P1 (4/n): unit tests and examples use the level-list constructor

test_shifted_jets, test_shifted_storage, test_raw_exchange and
test_channel_root pass refinements/level_* lists; examples
fixed_patch_jet and fixed_periodic_patch pass refinements=[BOUNDS]
instead of the positional bounds. Assertions kept; the shifted-storage
case base_block-without-fine_block now expects the level-list rule
'blocked refined levels below' (same constraint).

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

examples/fixed_patch_circle.py

@@ -90,8 +90,8 @@ def main():
     # The caller owns the CUDA context; the stepper must be closed first (the
     # nested with-statement does that).
     with CudaContext(0) as context, FixedPatchStepper(
-            cfg, BOUNDS, context=context, coarse_boundary=args.mode,
-            fine_objects=[body], fine_block=fine_block) as run:
+            cfg, context=context, coarse_boundary=args.mode, refinements=[BOUNDS],
+            level_blocks=[None, fine_block], level_objects=[(), (body,)]) as run:
         p = run.patch
         # Rest equilibrium is already postcollision G, so no initial collision is
         # needed. Non-leaf entries (covered, ghost, solid) are discarded by initialize.

examples/fixed_patch_jet.py

@@ -148,8 +148,8 @@ def main():
                   samples=[], status='running', last_synchronized_coarse_step=0)
     start, run = time.monotonic(), None
     try:
-        with CudaContext(0) as context, FixedPatchStepper(cfg, BOUNDS, context=context,
-                coarse_boundary='slot_reservoir') as run:
+        with CudaContext(0) as context, FixedPatchStepper(cfg, context=context,
+                coarse_boundary='slot_reservoir', refinements=[BOUNDS]) as run:
             p = run.patch
             masks = [np.ones(p.coarse_shape, bool), p.fine_kind == ACTIVE]
             masks[0][[0, -1]] = False

examples/fixed_periodic_patch.py

@@ -48,7 +48,7 @@ def main():
                   nx=16, ny=16, viscosity=.1, velocity=1e-3, rho=1.0,
                   lattice_model="D2Q9", collision="SRT", streaming="double_buffer",
                   store_precision="FP32", ddf_shifting=False, les_enabled=False)
-    with CudaContext(0) as context, PeriodicPatchStepper(cfg, (4, 4, 12, 12), context=context) as run:
+    with CudaContext(0) as context, PeriodicPatchStepper(cfg, context=context, refinements=[(4, 4, 12, 12)]) as run:
         p = run.patch
         coarse = shear_equilibrium(p.coarse_shape, (0, 0), 1.0, cfg.ny)
         fine = shear_equilibrium(p.fine_shape, p.fine_origin, .5, cfg.ny)

src/CelerisLab/lbm/block_stepper.py

@@ -204,11 +204,21 @@ class PeriodicBlockStepper:
                 raise
 
     def step(self, n=1):
-        """Advance n steps: halo refresh, then core pull/collide, per step."""
+        """Advance n steps: halo refresh, then core pull/collide, per step.
+
+        All n steps are enqueued in order on the one stream and the host waits
+        once before returning (same launches and bits as n step(1) calls).
+        Asynchronous device errors surface at that single wait, so they are not
+        attributed to the step that caused them; call step(1) repeatedly to
+        localize one. On any failure the instance is failed and step_count keeps
+        its entry value.
+        """
         if isinstance(n, bool) or not isinstance(n, Integral) or n < 0:
             raise ValueError("n must be a nonnegative integer")
         with self._lock, self.ctx.activate():
             self._require("ready")
+            if n == 0:
+                return
             kw = dict(block=self._block, stream=self._stream)
             try:
                 self._status = "advancing"
@@ -224,9 +234,9 @@ class PeriodicBlockStepper:
                     self._step(self._current, self._spare, np.uint32(self.layout.halo),
                                self._tables.get("flags", np.uintp(0)), np.uintp(0),  # no kind
                                grid=self._grid, **kw)
-                    self._stream.synchronize()
-                    self._current, self._spare = self._spare, self._current
-                    self._step_count += 1
+                    self._current, self._spare = self._spare, self._current  # host handles only
+                self._stream.synchronize()
+                self._step_count += n
                 self._status = "ready"
             except BaseException:
                 self._status = "failed"

src/CelerisLab/lbm/refinement_stepper.py

@@ -670,10 +670,9 @@ class FixedPatchStepper:
                 old, new, source, base_count=count, level_steps=(count, 2*count, 4*count),
                 phase="postcollision_g", **options)
             candidate = type(self)(
-                cfg, pairs[0].bounds, context=self.ctx, base_block=base_block,
-                fine_block=fine_block, child_block=child_block,
-                child_rectangles_in_parent=new.child.bounds,
-                child_objects=child_objects, child_jets=jets,
+                cfg, context=self.ctx, refinements=[pairs[0].bounds, new.child.bounds],
+                level_blocks=[base_block, fine_block, child_block],
+                level_objects=[(), (), child_objects], level_jets=[(), (), jets],
                 observe_raw_exchange=self._observe_raw_exchange,
                 observe_window_exchange=self._observe_window, explosion=self._explosion)
             try:
@@ -822,27 +821,41 @@ class FixedPatchStepper:
                             grid=((pairs + self._block[0] - 1) // self._block[0], 1), **kw)
 
     def step(self, n=1):
-        """Advance G→G by n base intervals: level l takes 2**l hops per interval."""
+        """Advance G→G by n base intervals: level l takes 2**l hops per interval.
+
+        All n intervals are enqueued in order on the one stream, and the host waits
+        once, before returning; step(0) launches and waits for nothing. On return
+        the device work is complete, step_count and an open window cover all n
+        intervals, and the raw-exchange ledger holds the final interval only.
+
+        Asynchronous device errors surface at that single wait, so they are not
+        attributed to the interval that caused them; call step(1) repeatedly to
+        localize one (same launches, same bits). On any failure the instance is
+        failed, the exchange ledger and window are invalid, and step_count keeps
+        its value from entry to the failing call.
+        """
         if isinstance(n, bool) or not isinstance(n, Integral) or n < 0:
             raise ValueError("n must be a nonnegative integer")
         with self._lock, self.ctx.activate():
             self._require("ready")
+            if n == 0:
+                return
             root = self._levels[0]
             kw = dict(block=self._block, stream=self._stream)
             try:
                 self._status = "advancing"
+                self._exchange_valid = False
                 for _ in range(n):
-                    if self._observe_raw_exchange:
-                        self._exchange_valid = False
+                    if self._observe_raw_exchange:  # stream-ordered: holds the last interval only
                         for b in self._level_boundaries:
                             if b is not None:
                                 cuda.memset_d8_async(b.interval_integral, 0,
                                                      len(b.tables["cell"]) * 32, self._stream)
                     self._hop(0, root.current, root.spare, **kw)
-                    self._stream.synchronize()
-                    root.current, root.spare = root.spare, root.current
-                    self._step_count += 1
-                    self._exchange_valid = self._observe_raw_exchange
+                    root.current, root.spare = root.spare, root.current  # host handles only
+                self._stream.synchronize()
+                self._step_count += n
+                self._exchange_valid = self._observe_raw_exchange
                 self._status = "ready"
             except BaseException:
                 self._window_valid = False

tests/unit/test_annulus_ledger.py

@@ -1,101 +0,0 @@
-"""Synthetic checks of the annulus mass ledger. Host-only, stdlib; not solver evidence."""
-
-import random
-import sys
-from pathlib import Path
-import unittest
-
-sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "validation"))
-import annulus_ledger as al  # noqa: E402
-
-NX = NY = 24
-# Annulus 4 <= r <= 8 around (12, 12); dyadic values keep every sum exact.
-A = {(x, y) for x in range(NX) for y in range(NY) if 16 <= (x - 12) ** 2 + (y - 12) ** 2 <= 64}
-DELTA = 0.375
-
-
-def owner(seed=1):
-    rng = random.Random(seed)
-    return [[[rng.randint(1, 1024) / 1024 for _ in range(NX)] for _ in range(NY)] for _ in range(9)]
-
-
-def collide(P, source=None):
-    """Mass-conserving stand-in: rotate populations within each cell (+ optional source)."""
-    D = [[[P[(q + 1) % 9][y][x] for x in range(NX)] for y in range(NY)] for q in range(9)]
-    if source:
-        (x, y), s = source
-        D[0][y][x] += s
-    return D
-
-
-def link(interior):
-    """(x, y, q) with x in A and x - c_q inside (seam) or outside (edge) A."""
-    for (x, y) in sorted(A):
-        for q in range(1, 9):
-            src = ((x - al.CX[q]) % NX, (y - al.CY[q]) % NY)
-            if (src in A) == interior:
-                return x, y, q
-    raise AssertionError
-
-
-class Ledger(unittest.TestCase):
-    def setUp(self):
-        self.O = owner()
-        self.P = al.pull(self.O, NX, NY)
-
-    def run_ledger(self, P, D):
-        return al.ledger(self.O, P, D, A, NX, NY)
-
-    def test_ideal_pull_has_no_h_and_closes(self):
-        r = self.run_ledger(self.P, collide(self.P))
-        self.assertEqual((r["H_seam"], r["H_edge"], r["C"], r["residual"]), (0, 0, 0, 0))
-        self.assertEqual(r["dM"], -r["Q_exact"])
-        self.assertNotEqual(r["Q_exact"], 0)
-
-    def test_collision_source_is_c(self):
-        x, y = sorted(A)[3]
-        r = self.run_ledger(self.P, collide(self.P, ((x, y), DELTA)))
-        self.assertEqual((r["C"], r["H"], r["residual"]), (DELTA, 0, 0))
-
-    def test_interior_seam_perturbation(self):
-        x, y, q = link(interior=True)
-        self.P[q][y][x] += DELTA
-        r = self.run_ledger(self.P, collide(self.P))
-        self.assertEqual((r["H_seam"], r["H_edge"], r["residual"]), (DELTA, 0, 0))
-        # Invisible to any flux through the edge of A; only H explains the mass change.
-        self.assertEqual(al.staged_flux(self.O, self.P, A, NX, NY), r["Q_exact"])
-        self.assertEqual(r["dM"] + r["Q_exact"], DELTA)
-
-    def test_edge_perturbation_and_staged_flux_double_count(self):
-        x, y, q = link(interior=False)
-        self.P[q][y][x] += DELTA
-        r = self.run_ledger(self.P, collide(self.P))
-        self.assertEqual((r["H_seam"], r["H_edge"], r["residual"]), (0, DELTA, 0))
-        staged = al.staged_flux(self.O, self.P, A, NX, NY)
-        self.assertEqual(staged, r["Q_exact"] - DELTA)
-        # Staged flux + full H counts the staging change twice.
-        self.assertEqual(r["dM"] + staged - r["C"] - r["H"], -DELTA)
-        # Staged flux alone closes only without the edge part of H.
-        self.assertEqual(r["dM"] + staged - r["C"] - r["H_seam"], 0)
-
-    def test_owner_snapshot_after_staging_hides_the_change(self):
-        # Snapshot taken after staging wrote the same slot into the owner image.
-        x, y, q = link(interior=False)
-        sx, sy = (x - al.CX[q]) % NX, (y - al.CY[q]) % NY
-        self.P[q][y][x] += DELTA
-        late = [[row[:] for row in plane] for plane in self.O]
-        late[q][sy][sx] += DELTA
-        r = al.ledger(late, self.P, collide(self.P), A, NX, NY)
-        self.assertEqual((r["H"], r["residual"]), (0, 0))
-
-    def test_wrong_pull_direction_is_flagged(self):
-        # Indexing error (push instead of pull): H is nonzero with no physical cause.
-        bad = [[[self.O[q][(y + al.CY[q]) % NY][(x + al.CX[q]) % NX] for x in range(NX)]
-                for y in range(NY)] for q in range(9)]
-        r = self.run_ledger(bad, collide(bad))
-        self.assertNotEqual(r["H"], 0)
-        self.assertEqual(r["residual"], 0)
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_block_step_sync.py

@@ -0,0 +1,102 @@
+"""Host contract of PeriodicBlockStepper.step(n): one stream wait per call (mocked driver)."""
+import ast
+from contextlib import nullcontext
+from pathlib import Path
+import types
+from unittest.mock import Mock
+import unittest
+
+import numpy as np
+
+import CelerisLab.lbm.block_stepper as b
+from CelerisLab.config import LBMConfig
+from CelerisLab.lbm.blocks import BlockLayout2D
+
+
+def host_module():
+    """block_stepper with pycuda/compiler replaced by mocks; no GPU context."""
+    path = Path(b.__file__)
+    tree = ast.parse(path.read_text())
+    tree.body = [node for node in tree.body if not (
+        isinstance(node, ast.Import) and any(a.name == "pycuda.driver" for a in node.names)
+        or isinstance(node, ast.ImportFrom) and node.module == "cuda")]
+    module = types.ModuleType("CelerisLab.lbm._test_host_block_stepper")
+    module.__package__ = "CelerisLab.lbm"
+    module.__dict__.update(cuda=Mock(), compiler=Mock())
+    exec(compile(tree, str(path), "exec"), module.__dict__)
+    return module
+
+
+def backend():
+    host, log = host_module(), []
+    host.cuda.mem_get_info.return_value = (1 << 40, 1 << 40)
+    host.cuda.mem_alloc.side_effect = lambda size: Mock(size=size)  # distinct buffers
+    module = Mock()
+    module.get_global.return_value = (Mock(), 20)
+    module.get_function.side_effect = lambda name: Mock(
+        side_effect=lambda *a, **k: log.append((name, a[:2])))
+    host.compiler.load_module.return_value = module
+    cfg = LBMConfig(nx=16, ny=16, viscosity=.1)
+    run = host.PeriodicBlockStepper(cfg, BlockLayout2D.build(16, 16, 8, 8),
+                                    context=Mock(activate=nullcontext, sm_arch="sm_70"))
+    run._stream.synchronize.side_effect = lambda: log.append(("sync", ()))
+    run.initialize(np.full((9, 16, 16), 1 / 9))
+    log.clear()
+    return run, log
+
+
+class BlockStepSync(unittest.TestCase):
+    def test_step_n_waits_once_and_matches_n_single_steps(self):
+        many, log_many = backend()
+        many.step(3)
+        single, log_single = backend()
+        for _ in range(3):
+            single.step(1)
+        names = [name for name, _ in log_many]
+        self.assertEqual(names.count("sync"), 1)
+        self.assertEqual(names[-1], "sync")
+        self.assertEqual(names.count("BlockStep"), 3)
+        # Same launch order and buffer roles as three step(1) calls.
+        strip = lambda log: [(n, tuple(id(x) for x in a)) for n, a in log if n != "sync"]
+        roles = lambda run, log: [(n, tuple({id(run._current): "c", id(run._spare): "s"}.get(x, "-")
+                                            for x in ids)) for n, ids in strip(log)]
+        self.assertEqual([n for n, _ in strip(log_many)], [n for n, _ in strip(log_single)])
+        self.assertEqual(roles(many, log_many), roles(single, log_single))
+        self.assertIsNot(many._current, many._spare)
+        self.assertEqual((many.step_count, single.step_count), (3, 3))
+
+    def test_step_zero_launches_and_waits_for_nothing(self):
+        run, log = backend()
+        run.step(0)
+        self.assertEqual((log, run.step_count), ([], 0))
+
+    def test_failure_keeps_entry_step_count(self):
+        run, log = backend()
+        run.step(1)
+        run._stream.synchronize.side_effect = RuntimeError("device fault")
+        with self.assertRaises(RuntimeError):
+            run.step(2)
+        self.assertEqual((run.step_count, run._status), (1, "failed"))
+
+    def test_launch_failure_mid_batch_fails_closed_without_waiting(self):
+        run, log = backend()
+        calls = []
+        step = run._step
+
+        def failing(*args, **kwargs):
+            calls.append(1)
+            if len(calls) == 2:
+                raise RuntimeError("launch failure")
+            return step(*args, **kwargs)
+
+        run._step = failing
+        with self.assertRaises(RuntimeError):
+            run.step(3)
+        self.assertNotIn("sync", [name for name, _ in log])
+        self.assertEqual((run.step_count, run._status), (0, "failed"))
+        with self.assertRaises(RuntimeError):
+            run.download()
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_channel_root.py

@@ -80,8 +80,8 @@ def test_evolved_ghost_snapshot_and_physical_download():
     host.cuda.memcpy_dtoh.side_effect = lambda a, ptr: np.copyto(a, storage[id(ptr)])
     context = Mock(activate=nullcontext, sm_arch="sm_70")
     cfg = LBMConfig(nx=24, ny=20, viscosity=.1, velocity=.025)
-    backend = host.FixedPatchStepper(cfg, (6, 6, 18, 14), context=context,
-                                    coarse_boundary="channel", base_block=(4, 6), fine_block=(4, 4))
+    backend = host.FixedPatchStepper(cfg, context=context, coarse_boundary="channel",
+                                    refinements=[(6, 6, 18, 14)], level_blocks=[(4, 6), (4, 4)])
     try:
         weights = np.array([4/9]+[1/9]*4+[1/36]*4)[:, None, None]
         arrays = [np.broadcast_to(weights, level.shape).copy() for level in backend._levels]

tests/unit/test_raw_exchange.py

@@ -157,8 +157,9 @@ class RawExchange(unittest.TestCase):
         host = host_module()
         ctx = Mock()
         with self.assertRaisesRegex(ValueError, 'blocked body'):
-            host.FixedPatchStepper(LBMConfig(nx=32, ny=32, viscosity=.1), (4, 4, 28, 28),
-                                   context=ctx, fine_objects=[body(radius=2.15)], observe_raw_exchange=True)
+            host.FixedPatchStepper(LBMConfig(nx=32, ny=32, viscosity=.1), context=ctx,
+                                   refinements=[(4, 4, 28, 28)],
+                                   level_objects=[(), (body(radius=2.15),)], observe_raw_exchange=True)
         ctx.activate.assert_not_called()
 
     def test_all_depth_weights(self):

tests/unit/test_refinement_three_level_multipatch.py

@@ -173,8 +173,10 @@ def bodies_and_jets(speed=.002):
     return bodies,jets
 
 
-KW=dict(base_block=(4,4),fine_block=(4,4),child_block=(4,4),
-        child_rectangles_in_parent=CHILDREN)
+def levels(parents=PARENTS,children=CHILDREN,blocks=((4,4),)*3,objects=((),(),()),jets=((),(),())):
+    """Level-list constructor keywords for the L0 set, L1 set and L2 set used here."""
+    return dict(refinements=[parents,children],level_blocks=list(blocks),
+                level_objects=list(objects),level_jets=list(jets))
 
 
 def mock_backend(*, children=CHILDREN, bodies=False, fail_compile=False, fail_upload=False):
@@ -201,9 +203,8 @@ def mock_backend(*, children=CHILDREN, bodies=False, fail_compile=False, fail_up
         module.cuda.memcpy_htod.side_effect=upload
     objects,jets=bodies_and_jets() if bodies else ((),())
     try:
-        run=module.FixedPatchStepper(CFG,PARENTS,context=context,
-            child_objects=objects,child_jets=jets,
-            **dict(KW,child_rectangles_in_parent=children))
+        run=module.FixedPatchStepper(CFG,context=context,
+            **levels(children=children,objects=((),(),objects),jets=((),(),jets)))
     except RuntimeError:
         for allocation in allocations:
             allocation.free.assert_called_once_with()
@@ -214,28 +215,29 @@ def mock_backend(*, children=CHILDREN, bodies=False, fail_compile=False, fail_up
 class ConstructorAndSchedule(unittest.TestCase):
     def test_invalid_inputs_fail_before_context_or_allocations(self):
         context=Mock()
-        cases=[dict(child=(8,8,16,16)),dict(child_rectangles_in_parent=[]),
-               dict(child_rectangles_in_parent=[(16,16,32)]),
-               dict(child_rectangles_in_parent=[(16.5,16,32,40)]),
-               dict(child_rectangles_in_parent=[(16,16,32,24),(16,27,32,55)]),
-               dict(child_rectangles_in_parent=[(40,16,48,40)]),
-               dict(child_rectangles_in_parent=[(8,16,32,40)]),
-               dict(child_block=None),dict(fine_block=None),dict(base_block=None),
-               dict(child_block=(5,4)),dict(fine_block=(5,4)),
-               dict(child_block=(4,)),dict(child_rectangles_in_parent=(16,16,32,40))]
+        b=(4,4)
+        cases=[dict(children=(8,8,16,16)),dict(children=[]),
+               dict(children=[(16,16,32)]),
+               dict(children=[(16.5,16,32,40)]),
+               dict(children=[(16,16,32,24),(16,27,32,55)]),
+               dict(children=[(40,16,48,40)]),
+               dict(children=[(8,16,32,40)]),
+               dict(blocks=(b,b,None)),dict(blocks=(b,None,b)),dict(blocks=(None,b,b)),
+               dict(blocks=(b,b,(5,4))),dict(blocks=(b,(5,4),b)),
+               dict(blocks=(b,b,(4,))),dict(children=(16,16,32,40))]
         for changes in cases:
             with self.subTest(changes=changes),self.assertRaises((ValueError,TypeError)):
-                host.FixedPatchStepper(CFG,PARENTS,context=context,**dict(KW,**changes))
+                host.FixedPatchStepper(CFG,context=context,**levels(**changes))
         with self.assertRaisesRegex(ValueError,'margin'):
-            host.FixedPatchStepper(CFG,[(1,4,20,28),(23,4,44,28)],context=context,**KW)
+            host.FixedPatchStepper(CFG,context=context,**levels(parents=[(1,4,20,28),(23,4,44,28)]))
         objects,jets=bodies_and_jets()
-        with self.assertRaisesRegex(ValueError,'only on L2'):
-            host.FixedPatchStepper(CFG,PARENTS,context=context,fine_objects=objects,**KW)
+        with self.assertRaisesRegex(ValueError,'only on the finest level'):
+            host.FixedPatchStepper(CFG,context=context,**levels(objects=((),objects,())))
         from CelerisLab.body.jets import Jet,Tube,Parallel
         spanning=Jet(Tube((10.5,14.),0.,25.,.3),Parallel(0.),amplitude=0.)
         with self.assertRaisesRegex(ValueError,'one jet'):
-            host.FixedPatchStepper(CFG,PARENTS,context=context,child_objects=objects,
-                                  child_jets=[spanning],**KW)
+            host.FixedPatchStepper(CFG,context=context,
+                                  **levels(objects=((),(),objects),jets=((),(),[spanning])))
         context.activate.assert_not_called()
         host.cuda.mem_alloc.assert_not_called()
 

tests/unit/test_shifted_jets.py

@@ -54,14 +54,13 @@ class ShiftedJets(unittest.TestCase):
                 (Jet(Tube((10.,14.),0.,26.,.3),Parallel(0.)),))]
         for objects,jets in cases:
             with self.subTest(objects=len(objects),jets=len(jets)),self.assertRaises(ValueError):
-                module.FixedPatchStepper(CFG,backend.PARENTS,context=None,
-                    base_block=(4,4),fine_block=(4,4),child_block=(4,4),
-                    child_rectangles_in_parent=A,child_objects=objects,child_jets=jets)
+                module.FixedPatchStepper(CFG,context=None,refinements=[backend.PARENTS,A],
+                    level_blocks=[(4,4)]*3,level_objects=[(),(),objects],level_jets=[(),(),jets])
         for blocks in ((None,None,None),((4,4),None,(4,4))):
             with self.assertRaises(ValueError):
-                module.FixedPatchStepper(CFG,backend.PARENTS,context=None,
-                    base_block=blocks[0],fine_block=blocks[1],child_block=blocks[2],
-                    child_rectangles_in_parent=A,child_objects=(body(),),child_jets=(jet(),))
+                module.FixedPatchStepper(CFG,context=None,refinements=[backend.PARENTS,A],
+                    level_blocks=list(blocks),level_objects=[(),(),(body(),)],
+                    level_jets=[(),(),(jet(),)])
         module.cuda.mem_alloc.assert_not_called()
         module.compiler.compile_kernel.assert_not_called()
 

tests/unit/test_shifted_storage.py

@@ -129,9 +129,10 @@ class ShiftedStorage(unittest.TestCase):
     def test_dense_or_mixed_shifted_rejected_before_compilation(self):
         module=backend.host_module()
         cfg=replace(backend.CFG,ddf_shifting=True)
-        for kwargs in ({},dict(base_block=(4,4)),dict(fine_block=(4,4))):
-            with self.assertRaisesRegex(ValueError,'all-blocked|base_block requires fine_block'):
-                module.FixedPatchStepper(cfg,(4,4,20,28),context=None,**kwargs)
+        for blocks in ([None,None],[(4,4),None],[None,(4,4)]):
+            with self.assertRaisesRegex(ValueError,'all-blocked|blocked refined levels below'):
+                module.FixedPatchStepper(cfg,context=None,refinements=[(4,4,20,28)],
+                                         level_blocks=blocks)
         module.compiler.compile_kernel.assert_not_called()
 
     def test_uniform_block_codec_and_raw_snapshot(self):

tests/unit/test_step_sync.py

@@ -0,0 +1,170 @@
+"""Host contract of FixedPatchStepper.step(n): one stream wait per call (mocked driver).
+
+All n base intervals are enqueued in order on the backend stream and the host
+waits once before step returns. Launch order and buffer arguments must equal n
+step(1) calls; completion metadata, raw-exchange and window ledgers, and failure
+invalidation are published only after that wait.
+"""
+from contextlib import nullcontext
+from unittest.mock import Mock
+import unittest
+
+import numpy as np
+
+from CelerisLab.config import LBMConfig
+from tests.unit.test_raw_exchange import body
+from tests.unit.test_refinement_three_level_multipatch import host_module
+
+BODY_LEVEL, HOPS = 3, 8  # body on L3: 2**3 hops per base interval
+
+
+def backend(window=False):
+    """Four-level host backend; every launch, memset and stream wait goes to one log."""
+    host = host_module()
+    log, allocations = [], []
+
+    def allocate(size):
+        allocations.append(Mock(size=size))
+        return allocations[-1]
+
+    module = Mock()
+    module.get_global.return_value = (Mock(), 20)
+    module.get_function.side_effect = lambda name: Mock(
+        side_effect=lambda *a, **k: log.append((name, a, k)))
+    host.compiler.load_module.return_value = module
+    host.cuda.mem_alloc.side_effect = allocate
+    host.cuda.memcpy_dtoh.side_effect = lambda array, pointer: array.fill(0)
+    host.cuda.memset_d8_async.side_effect = lambda *a: log.append(("memset", a, {}))
+    run = host.FixedPatchStepper(
+        LBMConfig(nx=48, ny=48, viscosity=.02), context=Mock(activate=nullcontext, sm_arch="sm_70"),
+        refinements=[[(6, 6, 26, 26)], [(20, 20, 44, 44)], [(56, 56, 72, 72)]],
+        level_blocks=[(4, 4)] * 4, level_objects=[(), (), (), (body(),)],
+        observe_raw_exchange=True, observe_window_exchange=window)
+    run._stream.synchronize.side_effect = lambda: log.append(("sync", (), {}))
+    run.initialize(*[np.full(level.shape, 1 / 9, np.float32) for level in run._levels])
+    log.clear()
+    return run, log, allocations
+
+
+def signature(log, allocations):
+    """Event names with device-pointer arguments replaced by allocation index."""
+    index = {id(a): i for i, a in enumerate(allocations)}
+    return [(name, tuple(index.get(id(a), "-") for a in args)) for name, args, _ in log]
+
+
+def names(log):
+    return [name for name, _, _ in log]
+
+
+class StepSync(unittest.TestCase):
+    def test_step1_waits_once_after_all_launches(self):
+        run, log, _ = backend()
+        run.step(1)
+        self.assertEqual(names(log).count("sync"), 1)
+        self.assertEqual(names(log)[-1], "sync")
+        self.assertEqual(names(log)[0], "memset")
+        self.assertEqual(names(log).count("BlockStep"), 1 + 2 + 4 + 8)
+        self.assertEqual(run.step_count, 1)
+        run.close()
+
+    def test_step_n_equals_n_step1_launches_with_one_wait(self):
+        single, single_log, single_alloc = backend()
+        for _ in range(3):
+            single.step(1)
+        batched, batched_log, batched_alloc = backend()
+        batched.step(3)
+        expected = [e for e in signature(single_log, single_alloc) if e[0] != "sync"]
+        got = signature(batched_log, batched_alloc)
+        self.assertEqual(got[-1][0], "sync")
+        self.assertEqual(names(batched_log).count("sync"), 1)
+        self.assertEqual(got[:-1], expected)  # same order, same ping-pong buffers
+        self.assertEqual(names(batched_log).count("memset"), 3)
+        self.assertEqual(batched.step_count, single.step_count)
+        index = [{id(a): i for i, a in enumerate(alloc)} for alloc in (single_alloc, batched_alloc)]
+        self.assertEqual(index[1][id(batched._levels[0].current)],
+                         index[0][id(single._levels[0].current)])
+        single.close()
+        batched.close()
+
+    def test_step0_launches_and_waits_for_nothing(self):
+        run, log, _ = backend()
+        run.step(2)
+        log.clear()
+        run.step(0)
+        self.assertEqual(log, [])
+        self.assertEqual(run.step_count, 2)
+        value = run.read_raw_exchange(0, level=BODY_LEVEL)  # step(0) keeps the ledger valid
+        self.assertEqual((value["time_start"], value["time_end"]), (1, 2))
+        run.close()
+
+    def test_completion_metadata_covers_all_intervals(self):
+        run, _, _ = backend()
+        with self.assertRaisesRegex(RuntimeError, "completed"):
+            run.read_raw_exchange(0, level=BODY_LEVEL)
+        run.step(3)
+        value = run.read_raw_exchange(0, level=BODY_LEVEL)
+        self.assertEqual((value["time_start"], value["time_end"], value["sample_count"]),
+                         (2, 3, HOPS))  # step(n) retains only the final base interval
+        run.step(2)
+        self.assertEqual(run.read_raw_exchange(0, level=BODY_LEVEL)["time_end"], 5)
+        run.close()
+
+    def test_window_accounting_across_batched_calls(self):
+        windows = []
+        for calls in ((1, 3), (4,), (1, 1, 1, 1)):
+            run, log, _ = backend(window=True)
+            run.step(1)
+            run.start_exchange_window()
+            log.clear()
+            for n in calls:
+                run.step(n)
+            self.assertEqual(names(log).count("BlockAccumulateExchange"), 2 * 4 * HOPS)
+            self.assertEqual(names(log).count("sync"), len(calls))
+            out = run.read_exchange_window(0, level=BODY_LEVEL)
+            windows.append((out["time_start"], out["time_end"], out["sample_count"]))
+            run.close()
+        self.assertEqual(windows, [(1., 5, 4 * HOPS)] * 3)
+
+    def test_failed_wait_publishes_nothing(self):
+        run, _, _ = backend(window=True)
+        run.step(2)
+        run.start_exchange_window()
+        run._stream.synchronize.side_effect = RuntimeError("device failure")
+        with self.assertRaisesRegex(RuntimeError, "device failure"):
+            run.step(3)
+        self.assertEqual(run.step_count, 2)  # value at entry to the failing call
+        self.assertFalse(run._exchange_valid)
+        self.assertFalse(run._window_valid)
+        for read in (lambda: run.read_raw_exchange(0, level=BODY_LEVEL),
+                     lambda: run.read_exchange_window(0, level=BODY_LEVEL), run.download,
+                     lambda: run.step(1)):
+            with self.assertRaisesRegex(RuntimeError, "failed"):
+                read()
+        run._stream.synchronize.side_effect = None
+        run.close()
+
+    def test_launch_error_mid_batch_skips_wait_and_fails(self):
+        run, log, _ = backend()
+        run.step(1)
+        log.clear()
+        hop, calls = run._hop, []
+
+        def failing(index, *args, **kw):
+            if index == 0:
+                calls.append(1)
+                if len(calls) == 2:
+                    raise RuntimeError("launch failure")
+            return hop(index, *args, **kw)
+        run._hop = failing
+        with self.assertRaisesRegex(RuntimeError, "launch failure"):
+            run.step(3)
+        self.assertNotIn("sync", names(log))
+        self.assertEqual(run.step_count, 1)
+        self.assertFalse(run._exchange_valid)
+        with self.assertRaisesRegex(RuntimeError, "failed"):
+            run.read_raw_exchange(0, level=BODY_LEVEL)
+        run.close()
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/validation/annulus_ledger.py

@@ -1,75 +0,0 @@
-"""Per-hop mass ledger of a fluid cell set A (host-only, stdlib, D2Q9 pull scheme).
-
-Diagnostic definition only; no solver code, no GPU. Arrays are indexed [q][y][x] on a
-periodic nx x ny lattice; A is a set of (x, y) ACTIVE cells.
-
-  O  owner populations before any staging (canonical owner slots, start of the hop)
-  P  populations each cell actually pulls: P[q](x) is what x reads for direction q
-     (after halo copy, BFL/coalesce staging, ...)
-  D  populations written by the cell after collision
-
-With M0 = sum_{A,q} O and M1 = sum_{A,q} D (both owner snapshots of A):
-
-  M1 - M0 + Q_exact = C + H                                            (exact)
-
-  C       = sum_{x in A, q} (D_q(x) - P_q(x))              collision source
-  H       = sum_{x in A, q} (P_q(x) - O_q(x - c_q))        actual minus ideal owner input,
-            split into H_seam (x - c_q in A: internal pulls, e.g. tile seams) and
-            H_edge (x - c_q not in A: inputs crossing the edge of A)
-  Q_exact = sum_{y in A, y+c_q not in A} O_q(y) - sum_{y not in A, y+c_q in A} O_q(y)
-            owner-based net outward flux (outgoing minus incoming)
-
-Proof: sum_{A,q} O_q(x - c_q) - M0 = -Q_exact (relabel y = x - c_q per direction), and
-sum_{A,q} D = C + H + sum_{A,q} O_q(x - c_q). Q_exact must use O, not staged values: a
-flux built from staged inputs already contains H_edge, so adding the full H counts it
-twice (see staged_flux). The edge of A must not cross cut links, otherwise O at the solid
-end enters Q_exact.
-"""
-
-CX = (0, 1, -1, 0, 0, 1, -1, 1, -1)
-CY = (0, 0, 0, 1, -1, 1, -1, -1, 1)
-
-
-def _src(x, y, q, nx, ny):
-    return (x - CX[q]) % nx, (y - CY[q]) % ny
-
-
-def pull(O, nx, ny):
-    """Ideal pulled input: P[q](x) = O[q](x - c_q)."""
-    return [[[O[q][_src(x, y, q, nx, ny)[1]][_src(x, y, q, nx, ny)[0]]
-              for x in range(nx)] for y in range(ny)] for q in range(9)]
-
-
-def ledger(O, P, D, A, nx, ny):
-    A = set(A)
-    out = dict(dM=0.0, C=0.0, H_seam=0.0, H_edge=0.0, Q_exact=0.0)
-    for (x, y) in A:
-        for q in range(9):
-            out["dM"] += D[q][y][x] - O[q][y][x]
-            out["C"] += D[q][y][x] - P[q][y][x]
-            sx, sy = _src(x, y, q, nx, ny)
-            key = "H_seam" if (sx, sy) in A else "H_edge"
-            out[key] += P[q][y][x] - O[q][sy][sx]
-            if (sx, sy) not in A:
-                out["Q_exact"] -= O[q][sy][sx]          # incoming owner population
-            tx, ty = (x + CX[q]) % nx, (y + CY[q]) % ny
-            if (tx, ty) not in A:
-                out["Q_exact"] += O[q][y][x]            # outgoing owner population
-    out["H"] = out["H_seam"] + out["H_edge"]
-    out["residual"] = out["dM"] + out["Q_exact"] - out["C"] - out["H"]
-    return out
-
-
-def staged_flux(O, P, A, nx, ny):
-    """Outward flux with incoming terms from the staged inputs P (the wrong combination)."""
-    A = set(A)
-    q_out = 0.0
-    for (x, y) in A:
-        for q in range(9):
-            sx, sy = _src(x, y, q, nx, ny)
-            if (sx, sy) not in A:
-                q_out -= P[q][y][x]
-            tx, ty = (x + CX[q]) % nx, (y + CY[q]) % ny
-            if (tx, ty) not in A:
-                q_out += O[q][y][x]
-    return q_out

tests/validation/run_dfg_re20.py

@@ -126,8 +126,8 @@ def run_case(a, h, case):
             cfg, pair, body, host = rr.host_geometry(a.source, h, a.collision)
             context = stack.enter_context(CudaContext(0))
             backend = stack.enter_context(FixedPatchStepper(
-                cfg, rr.PLACEMENTS["wide"], context=context, coarse_boundary="channel",
-                base_block=rr.BASE_BLOCK, fine_block=rr.FINE_BLOCK, fine_objects=(body,),
+                cfg, context=context, coarse_boundary="channel", refinements=[rr.PLACEMENTS["wide"]],
+                level_blocks=[rr.BASE_BLOCK, rr.FINE_BLOCK], level_objects=[(), (body,)],
                 observe_raw_exchange=True, observe_window_exchange=True))
             from CelerisLab.lbm.channel import channel_masks
             from CelerisLab.lbm.refinement import ACTIVE

tests/validation/run_jet_circle_cv.py

@@ -279,12 +279,11 @@ def run_case(c, ctx, output, provenance, continuation=False):
         PeriodicBlockStepper(fine_cfg, layout, context=ctx, objects=[fobj]) as uniform,
         FixedPatchStepper(
             cfg,
-            c["bounds"],
             context=ctx,
-            base_block=(8, 8),
-            fine_block=(8, 8),
-            fine_objects=[obj],
-            jets=jets,
+            refinements=[c["bounds"]],
+            level_blocks=[(8, 8), (8, 8)],
+            level_objects=[(), (obj,)],
+            level_jets=[(), tuple(jets)],
             observe_raw_exchange=True,
         ) as amr,
     ):

tests/validation/run_refined_dfg.py

@@ -383,13 +383,12 @@ def run_case(a, h, periodic, case):
             backend = stack.enter_context(
                 FixedPatchStepper(
                     cfg,
-                    PLACEMENTS[a.placement],
                     context=context,
                     coarse_boundary="channel",
-                    base_block=BASE_BLOCK,
-                    fine_block=FINE_BLOCK,
-                    fine_objects=(body,),
-                    jets=public_jets((80.5, 81.0), 20.0, a.jet_scenario),
+                    refinements=[PLACEMENTS[a.placement]],
+                    level_blocks=[BASE_BLOCK, FINE_BLOCK],
+                    level_objects=[(), (body,)],
+                    level_jets=[(), public_jets((80.5, 81.0), 20.0, a.jet_scenario)],
                     observe_raw_exchange=True,
                     **({"observe_window_exchange": True} if a.observation_mode == "window" else {}),
                 )

tests/validation/time_refined_dfg.py

@@ -173,8 +173,9 @@ def time_refined(a, h, sched):
         cfg, pair, body, host = r.host_geometry(a.source, h, "MRT")
         context = stack.enter_context(CudaContext(0))
         backend = stack.enter_context(FixedPatchStepper(
-            cfg, r.BOUNDS, context=context, coarse_boundary="channel", base_block=r.BASE_BLOCK,
-            fine_block=r.FINE_BLOCK, fine_objects=(body,), observe_raw_exchange=True))
+            cfg, context=context, coarse_boundary="channel", refinements=[r.BOUNDS],
+            level_blocks=[r.BASE_BLOCK, r.FINE_BLOCK], level_objects=[(), (body,)],
+            observe_raw_exchange=True))
         masks = [channel_masks(pair.coarse_shape)[0] & ~pair.covered,  # as run_refined_dfg
                  (pair.fine_kind == ACTIVE) & ((host.flags.reshape(pair.fine_shape) & SOLID) == 0)]
         fresh = (r.initial_state(pair.coarse_shape, (0.0, 0.0), 1.0, root=True),

tests/validation/time_window_dfg.py

@@ -130,8 +130,8 @@ def main():
         cfg, pair, body, host = r.host_geometry(a.source, h, "MRT")
         context = stack.enter_context(CudaContext(0))
         backend = stack.enter_context(FixedPatchStepper(
-            cfg, r.BOUNDS, context=context, coarse_boundary="channel", base_block=r.BASE_BLOCK,
-            fine_block=r.FINE_BLOCK, fine_objects=(body,), observe_raw_exchange=True,
+            cfg, context=context, coarse_boundary="channel", refinements=[r.BOUNDS],
+            level_blocks=[r.BASE_BLOCK, r.FINE_BLOCK], level_objects=[(), (body,)], observe_raw_exchange=True,
             observe_window_exchange=True))
         masks = [channel_masks(pair.coarse_shape)[0] & ~pair.covered,
                  (pair.fine_kind == ACTIVE) & ((host.flags.reshape(pair.fine_shape) & SOLID) == 0)]