OpenHands/openhands/agenthub/codeact_swe_agent/action_parser.py

import re

from openhands.controller.action_parser import ActionParser
from openhands.events.action import (
    Action,
    AgentFinishAction,
    CmdRunAction,
    IPythonRunCellAction,
    MessageAction,
)


class CodeActSWEActionParserFinish(ActionParser):
    """Parser action:
    - AgentFinishAction() - end the interaction
    """

    def __init__(
        self,
    ):
        self.finish_command = None

    def check_condition(self, action_str: str) -> bool:
        self.finish_command = re.search(r'<finish>.*</finish>', action_str, re.DOTALL)
        return self.finish_command is not None

    def parse(self, action_str: str) -> Action:
        assert (
            self.finish_command is not None
        ), 'self.finish_command should not be None when parse is called'
        thought = action_str.replace(self.finish_command.group(0), '').strip()
        return AgentFinishAction(thought=thought)


class CodeActSWEActionParserCmdRun(ActionParser):
    """Parser action:
    - CmdRunAction(command) - bash command to run
    - AgentFinishAction() - end the interaction
    """

    def __init__(
        self,
    ):
        self.bash_command = None

    def check_condition(self, action_str: str) -> bool:
        self.bash_command = re.search(
            r'<execute_bash>(.*?)</execute_bash>', action_str, re.DOTALL
        )
        return self.bash_command is not None

    def parse(self, action_str: str) -> Action:
        assert (
            self.bash_command is not None
        ), 'self.bash_command should not be None when parse is called'
        thought = action_str.replace(self.bash_command.group(0), '').strip()
        # a command was found
        command_group = self.bash_command.group(1).strip()
        if command_group.strip() == 'exit':
            return AgentFinishAction()
        return CmdRunAction(command=command_group, thought=thought)


class CodeActSWEActionParserIPythonRunCell(ActionParser):
    """Parser action:
    - IPythonRunCellAction(code) - IPython code to run
    """

    def __init__(
        self,
    ):
        self.python_code = None
        self.jupyter_kernel_init_code: str = 'from agentskills import *'

    def check_condition(self, action_str: str) -> bool:
        self.python_code = re.search(
            r'<execute_ipython>(.*?)</execute_ipython>', action_str, re.DOTALL
        )
        return self.python_code is not None

    def parse(self, action_str: str) -> Action:
        assert (
            self.python_code is not None
        ), 'self.python_code should not be None when parse is called'
        code_group = self.python_code.group(1).strip()
        thought = action_str.replace(self.python_code.group(0), '').strip()
        return IPythonRunCellAction(
            code=code_group,
            thought=thought,
            kernel_init_code=self.jupyter_kernel_init_code,
        )


class CodeActSWEActionParserMessage(ActionParser):
    """Parser action:
    - MessageAction(content) - Message action to run (e.g. ask for clarification)
    """

    def __init__(
        self,
    ):
        pass

    def check_condition(self, action_str: str) -> bool:
        # We assume the LLM is GOOD enough that when it returns pure natural language
        # it wants to talk to the user
        return True

    def parse(self, action_str: str) -> Action:
        return MessageAction(content=action_str, wait_for_response=True)