OpenHands/agenthub/browsing_agent/response_parser.py

import ast

from openhands.controller.action_parser import ActionParser, ResponseParser
from openhands.core.logger import openhands_logger as logger
from openhands.events.action import (
    Action,
    BrowseInteractiveAction,
)


class BrowsingResponseParser(ResponseParser):
    def __init__(self):
        # Need to pay attention to the item order in self.action_parsers
        super().__init__()
        self.action_parsers = [BrowsingActionParserMessage()]
        self.default_parser = BrowsingActionParserBrowseInteractive()

    def parse(self, response: str) -> Action:
        action_str = self.parse_response(response)
        return self.parse_action(action_str)

    def parse_response(self, response) -> str:
        action_str = response['choices'][0]['message']['content']
        if action_str is None:
            return ''
        action_str = action_str.strip()
        if not action_str.endswith('```'):
            action_str = action_str + ')```'
        logger.info(action_str)
        return action_str

    def parse_action(self, action_str: str) -> Action:
        for action_parser in self.action_parsers:
            if action_parser.check_condition(action_str):
                return action_parser.parse(action_str)
        return self.default_parser.parse(action_str)


class BrowsingActionParserMessage(ActionParser):
    """Parser action:
    - BrowseInteractiveAction(browser_actions) - unexpected response format, message back to user
    """

    def __init__(
        self,
    ):
        pass

    def check_condition(self, action_str: str) -> bool:
        return '```' not in action_str

    def parse(self, action_str: str) -> Action:
        msg = f'send_msg_to_user("""{action_str}""")'
        return BrowseInteractiveAction(
            browser_actions=msg,
            thought=action_str,
            browsergym_send_msg_to_user=action_str,
        )


class BrowsingActionParserBrowseInteractive(ActionParser):
    """Parser action:
    - BrowseInteractiveAction(browser_actions) - handle send message to user function call in BrowserGym
    """

    def __init__(
        self,
    ):
        pass

    def check_condition(self, action_str: str) -> bool:
        return True

    def parse(self, action_str: str) -> Action:
        thought = action_str.split('```')[0].strip()
        action_str = action_str.split('```')[1].strip()
        msg_content = ''
        for sub_action in action_str.split('\n'):
            if 'send_msg_to_user(' in sub_action:
                tree = ast.parse(sub_action)
                args = tree.body[0].value.args  # type: ignore
                msg_content = args[0].value

        return BrowseInteractiveAction(
            browser_actions=action_str,
            thought=thought,
            browsergym_send_msg_to_user=msg_content,
        )