test: annulus mass ledger definition with synthetic seam/edge checks

Host-only stdlib definition of the per-hop identity dM + Q_exact = C + H with Q_exact from pre-staging owner populations and H = sum over every annulus cell/direction of (pulled - ideal owner input), split into seam (internal) and edge parts. Synthetic tests: ideal pull, collision source, interior-seam and edge perturbations, the double count of staged flux + full H, a late owner snapshot hiding staging, and a wrong pull direction. No solver change, no GPU. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 18:32:42 +00:00
75 changed files with 962 additions and 1540 deletions
@@ -112,9 +112,8 @@ from CelerisLab.lbm.refinement_stepper import FixedPatchStepper
 cfg = LBMConfig(nx=32, ny=24, viscosity=.1)
 body = SimObject(0, geometry=CircleGeometry(16.0, 12.0, 2.15), center=(16.0, 12.0), radius=2.15,
                 surface_actuation=SurfaceActuation(0.7, 0.85, 0.002))  # angle, half-width, speed
-with CudaContext(0) as ctx, FixedPatchStepper(cfg, context=ctx, refinements=[(8, 6, 24, 18)],
-                                              level_blocks=[None, (16, 20)],
-                                              level_objects=[(), (body,)]) as run:
+with CudaContext(0) as ctx, FixedPatchStepper(cfg, (8, 6, 24, 18), context=ctx,
+                                              fine_objects=[body], fine_block=(16, 20)) as run:
    rest = np.asarray(compute_feq_d2q9(1.0, 0.0, 0.0), np.float32)[:, None, None]
    # (9, ny, nx) postcollision populations per level; non-leaf cells are discarded.
    run.initialize(np.broadcast_to(rest, (9, *run.patch.coarse_shape)),
@@ -125,8 +124,8 @@ with CudaContext(0) as ctx, FixedPatchStepper(cfg, context=ctx, refinements=[(8,

 Scope and limits:
 - The examples below use D2Q9, SRT, FP32, double buffer, unshifted, no LES or
-  forcing. Fixed 2:1 hierarchies use level lists of arbitrary depth; two- and
-  three-level examples below use that same constructor.
+  forcing. Fixed 2:1 hierarchies can use level lists of arbitrary depth; the
+  legacy two/three-level forms are shown below.
 - `coarse_boundary="periodic"` (default) or `"slot_reservoir"` (bottom slot, top
  reservoir; patch needs `y0 >= 4`, `y1 <= ny-4`). Periodic mode ignores the wall/slot config fields.
 - Object centers/radii use the coarse **cell-edge** frame (cell `I` spans `[I, I+1)`),
@@ -134,51 +133,50 @@ Scope and limits:
 - Bodies must be stationary circles whose whole boundary stencil lies in the fine
  active region, clear of the coarse/fine transfer cells; violations are rejected
  before any GPU allocation.
- `level_blocks=[None, (by, bx)]` stores the fine level in fixed-size blocks; `by`/`bx` must
+- `fine_block=(by, bx)` stores the fine level in fixed-size blocks; `by`/`bx` must
  divide the WHOLE fine allocation, i.e. `2*(y1-y0)+8` by `2*(x1-x0)+8` including the
  four-cell ghost band. It gives results identical to dense storage and is
  infrastructure for future block AMR, not a speedup.
 - Several regions: pass a sequence of `(x0, y0, x1, y1)` rectangles as
-  `refinements[0]`, with both levels blocked (`level_blocks`). Transfers are built once
+  `bounds`, with both `fine_block` and `base_block`. Transfers are built once
  from their union; adjacent, overlapping and concave unions are accepted when
  their actual dependencies close. There is no fixed rectangle-gap rule.
  The fine level is then one level-wide grid `(2*ny, 2*nx)`:
  `run.patch.fine_shape` gives it, `initialize`/`download` use it, and only the
  grid-aligned tiles intersecting the union plus its four-cell ghost band are stored.
  Block sizes must divide the level-wide grid; rectangle edges need not align
-  with tiles. Order of rectangles does not matter. L1 bodies/Jets (`level_objects[1]`/`level_jets[1]`) work
+  with tiles. Order of rectangles does not matter. `fine_objects`/`jets` work
  as for one patch: each circle (same coarse cell-edge frame) must lie wholly
  inside the union's active region with
  its boundary stencil clear of transfer cells; a jet may not select links of two
  different bodies, even across regions. Wall-touching patches remain unsupported.
-  For nesting, add further `refinements` entries as shown below.
+  For nesting, use the level lists or legacy child forms below.

  ```python
  cfg = LBMConfig(nx=32, ny=16, viscosity=.1)
  rest = np.asarray(compute_feq_d2q9(1.0, 0.0, 0.0), np.float32)[:, None, None]
  with CudaContext(0) as ctx, FixedPatchStepper(
-          cfg, context=ctx, refinements=[((4, 4, 12, 12), (16, 4, 24, 12))],
-          level_blocks=[(4, 4), (4, 4)]) as run:
+          cfg, ((4, 4, 12, 12), (16, 4, 24, 12)), context=ctx,
+          fine_block=(4, 4), base_block=(4, 4)) as run:
      run.initialize(np.broadcast_to(rest, (9, *run.patch.coarse_shape)),
                     np.broadcast_to(rest, (9, *run.patch.fine_shape)))  # (9, 32, 64)
      run.step(32)
      coarse_g, fine_g = run.download()  # coarse: NaN on every covered cell;
                                         # fine: NaN on every non-ACTIVE cell
  ```
- Three-level nested windows: pass two scalar rectangles in `refinements` —
-  L1 in L0 cells, L2 in **L1 window cells** (the parent's fine grid including its
-  4-cell ghost band) — plus all three `level_blocks` entries. L2 must sit inside
-  L1's ACTIVE cells, away from L1's ghost band and transfer footprint (checked
-  before any GPU allocation). `initialize` and `download` take/return three
-  arrays; each level is NaN on its non-ACTIVE (and child-covered) cells. One
-  coarse step = 2 L1 steps = 4 L2 steps. One L1 window only in this scalar
-  chain. Optional stationary circles and Jets live on L2 via `level_objects[2]`
-  and `level_jets[2]`; L1 bodies/Jets retain their L1 meaning and must be empty
-  in this mode. All object and Jet geometry uses the **L0 edge frame**, not the
-  child bounds' L1 window frame. L2 has dx=dt=0.25, so prescribed lattice
-  velocity is unchanged. Each whole body and its BFL stencil must be inside L2
-  ACTIVE cells, outside the transfer footprint. A Jet may select one physical
-  body across multiple blocks, never two bodies.
+- Legacy three-level scalar chain: add `child=(x0, y0, x1, y1)` in
+  **L1 window cells** (the patch's fine grid including its 4-cell ghost band) and
+  `child_block`, with `fine_block` and `base_block`. L2 must sit inside L1's
+  ACTIVE cells, away from L1's ghost band and transfer footprint (checked before
+  any GPU allocation). `initialize` and `download` take/return three arrays; each
+  level is NaN on its non-ACTIVE (and child-covered) cells. One coarse step = 2 L1
+  steps = 4 L2 steps. One L1 patch only. Optional stationary circles and Jets
+  live on L2 via `child_objects` and `child_jets`; `fine_objects`/`jets` retain
+  their L1 meaning and must be empty in this mode. All object and Jet geometry
+  uses the **L0 edge frame**, not the child bounds' L1 window frame. L2 has
+  dx=dt=0.25, so prescribed lattice velocity is unchanged. Each whole body and
+  its BFL stencil must be inside L2 ACTIVE cells, outside the transfer footprint.
+  A Jet may select one physical body across multiple blocks, never two bodies.

  ```python
  from CelerisLab.body.geometry.circle import CircleGeometry
@@ -190,9 +188,9 @@ Scope and limits:
  jet = Jet(Tube((6.5, 8.), 0., 3., .3), Parallel(0.), amplitude=.002)
  rest = np.asarray(compute_feq_d2q9(1.0, 0.0, 0.0), np.float32)[:, None, None]
  with CudaContext(0) as ctx, FixedPatchStepper(
-          cfg, context=ctx, refinements=[(4, 4, 12, 12), (8, 8, 16, 16)],
-          level_blocks=[(4, 4)] * 3, level_objects=[(), (), (body,)],
-          level_jets=[(), (), (jet,)]) as run:
+          cfg, (4, 4, 12, 12), context=ctx, fine_block=(4, 4), base_block=(4, 4),
+          child=(8, 8, 16, 16), child_block=(4, 4),
+          child_objects=[body], child_jets=[jet]) as run:
      shapes = (run.patch.coarse_shape, run.patch.fine_shape, run.child_patch.fine_shape)
      run.initialize(*(np.broadcast_to(rest, (9, *s)) for s in shapes))  # 16², 24², 24²
      run.step(4)
@@ -200,16 +198,16 @@ Scope and limits:
      run.step(4)
      coarse_g, l1_g, l2_g = run.download()  # solids/covered/nonleaves are NaN
  ```
- Level lists (the only constructor): `refinements[l]` describes level `l+1`
-  in allocated level-`l` integer cells; use a rectangle list for a union, or a
-  scalar rectangle for a single window (a scalar child requires a scalar
-  parent). `level_blocks`, `level_objects` and `level_jets` each have one entry
-  per level, including L0. Three or more levels require all-blocked storage and
-  bodies/Jets only on the finest level. Every adjacent pair must preserve
-  inherited ACTIVE coverage, valid donors/receivers, surviving pulls and the
-  upstream transfer footprint. Level `l` takes `2**l` steps per base interval.
-  This describes implemented topology and scheduling, not accuracy or
-  convergence qualification.
+- Level lists: `refinements[l]` describes level `l+1` in allocated level-`l`
+  integer cells; use a rectangle list for a union, or a scalar rectangle for a
+  single window (a scalar child requires a scalar parent). `level_blocks`,
+  `level_objects` and `level_jets` each have one entry per level, including L0.
+  These lists are mutually exclusive with the legacy patch keywords. Three or
+  more levels require all-blocked storage and bodies/Jets only on the finest
+  level. Every adjacent pair must preserve inherited ACTIVE coverage, valid
+  donors/receivers, surviving pulls and the upstream transfer footprint.
+  Level `l` takes `2**l` steps per base interval. This describes implemented
+  topology and scheduling, not accuracy or convergence qualification.
 - Blocked body levels can enable `observe_raw_exchange=True` and call
  `read_raw_exchange(body_id, level=...)` after a completed base interval.
  It reduces unique cut-link observations into wall/aperture/total force,
@@ -1,6 +1,6 @@
 # Blocked AMR root channel increment

-Opt in with `FixedPatchStepper(..., coarse_boundary="channel", refinements=[bounds], level_blocks=[(by,bx), (fy,fx)])`. Every level must be blocked. The supported boundary is the existing uniform D2Q9/SRT/FP32 double-buffer channel: local Zou-He west inlet, pressure-NEQ east outlet, stationary halfway bounce-back y walls. Uniform and parabolic inlet profiles and shifted/unshifted storage are supported; the existing configuration guards still reject MRT/LES and incompatible storage. This does not change the external DFG MRT reference.
+Opt in with `FixedPatchStepper(..., coarse_boundary="channel", base_block=(by,bx), fine_block=(fy,fx))`, or the existing level-list form. Every level must be blocked. The supported boundary is the existing uniform D2Q9/SRT/FP32 double-buffer channel: local Zou-He west inlet, pressure-NEQ east outlet, stationary halfway bounce-back y walls. Uniform and parabolic inlet profiles and shifted/unshifted storage are supported; the existing configuration guards still reject MRT/LES and incompatible storage. This does not change the external DFG MRT reference.

 `step/block_channel.cu` is a small root-only kernel. Fine kernels, transfer kernels and recursive hop scheduling are unchanged. Global coordinates and the global profile height/velocity are separate from block-local storage strides. Corner ownership and collision phases match `OneStep`:

@@ -1,8 +1,8 @@
 # Fixed three-level rectangle unions

-This page describes three-level `FixedPatchStepper` setups built from the
-`refinements` level list, with rectangle unions on either adjacent pair. The
-same constructor supports arbitrary depth; three or more levels require
+This page describes the legacy three-level entry point of `FixedPatchStepper`,
+with rectangle unions on either adjacent pair. The `refinements` level-list
+entry point also supports arbitrary depth; three or more levels require
 all-blocked storage and bodies/Jets only on the finest level. This is not
 general AMR: there is no per-region timestep, moving geometry, automatic
 dynamic refinement or L1 body support in the three-level form.
@@ -12,15 +12,15 @@ No CUDA kernel changes are involved.

 ## Explicit coordinate frames

-For a single scalar parent patch, pass a scalar rectangle as `refinements[1]`:
-`(x0,y0,x1,y1)` in half-open integer indices of the allocated L1 window,
-including its ghost band.
+Keep the existing scalar `child=(x0,y0,x1,y1)` for a single scalar parent patch.
+Its coordinates retain their original meaning: half-open integer indices in the
+allocated L1 window, including its ghost band.

-A rectangle list as `refinements[1]` accepts a scalar or a set parent and
-interprets every rectangle in the actual allocated L1 array, including ghost
-bands and holes. It never infers region-local coordinates. The physical root
-cell edge corresponding to an L1 index `(x,y)` is
-`parent.fine_origin + (x,y)/2`:
+The new keyword `child_rectangles_in_parent=[...]` is mutually exclusive with
+`child`. It accepts a scalar or a set parent and interprets every rectangle in
+the actual allocated L1 array, including ghost bands and holes. It never infers
+region-local coordinates. The physical root cell edge corresponding to an L1
+index `(x,y)` is `parent.fine_origin + (x,y)/2`:

 - A scalar L1 parent has a shifted window origin.
 - A set L1 parent has origin `(0,0)` and public shape `(2*ny,2*nx)`.
@@ -47,9 +47,9 @@ tile edges.

 ```python
 run = FixedPatchStepper(
-    cfg, context=ctx,
-    refinements=[[(4, 4, 20, 28), (24, 4, 44, 28)], [(16, 16, 32, 40), (56, 16, 80, 40)]],
-    level_blocks=[(4, 4)] * 3,
+    cfg, [(4, 4, 20, 28), (24, 4, 44, 28)], context=ctx,
+    base_block=(4, 4), fine_block=(4, 4), child_block=(4, 4),
+    child_rectangles_in_parent=[(16, 16, 32, 40), (56, 16, 80, 40)],
 )
 ```

@@ -57,7 +57,7 @@ This example uses a 48x32 root. `initialize` and `download` use three Q-major
 dense arrays. Public arrays and masks still scale with the full allocated
 extent; sparse device buffers do not remove that host-memory limit.

-Stationary whole-circle L2 bodies and Jets (`level_objects[2]`, `level_jets[2]`) use root edge
+Stationary whole-circle `child_objects` and `child_jets` use root edge
 coordinates and a single L2 boundary object. Body IDs are physical object-list
 positions, not region IDs or caller `obj_id`. Complete boundary stencils must
 avoid the transfer footprint. Change a child Jet with
@@ -1,87 +0,0 @@
-# Supported settings: 2D Jet + fixed multilevel refinement (candidate c95a7ba)
-
-Every entry names the guard that enforces it (file:line at c95a7ba) and, where one
-exists, an existing test that exercises it. A setting not listed here is not
-claimed. Observations at the end are tied to the exact case in which they were
-measured; they are not general bounds.
-
-## Lattice, storage, collision
-
-| Setting | Supported | Guard |
-|---|---|---|
-| Dimension / lattice | 2D D2Q9 only (3D refinement is future work) | `lbm/refinement.py:65`, `lbm/kernels/blocks.cu:25`, `lbm/kernels/refinement.cu:26` |
-| Precision / streaming | FP32 storage, double buffer | same guards |
-| Collision on refinement levels | SRT or MRT; TRT and LES rejected | `lbm/refinement.py:65` (re-checked for fine boundaries at `lbm/refinement.py:457`) |
-| Shifted (ddf_shifting) storage | only when every level is blocked; dense or mixed rejected | `lbm/refinement_stepper.py:198`, `:469`; `lbm/kernels/refinement.cu:26` (dense patch kernel unshifted only) |
-| Fine relaxation | 1/tau_fine must lie inside the configured omega guards | `lbm/refinement.py:80` |
-| Uniform blocked backend `PeriodicBlockStepper` | doubly periodic, SRT only, stationary passive circles | `lbm/block_stepper.py:84`, `:91`, `:45`-`:67` |
-
-Tests: `tests/unit/test_refinement_mrt.py`, `tests/validation/multigrid/test_refinement_mrt_gpu.py`,
-`tests/unit/test_shifted_storage.py`, `tests/unit/test_shifted_block_operators.py`.
-
-## Refinement hierarchy (`FixedPatchStepper(cfg, *, context, refinements, ...)`)
-
-| Setting | Supported | Guard |
-|---|---|---|
-| Depth | at least one refinement level; one entry per level in `level_blocks`/`level_objects`/`level_jets` | `lbm/refinement_stepper.py:72`, `:75` |
-| Single L1 rectangle | two-coarse-cell margin to the domain edge | `lbm/refinement.py:73` |
-| Several L1 rectangles (union) | require `level_blocks[0]` and `level_blocks[1]`; transfers must close (dependency checks, no fixed gap rule) | `lbm/refinement_stepper.py:84`; `lbm/refinement.py:283`-`:295` |
-| Nested levels | depth >= 3 must be all blocked; a blocked level requires blocked levels below; a scalar child needs a scalar parent | `lbm/refinement_stepper.py:82`, `:87`; `lbm/hierarchy.py:54` |
-| Nested transfer support | child only over inherited ACTIVE cells, donors/receivers uncovered ACTIVE, no child over the parent restriction footprint | `lbm/refinement.py:391`-`:407` |
-| Tile shape | positive `(by, bx)`; the level allocation must be divisible by the tile (no partial tiles yet) | `lbm/refinement_stepper.py:78`, `lbm/refinement.py:246` (shape); `lbm/blocks.py:134` (divisibility) |
-| Coarse boundary | `periodic`, `slot_reservoir` or `channel` | `lbm/refinement_stepper.py:177` |
-| `slot_reservoir` | on-site velocity bottom slot, reservoir top, velocity 0, 2 <= slot width < nx, patch rows 4..ny-4 | `lbm/refinement_stepper.py:205`, `:212`; `lbm/refinement.py:546` |
-| `channel` | all levels blocked; Zou-He inlet, pressure-NEQ outlet, stationary bounce-back walls; transfers away from the closure | `lbm/channel.py:22`, `:26`, `:43`, `:54` |
-| Explosion | `constant` (default); `projected_linear` only periodic, all-blocked SRT, no bodies/Jets, no LES (experimental) | `lbm/refinement_stepper.py:188`, `:193` |
-| L2 runtime remap (`remap_child`) | periodic three-level L2 sets only, no L0/L1 bodies, identical pinned boundary | `lbm/refinement_stepper.py:557`, `:567`-`:581` |
-
-Tests: `tests/unit/test_refinement_three_level_multipatch.py`, `tests/validation/multigrid/test_refinement_multipatch.py`,
-`test_refinement_three_level.py`, `test_refinement_three_level_multipatch_gpu.py`, `test_refinement_blocked_base.py`,
-`test_refinement_blocked_fine.py`, `test_channel_root_gpu.py`, `tests/unit/test_channel_root.py`,
-`tests/unit/test_projected_pair_stepper.py`, `test_runtime_child_remap_gpu.py`, `test_pinned_body_remap_gpu.py`.
-
-## Bodies and Jets on refined levels
-
-| Setting | Supported | Guard |
-|---|---|---|
-| Bodies | stationary circles without sensor/force-region roles, entirely inside the patch union, fully resolved, disjoint, stencil away from the two-hop transfer footprint | `lbm/refinement.py:474`-`:542` |
-| Level | not on L0; only on the finest level of a nested hierarchy | `lbm/refinement_stepper.py:80`, `:89` |
-| Jet condition | velocity only; `pressure` is reserved and raises NotImplementedError | `body/jets.py:148`, `:150` |
-| Jet geometry | each Jet selects resolved links of exactly one stationary body; no Jet/Jet or Jet/SurfaceActuation overlap; abs(amplitude) < 1 lattice | `body/jets.py:155`, `:175`, `:177`, `:255`, `:261`, `:263` |
-| Jets with shifted storage | only in the all-blocked stepper with SRT and no LES | `body/jets.py:249` |
-| SurfaceActuation | unshifted storage only | `body/objects.py:155` |
-| Raw boundary exchange (force) | blocked body levels only; the window ledger requires `observe_raw_exchange` | `lbm/refinement_stepper.py:264`, `:269` |
-| Checkpoint with Jets | refused | `simulation.py:687` |
-
-Raw exchange is the cut-link momentum reaction (wall + aperture), not a validated
-nozzle thrust or stress load. Jet amplitude is a lattice velocity, not a flow rate.
-
-Tests: `tests/unit/test_jets.py`, `test_jets_review.py`, `test_shifted_jets.py`, `test_raw_exchange.py`,
-`tests/validation/multigrid/test_refinement_jets.py`, `test_shifted_jets_gpu.py`, `test_raw_exchange_gpu.py`,
-`test_exchange_window.py`, `test_fine_surface_gpu.py`.
-
-## Observations from specific tested cases (not general bounds)
-
- SRT channel root vs uniform OneStep, strict-parity test
-  `tests/validation/multigrid/test_channel_root_gpu.py::ChannelRootGPU::test_uniform_matched_root`:
-  in one of its 18 sub-cases (2 storage modes x 3 profile/clamp/damp settings x 3 blocks; which
-  one is not recorded), 1 of the 4320 compared values differs, max abs 2.33e-10, max rel 1.77e-7
-  (about 2 ULP). The test remains failed; its cause and any general bound are unresolved.
- MRT root parity test
-  `tests/validation/multigrid/test_refinement_mrt_gpu.py::RefinementMRTGPU::test_uniform_matched_mrt_root`
-  (12 sub-cases: 2 storage modes x 2 profiles x 3 blocks, default outlet settings) passed bitwise
-  in the Horsea focused GPU run at K1 7813334 (2026-10-21).
- Periodic Taylor-Green Re 100, measured at 36ffc8b1 (V3 matched pair, N128 depth 2):
-  every per-sample screen passed; the constant explosion's aggregate worst velocity L2,
-  0.004418, exceeds its preregistered 0.002 budget, while projected_linear passed that budget.
- Curved-wall pressure (pilot harness, exact-q analytic annulus, tau 0.8): the coarse swirl r1
-  case exceeded its terminal density-gain cap (1.105e-4 vs 1e-4), so the frozen 9-case matrix
-  is NOT_ESTABLISHED. No validated fix exists. This is a pilot harness, not production code.
- DFG 2D-1 Re 20 (V4, SRT, t* 60, pressure-NEQ outlet and local Zou-He inlet): refined and uniform
-  runs were NOT_STEADY under the frozen steady rule, so no interval verdict was given.
-
-## Not supported in this release
-
-3D, dynamic/automatic AMR (tagging, time-varying hierarchies beyond `remap_child`),
-moving bodies on refined levels, pressure Jets, Jet checkpoints, LES or TRT on refined
-levels, partial (non-dividing) tiles.
@@ -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, context=context, coarse_boundary=args.mode, refinements=[BOUNDS],
-            level_blocks=[None, fine_block], level_objects=[(), (body,)]) as run:
+            cfg, BOUNDS, context=context, coarse_boundary=args.mode,
+            fine_objects=[body], fine_block=fine_block) 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.
@@ -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, context=context,
-                coarse_boundary='slot_reservoir', refinements=[BOUNDS]) as run:
+        with CudaContext(0) as context, FixedPatchStepper(cfg, BOUNDS, context=context,
+                coarse_boundary='slot_reservoir') as run:
            p = run.patch
            masks = [np.ones(p.coarse_shape, bool), p.fine_kind == ACTIVE]
            masks[0][[0, -1]] = False
@@ -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, context=context, refinements=[(4, 4, 12, 12)]) as run:
+    with CudaContext(0) as context, PeriodicPatchStepper(cfg, (4, 4, 12, 12), context=context) 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)
@@ -207,30 +207,19 @@ def surface_link_velocity(objects, cfg, flags, fluid_idx, dir, body_id, rx, ry,
                          jets=(), hits=None, *, _shifted_blocked=False):
    """Per-link prescribed surface velocity (n, 2) FP32 and aperture mask.

-    See _surface_links, which also returns the unit-amplitude jet shapes.
-    """
-    return _surface_links(objects, cfg, flags, fluid_idx, dir, body_id, rx, ry, jets, hits,
-                          _shifted_blocked=_shifted_blocked)[:2]
-
-
-def _surface_links(objects, cfg, flags, fluid_idx, dir, body_id, rx, ry,
-                   jets=(), hits=None, *, _shifted_blocked=False):
-    """(velocity, aperture, jet shape, jet id); the last two are None without jets.
-
    Host-only and storage-neutral: rows follow the given physical cut-link
-    order. Returns all None when neither an object carries surface
+    order. Returns (None, None) when neither an object carries surface
    actuation nor a jet is given. Jets need true FP64 ``hits`` (n, 2) and may
    not share a link with each other or with a legacy aperture.
    Shifted storage is privately enabled only by the all-blocked stepper.
    """
    enabled = [obj for obj in objects if obj.surface_actuation is not None]
    if not enabled and not jets:
-        return None, None, None, None
+        return None, None
    from .preprocess.flag_overlay import validate_cut_link_ownership
    validate_cut_link_ownership(flags, fluid_idx, dir, cfg.nq)
    surface_velocity = np.zeros((len(dir), 2), np.float32)
    surface_aperture = np.zeros(len(dir), bool)
-    shape = jet_id = None
    for obj in enabled:
        obj.validate_surface_actuation(cfg)
        selected = body_id == obj.obj_id
@@ -263,4 +252,4 @@ def _surface_links(objects, cfg, flags, fluid_idx, dir, body_id, rx, ry,
            raise ValueError("Jet overlaps a SurfaceActuation aperture")
        surface_velocity[driven] = jet_link_velocity(jets, shape, jet_id)[driven]
        surface_aperture |= driven
-    return surface_velocity, surface_aperture, shape, jet_id
+    return surface_velocity, surface_aperture
@@ -54,18 +54,14 @@ def _write(path: str, content: str):


 def generate_config(cfg: LBMConfig, n_objects: int = 0,
-                    *, build_root: Optional[str] = None, block_root_bc: int = 0) -> str:
+                    *, build_root: Optional[str] = None) -> str:
    """Snapshot kernels and render headers in a fresh private directory.

    Returns its path. Pass it explicitly to compile_kernel for interleaved
    builds. Legacy generate_config(); compile_kernel() remains context-local.
    The caller owns cleanup_build_dir() once the loaded module is no longer
    needed for recompilation/debugging. No package files are changed.
-    block_root_bc specializes a blocked root module; fine/dense builds use 0.
    """
-    if (isinstance(block_root_bc, bool) or not isinstance(block_root_bc, int)
-            or block_root_bc not in (0, 1, 2)):
-        raise ValueError("block_root_bc must be an integer mode 0, 1 or 2")
    macros = cfg.to_macros()
    if isinstance(n_objects, bool) or not isinstance(n_objects, int) or n_objects < 0:
        raise ValueError("n_objects must be a nonnegative integer")
@@ -75,15 +71,14 @@ def generate_config(cfg: LBMConfig, n_objects: int = 0,
    try:
        shutil.copytree(_KERNEL_DIR, build_dir, dirs_exist_ok=True,
                        ignore=shutil.ignore_patterns("*.ptx", "*.cubin", "*.tmp"))
-        _render_config(macros, n_objects, os.path.join(build_dir, "config"),
-                       block_root_bc=block_root_bc)
+        _render_config(macros, n_objects, os.path.join(build_dir, "config"))
        digest = hashlib.sha256()
        for path in sorted(Path(build_dir).rglob("*")):
            if path.is_file():
                digest.update(str(path.relative_to(build_dir)).encode())
                digest.update(path.read_bytes())
        metadata = {"source_sha256": digest.hexdigest(), "config": asdict(cfg),
-                    "n_objects": n_objects, "block_root_bc": block_root_bc}
+                    "n_objects": n_objects}
        _write(os.path.join(build_dir, ".celeris-build"), json.dumps(metadata, sort_keys=True))
    except BaseException:
        shutil.rmtree(build_dir)
@@ -106,7 +101,7 @@ def cleanup_build_dir(build_dir: Optional[str]) -> None:
        _last_ptx_path.set(None)


-def _render_config(m: dict, n_objects: int, cdir: str, *, block_root_bc: int = 0):
+def _render_config(m: dict, n_objects: int, cdir: str):
    _write(os.path.join(cdir, "config_grid.h"), f"""{_HEADER}\
 // Layer: Global / Grid
 #ifndef CELERIS_CONFIG_GRID_H
@@ -170,9 +165,6 @@ def _render_config(m: dict, n_objects: int, cdir: str, *, block_root_bc: int = 0
 #define STORE_PRECISION  {m['STORE_PRECISION']}
 #define USE_DDF_SHIFTING {m['USE_DDF_SHIFTING']}

-// Internal blocked root mode: 0=periodic/fine, 1=slot/reservoir, 2=channel.
-#define BLOCK_ROOT_BC {block_root_bc}
-
 #define USE_LES {m['USE_LES']}
 #define LES_CS  {m['LES_CS']}
 #define LES_CLOSED_FORM {m['LES_CLOSED_FORM']}
@@ -204,21 +204,11 @@ class PeriodicBlockStepper:
                raise

    def step(self, n=1):
-        """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.
-        """
+        """Advance n steps: halo refresh, then core pull/collide, per step."""
        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"
@@ -234,9 +224,9 @@ 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._current, self._spare = self._spare, self._current  # host handles only
-                self._stream.synchronize()
-                self._step_count += n
+                    self._stream.synchronize()
+                    self._current, self._spare = self._spare, self._current
+                    self._step_count += 1
                self._status = "ready"
            except BaseException:
                self._status = "failed"
@@ -94,10 +94,12 @@ class CurvedLinkSoA:
        """
        self.surface_velocity = self.aperture = None
        self.jets, self.jet_shape, self.jet_id = tuple(jets), None, None
-        from ..body.jets import _surface_links
-        self.surface_velocity, self.aperture, self.jet_shape, self.jet_id = _surface_links(
+        self.surface_velocity, self.aperture = surface_link_velocity(
            objects, cfg, flags, self.fluid_idx, self.dir, self.body_id, self.rx, self.ry,
            jets=self.jets, hits=hits)
+        if self.jets:
+            from ..body.jets import jet_link_shapes
+            self.jet_shape, self.jet_id = jet_link_shapes(self.jets, hits)

    def set_jet_amplitude(self, index, amplitude, stream=None):
        """Rewrite jet rows from cached shapes; re-upload only the velocity column.
@@ -1,6 +1,5 @@
 // CelerisLab/lbm/kernels/blocks.cu
-// One fixed-size blocked level (lbm/blocks.py layout), specialized at compile
-// time for periodic/fine, slot/reservoir or channel stepping. Separate
+// One periodic level of fixed-size blocks (lbm/blocks.py layout). Separate
 // compilation entry: NX, NY are the block window including halo, so index_f
 // and linear_index address one block; blockIdx.z selects the block, whose
 // populations start at b*NQ*TOTAL_CELLS (block-contiguous, Q-major inside).
@@ -13,7 +12,6 @@
 #include "core/params.cuh"
 #include "core/flags.cuh"
 #include "core/obs.cuh"
-#include "core/cell_kind.cuh"
 #include "operators/macro.cuh"
 #include "operators/collision_srt.cuh"
 #if COLLISION_MODEL == 2
@@ -21,29 +19,188 @@
 #endif
 #include "streaming/pull_double_buffer.cuh"
 #include "boundary/curved_boundary.cuh"
+#include "boundary/planar_velocity.cuh"

 #if DIM != 2 || NQ != 9 || (COLLISION_MODEL != 0 && COLLISION_MODEL != 2) || STORE_PRECISION != 0 || USE_LES || STREAMING_MODEL != 0
 #error "Blocks require FP32 D2Q9 SRT or MRT double buffers without LES"
 #endif
-#ifndef BLOCK_ROOT_BC
-#error "Blocks require a generated BLOCK_ROOT_BC mode"
-#elif BLOCK_ROOT_BC < 0 || BLOCK_ROOT_BC > 2
-#error "BLOCK_ROOT_BC must be 0, 1 or 2"
-#endif

-#if BLOCK_ROOT_BC == 1
-#include "boundary/block_wall.cuh"
-#endif
-#if BLOCK_ROOT_BC != 2
-#include "operators/block_collision.cuh"
-#endif
+// Fixed-patch cell kinds, matching refinement.py ACTIVE/INNER_GHOST/OUTER_GHOST.
+constexpr unsigned char KIND_ACTIVE = 0u, KIND_INNER = 1u, KIND_OUTER = 2u;

-// Kernels, in definition order: transfers, boundary staging, then the one full
-// step selected for this module (BlockStep, or BlockChannelStep for a channel root).
-#include "step/block_transfer.cu"
-#include "step/block_boundary.cu"
-#if BLOCK_ROOT_BC != 2
-#include "step/block_step.cu"
+// Zero-initialized for ordinary blocks/fine levels. Set only for parent walls;
+// NX/NY remain local storage strides, never physical wall coordinates.
+struct BlockWall { unsigned int nx, ny, slot_width; float amplitude; };
+extern "C" { __constant__ BlockWall d_block_wall; }
+
+// Halo refresh: block cell ids b*TOTAL_CELLS+c, sources are always core cells.
+extern "C" __global__ void BlockHaloCopy(
+    fpxx* f, const uint64_t* dst, const uint64_t* src, unsigned int count)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    const uint64_t d = dst[row], s = src[row];
+    fpxx* to = f + (d / TOTAL_CELLS) * NQ * TOTAL_CELLS;
+    const fpxx* from = f + (s / TOTAL_CELLS) * NQ * TOTAL_CELLS;
+    for (unsigned int q = 0; q < NQ; ++q)
+        to[index_f(d % TOTAL_CELLS, q)] = from[index_f(s % TOTAL_CELLS, q)];
+}
+
+// Fixed-patch explosion into blocked fine storage: target = owner block cell
+// id of a patch-ghost cell; donors are parent block cell ids. Dense parent
+// storage is the one-window case with coarse_cells = full domain size.
+extern "C" __global__ void BlockExplode(
+    const fpxx* coarse, fpxx* fine, const uint64_t* target, const uint64_t* donor,
+    unsigned int count, unsigned long coarse_cells)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    const uint64_t t = target[row];
+    fpxx* to = fine + (t / TOTAL_CELLS) * NQ * TOTAL_CELLS;
+    const uint64_t d = donor[row];
+    const fpxx* from = coarse + (d / coarse_cells) * NQ * coarse_cells;
+    for (unsigned int q = 0; q < NQ; ++q)
+        to[index_f(t % TOTAL_CELLS, q)] = from[q * coarse_cells + d % coarse_cells];
+}
+
+// Experimental Schornbaum--Ruede (arXiv:1508.07982, Algorithm 2)
+// and Chen et al. (doi:10.1016/j.physa.2005.09.036) population interpolation.
+// Independent implementation of the mathematical stencil; no upstream source copied.
+// Stencil cells are owner cores; a disabled axis repeats its center twice.
+extern "C" __global__ void BlockExplodeProjected(
+    const fpxx* coarse, fpxx* fine, const uint64_t* target, const uint64_t* donor,
+    unsigned int count, unsigned long coarse_cells,
+    const uint64_t* neighbors, const float* offsets)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    const uint64_t t = target[row], d = donor[row];
+    fpxx* to = fine + (t / TOTAL_CELLS) * NQ * TOTAL_CELLS;
+    for (unsigned int q = 0; q < NQ; ++q) {
+        float v[4];
+        for (unsigned int a = 0; a < 4; ++a) {
+            const uint64_t n = neighbors[4ul * row + a];
+            v[a] = coarse[(n / coarse_cells) * NQ * coarse_cells
+                          + q * coarse_cells + n % coarse_cells];
+        }
+        float gx = .5f * (v[1] - v[0]), gy = .5f * (v[3] - v[2]);
+        const float ex = d_cx[q], ey = d_cy[q];
+        if (q != 0) {
+            const float along = (ex * gx + ey * gy) / (ex * ex + ey * ey);
+            gx -= ex * along;
+            gy -= ey * along;
+        }
+        to[index_f(t % TOTAL_CELLS, q)] =
+            coarse[(d / coarse_cells) * NQ * coarse_cells + q * coarse_cells + d % coarse_cells]
+            + offsets[2ul * row] * gx + offsets[2ul * row + 1] * gy;
+    }
+}
+
+// Targets are receiver-local SOURCE slots for the immediately following pull.
+// Keep child summation order identical to PatchCoarseStep; no collision here.
+extern "C" __global__ void BlockCoalesce(
+    const fpxx* fine, fpxx* coarse, const uint64_t* target, const uint64_t* children,
+    unsigned int count)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    const uint64_t* s = children + 4ul * row;
+    coarse[target[row]] = 0.25f * (fine[s[0]] + fine[s[1]] + fine[s[2]] + fine[s[3]]);
+}
+
+// Static cut links, receiver-local staging: cell is the receiver's local core
+// cell, so the existing BFL writes the solid-source window image that this
+// block's next pull reads (no halo copy between this kernel and BlockStep).
+// surface_velocity (nullable, 2 floats per link): prescribed fluid velocity on
+// fixed geometry, same convention as CurvedBoundaryKernel. Optional raw rows
+// (jx,jy,torque,dm) are unique physical links, never body-observation slots.
+extern "C" __global__ void BlockCurvedBoundary(
+    fpxx* f, const uint32_t* block, const uint32_t* cell, const unsigned char* dir,
+    const float* q, const unsigned char* fallback, unsigned int count,
+    const float* surface_velocity, const float* rx, const float* ry, float* raw)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    float Uw = 0.0f, Vw = 0.0f;
+    if (surface_velocity != nullptr) {
+        const float u = surface_velocity[2 * row], v = surface_velocity[2 * row + 1];
+        if (u != 0.0f || v != 0.0f) { Uw = u; Vw = v; }
+    }
+    apply_bouzidi_link(dir[row], q[row], cell[row], f + (unsigned long)block[row] * NQ * TOTAL_CELLS,
+                       Uw, Vw, rx ? rx[row] : 0.0f, ry ? ry[row] : 0.0f,
+                       fallback[row], nullptr, -1, raw ? raw + 4ul * row : nullptr,
+                       raw ? raw + 4ul * row + 3 : nullptr);
+}
+
+// Same-stream BFL -> this row-owned accumulation -> pull step. No atomics,
+// no cross-row reduction and no history allocation proportional to substeps.
+extern "C" __global__ void BlockAccumulateExchange(
+    const float* raw, double* integral, unsigned int count, double h, double dt)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    const unsigned long k = 4ul * row;
+    const double impulse = h * dt;
+    integral[k] += impulse * (double)raw[k];
+    integral[k + 1] += impulse * (double)raw[k + 1];
+    integral[k + 2] += h * impulse * (double)raw[k + 2];
+    integral[k + 3] += h * h * (double)raw[k + 3];
+}
+
+// Pull/collide/store core cells only; halo cells of out are left untouched.
+// flags (block cell ids, nullable): solid cores store NaN and never collide.
+// kind (block cell ids, nullable = all ACTIVE): OUTER skips the pull and
+// stores NaN, INNER pulls without collision, ACTIVE pulls and collides.
+extern "C" __global__ void BlockStep(const fpxx* in, fpxx* out, unsigned int halo,
+                                     const uint16_t* flags, const unsigned char* kind) {
+    unsigned int x, y; unsigned long k;
+    index_from_thread(x, y, k);
+    if (x < halo || y < halo || x >= NX - halo || y >= NY - halo) return;
+    const unsigned long base = (unsigned long)blockIdx.z * NQ * TOTAL_CELLS;
+    const unsigned long cell = (unsigned long)blockIdx.z * TOTAL_CELLS + k;
+    const unsigned char cell_kind = kind != nullptr ? kind[cell] : KIND_ACTIVE;
+    float f[NQ];
+    if (cell_kind == KIND_OUTER || (flags != nullptr && is_solid(flags[cell]))) {
+        for (int q = 0; q < NQ; ++q) f[q] = NAN;
+    } else {
+        unsigned long j[NQ];
+        compute_neighbors(x, y, j);  // Core neighbors stay inside the window: no wrap.
+        stream_pull_load(k, f, in + base, j);
+        if (cell_kind == KIND_ACTIVE) {
+            if (d_block_wall.nx != 0) {
+                const unsigned int bx = NX - 2 * halo, by = NY - 2 * halo;
+                const unsigned int nbx = d_block_wall.nx / bx;
+                const unsigned int gx = (blockIdx.z % nbx) * bx + x - halo;
+                const unsigned int gy = (blockIdx.z / nbx) * by + y - halo;
+                if (gy == 1)
+                    reconstruct_bottom_velocity(f, 0.0f, bottom_wall_normal_velocity(
+                        gx, d_block_wall.nx, d_block_wall.slot_width, d_block_wall.amplitude));
+                else if (gy == d_block_wall.ny - 2) reconstruct_top_reservoir(f, RHO);
+            }
+#if COLLISION_MODEL == 2
+            // Uniform MRT sequence (collide_dispatch, zero forcing); SRT path below unchanged.
+            float rho, ux, uy;
+            compute_rho_u(f, rho, ux, uy);
+            collide_mrt_no_force(f, rho, ux, uy,
+                fminf(OMEGA_COLLISION_MAX, fmaxf(OMEGA_COLLISION_MIN, d_params.omega)));
 #else
-#include "step/block_channel.cu"
+            float rho, ux, uy, feq[NQ];
+            compute_rho_u(f, rho, ux, uy);
+#if USE_DDF_SHIFTING
+            // Preserve the density perturbation before adding the unit reference.
+            const float drho = f[0]+f[1]+f[2]+f[3]+f[4]+f[5]+f[6]+f[7]+f[8];
+            const float jx = f[1]-f[2]+f[5]-f[6]+f[7]-f[8];
+            const float jy = f[3]-f[4]+f[5]-f[6]-f[7]+f[8];
+            compute_feq_from_momentum(drho, jx, jy, ux, uy, feq);
+#else
+            compute_feq(rho, ux, uy, feq);
 #endif
+            collide_srt_no_force(f, feq, d_params.omega);
+#endif
+        }
+    }
+    stream_pull_store(k, f, out + base);
+}
+
+// Root channel closure; fine and periodic levels keep BlockStep.
+#include "step/block_channel.cu"
@@ -1,20 +0,0 @@
-// Physical parent walls; NX/NY remain local storage strides.
-#ifndef CELERIS_BOUNDARY_BLOCK_WALL_CUH
-#define CELERIS_BOUNDARY_BLOCK_WALL_CUH
-
-#include "planar_velocity.cuh"
-
-struct BlockWall { unsigned int nx, ny, slot_width; float amplitude; };
-extern "C" { __constant__ BlockWall d_block_wall; }
-
-__device__ __forceinline__ void block_wall(float* f, unsigned int x, unsigned int y,
-                                         unsigned int halo) {
-    unsigned int gx, gy;
-    block_global_xy(x, y, halo, d_block_wall.nx, gx, gy);
-    if (gy == 1)
-        reconstruct_bottom_velocity(f, 0.0f, bottom_wall_normal_velocity(
-            gx, d_block_wall.nx, d_block_wall.slot_width, d_block_wall.amplitude));
-    else if (gy == d_block_wall.ny - 2) reconstruct_top_reservoir(f, RHO);
-}
-
-#endif
@@ -15,13 +15,10 @@
 // D2Q9 y-wall half-way bounce-back for pull double-buffer streaming.
 // ---------------------------------------------------------------------------
 #if LATTICE_MODEL == LATTICE_D2Q9
-// Rows 1 and top_row (= physical ny - 2) next to walls at rows 0 and ny - 1.
-// y is the physical row; k addresses the node in fi_in (a block window may
-// have NX/NY strides different from the physical extent).
-__device__ inline void apply_wall_bb_d2q9_rows(unsigned int y, unsigned int top_row,
-                                               float* __restrict__ f,
-                                               const fpxx* __restrict__ fi_in,
-                                               unsigned long k)
+__device__ inline void apply_wall_bb_d2q9_y_pull(unsigned int y,
+                                                  float* __restrict__ f,
+                                                  const fpxx* __restrict__ fi_in,
+                                                  unsigned long k)
 {
    if (y == 1) {
        // Directions sourced from y=0 wall in pull step: +y, +x+y, -x+y.
@@ -29,22 +26,14 @@ __device__ inline void apply_wall_bb_d2q9_rows(unsigned int y, unsigned int top_
        f[5] = load_ddf(fi_in, index_f(k, 6u));
        f[8] = load_ddf(fi_in, index_f(k, 7u));
    }
-    else if (y == top_row) {
-        // Directions sourced from the y = ny - 1 wall in pull step: -y, -x-y, +x-y.
+    else if (y == (unsigned int)(NY - 2)) {
+        // Directions sourced from y=NY-1 wall in pull step: -y, -x-y, +x-y.
        f[4] = load_ddf(fi_in, index_f(k, 3u));
        f[6] = load_ddf(fi_in, index_f(k, 5u));
        f[7] = load_ddf(fi_in, index_f(k, 8u));
    }
 }

-__device__ inline void apply_wall_bb_d2q9_y_pull(unsigned int y,
-                                                  float* __restrict__ f,
-                                                  const fpxx* __restrict__ fi_in,
-                                                  unsigned long k)
-{
-    apply_wall_bb_d2q9_rows(y, (unsigned int)(NY - 2), f, fi_in, k);
-}
-
 // ---------------------------------------------------------------------------
 // D2Q9 y-wall free-slip (specular reflection) for pull double-buffer streaming.
 //
@@ -8,9 +8,6 @@
 #define STORE_PRECISION  0
 #define USE_DDF_SHIFTING 0

-// Internal blocked root mode: 0=periodic/fine, 1=slot/reservoir, 2=channel.
-#define BLOCK_ROOT_BC 0
-
 #define USE_LES 0
 #define LES_CS  0.160000f
 #define LES_CLOSED_FORM 1
@@ -1,16 +0,0 @@
-// CelerisLab – core/cell_kind.cuh
-// Fixed-patch cell kinds stored per block cell, matching lbm/refinement.py
-// ACTIVE/INNER_GHOST/OUTER_GHOST: OUTER is invalid (stores NaN, no pull),
-// INNER streams without collision, ACTIVE pulls and collides.
-#ifndef CELERIS_CORE_CELL_KIND_CUH
-#define CELERIS_CORE_CELL_KIND_CUH
-
-constexpr unsigned char KIND_ACTIVE = 0u, KIND_INNER = 1u, KIND_OUTER = 2u;
-
-// NaN populations mark a cell without valid state (OUTER ghost or solid core).
-__device__ __forceinline__ void fill_invalid(float* f)
-{
-    for (int q = 0; q < NQ; ++q) f[q] = NAN;
-}
-
-#endif
@@ -53,18 +53,6 @@ __device__ __forceinline__ void index_from_thread(unsigned int& x,
    k = (unsigned long)y * NX + x;
 }

-// Global cell of window cell (x, y) in block blockIdx.z of a row-major,
-// full-domain block layout domain_nx cells wide. NX/NY are the local strides.
-__device__ __forceinline__ void block_global_xy(unsigned int x, unsigned int y,
-                                                unsigned int halo, unsigned int domain_nx,
-                                                unsigned int& gx, unsigned int& gy)
-{
-    const unsigned int bx = NX - 2 * halo, by = NY - 2 * halo;
-    const unsigned int nbx = domain_nx / bx;
-    gx = (blockIdx.z % nbx) * bx + x - halo;
-    gy = (blockIdx.z / nbx) * by + y - halo;
-}
-
 // ---------------------------------------------------------------------------
 // Neighbor list (periodic BCs via modular arithmetic)
 // ---------------------------------------------------------------------------
@@ -1,31 +0,0 @@
-// Collision used by periodic/fine and slot/reservoir BlockStep.
-#ifndef CELERIS_OPERATORS_BLOCK_COLLISION_CUH
-#define CELERIS_OPERATORS_BLOCK_COLLISION_CUH
-
-#include "../core/params.cuh"
-#include "macro.cuh"
-#include "collision_srt.cuh"
-#if COLLISION_MODEL == 2
-#include "collision_mrt.cuh"
-#endif
-
-__device__ __forceinline__ void block_collide(float* f) {
-#if COLLISION_MODEL == 2
-    collide_mrt_unforced(f);  // SRT path below unchanged.
-#else
-    float rho, ux, uy, feq[NQ];
-    compute_rho_u(f, rho, ux, uy);
-#if USE_DDF_SHIFTING
-    // Preserve the density perturbation before adding the unit reference.
-    const float drho = f[0]+f[1]+f[2]+f[3]+f[4]+f[5]+f[6]+f[7]+f[8];
-    const float jx = f[1]-f[2]+f[5]-f[6]+f[7]-f[8];
-    const float jy = f[3]-f[4]+f[5]-f[6]-f[7]+f[8];
-    compute_feq_from_momentum(drho, jx, jy, ux, uy, feq);
-#else
-    compute_feq(rho, ux, uy, feq);
-#endif
-    collide_srt_no_force(f, feq, d_params.omega);
-#endif
-}
-
-#endif
@@ -1,14 +0,0 @@
-// CelerisLab – operators/bounce_back_swap.cuh
-// Full-way bounce-back at a wall node: swap every opposite pair (paired
-// order q, q+1). Needs only NQ; shared by the uniform and blocked steps.
-#ifndef CELERIS_OPERATORS_BOUNCE_BACK_SWAP_CUH
-#define CELERIS_OPERATORS_BOUNCE_BACK_SWAP_CUH
-
-__device__ __forceinline__ void bounce_back_swap(float* f) {
-    #pragma unroll
-    for (int i = 1; i < NQ; i += 2) {
-        float t = f[i]; f[i] = f[i+1]; f[i+1] = t;
-    }
-}
-
-#endif
@@ -114,16 +114,6 @@ __device__ __forceinline__ void collide_mrt_no_force(float* __restrict__ g,
    collide_mrt(g, rho, ux, uy, Fin, omega);
 }

-// Unforced MRT with the clamped device omega, as in collide_dispatch with zero
-// forcing. Shared by the blocked, channel-root and dense-patch collisions.
-__device__ __forceinline__ void collide_mrt_unforced(float* __restrict__ g)
-{
-    float rho, ux, uy;
-    compute_rho_u(g, rho, ux, uy);
-    collide_mrt_no_force(g, rho, ux, uy,
-        fminf(OMEGA_COLLISION_MAX, fmaxf(OMEGA_COLLISION_MIN, d_params.omega)));
-}
-
 #elif LATTICE_MODEL == LATTICE_D3Q19

 __device__ __forceinline__ void collide_mrt(float* __restrict__ g,
@@ -5,7 +5,12 @@
 #ifndef CELERIS_OPERATORS_HELPERS_CUH
 #define CELERIS_OPERATORS_HELPERS_CUH

-#include "bounce_back_swap.cuh"
+__device__ __forceinline__ void bounce_back_swap(float* f) {
+    #pragma unroll
+    for (int i = 1; i < NQ; i += 2) {
+        float t = f[i]; f[i] = f[i+1]; f[i+1] = t;
+    }
+}

 __device__ __forceinline__ void collide_dispatch(
    float* f, float rho_n,
@@ -9,7 +9,6 @@
 #include "core/params.cuh"
 #include "core/flags.cuh"
 #include "core/obs.cuh"
-#include "core/cell_kind.cuh"
 #include "operators/macro.cuh"
 #include "operators/collision_srt.cuh"
 #if COLLISION_MODEL == 2
@@ -36,5 +35,96 @@ __device__ unsigned int incoming_counts[NQ * TOTAL_CELLS];
 }
 #endif

-// Kernels: patch collision helper, PatchExplode, PatchFineStep, PatchCoarseStep.
-#include "step/patch_step.cu"
+__device__ __forceinline__ void patch_collide(float* f, unsigned long k) {
+#if COLLISION_MODEL == 2
+    float rho, ux, uy;
+    compute_rho_u(f, rho, ux, uy);
+    collide_mrt_no_force(f, rho, ux, uy,
+        fminf(OMEGA_COLLISION_MAX, fmaxf(OMEGA_COLLISION_MIN, d_params.omega)));
+#else
+    float rho, ux, uy, feq[NQ];
+    compute_rho_u(f, rho, ux, uy);
+    compute_feq(rho, ux, uy, feq);
+    collide_srt_no_force(f, feq, d_params.omega);
+#endif
+#ifdef CELERIS_REFINEMENT_AUDIT
+    ++collision_counts[k];
+#endif
+}
+
+extern "C" __global__ void PatchExplode(
+    const float* coarse, float* fine, const uint32_t* targets,
+    const uint32_t* donors, unsigned int count, unsigned long coarse_cells)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    for (unsigned int q = 0; q < NQ; ++q)
+        fine[index_f(targets[row], q)] = coarse[q * coarse_cells + donors[row]];
+#ifdef CELERIS_REFINEMENT_AUDIT
+    ++explosion_counts[targets[row]];
+#endif
+}
+
+extern "C" __global__ void PatchFineStep(const float* in, float* out, const uint16_t* flags) {
+    unsigned int x, y; unsigned long k;
+    index_from_thread(x, y, k);
+    if (x >= NX || y >= NY) return;
+    float f[NQ];
+    // Outer halo is invalid after EACH hop, including when reusing the buffer
+    // that held explosion data. Inner halo only streams; it never collides.
+    if (x < 2 || y < 2 || x >= NX - 2 || y >= NY - 2
+            || (flags != nullptr && is_solid(flags[k]))) {
+        for (int q = 0; q < NQ; ++q) f[q] = NAN;
+    } else {
+        unsigned long j[NQ];
+        compute_neighbors(x, y, j);  // These interior targets never wrap.
+        stream_pull_load(k, f, in, j);
+        if (x >= 4 && y >= 4 && x < NX - 4 && y < NY - 4)
+            patch_collide(f, k);
+    }
+    stream_pull_store(k, f, out);
+}
+
+extern "C" __global__ void PatchCoarseStep(
+    const float* in, float* out, const float* fine,
+    const uint64_t* targets, const uint64_t* children, unsigned int count,
+    unsigned int x0, unsigned int y0, unsigned int x1, unsigned int y1,
+    unsigned int wall_aware)
+{
+    unsigned int x, y; unsigned long k;
+    index_from_thread(x, y, k);
+    if (x >= NX || y >= NY) return;
+    // Both buffers were poisoned at initialization; covered cells stay invalid.
+    if (x >= x0 && x < x1 && y >= y0 && y < y1) return;
+    if (wall_aware && (y == 0 || y == NY - 1)) return;
+    unsigned long j[NQ];
+    compute_neighbors(x, y, j);
+    float f[NQ];
+    stream_pull_load(k, f, in, j);
+    if (x >= x0 - 1 && x <= x1 && y >= y0 - 1 && y <= y1) {
+        for (unsigned int q = 1; q < NQ; ++q) {
+            uint64_t slot = index_f(k, q);
+            unsigned int lo = 0, hi = count;
+            while (lo < hi) {
+                unsigned int mid = lo + (hi - lo) / 2;
+                if (targets[mid] < slot) lo = mid + 1;
+                else hi = mid;
+            }
+            if (lo < count && targets[lo] == slot) {
+                const uint64_t* s = children + 4ul * lo;
+                f[q] = 0.25f * (fine[s[0]] + fine[s[1]] + fine[s[2]] + fine[s[3]]);
+#ifdef CELERIS_REFINEMENT_AUDIT
+                ++incoming_counts[slot];
+#endif
+            }
+        }
+    }
+    // Includes the eight grazing-corner links with UNCOVERED coarse donors.
+    // All replacement arrivals must be in place before computing rho/u.
+    if (wall_aware) {
+        if (y == 1) reconstruct_bottom_velocity(f, 0.0f, bottom_wall_normal_velocity(x));
+        else if (y == NY - 2) reconstruct_top_reservoir(f, RHO);
+    }
+    patch_collide(f, k);
+    stream_pull_store(k, f, out);
+}
@@ -1,42 +0,0 @@
-// CelerisLab/lbm/kernels/step/block_boundary.cu
-// Receiver-local curved-boundary staging and its raw-exchange accumulation.
-// Part of the blocks.cu compilation entry; relies on its includes and guards.
-
-// Static cut links, receiver-local staging: cell is the receiver's local core
-// cell, so the existing BFL writes the solid-source window image that this
-// block's next pull reads (no halo copy between this kernel and BlockStep).
-// surface_velocity (nullable, 2 floats per link): prescribed fluid velocity on
-// fixed geometry, same convention as CurvedBoundaryKernel. Optional raw rows
-// (jx,jy,torque,dm) are unique physical links, never body-observation slots.
-extern "C" __global__ void BlockCurvedBoundary(
-    fpxx* f, const uint32_t* block, const uint32_t* cell, const unsigned char* dir,
-    const float* q, const unsigned char* fallback, unsigned int count,
-    const float* surface_velocity, const float* rx, const float* ry, float* raw)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    float Uw = 0.0f, Vw = 0.0f;
-    if (surface_velocity != nullptr) {
-        const float u = surface_velocity[2 * row], v = surface_velocity[2 * row + 1];
-        if (u != 0.0f || v != 0.0f) { Uw = u; Vw = v; }
-    }
-    apply_bouzidi_link(dir[row], q[row], cell[row], f + (unsigned long)block[row] * NQ * TOTAL_CELLS,
-                       Uw, Vw, rx ? rx[row] : 0.0f, ry ? ry[row] : 0.0f,
-                       fallback[row], nullptr, -1, raw ? raw + 4ul * row : nullptr,
-                       raw ? raw + 4ul * row + 3 : nullptr);
-}
-
-// Same-stream BFL -> this row-owned accumulation -> pull step. No atomics,
-// no cross-row reduction and no history allocation proportional to substeps.
-extern "C" __global__ void BlockAccumulateExchange(
-    const float* raw, double* integral, unsigned int count, double h, double dt)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const unsigned long k = 4ul * row;
-    const double impulse = h * dt;
-    integral[k] += impulse * (double)raw[k];
-    integral[k + 1] += impulse * (double)raw[k + 1];
-    integral[k + 2] += h * impulse * (double)raw[k + 2];
-    integral[k + 3] += h * h * (double)raw[k + 3];
-}
@@ -1,12 +1,5 @@
-#if BLOCK_ROOT_BC != 2
-#error "BlockChannelStep requires BLOCK_ROOT_BC == 2"
-#endif
-
 // Root-only blocked counterpart of OneStep's D2Q9/SRT channel closure.
 // NX/NY are LOCAL strides; all physical boundary decisions use global coordinates.
-#include "../core/cell_kind.cuh"
-#include "../operators/bounce_back_swap.cuh"
-#include "../boundary/bounce_back.cuh"
 #include "../boundary/inlet/common.cuh"
 #include "../boundary/inlet/zou_he_local.cuh"
 #include "../boundary/outlet/pressure_neq.cuh"
@@ -22,13 +15,15 @@ extern "C" __global__ void BlockChannelStep(
    unsigned int x, y; unsigned long k;
    index_from_thread(x, y, k);
    if (x < halo || y < halo || x >= NX - halo || y >= NY - halo) return;
-    unsigned int gx, gy;
-    block_global_xy(x, y, halo, d_block_channel.nx, gx, gy);
+    const unsigned int bx = NX - 2 * halo, by = NY - 2 * halo;
+    const unsigned int nbx = d_block_channel.nx / bx;
+    const unsigned int gx = (blockIdx.z % nbx) * bx + x - halo;
+    const unsigned int gy = (blockIdx.z / nbx) * by + y - halo;
    const unsigned long base = (unsigned long)blockIdx.z * NQ * TOTAL_CELLS;
    const unsigned long cell = (unsigned long)blockIdx.z * TOTAL_CELLS + k;
    float f[NQ];
    if (kind != nullptr && kind[cell] == KIND_OUTER) {
-        fill_invalid(f);
+        for (int q = 0; q < NQ; ++q) f[q] = NAN;
    } else {
        unsigned long j[NQ];
        compute_neighbors(x, y, j);
@@ -36,21 +31,35 @@ extern "C" __global__ void BlockChannelStep(
        const bool wall = gy == 0 || gy == d_block_channel.ny - 1;
        const bool outlet = gx == d_block_channel.nx - 1;
        if (wall) {
-            bounce_back_swap(f);  // Wall owns all four corners; ghosts never collide.
+            // Wall owns all four corners. Ghosts pull and swap, never collide.
+            for (int q = 1; q < NQ; q += 2) {
+                const float t = f[q]; f[q] = f[q + 1]; f[q + 1] = t;
+            }
        } else if (gx == 0) {
            apply_zou_he_left_velocity_inlet_d2q9(
                f, inlet_target_u((float)gy, d_block_channel.ny, d_block_channel.velocity), 0.0f);
        } else if (outlet) {
            // Immutable input donor, receiver-local (also valid across a block seam).
            float donor[NQ];
-            load_node(in + base, k - 1, donor);
+            for (int q = 0; q < NQ; ++q)
+                donor[q] = load_ddf(in + base, index_f(k - 1, q));
            apply_pressure_outlet_d2q9(f, donor);
-        } else {
-            apply_wall_bb_d2q9_rows(gy, d_block_channel.ny - 2, f, in + base, k);
+        } else if (gy == 1) {
+            f[3] = load_ddf(in + base, index_f(k, 4));
+            f[5] = load_ddf(in + base, index_f(k, 6));
+            f[8] = load_ddf(in + base, index_f(k, 7));
+        } else if (gy == d_block_channel.ny - 2) {
+            f[4] = load_ddf(in + base, index_f(k, 3));
+            f[6] = load_ddf(in + base, index_f(k, 5));
+            f[7] = load_ddf(in + base, index_f(k, 8));
        }
        if (!wall && !outlet) {
 #if COLLISION_MODEL == 2
-            collide_mrt_unforced(f);
+            // Match uniform MRT arithmetic (collide_dispatch, zero forcing).
+            float rho, ux, uy;
+            compute_rho_u(f, rho, ux, uy);
+            collide_mrt_no_force(f, rho, ux, uy,
+                fminf(OMEGA_COLLISION_MAX, fmaxf(OMEGA_COLLISION_MIN, d_params.omega)));
 #else
            // Match uniform SRT arithmetic, including its shifted equilibrium path.
            float rho, ux, uy, feq[NQ], forcing[NQ] = {};
@@ -1,35 +0,0 @@
-// CelerisLab/lbm/kernels/step/block_step.cu
-// Generic blocked pull/collide/store for periodic/fine and slot/reservoir levels.
-// Part of the blocks.cu compilation entry; relies on its includes and guards.
-#if BLOCK_ROOT_BC == 2
-#error "BlockStep is not built for the channel root (BLOCK_ROOT_BC == 2)"
-#endif
-
-// Pull/collide/store core cells only; halo cells of out are left untouched.
-// flags (block cell ids, nullable): solid cores store NaN and never collide.
-// kind (block cell ids, nullable = all ACTIVE): OUTER skips the pull and
-// stores NaN, INNER pulls without collision, ACTIVE pulls and collides.
-extern "C" __global__ void BlockStep(const fpxx* in, fpxx* out, unsigned int halo,
-                                     const uint16_t* flags, const unsigned char* kind) {
-    unsigned int x, y; unsigned long k;
-    index_from_thread(x, y, k);
-    if (x < halo || y < halo || x >= NX - halo || y >= NY - halo) return;
-    const unsigned long base = (unsigned long)blockIdx.z * NQ * TOTAL_CELLS;
-    const unsigned long cell = (unsigned long)blockIdx.z * TOTAL_CELLS + k;
-    const unsigned char cell_kind = kind != nullptr ? kind[cell] : KIND_ACTIVE;
-    float f[NQ];
-    if (cell_kind == KIND_OUTER || (flags != nullptr && is_solid(flags[cell]))) {
-        fill_invalid(f);
-    } else {
-        unsigned long j[NQ];
-        compute_neighbors(x, y, j);  // Core neighbors stay inside the window: no wrap.
-        stream_pull_load(k, f, in + base, j);
-        if (cell_kind == KIND_ACTIVE) {
-#if BLOCK_ROOT_BC == 1
-            block_wall(f, x, y, halo);
-#endif
-            block_collide(f);
-        }
-    }
-    stream_pull_store(k, f, out + base);
-}
@@ -1,78 +0,0 @@
-// CelerisLab/lbm/kernels/step/block_transfer.cu
-// Same-level halo refresh and 2:1 explosion/coalescence between blocked levels.
-// Part of the blocks.cu compilation entry; relies on its includes and guards.
-
-// Halo refresh: block cell ids b*TOTAL_CELLS+c, sources are always core cells.
-extern "C" __global__ void BlockHaloCopy(
-    fpxx* f, const uint64_t* dst, const uint64_t* src, unsigned int count)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const uint64_t d = dst[row], s = src[row];
-    fpxx* to = f + (d / TOTAL_CELLS) * NQ * TOTAL_CELLS;
-    const fpxx* from = f + (s / TOTAL_CELLS) * NQ * TOTAL_CELLS;
-    for (unsigned int q = 0; q < NQ; ++q)
-        to[index_f(d % TOTAL_CELLS, q)] = from[index_f(s % TOTAL_CELLS, q)];
-}
-
-// Fixed-patch explosion into blocked fine storage: target = owner block cell
-// id of a patch-ghost cell; donors are parent block cell ids. Dense parent
-// storage is the one-window case with coarse_cells = full domain size.
-extern "C" __global__ void BlockExplode(
-    const fpxx* coarse, fpxx* fine, const uint64_t* target, const uint64_t* donor,
-    unsigned int count, unsigned long coarse_cells)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const uint64_t t = target[row];
-    fpxx* to = fine + (t / TOTAL_CELLS) * NQ * TOTAL_CELLS;
-    const uint64_t d = donor[row];
-    const fpxx* from = coarse + (d / coarse_cells) * NQ * coarse_cells;
-    for (unsigned int q = 0; q < NQ; ++q)
-        to[index_f(t % TOTAL_CELLS, q)] = from[q * coarse_cells + d % coarse_cells];
-}
-
-// Experimental Schornbaum--Ruede (arXiv:1508.07982, Algorithm 2)
-// and Chen et al. (doi:10.1016/j.physa.2005.09.036) population interpolation.
-// Independent implementation of the mathematical stencil; no upstream source copied.
-// Stencil cells are owner cores; a disabled axis repeats its center twice.
-extern "C" __global__ void BlockExplodeProjected(
-    const fpxx* coarse, fpxx* fine, const uint64_t* target, const uint64_t* donor,
-    unsigned int count, unsigned long coarse_cells,
-    const uint64_t* neighbors, const float* offsets)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const uint64_t t = target[row], d = donor[row];
-    fpxx* to = fine + (t / TOTAL_CELLS) * NQ * TOTAL_CELLS;
-    for (unsigned int q = 0; q < NQ; ++q) {
-        float v[4];
-        for (unsigned int a = 0; a < 4; ++a) {
-            const uint64_t n = neighbors[4ul * row + a];
-            v[a] = coarse[(n / coarse_cells) * NQ * coarse_cells
-                          + q * coarse_cells + n % coarse_cells];
-        }
-        float gx = .5f * (v[1] - v[0]), gy = .5f * (v[3] - v[2]);
-        const float ex = d_cx[q], ey = d_cy[q];
-        if (q != 0) {
-            const float along = (ex * gx + ey * gy) / (ex * ex + ey * ey);
-            gx -= ex * along;
-            gy -= ey * along;
-        }
-        to[index_f(t % TOTAL_CELLS, q)] =
-            coarse[(d / coarse_cells) * NQ * coarse_cells + q * coarse_cells + d % coarse_cells]
-            + offsets[2ul * row] * gx + offsets[2ul * row + 1] * gy;
-    }
-}
-
-// Targets are receiver-local SOURCE slots for the immediately following pull.
-// Keep child summation order identical to PatchCoarseStep; no collision here.
-extern "C" __global__ void BlockCoalesce(
-    const fpxx* fine, fpxx* coarse, const uint64_t* target, const uint64_t* children,
-    unsigned int count)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const uint64_t* s = children + 4ul * row;
-    coarse[target[row]] = 0.25f * (fine[s[0]] + fine[s[1]] + fine[s[2]] + fine[s[3]]);
-}
@@ -1,95 +0,0 @@
-// CelerisLab/lbm/kernels/step/patch_step.cu
-// Dense fixed-patch collision, explosion and the fine/coarse steps.
-// Part of the refinement.cu compilation entry; relies on its includes, guards
-// and the optional CELERIS_REFINEMENT_AUDIT counters declared there.
-
-__device__ __forceinline__ void patch_collide(float* f, unsigned long k) {
-#if COLLISION_MODEL == 2
-    collide_mrt_unforced(f);
-#else
-    float rho, ux, uy, feq[NQ];
-    compute_rho_u(f, rho, ux, uy);
-    compute_feq(rho, ux, uy, feq);
-    collide_srt_no_force(f, feq, d_params.omega);
-#endif
-#ifdef CELERIS_REFINEMENT_AUDIT
-    ++collision_counts[k];
-#endif
-}
-
-extern "C" __global__ void PatchExplode(
-    const float* coarse, float* fine, const uint32_t* targets,
-    const uint32_t* donors, unsigned int count, unsigned long coarse_cells)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    for (unsigned int q = 0; q < NQ; ++q)
-        fine[index_f(targets[row], q)] = coarse[q * coarse_cells + donors[row]];
-#ifdef CELERIS_REFINEMENT_AUDIT
-    ++explosion_counts[targets[row]];
-#endif
-}
-
-extern "C" __global__ void PatchFineStep(const float* in, float* out, const uint16_t* flags) {
-    unsigned int x, y; unsigned long k;
-    index_from_thread(x, y, k);
-    if (x >= NX || y >= NY) return;
-    float f[NQ];
-    // Outer halo is invalid after EACH hop, including when reusing the buffer
-    // that held explosion data. Inner halo only streams; it never collides.
-    if (x < 2 || y < 2 || x >= NX - 2 || y >= NY - 2
-            || (flags != nullptr && is_solid(flags[k]))) {
-        fill_invalid(f);
-    } else {
-        unsigned long j[NQ];
-        compute_neighbors(x, y, j);  // These interior targets never wrap.
-        stream_pull_load(k, f, in, j);
-        if (x >= 4 && y >= 4 && x < NX - 4 && y < NY - 4)
-            patch_collide(f, k);
-    }
-    stream_pull_store(k, f, out);
-}
-
-extern "C" __global__ void PatchCoarseStep(
-    const float* in, float* out, const float* fine,
-    const uint64_t* targets, const uint64_t* children, unsigned int count,
-    unsigned int x0, unsigned int y0, unsigned int x1, unsigned int y1,
-    unsigned int wall_aware)
-{
-    unsigned int x, y; unsigned long k;
-    index_from_thread(x, y, k);
-    if (x >= NX || y >= NY) return;
-    // Both buffers were poisoned at initialization; covered cells stay invalid.
-    if (x >= x0 && x < x1 && y >= y0 && y < y1) return;
-    if (wall_aware && (y == 0 || y == NY - 1)) return;
-    unsigned long j[NQ];
-    compute_neighbors(x, y, j);
-    float f[NQ];
-    stream_pull_load(k, f, in, j);
-    if (x >= x0 - 1 && x <= x1 && y >= y0 - 1 && y <= y1) {
-        for (unsigned int q = 1; q < NQ; ++q) {
-            uint64_t slot = index_f(k, q);
-            unsigned int lo = 0, hi = count;
-            while (lo < hi) {
-                unsigned int mid = lo + (hi - lo) / 2;
-                if (targets[mid] < slot) lo = mid + 1;
-                else hi = mid;
-            }
-            if (lo < count && targets[lo] == slot) {
-                const uint64_t* s = children + 4ul * lo;
-                f[q] = 0.25f * (fine[s[0]] + fine[s[1]] + fine[s[2]] + fine[s[3]]);
-#ifdef CELERIS_REFINEMENT_AUDIT
-                ++incoming_counts[slot];
-#endif
-            }
-        }
-    }
-    // Includes the eight grazing-corner links with UNCOVERED coarse donors.
-    // All replacement arrivals must be in place before computing rho/u.
-    if (wall_aware) {
-        if (y == 1) reconstruct_bottom_velocity(f, 0.0f, bottom_wall_normal_velocity(x));
-        else if (y == NY - 2) reconstruct_top_reservoir(f, RHO);
-    }
-    patch_collide(f, k);
-    stream_pull_store(k, f, out);
-}
@@ -21,14 +21,6 @@
 //   i.e. the population traveling in direction i at node n
 //   arrived from the node at n - c_i  = neighbor in direction opp(i)
 // ---------------------------------------------------------------------------
-// load_node: all NQ populations of node n as stored (no streaming).
-__device__ __forceinline__ void load_node(const fpxx* __restrict__ fi, unsigned long n,
-                                          float* __restrict__ f)
-{
-    for (int q = 0; q < NQ; ++q)
-        f[q] = load_ddf(fi, index_f(n, q));
-}
-
 __device__ __forceinline__ void stream_pull_load(unsigned long n,
                                                 float* __restrict__ f,
                                                 const fpxx* __restrict__ fi,
@@ -65,8 +65,52 @@ def _level_name(level):
    return ("base", "fine", "child")[level] if level < 3 else f"level {level}"


+def _legacy_levels(bounds, *, fine_block, base_block, child, child_block, child_rectangles_in_parent,
+                   fine_objects, jets, child_objects, child_jets):
+    """Normalise the original two/three-level keywords to per-level lists (original errors)."""
+    if child is not None and child_rectangles_in_parent is not None:
+        raise ValueError("child and child_rectangles_in_parent are mutually exclusive")
+    nested = child is not None or child_rectangles_in_parent is not None
+    bounds = tuple(bounds)
+    if not is_rectangle(bounds) and (fine_block is None or base_block is None):
+        raise ValueError("several patches require fine_block and base_block")
+    fine_objects, jets = tuple(fine_objects), tuple(jets)
+    child_objects, child_jets = tuple(child_objects), tuple(child_jets)
+    if not nested and (child_objects or child_jets):
+        raise ValueError("child_objects/child_jets require a nested child")
+    if base_block is not None and fine_block is None:
+        raise ValueError("base_block requires fine_block")
+    refinements, blocks = [bounds], [base_block, fine_block]
+    objects, level_jets = [(), fine_objects], [(), jets]
+    if nested:
+        if child is not None and not is_rectangle(bounds):
+            raise ValueError("scalar child requires one parent patch; use child_rectangles_in_parent")
+        if fine_block is None or base_block is None or child_block is None:
+            raise ValueError("a nested child needs fine_block, base_block and child_block")
+        if fine_objects or jets:
+            raise ValueError("a nested child supports bodies/Jets only on L2; use child_objects/child_jets")
+        refinements.append(tuple(child) if child is not None else tuple(child_rectangles_in_parent))
+        blocks.append(child_block)
+        objects.append(child_objects)
+        level_jets.append(child_jets)
+    return refinements, blocks, objects, level_jets
+
+
+def _initial_levels(level_g, coarse_g, fine_g, child_g):
+    """One tuple of per-level arrays from initialize()'s positional or legacy named form."""
+    if coarse_g is None and fine_g is None:
+        if child_g is not None and len(level_g) != 2:
+            raise TypeError("child_g needs exactly the coarse and fine arrays before it")
+        return tuple(level_g) + (() if child_g is None else (child_g,))
+    if level_g:
+        raise TypeError("pass level arrays positionally or as coarse_g/fine_g/child_g, not both")
+    if coarse_g is None or fine_g is None:
+        raise TypeError("coarse_g and fine_g are both required in the named form")
+    return (coarse_g, fine_g) + (() if child_g is None else (child_g,))
+
+
 def _check_levels(refinements, blocks, objects, jets):
-    """Candidate limits of the level lists, checked before any device work."""
+    """Candidate limits shared by the list and the legacy entry points."""
    depth = len(refinements) + 1
    if depth < 2:
        raise ValueError("at least one refinement level is required")
@@ -75,13 +119,13 @@ def _check_levels(refinements, blocks, objects, jets):
            raise ValueError(f"{name} needs one entry per level ({depth})")
    for level, block in enumerate(blocks):
        if block is not None and len(block) != 2:
-            raise ValueError(f"level_blocks[{level}] must be (by, bx)")
+            raise ValueError(f"{_level_name(level)}_block must be (by, bx)")
    if objects[0] or jets[0]:
        raise ValueError("base-level bodies/Jets are not supported")
    if any(blocks[level - 1] is not None and blocks[level] is None for level in range(1, depth)):
        raise ValueError("a blocked level requires blocked refined levels below it")
    if not is_rectangle(refinements[0]) and (blocks[0] is None or blocks[1] is None):
-        raise ValueError("several L1 patches require level_blocks[0] and level_blocks[1]")
+        raise ValueError("several patches require fine_block and base_block")
    if depth > 2:
        if any(block is None for block in blocks):
            raise ValueError("three or more levels must all be blocked")
@@ -90,14 +134,7 @@ def _check_levels(refinements, blocks, objects, jets):


 class FixedPatchStepper:
-    """D2Q9 SRT/MRT FP32 fixed 2:1 refinement hierarchy, built from level lists.
-
-    ``refinements[l]`` gives level l+1 in level-l integer cells: one rectangle
-    (x0, y0, x1, y1) (FixedPatch2D, a fine window with its own origin) or a
-    sequence of rectangles (FixedPatchSet2D, a dependency-validated union on one
-    level-wide grid, public fine arrays (2*ny, 2*nx), NaN outside ACTIVE cells);
-    see lbm.hierarchy. ``level_blocks``, ``level_objects`` and ``level_jets``
-    hold one entry per level, L0 included (L0 bodies/Jets are not supported).
+    """D2Q9/SRT/FP32, one unforced internal 2:1 patch in an x-periodic box.

    ``coarse_boundary`` is ``periodic`` (default) or ``slot_reservoir``:
    a bottom on-site slot and top fixed-density reservoir from ``cfg``.
@@ -108,55 +145,68 @@ class FixedPatchStepper:
    actual channel closure footprint. Channel remapping is not supported.
    Periodic mode does not apply the wall/slot boundary fields in ``cfg``.
    Outer walls remain coarse; fine halo donors must be ordinary fluid.
+    ``fine_objects`` accepts fixed circles in coarse physical coordinates;
+    velocities are in coarse lattice units (dx=dt=1). Independent local copies
+    are projected at fine cell centers. Their complete stencil must be active
+    and disjoint from the actual two-hop transfer footprint.
+    These use the edge/cell-center frame (coarse centers I+.5), whereas ordinary Simulation objects use the integer-node frame.

-    Bodies are fixed circles in root (L0) physical coordinates; velocities are
-    in root lattice units (dx=dt=1). Independent local copies are projected at
-    fine cell centers; their complete stencil must be active and disjoint from
-    the actual two-hop transfer footprint. These use the edge/cell-center frame
-    (coarse centers I+.5), whereas ordinary Simulation objects use the
-    integer-node frame. Jets (body.jets.Jet) use the same frame and drive cut
-    links selected at their true hits; ``set_jet_amplitude(index, amplitude,
-    level=l)`` re-uploads the per-link velocity column only.
-
-    ``initialize(*level_g)`` accepts one physical Q-major (9, ny, nx) array per
-    level, already in postcollision phase. It does not collide or build channel
-    flags. Every ``step()`` publishes only after all levels complete on one
-    stream. On a device/launch failure the instance becomes unusable: close and
-    recreate it, rather than pretending a partially advanced buffer rolled back.
-
-    A ``level_blocks`` entry (by, bx) stores that level in blocks.cu storage:
-    the ENTIRE level shape, including the four-cell patch ghost band, is
-    partitioned by a non-periodic BlockLayout2D with one-cell same-level halos.
-    Patch kinds stay per cell (OUTER invalid, INNER stream only, ACTIVE
-    collide); halos are gathered before each hop. Public arrays keep the dense
-    shapes; only the allocation differs. A blocked level requires blocked
-    refined levels below it; several L1 rectangles and depth >= 3 require all
-    levels blocked. Blocked bodies are stationary circles, optionally
-    surface-actuated: prepare_fine_boundary decides legality on the dense grid,
-    then cut links are staged receiver-local per hop: halo -> BFL -> step, same
-    buffer. A blocked parent gathers halos before receiver-local coalescence
-    staging and pull/collision; covered cells are poisoned on every step.
+    ``initialize(coarse_g, fine_g)`` accepts physical Q-major (9,ny,nx) arrays
+    already in postcollision phase. It does not collide or build channel flags.
+    Every ``step()`` publishes only after both levels complete on one stream.
+    On a device/launch failure the instance becomes unusable: close and recreate
+    it, rather than pretending the partially advanced fine buffer rolled back.

+    ``fine_block=(by, bx)`` (opt-in) stores the fine level in
+    blocks.cu storage: the ENTIRE fine_shape, including the four-cell patch
+    ghost band, is partitioned by a non-periodic BlockLayout2D with one-cell
+    same-level halos. Patch kinds stay per cell (OUTER invalid, INNER stream
+    only, ACTIVE collide); halos are gathered before each fine hop. Public
+    arrays keep the dense (9, ny, nx) fine shape; only the allocation differs.
+    Blocked fine_objects are stationary circles, optionally surface-actuated:
+    prepare_fine_boundary decides legality on the dense fine grid, then cut
+    links are staged receiver-local per hop: halo -> BFL -> step, same buffer.
+    ``base_block=(by, bx)`` also blocks the parent; it requires ``fine_block``.
+    Parent halos precede receiver-local coalescence staging and pull/collision;
+    covered cells are explicitly poisoned on every step. Public shapes stay dense.
    ``observe_raw_exchange=True`` records blocked physical cut-link exchange
    without changing populations. read_raw_exchange reports the last complete
    base interval or last substep in base-lattice units per unit depth. This
    is boundary momentum reaction, not a validated nozzle/stress load. Dense
-    body levels are not supported by this diagnostic.
+    body layouts are not supported by this new diagnostic in this candidate.
    ``observe_window_exchange=True`` (requires observe_raw_exchange) adds a second
    per-link FP64 ledger accumulated by the same kernel between
    start_exchange_window() and read_exchange_window(); disabled by default.
+    ``jets`` (body.jets.Jet) use the same edge frame as ``fine_objects`` and
+    drive fine cut links selected at their true hits; ``set_jet_amplitude``
+    re-uploads the per-link velocity column only.

-    Nested levels: a child set's coordinates index the allocated parent array,
-    including ghost bands and holes: root edge = parent fine_origin + index / 2
-    (zero origin for a parent set; a scalar parent keeps its shifted window
-    origin). A scalar child requires a scalar parent. Rectangle unions impose no
-    fixed gap rule: adjacent, overlapping and concave unions are accepted when
-    their actual transfer dependencies close (FixedPatchSet2D /
-    nest_patch_set). All regions share one buffer pair per level and the fixed
-    schedule of 2**l hops per base step at level l. Bodies/Jets are supported only on the
-    finest level of a nested hierarchy (L2 dx=dt=.25 in root units, unchanged
-    lattice velocity); every whole circle and its BFL stencil must fit strictly
-    away from that level's transfer footprint.
+    Several patches: pass ``bounds`` as a sequence of (x0, y0, x1, y1)
+    rectangles (FixedPatchSet2D, dependency-validated union). This requires
+    fine_block and base_block; fine_objects/jets are projected once onto the
+    level-wide fine grid (each circle inside the union, body ids = object
+    positions, jet and writer checks level-wide), and
+    uses one level-wide fine grid (2*ny, 2*nx): public fine arrays have that
+    shape, NaN outside the patches' ACTIVE cells. The step sequence is the
+    blocked one above, with unique union transfers in one launch each.
+
+    Three-level separated unions: ``child_rectangles_in_parent=[...]`` is
+    mutually exclusive with scalar ``child`` and accepts either parent form.
+    Coordinates index the allocated L1 array, including ghost bands and holes:
+    root edge = patch.fine_origin + L1 index / 2. A parent set has origin zero;
+    a scalar parent retains its shifted window origin. The child set's public
+    extent is twice the allocated L1 shape, even though storage is sparse.
+    Each pair requires gap >= 4 in its own parent-cell units. All regions share
+    one buffer pair per level and the fixed 1:2:4 schedule; L2-only bodies/Jets
+    below apply unchanged, with object IDs assigned over the whole level.
+
+    Three-level single chain: ``child`` bounds use L1 window cells; all three
+    levels must be blocked. ``child_objects`` and ``child_jets`` use the L0
+    edge frame, with L2 dx=dt=.25 and unchanged lattice velocity. L1 bodies
+    and Jets remain unsupported in a chain. Every whole circle and its BFL
+    stencil must fit strictly away from the L2 transfer footprint. L2 runs
+    halo -> BFL -> step four times per base step. Runtime child Jet changes
+    require ``set_jet_amplitude(index, amplitude, level=2)``.

    ``explosion="projected_linear"`` selects experimental transverse linear
    reconstruction on each adjacent pair. Default "constant" is unchanged.
@@ -164,21 +214,43 @@ class FixedPatchStepper:
    bodies/Jets or LES; this backend supplies no forcing. Geometry is generic,
    but union/multilevel GPU and matched-physics qualification remain pending.

-    One recursive hop advances every level: a child explodes from its parent's
-    current hop source, takes two hops, then the parent gathers halos, stages
-    restriction, applies BFL and steps.
+    Level lists (any depth): ``refinements[l]`` gives level l+1 in level-l
+    integer cells (scalar window or rectangle list, see lbm.hierarchy);
+    ``level_blocks``/``level_objects``/``level_jets`` hold one entry per level,
+    L0 included. They are mutually exclusive with the legacy keywords above,
+    which are normalised to the same lists. One recursive hop advances every
+    level: a child explodes from its parent's current hop source, takes two
+    hops, then the parent gathers halos, stages restriction, applies BFL and
+    steps. Depth >= 3 must be fully blocked with bodies/Jets on the finest level.
    """
-    def __init__(self, cfg, *, context, refinements, coarse_boundary="periodic",
-                 level_blocks=None, level_objects=None, level_jets=None,
+    def __init__(self, cfg, bounds=None, *, context, coarse_boundary="periodic", fine_objects=(),
+                 fine_block=None, base_block=None, jets=(), child=None, child_block=None,
+                 child_objects=(), child_jets=(), child_rectangles_in_parent=None,
+                 refinements=None, level_blocks=None, level_objects=None, level_jets=None,
                 observe_raw_exchange=False, observe_window_exchange=False, explosion="constant"):
        if HALO != 4:
            raise RuntimeError("refinement.cu requires a four-cell fine halo")
        if coarse_boundary not in ("periodic", "slot_reservoir", "channel"):
            raise ValueError("coarse_boundary must be periodic, slot_reservoir or channel")
-        depth = len(refinements) + 1
-        level_blocks = [None] * depth if level_blocks is None else list(level_blocks)
-        level_objects = [()] * depth if level_objects is None else list(level_objects)
-        level_jets = [()] * depth if level_jets is None else list(level_jets)
+        if refinements is None:
+            if bounds is None:
+                raise ValueError("bounds or refinements is required")
+            if level_blocks is not None or level_objects is not None or level_jets is not None:
+                raise ValueError("level_blocks/level_objects/level_jets require refinements")
+            refinements, level_blocks, level_objects, level_jets = _legacy_levels(
+                bounds, fine_block=fine_block, base_block=base_block, child=child,
+                child_block=child_block, child_rectangles_in_parent=child_rectangles_in_parent,
+                fine_objects=fine_objects, jets=jets, child_objects=child_objects,
+                child_jets=child_jets)
+        else:
+            if (bounds is not None or child is not None or child_rectangles_in_parent is not None
+                    or fine_block is not None or base_block is not None or child_block is not None
+                    or tuple(fine_objects) or tuple(jets) or tuple(child_objects) or tuple(child_jets)):
+                raise ValueError("refinements and the legacy patch keywords are mutually exclusive")
+            depth = len(refinements) + 1
+            level_blocks = [None] * depth if level_blocks is None else list(level_blocks)
+            level_objects = [()] * depth if level_objects is None else list(level_objects)
+            level_jets = [()] * depth if level_jets is None else list(level_jets)
        level_objects = [tuple(o) for o in level_objects]
        level_jets = [tuple(j) for j in level_jets]
        level_blocks = [None if b is None else tuple(b) for b in level_blocks]
@@ -362,10 +434,7 @@ class FixedPatchStepper:
            raise RuntimeError("level omega/tau mismatch")
        host = self._boundary_hosts[index]
        n_objects = len(host.objects) if name == "PatchFineStep" and host is not None else 0
-        block_root_bc = 0
-        if index == 0 and layout is not None:
-            block_root_bc = 2 if self._channel else 1 if self._wall_aware else 0
-        build = compiler.generate_config(config, n_objects=n_objects, block_root_bc=block_root_bc)
+        build = compiler.generate_config(config, n_objects=n_objects)
        try:
            ptx = compiler.compile_kernel(self.ctx.sm_arch, source=source, build_dir=build)
            module = compiler.load_module(ptx)
@@ -471,13 +540,13 @@ class FixedPatchStepper:
        if self._ddf_shifting and any(layout is None for layout in self._layouts):
            raise ValueError("shifted populations require all-blocked levels")

-    def initialize(self, *level_g):
+    def initialize(self, *level_g, coarse_g=None, fine_g=None, child_g=None):
        """Upload physical postcollision G, encoding before any FP32 rounding.

        Shifted input should be physical FP64 to retain small perturbations.
        Public initialization resets the step count; non-leaves are discarded.
        """
-        given = tuple(level_g)
+        given = _initial_levels(level_g, coarse_g, fine_g, child_g)
        with self._lock, self.ctx.activate():
            self._require("new", "ready")
            self._check_storage()
@@ -601,9 +670,10 @@ class FixedPatchStepper:
                old, new, source, base_count=count, level_steps=(count, 2*count, 4*count),
                phase="postcollision_g", **options)
            candidate = type(self)(
-                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],
+                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,
                observe_raw_exchange=self._observe_raw_exchange,
                observe_window_exchange=self._observe_window, explosion=self._explosion)
            try:
@@ -752,41 +822,27 @@ 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.
-
-        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.
-        """
+        """Advance G→G by n base intervals: level l takes 2**l hops per interval."""
        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:  # stream-ordered: holds the last interval only
+                    if self._observe_raw_exchange:
+                        self._exchange_valid = False
                        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)
-                    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._stream.synchronize()
+                    root.current, root.spare = root.spare, root.current
+                    self._step_count += 1
+                    self._exchange_valid = self._observe_raw_exchange
                self._status = "ready"
            except BaseException:
                self._window_valid = False
@@ -8,7 +8,7 @@ from dataclasses import dataclass, replace
 import numpy as np

 from .blocks import blocked_link_tables
-from ..body.jets import _surface_links
+from ..body.jets import jet_link_shapes, surface_link_velocity
 from .descriptors import D2Q9_EX, D2Q9_EY
 from .refinement import ACTIVE, OUTER_GHOST

@@ -142,13 +142,11 @@ def _prepare_blocked_boundary(boundary, layout, cfg, jets, *, _shifted_blocked=F
    tables.update(body_id=np.asarray(body_id, np.int32), rx=np.asarray(rx, np.float32),
                  ry=np.asarray(ry, np.float32), aperture=np.zeros(len(dirs), bool))
    actuated = bool(jets) or any(o.surface_actuation is not None for o in boundary.objects)
-    jet_cache = None
    if actuated:
        cfg = replace(cfg)
        cfg.validate()
-        tables["surface_velocity"], tables["aperture"], shape, jet_id = _surface_links(
+        tables["surface_velocity"], tables["aperture"] = surface_link_velocity(
            boundary.objects, cfg, boundary.flags, fluid_idx, dirs, body_id, rx, ry,
            jets=jets, hits=boundary.curved_hits, _shifted_blocked=_shifted_blocked)
-        if jets:
-            jet_cache = (shape, jet_id)
-    return _BlockedBoundary(boundary, tables, jets, actuated, jet_cache)
+    return _BlockedBoundary(boundary, tables, jets, actuated,
+                            jet_link_shapes(jets, boundary.curved_hits) if jets else None)
@@ -1,66 +0,0 @@
-"""Checkpoint save -> load round trip for a scene with passive bodies. Requires GPU.
-
-A fresh Simulation with the same scene, restored from the checkpoint must hold the same populations,
-flags, body count and step count, and must stay bitwise identical to the original
-after both continue for the same number of steps. Checkpoints with Jets are
-refused (documented limitation) and are not covered here.
-"""
-
-import os
-import tempfile
-import unittest
-
-import numpy as np
-
-from ._cases import make_sim
-
-# Three separated cylinders (pinball-like); cut-link receivers stay in bulk fluid.
-CIRCLES = (((40, 32), 6), ((56, 22), 6), ((56, 42), 6))
-
-
-def scene():
-    sim = make_sim()
-    sim.initialize()
-    for center, radius in CIRCLES:
-        sim.add_body("circle", center=center, radius=radius)
-    sim.sync_bodies()
-    return sim
-
-
-class CheckpointBodiesGPU(unittest.TestCase):
-    def test_round_trip_is_bitwise_and_continues_identically(self):
-        sim = scene()
-        sim.run(60)
-        with tempfile.NamedTemporaryFile(suffix=".h5", delete=False) as f:
-            path = f.name
-        restored = None
-        try:
-            saved = sim.save_checkpoint(path)
-            # The loader requires the same body count and geometry: rebuild the scene.
-            restored = scene()
-            restored.load_checkpoint(saved)
-
-            self.assertEqual(restored.bodies.count, len(CIRCLES))
-            self.assertEqual(restored.stepper.step_count, sim.stepper.step_count)
-            np.testing.assert_array_equal(restored.get_flags(), sim.get_flags())
-            a, b = sim.get_ddf(), restored.get_ddf()
-            self.assertEqual(a.dtype, b.dtype)
-            self.assertEqual(a.tobytes(), b.tobytes())
-
-            sim.run(40)
-            restored.run(40)
-            self.assertEqual(restored.stepper.step_count, sim.stepper.step_count)
-            a, b = sim.get_ddf(), restored.get_ddf()
-            self.assertTrue(np.isfinite(a).all())
-            self.assertEqual(a.tobytes(), b.tobytes())
-            for i in range(len(CIRCLES)):
-                self.assertTrue(np.all(np.isfinite(restored.read_force(i))))
-        finally:
-            if restored is not None:
-                restored.close()
-            os.unlink(path)
-            sim.close()
-
-
-if __name__ == "__main__":
-    unittest.main()
@@ -16,7 +16,6 @@
 #define NZ 1
 #define NT 1
 #define COLLISION_MODEL 0
-#define BLOCK_ROOT_BC 2
 #define USE_LES 0
 #define RHO 1.f
 #define U0 .025f
@@ -41,7 +40,7 @@ inline float __fdiv_rn(float a,float b){return a/b;}
 #include "boundary/inlet_outlet.cuh"
 #include "step/one_step_double.cu"
 #else
-#include "core/cell_kind.cuh"
+constexpr unsigned char KIND_OUTER=2;
 #include "step/block_channel.cu"
 #endif
 int main(){
@@ -1,46 +0,0 @@
-"""Check historical source manifests against their own recorded commit, not today's checkout."""
-
-import io
-from pathlib import Path
-import subprocess
-import tarfile
-
-ROOT = Path(__file__).resolve().parents[2]
-
-
-def _require(commit):
-    """Missing recorded history is an explicit failure, never a skip or a repin."""
-    found = subprocess.run(
-        ["git", "-C", str(ROOT), "cat-file", "-e", commit + "^{commit}"],
-        capture_output=True,
-    )
-    if found.returncode:
-        raise AssertionError(
-            f"Required history missing: commit {commit} is not in this clone; "
-            "fetch it instead of repinning or substituting"
-        )
-
-
-def tracked(commit, prefix="src"):
-    """Tracked paths under prefix at the recorded commit."""
-    _require(commit)
-    return set(
-        subprocess.check_output(
-            ["git", "-C", str(ROOT), "ls-tree", "-r", "--name-only", commit, prefix],
-            text=True,
-        ).splitlines()
-    )
-
-
-def historical_tree(commit, dest):
-    """Extract the tracked tree of the recorded commit into dest."""
-    _require(commit)
-    archive = subprocess.check_output(
-        ["git", "-C", str(ROOT), "archive", "--format=tar", commit]
-    )
-    dest = Path(dest)
-    dest.mkdir(parents=True, exist_ok=True)
-    extra = {"filter": "data"} if hasattr(tarfile, "data_filter") else {}
-    with tarfile.open(fileobj=io.BytesIO(archive)) as tar:
-        tar.extractall(dest, **extra)
-    return dest
@@ -0,0 +1,101 @@
+"""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()
@@ -1,104 +0,0 @@
-"""Host contract of PeriodicBlockStepper.step(n): one stream wait per call (mocked driver)."""
-import ast
-from contextlib import nullcontext
-import importlib.util
-from pathlib import Path
-import types
-from unittest.mock import Mock
-import unittest
-
-import numpy as np
-
-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."""
-    # Locate the source without importing it: importing block_stepper loads pycuda.driver,
-    # which CPU-only import-boundary tests (test_build_contracts) must never see.
-    path = Path(importlib.util.find_spec("CelerisLab.lbm.block_stepper").origin)
-    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()
@@ -83,32 +83,6 @@ assert abs(sum(compute_feq_d2q9(1.,0.,0.)) - 1.) < 1e-6


 class BuildContracts(unittest.TestCase):
-    def test_block_root_modes_are_rendered_and_recorded(self):
-        with tempfile.TemporaryDirectory() as root:
-            for mode in (0, 1, 2):
-                with self.subTest(mode=mode):
-                    build = compiler.generate_config(LBMConfig(), build_root=root, block_root_bc=mode)
-                    try:
-                        method = Path(build, "config/config_method.h").read_text()
-                        self.assertIn(f"#define BLOCK_ROOT_BC {mode}\n", method)
-                        metadata = json.loads(Path(build, ".celeris-build").read_text())
-                        self.assertEqual(metadata["block_root_bc"], mode)
-                        self.assertNotIn("block_root_bc", metadata["config"])
-                    finally:
-                        compiler.cleanup_build_dir(build)
-            build = compiler.generate_config(LBMConfig(), build_root=root)
-            try:
-                self.assertEqual(json.loads(Path(build, ".celeris-build").read_text())["block_root_bc"], 0)
-            finally:
-                compiler.cleanup_build_dir(build)
-
-    def test_invalid_block_root_mode_fails_before_snapshot(self):
-        for mode in (-1, 3, True, False, 1.0, "1", None):
-            with self.subTest(mode=mode), patch.object(compiler.tempfile, "mkdtemp") as allocate:
-                with self.assertRaisesRegex(ValueError, "block_root_bc"):
-                    compiler.generate_config(LBMConfig(), block_root_bc=mode)
-                allocate.assert_not_called()
-
    @staticmethod
    def fake_compile(command, check):
        source = Path(command[-3])
@@ -50,7 +50,7 @@ def test_masks_and_minimal_footprint():
 def test_actual_closure_read_conflicts():
    pair, layout, targets = transfer((6, 6, 18, 14))
    validate_channel_transfers(pair, layout, targets)
-    for target in (layout.slot(int(layout.owner[5, -1]) - 1, 2),  # integer under NumPy 1 and 2
+    for target in (layout.slot(layout.owner[5, -1]-1, 2),
                   layout.slot(layout.owner[1, 4], 4),
                   layout.slot(layout.owner[-2, 4], 3)):
        with pytest.raises(ValueError, match="immutable"):
@@ -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, context=context, coarse_boundary="channel",
-                                    refinements=[(6, 6, 18, 14)], level_blocks=[(4, 6), (4, 4)])
+    backend = host.FixedPatchStepper(cfg, (6, 6, 18, 14), context=context,
+                                    coarse_boundary="channel", base_block=(4, 6), fine_block=(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]
@@ -97,6 +97,5 @@ def test_evolved_ghost_snapshot_and_physical_download():
        with pytest.raises(ValueError, match="finite"):
            backend.initialize(*arrays)
        assert backend._levels[0].kernel == host.compiler.load_module.return_value.get_function("BlockChannelStep")
-        assert [call.kwargs["block_root_bc"] for call in host.compiler.generate_config.call_args_list] == [2, 0]
    finally:
        backend.close()
@@ -8,7 +8,6 @@ import numpy as np
 ROOT = Path(__file__).resolve().parents[2]
 REPO = ROOT
 sys.path.insert(0, str(ROOT / "tests/validation"))
-sys.path.insert(0, str(ROOT / "tests/unit"))
 sys.path.insert(0, str(REPO / "src"))
 from run_jet_circle_cv import (
    CX,
@@ -20,7 +19,6 @@ from run_jet_circle_cv import (
    cv_from_macros,
    aperture_probe,
    measured_aperture_flux,
-    PIN,
    verify,
 )

@@ -168,13 +166,7 @@ class Host(unittest.TestCase):
        self.assertEqual(a["steps"] * 4, b["steps"])

    def test_source_pin(self):
-        from tempfile import TemporaryDirectory
-        from historical_tree import historical_tree
-
-        with self.assertRaisesRegex(RuntimeError, "Source hash mismatch"):
-            verify(REPO)
-        with TemporaryDirectory() as directory:
-            verify(historical_tree(PIN, directory))
+        verify(REPO)


 if __name__ == "__main__":
@@ -15,10 +15,6 @@ sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "validation"))
 from run_uniform_les_flow import source_guard, decode_macros, HERE, HEADER

 ROOT = HERE.parents[1]
-sys.path.insert(0, str(ROOT / "tests/unit"))
-from historical_tree import historical_tree, tracked
-
-A135 = "a135252ae78b47b57d7e77d19001700b3bedac8b"


 class GuardTests(unittest.TestCase):
@@ -46,23 +42,19 @@ class GuardTests(unittest.TestCase):
            decode_macros(invalid, w, cx, cy)

    def test_current_corrected_pins(self):
-        with TemporaryDirectory() as directory:
-            root = historical_tree(A135, directory)
-            with patch("run_uniform_les_flow.subprocess.check_output", return_value="historical-tree\n"):
-                identity = source_guard(root, "corrected", "a135252")
-            # base_commit comes from the pins file; the mock only feeds checkout_commit.
-            self.assertEqual(identity["base_commit"], A135)
-            self.assertEqual(identity["checkout_commit"], "historical-tree")
+        self.assertEqual(
+            source_guard(ROOT, "corrected", "a135252")["base_commit"],
+            "a135252ae78b47b57d7e77d19001700b3bedac8b",
+        )

    def test_corrected_and_tamper_guard(self):
        pins = json.loads((HERE / "data/les_flow/source_pins_a135252.json").read_text())
        with TemporaryDirectory() as directory:
-            origin = historical_tree(A135, Path(directory) / "origin")
-            root = Path(directory) / "fixture"
+            root = Path(directory)
            for name in pins["sources"]:
                dest = root / name
                dest.parent.mkdir(parents=True, exist_ok=True)
-                shutil.copyfile(origin / name, dest)
+                shutil.copyfile(ROOT / name, dest)
            with patch(
                "run_uniform_les_flow.subprocess.check_output",
                return_value="isolated-fixture\n",
@@ -95,26 +87,23 @@ class GuardTests(unittest.TestCase):

    def test_current_manifest_pins_actual_corrected_tree(self):
        pins = json.loads((HERE / "data/les_flow/source_pins_a135252.json").read_text())
-        self.assertEqual(pins["base_commit"], A135)
-        self.assertEqual(set(pins["sources"]), tracked(A135))
-        with TemporaryDirectory() as directory:
-            root = historical_tree(A135, directory)
-            for name, expected in pins["sources"].items():
-                self.assertEqual(hashlib.sha256((root / name).read_bytes()).hexdigest(), expected)
-            self.assertEqual(pins["sources"][HEADER], pins["candidate_header_sha256"])
-            self.assertNotEqual(pins["sources"][HEADER], pins["baseline_header_sha256"])
-            with self.assertRaisesRegex(RuntimeError, "Source pin mismatch"):
-                source_guard(root, "baseline", "a135252")
+        tracked = subprocess.check_output(["git", "-C", str(ROOT), "ls-files", "src"], text=True)
+        self.assertEqual(set(pins["sources"]), set(tracked.splitlines()))
+        for name, expected in pins["sources"].items():
+            self.assertEqual(hashlib.sha256((ROOT / name).read_bytes()).hexdigest(), expected)
+        self.assertEqual(pins["sources"][HEADER], pins["candidate_header_sha256"])
+        self.assertNotEqual(pins["sources"][HEADER], pins["baseline_header_sha256"])
+        with self.assertRaisesRegex(RuntimeError, "Source pin mismatch"):
+            source_guard(ROOT, "baseline", "a135252")

    def test_named_baseline_accepts_only_reversed_header(self):
        pins = json.loads((HERE / "data/les_flow/source_pins_a135252.json").read_text())
        with TemporaryDirectory() as directory:
-            origin = historical_tree(A135, Path(directory) / "origin")
-            root = Path(directory) / "fixture"
+            root = Path(directory)
            for name in pins["sources"]:
                dest = root / name
                dest.parent.mkdir(parents=True, exist_ok=True)
-                shutil.copyfile(origin / name, dest)
+                shutil.copyfile(ROOT / name, dest)
            subprocess.run(["git", "apply", "--reverse", str(HERE / "les/data/smagorinsky_normalization.patch")], cwd=root, check=True)
            with patch("run_uniform_les_flow.subprocess.check_output", return_value="baseline-fixture\n"):
                source_guard(root, "baseline", "a135252")
@@ -162,7 +162,7 @@ class ProjectedKernelTests(unittest.TestCase):
        targets = child.owner.ravel()[p.ghost_fine]
        donors = parent.owner.ravel()[p.ghost_coarse]
        source = (Path(__file__).resolve().parents[2] /
-                  "src/CelerisLab/lbm/kernels/step/block_transfer.cu").read_text()
+                  "src/CelerisLab/lbm/kernels/blocks.cu").read_text()
        kernel = source.split('extern "C" __global__ void BlockExplodeProjected(',1)[1]
        kernel = 'void BlockExplodeProjected(' + kernel.split('// Targets are receiver-local SOURCE slots',1)[0]
        def array(name, values, kind):
@@ -157,9 +157,8 @@ class RawExchange(unittest.TestCase):
        host = host_module()
        ctx = Mock()
        with self.assertRaisesRegex(ValueError, 'blocked body'):
-            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)
+            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)
        ctx.activate.assert_not_called()

    def test_all_depth_weights(self):
@@ -5,7 +5,6 @@ import pytest

 ROOT = Path(__file__).resolve().parents[2]
 sys.path.insert(0, str(ROOT / "tests/validation"))
-sys.path.insert(0, str(ROOT / "tests/unit"))
 import re100_helpers as h
 import periodic as p

@@ -63,16 +62,13 @@ def test_periodic_synthetic():
    assert not p.assess(rows()[:100])["periodic"]


-def test_production_unmodified(tmp_path):
-    from historical_tree import historical_tree
-
+def test_production_unmodified():
    m = json.loads(
        (ROOT / "tests/validation/data/dfg_re100/source_manifest.json").read_text()
    )
    assert m["commit"] == h.PIN
-    origin = historical_tree(m["commit"], tmp_path)
    for name, digest in m["production_sha256"].items():
-        assert hashlib.sha256((origin / name).read_bytes()).hexdigest() == digest, name
+        assert hashlib.sha256((ROOT / name).read_bytes()).hexdigest() == digest, name


 def test_reference():
@@ -7,10 +7,7 @@ import numpy as np
 import unittest

 sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "validation"))
-sys.path.insert(0, str(Path(__file__).resolve().parent))
 import run_refined_dfg as r
-from historical_tree import historical_tree
-from tempfile import TemporaryDirectory

 h, periodic = r.helpers(r.DEFAULT_SOURCE)

@@ -20,24 +17,11 @@ def test_source_pin():
    assert historical["commit"].startswith("cd3a657")
    mrt_history = json.loads((r.HERE / "data/refined_dfg/source_manifest_mrt.json").read_text())
    assert mrt_history["commit"].startswith("3ea131e")
-    with unittest.TestCase().assertRaisesRegex(RuntimeError, "Source mismatch"):
-        r.verify_source(r.DEFAULT_SOURCE, "MRT", "window")
+    assert r.verify_source(r.DEFAULT_SOURCE, "MRT", "window")["commit"].startswith("a233c90")
    with unittest.TestCase().assertRaisesRegex(RuntimeError, "Source mismatch"):
        r.verify_source(r.DEFAULT_SOURCE, "MRT")
    with unittest.TestCase().assertRaisesRegex(RuntimeError, "Source mismatch"):
        r.verify_source(r.DEFAULT_SOURCE, "SRT")
-    with TemporaryDirectory() as directory:
-        for collision, mode, prefix in (
-            ("SRT", "last_base_step", "cd3a657"),
-            ("MRT", "last_base_step", "3ea131e"),
-            ("MRT", "window", "a233c90"),
-        ):
-            name = {"SRT": "source_manifest.json", "MRT": "source_manifest_mrt.json"}[collision]
-            name = "source_manifest_window.json" if mode == "window" else name
-            commit = json.loads((r.HERE / "data/refined_dfg" / name).read_text())["commit"]
-            assert commit.startswith(prefix)
-            root = historical_tree(commit, Path(directory) / commit)
-            assert r.verify_source(root, collision, mode)["commit"] == commit


 def test_matched_units_and_planes():
@@ -157,47 +141,16 @@ def test_axis_specific_sampling_phase():
    np.testing.assert_allclose(fine_y - ((k + 43) - 0.5) * 0.00125, 0, atol=1e-15)


-def frozen_manifest(observation_mode):
-    """Frozen MRT manifest JSON as recorded, without hashing the working tree."""
-    name = "source_manifest_window.json" if observation_mode == "window" else "source_manifest_mrt.json"
-    return json.loads((r.HERE / "data/refined_dfg" / name).read_text())
-
-
-def selected_manifest(collision, observation_mode):
-    """verify_source's manifest selection with its working-tree hash comparison neutralised.
-
-    Source identity is owned by test_source_pin; this exercises only which frozen manifest
-    verify_source selects and returns for (collision, observation_mode).
-    """
-    from unittest.mock import patch
-
-    class Digest(str):
-        def __ne__(self, other):
-            return False
-
-    class Hash:
-        def __init__(self, data=b""):
-            pass
-
-        def hexdigest(self):
-            return Digest()
-
-    with patch.object(r.hashlib, "sha256", Hash):
-        return r.verify_source(r.DEFAULT_SOURCE, collision, observation_mode)
-
-
 def test_full_requires_completed_pilot():
    with unittest.TestCase().assertRaisesRegex(ValueError, "pilot-results"):
-        r.verify_pilot(None, frozen_manifest("window"))
+        r.verify_pilot(None, r.verify_source(r.DEFAULT_SOURCE, "MRT", "window"))


 def pilot_fixture(path, observation_mode="window", jet_scenario="none", case_selection="both", uniform_diameter=80, placement="wide"):
    """Synthetic contract fixture only; never a physical result or run receipt."""
-    # Receipt-logic fixture: the frozen manifest verify_source returns for a matching tree.
-    # Source identity itself is checked only by test_source_pin.
    manifest = (r.verify_source(r.DEFAULT_SOURCE, "MRT", "window", jet_scenario)
-                if observation_mode == "window" and jet_scenario != "none" else
-                frozen_manifest(observation_mode))
+                if observation_mode == "window" else
+                json.loads((r.HERE / "data/refined_dfg/source_manifest_mrt.json").read_text()))
    selection = dict(case_selection=case_selection, uniform_diameter=uniform_diameter, placement=placement)
    (path / "plan.json").write_text(
        json.dumps(
@@ -395,7 +348,7 @@ def test_record_actual_checkout_separately():
    actual = checkout_provenance(r.DEFAULT_SOURCE)
    assert len(actual["checkout_revision"]) == 40
    assert isinstance(actual["checkout_dirty"], bool)
-    assert selected_manifest("MRT", "window")["production_origin_commit"].startswith("d930")
+    assert r.verify_source(r.DEFAULT_SOURCE, "MRT", "window")["production_origin_commit"].startswith("d930")


 def test_window_plan_preserves_physics():
@@ -405,7 +358,7 @@ def test_window_plan_preserves_physics():
        assert baseline.pop("observation_mode") == "last_base_step"
        assert window.pop("observation_mode") == "window"
        assert baseline == window
-        assert selected_manifest(collision, "window")["observation_mode"] == "window"
+        assert r.verify_source(r.DEFAULT_SOURCE, collision, "window")["observation_mode"] == "window"
    with unittest.TestCase().assertRaises(ValueError):
        r.verify_source(r.DEFAULT_SOURCE, "MRT", "unknown")

@@ -22,16 +22,13 @@ class RefinementMRTHost(unittest.TestCase):

    def test_srt_statements_and_guards_preserved(self):
        """MRT is an additive compile-time branch; SRT statements and other guards remain."""
-        blocks = (KERNELS / "blocks.cu").read_text() + (KERNELS / "step/block_step.cu").read_text()
+        blocks = (KERNELS / "blocks.cu").read_text()
        channel = (KERNELS / "step/block_channel.cu").read_text()
-        block_collision = (KERNELS / "operators/block_collision.cuh").read_text()
-        self.assertIn('#include "operators/block_collision.cuh"', blocks)
-        self.assertEqual(blocks.count("block_collide(f);"), 1)
-        refinement = (KERNELS / "refinement.cu").read_text() + (KERNELS / "step/patch_step.cu").read_text()
+        refinement = (KERNELS / "refinement.cu").read_text()
        for text in ("compute_feq_from_momentum(drho, jx, jy, ux, uy, feq);",
                     "compute_feq(rho, ux, uy, feq);",
                     "collide_srt_no_force(f, feq, d_params.omega);"):
-            self.assertIn(text, block_collision)
+            self.assertIn(text, blocks)
        self.assertIn("collide_srt(f, feq, forcing, omega);", channel)
        self.assertIn("collide_srt_no_force(f, feq, d_params.omega);", refinement)
        for source in (blocks, refinement):
@@ -40,14 +37,8 @@ class RefinementMRTHost(unittest.TestCase):
            self.assertIn("STORE_PRECISION != 0", source)
            self.assertIn('#if COLLISION_MODEL == 2\n#include "operators/collision_mrt.cuh"\n#endif', source)
        self.assertIn("USE_DDF_SHIFTING ||", refinement)  # dense/mixed shifted stays rejected
-        # One shared unforced MRT body; each blocked/patch path calls it exactly once.
-        mrt = (KERNELS / "operators/collision_mrt.cuh").read_text()
-        self.assertEqual(mrt.count("void collide_mrt_unforced("), 1)
-        for source in (blocks + "\n" + block_collision, channel, refinement):
-            self.assertEqual(source.count("collide_mrt_unforced(f);"), 1)
-            self.assertNotIn("collide_mrt_no_force(", source)
-            self.assertNotIn("compute_rho_u(f, rho, ux, uy);\n            collide_mrt", source)
-            self.assertNotRegex(source, r"compute_rho_u\(f, rho, ux, uy\);\s*collide_mrt")
+        for source in (blocks, channel, refinement):
+            self.assertEqual(source.count("collide_mrt_no_force("), 1)


 if __name__ == "__main__": unittest.main()
@@ -173,10 +173,8 @@ def bodies_and_jets(speed=.002):
    return bodies,jets


-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))
+KW=dict(base_block=(4,4),fine_block=(4,4),child_block=(4,4),
+        child_rectangles_in_parent=CHILDREN)


 def mock_backend(*, children=CHILDREN, bodies=False, fail_compile=False, fail_upload=False):
@@ -203,8 +201,9 @@ 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,context=context,
-            **levels(children=children,objects=((),(),objects),jets=((),(),jets)))
+        run=module.FixedPatchStepper(CFG,PARENTS,context=context,
+            child_objects=objects,child_jets=jets,
+            **dict(KW,child_rectangles_in_parent=children))
    except RuntimeError:
        for allocation in allocations:
            allocation.free.assert_called_once_with()
@@ -215,29 +214,28 @@ 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()
-        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))]
+        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))]
        for changes in cases:
            with self.subTest(changes=changes),self.assertRaises((ValueError,TypeError)):
-                host.FixedPatchStepper(CFG,context=context,**levels(**changes))
+                host.FixedPatchStepper(CFG,PARENTS,context=context,**dict(KW,**changes))
        with self.assertRaisesRegex(ValueError,'margin'):
-            host.FixedPatchStepper(CFG,context=context,**levels(parents=[(1,4,20,28),(23,4,44,28)]))
+            host.FixedPatchStepper(CFG,[(1,4,20,28),(23,4,44,28)],context=context,**KW)
        objects,jets=bodies_and_jets()
-        with self.assertRaisesRegex(ValueError,'only on the finest level'):
-            host.FixedPatchStepper(CFG,context=context,**levels(objects=((),objects,())))
+        with self.assertRaisesRegex(ValueError,'only on L2'):
+            host.FixedPatchStepper(CFG,PARENTS,context=context,fine_objects=objects,**KW)
        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,context=context,
-                                  **levels(objects=((),(),objects),jets=((),(),[spanning])))
+            host.FixedPatchStepper(CFG,PARENTS,context=context,child_objects=objects,
+                                  child_jets=[spanning],**KW)
        context.activate.assert_not_called()
        host.cuda.mem_alloc.assert_not_called()

@@ -315,23 +313,21 @@ class ConstructorAndSchedule(unittest.TestCase):



-class RemovedLegacyAPI(unittest.TestCase):
-    """The pre-level-list constructor/initialize forms are gone and fail loudly."""
+class InitialLevels(unittest.TestCase):
+    """initialize() entry adapter: positional per-level arrays or the legacy names, never both."""

-    def test_removed_constructor_forms_raise_type_error(self):
-        import inspect
-        context = Mock()
-        with self.assertRaises(TypeError):  # positional bounds
-            host.FixedPatchStepper(CFG, PARENTS, context=context)
-        removed = dict(bounds=PARENTS, fine_block=(4, 4), base_block=(4, 4), fine_objects=(),
-                       jets=(), child=(8, 8, 16, 16), child_block=(4, 4), child_objects=(),
-                       child_jets=(), child_rectangles_in_parent=CHILDREN)
-        for name, value in removed.items():
-            with self.subTest(keyword=name), self.assertRaises(TypeError):
-                host.FixedPatchStepper(CFG, context=context, **levels(), **{name: value})
-        context.activate.assert_not_called()
-        self.assertEqual(list(inspect.signature(host.FixedPatchStepper.initialize).parameters),
-                         ["self", "level_g"])  # no coarse_g/fine_g/child_g
+    def test_forms(self):
+        a, b, c = object(), object(), object()
+        f = host._initial_levels
+        self.assertEqual(f((a, b), None, None, None), (a, b))
+        self.assertEqual(f((a, b, c), None, None, None), (a, b, c))
+        self.assertEqual(f((a, b), None, None, c), (a, b, c))      # old initialize(c, f, child_g=g)
+        self.assertEqual(f((), a, b, None), (a, b))
+        self.assertEqual(f((), a, b, c), (a, b, c))
+        for args in (((a,), None, None, c), ((a, b, c), None, None, c), ((a,), a, b, None),
+                     ((), a, None, None), ((), None, b, c)):
+            with self.subTest(args=args), self.assertRaises(TypeError):
+                f(*args)


 if __name__=='__main__':
@@ -54,13 +54,14 @@ 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,context=None,refinements=[backend.PARENTS,A],
-                    level_blocks=[(4,4)]*3,level_objects=[(),(),objects],level_jets=[(),(),jets])
+                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)
        for blocks in ((None,None,None),((4,4),None,(4,4))):
            with self.assertRaises(ValueError):
-                module.FixedPatchStepper(CFG,context=None,refinements=[backend.PARENTS,A],
-                    level_blocks=list(blocks),level_objects=[(),(),(body(),)],
-                    level_jets=[(),(),(jet(),)])
+                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.cuda.mem_alloc.assert_not_called()
        module.compiler.compile_kernel.assert_not_called()

@@ -78,15 +78,13 @@ class ShiftedStorage(unittest.TestCase):

    def test_shifted_density_and_tag_validation(self):
        old,new = topology(A),topology(B)
-        a = tuple(np.where(m[None], np.float32(-.001), np.float32(np.nan)).repeat(9,axis=0)
-                  for m in old.leaf_masks)  # FP32 under NumPy 1 and 2 promotion rules
+        a = tuple(np.where(m[None], np.float32(-.001), np.nan).repeat(9,axis=0) for m in old.leaf_masks)
        remap(old,new,a)
        with self.assertRaisesRegex(ValueError,'representation'): remap(old,new,a,False)
        with self.assertRaisesRegex(ValueError,'FP32'): remap(old,new,tuple(x.astype(np.float64) for x in a))
        a[0][:,old.leaf_masks[0]] = -1
        with self.assertRaisesRegex(ValueError,'positive density'): remap(old,new,a)
-        rest = tuple(np.where(m[None],np.float32(0),np.float32(np.nan)).repeat(9,axis=0)
-                     for m in old.leaf_masks)
+        rest = tuple(np.where(m[None],np.float32(0),np.nan).repeat(9,axis=0) for m in old.leaf_masks)
        remap(old,new,rest)
        with self.assertRaisesRegex(ValueError,'positive density'):
            remap_synchronized(old,new,rest,base_count=7,level_steps=(7,14,28),phase='postcollision_g')
@@ -131,10 +129,9 @@ 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 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)
+        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)
        module.compiler.compile_kernel.assert_not_called()

    def test_uniform_block_codec_and_raw_snapshot(self):
@@ -1,170 +0,0 @@
-"""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()
@@ -12,15 +12,13 @@ from source_provenance import checkout_provenance
 import re100_helpers
 import run_jet_circle_cv

-sys.path.insert(0, str(ROOT / "tests/unit"))
-from historical_tree import historical_tree, tracked
-
 ORIGIN = "47b05bc8abfc957fe876b0c63bdb386e3c6cbaa5"


-def test_manifests_cover_current_source_and_preserve_origin(tmp_path):
-    assert re100_helpers.PIN == run_jet_circle_cv.PIN == ORIGIN
-    manifests = {}
+def test_manifests_cover_current_source_and_preserve_origin():
+    names = subprocess.check_output(
+        ["git", "-C", str(ROOT), "ls-files", "src"], text=True
+    ).splitlines()
    for group, hashes_key, revision_key in (
        ("dfg_re100", "production_sha256", "commit"),
        ("jet_circle_cv", "files", "revision"),
@@ -31,22 +29,18 @@ def test_manifests_cover_current_source_and_preserve_origin(tmp_path):
            ).read_text()
        )
        assert manifest[revision_key] == ORIGIN
+        assert set(manifest[hashes_key]) == set(names)
        assert manifest["source_origin_commits"][-1] == ORIGIN
        assert (
            manifest["historical_checkpoints"]["production"]
            == "d79e3f6f0a424f5bcc3a1a6d610313e49daf97a2"
        )
        assert "not inherited from d79" in manifest["experiment"]
-        manifests[group] = manifest[hashes_key]
-    # History-dependent checks last, so a missing commit masks nothing above.
-    names = tracked(ORIGIN)
-    origin = historical_tree(ORIGIN, tmp_path)
-    for group, hashes in manifests.items():
-        assert set(hashes) == set(names), group
-        for name, expected in hashes.items():
+        for name, expected in manifest[hashes_key].items():
            assert (
-                hashlib.sha256((origin / name).read_bytes()).hexdigest() == expected
+                hashlib.sha256((ROOT / name).read_bytes()).hexdigest() == expected
            ), name
+    assert re100_helpers.PIN == run_jet_circle_cv.PIN == ORIGIN


 def test_runtime_checkout_identity_is_separate_from_source_origin(tmp_path):
@@ -0,0 +1,75 @@
+"""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
@@ -192,7 +192,6 @@ class CpuContracts(unittest.TestCase):
        backend._lock = RLock()
        backend._status = "ready"
        backend._step_count = 0
-        backend._ddf_shifting = False  # unshifted storage, as for the default config
        backend._stream = Mock()
        backend._module = Mock()
        backend._copy = backend._step = Mock()
@@ -27,7 +27,7 @@ def state(ny, nx):

 def compile_module(cfg, context, source):
    cfg.validate()
-    build = compiler.generate_config(cfg, block_root_bc=2 if source == "blocks.cu" else 0)
+    build = compiler.generate_config(cfg)
    try:
        module = compiler.load_module(compiler.compile_kernel(context.sm_arch, source=source, build_dir=build))
    finally:
@@ -106,10 +106,9 @@ class ChannelRootGPU(unittest.TestCase):
                    cfg = LBMConfig(nx=48, ny=32, viscosity=.1, velocity=.015, ddf_shifting=shifted)
                    reference = None
                    for block in ((32,48), (8,8), (4,1)):
-                        with FixedPatchStepper(cfg, context=context, coarse_boundary="channel",
-                                refinements=[(8,6,40,26)], level_blocks=[block, (8,8)],
-                                level_objects=[(), (body,) if bodies else ()],
-                                level_jets=[(), (jet,) if bodies else ()]) as backend:
+                        with FixedPatchStepper(cfg, (8,6,40,26), context=context,
+                                coarse_boundary="channel", base_block=block, fine_block=(8,8),
+                                fine_objects=(body,) if bodies else (), jets=(jet,) if bodies else ()) as backend:
                            arrays = [state(*level.shape[1:]) for level in backend._levels]
                            backend.initialize(*arrays)
                            backend.step(4)
@@ -25,8 +25,8 @@ EPS = np.finfo(np.float64).eps


 def build(m, window=True, raw=True):
-    return FixedPatchStepper(config("periodic"), context=m["context"], refinements=[BOUNDS],
-                             level_blocks=[(3, 4), (16, 20)], level_objects=[(), (circle(),)],
+    return FixedPatchStepper(config("periodic"), BOUNDS, context=m["context"], base_block=(3, 4),
+                             fine_block=(16, 20), fine_objects=[circle()],
                             observe_raw_exchange=raw, observe_window_exchange=window)


@@ -109,11 +109,10 @@ class ExchangeWindowGPU(unittest.TestCase):
        from test_raw_exchange_gpu import BOUNDS as RB, CFG, circle as rc, jet, state
        from CelerisLab.cuda.context import CudaContext
        with CudaContext(0) as ctx:
-            kw = dict(context=ctx, refinements=[RB], level_blocks=[None, (16, 20)],
-                      level_objects=[(), (rc(),)], level_jets=[(), (jet(),)],
+            kw = dict(context=ctx, fine_block=(16, 20), fine_objects=[rc()], jets=[jet()],
                      observe_raw_exchange=True)
-            with FixedPatchStepper(CFG, observe_window_exchange=True, **kw) as windowed, \
-                 FixedPatchStepper(CFG, **kw) as plain:
+            with FixedPatchStepper(CFG, RB, observe_window_exchange=True, **kw) as windowed, \
+                 FixedPatchStepper(CFG, RB, **kw) as plain:
                arrays = [state(level.shape) for level in windowed._levels]
                windowed.initialize(*arrays)
                plain.initialize(*arrays)
@@ -201,11 +200,11 @@ class ExchangeWindowShiftedMRTGPU(unittest.TestCase):
        from CelerisLab.cuda.context import CudaContext
        cfg = LBMConfig(nx=32, ny=24, viscosity=.1, collision="MRT", ddf_shifting=True)
        with CudaContext(0) as ctx:
-            kw = dict(context=ctx, refinements=[RB], level_blocks=[(12, 8), (16, 20)],
-                      level_objects=[(), (rc(),)], observe_raw_exchange=True)
-            with FixedPatchStepper(cfg, observe_window_exchange=True, **kw) as windowed, \
-                 FixedPatchStepper(cfg, observe_window_exchange=True, **kw) as split, \
-                 FixedPatchStepper(cfg, **kw) as plain:
+            kw = dict(context=ctx, base_block=(12, 8), fine_block=(16, 20), fine_objects=[rc()],
+                      observe_raw_exchange=True)
+            with FixedPatchStepper(cfg, RB, observe_window_exchange=True, **kw) as windowed, \
+                 FixedPatchStepper(cfg, RB, observe_window_exchange=True, **kw) as split, \
+                 FixedPatchStepper(cfg, RB, **kw) as plain:
                arrays = [state(level.shape) for level in windowed._levels]
                for run in (windowed, split, plain):
                    run.initialize(*arrays)
@@ -140,8 +140,7 @@ def run_patch(speed, *, audit=True):
        build = (patch.object(compiler, "compile_kernel", audit_compiler(compiler.compile_kernel))
                 if audit else nullcontext())
        with build:
-            backend = implementation.FixedPatchStepper(cfg, context=context, refinements=[BOUNDS],
-                                             level_objects=[(), (source,)])
+            backend = implementation.FixedPatchStepper(cfg, BOUNDS, context=context, fine_objects=[source])
        with backend, context.activate():
            c, f = backend._levels
            cl = backend._fine_curved
@@ -282,8 +281,7 @@ def test_fine_surface_four_hops(speed):
@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)
-    backend._boundary_hosts = [None, SimpleNamespace(objects=[object_spec(.002)])]
-    backend._level_jets = [(), ()]
+    backend.fine_boundary = SimpleNamespace(objects=[object_spec(.002)])
    backend._fine_curved = SimpleNamespace(fluid_idx_gpu=object(),
                                          surface_velocity_gpu=object(), link_exchange_gpu=object())
    setattr(backend._fine_curved, missing, None)
@@ -327,7 +325,6 @@ def test_cross_interface_donor_rejects_before_cuda():
    context.activate.side_effect = AssertionError("must reject before CUDA activation")
    with patch.object(cuda, "mem_alloc") as allocate:
        with pytest.raises(ValueError, match="donor crosses"):
-            implementation.FixedPatchStepper(cfg, context=context, refinements=[BOUNDS],
-                                             level_objects=[(), (source,)])
+            implementation.FixedPatchStepper(cfg, BOUNDS, context=context, fine_objects=[source])
        context.activate.assert_not_called()
        allocate.assert_not_called()
@@ -48,8 +48,9 @@ def make(context):
        for (x, y), amplitude in zip(centers, (.003, -.002))
    )
    run = FixedPatchStepper(
-        CFG, context=context, refinements=[PARENTS, START], level_blocks=[(4, 4)] * 3,
-        level_objects=[(), (), objects], level_jets=[(), (), jets],
+        CFG, PARENTS, context=context, base_block=(4, 4), fine_block=(4, 4),
+        child_block=(4, 4), child_rectangles_in_parent=START,
+        child_objects=objects, child_jets=jets,
    )
    return run, objects

@@ -25,8 +25,9 @@ B = ((16,16,32,40), (60,16,76,40))
 def make(ctx):
    body = SimObject(71, geometry=CircleGeometry(12.,14.,.8),center=(12.,14.),radius=.8)
    jet = Jet(Tube((10.5,14.),0.,3.,.3),Parallel(0.),'parabolic',.003)
-    run = FixedPatchStepper(CFG,context=ctx,refinements=[PARENTS,A],level_blocks=[(4,4)]*3,
-                           level_objects=[(),(),(body,)],level_jets=[(),(),(jet,)])
+    run = FixedPatchStepper(CFG,PARENTS,context=ctx,base_block=(4,4),fine_block=(4,4),
+                           child_block=(4,4),child_rectangles_in_parent=A,
+                           child_objects=(body,),child_jets=(jet,))
    return run,(body,)


@@ -90,18 +90,14 @@ def census(run, index, buffer):
    return totals(dense, leaf), external, independent


-
-def fine(block):
-    """Two-level circle+jet construction on BOUNDS; block None keeps the dense fine level."""
-    return dict(refinements=[BOUNDS], level_blocks=[None, block],
-                level_objects=[(), (circle(),)], level_jets=[(), (jet(),)])
-
 class RawExchangeGPU(unittest.TestCase):
    def test_row_ledger_interval_jet_switch_and_no_population_effect(self):
        with CudaContext(0) as ctx:
            for block in ((32, 40), (16, 20), (8, 10)):
-                with FixedPatchStepper(CFG, context=ctx, **fine(block), observe_raw_exchange=True) as measured, \
-                     FixedPatchStepper(CFG, context=ctx, **fine(block)) as plain:
+                with FixedPatchStepper(CFG, BOUNDS, context=ctx, fine_block=block,
+                        fine_objects=[circle()], jets=[jet()], observe_raw_exchange=True) as measured, \
+                     FixedPatchStepper(CFG, BOUNDS, context=ctx, fine_block=block,
+                        fine_objects=[circle()], jets=[jet()]) as plain:
                    arrays = [state(l.shape) for l in measured._levels]
                    measured.initialize(*arrays)
                    plain.initialize(*arrays)
@@ -150,8 +146,9 @@ class RawExchangeGPU(unittest.TestCase):
        """Same fine resolution/initial data with dense storage: a numerical
        reference for cut-link rows, not a uniform-whole-domain convergence study."""
        with CudaContext(0) as ctx:
-            with FixedPatchStepper(CFG, context=ctx, **fine(None)) as dense, \
-                 FixedPatchStepper(CFG, context=ctx, **fine((16, 20)), observe_raw_exchange=True) as blocked:
+            with FixedPatchStepper(CFG, BOUNDS, context=ctx, fine_objects=[circle()], jets=[jet()]) as dense, \
+                 FixedPatchStepper(CFG, BOUNDS, context=ctx, fine_block=(16, 20),
+                    fine_objects=[circle()], jets=[jet()], observe_raw_exchange=True) as blocked:
                arrays = [state(l.shape) for l in blocked._levels]
                dense.initialize(*arrays)
                blocked.initialize(*arrays)
@@ -232,7 +229,8 @@ class RawExchangeGPU(unittest.TestCase):
        layout = BlockLayout2D.build(48, 64, 8, 8)
        with CudaContext(0) as ctx:
            with PeriodicBlockStepper(fine_cfg, layout, context=ctx, objects=[obj]) as uniform, \
-                 FixedPatchStepper(CFG, context=ctx, **fine((16, 20)), observe_raw_exchange=True) as amr:
+                 FixedPatchStepper(CFG, BOUNDS, context=ctx, fine_block=(16, 20),
+                    fine_objects=[circle()], jets=[jet()], observe_raw_exchange=True) as amr:
                amr.initialize(*(state(l.shape) for l in amr._levels))
                uniform.initialize(state((9, 48, 64)))
                b = amr._level_boundaries[1]
@@ -83,10 +83,11 @@ def mocked_backend(mode="periodic", fail_alloc=None):
 class BlockedBaseCPU(unittest.TestCase):
    def test_reject_before_cuda(self):
        context = Mock(activate=Mock(side_effect=AssertionError("CUDA reached")))
-        for blocks in ([(12, 8), None], [(7, 8), FINE_BLOCK], [(12,), FINE_BLOCK]):
-            with self.subTest(blocks=blocks), self.assertRaises(ValueError):
-                FixedPatchStepper(config("periodic"), context=context, refinements=[BOUNDS],
-                                  level_blocks=blocks)
+        for kwargs in ({"base_block": (12, 8)},
+                       {"base_block": (7, 8), "fine_block": FINE_BLOCK},
+                       {"base_block": (12,), "fine_block": FINE_BLOCK}):
+            with self.subTest(kwargs=kwargs), self.assertRaises(ValueError):
+                FixedPatchStepper(config("periodic"), BOUNDS, context=context, **kwargs)
        context.activate.assert_not_called()

    def test_all_arrival_rows_donors_and_kind_masks(self):
@@ -192,10 +193,9 @@ class BlockedBaseCPU(unittest.TestCase):

    def test_launch_order_stream_wall_constants_and_buffer_swaps(self):
        with mocked_backend("slot_reservoir") as m:
-            backend = FixedPatchStepper(config("slot_reservoir"), context=m["context"],
-                                        coarse_boundary="slot_reservoir", refinements=[BOUNDS],
-                                        level_blocks=[(3, 4), FINE_BLOCK],
-                                        level_objects=[(), (circle(actuation(.002)),)])
+            backend = FixedPatchStepper(config("slot_reservoir"), BOUNDS, context=m["context"],
+                                        coarse_boundary="slot_reservoir", fine_block=FINE_BLOCK,
+                                        base_block=(3, 4), fine_objects=[circle(actuation(.002))])
            try:
                backend.initialize(state(NY, NX, 1), state(*backend.patch.fine_shape, 2))
                coarse, fine = backend._levels
@@ -223,8 +223,6 @@ class BlockedBaseCPU(unittest.TestCase):
                    self.assertIs(collide[4], coarse.kind)
                walls = [a for ptr, a in m["uploads"] if isinstance(ptr, str) and ptr == "d_block_wall"]
                self.assertEqual(len(walls), 1)
-                self.assertEqual([call.kwargs["block_root_bc"] for call in
-                                  compiler.generate_config.call_args_list], [1, 0])
                width, height, slot, speed = struct.unpack("=IIIf", walls[0])
                self.assertEqual((width, height, slot), (NX, NY, 8))
                self.assertAlmostEqual(speed, .001)
@@ -238,16 +236,16 @@ class BlockedBaseCPU(unittest.TestCase):
        for fail_at in (1, 6, 10):
            with self.subTest(fail_at=fail_at), mocked_backend(fail_alloc=fail_at) as m:
                with self.assertRaisesRegex(MemoryError, "injected allocation"):
-                    FixedPatchStepper(config("periodic"), context=m["context"], refinements=[BOUNDS],
-                                      level_blocks=[(3, 4), FINE_BLOCK])
+                    FixedPatchStepper(config("periodic"), BOUNDS, context=m["context"],
+                                      fine_block=FINE_BLOCK, base_block=(3, 4))
                self.assertEqual(len(m["allocations"]), fail_at)
                for allocation in m["allocations"]:
                    allocation.free.assert_called_once_with()

    def test_failed_parent_stage_cannot_publish_or_resume(self):
        with mocked_backend() as m:
-            backend = FixedPatchStepper(config("periodic"), context=m["context"], refinements=[BOUNDS],
-                                        level_blocks=[(3, 4), FINE_BLOCK])
+            backend = FixedPatchStepper(config("periodic"), BOUNDS, context=m["context"],
+                                        fine_block=FINE_BLOCK, base_block=(3, 4))
            backend.initialize(state(NY, NX, 1), state(*backend.patch.fine_shape, 2))
            m["functions"]["BlockCoalesce"].side_effect = RuntimeError("injected parent stage failure")
            current = backend._levels[0].current
@@ -291,10 +289,9 @@ class BlockedBaseGPU(unittest.TestCase):
                    for base_block in (None, *layouts):
                        label = f"{mode} width={width} speed={speed} base={base_block}"
                        snapshots = []
-                        with FixedPatchStepper(cfg, context=context, coarse_boundary=mode,
-                                               refinements=[BOUNDS], level_blocks=[base_block, FINE_BLOCK],
-                                               level_objects=[(), () if speed is None
-                                                              else (circle(actuation(speed)),)]) as backend:
+                        with FixedPatchStepper(cfg, BOUNDS, context=context, coarse_boundary=mode,
+                                               fine_block=FINE_BLOCK, base_block=base_block,
+                                               fine_objects=() if speed is None else [circle(actuation(speed))]) as backend:
                            backend.initialize(*arrays)
                            for step in (0, 1, 2, 8):
                                if step == 1 and base_block is not None:
@@ -105,10 +105,9 @@ class BlockedFineCPU(unittest.TestCase):
        return Mock(activate=Mock(side_effect=AssertionError("CUDA reached")), sm_arch="sm_70")

    def test_rejections_before_cuda(self):
-        for kw in ({"level_blocks": [None, (7, 7)]}, {"level_blocks": [None, (16,)]}):
+        for kw in ({"fine_block": (7, 7)}, {"fine_block": (16,)}):
            with self.subTest(kw=kw), self.assertRaises(ValueError):
-                FixedPatchStepper(config("periodic"), context=self.forbidden_context(),
-                                  refinements=[BOUNDS], **kw)
+                FixedPatchStepper(config("periodic"), BOUNDS, context=self.forbidden_context(), **kw)

    def test_single_block_layout_allocates_no_empty_halo_tables(self):
        # A 1x1 non-periodic fine layout has zero halo pairs; CUDA rejects mem_alloc(0).
@@ -126,8 +125,8 @@ class BlockedFineCPU(unittest.TestCase):
                patch.object(compiler, "compile_kernel"), patch.object(compiler, "cleanup_build_dir"), \
                patch.object(compiler, "load_module", return_value=module), \
                patch.object(cuda, "mem_alloc", side_effect=alloc), patch.object(cuda, "memcpy_htod"):
-            backend = FixedPatchStepper(config("periodic"), context=context, refinements=[BOUNDS],
-                                        level_blocks=[None, FINE_BLOCKS[0]])
+            backend = FixedPatchStepper(config("periodic"), BOUNDS, context=context,
+                                        fine_block=FINE_BLOCKS[0])
            self.assertEqual(len(backend.fine_layout.halo_dst), 0)
            self.assertIsNone(backend._levels[1].halo_dst)
            backend._gather_halo(backend._levels[1], Mock())  # no launch without pairs
@@ -178,9 +177,8 @@ class BlockedFineCPU(unittest.TestCase):
                patch.object(cuda, "mem_alloc", side_effect=lambda size: Mock()), \
                patch.object(cuda, "memcpy_htod"), \
                patch.object(curved_links, "CurvedLinkSoA", side_effect=AssertionError("dense SoA built")):
-            backend = FixedPatchStepper(config("periodic"), context=context, refinements=[BOUNDS],
-                                        level_blocks=[None, FINE_BLOCKS[1]],
-                                        level_objects=[(), tuple(objects)])
+            backend = FixedPatchStepper(config("periodic"), BOUNDS, context=context,
+                                        fine_objects=objects, fine_block=FINE_BLOCKS[1])
            backend.initialize(state(NY, NX, 1), state(*backend.patch.fine_shape, 2))
        return backend, calls

@@ -291,9 +289,8 @@ class BlockedFineGPU(unittest.TestCase):
            results = []
            with CudaContext(0) as context:
                for fine_block in (None, *FINE_BLOCKS):
-                    with FixedPatchStepper(cfg, context=context, coarse_boundary=mode,
-                                           refinements=[BOUNDS],
-                                           level_blocks=[None, fine_block]) as backend:
+                    with FixedPatchStepper(cfg, BOUNDS, context=context, coarse_boundary=mode,
+                                           fine_block=fine_block) as backend:
                        backend.initialize(g_coarse, g_fine)
                        backend.step(STEPS)
                        self.assertEqual(backend.step_count, STEPS)
@@ -321,9 +318,8 @@ class BlockedFineGPU(unittest.TestCase):
            results = []
            with CudaContext(0) as context:
                for fine_block in (None, *FINE_BLOCKS):
-                    with FixedPatchStepper(cfg, context=context, coarse_boundary=mode,
-                                           refinements=[BOUNDS], level_blocks=[None, fine_block],
-                                           level_objects=[(), (circle(),)]) as backend:
+                    with FixedPatchStepper(cfg, BOUNDS, context=context, coarse_boundary=mode,
+                                           fine_objects=[circle()], fine_block=fine_block) as backend:
                        backend.initialize(g_coarse, g_fine)
                        backend.step(STEPS)
                        results.append((backend.download(), raw(backend)))
@@ -350,9 +346,9 @@ class BlockedFineGPU(unittest.TestCase):
                results = []
                with CudaContext(0) as context:
                    for fine_block in (None, *FINE_BLOCKS):
-                        with FixedPatchStepper(cfg, context=context, coarse_boundary=mode,
-                                               refinements=[BOUNDS], level_blocks=[None, fine_block],
-                                               level_objects=[(), (circle(actuation(speed)),)]) as backend:
+                        with FixedPatchStepper(cfg, BOUNDS, context=context, coarse_boundary=mode,
+                                               fine_objects=[circle(actuation(speed))],
+                                               fine_block=fine_block) as backend:
                            backend.initialize(g_coarse, g_fine)
                            backend.step(STEPS)
                            results.append((backend.download(), raw(backend)))
@@ -94,8 +94,7 @@ class FaultGuardsCPU(unittest.TestCase):
                             ("slot_reservoir", (12, 4, 20, 21))):
            with self.subTest(mode=mode, bounds=bounds):
                with self.assertRaises(ValueError):
-                    implementation.FixedPatchStepper(cfg, context=context, coarse_boundary=mode,
-                                                     refinements=[bounds])
+                    implementation.FixedPatchStepper(cfg, bounds, context=context, coarse_boundary=mode)
                context.activate.assert_not_called()
        # Both exact channel limits and the original periodic two-cell margin
        # must reach context activation, with no allocation or device required.
@@ -103,14 +102,11 @@ class FaultGuardsCPU(unittest.TestCase):
                             ("periodic", (2, 2, 6, 5))):
            with self.subTest(mode=mode, bounds=bounds):
                with self.assertRaisesRegex(RuntimeError, "validated before CUDA"):
-                    implementation.FixedPatchStepper(cfg, context=context, coarse_boundary=mode,
-                                                     refinements=[bounds])
+                    implementation.FixedPatchStepper(cfg, bounds, context=context, coarse_boundary=mode)

    def fake_backend(self):
        backend = PeriodicPatchStepper.__new__(PeriodicPatchStepper)
-        backend._layouts = [None, None]  # dense storage on both levels
-        backend._ddf_shifting = False  # unshifted on every level, as _check_storage expects
-        backend._level_cfgs = [LBMConfig(nx=16, ny=16, viscosity=.1)] * 2  # ddf_shifting off
+        backend.fine_layout = None  # dense fine storage
        backend.ctx = Mock(activate=nullcontext)
        backend._lock = RLock()
        backend._status = "ready"
@@ -158,23 +154,12 @@ class FaultGuardsCPU(unittest.TestCase):
        context = Mock(activate=nullcontext, sm_arch="sm_70")
        with patch.object(implementation, "HALO", 2):
            with self.assertRaisesRegex(RuntimeError, "four-cell"):
-                PeriodicPatchStepper(cfg, context=context, refinements=[(4, 4, 12, 12)])
+                PeriodicPatchStepper(cfg, (4, 4, 12, 12), context=context)
        p = implementation.FixedPatch2D.from_config(cfg, (4, 4, 12, 12))
-        from CelerisLab.lbm import hierarchy
-        bad = patch.object(implementation.FixedPatch2D, "from_config",
-                           return_value=replace(p, tau_coarse=.9))
-        # A pair tau inconsistent with its level config is rejected twice over, both before
-        # any device allocation or upload: first by the hierarchy chain check, and, if that
-        # is bypassed, by the per-level omega/tau check in _build_level.
-        with patch.object(cuda, "Stream"), bad, patch.object(cuda, "mem_alloc") as alloc, \
-                patch.object(cuda, "memcpy_htod") as upload:
-            with self.assertRaisesRegex(RuntimeError, "config chain is inconsistent"):
-                PeriodicPatchStepper(cfg, context=context, refinements=[p.bounds])
-            with patch.object(hierarchy, "_check_chain"), \
-                    self.assertRaisesRegex(RuntimeError, "omega/tau"):
-                PeriodicPatchStepper(cfg, context=context, refinements=[p.bounds])
-            alloc.assert_not_called()
-            upload.assert_not_called()
+        with patch.object(cuda, "Stream"), patch.object(implementation.FixedPatch2D, "from_config",
+                                                       return_value=replace(p, tau_coarse=.9)):
+            with self.assertRaisesRegex(RuntimeError, "omega/tau"):
+                PeriodicPatchStepper(cfg, p.bounds, context=context)
        module = Mock()
        module.get_global.return_value = (Mock(), 16)
        with patch.object(cuda, "Stream"), patch.object(compiler, "generate_config"), \
@@ -182,7 +167,7 @@ class FaultGuardsCPU(unittest.TestCase):
                patch.object(compiler, "load_module", return_value=module), \
                patch.object(cuda, "memcpy_htod") as upload:
            with self.assertRaisesRegex(RuntimeError, "layout mismatch"):
-                PeriodicPatchStepper(cfg, context=context, refinements=[p.bounds])
+                PeriodicPatchStepper(cfg, p.bounds, context=context)
            upload.assert_not_called()


@@ -256,7 +241,7 @@ class NormalBuildGPU(unittest.TestCase):
        max_error = max_bc_error = 0.0
        with CudaContext(0) as context:
            with patch.object(compiler, "generate_config", side_effect=record_config):
-                backend = implementation.FixedPatchStepper(cfg, context=context, refinements=[bounds],
+                backend = implementation.FixedPatchStepper(cfg, bounds, context=context,
                                                            coarse_boundary="slot_reservoir")
            with backend:
                self.assertEqual(len(generated), 2)
@@ -326,8 +311,7 @@ class NormalBuildGPU(unittest.TestCase):
                            for a in (initial.coarse_f, initial.fine_f)))
        max_pop = max_drift = max_moment = 0.0
        with CudaContext(0) as context, PeriodicPatchStepper(
-                LBMConfig(nx=16, ny=16, viscosity=.1), context=context,
-                refinements=[(4, 4, 12, 12)]) as backend:
+                LBMConfig(nx=16, ny=16, viscosity=.1), (4, 4, 12, 12), context=context) as backend:
            backend.initialize(*postcollision(state, spec, maps))
            before = totals(backend.download(), maps)
            for step in range(1, 9):
@@ -358,7 +342,7 @@ class NormalBuildGPU(unittest.TestCase):
        fine_mask[4:-4, 4:-4] = True
        initial[1][:, ~fine_mask] = np.nan
        expected = scalar_interval(*[a.astype(np.float64) for a in initial], bounds)
-        with CudaContext(0) as context, PeriodicPatchStepper(cfg, context=context, refinements=[bounds]) as backend:
+        with CudaContext(0) as context, PeriodicPatchStepper(cfg, bounds, context=context) as backend:
            self.assertEqual(backend.patch.fine_shape, (14, 16))
            p = backend.patch
            allocated = 2 * 9 * (17*13+16*14) * 4 + sum(a.nbytes for a in
@@ -84,13 +84,13 @@ class CoupledGPU(unittest.TestCase):

        cases = (("dense_unshifted", False, {}),
                 ("blocked_shifted", True,
-                  dict(level_blocks=[(4, 4), (6, 6)])))
+                  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, context=context, refinements=[(4, 4, 12, 12)],
+                    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)
@@ -148,7 +148,7 @@ class CoupledGPU(unittest.TestCase):
        maps = ref.build_maps(spec)
        with CudaContext(0) as context:
            with PeriodicPatchStepper(LBMConfig(nx=16, ny=16, viscosity=.1),
-                                      context=context, refinements=[(4, 4, 12, 12)]) as backend:
+                                      (4, 4, 12, 12), context=context) as backend:
                backend.initialize(*postcollision(ref.make_state(spec), spec, maps))
                coarse, fine = backend._levels

@@ -187,7 +187,7 @@ class CoupledGPU(unittest.TestCase):

        with CudaContext(0) as context:
            with patch.object(compiler, "compile_kernel", audit_compile):
-                backend = PeriodicPatchStepper(cfg, context=context, refinements=[(4, 4, 12, 12)])
+                backend = PeriodicPatchStepper(cfg, (4, 4, 12, 12), context=context)
            with backend:
                # Production allocations: four DDF arrays and four compact tables.
                device_bytes = 2 * 9 * (16**2 + 24**2) * 4
@@ -270,7 +270,7 @@ class CoupledGPU(unittest.TestCase):
                backend.download()

            # Compile and execute the actual non-audited entry as well: one step.
-            with PeriodicPatchStepper(cfg, context=context, refinements=[(4, 4, 12, 12)]) as plain:
+            with PeriodicPatchStepper(cfg, (4, 4, 12, 12), context=context) as plain:
                rest = postcollision(ref.make_state(spec), spec, maps)
                plain.initialize(*rest)
                plain.step()
@@ -41,9 +41,8 @@ def mocked(objects, jets, fine_block):
            patch.object(compiler, "load_module", return_value=module), \
            patch.object(cuda, "mem_alloc", side_effect=lambda size: Mock()), \
            patch.object(cuda, "memcpy_htod", htod):
-        backend = FixedPatchStepper(config("periodic"), context=context, refinements=[BOUNDS],
-                                    level_blocks=[None, fine_block], level_objects=[(), tuple(objects)],
-                                    level_jets=[(), tuple(jets)])
+        backend = FixedPatchStepper(config("periodic"), BOUNDS, context=context,
+                                    fine_objects=objects, fine_block=fine_block, jets=jets)
    return backend, htod


@@ -150,9 +149,8 @@ class JetStepperCPU(unittest.TestCase):
    def test_jet_overlapping_legacy_aperture_rejected_before_cuda(self):
        with patch.object(cuda, "Stream", side_effect=AssertionError("CUDA touched")):
            with self.assertRaisesRegex(ValueError, "SurfaceActuation"):
-                FixedPatchStepper(config("periodic"), context=Mock(), refinements=[BOUNDS],
-                                  level_objects=[(), (circle(actuation(SPEED)),)],
-                                  level_jets=[(), (jet(),)])
+                FixedPatchStepper(config("periodic"), BOUNDS, context=Mock(),
+                                  fine_objects=[circle(actuation(SPEED))], jets=[jet()])


 def run(mode, fine_block, *, objects, jets, switch=None):
@@ -160,9 +158,8 @@ def run(mode, fine_block, *, objects, jets, switch=None):
    cfg = config(mode)
    patch_ = FixedPatch2D.from_config(cfg, BOUNDS)
    with CudaContext(0) as context, FixedPatchStepper(
-            cfg, context=context, coarse_boundary=mode, refinements=[BOUNDS],
-            level_blocks=[None, fine_block], level_objects=[(), tuple(objects)],
-            level_jets=[(), tuple(jets)]) as backend:
+            cfg, BOUNDS, context=context, coarse_boundary=mode, fine_objects=objects,
+            fine_block=fine_block, jets=jets) as backend:
        backend.initialize(state(NY, NX, 1), state(*patch_.fine_shape, 2))
        if switch is None:
            backend.step(STEPS)
@@ -42,9 +42,8 @@ class RefinementMRTGPU(unittest.TestCase):
                                    collision="MRT", ddf_shifting=shifted)
                    reference = None
                    for block in ((32, 48), (8, 8), (4, 1)):
-                        with FixedPatchStepper(cfg, context=context, coarse_boundary=boundary,
-                                               refinements=[(8, 6, 40, 26)], level_blocks=[block, (8, 8)],
-                                               level_objects=[(), (body,)]) as backend:
+                        with FixedPatchStepper(cfg, (8, 6, 40, 26), context=context, coarse_boundary=boundary,
+                                               base_block=block, fine_block=(8, 8), fine_objects=(body,)) as backend:
                            backend.initialize(*[state(*level.shape[1:]) for level in backend._levels])
                            backend.step(8)
                            raw = backend._download_raw()
@@ -64,8 +63,8 @@ class RefinementMRTGPU(unittest.TestCase):
            results = {}
            layouts = ((None, None), *((base, FINE_BLOCK) for base in (None, *BASE_BLOCKS)))
            for base_block, fine_block in layouts:
-                with FixedPatchStepper(cfg, context=context, refinements=[BOUNDS],
-                                       level_blocks=[base_block, fine_block]) as backend:
+                with FixedPatchStepper(cfg, BOUNDS, context=context, fine_block=fine_block,
+                                       base_block=base_block) as backend:
                    backend.initialize(*[fixture.state(*level.shape[1:], seed) for seed, level in enumerate(backend._levels)])
                    backend.step(4)
                    results[base_block, fine_block] = raw(backend)
@@ -76,9 +75,9 @@ class RefinementMRTGPU(unittest.TestCase):
    def test_shifted_all_blocked_three_level_mrt_smoke(self):
        """Per-level shear rate omega_l = 1/(3*2**l*nu + 1/2); finite ACTIVE leaves."""
        cfg = LBMConfig(nx=16, ny=16, viscosity=.1, collision="MRT", ddf_shifting=True)
-        kw = dict(refinements=[(4, 4, 12, 12), (8, 8, 16, 16)], level_blocks=[(4, 4)] * 3)
+        kw = dict(fine_block=(4, 4), base_block=(4, 4), child=(8, 8, 16, 16), child_block=(4, 4))
        with CudaContext(0) as context:
-            with FixedPatchStepper(cfg, context=context, **kw) as backend:
+            with FixedPatchStepper(cfg, (4, 4, 12, 12), context=context, **kw) as backend:
                self.assertEqual(len(backend._level_cfgs), 3)
                for level, level_cfg in enumerate(backend._level_cfgs):
                    checked = replace(level_cfg)
@@ -26,12 +26,6 @@ FACE = ((4, 4, 8, 12), (12, 4, 16, 12))
 S1 = ((4, 4, 12, 12), (20, 4, 28, 12))


-def levels(bounds, blocks=(None, None), objects=(), jets=(), **rest):
-    """Two-level constructor keywords: one L1 rectangle or set, per-level blocks, L1 bodies/Jets."""
-    return dict(refinements=[bounds], level_blocks=list(blocks),
-                level_objects=[(), tuple(objects)], level_jets=[(), tuple(jets)], **rest)
-
-
 def level_fine(patch_set, windows):
    """Level-wide fine array with each patch window filled from `windows`."""
    out = np.full((9, *patch_set.fine_shape), np.nan, np.float32)
@@ -51,21 +45,21 @@ class MultipatchCPU(unittest.TestCase):
    def test_rejections_before_cuda(self):
        cfg = config("periodic")
        context = object()  # never activated: every case must fail first
-        for kw in (dict(), dict(blocks=(None, (8, 4))), dict(blocks=((4, 4), None)),
-                   dict(blocks=((4, 4), (8, 4)), objects=[circle()]),
-                   dict(blocks=((4, 4), (5, 4)))):
+        for kw in (dict(), dict(fine_block=(8, 4)), dict(base_block=(4, 4)),
+                   dict(fine_block=(8, 4), base_block=(4, 4), fine_objects=[circle()]),
+                   dict(fine_block=(5, 4), base_block=(4, 4))):
            with self.subTest(kw=kw), self.assertRaises(ValueError):
-                FixedPatchStepper(cfg, context=context, **levels(((4, 4, 8, 12), (14, 4, 18, 12)), **kw))
+                FixedPatchStepper(cfg, ((4, 4, 8, 12), (14, 4, 18, 12)), context=context, **kw)
        with self.assertRaisesRegex(ValueError, "margin"):
-            FixedPatchStepper(cfg, context=context,
-                              **levels(((1, 4, 8, 12), (10, 4, 14, 12)), blocks=((4, 4), (8, 4))))
+            FixedPatchStepper(cfg, ((1, 4, 8, 12), (10, 4, 14, 12)), context=context,
+                              fine_block=(8, 4), base_block=(4, 4))
        from CelerisLab.body.jets import Jet, Parallel, Tube
        cfg32 = LBMConfig(nx=32, ny=16, viscosity=.1)
        span = Jet(Tube((5., 8.), 0., 22., .6), Parallel(0.), amplitude=0.)
        with self.assertRaisesRegex(ValueError, "one jet"):  # same obj_id cannot bypass it
-            FixedPatchStepper(cfg32, context=context,
-                              **levels(((2, 2, 14, 14), (18, 2, 30, 14)), blocks=((4, 4), (4, 4)),
-                                       objects=[body(8., 8.), body(24., 8.)], jets=[span]))
+            FixedPatchStepper(cfg32, ((2, 2, 14, 14), (18, 2, 30, 14)), context=context,
+                              fine_block=(4, 4), base_block=(4, 4),
+                              fine_objects=[body(8., 8.), body(24., 8.)], jets=[span])


 class MultipatchGPU(unittest.TestCase):
@@ -73,7 +67,7 @@ class MultipatchGPU(unittest.TestCase):

    def run_steps(self, context, cfg, bounds, coarse, fine, **kw):
        out = []
-        with FixedPatchStepper(cfg, context=context, **levels(bounds, **kw)) as backend:
+        with FixedPatchStepper(cfg, bounds, context=context, **kw) as backend:
            backend.initialize(coarse, fine)
            for step in self.STEPS:
                backend.step(step - backend.step_count)
@@ -88,7 +82,7 @@ class MultipatchGPU(unittest.TestCase):
                p = FixedPatch2D.from_config(cfg, BOUNDS)
                s = FixedPatchSet2D.from_config(cfg, (BOUNDS,))
                coarse, fine = state(NY, NX, 1), state(*p.fine_shape, 2)
-                kw = dict(coarse_boundary=mode, blocks=((3, 4), (8, 4)))
+                kw = dict(coarse_boundary=mode, fine_block=(8, 4), base_block=(3, 4))
                old = self.run_steps(context, cfg, BOUNDS, coarse, fine, **kw)
                new = self.run_steps(context, cfg, (BOUNDS,), coarse, level_fine(s, [fine]), **kw)
                for step, a, b in zip(self.STEPS, old, new):
@@ -105,7 +99,7 @@ class MultipatchGPU(unittest.TestCase):
        one = FixedPatchSet2D.from_config(cfg16, (S1[0],))
        two = FixedPatchSet2D.from_config(cfg32, S1)
        coarse, fine = state(16, 16, 3), state(*one.patches[0].fine_shape, 4)
-        kw = dict(blocks=((4, 4), (4, 4)))
+        kw = dict(fine_block=(4, 4), base_block=(4, 4))
        with CudaContext(0) as context:
            ref = self.run_steps(context, cfg16, (S1[0],), coarse, level_fine(one, [fine]), **kw)
            tiled = np.concatenate([coarse, coarse], axis=2)
@@ -124,7 +118,7 @@ class MultipatchGPU(unittest.TestCase):
        s = FixedPatchSet2D.from_config(cfg, FACE)
        coarse = state(16, 24, 5)
        fine = level_fine(s, [state(*p.fine_shape, 6 + i) for i, p in enumerate(s.patches)])
-        kw = dict(blocks=((4, 4), (4, 4)))
+        kw = dict(fine_block=(4, 4), base_block=(4, 4))
        leaf = s.fine_kind == ACTIVE
        support = s.fine_layout((4, 4)).owned
        outer = support & (s.fine_kind == OUTER_GHOST)
@@ -170,7 +164,7 @@ class MultipatchBodiesGPU(unittest.TestCase):

    def run_steps(self, context, cfg, bounds, coarse, fine, switch=None, **kw):
        out = []
-        with FixedPatchStepper(cfg, context=context, **levels(bounds, **kw)) as backend:
+        with FixedPatchStepper(cfg, bounds, context=context, **kw) as backend:
            backend.initialize(coarse, fine)
            for step in self.STEPS:
                if switch is not None and step == 8:
@@ -188,7 +182,8 @@ class MultipatchBodiesGPU(unittest.TestCase):
                p = FixedPatch2D.from_config(cfg, BOUNDS)
                s = FixedPatchSet2D.from_config(cfg, (BOUNDS,))
                coarse, fine = state(NY, NX, 1), state(*p.fine_shape, 2)
-                kw = dict(coarse_boundary=mode, blocks=((3, 4), (8, 4)), objects=[circle()])
+                kw = dict(coarse_boundary=mode, fine_block=(8, 4), base_block=(3, 4),
+                          fine_objects=[circle()])
                old = self.run_steps(context, cfg, BOUNDS, coarse, fine, **kw)
                new = self.run_steps(context, cfg, (BOUNDS,), coarse, level_fine(s, [fine]), **kw)
                for step, a, b in zip(self.STEPS, old, new):
@@ -207,17 +202,17 @@ class MultipatchBodiesGPU(unittest.TestCase):
        two = FixedPatchSet2D.from_config(cfg32, self.PATCHES)
        coarse, fine = state(16, 16, 3), state(*one.patches[0].fine_shape, 4)
        jet = lambda x: Jet(Tube((x, 8.), 0., 6., .6), Parallel(0.), amplitude=.002)
-        kw = dict(blocks=((4, 4), (4, 4)))
+        kw = dict(fine_block=(4, 4), base_block=(4, 4))
        with CudaContext(0) as context:
            for jets in ((), (jet(5.),)):
                ref = self.run_steps(context, cfg16, self.PATCHES[:1], coarse, level_fine(one, [fine]),
                                     switch=[(0, -.001)] if jets else None,
-                                     objects=[body(8., 8.)], jets=jets, **kw)
+                                     fine_objects=[body(8., 8.)], jets=jets, **kw)
                both = jets and (jet(5.), jet(21.))
                got = self.run_steps(context, cfg32, self.PATCHES, np.concatenate([coarse, coarse], 2),
                                     level_fine(two, [fine, fine]),
                                     switch=[(0, -.001), (1, -.001)] if jets else None,
-                                     objects=[body(8., 8., 5), body(24., 8., 5)],
+                                     fine_objects=[body(8., 8., 5), body(24., 8., 5)],
                                     jets=both or (), **kw)
                for step, a, b in zip(self.STEPS, ref, got):
                    label = f"jets={len(jets)} step {step}"
@@ -27,16 +27,7 @@ from test_refinement_blocked_base import raw

 CFG = LBMConfig(nx=16, ny=16, viscosity=.1)
 L1, L2 = (4, 4, 12, 12), (8, 8, 16, 16)
-B = (4, 4)
-
-
-def levels(l1=L1, l2=L2, blocks=(B, B, B), objects=((), (), ()), jets=((), (), ())):
-    """Level-list keywords for the scalar L1 patch with one scalar L2 child."""
-    return dict(refinements=[l1, l2], level_blocks=list(blocks),
-                level_objects=list(objects), level_jets=list(jets))
-
-
-KW = levels()
+KW = dict(fine_block=(4, 4), base_block=(4, 4), child=L2, child_block=(4, 4))


 def child_body(spec=None):
@@ -61,29 +52,26 @@ def mocked_child():
            patch.object(compiler, "load_module", return_value=module), \
            patch.object(cuda, "mem_alloc", side_effect=lambda size: Mock()), \
            patch.object(cuda, "memcpy_htod"):
-        return FixedPatchStepper(CFG, context=context,
-                                 **levels(objects=((), (), (child_body(),)), jets=((), (), (child_jet(),))))
+        return FixedPatchStepper(CFG, L1, context=context, child_objects=[child_body()],
+                                 child_jets=[child_jet()], **KW)


 class ThreeLevelCPU(unittest.TestCase):
    def test_rejections_before_cuda(self):
        context = object()  # never activated: every case must fail first
-        bad = (levels(blocks=(B, B, None)), levels(blocks=(B, None, B)),
-               levels(objects=((), (circle(),), ())), levels(l2=(4, 8, 16, 16)),
-               levels(blocks=(B, B, (5, 4))))
+        bad = (dict(KW, child_block=None), dict(KW, fine_block=None),
+               dict(KW, fine_objects=[circle()]), dict(KW, child=(4, 8, 16, 16)),
+               dict(KW, child_block=(5, 4)))
        for kw in bad:
            with self.subTest(kw=kw), self.assertRaises(ValueError):
-                FixedPatchStepper(CFG, context=context, **kw)
-        # L2 bodies/Jets without an L2 level (one entry too many), and an L2 Jet without a body.
-        two_level = dict(refinements=[L1], level_blocks=[None, None])
-        for kw in (dict(two_level, level_objects=[(), (), (child_body(),)]),
-                   dict(two_level, level_jets=[(), (), (child_jet(),)]),
-                   levels(jets=((), (), (child_jet(),)))):
+                FixedPatchStepper(CFG, L1, context=context, **kw)
+        for kw in (dict(child_objects=[child_body()]), dict(child_jets=[child_jet()]),
+                   dict(KW, child_jets=[child_jet()])):
            with self.assertRaises(ValueError):
-                FixedPatchStepper(CFG, context=context, **kw)
-        with self.assertRaises(ValueError):  # several L1 patches + scalar child: not yet
-            FixedPatchStepper(LBMConfig(nx=32, ny=16, viscosity=.1), context=context,
-                              **levels(l1=((4, 4, 12, 12), (20, 4, 28, 12))))
+                FixedPatchStepper(CFG, L1, context=context, **kw)
+        with self.assertRaises(ValueError):  # several L1 patches + child: not yet
+            FixedPatchStepper(LBMConfig(nx=32, ny=16, viscosity=.1), ((4, 4, 12, 12), (20, 4, 28, 12)),
+                              context=context, **KW)


    def test_four_halo_bfl_steps_and_fresh_middle_feeds(self):
@@ -168,7 +156,7 @@ class ThreeLevelGPU(unittest.TestCase):
    def test_equilibrium_is_kept_on_every_level(self):
        from CelerisLab.cuda.context import CudaContext
        feq = np.asarray(compute_feq_d2q9(1.0, .03, -.02), np.float32)[:, None, None]
-        with CudaContext(0) as ctx, FixedPatchStepper(CFG, context=ctx, **KW) as run:
+        with CudaContext(0) as ctx, FixedPatchStepper(CFG, L1, context=ctx, **KW) as run:
            shapes = ((16, 16), run.patch.fine_shape, run.child_patch.fine_shape)
            run.initialize(*(np.broadcast_to(feq, (9, *s)).copy() for s in shapes))
            run.step(8)
@@ -181,7 +169,7 @@ class ThreeLevelGPU(unittest.TestCase):

    def test_nonequilibrium_masks_and_fresh_middle_feeds(self):
        from CelerisLab.cuda.context import CudaContext
-        with CudaContext(0) as ctx, FixedPatchStepper(CFG, context=ctx, **KW) as run:
+        with CudaContext(0) as ctx, FixedPatchStepper(CFG, L1, context=ctx, **KW) as run:
            p1, p2 = run.patch, run.child_patch
            run.initialize(state(16, 16, 1), state(*p1.fine_shape, 2), state(*p2.fine_shape, 3))
            f = run._levels[1]
@@ -217,9 +205,8 @@ class ThreeLevelBodyGPU(unittest.TestCase):
            CFG, velocity=0., wall_normal_velocity=.001, wall_slot_width=4,
            y_wall_bc="on_site_velocity", top_wall_bc="reservoir")
        with CudaContext(0) as ctx, FixedPatchStepper(
-                cfg, context=ctx, coarse_boundary=mode,
-                **levels(blocks=(B, B, block), objects=((), (), (child_body(spec),)),
-                         jets=((), (), tuple(jets)))) as run:
+                cfg, L1, context=ctx, coarse_boundary=mode, child_objects=[child_body(spec)],
+                child_jets=jets, **dict(KW, child_block=block)) as run:
            run.initialize(*(state(*level.shape[1:], i + 1) for i, level in enumerate(run._levels)))
            snapshots = []
            for stop in (0, 1, 2, 4, 8):
@@ -78,10 +78,10 @@ class ThreeLevelMultipatchGPU(unittest.TestCase):
    def run_case(self, ctx, cfg=CFG, parents=PARENTS, children=CHILDREN,
                 mode='periodic', blocks=((4, 4), (4, 4)), objects=(), drive=(), switch=False,
                 scalar_child=None):
-        child = children if scalar_child is None else scalar_child
-        with FixedPatchStepper(config(cfg, mode), context=ctx, coarse_boundary=mode,
-                refinements=[parents, child], level_blocks=[(4, 4), blocks[0], blocks[1]],
-                level_objects=[(), (), objects], level_jets=[(), (), drive]) as run:
+        kwargs = dict(child_rectangles_in_parent=children) if scalar_child is None else dict(child=scalar_child)
+        with FixedPatchStepper(config(cfg, mode), parents, context=ctx, coarse_boundary=mode,
+                base_block=(4, 4), fine_block=blocks[0], child_block=blocks[1],
+                child_objects=objects, child_jets=drive, **kwargs) as run:
            frame = frames(run)
            run.initialize(*(physical_state(level.shape[1:], *f)
                             for level, f in zip(run._levels, frame)))
@@ -26,8 +26,9 @@ FP64_ATOL = 3e-6


 def make(ctx):
-    return FixedPatchStepper(CFG, context=ctx, refinements=[PARENTS, A],
-                             level_blocks=[(4, 4)] * 3)
+    return FixedPatchStepper(CFG, PARENTS, context=ctx, base_block=(4, 4),
+                             fine_block=(4, 4), child_block=(4, 4),
+                             child_rectangles_in_parent=A)


 def initial(run, uniform):
@@ -136,8 +136,8 @@ class ShiftedJetsGPU(unittest.TestCase):
                  Parallel(0.),amplitude=.013)
        for rho in (.99,1.01):
            with self.subTest(rho=rho),CudaContext(0) as ctx:
-                with FixedPatchStepper(cfg,context=ctx,refinements=[(8,6,24,18)],level_blocks=[(4,4)]*2,
-                        level_objects=[(),(obj,)],level_jets=[(),(whole,)],observe_raw_exchange=True) as run:
+                with FixedPatchStepper(cfg,(8,6,24,18),context=ctx,base_block=(4,4),fine_block=(4,4),
+                        fine_objects=(obj,),jets=(whole,),observe_raw_exchange=True) as run:
                    run._initialize_raw(initial(run,rho,u=.013,v=0.))
                    expected=run._download_raw();ledger=Ledger(self,run,1)
                    self.assertTrue(run._level_boundaries[1].tables['aperture'].all())
@@ -153,8 +153,7 @@ class ShiftedJetsGPU(unittest.TestCase):
        obj=circle((16.,12.),2.15);j=drive((16.,12.),2.15)
        for rho in (.99,1.01):
            with self.subTest(rho=rho),CudaContext(0) as ctx,ExitStack() as owned:
-                settings=dict(context=ctx,refinements=[(8,6,24,18)],level_blocks=[(4,4)]*2,
-                              level_objects=[(),(obj,)],level_jets=[(),(j,)])
+                settings=dict(bounds=(8,6,24,18),context=ctx,base_block=(4,4),fine_block=(4,4),fine_objects=(obj,),jets=(j,))
                measured=owned.enter_context(FixedPatchStepper(cfg,observe_raw_exchange=True,**settings))
                plain=owned.enter_context(FixedPatchStepper(cfg,**settings))
                measured._initialize_raw(initial(measured,rho));plain._initialize_raw(initial(plain,rho))
@@ -187,9 +186,8 @@ class ShiftedJetsGPU(unittest.TestCase):
        parents=((4,4,20,28),(24,4,44,28));a=((16,16,32,40),(56,16,72,40));b=(a[0],(60,16,76,40))
        obj=circle((12.,14.),.8);j=drive((12.,14.),.8)
        with CudaContext(0) as ctx,ExitStack() as owned:
-            old=owned.enter_context(FixedPatchStepper(cfg,context=ctx,refinements=[parents,a],
-                level_blocks=[(4,4)]*3,level_objects=[(),(),(obj,)],level_jets=[(),(),(j,)],
-                observe_raw_exchange=True))
+            old=owned.enter_context(FixedPatchStepper(cfg,parents,context=ctx,base_block=(4,4),fine_block=(4,4),
+                child_block=(4,4),child_rectangles_in_parent=a,child_objects=(obj,),child_jets=(j,),observe_raw_exchange=True))
            old._initialize_raw(initial(old,.99));ledger=Ledger(self,old,2)
            for speed in (.002,-.001):old.set_jet_amplitude(0,speed,level=2);ledger.step()
            before=old._download_raw();count=old.step_count
@@ -22,8 +22,9 @@ B=((20,16,36,40),)


 def make(ctx):
-    return FixedPatchStepper(CFG,context=ctx,refinements=[PARENTS,A],
-                             level_blocks=[(4,4)]*3)
+    return FixedPatchStepper(CFG,PARENTS,context=ctx,base_block=(4,4),
+                             fine_block=(4,4),child_block=(4,4),
+                             child_rectangles_in_parent=A)


 def initial(run):
@@ -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, context=context, coarse_boundary="channel", refinements=[rr.PLACEMENTS["wide"]],
-                level_blocks=[rr.BASE_BLOCK, rr.FINE_BLOCK], level_objects=[(), (body,)],
+                cfg, rr.PLACEMENTS["wide"], context=context, coarse_boundary="channel",
+                base_block=rr.BASE_BLOCK, fine_block=rr.FINE_BLOCK, fine_objects=(body,),
                observe_raw_exchange=True, observe_window_exchange=True))
            from CelerisLab.lbm.channel import channel_masks
            from CelerisLab.lbm.refinement import ACTIVE
@@ -279,11 +279,12 @@ 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,
-            refinements=[c["bounds"]],
-            level_blocks=[(8, 8), (8, 8)],
-            level_objects=[(), (obj,)],
-            level_jets=[(), tuple(jets)],
+            base_block=(8, 8),
+            fine_block=(8, 8),
+            fine_objects=[obj],
+            jets=jets,
            observe_raw_exchange=True,
        ) as amr,
    ):
@@ -383,12 +383,13 @@ def run_case(a, h, periodic, case):
            backend = stack.enter_context(
                FixedPatchStepper(
                    cfg,
+                    PLACEMENTS[a.placement],
                    context=context,
                    coarse_boundary="channel",
-                    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)],
+                    base_block=BASE_BLOCK,
+                    fine_block=FINE_BLOCK,
+                    fine_objects=(body,),
+                    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 {}),
                )
@@ -249,41 +249,19 @@ class ProjectedPairsTests(unittest.TestCase):
        self.assertFalse(assess(incomplete)["comparisons"][3]["passed"])

    def test_pinned_build_sources_match_host_generated_inputs(self):
-        """Check the pinned fingerprints using NUMERICAL_REVISION's renderer and kernels.
-        The imported LBMConfig is unchanged from that revision; this is a host
-        build-input check, not a reconstruction of the historical CUDA toolchain."""
-        import importlib.util
-        import tarfile
+        from CelerisLab.cuda import compiler_v2

-        kernels = "src/CelerisLab/lbm/kernels"
-        renderer = "src/CelerisLab/cuda/compiler_v2.py"
-        if subprocess.run(["git", "-C", str(REPO), "cat-file", "-e",
-                           f"{NUMERICAL_REVISION}^{{commit}}"], capture_output=True).returncode:
-            self.fail(f"{NUMERICAL_REVISION} is not in this clone; the pinned build "
-                      "sources cannot be checked")
-        archive = subprocess.run(["git", "-C", str(REPO), "archive", "--format=tar",
-                                  NUMERICAL_REVISION, kernels, renderer],
-                                 capture_output=True, check=True).stdout
-        with tempfile.TemporaryDirectory() as snapshot:
-            with tarfile.open(fileobj=io.BytesIO(archive)) as tar:
-                tar.extractall(snapshot)
-            spec = importlib.util.spec_from_file_location(
-                "CelerisLab.cuda._compiler_a135252", Path(snapshot) / renderer)
-            compiler = importlib.util.module_from_spec(spec)
-            spec.loader.exec_module(compiler)
-            with patch.object(compiler, "_KERNEL_DIR", str(Path(snapshot) / kernels)):
-                for size in (128, 256):
-                    with self.subTest(size=size):
-                        cfg = replace(run_case.config(size, 100), nx=10, ny=10)
-                        cfg.validate()
-                        root = compiler.generate_config(cfg)
-                        try:
-                            actual = json.loads((Path(root) / ".celeris-build").read_text())
-                            expected = build_metadata(size)
-                            self.assertEqual(actual, {key: expected[key] for key in
-                                                      ("source_sha256", "config", "n_objects")})
-                        finally:
-                            compiler.cleanup_build_dir(root)
+        for size in (128, 256):
+            cfg = replace(run_case.config(size, 100), nx=10, ny=10)
+            cfg.validate()
+            root = compiler_v2.generate_config(cfg)
+            try:
+                actual = json.loads((Path(root) / ".celeris-build").read_text())
+                expected = build_metadata(size)
+                self.assertEqual(actual, {key: expected[key] for key in
+                                          ("source_sha256", "config", "n_objects")})
+            finally:
+                compiler_v2.cleanup_build_dir(root)

    def test_source_preflight_requires_clean_exact_revision_and_tree(self):
        import oracle
@@ -173,9 +173,8 @@ 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, context=context, coarse_boundary="channel", refinements=[r.BOUNDS],
-            level_blocks=[r.BASE_BLOCK, r.FINE_BLOCK], level_objects=[(), (body,)],
-            observe_raw_exchange=True))
+            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))
        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),
@@ -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, context=context, coarse_boundary="channel", refinements=[r.BOUNDS],
-            level_blocks=[r.BASE_BLOCK, r.FINE_BLOCK], level_objects=[(), (body,)], observe_raw_exchange=True,
+            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,
            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)]