auto-sync 2026-07-03T18:45:41Z workspace (part 4)

workspace/tests/test_ctt.py

@@ -13,8 +13,10 @@ from scripts.eval_ctt_generated_rollout import (
     _action_bound_diagnostics_4d,
     _clip_to_action_space_4d,
     _measured_row_from_rollout,
+    _parse_execution_action_scale_vector,
     _scale_actions_4d,
     _source_pool_for_target,
+    _transform_actions_4d,
 )
 
 
@@ -140,6 +142,34 @@ def test_execution_action_scale_applies_before_bound_diagnostics():
     assert diagnostics["violation"].tolist() == [[False]]
 
 
+def test_execution_action_scale_vector_is_dimension_wise():
+    actions = np.asarray([[[[2.0, -4.0, 3.0]]]], dtype=np.float32)
+    vector = _parse_execution_action_scale_vector("0.5,0.25,2.0")
+
+    scaled = _scale_actions_4d(actions, 0.5, scale_vector=vector)
+
+    assert vector is not None
+    assert scaled.tolist() == [[[[0.5, -0.5, 3.0]]]]
+
+
+def test_tanh_execution_transform_maps_to_env_bounds():
+    env = SimpleNamespace(
+        single_action_space=SimpleNamespace(
+            low=np.asarray([-1.0, -2.0], dtype=np.float32),
+            high=np.asarray([1.0, 2.0], dtype=np.float32),
+        )
+    )
+    actions = np.asarray([[[[10.0, -10.0]]]], dtype=np.float32)
+
+    transformed = _transform_actions_4d(actions, env, "tanh")
+    diagnostics = _action_bound_diagnostics_4d(transformed, env)
+
+    assert transformed[0, 0, 0, 0] <= 1.0
+    assert transformed[0, 0, 0, 1] >= -2.0
+    assert diagnostics is not None
+    assert diagnostics["violation"].tolist() == [[False]]
+
+
 def test_measured_rollout_row_records_action_bound_safety_source():
     target = ChartItem(
         chart_id="chart_a",
@@ -175,9 +205,13 @@ def test_measured_rollout_row_records_action_bound_safety_source():
         action_clip_max_abs=[0.0, 0.2],
         restore_error=0.0,
         execution_action_scale=0.25,
+        execution_action_scale_vector=np.asarray([0.5, 2.0], dtype=np.float32),
+        execution_action_transform="tanh",
     )
 
     assert row["execution_action_scale"] == pytest.approx(0.25)
+    assert row["execution_action_scale_vector"] == [0.5, 2.0]
+    assert row["execution_action_transform"] == "tanh"
     assert row["base_outcome"]["safety_violation"] is False
     assert row["base_outcome"]["safety_violation_source"] == "action_bounds"
     assert row["candidate_outcomes"][0]["safety_violation"] is True