games.dominoes.configurable_config¶

Configurable Dominoes configuration using the generic player agent system.

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

Classes¶

ConfigurableDominoesConfig

Configurable Dominoes configuration with dynamic LLM selection.

Functions¶

create_advanced_dominoes_config(**kwargs)

Create an advanced Dominoes configuration with powerful models.

create_budget_dominoes_config(**kwargs)

Create a budget-friendly Dominoes configuration.

create_dominoes_config([player1_model, player2_model])

Create a configurable Dominoes configuration with simple model specifications.

create_dominoes_config_from_example(example_name, **kwargs)

Create a configurable Dominoes configuration from a predefined example.

create_dominoes_config_from_player_configs(...)

Create a configurable Dominoes configuration from detailed player configurations.

create_experimental_dominoes_config(**kwargs)

Create an experimental Dominoes configuration with mixed providers.

get_example_config(name)

Get a predefined example configuration by name.

list_example_configurations()

List all available example configurations.

Module Contents¶

class games.dominoes.configurable_config.ConfigurableDominoesConfig¶

Bases: haive.games.dominoes.config.DominoesAgentConfig

Configurable Dominoes configuration with dynamic LLM selection.

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

player1_model¶

Model for player1 (can be string or LLMConfig)

player2_model¶

Model for player2 (can be string or LLMConfig)

player1_name¶

Name for player1

player2_name¶

Name for player2

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.dominoes.configurable_config.create_advanced_dominoes_config(**kwargs)¶

Create an advanced Dominoes configuration with powerful models.

Return type:

ConfigurableDominoesConfig

games.dominoes.configurable_config.create_budget_dominoes_config(**kwargs)¶

Create a budget-friendly Dominoes configuration.

Return type:

ConfigurableDominoesConfig

games.dominoes.configurable_config.create_dominoes_config(player1_model='gpt-4o', player2_model='claude-3-5-sonnet-20240620', **kwargs)¶

Create a configurable Dominoes configuration with simple model specifications.

Parameters:

  • player1_model (str) – Model for player1 and analyzer

  • player2_model (str) – Model for player2 and analyzer

  • **kwargs – Additional configuration parameters

Returns:

Configured Dominoes game

Return type:

ConfigurableDominoesConfig

Examples

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

Create a configurable Dominoes configuration from a predefined example.

Parameters:

  • example_name (str) – Name of the example configuration

  • **kwargs – Additional configuration parameters to override

Returns:

Configured Dominoes game

Return type:

ConfigurableDominoesConfig

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_dominoes_config_from_example("budget", enable_analysis=False)
>>> config = create_dominoes_config_from_example("advanced", visualize_game=True)
games.dominoes.configurable_config.create_dominoes_config_from_player_configs(player_configs, **kwargs)¶

Create a configurable Dominoes configuration from detailed player configurations.

Parameters:
Returns:

Configured Dominoes game

Return type:

ConfigurableDominoesConfig

Expected roles:

  • “player1_player”: Player 1 configuration

  • “player2_player”: Player 2 configuration

  • “player1_analyzer”: Player 1 analyzer configuration

  • “player2_analyzer”: Player 2 analyzer configuration

Examples

>>> player_configs = {
...     "player1_player": PlayerAgentConfig(
...         llm_config="gpt-4o",
...         temperature=0.7,
...         player_name="Strategic Domino Master"
...     ),
...     "player2_player": PlayerAgentConfig(
...         llm_config="claude-3-opus",
...         temperature=0.3,
...         player_name="Tactical Domino Expert"
...     ),
...     "player1_analyzer": PlayerAgentConfig(
...         llm_config="gpt-4o",
...         temperature=0.2,
...         player_name="Dominoes Strategist"
...     ),
...     "player2_analyzer": PlayerAgentConfig(
...         llm_config="claude-3-opus",
...         temperature=0.2,
...         player_name="Dominoes Analyst"
...     ),
... }
>>> config = create_dominoes_config_from_player_configs(player_configs)
games.dominoes.configurable_config.create_experimental_dominoes_config(**kwargs)¶

Create an experimental Dominoes configuration with mixed providers.

Return type:

ConfigurableDominoesConfig

games.dominoes.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:

ConfigurableDominoesConfig

Raises:

ValueError – If the example name is not found

games.dominoes.configurable_config.list_example_configurations()¶

List all available example configurations.

Returns:

Mapping of configuration names to descriptions

Return type:

Dict[str, str]