test(D1): exchange, Jet and fine-surface checks run on all-blocked storage

- test_exchange_window and test_raw_exchange_gpu fine(): dense root becomes
  a (12, 8) blocked root (fine(None) stays only for the dense reference test
  that D2 retires);
- jets: G1/G3 compare blocked layouts against the FINE_BLOCKS[0] reference
  (blocked root); the dense run is a separate leg D2 removes; G2 legacy
  actuation vs Jet on the blocked reference; CPU fixtures use a blocked root;
- test_refinement_blocked_fine.raw reads every level through its layout;
- test_fine_surface_gpu: new test_fine_surface_blocked_matches_uniform_four_hops
  (fine ROI after each of four hops vs the uniform 48^2 solver with the same
  tolerances, blowing/suction mass sign from raw exchange, zero actuation ==
  passive bit for bit); the cross-interface donor rejection passes tiles.
  The dense hook/ledger/audit probes in test_fine_surface_four_hops and the
  dense SoA fault tests stay until D2 retires them by name.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/validation/multigrid/test_fine_surface_gpu.py

@@ -279,6 +279,61 @@ def test_fine_surface_four_hops(speed):
             np.testing.assert_array_equal(got, wanted)
 
 
+def run_blocked_patch(speed):
+    """All-blocked run (whole-level tiles) of the same case; fine ROI after each fine hop."""
+    cfg = LBMConfig(nx=24, ny=24, viscosity=.05, velocity=0, rho=1)
+    source = object_spec(speed)
+    with CudaContext(0) as context:
+        with implementation.FixedPatchStepper(cfg, context=context, refinements=[BOUNDS],
+                                              level_blocks=[(24, 24), (40, 40)],
+                                              level_objects=[(), (source,)],
+                                              observe_raw_exchange=True) as backend:
+            c, f = backend._levels
+            flags = backend.fine_boundary.flags.reshape(40, 40)
+            active = np.zeros((40, 40), bool)
+            active[4:-4, 4:-4] = True
+            active &= ((flags & FLUID) != 0) & ((flags & SOLID) == 0)
+            yy, xx = np.mgrid[:40, :40]
+            roi = active & ((xx-20)**2+(yy-20)**2 <= 9**2)
+            backend.initialize(rest((24, 24)), rest((40, 40)))
+            traces, original = [], f.kernel
+
+            def fine(*args, **kwargs):
+                original(*args, **kwargs)
+                backend._stream.synchronize()
+                advanced = f.layout.to_dense(read(args[1], f.layout.blocked_shape))
+                assert np.isfinite(advanced[:, active]).all()
+                assert np.isnan(advanced[:, (flags & SOLID) != 0]).all()
+                traces.append(advanced[:, roi].copy())
+
+            with patch.object(f, "kernel", fine):
+                backend.step(2)
+            assert len(traces) == 4 and backend.step_count == 2
+            mass = backend.read_raw_exchange(0)["total"]["mass_into_fluid"]
+            return traces, roi, backend.download(), float(mass)
+
+
+@pytest.mark.parametrize("speed", [0., .002, -.002])
+def test_fine_surface_blocked_matches_uniform_four_hops(speed):
+    """Blocked storage: fine ROI after each of four hops against the uniform 48^2 solver
+    (same tolerances as the dense test); blowing/suction drives mass with its sign;
+    zero actuation equals the passive circle bit for bit."""
+    actual, roi, final, mass = run_blocked_patch(speed)
+    reference = uniform_reference(speed, roi)
+    for got, wanted in zip(actual, reference):
+        np.testing.assert_allclose(got, wanted, atol=3e-6, rtol=0)
+        np.testing.assert_allclose(MOMENTS@got.astype(float), MOMENTS@wanted.astype(float),
+                                   atol=2e-5, rtol=0)
+    if speed:
+        assert speed*mass > 0
+    else:
+        passive, passive_roi, passive_final, _ = run_blocked_patch(None)
+        np.testing.assert_array_equal(passive_roi, roi)
+        for got, wanted in zip(actual+list(final), passive+list(passive_final)):
+            np.testing.assert_array_equal(got, wanted)
+    print(f"blocked speed={speed} four hops vs uniform PASS mass_into_fluid={mass:+.9g}", flush=True)
+
+
 @pytest.mark.parametrize("missing", ["surface_velocity_gpu", "link_exchange_gpu"])
 def test_missing_surface_device_buffer_rejects_before_launch(missing):
     backend = implementation.FixedPatchStepper.__new__(implementation.FixedPatchStepper)
@@ -328,6 +383,7 @@ def test_cross_interface_donor_rejects_before_cuda():
     with patch.object(cuda, "mem_alloc") as allocate:
         with pytest.raises(ValueError, match="donor crosses"):
             implementation.FixedPatchStepper(cfg, context=context, refinements=[BOUNDS],
+                                             level_blocks=[(24, 24), (40, 40)],
                                              level_objects=[(), (source,)])
         context.activate.assert_not_called()
         allocate.assert_not_called()