"""Functions for counting the number of tokens in a message or string."""
from __future__ import annotations

from typing import List
import json

import tiktoken_async


async def count_message_tokens(
        messages: List[dict], model: str = "gpt-3.5-turbo-0301"
) -> int:
    """
    Returns the number of tokens used by a list of messages.

    Args:
        messages (list): A list of messages, each of which is a dictionary
            containing the role and content of the message.
        model (str): The name of the model to use for tokenization.
            Defaults to "gpt-3.5-turbo-0301".

    Returns:
        int: The number of tokens used by the list of messages.
    """
    try:
        encoding = await tiktoken_async.encoding_for_model(model)
    except KeyError:
        print("Warning: model not found. Using cl100k_base encoding.")
        encoding = await tiktoken_async.get_encoding("cl100k_base")
    if model == "gpt-3.5-turbo":
        # !Note: gpt-3.5-turbo may change over time.
        # Returning num tokens assuming Mgpt-3.5-turbo-0301.")
        return await count_message_tokens(messages, model="gpt-3.5-turbo-0301")
    elif model == "gpt-4":
        # !Note: gpt-4 may change over time. Returning num tokens assuming gpt-4-0314.")
        return await count_message_tokens(messages, model="gpt-4-0314")
    # TODO: OpenAI has not mention how to count tokens for 0613, thus, we use the former method
    elif model == "gpt-3.5-turbo-0301" or model == "gpt-3.5-turbo-0613" or model == "gpt-3.5-turbo-16k-0613":
        tokens_per_message = (
            4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
        )
        tokens_per_name = -1  # if there's a name, the role is omitted
    elif model == "gpt-4-0314":
        tokens_per_message = 3
        tokens_per_name = 1
    else:
        raise NotImplementedError(
            f"num_tokens_from_messages() is not implemented for model {model}.\n"
            " See https://github.com/openai/openai-python/blob/main/chatml.md for"
            " information on how messages are converted to tokens."
        )
    num_tokens = 0
    for message in messages:
        num_tokens += tokens_per_message
        for key, value in message.items():
            if not isinstance(value, str):
                # TODO: Since openai does not mentioned how to count tokens of 'funciton_call',
                #   and only string is countable, thus, if the value is not a `str` (`function_call`
                #   field of a message), we convert it into json
                value = json.dumps(value)
            num_tokens += len(encoding.encode(value))
            if key == "name":
                num_tokens += tokens_per_name
    num_tokens += 3  # every reply is primed with <|start|>assistant<|message|>
    return num_tokens


async def count_string_tokens(string: str, model_name: str) -> int:
    """
    Returns the number of tokens in a text string.

    Args:
        string (str): The text string.
        model_name (str): The name of the encoding to use. (e.g., "gpt-3.5-turbo")

    Returns:
        int: The number of tokens in the text string.
    """
    encoding = await tiktoken_async.encoding_for_model(model_name)
    return len(encoding.encode(string))