haive.games.connect4.generic_engines
====================================

.. py:module:: haive.games.connect4.generic_engines

.. autoapi-nested-parse::

   Generic Connect4 engines using the new generic player agent system.

   This module demonstrates how to use the generic player agent system for Connect4,
   showing the same pattern working with red/yellow player identifiers.



Classes
-------

.. autoapisummary::

   haive.games.connect4.generic_engines.Connect4PromptGenerator


Functions
---------

.. autoapisummary::

   haive.games.connect4.generic_engines.create_generic_connect4_config_from_example
   haive.games.connect4.generic_engines.create_generic_connect4_engines
   haive.games.connect4.generic_engines.create_generic_connect4_engines_simple


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

.. py:class:: Connect4PromptGenerator(players)

   Bases: :py:obj:`haive.games.core.agent.generic_player_agent.GenericPromptGenerator`\ [\ :py:obj:`str`\ , :py:obj:`str`\ ]


   Connect4-specific prompt generator using the generic system.

   Init  .

   :param players: [TODO: Add description]


   .. py:method:: create_analysis_prompt(player)

      Create a Connect4 analysis prompt for the specified player.

      :param player: Player color ("red" or "yellow")

      :returns: Prompt template for position analysis
      :rtype: ChatPromptTemplate



   .. py:method:: create_move_prompt(player)

      Create a Connect4 move prompt for the specified player.

      :param player: Player color ("red" or "yellow")

      :returns: Prompt template for move generation
      :rtype: ChatPromptTemplate



   .. py:method:: get_analysis_output_model()

      Get the structured output model for Connect4 analysis.



   .. py:method:: get_move_output_model()

      Get the structured output model for Connect4 moves.



.. py:function:: create_generic_connect4_config_from_example(example_name, temperature = 0.7)

   Create Connect4 engines from predefined examples using generics.

   :param example_name: Name of the example configuration
   :param temperature: Temperature for all engines

   :returns: Dictionary of engines
   :rtype: dict[str, AugLLMConfig]

   Available examples:
       - "gpt_vs_claude": GPT-4 vs Claude
       - "gpt_only": GPT-4 for both players
       - "claude_only": Claude for both players
       - "budget": Cost-effective models
       - "mixed": Different provider per role



.. py:function:: create_generic_connect4_engines(player_configs)

   Create Connect4 engines using the generic system.

   :param player_configs: Dictionary of role name to player configuration

   :returns: Dictionary of configured engines
   :rtype: dict[str, AugLLMConfig]

   .. rubric:: Example

   >>> configs = {
   ...     "red_player": PlayerAgentConfig(llm_config="gpt-4"),
   ...     "yellow_player": PlayerAgentConfig(llm_config="claude-3-opus"),
   ...     "red_analyzer": PlayerAgentConfig(llm_config="gpt-4"),
   ...     "yellow_analyzer": PlayerAgentConfig(llm_config="claude-3-opus"),
   ... }
   >>> engines = create_generic_connect4_engines(configs)


.. py:function:: create_generic_connect4_engines_simple(red_model = 'gpt-4o', yellow_model = 'claude-3-5-sonnet-20240620', temperature = 0.7, **kwargs)

   Create Connect4 engines with simple model configurations using generics.

   :param red_model: Model for red player and analyzer
   :param yellow_model: Model for yellow player and analyzer
   :param temperature: Temperature for player engines
   :param \*\*kwargs: Additional configuration parameters

   :returns: Dictionary of engines
   :rtype: dict[str, AugLLMConfig]

   .. rubric:: Example

   >>> engines = create_generic_connect4_engines_simple("gpt-4", "claude-3-opus")
   >>> engines = create_generic_connect4_engines_simple(
   ...     "openai:gpt-4o",
   ...     "anthropic:claude-3-5-sonnet-20240620",
   ...     temperature=0.8
   ... )