games.reversi.configurable_config¶

Configurable Reversi configuration using the generic player agent system.

This module provides configurable Reversi game configurations that replace hardcoded LLM settings with dynamic, configurable player agents.

Classes¶

ConfigurableReversiConfig

Configurable Reversi configuration with dynamic LLM selection.

Functions¶

create_advanced_reversi_config(**kwargs)

Create an advanced Reversi configuration with powerful models.

create_budget_reversi_config(**kwargs)

Create a budget-friendly Reversi configuration.

create_experimental_reversi_config(**kwargs)

Create an experimental Reversi configuration with mixed providers.

create_reversi_config([black_model, white_model])

Create a configurable Reversi configuration with simple model specifications.

create_reversi_config_from_example(example_name, **kwargs)

Create a configurable Reversi configuration from a predefined example.

create_reversi_config_from_player_configs(...)

Create a configurable Reversi configuration from detailed player configurations.

get_example_config(name)

Get a predefined example configuration by name.

list_example_configurations()

List all available example configurations.

Module Contents¶

class games.reversi.configurable_config.ConfigurableReversiConfig¶

Bases: haive.games.reversi.config.ReversiConfig

Configurable Reversi configuration with dynamic LLM selection.

This configuration allows users to specify different LLMs for different roles in the Reversi game, providing flexibility and avoiding hardcoded models.

black_model¶

Model for black (can be string or LLMConfig)

white_model¶

Model for white (can be string or LLMConfig)

black_name¶

Name for black

white_name¶

Name for white

example_config¶

Optional example configuration name

player_configs¶

Optional detailed player configurations

temperature¶

Temperature for LLM generation

enable_analysis¶

Whether to enable strategic analysis

visualize_game¶

Whether to visualize game state

recursion_limit¶

Python recursion limit for game execution

model_post_init(__context)¶

Initialize engines after model creation.

Parameters:

__context (Any)

Return type:

None

games.reversi.configurable_config.create_advanced_reversi_config(**kwargs)¶

Create an advanced Reversi configuration with powerful models.

Return type:

ConfigurableReversiConfig

games.reversi.configurable_config.create_budget_reversi_config(**kwargs)¶

Create a budget-friendly Reversi configuration.

Return type:

ConfigurableReversiConfig

games.reversi.configurable_config.create_experimental_reversi_config(**kwargs)¶

Create an experimental Reversi configuration with mixed providers.

Return type:

ConfigurableReversiConfig

games.reversi.configurable_config.create_reversi_config(black_model='gpt-4o', white_model='claude-3-5-sonnet-20240620', **kwargs)¶

Create a configurable Reversi configuration with simple model specifications.

Parameters:

  • black_model (str) – Model for black and analyzer

  • white_model (str) – Model for white and analyzer

  • **kwargs – Additional configuration parameters

Returns:

Configured Reversi game

Return type:

ConfigurableReversiConfig

Examples

>>> config = create_reversi_config("gpt-4o", "claude-3-opus", temperature=0.5)
>>> config = create_reversi_config(
...     "openai:gpt-4o",
...     "anthropic:claude-3-5-sonnet-20240620",
...     enable_analysis=True
... )
games.reversi.configurable_config.create_reversi_config_from_example(example_name, **kwargs)¶

Create a configurable Reversi configuration from a predefined example.

Parameters:

  • example_name (str) – Name of the example configuration

  • **kwargs – Additional configuration parameters to override

Returns:

Configured Reversi game

Return type:

ConfigurableReversiConfig

Available examples:

  • “gpt_vs_claude”: GPT vs Claude

  • “gpt_only”: GPT for both players

  • “claude_only”: Claude for both players

  • “budget”: Cost-effective models

  • “mixed”: Different provider per role

  • “advanced”: High-powered models for strategic gameplay

Examples

>>> config = create_reversi_config_from_example("budget", enable_analysis=False)
>>> config = create_reversi_config_from_example("advanced", visualize_game=True)
games.reversi.configurable_config.create_reversi_config_from_player_configs(player_configs, **kwargs)¶

Create a configurable Reversi configuration from detailed player configurations.

Parameters:
Returns:

Configured Reversi game

Return type:

ConfigurableReversiConfig

Expected roles:

  • “black_player”: Player 1 configuration

  • “white_player”: Player 2 configuration

  • “black_analyzer”: Player 1 analyzer configuration

  • “white_analyzer”: Player 2 analyzer configuration

Examples

>>> player_configs = {
...     "black_player": PlayerAgentConfig(
...         llm_config="gpt-4o",
...         temperature=0.7,
...         player_name="Strategic Black Player"
...     ),
...     "white_player": PlayerAgentConfig(
...         llm_config="claude-3-opus",
...         temperature=0.3,
...         player_name="Tactical White Player"
...     ),
...     "black_analyzer": PlayerAgentConfig(
...         llm_config="gpt-4o",
...         temperature=0.2,
...         player_name="Reversi Strategist"
...     ),
...     "white_analyzer": PlayerAgentConfig(
...         llm_config="claude-3-opus",
...         temperature=0.2,
...         player_name="Reversi Analyst"
...     ),
... }
>>> config = create_reversi_config_from_player_configs(player_configs)
games.reversi.configurable_config.get_example_config(name)¶

Get a predefined example configuration by name.

Parameters:

name (str) – Name of the example configuration

Returns:

The example configuration

Return type:

ConfigurableReversiConfig

Raises:

ValueError – If the example name is not found

games.reversi.configurable_config.list_example_configurations()¶

List all available example configurations.

Returns:

Mapping of configuration names to descriptions

Return type:

Dict[str, str]