haive.games.poker.configurable_config¶

Configurable Poker configuration using the generic player agent system.

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

Classes¶

ConfigurablePokerConfig

Configurable Poker configuration with dynamic LLM selection.

Functions¶

create_advanced_poker_config(**kwargs)

Create an advanced Poker configuration with powerful models.

create_budget_poker_config(**kwargs)

Create a budget-friendly Poker configuration.

create_experimental_poker_config(**kwargs)

Create an experimental Poker configuration with mixed providers.

create_poker_config([player1_model, player2_model])

Create a configurable Poker configuration with simple model specifications.

create_poker_config_from_example(example_name, **kwargs)

Create a configurable Poker configuration from a predefined example.

create_poker_config_from_player_configs(...)

Create a configurable Poker 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 haive.games.poker.configurable_config.ConfigurablePokerConfig¶

Bases: haive.games.poker.config.PokerAgentConfig

Configurable Poker configuration with dynamic LLM selection.

This configuration allows users to specify different LLMs for different roles in the Poker 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

haive.games.poker.configurable_config.create_advanced_poker_config(**kwargs)¶

Create an advanced Poker configuration with powerful models.

Return type:

ConfigurablePokerConfig

haive.games.poker.configurable_config.create_budget_poker_config(**kwargs)¶

Create a budget-friendly Poker configuration.

Return type:

ConfigurablePokerConfig

haive.games.poker.configurable_config.create_experimental_poker_config(**kwargs)¶

Create an experimental Poker configuration with mixed providers.

Return type:

ConfigurablePokerConfig

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

Create a configurable Poker 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 Poker game

Return type:

ConfigurablePokerConfig

Examples

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

Create a configurable Poker configuration from a predefined example.

Parameters:

  • example_name (str) – Name of the example configuration

  • **kwargs – Additional configuration parameters to override

Returns:

Configured Poker game

Return type:

ConfigurablePokerConfig

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_poker_config_from_example("budget", enable_analysis=False)
>>> config = create_poker_config_from_example("advanced", visualize_game=True)
haive.games.poker.configurable_config.create_poker_config_from_player_configs(player_configs, **kwargs)¶

Create a configurable Poker configuration from detailed player configurations.

Parameters:
Returns:

Configured Poker game

Return type:

ConfigurablePokerConfig

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 Poker Pro"
...     ),
...     "player2_player": PlayerAgentConfig(
...         llm_config="claude-3-opus",
...         temperature=0.3,
...         player_name="Tactical Poker Ace"
...     ),
...     "player1_analyzer": PlayerAgentConfig(
...         llm_config="gpt-4o",
...         temperature=0.2,
...         player_name="Poker Strategist"
...     ),
...     "player2_analyzer": PlayerAgentConfig(
...         llm_config="claude-3-opus",
...         temperature=0.2,
...         player_name="Poker Analyst"
...     ),
... }
>>> config = create_poker_config_from_player_configs(player_configs)
haive.games.poker.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:

ConfigurablePokerConfig

Raises:

ValueError – If the example name is not found

haive.games.poker.configurable_config.list_example_configurations()¶

List all available example configurations.

Returns:

Mapping of configuration names to descriptions

Return type:

Dict[str, str]