haive.games.mancala.generic_engines¶

Generic Mancala engine creation using the generic player agent system.

This module provides generic engine creation functions for Mancala games, allowing for configurable LLM models and game-specific player identifiers.

Classes¶

MancalaEngineFactory

Factory for creating Mancala game engines.

MancalaPlayerIdentifiers

Player identifiers for Mancala game.

MancalaPromptGenerator

Prompt generator for Mancala game.

Functions¶

create_advanced_mancala_engines(**kwargs)

Create advanced Mancala engines with high-powered models.

create_budget_mancala_engines(**kwargs)

Create budget-friendly Mancala engines.

create_generic_mancala_config_from_example(example_name)

Create Mancala engines from a predefined example configuration.

create_generic_mancala_engines(player_configs)

Create Mancala engines from detailed player configurations.

create_generic_mancala_engines_simple(player1_model, ...)

Create Mancala engines with simple model specifications.

create_mixed_mancala_engines(**kwargs)

Create mixed-provider Mancala engines.

Module Contents¶

class haive.games.mancala.generic_engines.MancalaEngineFactory¶

Bases: haive.games.core.agent.generic_player_agent.GenericGameEngineFactory[str, str]

Factory for creating Mancala game engines.

Init .

get_structured_output_model(role)¶

Get the structured output model for a specific role.

Parameters:

role (str)

Return type:

type

class haive.games.mancala.generic_engines.MancalaPlayerIdentifiers¶

Bases: haive.games.core.agent.generic_player_agent.GamePlayerIdentifiers[str, str]

Player identifiers for Mancala game.

Init .

class haive.games.mancala.generic_engines.MancalaPromptGenerator(players)¶

Bases: haive.games.core.agent.generic_player_agent.GenericPromptGenerator[str, str]

Prompt generator for Mancala game.

Init .

Parameters:

players (GamePlayerIdentifiers[PlayerType, PlayerType2]) – [TODO: Add description]

create_analyzer_prompt(player)¶

Create analysis prompt for Mancala game state.

Parameters:

player (str)

Return type:

langchain_core.prompts.ChatPromptTemplate

create_move_prompt(player)¶

Create move prompt for Mancala player.

Parameters:

player (str)

Return type:

langchain_core.prompts.ChatPromptTemplate

haive.games.mancala.generic_engines.create_advanced_mancala_engines(**kwargs)¶

Create advanced Mancala engines with high-powered models.

Return type:

dict[str, haive.core.engine.aug_llm.AugLLMConfig]

haive.games.mancala.generic_engines.create_budget_mancala_engines(**kwargs)¶

Create budget-friendly Mancala engines.

Return type:

dict[str, haive.core.engine.aug_llm.AugLLMConfig]

haive.games.mancala.generic_engines.create_generic_mancala_config_from_example(example_name, temperature=0.3)¶

Create Mancala engines from a predefined example configuration.

Parameters:

  • example_name (str) – Name of the example configuration

  • temperature (float) – Generation temperature

Returns:

Dictionary of Mancala engines

Return type:

Dict[str, AugLLMConfig]

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

haive.games.mancala.generic_engines.create_generic_mancala_engines(player_configs)¶

Create Mancala engines from detailed player configurations.

Parameters:

player_configs (dict[str, haive.games.core.agent.player_agent.PlayerAgentConfig]) – Dictionary mapping role names to player configurations

Returns:

Dictionary of Mancala engines

Return type:

Dict[str, AugLLMConfig]

Expected roles:

  • “player1_player”: Player 1 configuration

  • “player2_player”: Player 2 configuration

  • “player1_analyzer”: Player 1 analyzer configuration

  • “player2_analyzer”: Player 2 analyzer configuration

haive.games.mancala.generic_engines.create_generic_mancala_engines_simple(player1_model, player2_model, temperature=0.3)¶

Create Mancala engines with simple model specifications.

Parameters:

  • player1_model (str) – Model for player1 and analyzer

  • player2_model (str) – Model for player2 and analyzer

  • temperature (float) – Generation temperature

Returns:

Dictionary of Mancala engines

Return type:

Dict[str, AugLLMConfig]

haive.games.mancala.generic_engines.create_mixed_mancala_engines(**kwargs)¶

Create mixed-provider Mancala engines.

Return type:

dict[str, haive.core.engine.aug_llm.AugLLMConfig]