open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-27 17:23:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Add score_answer method to RushHourDataset with input validation

Browse source
This commit is contained in:
Andreas Koepf (aider) 2025-02-14 17:31:53 +01:00 • committed by Andreas Koepf
parent 8278a9521c
commit d5ce2bfdf5
2 changed files with 45 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

18
tests/test_rush_hour.py
View file

@ -62,6 +62,24 @@ def test_rush_hour_move_filtering():
assert 5 <= moves <= 10, f"Puzzle with {moves} moves outside configured range 5-10"
def test_score_answer():
"""Test that score_answer correctly validates solutions"""
config = RushHourConfig(min_moves=1, max_moves=50, size=10, seed=42)
dataset = RushHourDataset(config)
# Get a puzzle
puzzle = dataset[0]
# Test invalid answers
assert dataset.score_answer(None, puzzle) == 0.0
assert dataset.score_answer("", puzzle) == 0.0
assert dataset.score_answer("invalid", puzzle) == 0.0
assert dataset.score_answer("A+1 B-2 INVALID", puzzle) == 0.0
# Test incomplete solution
assert dataset.score_answer("A+1 B-2", puzzle) == 0.0
def test_perform_moves():
b = Board("GBBoLoGHIoLMGHIAAMCCCKoMooJKDDEEJFFo")
assert not b.solved