user_proxy_agent.py

from typing import Callable, Dict, List, Literal, Optional, Union

from ..runtime_logging import log_new_agent, logging_enabled
from .conversable_agent import ConversableAgent


class UserProxyAgent(ConversableAgent):
    """(In preview) A proxy agent for the user, that can execute code and provide feedback to the other agents.

    UserProxyAgent is a subclass of ConversableAgent configured with `human_input_mode` to ALWAYS
    and `llm_config` to False. By default, the agent will prompt for human input every time a message is received.
    Code execution is enabled by default. LLM-based auto reply is disabled by default.
    To modify auto reply, register a method with [`register_reply`](conversable_agent#register_reply).
    To modify the way to get human input, override `get_human_input` method.
    To modify the way to execute code blocks, single code block, or function call, override `execute_code_blocks`,
    `run_code`, and `execute_function` methods respectively.
    """

    # Default UserProxyAgent.description values, based on human_input_mode
    DEFAULT_USER_PROXY_AGENT_DESCRIPTIONS = {
        "ALWAYS": "An attentive HUMAN user who can answer questions about the task, and can perform tasks such as running Python code or inputting command line commands at a Linux terminal and reporting back the execution results.",
        "TERMINATE": "A user that can run Python code or input command line commands at a Linux terminal and report back the execution results.",
        "NEVER": "A computer terminal that performs no other action than running Python scripts (provided to it quoted in ```python code blocks), or sh shell scripts (provided to it quoted in ```sh code blocks).",
    }

    def __init__(
        self,
        name: str,
        is_termination_msg: Optional[Callable[[Dict], bool]] = None,
        max_consecutive_auto_reply: Optional[int] = None,
        human_input_mode: Literal["ALWAYS", "TERMINATE", "NEVER"] = "ALWAYS",
        function_map: Optional[Dict[str, Callable]] = None,
        code_execution_config: Union[Dict, Literal[False]] = {},
        default_auto_reply: Optional[Union[str, Dict, None]] = "",
        llm_config: Optional[Union[Dict, Literal[False]]] = False,
        system_message: Optional[Union[str, List]] = "",
        description: Optional[str] = None,
    ):
        """
        Args:
            name (str): name of the agent.
            is_termination_msg (function): a function that takes a message in the form of a dictionary
                and returns a boolean value indicating if this received message is a termination message.
                The dict can contain the following keys: "content", "role", "name", "function_call".
            max_consecutive_auto_reply (int): the maximum number of consecutive auto replies.
                default to None (no limit provided, class attribute MAX_CONSECUTIVE_AUTO_REPLY will be used as the limit in this case).
                The limit only plays a role when human_input_mode is not "ALWAYS".
            human_input_mode (str): whether to ask for human inputs every time a message is received.
                Possible values are "ALWAYS", "TERMINATE", "NEVER".
                (1) When "ALWAYS", the agent prompts for human input every time a message is received.
                    Under this mode, the conversation stops when the human input is "exit",
                    or when is_termination_msg is True and there is no human input.
                (2) When "TERMINATE", the agent only prompts for human input only when a termination message is received or
                    the number of auto reply reaches the max_consecutive_auto_reply.
                (3) When "NEVER", the agent will never prompt for human input. Under this mode, the conversation stops
                    when the number of auto reply reaches the max_consecutive_auto_reply or when is_termination_msg is True.
            function_map (dict[str, callable]): Mapping function names (passed to openai) to callable functions.
            code_execution_config (dict or False): config for the code execution.
                To disable code execution, set to False. Otherwise, set to a dictionary with the following keys:
                - work_dir (Optional, str): The working directory for the code execution.
                    If None, a default working directory will be used.
                    The default working directory is the "extensions" directory under
                    "path_to_autogen".
                - use_docker (Optional, list, str or bool): The docker image to use for code execution.
                    Default is True, which means the code will be executed in a docker container. A default list of images will be used.
                    If a list or a str of image name(s) is provided, the code will be executed in a docker container
                    with the first image successfully pulled.
                    If False, the code will be executed in the current environment.
                    We strongly recommend using docker for code execution.
                - timeout (Optional, int): The maximum execution time in seconds.
                - last_n_messages (Experimental, Optional, int): The number of messages to look back for code execution. Default to 1.
            default_auto_reply (str or dict or None): the default auto reply message when no code execution or llm based reply is generated.
            llm_config (dict or False or None): llm inference configuration.
                Please refer to [OpenAIWrapper.create](/docs/reference/oai/client#create)
                for available options.
                Default to False, which disables llm-based auto reply.
                When set to None, will use self.DEFAULT_CONFIG, which defaults to False.
            system_message (str or List): system message for ChatCompletion inference.
                Only used when llm_config is not False. Use it to reprogram the agent.
            description (str): a short description of the agent. This description is used by other agents
                (e.g. the GroupChatManager) to decide when to call upon this agent. (Default: system_message)
        """
        super().__init__(
            name=name,
            system_message=system_message,
            is_termination_msg=is_termination_msg,
            max_consecutive_auto_reply=max_consecutive_auto_reply,
            human_input_mode=human_input_mode,
            function_map=function_map,
            code_execution_config=code_execution_config,
            llm_config=llm_config,
            default_auto_reply=default_auto_reply,
            description=(
                description if description is not None else self.DEFAULT_USER_PROXY_AGENT_DESCRIPTIONS[human_input_mode]
            ),
        )

        if logging_enabled():
            log_new_agent(self, locals())