import numpy as np

from sim_reveal.procedural_envs import BAG_PROXY, make_proxy_env


def test_proposal_semantic_diversity():
    env = make_proxy_env(proxy_name=BAG_PROXY.name, resolution=32, seed=7, rollout_horizon=4)
    _, _ = env.reset(seed=7)
    teacher_chunk, _ = env.teacher_chunk_and_rollout(chunk_horizon=4, rollout_horizon=4)
    candidates, outcomes = env.sample_candidate_action_chunks(
        teacher_chunk=teacher_chunk,
        num_candidates=6,
        rollout_horizon=4,
    )

    assert candidates.shape[0] == 6
    assert len(set(outcomes["candidate_macro_names"])) >= 4
    assert len(set(outcomes["candidate_negative_families"])) >= 3
    assert float(np.std(outcomes["candidate_utility"])) > 0.0