games.tic_tac_toe.configurable_config¶

Configurable Tic-Tac-Toe configuration using the generic player agent system.

This module provides configurable Tic-Tac-Toe game configurations that replace hardcoded LLM settings with dynamic, configurable player agents.

Classes¶

ConfigurableTicTacToeConfig

Configurable Tic-Tac-Toe configuration with dynamic LLM selection.

Functions¶

create_budget_ttt_config(**kwargs)

Create a budget-friendly Tic-Tac-Toe configuration.

create_experimental_ttt_config(**kwargs)

Create an experimental Tic-Tac-Toe configuration with mixed providers.

create_quick_ttt_config(**kwargs)

Create a quick Tic-Tac-Toe configuration with fast models.

create_ttt_config([x_model, o_model])

Create a configurable Tic-Tac-Toe configuration with simple model specifications.

create_ttt_config_from_example(example_name, **kwargs)

Create a configurable Tic-Tac-Toe configuration from a predefined example.

create_ttt_config_from_player_configs(player_configs, ...)

Create a configurable Tic-Tac-Toe configuration from detailed player.

get_example_config(name)

Get a predefined example configuration by name.

list_example_configurations()

List all available example configurations.

Module Contents¶

class games.tic_tac_toe.configurable_config.ConfigurableTicTacToeConfig¶

Bases: haive.games.tic_tac_toe.config.TicTacToeConfig

Configurable Tic-Tac-Toe configuration with dynamic LLM selection.

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

x_model¶

Model for X player (can be string or LLMConfig)

o_model¶

Model for O player (can be string or LLMConfig)

x_player_name¶

Name for the X player

o_player_name¶

Name for the O player

example_config¶

Optional example configuration name

player_configs¶

Optional detailed player configurations

temperature¶

Temperature for LLM generation

max_moves¶

Maximum number of moves before draw

enable_analysis¶

Whether to enable position analysis

recursion_limit¶

Python recursion limit for game execution

model_post_init(__context)¶

Initialize engines after model creation.

Parameters:

__context (Any)

Return type:

None

games.tic_tac_toe.configurable_config.create_budget_ttt_config(**kwargs)¶

Create a budget-friendly Tic-Tac-Toe configuration.

Return type:

ConfigurableTicTacToeConfig

games.tic_tac_toe.configurable_config.create_experimental_ttt_config(**kwargs)¶

Create an experimental Tic-Tac-Toe configuration with mixed providers.

Return type:

ConfigurableTicTacToeConfig

games.tic_tac_toe.configurable_config.create_quick_ttt_config(**kwargs)¶

Create a quick Tic-Tac-Toe configuration with fast models.

Return type:

ConfigurableTicTacToeConfig

games.tic_tac_toe.configurable_config.create_ttt_config(x_model='gpt-4o', o_model='claude-3-5-sonnet-20240620', **kwargs)¶

Create a configurable Tic-Tac-Toe configuration with simple model specifications.

Parameters:

  • x_model (str) – Model for X player and analyzer

  • o_model (str) – Model for O player and analyzer

  • **kwargs – Additional configuration parameters

Returns:

Configured Tic-Tac-Toe game

Return type:

ConfigurableTicTacToeConfig

Examples

>>> config = create_ttt_config("gpt-4o", "claude-3-opus", temperature=0.5)
>>> config = create_ttt_config(
...     "openai:gpt-4o",
...     "anthropic:claude-3-5-sonnet-20240620",
...     max_moves=9
... )
games.tic_tac_toe.configurable_config.create_ttt_config_from_example(example_name, **kwargs)¶

Create a configurable Tic-Tac-Toe configuration from a predefined example.

Parameters:

  • example_name (str) – Name of the example configuration

  • **kwargs – Additional configuration parameters to override

Returns:

Configured Tic-Tac-Toe game

Return type:

ConfigurableTicTacToeConfig

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

Examples

>>> config = create_ttt_config_from_example("budget", max_moves=9)
>>> config = create_ttt_config_from_example("gpt_vs_claude", enable_analysis=False)
games.tic_tac_toe.configurable_config.create_ttt_config_from_player_configs(player_configs, **kwargs)¶

Create a configurable Tic-Tac-Toe configuration from detailed player. configurations.

Parameters:
Returns:

Configured Tic-Tac-Toe game

Return type:

ConfigurableTicTacToeConfig

Expected roles:

  • “X_player”: X player configuration

  • “O_player”: O player configuration

  • “X_analyzer”: X analyzer configuration

  • “O_analyzer”: O analyzer configuration

Examples

>>> player_configs = {
...     "X_player": PlayerAgentConfig(
...         llm_config="gpt-4o",
...         temperature=0.7,
...         player_name="Strategic X"
...     ),
...     "O_player": PlayerAgentConfig(
...         llm_config="claude-3-opus",
...         temperature=0.3,
...         player_name="Tactical O"
...     ),
...     "X_analyzer": PlayerAgentConfig(
...         llm_config="gpt-4o",
...         temperature=0.2,
...         player_name="X Analyst"
...     ),
...     "O_analyzer": PlayerAgentConfig(
...         llm_config="claude-3-opus",
...         temperature=0.2,
...         player_name="O Analyst"
...     ),
... }
>>> config = create_ttt_config_from_player_configs(player_configs)
games.tic_tac_toe.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:

ConfigurableTicTacToeConfig

Raises:

ValueError – If the example name is not found

games.tic_tac_toe.configurable_config.list_example_configurations()¶

List all available example configurations.

Returns:

Mapping of configuration names to descriptions

Return type:

Dict[str, str]