# Agents ## Get Agent by ID **get** `/agents/{agent_id}` Get an agent by its unique ID. ### Path Parameters - `agent_id: string` ### Returns - `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) - `"sync"` - `"async"` - `"agentic"` - `created_at: string` The timestamp when the agent was created - `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 - `agent_input_type: optional "text" or "json"` The type of input the agent expects. - `"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 - `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. - `"Ready"` - `"Failed"` - `"Unknown"` - `"Deleted"` - `"Unhealthy"` - `"BuildOnly"` - `status_reason: optional string` The reason for the status of the action. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "acp_type": "sync", "created_at": "2019-12-27T18:11:19.117Z", "description": "description", "name": "name", "updated_at": "2019-12-27T18:11:19.117Z", "agent_input_type": "text", "production_deployment_id": "production_deployment_id", "registered_at": "2019-12-27T18:11:19.117Z", "registration_metadata": { "foo": "bar" }, "status": "Ready", "status_reason": "status_reason" } ``` ## Delete Agent by ID **delete** `/agents/{agent_id}` Delete an agent by its unique ID. ### Path Parameters - `agent_id: string` ### Returns - `DeleteResponse object { id, message }` - `id: string` - `message: string` ### Example ```http curl http://localhost:5003/agents/$AGENT_ID \ -X DELETE \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "message": "message" } ``` ## List Agents **get** `/agents` List all registered agents, optionally filtered by query parameters. ### Query Parameters - `agent_card_metadata: optional string` JSON-encoded object used to filter agents on `registration_metadata.agent_card.metadata` via JSONB containment. Example: {"permits_capable": true}. Only matches cards published through the direct registration path: registrations that carry a `deployment_id` write the card to the deployment record instead of `registration_metadata`, so those agents never match this filter. - `limit: optional number` Limit - `order_by: optional string` Field to order by - `order_direction: optional string` Order direction (asc or desc) - `page_number: optional number` Page number - `task_id: optional string` Task ID ### Returns - `id: string` The unique identifier of the agent. - `acp_type: AcpType` The type of the ACP Server (Either sync or async) - `"sync"` - `"async"` - `"agentic"` - `created_at: string` The timestamp when the agent was created - `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 - `agent_input_type: optional "text" or "json"` The type of input the agent expects. - `"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 - `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. - `"Ready"` - `"Failed"` - `"Unknown"` - `"Deleted"` - `"Unhealthy"` - `"BuildOnly"` - `status_reason: optional string` The reason for the status of the action. ### Example ```http curl http://localhost:5003/agents \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json [ { "id": "id", "acp_type": "sync", "created_at": "2019-12-27T18:11:19.117Z", "description": "description", "name": "name", "updated_at": "2019-12-27T18:11:19.117Z", "agent_input_type": "text", "production_deployment_id": "production_deployment_id", "registered_at": "2019-12-27T18:11:19.117Z", "registration_metadata": { "foo": "bar" }, "status": "Ready", "status_reason": "status_reason" } ] ``` ## Handle Agent RPC by ID **post** `/agents/{agent_id}/rpc` Handle JSON-RPC requests for an agent by its unique ID. ### Path Parameters - `agent_id: string` ### Body Parameters - `method: "event/send" or "task/create" or "message/send" or 2 more` - `"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 - `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 }` - `content: TaskMessageContent` The message that was sent to the agent - `TextContent object { author, content, attachments, 3 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"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. - `"markdown"` - `"plain"` - `"code"` - `style: optional MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type: optional "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent object { author, summary, content, 2 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent object { author, data, style, type }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent object { arguments, author, name, 3 more }` - `arguments: map[unknown]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent object { author, content, name, 4 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_response"` The type of the message, in this case `tool_response`. - `"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 - `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` - `number` - `string` - `jsonrpc: optional "2.0"` - `"2.0"` ### Returns - `AgentRpcResponse object { result, id, error, jsonrpc }` - `result: AgentRpcResult` The result of the agent RPC request - `array of TaskMessage` - `content: TaskMessageContent` The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user. - `TextContent object { author, content, attachments, 3 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"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. - `"markdown"` - `"plain"` - `"code"` - `style: optional MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type: optional "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent object { author, summary, content, 2 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent object { author, data, style, type }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent object { arguments, author, name, 3 more }` - `arguments: map[unknown]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent object { author, content, name, 4 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_response"` The type of the message, in this case `tool_response`. - `"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 - `streaming_status: optional "IN_PROGRESS" or "DONE"` - `"IN_PROGRESS"` - `"DONE"` - `updated_at: optional string` The timestamp when the message was last updated - `StreamTaskMessageStart object { content, index, parent_task_message, type }` Event for starting a streaming message - `content: TaskMessageContent` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `content: TaskMessageContent` The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user. - `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 - `streaming_status: optional "IN_PROGRESS" or "DONE"` - `updated_at: optional string` The timestamp when the message was last updated - `type: optional "start"` - `"start"` - `StreamTaskMessageDelta object { delta, index, parent_task_message, type }` Event for streaming chunks of content - `delta: optional TaskMessageDelta` Delta for text updates - `TextDelta object { text_delta, type }` Delta for text updates - `text_delta: optional string` - `type: optional "text"` - `"text"` - `DataDelta object { data_delta, type }` Delta for data updates - `data_delta: optional string` - `type: optional "data"` - `"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"` - `"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"` - `"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"` - `"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"` - `"reasoning_content"` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "delta"` - `"delta"` - `StreamTaskMessageFull object { content, index, parent_task_message, type }` Event for streaming the full content - `content: TaskMessageContent` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "full"` - `"full"` - `StreamTaskMessageDone object { index, parent_task_message, type }` Event for indicating the task is done - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "done"` - `"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` - `"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 - `created_at: optional string` The timestamp of the event - `id: optional number or string` - `number` - `string` - `error: optional unknown` - `jsonrpc: optional "2.0"` - `"2.0"` ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/rpc \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" \ -d '{ "method": "event/send", "params": {} }' ``` #### Response ```json { "result": [ { "content": { "author": "user", "content": "content", "attachments": [ { "file_id": "file_id", "name": "name", "size": 0, "type": "type" } ], "format": "markdown", "style": "static", "type": "text" }, "task_id": "task_id", "id": "id", "created_at": "2019-12-27T18:11:19.117Z", "streaming_status": "IN_PROGRESS", "updated_at": "2019-12-27T18:11:19.117Z" } ], "id": 0, "error": {}, "jsonrpc": "2.0" } ``` ## Get Agent by Name **get** `/agents/name/{agent_name}` Get an agent by its unique name. ### Path Parameters - `agent_name: string` ### Returns - `Agent object { id, acp_type, created_at, 9 more }` - `id: string` The unique identifier of the agent. - `acp_type: AcpType` The type of the ACP Server (Either sync or async) - `"sync"` - `"async"` - `"agentic"` - `created_at: string` The timestamp when the agent was created - `description: string` The description of the action. - `name: string` The unique name of the agent. - `updated_at: string` The timestamp when the agent was last updated - `agent_input_type: optional "text" or "json"` The type of input the agent expects. - `"text"` - `"json"` - `production_deployment_id: optional string` ID of the current production deployment. - `registered_at: optional string` The timestamp when the agent was last registered - `registration_metadata: optional map[unknown]` The metadata for the agent's registration. - `status: optional "Ready" or "Failed" or "Unknown" or 3 more` The status of the action, indicating if it's building, ready, failed, etc. - `"Ready"` - `"Failed"` - `"Unknown"` - `"Deleted"` - `"Unhealthy"` - `"BuildOnly"` - `status_reason: optional string` The reason for the status of the action. ### Example ```http curl http://localhost:5003/agents/name/$AGENT_NAME \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "acp_type": "sync", "created_at": "2019-12-27T18:11:19.117Z", "description": "description", "name": "name", "updated_at": "2019-12-27T18:11:19.117Z", "agent_input_type": "text", "production_deployment_id": "production_deployment_id", "registered_at": "2019-12-27T18:11:19.117Z", "registration_metadata": { "foo": "bar" }, "status": "Ready", "status_reason": "status_reason" } ``` ## Delete Agent by Name **delete** `/agents/name/{agent_name}` Delete an agent by its unique name. ### Path Parameters - `agent_name: string` ### Returns - `DeleteResponse object { id, message }` - `id: string` - `message: string` ### Example ```http curl http://localhost:5003/agents/name/$AGENT_NAME \ -X DELETE \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "message": "message" } ``` ## Handle Agent RPC by Name **post** `/agents/name/{agent_name}/rpc` Handle JSON-RPC requests for an agent by its unique name. ### Path Parameters - `agent_name: string` ### Body Parameters - `method: "event/send" or "task/create" or "message/send" or 2 more` - `"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 - `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 }` - `content: TaskMessageContent` The message that was sent to the agent - `TextContent object { author, content, attachments, 3 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"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. - `"markdown"` - `"plain"` - `"code"` - `style: optional MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type: optional "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent object { author, summary, content, 2 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent object { author, data, style, type }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent object { arguments, author, name, 3 more }` - `arguments: map[unknown]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent object { author, content, name, 4 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_response"` The type of the message, in this case `tool_response`. - `"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 - `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` - `number` - `string` - `jsonrpc: optional "2.0"` - `"2.0"` ### Returns - `AgentRpcResponse object { result, id, error, jsonrpc }` - `result: AgentRpcResult` The result of the agent RPC request - `array of TaskMessage` - `content: TaskMessageContent` The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user. - `TextContent object { author, content, attachments, 3 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"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. - `"markdown"` - `"plain"` - `"code"` - `style: optional MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type: optional "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent object { author, summary, content, 2 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent object { author, data, style, type }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent object { arguments, author, name, 3 more }` - `arguments: map[unknown]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent object { author, content, name, 4 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_response"` The type of the message, in this case `tool_response`. - `"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 - `streaming_status: optional "IN_PROGRESS" or "DONE"` - `"IN_PROGRESS"` - `"DONE"` - `updated_at: optional string` The timestamp when the message was last updated - `StreamTaskMessageStart object { content, index, parent_task_message, type }` Event for starting a streaming message - `content: TaskMessageContent` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `content: TaskMessageContent` The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user. - `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 - `streaming_status: optional "IN_PROGRESS" or "DONE"` - `updated_at: optional string` The timestamp when the message was last updated - `type: optional "start"` - `"start"` - `StreamTaskMessageDelta object { delta, index, parent_task_message, type }` Event for streaming chunks of content - `delta: optional TaskMessageDelta` Delta for text updates - `TextDelta object { text_delta, type }` Delta for text updates - `text_delta: optional string` - `type: optional "text"` - `"text"` - `DataDelta object { data_delta, type }` Delta for data updates - `data_delta: optional string` - `type: optional "data"` - `"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"` - `"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"` - `"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"` - `"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"` - `"reasoning_content"` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "delta"` - `"delta"` - `StreamTaskMessageFull object { content, index, parent_task_message, type }` Event for streaming the full content - `content: TaskMessageContent` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "full"` - `"full"` - `StreamTaskMessageDone object { index, parent_task_message, type }` Event for indicating the task is done - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "done"` - `"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` - `"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 - `created_at: optional string` The timestamp of the event - `id: optional number or string` - `number` - `string` - `error: optional unknown` - `jsonrpc: optional "2.0"` - `"2.0"` ### Example ```http curl http://localhost:5003/agents/name/$AGENT_NAME/rpc \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" \ -d '{ "method": "event/send", "params": {} }' ``` #### Response ```json { "result": [ { "content": { "author": "user", "content": "content", "attachments": [ { "file_id": "file_id", "name": "name", "size": 0, "type": "type" } ], "format": "markdown", "style": "static", "type": "text" }, "task_id": "task_id", "id": "id", "created_at": "2019-12-27T18:11:19.117Z", "streaming_status": "IN_PROGRESS", "updated_at": "2019-12-27T18:11:19.117Z" } ], "id": 0, "error": {}, "jsonrpc": "2.0" } ``` ## Register Build **post** `/agents/register-build` Register an agent at build time, before it is deployed, so it can be permissioned and shared prior to deploy. Idempotent by name. ### Body Parameters - `description: string` The description of the agent. - `name: string` The unique name of the agent. - `agent_input_type: optional "text" or "json"` The type of input the agent expects. - `"text"` - `"json"` - `registration_metadata: optional map[unknown]` The metadata for the agent's build registration. ### Returns - `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) - `"sync"` - `"async"` - `"agentic"` - `created_at: string` The timestamp when the agent was created - `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 - `agent_input_type: optional "text" or "json"` The type of input the agent expects. - `"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 - `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. - `"Ready"` - `"Failed"` - `"Unknown"` - `"Deleted"` - `"Unhealthy"` - `"BuildOnly"` - `status_reason: optional string` The reason for the status of the action. ### Example ```http curl http://localhost:5003/agents/register-build \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" \ -d '{ "description": "description", "name": "name" }' ``` #### Response ```json { "id": "id", "acp_type": "sync", "created_at": "2019-12-27T18:11:19.117Z", "description": "description", "name": "name", "updated_at": "2019-12-27T18:11:19.117Z", "agent_input_type": "text", "production_deployment_id": "production_deployment_id", "registered_at": "2019-12-27T18:11:19.117Z", "registration_metadata": { "foo": "bar" }, "status": "Ready", "status_reason": "status_reason" } ``` ## Domain Types ### Acp Type - `AcpType = "sync" or "async" or "agentic"` - `"sync"` - `"async"` - `"agentic"` ### Agent - `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) - `"sync"` - `"async"` - `"agentic"` - `created_at: string` The timestamp when the agent was created - `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 - `agent_input_type: optional "text" or "json"` The type of input the agent expects. - `"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 - `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. - `"Ready"` - `"Failed"` - `"Unknown"` - `"Deleted"` - `"Unhealthy"` - `"BuildOnly"` - `status_reason: optional string` The reason for the status of the action. ### Agent Rpc Request - `AgentRpcRequest object { method, params, id, jsonrpc }` - `method: "event/send" or "task/create" or "message/send" or 2 more` - `"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 - `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 }` - `content: TaskMessageContent` The message that was sent to the agent - `TextContent object { author, content, attachments, 3 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"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. - `"markdown"` - `"plain"` - `"code"` - `style: optional MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type: optional "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent object { author, summary, content, 2 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent object { author, data, style, type }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent object { arguments, author, name, 3 more }` - `arguments: map[unknown]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent object { author, content, name, 4 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_response"` The type of the message, in this case `tool_response`. - `"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 - `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` - `number` - `string` - `jsonrpc: optional "2.0"` - `"2.0"` ### Agent Rpc Response - `AgentRpcResponse object { result, id, error, jsonrpc }` - `result: AgentRpcResult` The result of the agent RPC request - `array of TaskMessage` - `content: TaskMessageContent` The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user. - `TextContent object { author, content, attachments, 3 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"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. - `"markdown"` - `"plain"` - `"code"` - `style: optional MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type: optional "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent object { author, summary, content, 2 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent object { author, data, style, type }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent object { arguments, author, name, 3 more }` - `arguments: map[unknown]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent object { author, content, name, 4 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_response"` The type of the message, in this case `tool_response`. - `"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 - `streaming_status: optional "IN_PROGRESS" or "DONE"` - `"IN_PROGRESS"` - `"DONE"` - `updated_at: optional string` The timestamp when the message was last updated - `StreamTaskMessageStart object { content, index, parent_task_message, type }` Event for starting a streaming message - `content: TaskMessageContent` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `content: TaskMessageContent` The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user. - `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 - `streaming_status: optional "IN_PROGRESS" or "DONE"` - `updated_at: optional string` The timestamp when the message was last updated - `type: optional "start"` - `"start"` - `StreamTaskMessageDelta object { delta, index, parent_task_message, type }` Event for streaming chunks of content - `delta: optional TaskMessageDelta` Delta for text updates - `TextDelta object { text_delta, type }` Delta for text updates - `text_delta: optional string` - `type: optional "text"` - `"text"` - `DataDelta object { data_delta, type }` Delta for data updates - `data_delta: optional string` - `type: optional "data"` - `"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"` - `"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"` - `"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"` - `"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"` - `"reasoning_content"` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "delta"` - `"delta"` - `StreamTaskMessageFull object { content, index, parent_task_message, type }` Event for streaming the full content - `content: TaskMessageContent` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "full"` - `"full"` - `StreamTaskMessageDone object { index, parent_task_message, type }` Event for indicating the task is done - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "done"` - `"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` - `"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 - `created_at: optional string` The timestamp of the event - `id: optional number or string` - `number` - `string` - `error: optional unknown` - `jsonrpc: optional "2.0"` - `"2.0"` ### Agent Rpc Result - `AgentRpcResult = array of TaskMessage 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 - `array of TaskMessage` - `content: TaskMessageContent` The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user. - `TextContent object { author, content, attachments, 3 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"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. - `"markdown"` - `"plain"` - `"code"` - `style: optional MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type: optional "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent object { author, summary, content, 2 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent object { author, data, style, type }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent object { arguments, author, name, 3 more }` - `arguments: map[unknown]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent object { author, content, name, 4 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_response"` The type of the message, in this case `tool_response`. - `"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 - `streaming_status: optional "IN_PROGRESS" or "DONE"` - `"IN_PROGRESS"` - `"DONE"` - `updated_at: optional string` The timestamp when the message was last updated - `StreamTaskMessageStart object { content, index, parent_task_message, type }` Event for starting a streaming message - `content: TaskMessageContent` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `content: TaskMessageContent` The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user. - `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 - `streaming_status: optional "IN_PROGRESS" or "DONE"` - `updated_at: optional string` The timestamp when the message was last updated - `type: optional "start"` - `"start"` - `StreamTaskMessageDelta object { delta, index, parent_task_message, type }` Event for streaming chunks of content - `delta: optional TaskMessageDelta` Delta for text updates - `TextDelta object { text_delta, type }` Delta for text updates - `text_delta: optional string` - `type: optional "text"` - `"text"` - `DataDelta object { data_delta, type }` Delta for data updates - `data_delta: optional string` - `type: optional "data"` - `"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"` - `"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"` - `"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"` - `"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"` - `"reasoning_content"` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "delta"` - `"delta"` - `StreamTaskMessageFull object { content, index, parent_task_message, type }` Event for streaming the full content - `content: TaskMessageContent` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "full"` - `"full"` - `StreamTaskMessageDone object { index, parent_task_message, type }` Event for indicating the task is done - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "done"` - `"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` - `"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 - `created_at: optional string` The timestamp of the event ### Data Delta - `DataDelta object { data_delta, type }` Delta for data updates - `data_delta: optional string` - `type: optional "data"` - `"data"` ### Reasoning Content Delta - `ReasoningContentDelta object { content_index, content_delta, type }` Delta for reasoning content updates - `content_index: number` - `content_delta: optional string` - `type: optional "reasoning_content"` - `"reasoning_content"` ### Reasoning Summary Delta - `ReasoningSummaryDelta object { summary_index, summary_delta, type }` Delta for reasoning summary updates - `summary_index: number` - `summary_delta: optional string` - `type: optional "reasoning_summary"` - `"reasoning_summary"` ### Task Message Content - `TaskMessageContent = TextContent or ReasoningContent or DataContent or 2 more` - `TextContent object { author, content, attachments, 3 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"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. - `"markdown"` - `"plain"` - `"code"` - `style: optional MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type: optional "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent object { author, summary, content, 2 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent object { author, data, style, type }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent object { arguments, author, name, 3 more }` - `arguments: map[unknown]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent object { author, content, name, 4 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_response"` The type of the message, in this case `tool_response`. - `"tool_response"` ### Task Message Delta - `TaskMessageDelta = TextDelta or DataDelta or ToolRequestDelta or 3 more` Delta for text updates - `TextDelta object { text_delta, type }` Delta for text updates - `text_delta: optional string` - `type: optional "text"` - `"text"` - `DataDelta object { data_delta, type }` Delta for data updates - `data_delta: optional string` - `type: optional "data"` - `"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"` - `"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"` - `"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"` - `"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"` - `"reasoning_content"` ### Task Message Update - `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 - `Start object { content, index, parent_task_message, type }` Event for starting a streaming message - `content: TaskMessageContent` - `TextContent object { author, content, attachments, 3 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"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. - `"markdown"` - `"plain"` - `"code"` - `style: optional MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type: optional "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent object { author, summary, content, 2 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent object { author, data, style, type }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent object { arguments, author, name, 3 more }` - `arguments: map[unknown]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent object { author, content, name, 4 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_response"` The type of the message, in this case `tool_response`. - `"tool_response"` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `content: TaskMessageContent` The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user. - `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 - `streaming_status: optional "IN_PROGRESS" or "DONE"` - `"IN_PROGRESS"` - `"DONE"` - `updated_at: optional string` The timestamp when the message was last updated - `type: optional "start"` - `"start"` - `Delta object { delta, index, parent_task_message, type }` Event for streaming chunks of content - `delta: optional TaskMessageDelta` Delta for text updates - `TextDelta object { text_delta, type }` Delta for text updates - `text_delta: optional string` - `type: optional "text"` - `"text"` - `DataDelta object { data_delta, type }` Delta for data updates - `data_delta: optional string` - `type: optional "data"` - `"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"` - `"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"` - `"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"` - `"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"` - `"reasoning_content"` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "delta"` - `"delta"` - `Full object { content, index, parent_task_message, type }` Event for streaming the full content - `content: TaskMessageContent` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "full"` - `"full"` - `Done object { index, parent_task_message, type }` Event for indicating the task is done - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "done"` - `"done"` ### Text Delta - `TextDelta object { text_delta, type }` Delta for text updates - `text_delta: optional string` - `type: optional "text"` - `"text"` ### Tool Request Delta - `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"` - `"tool_request"` ### Tool Response Delta - `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"` - `"tool_response"` ### Agent List Response - `AgentListResponse = array of Agent` - `id: string` The unique identifier of the agent. - `acp_type: AcpType` The type of the ACP Server (Either sync or async) - `"sync"` - `"async"` - `"agentic"` - `created_at: string` The timestamp when the agent was created - `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 - `agent_input_type: optional "text" or "json"` The type of input the agent expects. - `"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 - `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. - `"Ready"` - `"Failed"` - `"Unknown"` - `"Deleted"` - `"Unhealthy"` - `"BuildOnly"` - `status_reason: optional string` The reason for the status of the action. # Deployments ## Create Deployment **post** `/agents/{agent_id}/deployments` Create a new deployment record in PENDING status. ### Path Parameters - `agent_id: string` ### Body Parameters - `docker_image: string` Full Docker image URI. - `helm_release_name: optional string` Helm release name. - `registration_metadata: optional map[unknown]` Git/build metadata (commit_hash, branch_name, author_name, author_email, build_timestamp). - `sgp_deploy_id: optional string` SGP deployment ID. ### Returns - `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. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: optional string` ACP URL set when agent registers. - `created_at: optional string` When the deployment was created. - `expires_at: optional string` When marked for cleanup. - `helm_release_name: optional string` Helm release name for cleanup. - `promoted_at: optional string` When promoted to production. - `registration_metadata: optional map[unknown]` Git/build metadata from the agent pod. - `sgp_deploy_id: optional string` Correlates to SGP's agentex_deploys.id. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/deployments \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" \ -d '{ "docker_image": "docker_image" }' ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "docker_image": "docker_image", "is_production": true, "status": "Pending", "acp_url": "acp_url", "created_at": "2019-12-27T18:11:19.117Z", "expires_at": "2019-12-27T18:11:19.117Z", "helm_release_name": "helm_release_name", "promoted_at": "2019-12-27T18:11:19.117Z", "registration_metadata": { "foo": "bar" }, "sgp_deploy_id": "sgp_deploy_id" } ``` ## List Deployments **get** `/agents/{agent_id}/deployments` List deployments for an agent, newest first. ### Path Parameters - `agent_id: string` ### Query Parameters - `limit: optional number` Limit - `order_by: optional string` Field to order by - `order_direction: optional string` Order direction (asc or desc) - `page_number: optional number` Page number ### Returns - `id: string` The unique identifier of the deployment. - `agent_id: string` The agent this deployment belongs to. - `docker_image: string` Full Docker image URI. - `is_production: boolean` Whether this is the production deployment. - `status: "Pending" or "Ready" or "Failed"` Current deployment status. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: optional string` ACP URL set when agent registers. - `created_at: optional string` When the deployment was created. - `expires_at: optional string` When marked for cleanup. - `helm_release_name: optional string` Helm release name for cleanup. - `promoted_at: optional string` When promoted to production. - `registration_metadata: optional map[unknown]` Git/build metadata from the agent pod. - `sgp_deploy_id: optional string` Correlates to SGP's agentex_deploys.id. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/deployments \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json [ { "id": "id", "agent_id": "agent_id", "docker_image": "docker_image", "is_production": true, "status": "Pending", "acp_url": "acp_url", "created_at": "2019-12-27T18:11:19.117Z", "expires_at": "2019-12-27T18:11:19.117Z", "helm_release_name": "helm_release_name", "promoted_at": "2019-12-27T18:11:19.117Z", "registration_metadata": { "foo": "bar" }, "sgp_deploy_id": "sgp_deploy_id" } ] ``` ## Get Deployment **get** `/agents/{agent_id}/deployments/{deployment_id}` Get a specific deployment by ID. ### Path Parameters - `agent_id: string` - `deployment_id: string` ### Returns - `id: string` The unique identifier of the deployment. - `agent_id: string` The agent this deployment belongs to. - `docker_image: string` Full Docker image URI. - `is_production: boolean` Whether this is the production deployment. - `status: "Pending" or "Ready" or "Failed"` Current deployment status. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: optional string` ACP URL set when agent registers. - `created_at: optional string` When the deployment was created. - `expires_at: optional string` When marked for cleanup. - `helm_release_name: optional string` Helm release name for cleanup. - `promoted_at: optional string` When promoted to production. - `registration_metadata: optional map[unknown]` Git/build metadata from the agent pod. - `sgp_deploy_id: optional string` Correlates to SGP's agentex_deploys.id. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/deployments/$DEPLOYMENT_ID \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "docker_image": "docker_image", "is_production": true, "status": "Pending", "acp_url": "acp_url", "created_at": "2019-12-27T18:11:19.117Z", "expires_at": "2019-12-27T18:11:19.117Z", "helm_release_name": "helm_release_name", "promoted_at": "2019-12-27T18:11:19.117Z", "registration_metadata": { "foo": "bar" }, "sgp_deploy_id": "sgp_deploy_id" } ``` ## Delete Deployment **delete** `/agents/{agent_id}/deployments/{deployment_id}` Delete a non-production deployment. ### Path Parameters - `agent_id: string` - `deployment_id: string` ### Returns - `DeleteResponse object { id, message }` - `id: string` - `message: string` ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/deployments/$DEPLOYMENT_ID \ -X DELETE \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "message": "message" } ``` ## Promote Deployment **post** `/agents/{agent_id}/deployments/{deployment_id}/promote` Promote a deployment to production with atomic cutover. ### Path Parameters - `agent_id: string` - `deployment_id: string` ### Returns - `id: string` The unique identifier of the deployment. - `agent_id: string` The agent this deployment belongs to. - `docker_image: string` Full Docker image URI. - `is_production: boolean` Whether this is the production deployment. - `status: "Pending" or "Ready" or "Failed"` Current deployment status. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: optional string` ACP URL set when agent registers. - `created_at: optional string` When the deployment was created. - `expires_at: optional string` When marked for cleanup. - `helm_release_name: optional string` Helm release name for cleanup. - `promoted_at: optional string` When promoted to production. - `registration_metadata: optional map[unknown]` Git/build metadata from the agent pod. - `sgp_deploy_id: optional string` Correlates to SGP's agentex_deploys.id. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/deployments/$DEPLOYMENT_ID/promote \ -X POST \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "docker_image": "docker_image", "is_production": true, "status": "Pending", "acp_url": "acp_url", "created_at": "2019-12-27T18:11:19.117Z", "expires_at": "2019-12-27T18:11:19.117Z", "helm_release_name": "helm_release_name", "promoted_at": "2019-12-27T18:11:19.117Z", "registration_metadata": { "foo": "bar" }, "sgp_deploy_id": "sgp_deploy_id" } ``` ## Preview RPC **post** `/agents/{agent_id}/deployments/{deployment_id}/rpc` Send an RPC request to a specific deployment (for preview testing). ### Path Parameters - `agent_id: string` - `deployment_id: string` ### Body Parameters - `method: "event/send" or "task/create" or "message/send" or 2 more` - `"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 - `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 }` - `content: TaskMessageContent` The message that was sent to the agent - `TextContent object { author, content, attachments, 3 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"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. - `"markdown"` - `"plain"` - `"code"` - `style: optional MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type: optional "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent object { author, summary, content, 2 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent object { author, data, style, type }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent object { arguments, author, name, 3 more }` - `arguments: map[unknown]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent object { author, content, name, 4 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_response"` The type of the message, in this case `tool_response`. - `"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 - `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` - `number` - `string` - `jsonrpc: optional "2.0"` - `"2.0"` ### Returns - `AgentRpcResponse object { result, id, error, jsonrpc }` - `result: AgentRpcResult` The result of the agent RPC request - `array of TaskMessage` - `content: TaskMessageContent` The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user. - `TextContent object { author, content, attachments, 3 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"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. - `"markdown"` - `"plain"` - `"code"` - `style: optional MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type: optional "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent object { author, summary, content, 2 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent object { author, data, style, type }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent object { arguments, author, name, 3 more }` - `arguments: map[unknown]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent object { author, content, name, 4 more }` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `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. - `type: optional "tool_response"` The type of the message, in this case `tool_response`. - `"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 - `streaming_status: optional "IN_PROGRESS" or "DONE"` - `"IN_PROGRESS"` - `"DONE"` - `updated_at: optional string` The timestamp when the message was last updated - `StreamTaskMessageStart object { content, index, parent_task_message, type }` Event for starting a streaming message - `content: TaskMessageContent` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `content: TaskMessageContent` The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user. - `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 - `streaming_status: optional "IN_PROGRESS" or "DONE"` - `updated_at: optional string` The timestamp when the message was last updated - `type: optional "start"` - `"start"` - `StreamTaskMessageDelta object { delta, index, parent_task_message, type }` Event for streaming chunks of content - `delta: optional TaskMessageDelta` Delta for text updates - `TextDelta object { text_delta, type }` Delta for text updates - `text_delta: optional string` - `type: optional "text"` - `"text"` - `DataDelta object { data_delta, type }` Delta for data updates - `data_delta: optional string` - `type: optional "data"` - `"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"` - `"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"` - `"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"` - `"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"` - `"reasoning_content"` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "delta"` - `"delta"` - `StreamTaskMessageFull object { content, index, parent_task_message, type }` Event for streaming the full content - `content: TaskMessageContent` - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "full"` - `"full"` - `StreamTaskMessageDone object { index, parent_task_message, type }` Event for indicating the task is done - `index: optional number` - `parent_task_message: optional TaskMessage` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type: optional "done"` - `"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` - `"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 - `created_at: optional string` The timestamp of the event - `id: optional number or string` - `number` - `string` - `error: optional unknown` - `jsonrpc: optional "2.0"` - `"2.0"` ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/deployments/$DEPLOYMENT_ID/rpc \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" \ -d '{ "method": "event/send", "params": {} }' ``` #### Response ```json { "result": [ { "content": { "author": "user", "content": "content", "attachments": [ { "file_id": "file_id", "name": "name", "size": 0, "type": "type" } ], "format": "markdown", "style": "static", "type": "text" }, "task_id": "task_id", "id": "id", "created_at": "2019-12-27T18:11:19.117Z", "streaming_status": "IN_PROGRESS", "updated_at": "2019-12-27T18:11:19.117Z" } ], "id": 0, "error": {}, "jsonrpc": "2.0" } ``` ## Domain Types ### Deployment Create Response - `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. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: optional string` ACP URL set when agent registers. - `created_at: optional string` When the deployment was created. - `expires_at: optional string` When marked for cleanup. - `helm_release_name: optional string` Helm release name for cleanup. - `promoted_at: optional string` When promoted to production. - `registration_metadata: optional map[unknown]` Git/build metadata from the agent pod. - `sgp_deploy_id: optional string` Correlates to SGP's agentex_deploys.id. ### Deployment List Response - `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. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: optional string` ACP URL set when agent registers. - `created_at: optional string` When the deployment was created. - `expires_at: optional string` When marked for cleanup. - `helm_release_name: optional string` Helm release name for cleanup. - `promoted_at: optional string` When promoted to production. - `registration_metadata: optional map[unknown]` Git/build metadata from the agent pod. - `sgp_deploy_id: optional string` Correlates to SGP's agentex_deploys.id. ### Deployment Retrieve Response - `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. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: optional string` ACP URL set when agent registers. - `created_at: optional string` When the deployment was created. - `expires_at: optional string` When marked for cleanup. - `helm_release_name: optional string` Helm release name for cleanup. - `promoted_at: optional string` When promoted to production. - `registration_metadata: optional map[unknown]` Git/build metadata from the agent pod. - `sgp_deploy_id: optional string` Correlates to SGP's agentex_deploys.id. ### Deployment Promote Response - `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. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: optional string` ACP URL set when agent registers. - `created_at: optional string` When the deployment was created. - `expires_at: optional string` When marked for cleanup. - `helm_release_name: optional string` Helm release name for cleanup. - `promoted_at: optional string` When promoted to production. - `registration_metadata: optional map[unknown]` Git/build metadata from the agent pod. - `sgp_deploy_id: optional string` Correlates to SGP's agentex_deploys.id. # Schedules ## Create Run Schedule **post** `/agents/{agent_id}/schedules` Create a recurring schedule that starts a fresh agent run on each fire. ### Path Parameters - `agent_id: string` ### Body Parameters - `initial_input: object { content, author, type }` The first input delivered to each created task. - `content: string` The initial prompt delivered to the task. - `author: optional MessageAuthor` The author attributed to the initial input. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `name: string` Human-readable name, unique among active schedules for the agent. - `cron_expression: optional string` Cron expression for the cadence (e.g. '0 17 * * MON-FRI'). Mutually exclusive with interval_seconds. - `description: optional string` Optional description of what this schedule does. - `end_at: optional string` When the schedule should stop being active. - `interval_seconds: optional number` Interval cadence in seconds. Mutually exclusive with cron_expression. - `paused: optional boolean` Whether to create the schedule in a paused state. - `start_at: optional string` When the schedule should start being active. - `task_metadata: optional map[unknown]` Metadata copied onto each created task at fire time. - `task_params: optional map[unknown]` Resolved config forwarded as task `params` at fire time. - `timezone: optional string` IANA timezone the cron expression is evaluated in (e.g. 'America/New_York'). ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" \ -d '{ "initial_input": { "content": "content" }, "name": "name" }' ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## List Run Schedules **get** `/agents/{agent_id}/schedules` List run schedules for an agent. ### Path Parameters - `agent_id: string` ### Query Parameters - `include_live: optional boolean` Include live Temporal state and upcoming action times. - `limit: optional number` ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. - `total: number` The number of run schedules returned. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "run_schedules": [ { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ], "total": 0 } ``` ## Get Run Schedule **get** `/agents/{agent_id}/schedules/{schedule_id}` Get a run schedule by its id. ### Path Parameters - `agent_id: string` - `schedule_id: string` ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/$SCHEDULE_ID \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Update Run Schedule **patch** `/agents/{agent_id}/schedules/{schedule_id}` Partially update a run schedule's definition (cadence, window, input, etc.). ### Path Parameters - `agent_id: string` - `schedule_id: string` ### Body Parameters - `cron_expression: optional string` New cron cadence. Mutually exclusive with interval_seconds. - `description: optional string` Optional description of what this schedule does. - `end_at: optional string` When the schedule should stop being active. - `initial_input: optional object { content, author, type }` The first input delivered to each freshly created scheduled task. - `content: string` The initial prompt delivered to the task. - `author: optional MessageAuthor` The author attributed to the initial input. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `interval_seconds: optional number` New interval cadence in seconds. Mutually exclusive with cron_expression. - `name: optional string` Human-readable name, unique among active schedules for the agent. - `paused: optional boolean` Pause/resume the schedule as part of the update. - `start_at: optional string` When the schedule should start being active. - `task_metadata: optional map[unknown]` Metadata copied onto each created task at fire time. - `task_params: optional map[unknown]` Resolved config forwarded as task `params` at fire time. - `timezone: optional string` IANA timezone the cron expression is evaluated in. ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/$SCHEDULE_ID \ -X PATCH \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" \ -d '{}' ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Delete Run Schedule **delete** `/agents/{agent_id}/schedules/{schedule_id}` Delete a run schedule permanently. ### Path Parameters - `agent_id: string` - `schedule_id: string` ### Returns - `DeleteResponse object { id, message }` - `id: string` - `message: string` ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/$SCHEDULE_ID \ -X DELETE \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "message": "message" } ``` ## Pause Run Schedule **post** `/agents/{agent_id}/schedules/{schedule_id}/pause` Pause a run schedule so it stops firing. ### Path Parameters - `agent_id: string` - `schedule_id: string` ### Body Parameters - `note: optional string` Optional note explaining the pause. ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/$SCHEDULE_ID/pause \ -X POST \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Resume Run Schedule **post** `/agents/{agent_id}/schedules/{schedule_id}/resume` Resume a paused run schedule so it fires again. ### Path Parameters - `agent_id: string` - `schedule_id: string` ### Body Parameters - `note: optional string` Optional note explaining the resume. ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/$SCHEDULE_ID/resume \ -X POST \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Trigger Run Schedule **post** `/agents/{agent_id}/schedules/{schedule_id}/trigger` Trigger an immediate, out-of-band run of the schedule (in addition to its cadence). ### Path Parameters - `agent_id: string` - `schedule_id: string` ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/$SCHEDULE_ID/trigger \ -X POST \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Skip Run Schedule Action **post** `/agents/{agent_id}/schedules/{schedule_id}/skip` Skip a recurring fire of the schedule. ### Path Parameters - `agent_id: string` - `schedule_id: string` ### Body Parameters - `scheduled_time: string` Specific scheduled fire time to skip. ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/$SCHEDULE_ID/skip \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" \ -d '{ "scheduled_time": "2019-12-27T18:11:19.117Z" }' ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Unskip Run Schedule Action **post** `/agents/{agent_id}/schedules/{schedule_id}/unskip` Remove a skip for a recurring fire of the schedule. ### Path Parameters - `agent_id: string` - `schedule_id: string` ### Body Parameters - `scheduled_time: string` Specific scheduled fire time to unskip. ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/$SCHEDULE_ID/unskip \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" \ -d '{ "scheduled_time": "2019-12-27T18:11:19.117Z" }' ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Get Run Schedule By Name **get** `/agents/{agent_id}/schedules/name/{name}` Get a run schedule by its active name. ### Path Parameters - `agent_id: string` - `name: string` ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/name/$NAME \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Update Run Schedule By Name **patch** `/agents/{agent_id}/schedules/name/{name}` Partially update a run schedule's definition by its active name. ### Path Parameters - `agent_id: string` - `name: string` ### Body Parameters - `cron_expression: optional string` New cron cadence. Mutually exclusive with interval_seconds. - `description: optional string` Optional description of what this schedule does. - `end_at: optional string` When the schedule should stop being active. - `initial_input: optional object { content, author, type }` The first input delivered to each freshly created scheduled task. - `content: string` The initial prompt delivered to the task. - `author: optional MessageAuthor` The author attributed to the initial input. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `interval_seconds: optional number` New interval cadence in seconds. Mutually exclusive with cron_expression. - `name: optional string` Human-readable name, unique among active schedules for the agent. - `paused: optional boolean` Pause/resume the schedule as part of the update. - `start_at: optional string` When the schedule should start being active. - `task_metadata: optional map[unknown]` Metadata copied onto each created task at fire time. - `task_params: optional map[unknown]` Resolved config forwarded as task `params` at fire time. - `timezone: optional string` IANA timezone the cron expression is evaluated in. ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/name/$NAME \ -X PATCH \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" \ -d '{}' ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Delete Run Schedule By Name **delete** `/agents/{agent_id}/schedules/name/{name}` Delete a run schedule by its active name. ### Path Parameters - `agent_id: string` - `name: string` ### Returns - `DeleteResponse object { id, message }` - `id: string` - `message: string` ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/name/$NAME \ -X DELETE \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "message": "message" } ``` ## Pause Run Schedule By Name **post** `/agents/{agent_id}/schedules/name/{name}/pause` Pause a run schedule by its active name. ### Path Parameters - `agent_id: string` - `name: string` ### Body Parameters - `note: optional string` Optional note explaining the pause. ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/name/$NAME/pause \ -X POST \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Resume Run Schedule By Name **post** `/agents/{agent_id}/schedules/name/{name}/resume` Resume a paused run schedule by its active name. ### Path Parameters - `agent_id: string` - `name: string` ### Body Parameters - `note: optional string` Optional note explaining the resume. ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/name/$NAME/resume \ -X POST \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Trigger Run Schedule By Name **post** `/agents/{agent_id}/schedules/name/{name}/trigger` Trigger an immediate, out-of-band run of the schedule by its active name. ### Path Parameters - `agent_id: string` - `name: string` ### Returns - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Example ```http curl http://localhost:5003/agents/$AGENT_ID/schedules/name/$NAME/trigger \ -X POST \ -H "Authorization: Bearer $AGENTEX_SDK_API_KEY" ``` #### Response ```json { "id": "id", "agent_id": "agent_id", "initial_input": { "content": "content", "author": "user", "type": "text" }, "initial_input_method": "initial_input_method", "name": "name", "created_at": "2019-12-27T18:11:19.117Z", "creator_principal": { "account_id": "account_id", "principal_type": "principal_type", "service_account_id": "service_account_id", "user_id": "user_id" }, "cron_expression": "cron_expression", "description": "description", "end_at": "2019-12-27T18:11:19.117Z", "interval_seconds": 0, "last_action_time": "2019-12-27T18:11:19.117Z", "live_data_available": true, "next_action_times": [ "2019-12-27T18:11:19.117Z" ], "num_actions_taken": 0, "paused": true, "skipped_action_times": [ "2019-12-27T18:11:19.117Z" ], "start_at": "2019-12-27T18:11:19.117Z", "state": "ACTIVE", "task_metadata": { "foo": "bar" }, "task_params": { "foo": "bar" }, "timezone": "timezone", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Domain Types ### Schedule Create Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Schedule List Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. - `total: number` The number of run schedules returned. ### Schedule Retrieve Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Schedule Update Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Schedule Pause Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Schedule Resume Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Schedule Trigger Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Schedule Skip Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Schedule Unskip Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Schedule Retrieve By Name Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Schedule Update By Name Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Schedule Pause By Name Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Schedule Resume By Name Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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. ### Schedule Trigger By Name Response - `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. - `"user"` - `"agent"` - `type: optional "text"` Input content type. - `"text"` - `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. - `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. - `interval_seconds: optional number` Interval cadence in seconds, if interval-based. - `last_action_time: optional string` When the schedule last fired. - `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. - `state: optional "ACTIVE" or "PAUSED"` Live schedule state from Temporal. - `"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.