haive.games.poker.engines

Poker agent LLM configurations and prompts.

This module defines the language model configurations and prompt templates for different poker playing styles and roles. It includes:

• Player prompt generation for different styles

• Hand analysis prompt generation

• LLM provider selection and configuration

• Agent configuration creation

The module supports multiple LLM providers (Azure, DeepSeek, Anthropic, Gemini, Mistral) and configures them with appropriate models and prompts for poker gameplay.

Functions

create_default_agent_configs(config)	Create default configurations for poker agents based on config.
create_llm_config_for_provider(provider, **kwargs)	Create an LLM configuration for a specific provider.
create_poker_agent_configs()	Create structured configurations for poker agents.
generate_hand_analysis_prompt()	Generate a structured prompt for poker hand analysis.
generate_poker_prompt(player_style)	Generate a structured prompt for a poker player.
get_available_providers()	Determine all available LLM providers based on environment variables.
get_model_for_provider(provider)	Get the best model for a given provider.
get_poker_llm_provider()	Determine the best available LLM provider.

Module Contents

haive.games.poker.engines.create_default_agent_configs(config)

Create default configurations for poker agents based on config.

haive.games.poker.engines.create_llm_config_for_provider(provider, **kwargs)

Create an LLM configuration for a specific provider.

Parameters:

provider (haive.core.models.llm.base.LLMProvider)

haive.games.poker.engines.create_poker_agent_configs()

Create structured configurations for poker agents.

Return type:

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

haive.games.poker.engines.generate_hand_analysis_prompt()

Generate a structured prompt for poker hand analysis.

Return type:

langchain_core.prompts.ChatPromptTemplate

haive.games.poker.engines.generate_poker_prompt(player_style)

Generate a structured prompt for a poker player.

Parameters:

player_style (str)

Return type:

langchain_core.prompts.ChatPromptTemplate

haive.games.poker.engines.get_available_providers()

Determine all available LLM providers based on environment variables.

Return type:

list[haive.core.models.llm.base.LLMProvider]

haive.games.poker.engines.get_model_for_provider(provider)

Get the best model for a given provider.

Parameters:

provider (haive.core.models.llm.base.LLMProvider)

Return type:

str

haive.games.poker.engines.get_poker_llm_provider()

Determine the best available LLM provider.

Return type:

haive.core.models.llm.base.LLMProvider