haive.games.chess.config
========================

.. py:module:: haive.games.chess.config

.. autoapi-nested-parse::

   Chess agent configuration module.

   from typing import Any
   This module provides configuration classes for chess agents, including:
       - Core game parameters
       - LLM engine settings
       - Analysis options
       - Visualization settings
       - State schema definition

   The configuration system uses Pydantic for validation and default values,
   making it easy to create and customize chess agent instances.



Classes
-------

.. autoapisummary::

   haive.games.chess.config.ChessConfig


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

.. py:class:: ChessConfig

   Bases: :py:obj:`haive.games.core.config.BaseGameConfig`


   Configuration class for chess game agents.

   This class defines all configuration parameters for a chess agent,
   including state schema, LLM engines, game settings, and visualization
   options.

   .. attribute:: state_schema

      The state schema for the game.

      :type: Type[ChessState]

   .. attribute:: white_player_name

      Name of the white player.

      :type: str

   .. attribute:: black_player_name

      Name of the black player.

      :type: str

   .. attribute:: enable_analysis

      Whether to enable position analysis during gameplay.

      :type: bool

   .. attribute:: should_visualize_graph

      Whether to visualize the game workflow graph.

      :type: bool

   .. attribute:: max_moves

      Maximum number of moves before forcing a draw.

      :type: int

   .. attribute:: engines

      LLM configurations for players and analyzers.

      :type: Dict[str, AugLLMConfig]

   .. attribute:: runnable_config

      Runtime configuration for the agent.

      :type: Dict[str, Any]

   .. rubric:: Examples

   >>> # Create a basic configuration
   >>> config = ChessConfig()
   >>>
   >>> # Create a configuration with analysis disabled
   >>> config = ChessConfig(enable_analysis=False)
   >>>
   >>> # Create a configuration with custom LLM engines
   >>> from haive.core.engine.aug_llm import build_aug_llm
   >>> engines = {
   ...     "white_player": build_aug_llm("openai", "gpt-4"),
   ...     "black_player": build_aug_llm("anthropic", "claude-3-opus-20240229"),
   ... }
   >>> config = ChessConfig(engines=engines)


   .. py:class:: Config

      Pydantic configuration.

      This inner class configures Pydantic behavior for the ChessAgentConfig.

      .. attribute:: arbitrary_types_allowed

         Whether to allow arbitrary types in the model.

         :type: bool



   .. py:method:: build_legacy_engines()

      Build legacy hardcoded engines.



   .. py:method:: create_engines_from_player_configs(player_configs)

      Create engines from player configurations.



   .. py:method:: create_simple_player_configs()

      Create player configs from simple model strings.



   .. py:method:: finalize_config()

      Finalize configuration after engine setup.



   .. py:method:: get_example_configs()

      Define example chess configurations.



   .. py:method:: get_role_definitions()

      Define chess player roles.