anthropic[major]: support python 3.13 (#27916)

Last week Anthropic released version 0.39.0 of its python sdk, which
enabled support for Python 3.13. This release deleted a legacy
`client.count_tokens` method, which we currently access during init of
the `Anthropic` LLM. Anthropic has replaced this functionality with the
[client.beta.messages.count_tokens()
API](https://github.com/anthropics/anthropic-sdk-python/pull/726).

To enable support for `anthropic >= 0.39.0` and Python 3.13, here we
drop support for the legacy token counting method, and add support for
the new method via `ChatAnthropic.get_num_tokens_from_messages`.

To fully support the token counting API, we update the signature of
`get_num_tokens_from_message` to accept tools everywhere.

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>

libs/langchain/tests/unit_tests/chat_models/test_base.py

@@ -3,7 +3,6 @@ from unittest import mock
 
 import pytest
 from langchain_core.language_models import BaseChatModel
-from langchain_core.messages import HumanMessage
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_core.runnables import RunnableConfig, RunnableSequence
 from pydantic import SecretStr
@@ -180,9 +179,6 @@ def test_configurable_with_default() -> None:
     )
 
     assert model_with_config.model == "claude-3-sonnet-20240229"  # type: ignore[attr-defined]
-    # Anthropic defaults to using `transformers` for token counting.
-    with pytest.raises(ImportError):
-        model_with_config.get_num_tokens_from_messages([(HumanMessage("foo"))])  # type: ignore[attr-defined]
 
     assert model_with_config.model_dump() == {  # type: ignore[attr-defined]
         "name": None,