haive.games.risk.configurable_config¶

Configurable Risk configuration using the generic player agent system.

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

Classes¶

ConfigurableRiskConfig

Configurable Risk configuration with dynamic LLM selection.

Functions¶

create_advanced_risk_config(**kwargs)

Create an advanced Risk configuration with powerful models.

create_budget_risk_config(**kwargs)

Create a budget-friendly Risk configuration.

create_experimental_risk_config(**kwargs)

Create an experimental Risk configuration with mixed providers.

create_risk_config([player1_model, player2_model])

Create a configurable Risk configuration with simple model specifications.

create_risk_config_from_example(example_name, **kwargs)

Create a configurable Risk configuration from a predefined example.

create_risk_config_from_player_configs(player_configs, ...)

Create a configurable Risk 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.risk.configurable_config.ConfigurableRiskConfig(/, **data)¶

Bases: haive.games.risk.config.RiskConfig

Configurable Risk configuration with dynamic LLM selection.

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

Parameters:

data (Any)

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

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

model_post_init(__context)¶

Initialize engines after model creation.

Parameters:

__context (Any)

Return type:

None

haive.games.risk.configurable_config.create_advanced_risk_config(**kwargs)¶

Create an advanced Risk configuration with powerful models.

Return type:

ConfigurableRiskConfig

haive.games.risk.configurable_config.create_budget_risk_config(**kwargs)¶

Create a budget-friendly Risk configuration.

Return type:

ConfigurableRiskConfig

haive.games.risk.configurable_config.create_experimental_risk_config(**kwargs)¶

Create an experimental Risk configuration with mixed providers.

Return type:

ConfigurableRiskConfig

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

Create a configurable Risk 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 Risk game

Return type:

ConfigurableRiskConfig

Examples

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

Create a configurable Risk configuration from a predefined example.

Parameters:

  • example_name (str) – Name of the example configuration

  • **kwargs – Additional configuration parameters to override

Returns:

Configured Risk game

Return type:

ConfigurableRiskConfig

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_risk_config_from_example("budget", enable_analysis=False)
>>> config = create_risk_config_from_example("advanced", visualize_game=True)
haive.games.risk.configurable_config.create_risk_config_from_player_configs(player_configs, **kwargs)¶

Create a configurable Risk configuration from detailed player configurations.

Parameters:
Returns:

Configured Risk game

Return type:

ConfigurableRiskConfig

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 General"
...     ),
...     "player2_player": PlayerAgentConfig(
...         llm_config="claude-3-opus",
...         temperature=0.3,
...         player_name="Tactical Commander"
...     ),
...     "player1_analyzer": PlayerAgentConfig(
...         llm_config="gpt-4o",
...         temperature=0.2,
...         player_name="Risk Strategist"
...     ),
...     "player2_analyzer": PlayerAgentConfig(
...         llm_config="claude-3-opus",
...         temperature=0.2,
...         player_name="Risk Analyst"
...     ),
... }
>>> config = create_risk_config_from_player_configs(player_configs)
haive.games.risk.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:

ConfigurableRiskConfig

Raises:

ValueError – If the example name is not found

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

List all available example configurations.

Returns:

Mapping of configuration names to descriptions

Return type:

Dict[str, str]