test(cp6): lock optimal!=habit handover invariant for all difficulty bands

tests/grid/test_difficulty_layouts.py

@@ -62,3 +62,35 @@ def test_each_band_is_deterministic():
         g1, _ = _game(d, seed=7)
         g2, _ = _game(d, seed=7)
         assert np.array_equal(g1.current_grid(), g2.current_grid())
+
+
+def _drive_to_handover(difficulty, seed=42):
+    """Replay the Cut pre-roll (scripted 'left') to the handover state."""
+    s = _scenario()
+    game = MotiveGridGame(s, random.Random(seed), difficulty, max_steps=40)
+    for _ in range(s.cut_length(difficulty)):
+        action = s.cut_focal_policy(game)
+        game.apply_motive_action(action)
+        s.record_focal_move(action)
+    return game, s
+
+
+def test_invariant_optimal_differs_from_habit_each_band():
+    # The whole discrimination metric depends on optimal != habit at the Cut
+    # handover, for EVERY difficulty band.
+    for d in _BANDS:
+        game, s = _drive_to_handover(d)
+        optimal = s.optimal_action(game)
+        habit = s.habit_action(game)
+        assert optimal != habit, f"{d}: optimal {optimal} == habit {habit}"
+        # Habit ('left', the pre-roll direction) must be trapped: moving left
+        # is blocked (a wall) so it does not increase distance.
+        assert habit == "left"
+
+
+def test_handover_is_deterministic_each_band():
+    for d in _BANDS:
+        g1, s1 = _drive_to_handover(d, seed=11)
+        g2, s2 = _drive_to_handover(d, seed=11)
+        assert (g1.focal_sprite.x, g1.focal_sprite.y) == (g2.focal_sprite.x, g2.focal_sprite.y)
+        assert (g1.predator_sprite.x, g1.predator_sprite.y) == (g2.predator_sprite.x, g2.predator_sprite.y)