test: cover TRT restart and actual-rate refinement phase

Integrate reviewed test changes from 7c1517de819741907fb945ea0ab7864734fa3856 and 340ba4e1dc6386581839c0b28c8fe8a1f4aeb70b unchanged. Document bounded 2D implementation, evidence and open gates; production source and historical manifests are unchanged.

tests/validation/multigrid/test_refinement_gpu.py

@@ -7,6 +7,7 @@ At most eight coarse steps per case. No files, plots or flow arrays are saved.
 import hashlib
 import importlib.util
 from contextlib import nullcontext
+from dataclasses import replace
 from pathlib import Path
 import resource
 import sys
@@ -21,7 +22,7 @@ import CelerisLab
 from CelerisLab.config import LBMConfig
 from CelerisLab.cuda import compiler_v2 as compiler
 from CelerisLab.cuda.context import CudaContext
-from CelerisLab.lbm.refinement_stepper import PeriodicPatchStepper
+from CelerisLab.lbm.refinement_stepper import FixedPatchStepper, PeriodicPatchStepper
 
 ROOT = Path(__file__).resolve().parents[3]
 POP_ATOL = 3e-6
@@ -60,6 +61,69 @@ def global_array(module, name, shape):
 
 
 class CoupledGPU(unittest.TestCase):
+    def test_actual_tg_rates_one_interval(self):
+        """Algebraic rate/phase check, not a new physical Taylor--Green benchmark.
+
+        The N64/Re100 TG rates are exercised on the existing small patch with
+        a nonequilibrium state. One interval checks g=C(f), including the
+        shifted blocked path; no accuracy gate or production source changes.
+        """
+        self.assertEqual(Path(CelerisLab.__file__).resolve(), ROOT / "src/CelerisLab/__init__.py")
+        self.assertEqual(Path(compiler._KERNEL_DIR).resolve(), ROOT / "src/CelerisLab/lbm/kernels")
+        spec = replace(ref.make_spec(collision="srt"),
+                       tau_coarse=.5576, tau_fine=.6152)
+        maps = ref.build_maps(spec)
+        state = ref.make_state(spec, velocity=(.03, -.02))
+        rng = np.random.default_rng(1)
+        state = ref.State(*(a * (1 + 1e-3 * rng.standard_normal(a.shape))
+                            for a in (state.coarse_f, state.fine_f)))
+        initial = postcollision(state, spec, maps)
+        next_state, _ = ref.advance_coarse_once(spec, maps, state)
+        expected = postcollision(next_state, spec, maps)
+        arrivals = (next_state.coarse_f, next_state.fine_f)
+
+        cases = (("dense_unshifted", False, {}),
+                 ("blocked_shifted", True,
+                  dict(base_block=(4, 4), fine_block=(6, 6))))
+        with CudaContext(0) as context:
+            for label, shifted, storage in cases:
+                with self.subTest(storage=label):
+                    cfg = LBMConfig(nx=16, ny=16, viscosity=.0192,
+                                    ddf_shifting=shifted)
+                    with FixedPatchStepper(cfg, (4, 4, 12, 12), context=context,
+                                           **storage) as backend:
+                        self.assertAlmostEqual(backend.patch.tau_coarse, spec.tau_coarse)
+                        self.assertAlmostEqual(backend.patch.tau_fine, spec.tau_fine)
+                        self.assertEqual(tuple(level.shape for level in backend._levels),
+                                         ((9, 16, 16), (9, 24, 24)))
+                        # Physical FP64 g is encoded by initialize before FP32 rounding.
+                        backend.initialize(*initial)
+                        before = totals(backend.download(), maps)
+                        backend.step(1)
+                        actual = backend.download()
+                        self.assertEqual(backend.step_count, 1)
+                        backend.patch.check_synchronization(
+                            1, next_state.tick, phase="postcollision_g")
+                        for got, want, arrival in zip(actual, expected, arrivals):
+                            np.testing.assert_array_equal(np.isnan(got), np.isnan(want))
+                            np.testing.assert_allclose(got, want, rtol=0, atol=POP_ATOL,
+                                                       equal_nan=True)
+                            # A raw arrival-f comparison must fail on BOTH levels.
+                            # Equilibrium-only data would make this control vacuous.
+                            with self.assertRaises(AssertionError):
+                                np.testing.assert_allclose(got, arrival, rtol=0,
+                                                           atol=POP_ATOL, equal_nan=True)
+                        np.testing.assert_allclose(totals(actual, maps), before,
+                                                   rtol=0, atol=MOMENT_ATOL)
+                        np.testing.assert_allclose(totals(actual, maps),
+                                                   totals(expected, maps),
+                                                   rtol=0, atol=MOMENT_ATOL)
+                        error = max(float(np.nanmax(np.abs(a - e)))
+                                    for a, e in zip(actual, expected))
+                        print(f"actual-TG-rate algebraic check: {label} steps=1 "
+                              f"tau=.5576/.6152 max_population={error:.9g}; "
+                              "wrong-phase controls PASS", flush=True)
+
     def test_cleanup_attempts_every_allocation(self):
         backend = PeriodicPatchStepper.__new__(PeriodicPatchStepper)
         backend.ctx = Mock(activate=nullcontext)