Skip to content

Agents

Get Agent by ID
GET/agents/{agent_id}
Delete Agent by ID
DELETE/agents/{agent_id}
List Agents
GET/agents
Handle Agent RPC by ID
POST/agents/{agent_id}/rpc
Get Agent by Name
GET/agents/name/{agent_name}
Delete Agent by Name
DELETE/agents/name/{agent_name}
Handle Agent RPC by Name
POST/agents/name/{agent_name}/rpc
Register Build
POST/agents/register-build
ModelsExpand Collapse
AcpType = "sync" or "async" or "agentic"
One of the following:
"sync"
"async"
"agentic"
Agent object { 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: optional "text" or "json"

The type of input the agent expects.

One of the following:
"text"
"json"
production_deployment_id: optional string

ID of the current production deployment.

registered_at: optional string

The timestamp when the agent was last registered

formatdate-time
registration_metadata: optional map[unknown]

The metadata for the agent’s registration.

status: optional "Ready" or "Failed" or "Unknown" or 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: optional string

The reason for the status of the action.

AgentRpcRequest object { method, params, id, jsonrpc }
method: "event/send" or "task/create" or "message/send" or 2 more
One of the following:
"event/send"
"task/create"
"message/send"
"task/cancel"
"task/interrupt"
params: object { name, params, task_metadata } or object { task_id, task_name } or object { task_id, task_name } or 2 more

The parameters for the agent RPC request

One of the following:
CreateTaskRequest object { name, params, task_metadata }
name: optional string

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: optional map[unknown]

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: optional map[unknown]

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 object { task_id, task_name }
task_id: optional string

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

task_name: optional string

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

InterruptTaskRequest object { task_id, task_name }
task_id: optional string

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

task_name: optional string

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

SendMessageRequest object { content, stream, task_id, 2 more }

The message that was sent to the agent

One of the following:
TextContent object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

stream: optional boolean

Whether to stream the response message back to the client

task_id: optional string

The ID of the task that the message was sent to

task_name: optional string

The name of the task that the message was sent to

task_params: optional map[unknown]

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

SendEventRequest object { content, task_id, task_name }
content: optional TaskMessageContent

The content to send to the event

One of the following:
TextContent object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: optional string

The ID of the task that the event was sent to

task_name: optional string

The name of the task that the event was sent to

id: optional number or string
One of the following:
number
string
jsonrpc: optional "2.0"
AgentRpcResponse object { result, id, error, jsonrpc }

The result of the agent RPC request

One of the following:
array of TaskMessage { content, task_id, id, 3 more }

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
StreamTaskMessageStart object { content, index, parent_task_message, type }

Event for starting a streaming message

One of the following:
TextContent object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

index: optional number
parent_task_message: optional TaskMessage { content, task_id, id, 3 more }

Represents a message in the agent system.

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

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
type: optional "start"
StreamTaskMessageDelta object { delta, index, parent_task_message, type }

Event for streaming chunks of content

delta: optional TaskMessageDelta

Delta for text updates

One of the following:
TextDelta object { text_delta, type }

Delta for text updates

text_delta: optional string
type: optional "text"
DataDelta object { data_delta, type }

Delta for data updates

data_delta: optional string
type: optional "data"
ToolRequestDelta object { name, tool_call_id, arguments_delta, type }

Delta for tool request updates

name: string
tool_call_id: string
arguments_delta: optional string
type: optional "tool_request"
ToolResponseDelta object { name, tool_call_id, content_delta, type }

Delta for tool response updates

name: string
tool_call_id: string
content_delta: optional string
type: optional "tool_response"
ReasoningSummaryDelta object { summary_index, summary_delta, type }

Delta for reasoning summary updates

summary_index: number
summary_delta: optional string
type: optional "reasoning_summary"
ReasoningContentDelta object { content_index, content_delta, type }

Delta for reasoning content updates

content_index: number
content_delta: optional string
type: optional "reasoning_content"
index: optional number
parent_task_message: optional TaskMessage { content, task_id, id, 3 more }

Represents a message in the agent system.

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

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
type: optional "delta"
StreamTaskMessageFull object { content, index, parent_task_message, type }

Event for streaming the full content

One of the following:
TextContent object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

index: optional number
parent_task_message: optional TaskMessage { content, task_id, id, 3 more }

Represents a message in the agent system.

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

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
type: optional "full"
StreamTaskMessageDone object { index, parent_task_message, type }

Event for indicating the task is done

index: optional number
parent_task_message: optional TaskMessage { content, task_id, id, 3 more }

Represents a message in the agent system.

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

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
type: optional "done"
Task object { id, cleaned_at, created_at, 6 more }
id: string
cleaned_at: optional string
created_at: optional string
name: optional string
params: optional map[unknown]
status: optional "CANCELED" or "COMPLETED" or "FAILED" or 5 more
One of the following:
"CANCELED"
"COMPLETED"
"FAILED"
"RUNNING"
"INTERRUPTED"
"TERMINATED"
"TIMED_OUT"
"DELETED"
status_reason: optional string
task_metadata: optional map[unknown]
updated_at: optional string
Event object { 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: optional TaskMessageContent

The content of the event

One of the following:
TextContent object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

created_at: optional string

The timestamp of the event

formatdate-time
id: optional number or string
One of the following:
number
string
error: optional unknown
jsonrpc: optional "2.0"
AgentRpcResult = array of TaskMessage { content, task_id, id, 3 more } or object { content, index, parent_task_message, type } or object { delta, index, parent_task_message, type } or 4 more

Event for starting a streaming message

One of the following:
array of TaskMessage { content, task_id, id, 3 more }

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
StreamTaskMessageStart object { content, index, parent_task_message, type }

Event for starting a streaming message

One of the following:
TextContent object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

index: optional number
parent_task_message: optional TaskMessage { content, task_id, id, 3 more }

Represents a message in the agent system.

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

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
type: optional "start"
StreamTaskMessageDelta object { delta, index, parent_task_message, type }

Event for streaming chunks of content

delta: optional TaskMessageDelta

Delta for text updates

One of the following:
TextDelta object { text_delta, type }

Delta for text updates

text_delta: optional string
type: optional "text"
DataDelta object { data_delta, type }

Delta for data updates

data_delta: optional string
type: optional "data"
ToolRequestDelta object { name, tool_call_id, arguments_delta, type }

Delta for tool request updates

name: string
tool_call_id: string
arguments_delta: optional string
type: optional "tool_request"
ToolResponseDelta object { name, tool_call_id, content_delta, type }

Delta for tool response updates

name: string
tool_call_id: string
content_delta: optional string
type: optional "tool_response"
ReasoningSummaryDelta object { summary_index, summary_delta, type }

Delta for reasoning summary updates

summary_index: number
summary_delta: optional string
type: optional "reasoning_summary"
ReasoningContentDelta object { content_index, content_delta, type }

Delta for reasoning content updates

content_index: number
content_delta: optional string
type: optional "reasoning_content"
index: optional number
parent_task_message: optional TaskMessage { content, task_id, id, 3 more }

Represents a message in the agent system.

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

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
type: optional "delta"
StreamTaskMessageFull object { content, index, parent_task_message, type }

Event for streaming the full content

One of the following:
TextContent object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

index: optional number
parent_task_message: optional TaskMessage { content, task_id, id, 3 more }

Represents a message in the agent system.

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

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
type: optional "full"
StreamTaskMessageDone object { index, parent_task_message, type }

Event for indicating the task is done

index: optional number
parent_task_message: optional TaskMessage { content, task_id, id, 3 more }

Represents a message in the agent system.

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

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
type: optional "done"
Task object { id, cleaned_at, created_at, 6 more }
id: string
cleaned_at: optional string
created_at: optional string
name: optional string
params: optional map[unknown]
status: optional "CANCELED" or "COMPLETED" or "FAILED" or 5 more
One of the following:
"CANCELED"
"COMPLETED"
"FAILED"
"RUNNING"
"INTERRUPTED"
"TERMINATED"
"TIMED_OUT"
"DELETED"
status_reason: optional string
task_metadata: optional map[unknown]
updated_at: optional string
Event object { 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: optional TaskMessageContent

The content of the event

One of the following:
TextContent object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

created_at: optional string

The timestamp of the event

formatdate-time
DataDelta object { data_delta, type }

Delta for data updates

data_delta: optional string
type: optional "data"
ReasoningContentDelta object { content_index, content_delta, type }

Delta for reasoning content updates

content_index: number
content_delta: optional string
type: optional "reasoning_content"
ReasoningSummaryDelta object { summary_index, summary_delta, type }

Delta for reasoning summary updates

summary_index: number
summary_delta: optional string
type: optional "reasoning_summary"
TaskMessageContent = TextContent { author, content, attachments, 3 more } or ReasoningContent { author, summary, content, 2 more } or DataContent { author, data, style, type } or 2 more
One of the following:
TextContent object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

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

Delta for text updates

One of the following:
TextDelta object { text_delta, type }

Delta for text updates

text_delta: optional string
type: optional "text"
DataDelta object { data_delta, type }

Delta for data updates

data_delta: optional string
type: optional "data"
ToolRequestDelta object { name, tool_call_id, arguments_delta, type }

Delta for tool request updates

name: string
tool_call_id: string
arguments_delta: optional string
type: optional "tool_request"
ToolResponseDelta object { name, tool_call_id, content_delta, type }

Delta for tool response updates

name: string
tool_call_id: string
content_delta: optional string
type: optional "tool_response"
ReasoningSummaryDelta object { summary_index, summary_delta, type }

Delta for reasoning summary updates

summary_index: number
summary_delta: optional string
type: optional "reasoning_summary"
ReasoningContentDelta object { content_index, content_delta, type }

Delta for reasoning content updates

content_index: number
content_delta: optional string
type: optional "reasoning_content"
TaskMessageUpdate = object { content, index, parent_task_message, type } or object { delta, index, parent_task_message, type } or object { content, index, parent_task_message, type } or object { index, parent_task_message, type }

Event for starting a streaming message

One of the following:
Start object { content, index, parent_task_message, type }

Event for starting a streaming message

One of the following:
TextContent object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

index: optional number
parent_task_message: optional TaskMessage { content, task_id, id, 3 more }

Represents a message in the agent system.

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

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
type: optional "start"
Delta object { delta, index, parent_task_message, type }

Event for streaming chunks of content

delta: optional TaskMessageDelta

Delta for text updates

One of the following:
TextDelta object { text_delta, type }

Delta for text updates

text_delta: optional string
type: optional "text"
DataDelta object { data_delta, type }

Delta for data updates

data_delta: optional string
type: optional "data"
ToolRequestDelta object { name, tool_call_id, arguments_delta, type }

Delta for tool request updates

name: string
tool_call_id: string
arguments_delta: optional string
type: optional "tool_request"
ToolResponseDelta object { name, tool_call_id, content_delta, type }

Delta for tool response updates

name: string
tool_call_id: string
content_delta: optional string
type: optional "tool_response"
ReasoningSummaryDelta object { summary_index, summary_delta, type }

Delta for reasoning summary updates

summary_index: number
summary_delta: optional string
type: optional "reasoning_summary"
ReasoningContentDelta object { content_index, content_delta, type }

Delta for reasoning content updates

content_index: number
content_delta: optional string
type: optional "reasoning_content"
index: optional number
parent_task_message: optional TaskMessage { content, task_id, id, 3 more }

Represents a message in the agent system.

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

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
type: optional "delta"
Full object { content, index, parent_task_message, type }

Event for streaming the full content

One of the following:
TextContent object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

index: optional number
parent_task_message: optional TaskMessage { content, task_id, id, 3 more }

Represents a message in the agent system.

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

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
type: optional "full"
Done object { index, parent_task_message, type }

Event for indicating the task is done

index: optional number
parent_task_message: optional TaskMessage { content, task_id, id, 3 more }

Represents a message in the agent system.

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

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 object { author, content, attachments, 3 more }

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: optional array of object { file_id, name, size, type }

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: optional 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: optional 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: optional "text"

The type of the message, in this case text.

ReasoningContent object { author, summary, content, 2 more }

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

One of the following:
"user"
"agent"
summary: array of string

A list of short reasoning summaries

content: optional array of string

The reasoning content or chain-of-thought text

style: optional 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: optional "reasoning"

The type of the message, in this case reasoning.

DataContent object { author, data, style, type }

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

One of the following:
"user"
"agent"
data: map[unknown]

The contents of the data message.

style: optional 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: optional "data"

The type of the message, in this case data.

ToolRequestContent object { arguments, author, name, 3 more }
arguments: map[unknown]

The arguments to the tool.

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: optional 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: optional "tool_request"

The type of the message, in this case tool_request.

ToolResponseContent object { author, content, name, 4 more }

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: optional boolean

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

style: optional 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: optional "tool_response"

The type of the message, in this case tool_response.

task_id: string

ID of the task this message belongs to

id: optional string

The task message’s unique id

created_at: optional string

The timestamp when the message was created

formatdate-time
streaming_status: optional "IN_PROGRESS" or "DONE"
One of the following:
"IN_PROGRESS"
"DONE"
updated_at: optional string

The timestamp when the message was last updated

formatdate-time
type: optional "done"
TextDelta object { text_delta, type }

Delta for text updates

text_delta: optional string
type: optional "text"
ToolRequestDelta object { name, tool_call_id, arguments_delta, type }

Delta for tool request updates

name: string
tool_call_id: string
arguments_delta: optional string
type: optional "tool_request"
ToolResponseDelta object { name, tool_call_id, content_delta, type }

Delta for tool response updates

name: string
tool_call_id: string
content_delta: optional string
type: optional "tool_response"
AgentListResponse = array of 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: optional "text" or "json"

The type of input the agent expects.

One of the following:
"text"
"json"
production_deployment_id: optional string

ID of the current production deployment.

registered_at: optional string

The timestamp when the agent was last registered

formatdate-time
registration_metadata: optional map[unknown]

The metadata for the agent’s registration.

status: optional "Ready" or "Failed" or "Unknown" or 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: optional string

The reason for the status of the action.

AgentsDeployments

Create Deployment
POST/agents/{agent_id}/deployments
List Deployments
GET/agents/{agent_id}/deployments
Get Deployment
GET/agents/{agent_id}/deployments/{deployment_id}
Delete Deployment
DELETE/agents/{agent_id}/deployments/{deployment_id}
Promote Deployment
POST/agents/{agent_id}/deployments/{deployment_id}/promote
Preview RPC
POST/agents/{agent_id}/deployments/{deployment_id}/rpc
ModelsExpand Collapse
DeploymentCreateResponse object { 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" or "Ready" or "Failed"

Current deployment status.

One of the following:
"Pending"
"Ready"
"Failed"
acp_url: optional string

ACP URL set when agent registers.

created_at: optional string

When the deployment was created.

formatdate-time
expires_at: optional string

When marked for cleanup.

formatdate-time
helm_release_name: optional string

Helm release name for cleanup.

When promoted to production.

formatdate-time
registration_metadata: optional map[unknown]

Git/build metadata from the agent pod.

sgp_deploy_id: optional string

Correlates to SGP’s agentex_deploys.id.

DeploymentListResponse = array of object { 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" or "Ready" or "Failed"

Current deployment status.

One of the following:
"Pending"
"Ready"
"Failed"
acp_url: optional string

ACP URL set when agent registers.

created_at: optional string

When the deployment was created.

formatdate-time
expires_at: optional string

When marked for cleanup.

formatdate-time
helm_release_name: optional string

Helm release name for cleanup.

When promoted to production.

formatdate-time
registration_metadata: optional map[unknown]

Git/build metadata from the agent pod.

sgp_deploy_id: optional string

Correlates to SGP’s agentex_deploys.id.

DeploymentRetrieveResponse object { 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" or "Ready" or "Failed"

Current deployment status.

One of the following:
"Pending"
"Ready"
"Failed"
acp_url: optional string

ACP URL set when agent registers.

created_at: optional string

When the deployment was created.

formatdate-time
expires_at: optional string

When marked for cleanup.

formatdate-time
helm_release_name: optional string

Helm release name for cleanup.

When promoted to production.

formatdate-time
registration_metadata: optional map[unknown]

Git/build metadata from the agent pod.

sgp_deploy_id: optional string

Correlates to SGP’s agentex_deploys.id.

DeploymentPromoteResponse object { 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" or "Ready" or "Failed"

Current deployment status.

One of the following:
"Pending"
"Ready"
"Failed"
acp_url: optional string

ACP URL set when agent registers.

created_at: optional string

When the deployment was created.

formatdate-time
expires_at: optional string

When marked for cleanup.

formatdate-time
helm_release_name: optional string

Helm release name for cleanup.

When promoted to production.

formatdate-time
registration_metadata: optional map[unknown]

Git/build metadata from the agent pod.

sgp_deploy_id: optional string

Correlates to SGP’s agentex_deploys.id.

AgentsSchedules

Create Run Schedule
POST/agents/{agent_id}/schedules
List Run Schedules
GET/agents/{agent_id}/schedules
Get Run Schedule
GET/agents/{agent_id}/schedules/{schedule_id}
Update Run Schedule
PATCH/agents/{agent_id}/schedules/{schedule_id}
Delete Run Schedule
DELETE/agents/{agent_id}/schedules/{schedule_id}
Pause Run Schedule
POST/agents/{agent_id}/schedules/{schedule_id}/pause
Resume Run Schedule
POST/agents/{agent_id}/schedules/{schedule_id}/resume
Trigger Run Schedule
POST/agents/{agent_id}/schedules/{schedule_id}/trigger
Skip Run Schedule Action
POST/agents/{agent_id}/schedules/{schedule_id}/skip
Unskip Run Schedule Action
POST/agents/{agent_id}/schedules/{schedule_id}/unskip
Get Run Schedule By Name
GET/agents/{agent_id}/schedules/name/{name}
Update Run Schedule By Name
PATCH/agents/{agent_id}/schedules/name/{name}
Delete Run Schedule By Name
DELETE/agents/{agent_id}/schedules/name/{name}
Pause Run Schedule By Name
POST/agents/{agent_id}/schedules/name/{name}/pause
Resume Run Schedule By Name
POST/agents/{agent_id}/schedules/name/{name}/resume
Trigger Run Schedule By Name
POST/agents/{agent_id}/schedules/name/{name}/trigger
ModelsExpand Collapse
ScheduleCreateResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
ScheduleListResponse object { run_schedules, total }

Response model for listing run schedules.

run_schedules: array of object { id, agent_id, initial_input, 20 more }

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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
total: number

The number of run schedules returned.

ScheduleRetrieveResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
ScheduleUpdateResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
SchedulePauseResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
ScheduleResumeResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
ScheduleTriggerResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
ScheduleSkipResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
ScheduleUnskipResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
ScheduleRetrieveByNameResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
ScheduleUpdateByNameResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
SchedulePauseByNameResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
ScheduleResumeByNameResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time
ScheduleTriggerByNameResponse object { 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: object { content, author, type }

The initial input.

content: string

The initial prompt delivered to the task.

author: optional MessageAuthor

The author attributed to the initial input.

One of the following:
"user"
"agent"
type: optional "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: optional string

When the schedule was created.

formatdate-time
creator_principal: optional object { account_id, principal_type, service_account_id, user_id }

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: optional string

Account/workspace id of the creator.

principal_type: optional string

e.g. ‘user’ or ‘service_account’.

service_account_id: optional string

Creator service-account id, if a service principal.

user_id: optional string

Creator user id, if a user principal.

cron_expression: optional string

Cron cadence, if cron-based.

description: optional string

Optional description.

end_at: optional string

Schedule deactivation time.

formatdate-time
interval_seconds: optional number

Interval cadence in seconds, if interval-based.

last_action_time: optional string

When the schedule last fired.

formatdate-time
live_data_available: optional boolean

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

next_action_times: optional array of string

Upcoming scheduled fire times.

num_actions_taken: optional number

Number of times the schedule has fired.

paused: optional boolean

Whether the schedule is paused.

skipped_action_times: optional array of string

Skipped one-off scheduled fire times.

start_at: optional string

Schedule activation time.

formatdate-time
state: optional "ACTIVE" or "PAUSED"

Live schedule state from Temporal.

One of the following:
"ACTIVE"
"PAUSED"
task_metadata: optional map[unknown]

Task metadata at fire time.

task_params: optional map[unknown]

Task params at fire time.

timezone: optional string

Timezone the cron expression is evaluated in.

updated_at: optional string

When the schedule was updated.

formatdate-time