# Agents ## Get Agent by ID `agents.retrieve(stragent_id) -> Agent` **get** `/agents/{agent_id}` Get an agent by its unique ID. ### Parameters - `agent_id: str` ### Returns - `class Agent: …` - `id: str` The unique identifier of the agent. - `acp_type: AcpType` The type of the ACP Server (Either sync or async) - `"sync"` - `"async"` - `"agentic"` - `created_at: datetime` The timestamp when the agent was created - `description: str` The description of the action. - `name: str` The unique name of the agent. - `updated_at: datetime` The timestamp when the agent was last updated - `agent_input_type: Optional[Literal["text", "json"]]` The type of input the agent expects. - `"text"` - `"json"` - `production_deployment_id: Optional[str]` ID of the current production deployment. - `registered_at: Optional[datetime]` The timestamp when the agent was last registered - `registration_metadata: Optional[Dict[str, object]]` The metadata for the agent's registration. - `status: Optional[Literal["Ready", "Failed", "Unknown", 3 more]]` The status of the action, indicating if it's building, ready, failed, etc. - `"Ready"` - `"Failed"` - `"Unknown"` - `"Deleted"` - `"Unhealthy"` - `"BuildOnly"` - `status_reason: Optional[str]` The reason for the status of the action. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) agent = client.agents.retrieve( "agent_id", ) print(agent.id) ``` #### 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 `agents.delete(stragent_id) -> DeleteResponse` **delete** `/agents/{agent_id}` Delete an agent by its unique ID. ### Parameters - `agent_id: str` ### Returns - `class DeleteResponse: …` - `id: str` - `message: str` ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) delete_response = client.agents.delete( "agent_id", ) print(delete_response.id) ``` #### Response ```json { "id": "id", "message": "message" } ``` ## List Agents `agents.list(AgentListParams**kwargs) -> AgentListResponse` **get** `/agents` List all registered agents, optionally filtered by query parameters. ### Parameters - `agent_card_metadata: Optional[str]` 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[int]` Limit - `order_by: Optional[str]` Field to order by - `order_direction: Optional[str]` Order direction (asc or desc) - `page_number: Optional[int]` Page number - `task_id: Optional[str]` Task ID ### Returns - `List[Agent]` - `id: str` The unique identifier of the agent. - `acp_type: AcpType` The type of the ACP Server (Either sync or async) - `"sync"` - `"async"` - `"agentic"` - `created_at: datetime` The timestamp when the agent was created - `description: str` The description of the action. - `name: str` The unique name of the agent. - `updated_at: datetime` The timestamp when the agent was last updated - `agent_input_type: Optional[Literal["text", "json"]]` The type of input the agent expects. - `"text"` - `"json"` - `production_deployment_id: Optional[str]` ID of the current production deployment. - `registered_at: Optional[datetime]` The timestamp when the agent was last registered - `registration_metadata: Optional[Dict[str, object]]` The metadata for the agent's registration. - `status: Optional[Literal["Ready", "Failed", "Unknown", 3 more]]` The status of the action, indicating if it's building, ready, failed, etc. - `"Ready"` - `"Failed"` - `"Unknown"` - `"Deleted"` - `"Unhealthy"` - `"BuildOnly"` - `status_reason: Optional[str]` The reason for the status of the action. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) agents = client.agents.list() print(agents) ``` #### 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 `agents.rpc(stragent_id, AgentRpcParams**kwargs) -> AgentRpcResponse` **post** `/agents/{agent_id}/rpc` Handle JSON-RPC requests for an agent by its unique ID. ### Parameters - `agent_id: str` - `method: Literal["event/send", "task/create", "message/send", 2 more]` - `"event/send"` - `"task/create"` - `"message/send"` - `"task/cancel"` - `"task/interrupt"` - `params: Params` The parameters for the agent RPC request - `class ParamsCreateTaskRequest: …` - `name: Optional[str]` 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[Dict[str, object]]` 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[Dict[str, object]]` 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. - `class ParamsCancelTaskRequest: …` - `task_id: Optional[str]` The ID of the task to cancel. Either this or task_name must be provided. - `task_name: Optional[str]` The name of the task to cancel. Either this or task_id must be provided. - `class ParamsInterruptTaskRequest: …` - `task_id: Optional[str]` The ID of the task to interrupt. Either this or task_name must be provided. - `task_name: Optional[str]` The name of the task to interrupt. Either this or task_id must be provided. - `class ParamsSendMessageRequest: …` - `content: TaskMessageContentParam` The message that was sent to the agent - `class TextContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"user"` - `"agent"` - `content: str` The contents of the text message. - `attachments: Optional[List[Attachment]]` Optional list of file attachments with structured metadata. - `file_id: str` The unique ID of the attached file - `name: str` The name of the file - `size: int` The size of the file in bytes - `type: str` 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[Literal["text"]]` The type of the message, in this case `text`. - `"text"` - `class ReasoningContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: List[str]` A list of short reasoning summaries - `content: Optional[List[str]]` 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[Literal["reasoning"]]` The type of the message, in this case `reasoning`. - `"reasoning"` - `class DataContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Dict[str, object]` 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[Literal["data"]]` The type of the message, in this case `data`. - `"data"` - `class ToolRequestContent: …` - `arguments: Dict[str, object]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `name: str` The name of the tool that is being requested. - `tool_call_id: str` 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[Literal["tool_request"]]` The type of the message, in this case `tool_request`. - `"tool_request"` - `class ToolResponseContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `content: object` The result of the tool. - `name: str` The name of the tool that is being responded to. - `tool_call_id: str` The ID of the tool call that is being responded to. - `is_error: Optional[bool]` 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[Literal["tool_response"]]` The type of the message, in this case `tool_response`. - `"tool_response"` - `stream: Optional[bool]` Whether to stream the response message back to the client - `task_id: Optional[str]` The ID of the task that the message was sent to - `task_name: Optional[str]` The name of the task that the message was sent to - `task_params: Optional[Dict[str, object]]` The parameters for the task (only used when creating new tasks) - `class ParamsSendEventRequest: …` - `content: Optional[TaskMessageContentParam]` The content to send to the event - `task_id: Optional[str]` The ID of the task that the event was sent to - `task_name: Optional[str]` The name of the task that the event was sent to - `id: Optional[Union[int, str, null]]` - `int` - `str` - `jsonrpc: Optional[Literal["2.0"]]` - `"2.0"` ### Returns - `class AgentRpcResponse: …` - `result: Optional[AgentRpcResult]` The result of the agent RPC request - `List[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. - `class TextContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"user"` - `"agent"` - `content: str` The contents of the text message. - `attachments: Optional[List[Attachment]]` Optional list of file attachments with structured metadata. - `file_id: str` The unique ID of the attached file - `name: str` The name of the file - `size: int` The size of the file in bytes - `type: str` 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[Literal["text"]]` The type of the message, in this case `text`. - `"text"` - `class ReasoningContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: List[str]` A list of short reasoning summaries - `content: Optional[List[str]]` 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[Literal["reasoning"]]` The type of the message, in this case `reasoning`. - `"reasoning"` - `class DataContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Dict[str, object]` 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[Literal["data"]]` The type of the message, in this case `data`. - `"data"` - `class ToolRequestContent: …` - `arguments: Dict[str, object]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `name: str` The name of the tool that is being requested. - `tool_call_id: str` 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[Literal["tool_request"]]` The type of the message, in this case `tool_request`. - `"tool_request"` - `class ToolResponseContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `content: object` The result of the tool. - `name: str` The name of the tool that is being responded to. - `tool_call_id: str` The ID of the tool call that is being responded to. - `is_error: Optional[bool]` 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[Literal["tool_response"]]` The type of the message, in this case `tool_response`. - `"tool_response"` - `task_id: str` ID of the task this message belongs to - `id: Optional[str]` The task message's unique id - `created_at: Optional[datetime]` The timestamp when the message was created - `streaming_status: Optional[Literal["IN_PROGRESS", "DONE"]]` - `"IN_PROGRESS"` - `"DONE"` - `updated_at: Optional[datetime]` The timestamp when the message was last updated - `class StreamTaskMessageStart: …` Event for starting a streaming message - `content: TaskMessageContent` - `index: Optional[int]` - `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: str` ID of the task this message belongs to - `id: Optional[str]` The task message's unique id - `created_at: Optional[datetime]` The timestamp when the message was created - `streaming_status: Optional[Literal["IN_PROGRESS", "DONE"]]` - `updated_at: Optional[datetime]` The timestamp when the message was last updated - `type: Optional[Literal["start"]]` - `"start"` - `class StreamTaskMessageDelta: …` Event for streaming chunks of content - `delta: Optional[TaskMessageDelta]` Delta for text updates - `class TextDelta: …` Delta for text updates - `text_delta: Optional[str]` - `type: Optional[Literal["text"]]` - `"text"` - `class DataDelta: …` Delta for data updates - `data_delta: Optional[str]` - `type: Optional[Literal["data"]]` - `"data"` - `class ToolRequestDelta: …` Delta for tool request updates - `name: str` - `tool_call_id: str` - `arguments_delta: Optional[str]` - `type: Optional[Literal["tool_request"]]` - `"tool_request"` - `class ToolResponseDelta: …` Delta for tool response updates - `name: str` - `tool_call_id: str` - `content_delta: Optional[str]` - `type: Optional[Literal["tool_response"]]` - `"tool_response"` - `class ReasoningSummaryDelta: …` Delta for reasoning summary updates - `summary_index: int` - `summary_delta: Optional[str]` - `type: Optional[Literal["reasoning_summary"]]` - `"reasoning_summary"` - `class ReasoningContentDelta: …` Delta for reasoning content updates - `content_index: int` - `content_delta: Optional[str]` - `type: Optional[Literal["reasoning_content"]]` - `"reasoning_content"` - `index: Optional[int]` - `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[Literal["delta"]]` - `"delta"` - `class StreamTaskMessageFull: …` Event for streaming the full content - `content: TaskMessageContent` - `index: Optional[int]` - `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[Literal["full"]]` - `"full"` - `class StreamTaskMessageDone: …` Event for indicating the task is done - `index: Optional[int]` - `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[Literal["done"]]` - `"done"` - `class Task: …` - `id: str` - `cleaned_at: Optional[datetime]` - `created_at: Optional[datetime]` - `name: Optional[str]` - `params: Optional[Dict[str, object]]` - `status: Optional[Literal["CANCELED", "COMPLETED", "FAILED", 5 more]]` - `"CANCELED"` - `"COMPLETED"` - `"FAILED"` - `"RUNNING"` - `"INTERRUPTED"` - `"TERMINATED"` - `"TIMED_OUT"` - `"DELETED"` - `status_reason: Optional[str]` - `task_metadata: Optional[Dict[str, object]]` - `updated_at: Optional[datetime]` - `class Event: …` - `id: str` The UUID of the event - `agent_id: str` The UUID of the agent that the event belongs to - `sequence_id: int` The sequence ID of the event - `task_id: str` The UUID of the task that the event belongs to - `content: Optional[TaskMessageContent]` The content of the event - `created_at: Optional[datetime]` The timestamp of the event - `id: Optional[Union[int, str, null]]` - `int` - `str` - `error: Optional[object]` - `jsonrpc: Optional[Literal["2.0"]]` - `"2.0"` ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) agent_rpc_response = client.agents.rpc( agent_id="agent_id", method="event/send", params={}, ) print(agent_rpc_response.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" } ``` ## Get Agent by Name `agents.retrieve_by_name(stragent_name) -> Agent` **get** `/agents/name/{agent_name}` Get an agent by its unique name. ### Parameters - `agent_name: str` ### Returns - `class Agent: …` - `id: str` The unique identifier of the agent. - `acp_type: AcpType` The type of the ACP Server (Either sync or async) - `"sync"` - `"async"` - `"agentic"` - `created_at: datetime` The timestamp when the agent was created - `description: str` The description of the action. - `name: str` The unique name of the agent. - `updated_at: datetime` The timestamp when the agent was last updated - `agent_input_type: Optional[Literal["text", "json"]]` The type of input the agent expects. - `"text"` - `"json"` - `production_deployment_id: Optional[str]` ID of the current production deployment. - `registered_at: Optional[datetime]` The timestamp when the agent was last registered - `registration_metadata: Optional[Dict[str, object]]` The metadata for the agent's registration. - `status: Optional[Literal["Ready", "Failed", "Unknown", 3 more]]` The status of the action, indicating if it's building, ready, failed, etc. - `"Ready"` - `"Failed"` - `"Unknown"` - `"Deleted"` - `"Unhealthy"` - `"BuildOnly"` - `status_reason: Optional[str]` The reason for the status of the action. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) agent = client.agents.retrieve_by_name( "agent_name", ) print(agent.id) ``` #### 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 `agents.delete_by_name(stragent_name) -> DeleteResponse` **delete** `/agents/name/{agent_name}` Delete an agent by its unique name. ### Parameters - `agent_name: str` ### Returns - `class DeleteResponse: …` - `id: str` - `message: str` ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) delete_response = client.agents.delete_by_name( "agent_name", ) print(delete_response.id) ``` #### Response ```json { "id": "id", "message": "message" } ``` ## Handle Agent RPC by Name `agents.rpc_by_name(stragent_name, AgentRpcByNameParams**kwargs) -> AgentRpcResponse` **post** `/agents/name/{agent_name}/rpc` Handle JSON-RPC requests for an agent by its unique name. ### Parameters - `agent_name: str` - `method: Literal["event/send", "task/create", "message/send", 2 more]` - `"event/send"` - `"task/create"` - `"message/send"` - `"task/cancel"` - `"task/interrupt"` - `params: Params` The parameters for the agent RPC request - `class ParamsCreateTaskRequest: …` - `name: Optional[str]` 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[Dict[str, object]]` 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[Dict[str, object]]` 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. - `class ParamsCancelTaskRequest: …` - `task_id: Optional[str]` The ID of the task to cancel. Either this or task_name must be provided. - `task_name: Optional[str]` The name of the task to cancel. Either this or task_id must be provided. - `class ParamsInterruptTaskRequest: …` - `task_id: Optional[str]` The ID of the task to interrupt. Either this or task_name must be provided. - `task_name: Optional[str]` The name of the task to interrupt. Either this or task_id must be provided. - `class ParamsSendMessageRequest: …` - `content: TaskMessageContentParam` The message that was sent to the agent - `class TextContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"user"` - `"agent"` - `content: str` The contents of the text message. - `attachments: Optional[List[Attachment]]` Optional list of file attachments with structured metadata. - `file_id: str` The unique ID of the attached file - `name: str` The name of the file - `size: int` The size of the file in bytes - `type: str` 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[Literal["text"]]` The type of the message, in this case `text`. - `"text"` - `class ReasoningContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: List[str]` A list of short reasoning summaries - `content: Optional[List[str]]` 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[Literal["reasoning"]]` The type of the message, in this case `reasoning`. - `"reasoning"` - `class DataContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Dict[str, object]` 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[Literal["data"]]` The type of the message, in this case `data`. - `"data"` - `class ToolRequestContent: …` - `arguments: Dict[str, object]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `name: str` The name of the tool that is being requested. - `tool_call_id: str` 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[Literal["tool_request"]]` The type of the message, in this case `tool_request`. - `"tool_request"` - `class ToolResponseContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `content: object` The result of the tool. - `name: str` The name of the tool that is being responded to. - `tool_call_id: str` The ID of the tool call that is being responded to. - `is_error: Optional[bool]` 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[Literal["tool_response"]]` The type of the message, in this case `tool_response`. - `"tool_response"` - `stream: Optional[bool]` Whether to stream the response message back to the client - `task_id: Optional[str]` The ID of the task that the message was sent to - `task_name: Optional[str]` The name of the task that the message was sent to - `task_params: Optional[Dict[str, object]]` The parameters for the task (only used when creating new tasks) - `class ParamsSendEventRequest: …` - `content: Optional[TaskMessageContentParam]` The content to send to the event - `task_id: Optional[str]` The ID of the task that the event was sent to - `task_name: Optional[str]` The name of the task that the event was sent to - `id: Optional[Union[int, str, null]]` - `int` - `str` - `jsonrpc: Optional[Literal["2.0"]]` - `"2.0"` ### Returns - `class AgentRpcResponse: …` - `result: Optional[AgentRpcResult]` The result of the agent RPC request - `List[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. - `class TextContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"user"` - `"agent"` - `content: str` The contents of the text message. - `attachments: Optional[List[Attachment]]` Optional list of file attachments with structured metadata. - `file_id: str` The unique ID of the attached file - `name: str` The name of the file - `size: int` The size of the file in bytes - `type: str` 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[Literal["text"]]` The type of the message, in this case `text`. - `"text"` - `class ReasoningContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: List[str]` A list of short reasoning summaries - `content: Optional[List[str]]` 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[Literal["reasoning"]]` The type of the message, in this case `reasoning`. - `"reasoning"` - `class DataContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Dict[str, object]` 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[Literal["data"]]` The type of the message, in this case `data`. - `"data"` - `class ToolRequestContent: …` - `arguments: Dict[str, object]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `name: str` The name of the tool that is being requested. - `tool_call_id: str` 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[Literal["tool_request"]]` The type of the message, in this case `tool_request`. - `"tool_request"` - `class ToolResponseContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `content: object` The result of the tool. - `name: str` The name of the tool that is being responded to. - `tool_call_id: str` The ID of the tool call that is being responded to. - `is_error: Optional[bool]` 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[Literal["tool_response"]]` The type of the message, in this case `tool_response`. - `"tool_response"` - `task_id: str` ID of the task this message belongs to - `id: Optional[str]` The task message's unique id - `created_at: Optional[datetime]` The timestamp when the message was created - `streaming_status: Optional[Literal["IN_PROGRESS", "DONE"]]` - `"IN_PROGRESS"` - `"DONE"` - `updated_at: Optional[datetime]` The timestamp when the message was last updated - `class StreamTaskMessageStart: …` Event for starting a streaming message - `content: TaskMessageContent` - `index: Optional[int]` - `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: str` ID of the task this message belongs to - `id: Optional[str]` The task message's unique id - `created_at: Optional[datetime]` The timestamp when the message was created - `streaming_status: Optional[Literal["IN_PROGRESS", "DONE"]]` - `updated_at: Optional[datetime]` The timestamp when the message was last updated - `type: Optional[Literal["start"]]` - `"start"` - `class StreamTaskMessageDelta: …` Event for streaming chunks of content - `delta: Optional[TaskMessageDelta]` Delta for text updates - `class TextDelta: …` Delta for text updates - `text_delta: Optional[str]` - `type: Optional[Literal["text"]]` - `"text"` - `class DataDelta: …` Delta for data updates - `data_delta: Optional[str]` - `type: Optional[Literal["data"]]` - `"data"` - `class ToolRequestDelta: …` Delta for tool request updates - `name: str` - `tool_call_id: str` - `arguments_delta: Optional[str]` - `type: Optional[Literal["tool_request"]]` - `"tool_request"` - `class ToolResponseDelta: …` Delta for tool response updates - `name: str` - `tool_call_id: str` - `content_delta: Optional[str]` - `type: Optional[Literal["tool_response"]]` - `"tool_response"` - `class ReasoningSummaryDelta: …` Delta for reasoning summary updates - `summary_index: int` - `summary_delta: Optional[str]` - `type: Optional[Literal["reasoning_summary"]]` - `"reasoning_summary"` - `class ReasoningContentDelta: …` Delta for reasoning content updates - `content_index: int` - `content_delta: Optional[str]` - `type: Optional[Literal["reasoning_content"]]` - `"reasoning_content"` - `index: Optional[int]` - `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[Literal["delta"]]` - `"delta"` - `class StreamTaskMessageFull: …` Event for streaming the full content - `content: TaskMessageContent` - `index: Optional[int]` - `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[Literal["full"]]` - `"full"` - `class StreamTaskMessageDone: …` Event for indicating the task is done - `index: Optional[int]` - `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[Literal["done"]]` - `"done"` - `class Task: …` - `id: str` - `cleaned_at: Optional[datetime]` - `created_at: Optional[datetime]` - `name: Optional[str]` - `params: Optional[Dict[str, object]]` - `status: Optional[Literal["CANCELED", "COMPLETED", "FAILED", 5 more]]` - `"CANCELED"` - `"COMPLETED"` - `"FAILED"` - `"RUNNING"` - `"INTERRUPTED"` - `"TERMINATED"` - `"TIMED_OUT"` - `"DELETED"` - `status_reason: Optional[str]` - `task_metadata: Optional[Dict[str, object]]` - `updated_at: Optional[datetime]` - `class Event: …` - `id: str` The UUID of the event - `agent_id: str` The UUID of the agent that the event belongs to - `sequence_id: int` The sequence ID of the event - `task_id: str` The UUID of the task that the event belongs to - `content: Optional[TaskMessageContent]` The content of the event - `created_at: Optional[datetime]` The timestamp of the event - `id: Optional[Union[int, str, null]]` - `int` - `str` - `error: Optional[object]` - `jsonrpc: Optional[Literal["2.0"]]` - `"2.0"` ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) agent_rpc_response = client.agents.rpc_by_name( agent_name="agent_name", method="event/send", params={}, ) print(agent_rpc_response.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" } ``` ## Register Build `agents.register_build(AgentRegisterBuildParams**kwargs) -> Agent` **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. ### Parameters - `description: str` The description of the agent. - `name: str` The unique name of the agent. - `agent_input_type: Optional[Literal["text", "json"]]` The type of input the agent expects. - `"text"` - `"json"` - `registration_metadata: Optional[Dict[str, object]]` The metadata for the agent's build registration. ### Returns - `class Agent: …` - `id: str` The unique identifier of the agent. - `acp_type: AcpType` The type of the ACP Server (Either sync or async) - `"sync"` - `"async"` - `"agentic"` - `created_at: datetime` The timestamp when the agent was created - `description: str` The description of the action. - `name: str` The unique name of the agent. - `updated_at: datetime` The timestamp when the agent was last updated - `agent_input_type: Optional[Literal["text", "json"]]` The type of input the agent expects. - `"text"` - `"json"` - `production_deployment_id: Optional[str]` ID of the current production deployment. - `registered_at: Optional[datetime]` The timestamp when the agent was last registered - `registration_metadata: Optional[Dict[str, object]]` The metadata for the agent's registration. - `status: Optional[Literal["Ready", "Failed", "Unknown", 3 more]]` The status of the action, indicating if it's building, ready, failed, etc. - `"Ready"` - `"Failed"` - `"Unknown"` - `"Deleted"` - `"Unhealthy"` - `"BuildOnly"` - `status_reason: Optional[str]` The reason for the status of the action. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) agent = client.agents.register_build( description="description", name="name", ) print(agent.id) ``` #### 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 - `Literal["sync", "async", "agentic"]` - `"sync"` - `"async"` - `"agentic"` ### Agent - `class Agent: …` - `id: str` The unique identifier of the agent. - `acp_type: AcpType` The type of the ACP Server (Either sync or async) - `"sync"` - `"async"` - `"agentic"` - `created_at: datetime` The timestamp when the agent was created - `description: str` The description of the action. - `name: str` The unique name of the agent. - `updated_at: datetime` The timestamp when the agent was last updated - `agent_input_type: Optional[Literal["text", "json"]]` The type of input the agent expects. - `"text"` - `"json"` - `production_deployment_id: Optional[str]` ID of the current production deployment. - `registered_at: Optional[datetime]` The timestamp when the agent was last registered - `registration_metadata: Optional[Dict[str, object]]` The metadata for the agent's registration. - `status: Optional[Literal["Ready", "Failed", "Unknown", 3 more]]` The status of the action, indicating if it's building, ready, failed, etc. - `"Ready"` - `"Failed"` - `"Unknown"` - `"Deleted"` - `"Unhealthy"` - `"BuildOnly"` - `status_reason: Optional[str]` The reason for the status of the action. ### Agent Rpc Request - `class AgentRpcRequest: …` - `method: Literal["event/send", "task/create", "message/send", 2 more]` - `"event/send"` - `"task/create"` - `"message/send"` - `"task/cancel"` - `"task/interrupt"` - `params: Params` The parameters for the agent RPC request - `class ParamsCreateTaskRequest: …` - `name: Optional[str]` 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[Dict[str, object]]` 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[Dict[str, object]]` 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. - `class ParamsCancelTaskRequest: …` - `task_id: Optional[str]` The ID of the task to cancel. Either this or task_name must be provided. - `task_name: Optional[str]` The name of the task to cancel. Either this or task_id must be provided. - `class ParamsInterruptTaskRequest: …` - `task_id: Optional[str]` The ID of the task to interrupt. Either this or task_name must be provided. - `task_name: Optional[str]` The name of the task to interrupt. Either this or task_id must be provided. - `class ParamsSendMessageRequest: …` - `content: TaskMessageContent` The message that was sent to the agent - `class TextContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"user"` - `"agent"` - `content: str` The contents of the text message. - `attachments: Optional[List[Attachment]]` Optional list of file attachments with structured metadata. - `file_id: str` The unique ID of the attached file - `name: str` The name of the file - `size: int` The size of the file in bytes - `type: str` 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[Literal["text"]]` The type of the message, in this case `text`. - `"text"` - `class ReasoningContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: List[str]` A list of short reasoning summaries - `content: Optional[List[str]]` 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[Literal["reasoning"]]` The type of the message, in this case `reasoning`. - `"reasoning"` - `class DataContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Dict[str, object]` 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[Literal["data"]]` The type of the message, in this case `data`. - `"data"` - `class ToolRequestContent: …` - `arguments: Dict[str, object]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `name: str` The name of the tool that is being requested. - `tool_call_id: str` 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[Literal["tool_request"]]` The type of the message, in this case `tool_request`. - `"tool_request"` - `class ToolResponseContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `content: object` The result of the tool. - `name: str` The name of the tool that is being responded to. - `tool_call_id: str` The ID of the tool call that is being responded to. - `is_error: Optional[bool]` 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[Literal["tool_response"]]` The type of the message, in this case `tool_response`. - `"tool_response"` - `stream: Optional[bool]` Whether to stream the response message back to the client - `task_id: Optional[str]` The ID of the task that the message was sent to - `task_name: Optional[str]` The name of the task that the message was sent to - `task_params: Optional[Dict[str, object]]` The parameters for the task (only used when creating new tasks) - `class ParamsSendEventRequest: …` - `content: Optional[TaskMessageContent]` The content to send to the event - `task_id: Optional[str]` The ID of the task that the event was sent to - `task_name: Optional[str]` The name of the task that the event was sent to - `id: Optional[Union[int, str, null]]` - `int` - `str` - `jsonrpc: Optional[Literal["2.0"]]` - `"2.0"` ### Agent Rpc Response - `class AgentRpcResponse: …` - `result: Optional[AgentRpcResult]` The result of the agent RPC request - `List[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. - `class TextContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"user"` - `"agent"` - `content: str` The contents of the text message. - `attachments: Optional[List[Attachment]]` Optional list of file attachments with structured metadata. - `file_id: str` The unique ID of the attached file - `name: str` The name of the file - `size: int` The size of the file in bytes - `type: str` 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[Literal["text"]]` The type of the message, in this case `text`. - `"text"` - `class ReasoningContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: List[str]` A list of short reasoning summaries - `content: Optional[List[str]]` 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[Literal["reasoning"]]` The type of the message, in this case `reasoning`. - `"reasoning"` - `class DataContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Dict[str, object]` 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[Literal["data"]]` The type of the message, in this case `data`. - `"data"` - `class ToolRequestContent: …` - `arguments: Dict[str, object]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `name: str` The name of the tool that is being requested. - `tool_call_id: str` 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[Literal["tool_request"]]` The type of the message, in this case `tool_request`. - `"tool_request"` - `class ToolResponseContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `content: object` The result of the tool. - `name: str` The name of the tool that is being responded to. - `tool_call_id: str` The ID of the tool call that is being responded to. - `is_error: Optional[bool]` 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[Literal["tool_response"]]` The type of the message, in this case `tool_response`. - `"tool_response"` - `task_id: str` ID of the task this message belongs to - `id: Optional[str]` The task message's unique id - `created_at: Optional[datetime]` The timestamp when the message was created - `streaming_status: Optional[Literal["IN_PROGRESS", "DONE"]]` - `"IN_PROGRESS"` - `"DONE"` - `updated_at: Optional[datetime]` The timestamp when the message was last updated - `class StreamTaskMessageStart: …` Event for starting a streaming message - `content: TaskMessageContent` - `index: Optional[int]` - `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: str` ID of the task this message belongs to - `id: Optional[str]` The task message's unique id - `created_at: Optional[datetime]` The timestamp when the message was created - `streaming_status: Optional[Literal["IN_PROGRESS", "DONE"]]` - `updated_at: Optional[datetime]` The timestamp when the message was last updated - `type: Optional[Literal["start"]]` - `"start"` - `class StreamTaskMessageDelta: …` Event for streaming chunks of content - `delta: Optional[TaskMessageDelta]` Delta for text updates - `class TextDelta: …` Delta for text updates - `text_delta: Optional[str]` - `type: Optional[Literal["text"]]` - `"text"` - `class DataDelta: …` Delta for data updates - `data_delta: Optional[str]` - `type: Optional[Literal["data"]]` - `"data"` - `class ToolRequestDelta: …` Delta for tool request updates - `name: str` - `tool_call_id: str` - `arguments_delta: Optional[str]` - `type: Optional[Literal["tool_request"]]` - `"tool_request"` - `class ToolResponseDelta: …` Delta for tool response updates - `name: str` - `tool_call_id: str` - `content_delta: Optional[str]` - `type: Optional[Literal["tool_response"]]` - `"tool_response"` - `class ReasoningSummaryDelta: …` Delta for reasoning summary updates - `summary_index: int` - `summary_delta: Optional[str]` - `type: Optional[Literal["reasoning_summary"]]` - `"reasoning_summary"` - `class ReasoningContentDelta: …` Delta for reasoning content updates - `content_index: int` - `content_delta: Optional[str]` - `type: Optional[Literal["reasoning_content"]]` - `"reasoning_content"` - `index: Optional[int]` - `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[Literal["delta"]]` - `"delta"` - `class StreamTaskMessageFull: …` Event for streaming the full content - `content: TaskMessageContent` - `index: Optional[int]` - `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[Literal["full"]]` - `"full"` - `class StreamTaskMessageDone: …` Event for indicating the task is done - `index: Optional[int]` - `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[Literal["done"]]` - `"done"` - `class Task: …` - `id: str` - `cleaned_at: Optional[datetime]` - `created_at: Optional[datetime]` - `name: Optional[str]` - `params: Optional[Dict[str, object]]` - `status: Optional[Literal["CANCELED", "COMPLETED", "FAILED", 5 more]]` - `"CANCELED"` - `"COMPLETED"` - `"FAILED"` - `"RUNNING"` - `"INTERRUPTED"` - `"TERMINATED"` - `"TIMED_OUT"` - `"DELETED"` - `status_reason: Optional[str]` - `task_metadata: Optional[Dict[str, object]]` - `updated_at: Optional[datetime]` - `class Event: …` - `id: str` The UUID of the event - `agent_id: str` The UUID of the agent that the event belongs to - `sequence_id: int` The sequence ID of the event - `task_id: str` The UUID of the task that the event belongs to - `content: Optional[TaskMessageContent]` The content of the event - `created_at: Optional[datetime]` The timestamp of the event - `id: Optional[Union[int, str, null]]` - `int` - `str` - `error: Optional[object]` - `jsonrpc: Optional[Literal["2.0"]]` - `"2.0"` ### Agent Rpc Result - `Optional[AgentRpcResult]` Event for starting a streaming message - `List[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. - `class TextContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"user"` - `"agent"` - `content: str` The contents of the text message. - `attachments: Optional[List[Attachment]]` Optional list of file attachments with structured metadata. - `file_id: str` The unique ID of the attached file - `name: str` The name of the file - `size: int` The size of the file in bytes - `type: str` 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[Literal["text"]]` The type of the message, in this case `text`. - `"text"` - `class ReasoningContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: List[str]` A list of short reasoning summaries - `content: Optional[List[str]]` 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[Literal["reasoning"]]` The type of the message, in this case `reasoning`. - `"reasoning"` - `class DataContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Dict[str, object]` 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[Literal["data"]]` The type of the message, in this case `data`. - `"data"` - `class ToolRequestContent: …` - `arguments: Dict[str, object]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `name: str` The name of the tool that is being requested. - `tool_call_id: str` 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[Literal["tool_request"]]` The type of the message, in this case `tool_request`. - `"tool_request"` - `class ToolResponseContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `content: object` The result of the tool. - `name: str` The name of the tool that is being responded to. - `tool_call_id: str` The ID of the tool call that is being responded to. - `is_error: Optional[bool]` 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[Literal["tool_response"]]` The type of the message, in this case `tool_response`. - `"tool_response"` - `task_id: str` ID of the task this message belongs to - `id: Optional[str]` The task message's unique id - `created_at: Optional[datetime]` The timestamp when the message was created - `streaming_status: Optional[Literal["IN_PROGRESS", "DONE"]]` - `"IN_PROGRESS"` - `"DONE"` - `updated_at: Optional[datetime]` The timestamp when the message was last updated - `class StreamTaskMessageStart: …` Event for starting a streaming message - `content: TaskMessageContent` - `index: Optional[int]` - `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: str` ID of the task this message belongs to - `id: Optional[str]` The task message's unique id - `created_at: Optional[datetime]` The timestamp when the message was created - `streaming_status: Optional[Literal["IN_PROGRESS", "DONE"]]` - `updated_at: Optional[datetime]` The timestamp when the message was last updated - `type: Optional[Literal["start"]]` - `"start"` - `class StreamTaskMessageDelta: …` Event for streaming chunks of content - `delta: Optional[TaskMessageDelta]` Delta for text updates - `class TextDelta: …` Delta for text updates - `text_delta: Optional[str]` - `type: Optional[Literal["text"]]` - `"text"` - `class DataDelta: …` Delta for data updates - `data_delta: Optional[str]` - `type: Optional[Literal["data"]]` - `"data"` - `class ToolRequestDelta: …` Delta for tool request updates - `name: str` - `tool_call_id: str` - `arguments_delta: Optional[str]` - `type: Optional[Literal["tool_request"]]` - `"tool_request"` - `class ToolResponseDelta: …` Delta for tool response updates - `name: str` - `tool_call_id: str` - `content_delta: Optional[str]` - `type: Optional[Literal["tool_response"]]` - `"tool_response"` - `class ReasoningSummaryDelta: …` Delta for reasoning summary updates - `summary_index: int` - `summary_delta: Optional[str]` - `type: Optional[Literal["reasoning_summary"]]` - `"reasoning_summary"` - `class ReasoningContentDelta: …` Delta for reasoning content updates - `content_index: int` - `content_delta: Optional[str]` - `type: Optional[Literal["reasoning_content"]]` - `"reasoning_content"` - `index: Optional[int]` - `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[Literal["delta"]]` - `"delta"` - `class StreamTaskMessageFull: …` Event for streaming the full content - `content: TaskMessageContent` - `index: Optional[int]` - `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[Literal["full"]]` - `"full"` - `class StreamTaskMessageDone: …` Event for indicating the task is done - `index: Optional[int]` - `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[Literal["done"]]` - `"done"` - `class Task: …` - `id: str` - `cleaned_at: Optional[datetime]` - `created_at: Optional[datetime]` - `name: Optional[str]` - `params: Optional[Dict[str, object]]` - `status: Optional[Literal["CANCELED", "COMPLETED", "FAILED", 5 more]]` - `"CANCELED"` - `"COMPLETED"` - `"FAILED"` - `"RUNNING"` - `"INTERRUPTED"` - `"TERMINATED"` - `"TIMED_OUT"` - `"DELETED"` - `status_reason: Optional[str]` - `task_metadata: Optional[Dict[str, object]]` - `updated_at: Optional[datetime]` - `class Event: …` - `id: str` The UUID of the event - `agent_id: str` The UUID of the agent that the event belongs to - `sequence_id: int` The sequence ID of the event - `task_id: str` The UUID of the task that the event belongs to - `content: Optional[TaskMessageContent]` The content of the event - `created_at: Optional[datetime]` The timestamp of the event ### Data Delta - `class DataDelta: …` Delta for data updates - `data_delta: Optional[str]` - `type: Optional[Literal["data"]]` - `"data"` ### Reasoning Content Delta - `class ReasoningContentDelta: …` Delta for reasoning content updates - `content_index: int` - `content_delta: Optional[str]` - `type: Optional[Literal["reasoning_content"]]` - `"reasoning_content"` ### Reasoning Summary Delta - `class ReasoningSummaryDelta: …` Delta for reasoning summary updates - `summary_index: int` - `summary_delta: Optional[str]` - `type: Optional[Literal["reasoning_summary"]]` - `"reasoning_summary"` ### Task Message Content - `TaskMessageContent` - `class TextContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"user"` - `"agent"` - `content: str` The contents of the text message. - `attachments: Optional[List[Attachment]]` Optional list of file attachments with structured metadata. - `file_id: str` The unique ID of the attached file - `name: str` The name of the file - `size: int` The size of the file in bytes - `type: str` 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[Literal["text"]]` The type of the message, in this case `text`. - `"text"` - `class ReasoningContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: List[str]` A list of short reasoning summaries - `content: Optional[List[str]]` 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[Literal["reasoning"]]` The type of the message, in this case `reasoning`. - `"reasoning"` - `class DataContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Dict[str, object]` 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[Literal["data"]]` The type of the message, in this case `data`. - `"data"` - `class ToolRequestContent: …` - `arguments: Dict[str, object]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `name: str` The name of the tool that is being requested. - `tool_call_id: str` 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[Literal["tool_request"]]` The type of the message, in this case `tool_request`. - `"tool_request"` - `class ToolResponseContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `content: object` The result of the tool. - `name: str` The name of the tool that is being responded to. - `tool_call_id: str` The ID of the tool call that is being responded to. - `is_error: Optional[bool]` 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[Literal["tool_response"]]` The type of the message, in this case `tool_response`. - `"tool_response"` ### Task Message Delta - `TaskMessageDelta` Delta for text updates - `class TextDelta: …` Delta for text updates - `text_delta: Optional[str]` - `type: Optional[Literal["text"]]` - `"text"` - `class DataDelta: …` Delta for data updates - `data_delta: Optional[str]` - `type: Optional[Literal["data"]]` - `"data"` - `class ToolRequestDelta: …` Delta for tool request updates - `name: str` - `tool_call_id: str` - `arguments_delta: Optional[str]` - `type: Optional[Literal["tool_request"]]` - `"tool_request"` - `class ToolResponseDelta: …` Delta for tool response updates - `name: str` - `tool_call_id: str` - `content_delta: Optional[str]` - `type: Optional[Literal["tool_response"]]` - `"tool_response"` - `class ReasoningSummaryDelta: …` Delta for reasoning summary updates - `summary_index: int` - `summary_delta: Optional[str]` - `type: Optional[Literal["reasoning_summary"]]` - `"reasoning_summary"` - `class ReasoningContentDelta: …` Delta for reasoning content updates - `content_index: int` - `content_delta: Optional[str]` - `type: Optional[Literal["reasoning_content"]]` - `"reasoning_content"` ### Task Message Update - `TaskMessageUpdate` Event for starting a streaming message - `class StreamTaskMessageStart: …` Event for starting a streaming message - `content: TaskMessageContent` - `class TextContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"user"` - `"agent"` - `content: str` The contents of the text message. - `attachments: Optional[List[Attachment]]` Optional list of file attachments with structured metadata. - `file_id: str` The unique ID of the attached file - `name: str` The name of the file - `size: int` The size of the file in bytes - `type: str` 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[Literal["text"]]` The type of the message, in this case `text`. - `"text"` - `class ReasoningContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: List[str]` A list of short reasoning summaries - `content: Optional[List[str]]` 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[Literal["reasoning"]]` The type of the message, in this case `reasoning`. - `"reasoning"` - `class DataContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Dict[str, object]` 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[Literal["data"]]` The type of the message, in this case `data`. - `"data"` - `class ToolRequestContent: …` - `arguments: Dict[str, object]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `name: str` The name of the tool that is being requested. - `tool_call_id: str` 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[Literal["tool_request"]]` The type of the message, in this case `tool_request`. - `"tool_request"` - `class ToolResponseContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `content: object` The result of the tool. - `name: str` The name of the tool that is being responded to. - `tool_call_id: str` The ID of the tool call that is being responded to. - `is_error: Optional[bool]` 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[Literal["tool_response"]]` The type of the message, in this case `tool_response`. - `"tool_response"` - `index: Optional[int]` - `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: str` ID of the task this message belongs to - `id: Optional[str]` The task message's unique id - `created_at: Optional[datetime]` The timestamp when the message was created - `streaming_status: Optional[Literal["IN_PROGRESS", "DONE"]]` - `"IN_PROGRESS"` - `"DONE"` - `updated_at: Optional[datetime]` The timestamp when the message was last updated - `type: Optional[Literal["start"]]` - `"start"` - `class StreamTaskMessageDelta: …` Event for streaming chunks of content - `delta: Optional[TaskMessageDelta]` Delta for text updates - `class TextDelta: …` Delta for text updates - `text_delta: Optional[str]` - `type: Optional[Literal["text"]]` - `"text"` - `class DataDelta: …` Delta for data updates - `data_delta: Optional[str]` - `type: Optional[Literal["data"]]` - `"data"` - `class ToolRequestDelta: …` Delta for tool request updates - `name: str` - `tool_call_id: str` - `arguments_delta: Optional[str]` - `type: Optional[Literal["tool_request"]]` - `"tool_request"` - `class ToolResponseDelta: …` Delta for tool response updates - `name: str` - `tool_call_id: str` - `content_delta: Optional[str]` - `type: Optional[Literal["tool_response"]]` - `"tool_response"` - `class ReasoningSummaryDelta: …` Delta for reasoning summary updates - `summary_index: int` - `summary_delta: Optional[str]` - `type: Optional[Literal["reasoning_summary"]]` - `"reasoning_summary"` - `class ReasoningContentDelta: …` Delta for reasoning content updates - `content_index: int` - `content_delta: Optional[str]` - `type: Optional[Literal["reasoning_content"]]` - `"reasoning_content"` - `index: Optional[int]` - `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[Literal["delta"]]` - `"delta"` - `class StreamTaskMessageFull: …` Event for streaming the full content - `content: TaskMessageContent` - `index: Optional[int]` - `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[Literal["full"]]` - `"full"` - `class StreamTaskMessageDone: …` Event for indicating the task is done - `index: Optional[int]` - `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[Literal["done"]]` - `"done"` ### Text Delta - `class TextDelta: …` Delta for text updates - `text_delta: Optional[str]` - `type: Optional[Literal["text"]]` - `"text"` ### Tool Request Delta - `class ToolRequestDelta: …` Delta for tool request updates - `name: str` - `tool_call_id: str` - `arguments_delta: Optional[str]` - `type: Optional[Literal["tool_request"]]` - `"tool_request"` ### Tool Response Delta - `class ToolResponseDelta: …` Delta for tool response updates - `name: str` - `tool_call_id: str` - `content_delta: Optional[str]` - `type: Optional[Literal["tool_response"]]` - `"tool_response"` ### Agent List Response - `List[Agent]` - `id: str` The unique identifier of the agent. - `acp_type: AcpType` The type of the ACP Server (Either sync or async) - `"sync"` - `"async"` - `"agentic"` - `created_at: datetime` The timestamp when the agent was created - `description: str` The description of the action. - `name: str` The unique name of the agent. - `updated_at: datetime` The timestamp when the agent was last updated - `agent_input_type: Optional[Literal["text", "json"]]` The type of input the agent expects. - `"text"` - `"json"` - `production_deployment_id: Optional[str]` ID of the current production deployment. - `registered_at: Optional[datetime]` The timestamp when the agent was last registered - `registration_metadata: Optional[Dict[str, object]]` The metadata for the agent's registration. - `status: Optional[Literal["Ready", "Failed", "Unknown", 3 more]]` The status of the action, indicating if it's building, ready, failed, etc. - `"Ready"` - `"Failed"` - `"Unknown"` - `"Deleted"` - `"Unhealthy"` - `"BuildOnly"` - `status_reason: Optional[str]` The reason for the status of the action. # Deployments ## Create Deployment `agents.deployments.create(stragent_id, DeploymentCreateParams**kwargs) -> DeploymentCreateResponse` **post** `/agents/{agent_id}/deployments` Create a new deployment record in PENDING status. ### Parameters - `agent_id: str` - `docker_image: str` Full Docker image URI. - `helm_release_name: Optional[str]` Helm release name. - `registration_metadata: Optional[Dict[str, object]]` Git/build metadata (commit_hash, branch_name, author_name, author_email, build_timestamp). - `sgp_deploy_id: Optional[str]` SGP deployment ID. ### Returns - `class DeploymentCreateResponse: …` - `id: str` The unique identifier of the deployment. - `agent_id: str` The agent this deployment belongs to. - `docker_image: str` Full Docker image URI. - `is_production: bool` Whether this is the production deployment. - `status: Literal["Pending", "Ready", "Failed"]` Current deployment status. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: Optional[str]` ACP URL set when agent registers. - `created_at: Optional[datetime]` When the deployment was created. - `expires_at: Optional[datetime]` When marked for cleanup. - `helm_release_name: Optional[str]` Helm release name for cleanup. - `promoted_at: Optional[datetime]` When promoted to production. - `registration_metadata: Optional[Dict[str, object]]` Git/build metadata from the agent pod. - `sgp_deploy_id: Optional[str]` Correlates to SGP's agentex_deploys.id. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) deployment = client.agents.deployments.create( agent_id="agent_id", docker_image="docker_image", ) print(deployment.id) ``` #### 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 `agents.deployments.list(stragent_id, DeploymentListParams**kwargs) -> DeploymentListResponse` **get** `/agents/{agent_id}/deployments` List deployments for an agent, newest first. ### Parameters - `agent_id: str` - `limit: Optional[int]` Limit - `order_by: Optional[str]` Field to order by - `order_direction: Optional[str]` Order direction (asc or desc) - `page_number: Optional[int]` Page number ### Returns - `List[DeploymentListResponseItem]` - `id: str` The unique identifier of the deployment. - `agent_id: str` The agent this deployment belongs to. - `docker_image: str` Full Docker image URI. - `is_production: bool` Whether this is the production deployment. - `status: Literal["Pending", "Ready", "Failed"]` Current deployment status. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: Optional[str]` ACP URL set when agent registers. - `created_at: Optional[datetime]` When the deployment was created. - `expires_at: Optional[datetime]` When marked for cleanup. - `helm_release_name: Optional[str]` Helm release name for cleanup. - `promoted_at: Optional[datetime]` When promoted to production. - `registration_metadata: Optional[Dict[str, object]]` Git/build metadata from the agent pod. - `sgp_deploy_id: Optional[str]` Correlates to SGP's agentex_deploys.id. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) deployments = client.agents.deployments.list( agent_id="agent_id", ) print(deployments) ``` #### 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 `agents.deployments.retrieve(strdeployment_id, DeploymentRetrieveParams**kwargs) -> DeploymentRetrieveResponse` **get** `/agents/{agent_id}/deployments/{deployment_id}` Get a specific deployment by ID. ### Parameters - `agent_id: str` - `deployment_id: str` ### Returns - `class DeploymentRetrieveResponse: …` - `id: str` The unique identifier of the deployment. - `agent_id: str` The agent this deployment belongs to. - `docker_image: str` Full Docker image URI. - `is_production: bool` Whether this is the production deployment. - `status: Literal["Pending", "Ready", "Failed"]` Current deployment status. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: Optional[str]` ACP URL set when agent registers. - `created_at: Optional[datetime]` When the deployment was created. - `expires_at: Optional[datetime]` When marked for cleanup. - `helm_release_name: Optional[str]` Helm release name for cleanup. - `promoted_at: Optional[datetime]` When promoted to production. - `registration_metadata: Optional[Dict[str, object]]` Git/build metadata from the agent pod. - `sgp_deploy_id: Optional[str]` Correlates to SGP's agentex_deploys.id. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) deployment = client.agents.deployments.retrieve( deployment_id="deployment_id", agent_id="agent_id", ) print(deployment.id) ``` #### 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 `agents.deployments.delete(strdeployment_id, DeploymentDeleteParams**kwargs) -> DeleteResponse` **delete** `/agents/{agent_id}/deployments/{deployment_id}` Delete a non-production deployment. ### Parameters - `agent_id: str` - `deployment_id: str` ### Returns - `class DeleteResponse: …` - `id: str` - `message: str` ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) delete_response = client.agents.deployments.delete( deployment_id="deployment_id", agent_id="agent_id", ) print(delete_response.id) ``` #### Response ```json { "id": "id", "message": "message" } ``` ## Promote Deployment `agents.deployments.promote(strdeployment_id, DeploymentPromoteParams**kwargs) -> DeploymentPromoteResponse` **post** `/agents/{agent_id}/deployments/{deployment_id}/promote` Promote a deployment to production with atomic cutover. ### Parameters - `agent_id: str` - `deployment_id: str` ### Returns - `class DeploymentPromoteResponse: …` - `id: str` The unique identifier of the deployment. - `agent_id: str` The agent this deployment belongs to. - `docker_image: str` Full Docker image URI. - `is_production: bool` Whether this is the production deployment. - `status: Literal["Pending", "Ready", "Failed"]` Current deployment status. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: Optional[str]` ACP URL set when agent registers. - `created_at: Optional[datetime]` When the deployment was created. - `expires_at: Optional[datetime]` When marked for cleanup. - `helm_release_name: Optional[str]` Helm release name for cleanup. - `promoted_at: Optional[datetime]` When promoted to production. - `registration_metadata: Optional[Dict[str, object]]` Git/build metadata from the agent pod. - `sgp_deploy_id: Optional[str]` Correlates to SGP's agentex_deploys.id. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) response = client.agents.deployments.promote( deployment_id="deployment_id", agent_id="agent_id", ) print(response.id) ``` #### 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 `agents.deployments.preview_rpc(strdeployment_id, DeploymentPreviewRpcParams**kwargs) -> AgentRpcResponse` **post** `/agents/{agent_id}/deployments/{deployment_id}/rpc` Send an RPC request to a specific deployment (for preview testing). ### Parameters - `agent_id: str` - `deployment_id: str` - `method: Literal["event/send", "task/create", "message/send", 2 more]` - `"event/send"` - `"task/create"` - `"message/send"` - `"task/cancel"` - `"task/interrupt"` - `params: Params` The parameters for the agent RPC request - `class ParamsCreateTaskRequest: …` - `name: Optional[str]` 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[Dict[str, object]]` 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[Dict[str, object]]` 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. - `class ParamsCancelTaskRequest: …` - `task_id: Optional[str]` The ID of the task to cancel. Either this or task_name must be provided. - `task_name: Optional[str]` The name of the task to cancel. Either this or task_id must be provided. - `class ParamsInterruptTaskRequest: …` - `task_id: Optional[str]` The ID of the task to interrupt. Either this or task_name must be provided. - `task_name: Optional[str]` The name of the task to interrupt. Either this or task_id must be provided. - `class ParamsSendMessageRequest: …` - `content: TaskMessageContentParam` The message that was sent to the agent - `class TextContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"user"` - `"agent"` - `content: str` The contents of the text message. - `attachments: Optional[List[Attachment]]` Optional list of file attachments with structured metadata. - `file_id: str` The unique ID of the attached file - `name: str` The name of the file - `size: int` The size of the file in bytes - `type: str` 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[Literal["text"]]` The type of the message, in this case `text`. - `"text"` - `class ReasoningContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: List[str]` A list of short reasoning summaries - `content: Optional[List[str]]` 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[Literal["reasoning"]]` The type of the message, in this case `reasoning`. - `"reasoning"` - `class DataContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Dict[str, object]` 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[Literal["data"]]` The type of the message, in this case `data`. - `"data"` - `class ToolRequestContent: …` - `arguments: Dict[str, object]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `name: str` The name of the tool that is being requested. - `tool_call_id: str` 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[Literal["tool_request"]]` The type of the message, in this case `tool_request`. - `"tool_request"` - `class ToolResponseContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `content: object` The result of the tool. - `name: str` The name of the tool that is being responded to. - `tool_call_id: str` The ID of the tool call that is being responded to. - `is_error: Optional[bool]` 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[Literal["tool_response"]]` The type of the message, in this case `tool_response`. - `"tool_response"` - `stream: Optional[bool]` Whether to stream the response message back to the client - `task_id: Optional[str]` The ID of the task that the message was sent to - `task_name: Optional[str]` The name of the task that the message was sent to - `task_params: Optional[Dict[str, object]]` The parameters for the task (only used when creating new tasks) - `class ParamsSendEventRequest: …` - `content: Optional[TaskMessageContentParam]` The content to send to the event - `task_id: Optional[str]` The ID of the task that the event was sent to - `task_name: Optional[str]` The name of the task that the event was sent to - `id: Optional[Union[int, str, null]]` - `int` - `str` - `jsonrpc: Optional[Literal["2.0"]]` - `"2.0"` ### Returns - `class AgentRpcResponse: …` - `result: Optional[AgentRpcResult]` The result of the agent RPC request - `List[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. - `class TextContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `"user"` - `"agent"` - `content: str` The contents of the text message. - `attachments: Optional[List[Attachment]]` Optional list of file attachments with structured metadata. - `file_id: str` The unique ID of the attached file - `name: str` The name of the file - `size: int` The size of the file in bytes - `type: str` 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[Literal["text"]]` The type of the message, in this case `text`. - `"text"` - `class ReasoningContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `summary: List[str]` A list of short reasoning summaries - `content: Optional[List[str]]` 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[Literal["reasoning"]]` The type of the message, in this case `reasoning`. - `"reasoning"` - `class DataContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `data: Dict[str, object]` 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[Literal["data"]]` The type of the message, in this case `data`. - `"data"` - `class ToolRequestContent: …` - `arguments: Dict[str, object]` The arguments to the tool. - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `name: str` The name of the tool that is being requested. - `tool_call_id: str` 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[Literal["tool_request"]]` The type of the message, in this case `tool_request`. - `"tool_request"` - `class ToolResponseContent: …` - `author: MessageAuthor` The role of the messages author, in this case `system`, `user`, `assistant`, or `tool`. - `content: object` The result of the tool. - `name: str` The name of the tool that is being responded to. - `tool_call_id: str` The ID of the tool call that is being responded to. - `is_error: Optional[bool]` 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[Literal["tool_response"]]` The type of the message, in this case `tool_response`. - `"tool_response"` - `task_id: str` ID of the task this message belongs to - `id: Optional[str]` The task message's unique id - `created_at: Optional[datetime]` The timestamp when the message was created - `streaming_status: Optional[Literal["IN_PROGRESS", "DONE"]]` - `"IN_PROGRESS"` - `"DONE"` - `updated_at: Optional[datetime]` The timestamp when the message was last updated - `class StreamTaskMessageStart: …` Event for starting a streaming message - `content: TaskMessageContent` - `index: Optional[int]` - `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: str` ID of the task this message belongs to - `id: Optional[str]` The task message's unique id - `created_at: Optional[datetime]` The timestamp when the message was created - `streaming_status: Optional[Literal["IN_PROGRESS", "DONE"]]` - `updated_at: Optional[datetime]` The timestamp when the message was last updated - `type: Optional[Literal["start"]]` - `"start"` - `class StreamTaskMessageDelta: …` Event for streaming chunks of content - `delta: Optional[TaskMessageDelta]` Delta for text updates - `class TextDelta: …` Delta for text updates - `text_delta: Optional[str]` - `type: Optional[Literal["text"]]` - `"text"` - `class DataDelta: …` Delta for data updates - `data_delta: Optional[str]` - `type: Optional[Literal["data"]]` - `"data"` - `class ToolRequestDelta: …` Delta for tool request updates - `name: str` - `tool_call_id: str` - `arguments_delta: Optional[str]` - `type: Optional[Literal["tool_request"]]` - `"tool_request"` - `class ToolResponseDelta: …` Delta for tool response updates - `name: str` - `tool_call_id: str` - `content_delta: Optional[str]` - `type: Optional[Literal["tool_response"]]` - `"tool_response"` - `class ReasoningSummaryDelta: …` Delta for reasoning summary updates - `summary_index: int` - `summary_delta: Optional[str]` - `type: Optional[Literal["reasoning_summary"]]` - `"reasoning_summary"` - `class ReasoningContentDelta: …` Delta for reasoning content updates - `content_index: int` - `content_delta: Optional[str]` - `type: Optional[Literal["reasoning_content"]]` - `"reasoning_content"` - `index: Optional[int]` - `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[Literal["delta"]]` - `"delta"` - `class StreamTaskMessageFull: …` Event for streaming the full content - `content: TaskMessageContent` - `index: Optional[int]` - `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[Literal["full"]]` - `"full"` - `class StreamTaskMessageDone: …` Event for indicating the task is done - `index: Optional[int]` - `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[Literal["done"]]` - `"done"` - `class Task: …` - `id: str` - `cleaned_at: Optional[datetime]` - `created_at: Optional[datetime]` - `name: Optional[str]` - `params: Optional[Dict[str, object]]` - `status: Optional[Literal["CANCELED", "COMPLETED", "FAILED", 5 more]]` - `"CANCELED"` - `"COMPLETED"` - `"FAILED"` - `"RUNNING"` - `"INTERRUPTED"` - `"TERMINATED"` - `"TIMED_OUT"` - `"DELETED"` - `status_reason: Optional[str]` - `task_metadata: Optional[Dict[str, object]]` - `updated_at: Optional[datetime]` - `class Event: …` - `id: str` The UUID of the event - `agent_id: str` The UUID of the agent that the event belongs to - `sequence_id: int` The sequence ID of the event - `task_id: str` The UUID of the task that the event belongs to - `content: Optional[TaskMessageContent]` The content of the event - `created_at: Optional[datetime]` The timestamp of the event - `id: Optional[Union[int, str, null]]` - `int` - `str` - `error: Optional[object]` - `jsonrpc: Optional[Literal["2.0"]]` - `"2.0"` ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) agent_rpc_response = client.agents.deployments.preview_rpc( deployment_id="deployment_id", agent_id="agent_id", method="event/send", params={}, ) print(agent_rpc_response.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" } ``` ## Domain Types ### Deployment Create Response - `class DeploymentCreateResponse: …` - `id: str` The unique identifier of the deployment. - `agent_id: str` The agent this deployment belongs to. - `docker_image: str` Full Docker image URI. - `is_production: bool` Whether this is the production deployment. - `status: Literal["Pending", "Ready", "Failed"]` Current deployment status. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: Optional[str]` ACP URL set when agent registers. - `created_at: Optional[datetime]` When the deployment was created. - `expires_at: Optional[datetime]` When marked for cleanup. - `helm_release_name: Optional[str]` Helm release name for cleanup. - `promoted_at: Optional[datetime]` When promoted to production. - `registration_metadata: Optional[Dict[str, object]]` Git/build metadata from the agent pod. - `sgp_deploy_id: Optional[str]` Correlates to SGP's agentex_deploys.id. ### Deployment List Response - `List[DeploymentListResponseItem]` - `id: str` The unique identifier of the deployment. - `agent_id: str` The agent this deployment belongs to. - `docker_image: str` Full Docker image URI. - `is_production: bool` Whether this is the production deployment. - `status: Literal["Pending", "Ready", "Failed"]` Current deployment status. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: Optional[str]` ACP URL set when agent registers. - `created_at: Optional[datetime]` When the deployment was created. - `expires_at: Optional[datetime]` When marked for cleanup. - `helm_release_name: Optional[str]` Helm release name for cleanup. - `promoted_at: Optional[datetime]` When promoted to production. - `registration_metadata: Optional[Dict[str, object]]` Git/build metadata from the agent pod. - `sgp_deploy_id: Optional[str]` Correlates to SGP's agentex_deploys.id. ### Deployment Retrieve Response - `class DeploymentRetrieveResponse: …` - `id: str` The unique identifier of the deployment. - `agent_id: str` The agent this deployment belongs to. - `docker_image: str` Full Docker image URI. - `is_production: bool` Whether this is the production deployment. - `status: Literal["Pending", "Ready", "Failed"]` Current deployment status. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: Optional[str]` ACP URL set when agent registers. - `created_at: Optional[datetime]` When the deployment was created. - `expires_at: Optional[datetime]` When marked for cleanup. - `helm_release_name: Optional[str]` Helm release name for cleanup. - `promoted_at: Optional[datetime]` When promoted to production. - `registration_metadata: Optional[Dict[str, object]]` Git/build metadata from the agent pod. - `sgp_deploy_id: Optional[str]` Correlates to SGP's agentex_deploys.id. ### Deployment Promote Response - `class DeploymentPromoteResponse: …` - `id: str` The unique identifier of the deployment. - `agent_id: str` The agent this deployment belongs to. - `docker_image: str` Full Docker image URI. - `is_production: bool` Whether this is the production deployment. - `status: Literal["Pending", "Ready", "Failed"]` Current deployment status. - `"Pending"` - `"Ready"` - `"Failed"` - `acp_url: Optional[str]` ACP URL set when agent registers. - `created_at: Optional[datetime]` When the deployment was created. - `expires_at: Optional[datetime]` When marked for cleanup. - `helm_release_name: Optional[str]` Helm release name for cleanup. - `promoted_at: Optional[datetime]` When promoted to production. - `registration_metadata: Optional[Dict[str, object]]` Git/build metadata from the agent pod. - `sgp_deploy_id: Optional[str]` Correlates to SGP's agentex_deploys.id. # Schedules ## Create Run Schedule `agents.schedules.create(stragent_id, ScheduleCreateParams**kwargs) -> ScheduleCreateResponse` **post** `/agents/{agent_id}/schedules` Create a recurring schedule that starts a fresh agent run on each fire. ### Parameters - `agent_id: str` - `initial_input: InitialInput` The first input delivered to each created task. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `name: str` Human-readable name, unique among active schedules for the agent. - `cron_expression: Optional[str]` Cron expression for the cadence (e.g. '0 17 * * MON-FRI'). Mutually exclusive with interval_seconds. - `description: Optional[str]` Optional description of what this schedule does. - `end_at: Optional[Union[str, datetime, null]]` When the schedule should stop being active. - `interval_seconds: Optional[int]` Interval cadence in seconds. Mutually exclusive with cron_expression. - `paused: Optional[bool]` Whether to create the schedule in a paused state. - `start_at: Optional[Union[str, datetime, null]]` When the schedule should start being active. - `task_metadata: Optional[Dict[str, object]]` Metadata copied onto each created task at fire time. - `task_params: Optional[Dict[str, object]]` Resolved config forwarded as task `params` at fire time. - `timezone: Optional[str]` IANA timezone the cron expression is evaluated in (e.g. 'America/New_York'). ### Returns - `class ScheduleCreateResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) schedule = client.agents.schedules.create( agent_id="agent_id", initial_input={ "content": "content" }, name="name", ) print(schedule.id) ``` #### 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 `agents.schedules.list(stragent_id, ScheduleListParams**kwargs) -> ScheduleListResponse` **get** `/agents/{agent_id}/schedules` List run schedules for an agent. ### Parameters - `agent_id: str` - `include_live: Optional[bool]` Include live Temporal state and upcoming action times. - `limit: Optional[int]` ### Returns - `class ScheduleListResponse: …` Response model for listing run schedules. - `run_schedules: List[RunSchedule]` The list of run schedules. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: RunScheduleInitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[RunScheduleCreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. - `total: int` The number of run schedules returned. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) schedules = client.agents.schedules.list( agent_id="agent_id", ) print(schedules.run_schedules) ``` #### 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 `agents.schedules.retrieve(strschedule_id, ScheduleRetrieveParams**kwargs) -> ScheduleRetrieveResponse` **get** `/agents/{agent_id}/schedules/{schedule_id}` Get a run schedule by its id. ### Parameters - `agent_id: str` - `schedule_id: str` ### Returns - `class ScheduleRetrieveResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) schedule = client.agents.schedules.retrieve( schedule_id="schedule_id", agent_id="agent_id", ) print(schedule.id) ``` #### 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 `agents.schedules.update(strschedule_id, ScheduleUpdateParams**kwargs) -> ScheduleUpdateResponse` **patch** `/agents/{agent_id}/schedules/{schedule_id}` Partially update a run schedule's definition (cadence, window, input, etc.). ### Parameters - `agent_id: str` - `schedule_id: str` - `cron_expression: Optional[str]` New cron cadence. Mutually exclusive with interval_seconds. - `description: Optional[str]` Optional description of what this schedule does. - `end_at: Optional[Union[str, datetime, null]]` When the schedule should stop being active. - `initial_input: Optional[InitialInput]` The first input delivered to each freshly created scheduled task. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `interval_seconds: Optional[int]` New interval cadence in seconds. Mutually exclusive with cron_expression. - `name: Optional[str]` Human-readable name, unique among active schedules for the agent. - `paused: Optional[bool]` Pause/resume the schedule as part of the update. - `start_at: Optional[Union[str, datetime, null]]` When the schedule should start being active. - `task_metadata: Optional[Dict[str, object]]` Metadata copied onto each created task at fire time. - `task_params: Optional[Dict[str, object]]` Resolved config forwarded as task `params` at fire time. - `timezone: Optional[str]` IANA timezone the cron expression is evaluated in. ### Returns - `class ScheduleUpdateResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) schedule = client.agents.schedules.update( schedule_id="schedule_id", agent_id="agent_id", ) print(schedule.id) ``` #### 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 `agents.schedules.delete(strschedule_id, ScheduleDeleteParams**kwargs) -> DeleteResponse` **delete** `/agents/{agent_id}/schedules/{schedule_id}` Delete a run schedule permanently. ### Parameters - `agent_id: str` - `schedule_id: str` ### Returns - `class DeleteResponse: …` - `id: str` - `message: str` ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) delete_response = client.agents.schedules.delete( schedule_id="schedule_id", agent_id="agent_id", ) print(delete_response.id) ``` #### Response ```json { "id": "id", "message": "message" } ``` ## Pause Run Schedule `agents.schedules.pause(strschedule_id, SchedulePauseParams**kwargs) -> SchedulePauseResponse` **post** `/agents/{agent_id}/schedules/{schedule_id}/pause` Pause a run schedule so it stops firing. ### Parameters - `agent_id: str` - `schedule_id: str` - `note: Optional[str]` Optional note explaining the pause. ### Returns - `class SchedulePauseResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) response = client.agents.schedules.pause( schedule_id="schedule_id", agent_id="agent_id", ) print(response.id) ``` #### 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 `agents.schedules.resume(strschedule_id, ScheduleResumeParams**kwargs) -> ScheduleResumeResponse` **post** `/agents/{agent_id}/schedules/{schedule_id}/resume` Resume a paused run schedule so it fires again. ### Parameters - `agent_id: str` - `schedule_id: str` - `note: Optional[str]` Optional note explaining the resume. ### Returns - `class ScheduleResumeResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) response = client.agents.schedules.resume( schedule_id="schedule_id", agent_id="agent_id", ) print(response.id) ``` #### 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 `agents.schedules.trigger(strschedule_id, ScheduleTriggerParams**kwargs) -> ScheduleTriggerResponse` **post** `/agents/{agent_id}/schedules/{schedule_id}/trigger` Trigger an immediate, out-of-band run of the schedule (in addition to its cadence). ### Parameters - `agent_id: str` - `schedule_id: str` ### Returns - `class ScheduleTriggerResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) response = client.agents.schedules.trigger( schedule_id="schedule_id", agent_id="agent_id", ) print(response.id) ``` #### 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 `agents.schedules.skip(strschedule_id, ScheduleSkipParams**kwargs) -> ScheduleSkipResponse` **post** `/agents/{agent_id}/schedules/{schedule_id}/skip` Skip a recurring fire of the schedule. ### Parameters - `agent_id: str` - `schedule_id: str` - `scheduled_time: Union[str, datetime]` Specific scheduled fire time to skip. ### Returns - `class ScheduleSkipResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from datetime import datetime from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) response = client.agents.schedules.skip( schedule_id="schedule_id", agent_id="agent_id", scheduled_time=datetime.fromisoformat("2019-12-27T18:11:19.117"), ) print(response.id) ``` #### 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 `agents.schedules.unskip(strschedule_id, ScheduleUnskipParams**kwargs) -> ScheduleUnskipResponse` **post** `/agents/{agent_id}/schedules/{schedule_id}/unskip` Remove a skip for a recurring fire of the schedule. ### Parameters - `agent_id: str` - `schedule_id: str` - `scheduled_time: Union[str, datetime]` Specific scheduled fire time to unskip. ### Returns - `class ScheduleUnskipResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from datetime import datetime from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) response = client.agents.schedules.unskip( schedule_id="schedule_id", agent_id="agent_id", scheduled_time=datetime.fromisoformat("2019-12-27T18:11:19.117"), ) print(response.id) ``` #### 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 `agents.schedules.retrieve_by_name(strname, ScheduleRetrieveByNameParams**kwargs) -> ScheduleRetrieveByNameResponse` **get** `/agents/{agent_id}/schedules/name/{name}` Get a run schedule by its active name. ### Parameters - `agent_id: str` - `name: str` ### Returns - `class ScheduleRetrieveByNameResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) response = client.agents.schedules.retrieve_by_name( name="name", agent_id="agent_id", ) print(response.id) ``` #### 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 `agents.schedules.update_by_name(strpath_name, ScheduleUpdateByNameParams**kwargs) -> ScheduleUpdateByNameResponse` **patch** `/agents/{agent_id}/schedules/name/{name}` Partially update a run schedule's definition by its active name. ### Parameters - `agent_id: str` - `name: str` - `cron_expression: Optional[str]` New cron cadence. Mutually exclusive with interval_seconds. - `description: Optional[str]` Optional description of what this schedule does. - `end_at: Optional[Union[str, datetime, null]]` When the schedule should stop being active. - `initial_input: Optional[InitialInput]` The first input delivered to each freshly created scheduled task. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `interval_seconds: Optional[int]` New interval cadence in seconds. Mutually exclusive with cron_expression. - `name: str` - `paused: Optional[bool]` Pause/resume the schedule as part of the update. - `start_at: Optional[Union[str, datetime, null]]` When the schedule should start being active. - `task_metadata: Optional[Dict[str, object]]` Metadata copied onto each created task at fire time. - `task_params: Optional[Dict[str, object]]` Resolved config forwarded as task `params` at fire time. - `timezone: Optional[str]` IANA timezone the cron expression is evaluated in. ### Returns - `class ScheduleUpdateByNameResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) response = client.agents.schedules.update_by_name( path_name="name", agent_id="agent_id", ) print(response.id) ``` #### 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 `agents.schedules.delete_by_name(strname, ScheduleDeleteByNameParams**kwargs) -> DeleteResponse` **delete** `/agents/{agent_id}/schedules/name/{name}` Delete a run schedule by its active name. ### Parameters - `agent_id: str` - `name: str` ### Returns - `class DeleteResponse: …` - `id: str` - `message: str` ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) delete_response = client.agents.schedules.delete_by_name( name="name", agent_id="agent_id", ) print(delete_response.id) ``` #### Response ```json { "id": "id", "message": "message" } ``` ## Pause Run Schedule By Name `agents.schedules.pause_by_name(strname, SchedulePauseByNameParams**kwargs) -> SchedulePauseByNameResponse` **post** `/agents/{agent_id}/schedules/name/{name}/pause` Pause a run schedule by its active name. ### Parameters - `agent_id: str` - `name: str` - `note: Optional[str]` Optional note explaining the pause. ### Returns - `class SchedulePauseByNameResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) response = client.agents.schedules.pause_by_name( name="name", agent_id="agent_id", ) print(response.id) ``` #### 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 `agents.schedules.resume_by_name(strname, ScheduleResumeByNameParams**kwargs) -> ScheduleResumeByNameResponse` **post** `/agents/{agent_id}/schedules/name/{name}/resume` Resume a paused run schedule by its active name. ### Parameters - `agent_id: str` - `name: str` - `note: Optional[str]` Optional note explaining the resume. ### Returns - `class ScheduleResumeByNameResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) response = client.agents.schedules.resume_by_name( name="name", agent_id="agent_id", ) print(response.id) ``` #### 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 `agents.schedules.trigger_by_name(strname, ScheduleTriggerByNameParams**kwargs) -> ScheduleTriggerByNameResponse` **post** `/agents/{agent_id}/schedules/name/{name}/trigger` Trigger an immediate, out-of-band run of the schedule by its active name. ### Parameters - `agent_id: str` - `name: str` ### Returns - `class ScheduleTriggerByNameResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Example ```python import os from agentex import Agentex client = Agentex( api_key=os.environ.get("AGENTEX_SDK_API_KEY"), # This is the default and can be omitted ) response = client.agents.schedules.trigger_by_name( name="name", agent_id="agent_id", ) print(response.id) ``` #### 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 - `class ScheduleCreateResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Schedule List Response - `class ScheduleListResponse: …` Response model for listing run schedules. - `run_schedules: List[RunSchedule]` The list of run schedules. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: RunScheduleInitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[RunScheduleCreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. - `total: int` The number of run schedules returned. ### Schedule Retrieve Response - `class ScheduleRetrieveResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Schedule Update Response - `class ScheduleUpdateResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Schedule Pause Response - `class SchedulePauseResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Schedule Resume Response - `class ScheduleResumeResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Schedule Trigger Response - `class ScheduleTriggerResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Schedule Skip Response - `class ScheduleSkipResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Schedule Unskip Response - `class ScheduleUnskipResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Schedule Retrieve By Name Response - `class ScheduleRetrieveByNameResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Schedule Update By Name Response - `class ScheduleUpdateByNameResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Schedule Pause By Name Response - `class SchedulePauseByNameResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Schedule Resume By Name Response - `class ScheduleResumeByNameResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated. ### Schedule Trigger By Name Response - `class ScheduleTriggerByNameResponse: …` Response model describing a scheduled agent run. - `id: str` The unique identifier of the run schedule. - `agent_id: str` The agent this schedule belongs to. - `initial_input: InitialInput` The initial input. - `content: str` The initial prompt delivered to the task. - `author: Optional[MessageAuthor]` The author attributed to the initial input. - `"user"` - `"agent"` - `type: Optional[Literal["text"]]` Input content type. - `"text"` - `initial_input_method: str` Delivery method, inferred from the agent's ACP type. - `name: str` Human-readable schedule name. - `created_at: Optional[datetime]` When the schedule was created. - `creator_principal: Optional[CreatorPrincipal]` 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[str]` Account/workspace id of the creator. - `principal_type: Optional[str]` e.g. 'user' or 'service_account'. - `service_account_id: Optional[str]` Creator service-account id, if a service principal. - `user_id: Optional[str]` Creator user id, if a user principal. - `cron_expression: Optional[str]` Cron cadence, if cron-based. - `description: Optional[str]` Optional description. - `end_at: Optional[datetime]` Schedule deactivation time. - `interval_seconds: Optional[int]` Interval cadence in seconds, if interval-based. - `last_action_time: Optional[datetime]` When the schedule last fired. - `live_data_available: Optional[bool]` Whether requested live Temporal fields were retrieved successfully. Null when live enrichment was not requested. - `next_action_times: Optional[List[datetime]]` Upcoming scheduled fire times. - `num_actions_taken: Optional[int]` Number of times the schedule has fired. - `paused: Optional[bool]` Whether the schedule is paused. - `skipped_action_times: Optional[List[datetime]]` Skipped one-off scheduled fire times. - `start_at: Optional[datetime]` Schedule activation time. - `state: Optional[Literal["ACTIVE", "PAUSED"]]` Live schedule state from Temporal. - `"ACTIVE"` - `"PAUSED"` - `task_metadata: Optional[Dict[str, object]]` Task metadata at fire time. - `task_params: Optional[Dict[str, object]]` Task params at fire time. - `timezone: Optional[str]` Timezone the cron expression is evaluated in. - `updated_at: Optional[datetime]` When the schedule was updated.