haive.games.fox_and_geese.configurable_config¶

Configurable FoxAndGeese configuration using the generic player agent system.

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

Classes¶

ConfigurableFoxAndGeeseConfig

Configurable FoxAndGeese configuration with dynamic LLM selection.

Functions¶

create_advanced_fox_and_geese_config(**kwargs)

Create an advanced FoxAndGeese configuration with powerful models.

create_budget_fox_and_geese_config(**kwargs)

Create a budget-friendly FoxAndGeese configuration.

create_experimental_fox_and_geese_config(**kwargs)

Create an experimental FoxAndGeese configuration with mixed providers.

create_fox_and_geese_config([fox_model, geese_model])

Create a configurable FoxAndGeese configuration with simple model specifications.

create_fox_and_geese_config_from_example(example_name, ...)

Create a configurable FoxAndGeese configuration from a predefined example.

create_fox_and_geese_config_from_player_configs(...)

Create a configurable FoxAndGeese 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 haive.games.fox_and_geese.configurable_config.ConfigurableFoxAndGeeseConfig¶

Bases: haive.games.fox_and_geese.config.FoxAndGeeseConfig

Configurable FoxAndGeese configuration with dynamic LLM selection.

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

fox_model¶

Model for fox (can be string or LLMConfig)

geese_model¶

Model for geese (can be string or LLMConfig)

fox_name¶

Name for fox

geese_name¶

Name for geese

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.fox_and_geese.configurable_config.create_advanced_fox_and_geese_config(**kwargs)¶

Create an advanced FoxAndGeese configuration with powerful models.

Return type:

ConfigurableFoxAndGeeseConfig

haive.games.fox_and_geese.configurable_config.create_budget_fox_and_geese_config(**kwargs)¶

Create a budget-friendly FoxAndGeese configuration.

Return type:

ConfigurableFoxAndGeeseConfig

haive.games.fox_and_geese.configurable_config.create_experimental_fox_and_geese_config(**kwargs)¶

Create an experimental FoxAndGeese configuration with mixed providers.

Return type:

ConfigurableFoxAndGeeseConfig

haive.games.fox_and_geese.configurable_config.create_fox_and_geese_config(fox_model='gpt-4o', geese_model='claude-3-5-sonnet-20240620', **kwargs)¶

Create a configurable FoxAndGeese configuration with simple model specifications.

Parameters:

  • fox_model (str) – Model for fox and analyzer

  • geese_model (str) – Model for geese and analyzer

  • **kwargs – Additional configuration parameters

Returns:

Configured FoxAndGeese game

Return type:

ConfigurableFoxAndGeeseConfig

Examples

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

Create a configurable FoxAndGeese configuration from a predefined example.

Parameters:

  • example_name (str) – Name of the example configuration

  • **kwargs – Additional configuration parameters to override

Returns:

Configured FoxAndGeese game

Return type:

ConfigurableFoxAndGeeseConfig

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_fox_and_geese_config_from_example("budget", enable_analysis=False)
>>> config = create_fox_and_geese_config_from_example("advanced", visualize_game=True)
haive.games.fox_and_geese.configurable_config.create_fox_and_geese_config_from_player_configs(player_configs, **kwargs)¶

Create a configurable FoxAndGeese configuration from detailed player. configurations.

Parameters:
Returns:

Configured FoxAndGeese game

Return type:

ConfigurableFoxAndGeeseConfig

Expected roles:

  • “fox_player”: Player 1 configuration

  • “geese_player”: Player 2 configuration

  • “fox_analyzer”: Player 1 analyzer configuration

  • “geese_analyzer”: Player 2 analyzer configuration

Examples

>>> player_configs = {
...     "fox_player": PlayerAgentConfig(
...         llm_config="gpt-4o",
...         temperature=0.7,
...         player_name="Strategic Fox"
...     ),
...     "geese_player": PlayerAgentConfig(
...         llm_config="claude-3-opus",
...         temperature=0.3,
...         player_name="Tactical Geese"
...     ),
...     "fox_analyzer": PlayerAgentConfig(
...         llm_config="gpt-4o",
...         temperature=0.2,
...         player_name="FoxAndGeese Strategist"
...     ),
...     "geese_analyzer": PlayerAgentConfig(
...         llm_config="claude-3-opus",
...         temperature=0.2,
...         player_name="FoxAndGeese Analyst"
...     ),
... }
>>> config = create_fox_and_geese_config_from_player_configs(player_configs)
haive.games.fox_and_geese.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:

ConfigurableFoxAndGeeseConfig

Raises:

ValueError – If the example name is not found

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

List all available example configurations.

Returns:

Mapping of configuration names to descriptions

Return type:

Dict[str, str]