import re
from typing import Any, Union

from langchain.agents.output_parsers import ReActSingleInputOutputParser
from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.exceptions import OutputParserException

from crewai.utilities import I18N

FINAL_ANSWER_ACTION = "Final Answer:"
MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE = "I did it wrong. Invalid Format: I missed the 'Action:' after 'Thought:'. I will do right next, and don't use a tool I have already used.\n"
MISSING_ACTION_INPUT_AFTER_ACTION_ERROR_MESSAGE = "I did it wrong. Invalid Format: I missed the 'Action Input:' after 'Action:'. I will do right next, and don't use a tool I have already used.\n"
FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE = "I did it wrong. Tried to both perform Action and give a Final Answer at the same time, I must do one or the other"


class CrewAgentParser(ReActSingleInputOutputParser):
    """Parses ReAct-style LLM calls that have a single tool input.

    Expects output to be in one of two formats.

    If the output signals that an action should be taken,
    should be in the below format. This will result in an AgentAction
    being returned.

    Thought: agent thought here
    Action: search
    Action Input: what is the temperature in SF?

    If the output signals that a final answer should be given,
    should be in the below format. This will result in an AgentFinish
    being returned.

    Thought: agent thought here
    Final Answer: The temperature is 100 degrees
    """

    _i18n: I18N = I18N()
    agent: Any = None

    def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
        includes_answer = FINAL_ANSWER_ACTION in text
        regex = (
            r"Action\s*\d*\s*:[\s]*(.*?)[\s]*Action\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)"
        )
        action_match = re.search(regex, text, re.DOTALL)
        if action_match:
            if includes_answer:
                raise OutputParserException(
                    f"{FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE}: {text}"
                )
            action = action_match.group(1).strip()
            action_input = action_match.group(2)
            tool_input = action_input.strip(" ")
            tool_input = tool_input.strip('"')
            return AgentAction(action, tool_input, text)

        elif includes_answer:
            return AgentFinish(
                {"output": text.split(FINAL_ANSWER_ACTION)[-1].strip()}, text
            )

        if not re.search(r"Action\s*\d*\s*:[\s]*(.*?)", text, re.DOTALL):
            self.agent.increment_formatting_errors()
            raise OutputParserException(
                f"Could not parse LLM output: `{text}`",
                observation=f"{MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE}\n{self._i18n.slice('final_answer_format')}",
                llm_output=text,
                send_to_llm=True,
            )
        elif not re.search(
            r"[\s]*Action\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)", text, re.DOTALL
        ):
            self.agent.increment_formatting_errors()
            raise OutputParserException(
                f"Could not parse LLM output: `{text}`",
                observation=MISSING_ACTION_INPUT_AFTER_ACTION_ERROR_MESSAGE,
                llm_output=text,
                send_to_llm=True,
            )
        else:
            format = self._i18n.slice("format_without_tools")
            error = f"{format}"
            self.agent.increment_formatting_errors()
            raise OutputParserException(
                error,
                observation=error,
                llm_output=text,
                send_to_llm=True,
            )