autogen.SwarmAgent

​

SwarmAgent

SwarmAgent(
    name: str,
    system_message: str | None = 'You are a helpful AI Assistant.',
    llm_config: dict | Literal[False] | None = None,
    functions: list[typing.Callable] | Callable = None,
    is_termination_msg: Callable[[dict], bool] | None = None,
    max_consecutive_auto_reply: int | None = None,
    human_input_mode: Literal['ALWAYS', 'NEVER', 'TERMINATE'] = 'NEVER',
    description: str | None = None,
    code_execution_config=False,
    update_agent_state_before_reply: list[Callable | autogen.UPDATE_SYSTEM_MESSAGE] | Callable | autogen.UPDATE_SYSTEM_MESSAGE | None = None,
    **kwargs
)

Swarm agent for participating in a swarm.

SwarmAgent is a subclass of ConversableAgent.

Additional args: functions (List[Callable]): A list of functions to register with the agent. update_agent_state_before_reply (List[Callable]): A list of functions, including UPDATE_SYSTEM_MESSAGEs, called to update the agent before it replies.

​

Static Methods

​

process_nested_chat_carryover

process_nested_chat_carryover(
    chat: dict[str, typing.Any],
    recipient: autogen.ConversableAgent,
    messages: list[dict[str, typing.Any]],
    sender: autogen.ConversableAgent,
    config: Any,
    trim_n_messages: int = 0
) -> None

Process carryover messages for a nested chat (typically for the first chat of a swarm)

The carryover_config key is a dictionary containing: “summary_method”: The method to use to summarise the messages, can be “all”, “last_msg”, “reflection_with_llm” or a Callable “summary_args”: Optional arguments for the summary method

Supported carryover ‘summary_methods’ are: “all” - all messages will be incorporated “last_msg” - the last message will be incorporated “reflection_with_llm” - an llm will summarise all the messages and the summary will be incorporated as a single message Callable - a callable with the signature: my_method(agent: ConversableAgent, messages: List[Dict[str, Any]]) -> str

​

Instance Methods

​

add_functions

add_functions(self, func_list: list[typing.Callable]) -> 

​

add_single_function

add_single_function(
    self,
    func: Callable,
    name=None,
    description=''
) -> 

Add a single function to the agent, removing context variables for LLM use

​

generate_swarm_tool_reply

generate_swarm_tool_reply(
    self,
    messages: list[dict] | None = None,
    sender: autogen.Agent | None = None,
    config: autogen.OpenAIWrapper | None = None
) -> tuple[bool, dict]

Pre-processes and generates tool call replies.

This function:

1. Adds context_variables back to the tool call for the function, if necessary.
2. Generates the tool calls reply.
3. Updates context_variables and next_agent based on the tool call response.

​

register_hand_off

register_hand_off(self, hand_to: list[autogen.ON_CONDITION | autogen.AFTER_WORK] | autogen.ON_CONDITION | autogen.AFTER_WORK) -> 

Register a function to hand off to another agent.

​

register_update_agent_state_before_reply

register_update_agent_state_before_reply(self, functions: list[typing.Callable] | Callable | None) -> 

Register functions that will be called when the agent is selected and before it speaks. You can add your own validation or precondition functions here.