haive.games.chess.configurable_config
=====================================

.. py:module:: haive.games.chess.configurable_config

.. autoapi-nested-parse::

   Configurable chess agent configuration using player agents.

   This module provides a chess configuration that supports configurable player agents
   instead of hardcoded engine configurations.



Classes
-------

.. autoapisummary::

   haive.games.chess.configurable_config.ConfigurableChessConfig


Functions
---------

.. autoapisummary::

   haive.games.chess.configurable_config.create_chess_config
   haive.games.chess.configurable_config.create_chess_config_from_example
   haive.games.chess.configurable_config.create_chess_config_from_player_configs


Module Contents
---------------

.. py:class:: ConfigurableChessConfig

   Bases: :py:obj:`haive.core.engine.agent.agent.AgentConfig`


   Configurable chess agent configuration.

   This configuration supports using different LLM configurations for
   different players without hardcoding them in engines.

   .. rubric:: Examples

   >>> # Simple string-based configuration
   >>> config = ConfigurableChessConfig(
   ...     white_model="gpt-4",
   ...     black_model="claude-3-opus"
   ... )

   >>> # Using player agent configs
   >>> config = ConfigurableChessConfig(
   ...     player_configs={
   ...         "white_player": PlayerAgentConfig(llm_config="gpt-4"),
   ...         "black_player": PlayerAgentConfig(llm_config="claude-3-opus"),
   ...     }
   ... )

   >>> # Using example configuration
   >>> config = ConfigurableChessConfig(
   ...     example_config="anthropic_vs_openai"
   ... )


   .. py:class:: Config

      Pydantic configuration.



   .. py:method:: configure_engines_and_names()

      Configure engines from the provided player configurations.



.. py:function:: create_chess_config(white_model = 'gpt-4o', black_model = 'claude-3-5-sonnet-20240620', temperature = 0.7, enable_analysis = True, **kwargs)

   Create a chess configuration with simple model strings.

   :param white_model: Model for white player
   :param black_model: Model for black player
   :param temperature: Temperature for all engines
   :param enable_analysis: Whether to enable position analysis
   :param \*\*kwargs: Additional configuration parameters

   :returns: Configured chess agent
   :rtype: ConfigurableChessConfig

   .. rubric:: Example

   >>> config = create_chess_config("gpt-4", "claude-3-opus", temperature=0.8)


.. py:function:: create_chess_config_from_example(example_name, enable_analysis = True, **kwargs)

   Create a chess configuration from an example.

   :param example_name: Name of the example configuration
   :param enable_analysis: Whether to enable position analysis
   :param \*\*kwargs: Additional configuration parameters

   :returns: Configured chess agent
   :rtype: ConfigurableChessConfig

   Available examples: anthropic_vs_openai, gpt4_only, claude_only,
                      mixed_providers, budget_friendly

   .. rubric:: Example

   >>> config = create_chess_config_from_example("budget_friendly")


.. py:function:: create_chess_config_from_player_configs(player_configs, enable_analysis = True, **kwargs)

   Create a chess configuration from player agent configurations.

   :param player_configs: Dictionary of role to player configuration
   :param enable_analysis: Whether to enable position analysis
   :param \*\*kwargs: Additional configuration parameters

   :returns: Configured chess agent
   :rtype: ConfigurableChessConfig

   .. rubric:: Example

   >>> configs = {
   ...     "white_player": create_player_config("gpt-4", player_name="Deep Blue"),
   ...     "black_player": create_player_config("claude-3-opus", player_name="AlphaZero"),
   ... }
   >>> config = create_chess_config_from_player_configs(configs)