID) whenever each call should produce a fresh task.

params?: Record<string, unknown> | null

The parameters for the task. On a get-or-create by name, providing params overwrites the existing task’s params (it is not a pure read).

task_metadata?: Record<string, unknown> | null

Caller-provided metadata to persist on the task row. Only applied at task creation; ignored if a task with this name already exists. Forwarded to the agent inside the ACP payload for backward compatibility.

CancelTaskRequest { task_id, task_name }

task_id?: string | null

The ID of the task to cancel. Either this or task_name must be provided.

task_name?: string | null

The name of the task to cancel. Either this or task_id must be provided.

InterruptTaskRequest { task_id, task_name }

task_id?: string | null

The ID of the task to interrupt. Either this or task_name must be provided.

task_name?: string | null

The name of the task to interrupt. Either this or task_id must be provided.

SendMessageRequest { content, stream, task_id, 2 more }

content: TaskMessageContent

The message that was sent to the agent

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

stream?: boolean

Whether to stream the response message back to the client

task_id?: string | null

The ID of the task that the message was sent to

task_name?: string | null

The name of the task that the message was sent to

task_params?: Record<string, unknown> | null

The parameters for the task (only used when creating new tasks)

SendEventRequest { content, task_id, task_name }

content?: TaskMessageContent | null

The content to send to the event

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id?: string | null

The ID of the task that the event was sent to

task_name?: string | null

The name of the task that the event was sent to

id?: number | string | null

One of the following:

number

string

jsonrpc?: "2.0"

AgentRpcResponse { result, id, error, jsonrpc }

result: AgentRpcResult | null

The result of the agent RPC request

One of the following:

Array<TaskMessage { content, task_id, id, 3 more } >

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

StreamTaskMessageStart { content, index, parent_task_message, type }

Event for starting a streaming message

content: TaskMessageContent

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

index?: number | null

parent_task_message?: TaskMessage { content, task_id, id, 3 more } | null

Represents a message in the agent system.

This entity is used to store messages in MongoDB, with each message associated with a specific task.

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

type?: "start"

StreamTaskMessageDelta { delta, index, parent_task_message, type }

Event for streaming chunks of content

delta?: TaskMessageDelta | null

Delta for text updates

One of the following:

TextDelta { text_delta, type }

Delta for text updates

text_delta?: string | null

type?: "text"

DataDelta { data_delta, type }

Delta for data updates

data_delta?: string | null

type?: "data"

ToolRequestDelta { name, tool_call_id, arguments_delta, type }

Delta for tool request updates

name: string

tool_call_id: string

arguments_delta?: string | null

type?: "tool_request"

ToolResponseDelta { name, tool_call_id, content_delta, type }

Delta for tool response updates

name: string

tool_call_id: string

content_delta?: string | null

type?: "tool_response"

ReasoningSummaryDelta { summary_index, summary_delta, type }

Delta for reasoning summary updates

summary_index: number

summary_delta?: string | null

type?: "reasoning_summary"

ReasoningContentDelta { content_index, content_delta, type }

Delta for reasoning content updates

content_index: number

content_delta?: string | null

type?: "reasoning_content"

index?: number | null

parent_task_message?: TaskMessage { content, task_id, id, 3 more } | null

Represents a message in the agent system.

This entity is used to store messages in MongoDB, with each message associated with a specific task.

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

type?: "delta"

StreamTaskMessageFull { content, index, parent_task_message, type }

Event for streaming the full content

content: TaskMessageContent

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

index?: number | null

parent_task_message?: TaskMessage { content, task_id, id, 3 more } | null

Represents a message in the agent system.

This entity is used to store messages in MongoDB, with each message associated with a specific task.

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

type?: "full"

StreamTaskMessageDone { index, parent_task_message, type }

Event for indicating the task is done

index?: number | null

parent_task_message?: TaskMessage { content, task_id, id, 3 more } | null

Represents a message in the agent system.

This entity is used to store messages in MongoDB, with each message associated with a specific task.

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

type?: "done"

Task { id, cleaned_at, created_at, 6 more }

id: string

cleaned_at?: string | null

created_at?: string | null

name?: string | null

params?: Record<string, unknown> | null

status?: "CANCELED" | "COMPLETED" | "FAILED" | 5 more | null

One of the following:

"CANCELED"

"COMPLETED"

"FAILED"

"RUNNING"

"INTERRUPTED"

"TERMINATED"

"TIMED_OUT"

"DELETED"

status_reason?: string | null

task_metadata?: Record<string, unknown> | null

updated_at?: string | null

Event { id, agent_id, sequence_id, 3 more }

id: string

The UUID of the event

agent_id: string

The UUID of the agent that the event belongs to

sequence_id: number

The sequence ID of the event

task_id: string

The UUID of the task that the event belongs to

content?: TaskMessageContent | null

The content of the event

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

created_at?: string | null

The timestamp of the event

formatdate-time

id?: number | string | null

One of the following:

number

string

error?: unknown

jsonrpc?: "2.0"

AgentRpcResult = Array<TaskMessage { content, task_id, id, 3 more } > | StreamTaskMessageStart { content, index, parent_task_message, type } | StreamTaskMessageDelta { delta, index, parent_task_message, type } | 4 more | null

Event for starting a streaming message

One of the following:

Array<TaskMessage { content, task_id, id, 3 more } >

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

StreamTaskMessageStart { content, index, parent_task_message, type }

Event for starting a streaming message

content: TaskMessageContent

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

index?: number | null

parent_task_message?: TaskMessage { content, task_id, id, 3 more } | null

Represents a message in the agent system.

This entity is used to store messages in MongoDB, with each message associated with a specific task.

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

type?: "start"

StreamTaskMessageDelta { delta, index, parent_task_message, type }

Event for streaming chunks of content

delta?: TaskMessageDelta | null

Delta for text updates

One of the following:

TextDelta { text_delta, type }

Delta for text updates

text_delta?: string | null

type?: "text"

DataDelta { data_delta, type }

Delta for data updates

data_delta?: string | null

type?: "data"

ToolRequestDelta { name, tool_call_id, arguments_delta, type }

Delta for tool request updates

name: string

tool_call_id: string

arguments_delta?: string | null

type?: "tool_request"

ToolResponseDelta { name, tool_call_id, content_delta, type }

Delta for tool response updates

name: string

tool_call_id: string

content_delta?: string | null

type?: "tool_response"

ReasoningSummaryDelta { summary_index, summary_delta, type }

Delta for reasoning summary updates

summary_index: number

summary_delta?: string | null

type?: "reasoning_summary"

ReasoningContentDelta { content_index, content_delta, type }

Delta for reasoning content updates

content_index: number

content_delta?: string | null

type?: "reasoning_content"

index?: number | null

parent_task_message?: TaskMessage { content, task_id, id, 3 more } | null

Represents a message in the agent system.

This entity is used to store messages in MongoDB, with each message associated with a specific task.

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

type?: "delta"

StreamTaskMessageFull { content, index, parent_task_message, type }

Event for streaming the full content

content: TaskMessageContent

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

index?: number | null

parent_task_message?: TaskMessage { content, task_id, id, 3 more } | null

Represents a message in the agent system.

This entity is used to store messages in MongoDB, with each message associated with a specific task.

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

type?: "full"

StreamTaskMessageDone { index, parent_task_message, type }

Event for indicating the task is done

index?: number | null

parent_task_message?: TaskMessage { content, task_id, id, 3 more } | null

Represents a message in the agent system.

This entity is used to store messages in MongoDB, with each message associated with a specific task.

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

type?: "done"

Task { id, cleaned_at, created_at, 6 more }

id: string

cleaned_at?: string | null

created_at?: string | null

name?: string | null

params?: Record<string, unknown> | null

status?: "CANCELED" | "COMPLETED" | "FAILED" | 5 more | null

One of the following:

"CANCELED"

"COMPLETED"

"FAILED"

"RUNNING"

"INTERRUPTED"

"TERMINATED"

"TIMED_OUT"

"DELETED"

status_reason?: string | null

task_metadata?: Record<string, unknown> | null

updated_at?: string | null

Event { id, agent_id, sequence_id, 3 more }

id: string

The UUID of the event

agent_id: string

The UUID of the agent that the event belongs to

sequence_id: number

The sequence ID of the event

task_id: string

The UUID of the task that the event belongs to

content?: TaskMessageContent | null

The content of the event

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

created_at?: string | null

The timestamp of the event

formatdate-time

DataDelta { data_delta, type }

Delta for data updates

data_delta?: string | null

type?: "data"

ReasoningContentDelta { content_index, content_delta, type }

Delta for reasoning content updates

content_index: number

content_delta?: string | null

type?: "reasoning_content"

ReasoningSummaryDelta { summary_index, summary_delta, type }

Delta for reasoning summary updates

summary_index: number

summary_delta?: string | null

type?: "reasoning_summary"

TaskMessageContent = TextContent { author, content, attachments, 3 more } | ReasoningContent { author, summary, content, 2 more } | DataContent { author, data, style, type } | 2 more

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

TaskMessageDelta = TextDelta { text_delta, type } | DataDelta { data_delta, type } | ToolRequestDelta { name, tool_call_id, arguments_delta, type } | 3 more

Delta for text updates

One of the following:

TextDelta { text_delta, type }

Delta for text updates

text_delta?: string | null

type?: "text"

DataDelta { data_delta, type }

Delta for data updates

data_delta?: string | null

type?: "data"

ToolRequestDelta { name, tool_call_id, arguments_delta, type }

Delta for tool request updates

name: string

tool_call_id: string

arguments_delta?: string | null

type?: "tool_request"

ToolResponseDelta { name, tool_call_id, content_delta, type }

Delta for tool response updates

name: string

tool_call_id: string

content_delta?: string | null

type?: "tool_response"

ReasoningSummaryDelta { summary_index, summary_delta, type }

Delta for reasoning summary updates

summary_index: number

summary_delta?: string | null

type?: "reasoning_summary"

ReasoningContentDelta { content_index, content_delta, type }

Delta for reasoning content updates

content_index: number

content_delta?: string | null

type?: "reasoning_content"

TaskMessageUpdate = StreamTaskMessageStart { content, index, parent_task_message, type } | StreamTaskMessageDelta { delta, index, parent_task_message, type } | StreamTaskMessageFull { content, index, parent_task_message, type } | StreamTaskMessageDone { index, parent_task_message, type }

Event for starting a streaming message

One of the following:

StreamTaskMessageStart { content, index, parent_task_message, type }

Event for starting a streaming message

content: TaskMessageContent

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

index?: number | null

parent_task_message?: TaskMessage { content, task_id, id, 3 more } | null

Represents a message in the agent system.

This entity is used to store messages in MongoDB, with each message associated with a specific task.

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

type?: "start"

StreamTaskMessageDelta { delta, index, parent_task_message, type }

Event for streaming chunks of content

delta?: TaskMessageDelta | null

Delta for text updates

One of the following:

TextDelta { text_delta, type }

Delta for text updates

text_delta?: string | null

type?: "text"

DataDelta { data_delta, type }

Delta for data updates

data_delta?: string | null

type?: "data"

ToolRequestDelta { name, tool_call_id, arguments_delta, type }

Delta for tool request updates

name: string

tool_call_id: string

arguments_delta?: string | null

type?: "tool_request"

ToolResponseDelta { name, tool_call_id, content_delta, type }

Delta for tool response updates

name: string

tool_call_id: string

content_delta?: string | null

type?: "tool_response"

ReasoningSummaryDelta { summary_index, summary_delta, type }

Delta for reasoning summary updates

summary_index: number

summary_delta?: string | null

type?: "reasoning_summary"

ReasoningContentDelta { content_index, content_delta, type }

Delta for reasoning content updates

content_index: number

content_delta?: string | null

type?: "reasoning_content"

index?: number | null

parent_task_message?: TaskMessage { content, task_id, id, 3 more } | null

Represents a message in the agent system.

This entity is used to store messages in MongoDB, with each message associated with a specific task.

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

type?: "delta"

StreamTaskMessageFull { content, index, parent_task_message, type }

Event for streaming the full content

content: TaskMessageContent

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

index?: number | null

parent_task_message?: TaskMessage { content, task_id, id, 3 more } | null

Represents a message in the agent system.

This entity is used to store messages in MongoDB, with each message associated with a specific task.

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

type?: "full"

StreamTaskMessageDone { index, parent_task_message, type }

Event for indicating the task is done

index?: number | null

parent_task_message?: TaskMessage { content, task_id, id, 3 more } | null

Represents a message in the agent system.

This entity is used to store messages in MongoDB, with each message associated with a specific task.

content: TaskMessageContent

The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user.

One of the following:

TextContent { author, content, attachments, 3 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: string

The contents of the text message.

attachments?: Array<Attachment> | null

Optional list of file attachments with structured metadata.

file_id: string

The unique ID of the attached file

name: string

The name of the file

size: number

The size of the file in bytes

type: string

The MIME type or content type of the file

format?: TextFormat

The format of the message. This is used by the client to determine how to display the message.

One of the following:

"markdown"

"plain"

"code"

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "text"

The type of the message, in this case text.

ReasoningContent { author, summary, content, 2 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

summary: Array<string>

A list of short reasoning summaries

content?: Array<string> | null

The reasoning content or chain-of-thought text

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "reasoning"

The type of the message, in this case reasoning.

DataContent { author, data, style, type }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

data: Record<string, unknown>

The contents of the data message.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "data"

The type of the message, in this case data.

ToolRequestContent { arguments, author, name, 3 more }

arguments: Record<string, unknown>

The arguments to the tool.

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

name: string

The name of the tool that is being requested.

tool_call_id: string

The ID of the tool call that is being requested.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent { author, content, name, 4 more }

author: MessageAuthor

The role of the messages author, in this case system, user, assistant, or tool.

One of the following:

"user"

"agent"

content: unknown

The result of the tool.

name: string

The name of the tool that is being responded to.

tool_call_id: string

The ID of the tool call that is being responded to.

is_error?: boolean | null

Whether the tool call resulted in an error. None when the harness does not report a status.

style?: MessageStyle

The style of the message. This is used by the client to determine how to display the message.

One of the following:

"static"

"active"

type?: "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id?: string | null

The task message’s unique id

created_at?: string | null

The timestamp when the message was created

formatdate-time

streaming_status?: "IN_PROGRESS" | "DONE" | null

One of the following:

"IN_PROGRESS"

"DONE"

updated_at?: string | null

The timestamp when the message was last updated

formatdate-time

type?: "done"

TextDelta { text_delta, type }

Delta for text updates

text_delta?: string | null

type?: "text"

ToolRequestDelta { name, tool_call_id, arguments_delta, type }

Delta for tool request updates

name: string

tool_call_id: string

arguments_delta?: string | null

type?: "tool_request"

ToolResponseDelta { name, tool_call_id, content_delta, type }

Delta for tool response updates

name: string

tool_call_id: string

content_delta?: string | null

type?: "tool_response"

AgentListResponse = Array<Agent { id, acp_type, created_at, 9 more } >

id: string

The unique identifier of the agent.

acp_type: AcpType

The type of the ACP Server (Either sync or async)

One of the following:

"sync"

"async"

"agentic"

created_at: string

The timestamp when the agent was created

formatdate-time

description: string

The description of the action.

name: string

The unique name of the agent.

updated_at: string

The timestamp when the agent was last updated

formatdate-time

agent_input_type?: "text" | "json" | null

The type of input the agent expects.

One of the following:

"text"

"json"

production_deployment_id?: string | null

ID of the current production deployment.

registered_at?: string | null

The timestamp when the agent was last registered

formatdate-time

registration_metadata?: Record<string, unknown> | null

The metadata for the agent’s registration.

status?: "Ready" | "Failed" | "Unknown" | 3 more

The status of the action, indicating if it’s building, ready, failed, etc.

One of the following:

"Ready"

"Failed"

"Unknown"

"Deleted"

"Unhealthy"

"BuildOnly"

status_reason?: string | null

The reason for the status of the action.

AgentsDeployments

Create Deployment

client.agents.deployments.create(stringagentID, DeploymentCreateParams { docker_image, helm_release_name, registration_metadata, sgp_deploy_id } body, RequestOptionsoptions?): DeploymentCreateResponse { id, agent_id, docker_image, 9 more }

POST/agents/{agent_id}/deployments

List Deployments

client.agents.deployments.list(stringagentID, DeploymentListParams { limit, order_by, order_direction, page_number } query?, RequestOptionsoptions?): DeploymentListResponse { id, agent_id, docker_image, 9 more }

GET/agents/{agent_id}/deployments

Get Deployment

client.agents.deployments.retrieve(stringdeploymentID, DeploymentRetrieveParams { agent_id } params, RequestOptionsoptions?): DeploymentRetrieveResponse { id, agent_id, docker_image, 9 more }

GET/agents/{agent_id}/deployments/{deployment_id}

Delete Deployment

client.agents.deployments.delete(stringdeploymentID, DeploymentDeleteParams { agent_id } params, RequestOptionsoptions?): DeleteResponse { id, message }

DELETE/agents/{agent_id}/deployments/{deployment_id}

Promote Deployment

client.agents.deployments.promote(stringdeploymentID, DeploymentPromoteParams { agent_id } params, RequestOptionsoptions?): DeploymentPromoteResponse { id, agent_id, docker_image, 9 more }

POST/agents/{agent_id}/deployments/{deployment_id}/promote

Preview RPC

client.agents.deployments.previewRpc(stringdeploymentID, DeploymentPreviewRpcParams { agent_id, method, params, 2 more } params, RequestOptionsoptions?): AgentRpcResponse { result, id, error, jsonrpc }

POST/agents/{agent_id}/deployments/{deployment_id}/rpc

ModelsExpand Collapse

DeploymentCreateResponse { id, agent_id, docker_image, 9 more }

id: string

The unique identifier of the deployment.

agent_id: string

The agent this deployment belongs to.

docker_image: string

Full Docker image URI.

is_production: boolean

Whether this is the production deployment.

status: "Pending" | "Ready" | "Failed"

Current deployment status.

One of the following:

"Pending"

"Ready"

"Failed"

acp_url?: string | null

ACP URL set when agent registers.

created_at?: string | null

When the deployment was created.

formatdate-time

expires_at?: string | null

When marked for cleanup.

formatdate-time

helm_release_name?: string | null

Helm release name for cleanup.

promoted_at?: string | null

When promoted to production.

formatdate-time

registration_metadata?: Record<string, unknown> | null

Git/build metadata from the agent pod.

sgp_deploy_id?: string | null

Correlates to SGP’s agentex_deploys.id.

DeploymentListResponse = Array<DeploymentListResponseItem>

id: string

The unique identifier of the deployment.

agent_id: string

The agent this deployment belongs to.

docker_image: string

Full Docker image URI.

is_production: boolean

Whether this is the production deployment.

status: "Pending" | "Ready" | "Failed"

Current deployment status.

One of the following:

"Pending"

"Ready"

"Failed"

acp_url?: string | null

ACP URL set when agent registers.

created_at?: string | null

When the deployment was created.

formatdate-time

expires_at?: string | null

When marked for cleanup.

formatdate-time

helm_release_name?: string | null

Helm release name for cleanup.

promoted_at?: string | null

When promoted to production.

formatdate-time

registration_metadata?: Record<string, unknown> | null

Git/build metadata from the agent pod.

sgp_deploy_id?: string | null

Correlates to SGP’s agentex_deploys.id.

DeploymentRetrieveResponse { id, agent_id, docker_image, 9 more }

id: string

The unique identifier of the deployment.

agent_id: string

The agent this deployment belongs to.

docker_image: string

Full Docker image URI.

is_production: boolean

Whether this is the production deployment.

status: "Pending" | "Ready" | "Failed"

Current deployment status.

One of the following:

"Pending"

"Ready"

"Failed"

acp_url?: string | null

ACP URL set when agent registers.

created_at?: string | null

When the deployment was created.

formatdate-time

expires_at?: string | null

When marked for cleanup.

formatdate-time

helm_release_name?: string | null

Helm release name for cleanup.

promoted_at?: string | null

When promoted to production.

formatdate-time

registration_metadata?: Record<string, unknown> | null

Git/build metadata from the agent pod.

sgp_deploy_id?: string | null

Correlates to SGP’s agentex_deploys.id.

DeploymentPromoteResponse { id, agent_id, docker_image, 9 more }

id: string

The unique identifier of the deployment.

agent_id: string

The agent this deployment belongs to.

docker_image: string

Full Docker image URI.

is_production: boolean

Whether this is the production deployment.

status: "Pending" | "Ready" | "Failed"

Current deployment status.

One of the following:

"Pending"

"Ready"

"Failed"

acp_url?: string | null

ACP URL set when agent registers.

created_at?: string | null

When the deployment was created.

formatdate-time

expires_at?: string | null

When marked for cleanup.

formatdate-time

helm_release_name?: string | null

Helm release name for cleanup.

promoted_at?: string | null

When promoted to production.

formatdate-time

registration_metadata?: Record<string, unknown> | null

Git/build metadata from the agent pod.

sgp_deploy_id?: string | null

Correlates to SGP’s agentex_deploys.id.

AgentsSchedules

Create Run Schedule

client.agents.schedules.create(stringagentID, ScheduleCreateParams { initial_input, name, cron_expression, 8 more } body, RequestOptionsoptions?): ScheduleCreateResponse { id, agent_id, initial_input, 20 more }

POST/agents/{agent_id}/schedules

List Run Schedules

client.agents.schedules.list(stringagentID, ScheduleListParams { include_live, limit } query?, RequestOptionsoptions?): ScheduleListResponse { run_schedules, total }

GET/agents/{agent_id}/schedules

Get Run Schedule

client.agents.schedules.retrieve(stringscheduleID, ScheduleRetrieveParams { agent_id } params, RequestOptionsoptions?): ScheduleRetrieveResponse { id, agent_id, initial_input, 20 more }

GET/agents/{agent_id}/schedules/{schedule_id}

Update Run Schedule

client.agents.schedules.update(stringscheduleID, ScheduleUpdateParams { agent_id, cron_expression, description, 9 more } params, RequestOptionsoptions?): ScheduleUpdateResponse { id, agent_id, initial_input, 20 more }

PATCH/agents/{agent_id}/schedules/{schedule_id}

Delete Run Schedule

client.agents.schedules.delete(stringscheduleID, ScheduleDeleteParams { agent_id } params, RequestOptionsoptions?): DeleteResponse { id, message }

DELETE/agents/{agent_id}/schedules/{schedule_id}

Pause Run Schedule

client.agents.schedules.pause(stringscheduleID, SchedulePauseParams { agent_id, note } params, RequestOptionsoptions?): SchedulePauseResponse { id, agent_id, initial_input, 20 more }

POST/agents/{agent_id}/schedules/{schedule_id}/pause

Resume Run Schedule

client.agents.schedules.resume(stringscheduleID, ScheduleResumeParams { agent_id, note } params, RequestOptionsoptions?): ScheduleResumeResponse { id, agent_id, initial_input, 20 more }

POST/agents/{agent_id}/schedules/{schedule_id}/resume

Trigger Run Schedule

client.agents.schedules.trigger(stringscheduleID, ScheduleTriggerParams { agent_id } params, RequestOptionsoptions?): ScheduleTriggerResponse { id, agent_id, initial_input, 20 more }

POST/agents/{agent_id}/schedules/{schedule_id}/trigger

Skip Run Schedule Action

client.agents.schedules.skip(stringscheduleID, ScheduleSkipParams { agent_id, scheduled_time } params, RequestOptionsoptions?): ScheduleSkipResponse { id, agent_id, initial_input, 20 more }

POST/agents/{agent_id}/schedules/{schedule_id}/skip

Unskip Run Schedule Action

client.agents.schedules.unskip(stringscheduleID, ScheduleUnskipParams { agent_id, scheduled_time } params, RequestOptionsoptions?): ScheduleUnskipResponse { id, agent_id, initial_input, 20 more }

POST/agents/{agent_id}/schedules/{schedule_id}/unskip

Get Run Schedule By Name

client.agents.schedules.retrieveByName(stringname, ScheduleRetrieveByNameParams { agent_id } params, RequestOptionsoptions?): ScheduleRetrieveByNameResponse { id, agent_id, initial_input, 20 more }

GET/agents/{agent_id}/schedules/name/{name}

Update Run Schedule By Name

client.agents.schedules.updateByName(stringname, ScheduleUpdateByNameParams { agent_id, cron_expression, description, 9 more } params, RequestOptionsoptions?): ScheduleUpdateByNameResponse { id, agent_id, initial_input, 20 more }

PATCH/agents/{agent_id}/schedules/name/{name}

Delete Run Schedule By Name

client.agents.schedules.deleteByName(stringname, ScheduleDeleteByNameParams { agent_id } params, RequestOptionsoptions?): DeleteResponse { id, message }

DELETE/agents/{agent_id}/schedules/name/{name}

Pause Run Schedule By Name

client.agents.schedules.pauseByName(stringname, SchedulePauseByNameParams { agent_id, note } params, RequestOptionsoptions?): SchedulePauseByNameResponse { id, agent_id, initial_input, 20 more }

POST/agents/{agent_id}/schedules/name/{name}/pause

Resume Run Schedule By Name

client.agents.schedules.resumeByName(stringname, ScheduleResumeByNameParams { agent_id, note } params, RequestOptionsoptions?): ScheduleResumeByNameResponse { id, agent_id, initial_input, 20 more }

POST/agents/{agent_id}/schedules/name/{name}/resume

Trigger Run Schedule By Name

client.agents.schedules.triggerByName(stringname, ScheduleTriggerByNameParams { agent_id } params, RequestOptionsoptions?): ScheduleTriggerByNameResponse { id, agent_id, initial_input, 20 more }

POST/agents/{agent_id}/schedules/name/{name}/trigger

ModelsExpand Collapse

ScheduleCreateResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

ScheduleListResponse { run_schedules, total }

Response model for listing run schedules.

run_schedules: Array<RunSchedule>

The list of run schedules.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

total: number

The number of run schedules returned.

ScheduleRetrieveResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

ScheduleUpdateResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

SchedulePauseResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

ScheduleResumeResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

ScheduleTriggerResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

ScheduleSkipResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

ScheduleUnskipResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

ScheduleRetrieveByNameResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

ScheduleUpdateByNameResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

SchedulePauseByNameResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

ScheduleResumeByNameResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time

ScheduleTriggerByNameResponse { id, agent_id, initial_input, 20 more }

Response model describing a scheduled agent run.

id: string

The unique identifier of the run schedule.

agent_id: string

The agent this schedule belongs to.

initial_input: InitialInput { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author?: MessageAuthor

The author attributed to the initial input.

One of the following:

"user"

"agent"

type?: "text"

Input content type.

initial_input_method: string

Delivery method, inferred from the agent’s ACP type.

name: string

Human-readable schedule name.

created_at?: string | null

When the schedule was created.

formatdate-time

creator_principal?: CreatorPrincipal | null

Credential-free creator identity stored with the schedule.

Never carries cookies, JWTs, API keys, OAuth tokens, or request headers — it is creator context used only for AuthZ and ownership at fire time.

account_id?: string | null

Account/workspace id of the creator.

principal_type?: string | null

e.g. ‘user’ or ‘service_account’.

service_account_id?: string | null

Creator service-account id, if a service principal.

user_id?: string | null

Creator user id, if a user principal.

cron_expression?: string | null

Cron cadence, if cron-based.

description?: string | null

Optional description.

end_at?: string | null

Schedule deactivation time.

formatdate-time

interval_seconds?: number | null

Interval cadence in seconds, if interval-based.

last_action_time?: string | null

When the schedule last fired.

formatdate-time

live_data_available?: boolean | null

Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested.

next_action_times?: Array<string>

Upcoming scheduled fire times.

num_actions_taken?: number

Number of times the schedule has fired.

paused?: boolean

Whether the schedule is paused.

skipped_action_times?: Array<string>

Skipped one-off scheduled fire times.

start_at?: string | null

Schedule activation time.

formatdate-time

state?: "ACTIVE" | "PAUSED"

Live schedule state from Temporal.

One of the following:

"ACTIVE"

"PAUSED"

task_metadata?: Record<string, unknown> | null

Task metadata at fire time.

task_params?: Record<string, unknown> | null

Task params at fire time.

timezone?: string

Timezone the cron expression is evaluated in.

updated_at?: string | null

When the schedule was updated.

formatdate-time