games.poker.debug

Debugging utilities for the poker agent.

This module provides tools for debugging, testing and analyzing the poker agent’s performance, including: - Test harnesses for structured output validation - Decision validation and verification - Error analysis and reporting - Game state visualization

Classes

DecisionAnalyzer	Analyze and validate player decisions for correctness.
GameStatePrinter	Utility for visualizing poker game state during debugging.
StructuredOutputTester	Test harness for validating LLM structured output handling.

Module Contents

class games.poker.debug.DecisionAnalyzer

Analyze and validate player decisions for correctness.

static validate_decision(decision, player, game_state)

Validate if a decision is legal and reasonable.

Parameters:

• decision (haive.games.poker.models.AgentDecision)

• player (haive.games.poker.models.Player)

Return type:

dict[str, Any]

class games.poker.debug.GameStatePrinter

Utility for visualizing poker game state during debugging.

static print_game_state(state)

Print a human-readable version of the current game state.

class games.poker.debug.StructuredOutputTester(llm_runnable, input_values)

Test harness for validating LLM structured output handling.

Initialize the tester with an LLM runnable and test inputs.

Parameters:

input_values (dict[str, Any])

print_report()

Print a detailed report of the test results.

run_batch_test(iterations=10)

Run multiple tests and collect statistics.

Parameters:

iterations (int)

Return type:

dict[str, Any]

run_test(retries=3)

Run a single test of the LLM runnable with retries.

Parameters:

retries (int)

Return type:

dict[str, Any]