## Handle Agent RPC by ID `client.agents.rpc(stringagentID, AgentRpcParamsbody, RequestOptionsoptions?): AgentRpcResponse` **post** `/agents/{agent_id}/rpc` Handle JSON-RPC requests for an agent by its unique ID. ### Parameters - `agentID: string` - `body: AgentRpcParams` - `method: "event/send" | "task/create" | "message/send" | 2 more` - `"event/send"` - `"task/create"` - `"message/send"` - `"task/cancel"` - `"task/interrupt"` - `params: CreateTaskRequest | CancelTaskRequest | InterruptTaskRequest | 2 more` The parameters for the agent RPC request - `CreateTaskRequest` - `name?: string | null` Optional human-readable name for the task. When set it must be globally unique. task/create is get-or-create by name: reusing an existing name returns the existing task (with its prior history) instead of creating a new one, so omit name (or make it unique, e.g. by appending a UUID) whenever each call should produce a fresh task. - `params?: Record | null` The parameters for the task. On a get-or-create by name, providing params overwrites the existing task's params (it is not a pure read). - `task_metadata?: Record | null` Caller-provided metadata to persist on the task row. Only applied at task creation; ignored if a task with this name already exists. Forwarded to the agent inside the ACP payload for backward compatibility. - `CancelTaskRequest` - `task_id?: string | null` The ID of the task to cancel. Either this or task_name must be provided. - `task_name?: string | null` The name of the task to cancel. Either this or task_id must be provided. - `InterruptTaskRequest` - `task_id?: string | null` The ID of the task to interrupt. Either this or task_name must be provided. - `task_name?: string | null` The name of the task to interrupt. Either this or task_id must be provided. - `SendMessageRequest` - `content: TaskMessageContent` The message that was sent to the agent - `TextContent` - `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?: Array | null` Optional list of file attachments with structured metadata. - `file_id: string` The unique ID of the attached file - `name: string` The name of the file - `size: number` The size of the file in bytes - `type: string` The MIME type or content type of the file - `format?: TextFormat` The format of the message. This is used by the client to determine how to display the message. - `"markdown"` - `"plain"` - `"code"` - `style?: MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type?: "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: Array` A list of short reasoning summaries - `content?: Array | null` The reasoning content or chain-of-thought text - `style?: MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `type?: "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Record` The contents of the data message. - `style?: MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `type?: "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent` - `arguments: Record` 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?: MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `type?: "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent` - `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?: boolean | null` Whether the tool call resulted in an error. `None` when the harness does not report a status. - `style?: MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `type?: "tool_response"` The type of the message, in this case `tool_response`. - `"tool_response"` - `stream?: boolean` Whether to stream the response message back to the client - `task_id?: string | null` The ID of the task that the message was sent to - `task_name?: string | null` The name of the task that the message was sent to - `task_params?: Record | null` The parameters for the task (only used when creating new tasks) - `SendEventRequest` - `content?: TaskMessageContent | null` The content to send to the event - `task_id?: string | null` The ID of the task that the event was sent to - `task_name?: string | null` The name of the task that the event was sent to - `id?: number | string | null` - `number` - `string` - `jsonrpc?: "2.0"` - `"2.0"` ### Returns - `AgentRpcResponse` - `result: AgentRpcResult | null` The result of the agent RPC request - `Array` - `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` - `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?: Array | null` Optional list of file attachments with structured metadata. - `file_id: string` The unique ID of the attached file - `name: string` The name of the file - `size: number` The size of the file in bytes - `type: string` The MIME type or content type of the file - `format?: TextFormat` The format of the message. This is used by the client to determine how to display the message. - `"markdown"` - `"plain"` - `"code"` - `style?: MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `"static"` - `"active"` - `type?: "text"` The type of the message, in this case `text`. - `"text"` - `ReasoningContent` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: Array` A list of short reasoning summaries - `content?: Array | null` The reasoning content or chain-of-thought text - `style?: MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `type?: "reasoning"` The type of the message, in this case `reasoning`. - `"reasoning"` - `DataContent` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Record` The contents of the data message. - `style?: MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `type?: "data"` The type of the message, in this case `data`. - `"data"` - `ToolRequestContent` - `arguments: Record` 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?: MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `type?: "tool_request"` The type of the message, in this case `tool_request`. - `"tool_request"` - `ToolResponseContent` - `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?: boolean | null` Whether the tool call resulted in an error. `None` when the harness does not report a status. - `style?: MessageStyle` The style of the message. This is used by the client to determine how to display the message. - `type?: "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?: string | null` The task message's unique id - `created_at?: string | null` The timestamp when the message was created - `streaming_status?: "IN_PROGRESS" | "DONE" | null` - `"IN_PROGRESS"` - `"DONE"` - `updated_at?: string | null` The timestamp when the message was last updated - `StreamTaskMessageStart` Event for starting a streaming message - `content: TaskMessageContent` - `index?: number | null` - `parent_task_message?: TaskMessage | null` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `content: TaskMessageContent` The content of the message. This content is not OpenAI compatible. These are messages that are meant to be displayed to the user. - `task_id: string` ID of the task this message belongs to - `id?: string | null` The task message's unique id - `created_at?: string | null` The timestamp when the message was created - `streaming_status?: "IN_PROGRESS" | "DONE" | null` - `updated_at?: string | null` The timestamp when the message was last updated - `type?: "start"` - `"start"` - `StreamTaskMessageDelta` Event for streaming chunks of content - `delta?: TaskMessageDelta | null` Delta for text updates - `TextDelta` Delta for text updates - `text_delta?: string | null` - `type?: "text"` - `"text"` - `DataDelta` Delta for data updates - `data_delta?: string | null` - `type?: "data"` - `"data"` - `ToolRequestDelta` Delta for tool request updates - `name: string` - `tool_call_id: string` - `arguments_delta?: string | null` - `type?: "tool_request"` - `"tool_request"` - `ToolResponseDelta` Delta for tool response updates - `name: string` - `tool_call_id: string` - `content_delta?: string | null` - `type?: "tool_response"` - `"tool_response"` - `ReasoningSummaryDelta` Delta for reasoning summary updates - `summary_index: number` - `summary_delta?: string | null` - `type?: "reasoning_summary"` - `"reasoning_summary"` - `ReasoningContentDelta` Delta for reasoning content updates - `content_index: number` - `content_delta?: string | null` - `type?: "reasoning_content"` - `"reasoning_content"` - `index?: number | null` - `parent_task_message?: TaskMessage | null` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type?: "delta"` - `"delta"` - `StreamTaskMessageFull` Event for streaming the full content - `content: TaskMessageContent` - `index?: number | null` - `parent_task_message?: TaskMessage | null` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type?: "full"` - `"full"` - `StreamTaskMessageDone` Event for indicating the task is done - `index?: number | null` - `parent_task_message?: TaskMessage | null` Represents a message in the agent system. This entity is used to store messages in MongoDB, with each message associated with a specific task. - `type?: "done"` - `"done"` - `Task` - `id: string` - `cleaned_at?: string | null` - `created_at?: string | null` - `name?: string | null` - `params?: Record | null` - `status?: "CANCELED" | "COMPLETED" | "FAILED" | 5 more | null` - `"CANCELED"` - `"COMPLETED"` - `"FAILED"` - `"RUNNING"` - `"INTERRUPTED"` - `"TERMINATED"` - `"TIMED_OUT"` - `"DELETED"` - `status_reason?: string | null` - `task_metadata?: Record | null` - `updated_at?: string | null` - `Event` - `id: string` The UUID of the event - `agent_id: string` The UUID of the agent that the event belongs to - `sequence_id: number` The sequence ID of the event - `task_id: string` The UUID of the task that the event belongs to - `content?: TaskMessageContent | null` The content of the event - `created_at?: string | null` The timestamp of the event - `id?: number | string | null` - `number` - `string` - `error?: unknown` - `jsonrpc?: "2.0"` - `"2.0"` ### Example ```typescript import Agentex from 'agentex'; const client = new Agentex({ apiKey: process.env['AGENTEX_SDK_API_KEY'], // This is the default and can be omitted }); const agentRpcResponse = await client.agents.rpc('agent_id', { method: 'event/send', params: {}, }); console.log(agentRpcResponse.id); ``` #### 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" } ```