test: give the fault-guard fake backend its storage representation

download() now runs _check_storage(), which reads _ddf_shifting and the per-level configs; the fake backend set neither. Both are set to the unshifted default, so the download/step failure assertions run again. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
test: update stale fixtures for current sources (no src change)
2026-10-20 18:14:02 +00:00 · 2026-10-20 13:51:12 +00:00
107 changed files with 1493 additions and 3806 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,
@@ -1,35 +0,0 @@
-# Compatibility and API changes
-
-Changes that can make a previously accepted setup or call behave differently.
-Each entry names the commit, the affected entry points and the observable result.
-
-## 87c3a31: cut-link ownership is validated for every body
-
-`validate_cut_link_ownership` (`body/preprocess/flag_overlay.py`) now runs for
-passive bodies as well as Jet/aperture bodies. Every cut link must have an
-active fluid receiver (FLUID set, SOLID clear), and each `(receiver, direction)`
-population may have only one writer.
-
-Rejected with `ValueError`, before flags, populations or device buffers change:
-
-1. Overlapping or touching passive solids whose cut links write the same
-   population ("Boundary requires unique cut-link writers").
-2. A body whose cut-link receiver is a non-fluid cell, e.g. a channel wall row
-   or the inlet/outlet column ("Cut links must have active fluid receivers").
-
-Both were previously accepted silently for passive bodies; the interpolated
-boundary then had undefined results. The rules apply to the cut links of all
-bodies together, so a passive body overlapping a Jet body is rejected as well.
-The check runs in `Simulation.initialize`, runtime body sync (`sync_bodies`),
-checkpoint save and checkpoint load (`common/checkpoint.py`). Load validates
-before restoring anything, so a checkpoint whose saved geometry violates either
-rule no longer restores; rebuild the geometry with separated bodies.
-
-## 87c3a31: `Simulation.read_surface_exchange` accepts Jet-driven bodies
-
-`read_surface_exchange(id)` previously required `SurfaceActuation` on the body.
-It now also accepts bodies that own Jet aperture links, including Jets with zero
-or negative amplitude (the aperture test is geometric). Bodies with neither
-`SurfaceActuation` nor aperture links still raise
-`ValueError("Body has no surface actuation")`. The value is unchanged: the latest
-step's wall/aperture exchange, not total nozzle force.
@@ -25,7 +25,7 @@ under the alternate compile branch.
 - No LES, no external forcing (`d_params` force fields stay zero).
 - Shifted Jets stay SRT-only: `body/jets.py` keeps its existing guard. This extension does not
  provide shifted MRT Jets.
- `PeriodicBlockStepper` (uniform blocked stepper) remained SRT-only; it was removed in 8e1feff and its single-level capability, still SRT-only, is `FixedPatchStepper(refinements=[])`.
+- `PeriodicBlockStepper` (uniform blocked stepper) remains SRT-only.

 ## Evidence status
 CPU: `tests/unit/test_refinement_mrt.py` (host guards, source contract). GPU:
@@ -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`:

@@ -1,393 +0,0 @@
-# Evidence index (draft, R0)
-
-Active-tree evidence at candidate 0f8fdbc30ea640c764b38ee598d8f4d135c81c85, classified for the release cleanup
-(thread C0C78UFKGRM 1793021833.593279). Draft for review: nothing is removed by this file.
-Recovery of any listed file: `git show 0f8fdbc3:<path>` (blob id given; an immutable tag is requested as anchor).
-
-Classes: K = conclusion kept in the active tree; K-code = tested research code kept; D-snapshot = pre-Gitea
-patch/diff transport (code landed in git from ed1a6ee on; not yet verified hunk by hunk); P-pin = generated hash inventories, git-status dumps and manifests;
-R-raw = run outputs, logs, signals, frames, one-shot run scripts and handoff notes. D, P, R leave the active tree in R1.
-No file under src/ or a test reads any of these paths (git grep at 0f8fdbc3); runners under tests/validation
-that read research/j* are handled in R2.
-
-| Class | Files | Bytes |
-|---|---:|---:|
-| K | 31 | 196,506 |
-| K-code | 3 | 24,324 |
-| D-snapshot | 18 | 338,948 |
-| P-pin | 50 | 979,177 |
-| R-raw | 142 | 3,790,554 |
-
-## (root)
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| BASELINE_JET_AMR.txt | R-raw | 5,244 | 62aa2a66dc05 |
-
-## output
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| round3_compatibility_summary.md | R-raw | 4,366 | f243318f5591 |
-
-## research/fine_surface_20261014
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| baseline.json | P-pin | 54,507 | 71a4543ead37 |
-| cpu_device_guard_cmd.txt | R-raw | 241 | 06e0f35d92b3 |
-| cpu_device_guard_exit.txt | R-raw | 2 | 573541ac9702 |
-| cpu_device_guard_stdout.txt | R-raw | 98 | 424d584a031c |
-| cpu_existing_runs.json | R-raw | 650 | 3179536407b7 |
-| cpu_final_run.json | R-raw | 386 | 523fadb3fec9 |
-| cpu_final_stdout.txt | R-raw | 99 | 9cfe73da3858 |
-| cpu_lifecycle_run.json | R-raw | 387 | 5b403b9e2f30 |
-| cpu_lifecycle_stdout.txt | R-raw | 112 | 3c5c49b285fa |
-| cpu_maps_stdout.txt | R-raw | 95 | 71dd87f9faf9 |
-| cpu_preallocation_run.json | R-raw | 337 | fa6e96d98cdd |
-| cpu_preallocation_stdout.txt | R-raw | 98 | 5d643576f251 |
-| cpu_shared_kernel_stdout.txt | R-raw | 98 | 8a0c046bb9b1 |
-| cpu_surface_command.txt | R-raw | 113 | 2a5ff31e8d06 |
-| cpu_surface_exit.txt | R-raw | 2 | 573541ac9702 |
-| cpu_surface_projection_command.txt | R-raw | 171 | 70b7f5c62c1a |
-| cpu_surface_projection_exit.txt | R-raw | 2 | 573541ac9702 |
-| cpu_surface_projection_stdout.txt | R-raw | 113 | efd37a149cc1 |
-| cpu_surface_stdout.txt | R-raw | 99 | 9cfe73da3858 |
-| gpu_preparation_run1.py | R-raw | 14,043 | ee586d035b7a |
-| gpu_run.json | R-raw | 2,943 | 15b8ba70d528 |
-| gpu_stdout.txt | R-raw | 5,424 | c5216e0267f3 |
-| gpu_test_run1.py | R-raw | 15,479 | f30376abc97f |
-| incremental.diff | D-snapshot | 53,853 | 318d92e7d177 |
-| manifest.json | P-pin | 8,411 | 8281338416af |
-| report.txt | K | 8,373 | 6b9e5123e414 |
-
-## research/fine_surface_joint_20261014
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| baseline_00.json | P-pin | 21,302 | 4ae101ebd02b |
-| baseline_01.json | P-pin | 26,191 | 548cf7b3b494 |
-| baseline_02.json | P-pin | 22,440 | e0421e7a4052 |
-| baseline_03.json | P-pin | 8,584 | da99b45f32a4 |
-| blow_boundary.csv | R-raw | 12,536 | e13363b69457 |
-| blow_collisions.csv | R-raw | 19,145 | 5d5b395486bb |
-| blow_ledger.csv | R-raw | 15,977 | b43bbfd0b8d2 |
-| blow_propagation.csv | R-raw | 9,714 | f06d80d296ca |
-| blow_signals.npz | R-raw | 221,114 | 528adf75baa2 |
-| blow_summary.json | R-raw | 4,113 | 32285ac15be3 |
-| command.txt | R-raw | 232 | 510ecb2925dd |
-| criteria.txt | K | 7,480 | dd36e76a3be1 |
-| frozen.json | R-raw | 11,972 | b5a3324e8686 |
-| gpu_run.json | R-raw | 1,955 | 67ac4785f7e4 |
-| incremental.diff | D-snapshot | 625 | e03c132d22df |
-| integrity.json | P-pin | 826 | a8b6e4be88d2 |
-| manifest.json | P-pin | 4,388 | d2af50260c39 |
-| regions.json | R-raw | 27,525 | 7bba26904221 |
-| report.txt | K | 8,207 | d7571e068ad3 |
-| result.json | R-raw | 11,442 | 9580c2686e70 |
-| review.txt | K | 2,117 | bbe1d8a83d47 |
-| runner.py | R-raw | 5,847 | 812973acc000 |
-| stdout.txt | R-raw | 19,940 | c9218e2e48fc |
-| suction_boundary.csv | R-raw | 12,505 | b870be05e6c0 |
-| suction_collisions.csv | R-raw | 19,173 | 2de48c0a84ab |
-| suction_ledger.csv | R-raw | 16,208 | 92cf1f44911e |
-| suction_propagation.csv | R-raw | 9,720 | f017bcc3ca6f |
-| suction_signals.npz | R-raw | 220,058 | 66d06cf2d909 |
-| suction_summary.json | R-raw | 4,126 | d70a1d371950 |
-| validate.py | R-raw | 19,576 | 37441febd168 |
-| zero_boundary.csv | R-raw | 11,491 | 65c92e48c974 |
-| zero_collisions.csv | R-raw | 18,915 | 027cb8ff6b23 |
-| zero_ledger.csv | R-raw | 16,051 | 34a99bb89dd7 |
-| zero_signals.npz | R-raw | 127,958 | a966f093a9cd |
-| zero_summary.json | R-raw | 1,508 | 6e033f991438 |
-
-## research/fixed_patch_jet_20261013
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| baseline.json | P-pin | 69,721 | 91ad9c4d1e88 |
-| before.json | R-raw | 690 | 06e1b6278a29 |
-| fixed_patch_jet.py | R-raw | 9,646 | 6fbdcd9a076b |
-| incremental.patch | D-snapshot | 9,891 | b43129d82c69 |
-| manifest.json | P-pin | 1,967 | 08daa0248f60 |
-| notes.txt | K | 2,214 | 50070fe54efb |
-| results.json | R-raw | 1,100 | d959a6a1cc2c |
-| stdout.txt | R-raw | 1,272 | eccdc0f6b16a |
-
-## research/fixed_patch_jet_closure_20261013
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| baseline.json | P-pin | 72,692 | 8a157af82ecf |
-| cpu_results.json | R-raw | 628 | 8e4a1c090c93 |
-| cpu_stdout.txt | R-raw | 590 | d800b783fe47 |
-| incremental.patch | D-snapshot | 3,490 | a9a486c68afd |
-| layout_uncropped.png | R-raw | 51,785 | 0cf1cfa5e99d |
-| manifest.json | P-pin | 1,849 | 31cf0c739241 |
-| notes.txt | K | 3,023 | 0f7e7bdfd0e6 |
-
-## research/fixed_patch_jet_records_20261013
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| baseline.json | P-pin | 71,228 | a8e967f76e08 |
-| before.json | R-raw | 690 | ebd6f4251fc2 |
-| fixed_patch_jet.py | R-raw | 10,650 | f6b299885da0 |
-| incremental.patch | D-snapshot | 5,539 | c7f4d0c02ccc |
-| manifest.json | P-pin | 2,057 | 1d616c2541df |
-| notes.txt | K | 2,449 | b58cec14d359 |
-| results.json | R-raw | 1,136 | 788af64a6ebd |
-| stdout.txt | R-raw | 20,750 | a765b06deefa |
-
-## research/j1-2026-10-12
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| REVIEW.md | K | 7,667 | 8f469daef054 |
-| baseline-status.txt | P-pin | 2,601 | 64ca05ab952e |
-| baseline.json | P-pin | 23,052 | ab5852bcb0ef |
-| incremental.diff | D-snapshot | 29,912 | dd9c4e688888 |
-| results.json | R-raw | 68,294 | 56547aa8a678 |
-
-## research/j2-slot-2026-10-12
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| REVIEW.md | K | 12,930 | 69fa4d3bccd3 |
-| baseline-status.txt | P-pin | 2,825 | e711afb0016c |
-| baseline.json | P-pin | 24,660 | 286e023da94f |
-| incremental.diff | D-snapshot | 25,231 | 649f3b5d168d |
-| results.json | R-raw | 477,249 | b4272e25179d |
-
-## research/j3-coverage-2026-10-12
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| REVIEW.md | K | 11,409 | 5887cf73dce2 |
-| baseline-status.txt | P-pin | 3,055 | 78e88356caa3 |
-| baseline.json | P-pin | 30,407 | 095972547a7f |
-| incremental.diff | D-snapshot | 20,114 | f0d502dc5c5b |
-| negative-budget-20744.h5 | R-raw | 88,017 | 693b133be84d |
-| negative-end-20760.h5 | R-raw | 88,174 | 429270d263d4 |
-| restart-21280.h5 | R-raw | 88,062 | 74900affae38 |
-| restart-reference-21296.h5 | R-raw | 88,154 | 7510ee97885b |
-| results.json | R-raw | 296,314 | 7806b10e65cb |
-| verification.json | K | 1,468 | 78a07c47aea4 |
-
-## research/j3-lag-2026-10-12
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| REVIEW.md | K | 11,732 | 34fe5dbb2cae |
-| baseline-status.txt | P-pin | 2,968 | 6ae6094ea9d7 |
-| baseline.json | P-pin | 26,505 | 5c289d14ff30 |
-| end-21280.h5 | R-raw | 92,366 | f30b209179ab |
-| incremental.diff | D-snapshot | 15,790 | 5c6c485e1f75 |
-| results.json | R-raw | 21,718 | 2bf58939129c |
-| start-20760.h5 | R-raw | 92,247 | ae0abd05190c |
-
-## research/j3-offline-2026-10-12
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| REVIEW.md | K | 6,271 | a76e1b486bd2 |
-| lags.csv | R-raw | 1,104 | dd3136dd2dc2 |
-| localization.png | R-raw | 136,013 | 74b56f3e814c |
-| regions.csv | R-raw | 2,126 | 5d361e6872af |
-| results.json | R-raw | 8,852 | bf77b0f534d4 |
-
-## research/j3-reservoir-2026-10-12
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| REVIEW.md | K | 13,563 | a74b67a64e0d |
-| baseline-status.txt | P-pin | 2,896 | a318e077dfae |
-| baseline.json | P-pin | 25,571 | 060502ea7dd8 |
-| incremental.diff | D-snapshot | 22,898 | 8e2c79a86c98 |
-| results.json | R-raw | 182,747 | 7fd5e51a1785 |
-
-## research/refinement_example_20261013
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| baseline.json | P-pin | 8,286 | 591478100da8 |
-| before.json | R-raw | 818 | 7ab0962775b1 |
-| incremental.patch | D-snapshot | 8,682 | 7ad8719d0167 |
-| manifest.json | P-pin | 1,798 | bf1eee8a7cf8 |
-| notes.txt | K | 1,185 | 7ff019ad023d |
-| results.json | R-raw | 1,118 | 94697b0988b9 |
-| stdout.txt | R-raw | 325 | 501446f557f4 |
-
-## research/refinement_followup_20261013
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| README.txt | K | 4,887 | af65e889f20e |
-| baseline.json | P-pin | 5,343 | 7c60ad8ad692 |
-| cleanup.json | R-raw | 1,253 | 15cf342fba2e |
-| cpu_results.json | R-raw | 1,056 | 1166dffd2a09 |
-| cpu_results_attempt1.json | R-raw | 642 | d139d5508105 |
-| cpu_stdout.txt | R-raw | 499 | d1b33ea20563 |
-| cpu_stdout_attempt1.txt | R-raw | 879 | 6a9fe7fce39a |
-| gpu_before.json | R-raw | 589 | 46762a0ab207 |
-| gpu_before_no_launch.json | R-raw | 589 | 074982d1b2d4 |
-| gpu_rectangle_before.json | R-raw | 589 | 831e3793339f |
-| gpu_rectangle_before_no_launch_1791886104981638567.json | R-raw | 589 | c33885d50bfd |
-| gpu_rectangle_results.json | R-raw | 1,003 | 9c6da219ac6c |
-| gpu_rectangle_stdout.txt | R-raw | 332 | 9185bf303954 |
-| gpu_results.json | R-raw | 1,189 | 53e4f1c44de1 |
-| gpu_seed1_before.json | R-raw | 589 | c77ea3485f84 |
-| gpu_seed1_results.json | R-raw | 996 | b718e8af84e4 |
-| gpu_seed1_stdout.txt | R-raw | 306 | 4d7de0897137 |
-| gpu_stdout.txt | R-raw | 68 | b0956fe3cdb0 |
-| incremental.patch | D-snapshot | 16,836 | 9df25d8c177a |
-| manifest.json | P-pin | 4,410 | 177704d6f1ae |
-| run_gpu.py | R-raw | 5,237 | b5af3f0d4f79 |
-
-## research/refinement_prepare_20261013
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| README.txt | K | 8,939 | 8e210c28c7c5 |
-| baseline.json | P-pin | 46,348 | d5f257216b8d |
-| incremental.patch | D-snapshot | 15,751 | 0ddb32550584 |
-| manifest.json | P-pin | 2,113 | 9fd94ccf2c3e |
-| validation.json | R-raw | 3,567 | f057e7cbcd35 |
-| validation.txt | R-raw | 873 | 594daa45c58c |
-
-## research/refinement_slot_20261013
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| baseline.json | P-pin | 67,717 | d498081e7c50 |
-| before.json | R-raw | 690 | 430e76b3aa8a |
-| cpu_results.json | R-raw | 1,421 | 4f6bc4d9428f |
-| incremental.patch | D-snapshot | 18,676 | 67a3e8cc9e68 |
-| manifest.json | P-pin | 2,270 | 6515458290f4 |
-| notes.txt | K | 2,612 | 08a713ba4b37 |
-| results.json | R-raw | 1,160 | 03e683027ba8 |
-| stdout.txt | R-raw | 643 | d57b91769826 |
-
-## research/refinement_slot_followup_20261013
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| baseline.json | P-pin | 68,536 | 89a26ce79438 |
-| before.json | R-raw | 690 | e707df192ff2 |
-| incremental.patch | D-snapshot | 495 | c6f6fa11237d |
-| manifest.json | P-pin | 1,920 | 4840243a33aa |
-| notes.txt | K | 1,549 | 4b77583ca116 |
-| planar_velocity.cuh | R-raw | 1,911 | 87db7466c843 |
-| planar_velocity.sha256 | P-pin | 251 | 6694c4a1c1f0 |
-| results.json | R-raw | 1,050 | 6ef6eda854c6 |
-| stdout.txt | R-raw | 1,160 | 461860351c0c |
-
-## research/refinement_step_20261013
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| README.txt | K | 10,671 | 88d6f24743f5 |
-| baseline.json | P-pin | 40,620 | 20f61559dd38 |
-| cpu_validation.json | R-raw | 1,231 | 7999fd30018c |
-| gpu_failure_validation.json | R-raw | 868 | 5f6db65ee4f9 |
-| gpu_failure_validation.txt | R-raw | 248 | d9a570a1e9e9 |
-| gpu_validation.json | R-raw | 672 | 2028f59e1055 |
-| gpu_validation.txt | R-raw | 632 | 9699918ee127 |
-| incremental.patch | D-snapshot | 26,516 | d95f9347633d |
-| manifest.json | P-pin | 2,075 | 32a7f1a7309e |
-
-## research/repair-2026-10-10
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| TRON_HANDOFF.md | R-raw | 25,208 | a339786c7944 |
-| baseline-hashes.json | P-pin | 16,020 | 9b4e24cb1d10 |
-| baseline-status.txt | P-pin | 429 | 515be249b638 |
-| checkpoint-domain-2026-10-12.diff | D-snapshot | 14,443 | 035ed630dda1 |
-| classic-results.json | R-raw | 244,729 | 7297aa0d5bca |
-| classic-signals.npz | R-raw | 630,332 | 8cf6d1218aa0 |
-| final-gpu.log | R-raw | 191 | a0eec1a8ea31 |
-| final-unit.log | R-raw | 188 | 94efba2f1d42 |
-| provenance.json | P-pin | 1,020 | 25e22b4f0696 |
-| repair-architecture.md | K | 9,498 | 12051c3e8571 |
-| repair-numerical.md | K | 10,769 | 0c5757fe5f36 |
-| repair-state.md | K | 8,481 | 3c7f2d5b687a |
-| simplification-checks.log | R-raw | 1,045 | fa9d464be740 |
-
-## research/shear_refinement
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| README.md | K-code | 4,142 | 67bdd8ed622b |
-| boundary_shear_tagging.py | K-code | 13,859 | b5415a1c4ea1 |
-| example.py | K-code | 6,323 | 66295d3f0273 |
-
-## research/surface_actuation_20261014
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| baseline.json | P-pin | 54,139 | 0ad06888dbeb |
-| cpu_checkpoint_run.json | R-raw | 400 | 39681b60ff15 |
-| cpu_checkpoint_stdout.txt | R-raw | 114 | 929e4b8d4f46 |
-| cpu_initial.txt | R-raw | 620 | 29213c58a679 |
-| cpu_surface_command.txt | R-raw | 118 | 6d8c615a6e03 |
-| cpu_surface_exit.txt | R-raw | 2 | 573541ac9702 |
-| cpu_surface_stdout.txt | R-raw | 99 | ee9237fc26e5 |
-| gpu_run.json | R-raw | 1,698 | dc8f87eafaa9 |
-| gpu_stdout.txt | R-raw | 159 | b262891e52c3 |
-| incremental.diff | D-snapshot | 50,206 | 43090a1a8b11 |
-| manifest.json | P-pin | 7,527 | 35daa01271cb |
-| report.txt | K | 5,078 | 1162a6479f9f |
-
-## research/wall_seam_pulse_20261014
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| analyze.py | R-raw | 10,343 | ed7cf6999a49 |
-| interpretation.txt | K | 3,514 | 90935db2aa99 |
-| results.json | R-raw | 15,137 | 678a0759871a |
-| run.json | R-raw | 1,170 | 53e303fd0d5d |
-| sources.csv | R-raw | 2,313 | 40d3736b8ef1 |
-| stdout.txt | R-raw | 1,179 | 756d8c38e213 |
-
-## tests/validation/multigrid/cpuref_0_3_evidence
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| README.txt | K | 4,133 | 62897bfd9812 |
-| README_grok.md | K | 1,751 | 2d36e05661a8 |
-| baseline.json | P-pin | 39,291 | 188491096547 |
-| manifest.json | P-pin | 3,495 | 10c19f5fe5ca |
-| results_horsea.json | R-raw | 2,281 | 3b163384e376 |
-| stdout_grok.txt | R-raw | 7,143 | 5a0c270ea4ae |
-| stdout_horsea.txt | R-raw | 9,013 | adff8bb8d295 |
-
-## tests/validation/multigrid/local_stress_v1_evidence
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| README.txt | K | 8,239 | 3513fd294223 |
-| TABLE_local_stress_observable_v1.md | K | 2,967 | 6115dcde0f46 |
-| baseline.json | P-pin | 43,991 | ab631ea4f2ad |
-| comparison.json | R-raw | 13,248 | d7d1b36eb247 |
-| manifest.json | P-pin | 4,132 | c6c44d8125cd |
-| results_horsea.json | R-raw | 2,671 | 79bdf001f948 |
-| run_once.py | R-raw | 4,313 | fa9c5239e993 |
-| source_manifest.json | P-pin | 622 | 0516f1860407 |
-| stdout_horsea.txt | R-raw | 17,091 | a20c554693df |
-| stdout_local_stress_observable_v1.txt | R-raw | 12,238 | 692ffe1a05da |
-
-## tests/validation/multigrid/shear_v0_2_evidence
-
-| File | Class | Bytes | Blob |
-|---|---|---:|---|
-| README.txt | K | 7,220 | 772f74ad40ff |
-| baseline.json | P-pin | 41,751 | 70d9c9fa71c0 |
-| comparison.json | R-raw | 7,679 | 0af8736f9a01 |
-| joint_report.md | K | 6,110 | eed871221298 |
-| manifest.json | P-pin | 3,796 | b22d03a1ba9e |
-| results_horsea.json | R-raw | 1,957 | b2cd48a07a08 |
-| run_once.py | R-raw | 3,245 | 0b8d5e21f326 |
-| source_manifest.json | P-pin | 574 | 4d1c742690c7 |
-| stdout_grok.txt | R-raw | 7,950 | 0e80b1aba7f6 |
-| stdout_horsea.txt | R-raw | 11,421 | 3c867cdac197 |
@@ -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
@@ -1,25 +0,0 @@
-# Device state lifecycle (uniform Simulation, FixedPatchStepper)
-
-State is grouped by what a change invalidates. This file describes the code as
-it is; it adds no framework. Line references are to candidate 0f8fdbc3.
-
-| Class | Contents | How it changes | Owner rule |
-|---|---|---|---|
-| 1. Module and its globals | Compile-time (visible to the compiler, fixed per module): `config.h` macros incl. `NX`/`NY`, `COLLISION_MODEL`, `BLOCK_ROOT_BC`, `WALL_*`. Runtime per-module globals (not visible to the compiler; written by host code): `__constant__` `d_params`, `d_w`, `d_cx`, `d_cy`, `d_block_channel`, `d_block_wall`; plus bound kernel handles | Globals are written once by the owner right after `load_module`. Uniform grid: `Simulation._recompile` (construction, body-topology sync) loads a new module and re-uploads; `update_runtime_params` rewrites `d_params` (omega, force, n_objects) between runs. Steppers: never rewritten after construction, so they are immutable for the instance's lifetime although they are runtime values. The same quantity can be a macro in one route and a global in another (dense slot root: `WALL_SLOT_WIDTH`/`WALL_NORMAL_VELOCITY` macros; blocked slot root: `d_block_wall`), which can change generated arithmetic. | Every owner loads its own module (`compiler.load_module` = `module_from_file`, no cache). A loaded module is never shared between live owners: globals are per module, so sharing would share mutable `d_params`. |
-| 2. Geometry, layout, tables | flags, curved-link tables, block layouts and halo pairs, transfer (explode/coalesce) tables, block kinds | Immutable for the life of an instance. Uniform grid: rebuilt by body sync. `FixedPatchStepper`: a geometry change is a new instance (`remap_child`), committed only after a successful transfer. | No in-place table edits. |
-| 3. Controls and dependent boundary columns | Jet amplitude -> per-link `surface_velocity`; body actions (uniform grid) | Between steps, without a table or module rebuild (`set_jet_amplitude`). | Host copy commits only after the device upload succeeded; a device error fails the instance. |
-| 4. Per-step state | population double buffers and their parity, raw-exchange ledgers, observations | Device-only during `step(n)` / `run(n)`; buffer swaps are host-handle swaps. | Valid on the host only after the single wait at the end of the call. |
-
-Storage routes are separate concerns:
-
- Original uniform grid (`uniform.cu`, `Simulation`): whole-domain `NX`/`NY`.
- Blocked levels (`blocked.cu`; every `FixedPatchStepper` level, including the
-  single level of `refinements=[]`): `NX`/`NY` are one block window including halo.
- Dense refinement levels (`refinement.cu`, `level_blocks[l] is None`).
-
-A single-rectangle refinement (`FixedPatch2D`) is stored in its own fine
-window frame in both dense and blocked form (`refinement_stepper.py:222-224`,
-`BlockLayout2D.build(*pair.fine_shape, ...)`). Only a rectangle set
-(`FixedPatchSet2D`) uses the level-wide frame `(2*ny, 2*nx)`, whose
-`fine_layout` requires that full grid to be divisible by the tile
-(`refinement.py:240-252`).
@@ -1,88 +0,0 @@
-# Supported settings: 2D Jet + fixed multilevel refinement (candidate 888c8038)
-
-Every entry names the guard that enforces it (file and function or kernel guard,
-at source revision 888c80381c006e976be2af8a452288729fc17c1b) 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` `FixedPatch2D.from_config`; `#error` guards in `lbm/kernels/blocks.cu` and `lbm/kernels/refinement.cu` |
-| Precision / streaming | FP32 storage, double buffer | same guards |
-| Collision on refinement levels | SRT or MRT; TRT and LES rejected | `lbm/refinement.py` `FixedPatch2D.from_config` (re-checked for fine boundaries in `prepare_fine_boundary`) |
-| Shifted (ddf_shifting) storage | only when every level is blocked; dense or mixed rejected | `lbm/refinement_stepper.py` `FixedPatchStepper.__init__`, `FixedPatchStepper._check_storage`; `#error` guard in `lbm/kernels/refinement.cu` (dense patch kernel unshifted only) |
-| Fine relaxation | 1/tau_fine must lie inside the configured omega guards | `lbm/refinement.py` `FixedPatch2D.from_config` |
-| Single blocked level `FixedPatchStepper(refinements=[], level_blocks=[(by, bx)], level_objects=[circles])` (replaces `PeriodicBlockStepper`, removed in 8e1feff) | doubly periodic, SRT only, no LES/Jets/projection/exchange observation, stationary passive circles; `download()` returns a 1-tuple | `lbm/refinement_stepper.py` `_check_levels`, `FixedPatchStepper.__init__`; `lbm/blocks.py` `static_circle_tables` |
-
-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` `_check_levels` |
-| Single L1 rectangle | two-coarse-cell margin to the domain edge | `lbm/refinement.py` `FixedPatch2D.from_config` |
-| 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` `_check_levels`; `lbm/refinement.py` `_check_parent_pull_closure` |
-| 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` `_check_levels`; `lbm/hierarchy.py` `build_hierarchy` |
-| Nested transfer support | child only over inherited ACTIVE cells, donors/receivers uncovered ACTIVE, no child over the parent restriction footprint | `lbm/refinement.py` `_nested_kind` |
-| Tile shape | positive `(by, bx)`; the level allocation must be divisible by the tile (no partial tiles yet) | `lbm/refinement_stepper.py` `_check_levels`, `lbm/refinement.py` `FixedPatchSet2D.fine_layout` (shape); `lbm/blocks.py` `BlockLayout2D.build` (divisibility) |
-| Coarse boundary | `periodic`, `slot_reservoir` or `channel` | `lbm/refinement_stepper.py` `FixedPatchStepper.__init__` |
-| `slot_reservoir` | on-site velocity bottom slot, reservoir top, velocity 0, 2 <= slot width < nx, patch rows 4..ny-4 | `lbm/refinement_stepper.py` `FixedPatchStepper.__init__`; `lbm/refinement.py` `prepare_fine_boundary` |
-| `channel` | all levels blocked; Zou-He inlet, pressure-NEQ outlet, stationary bounce-back walls; transfers away from the closure | `lbm/channel.py` `validate_channel_config`, `validate_channel_transfers` |
-| Explosion | `constant` (default); `projected_linear` only periodic, all-blocked SRT, no bodies/Jets, no LES (experimental) | `lbm/refinement_stepper.py` `FixedPatchStepper.__init__` |
-| L2 runtime remap (`remap_child`) | periodic three-level L2 sets only, no L0/L1 bodies, identical pinned boundary | `lbm/refinement_stepper.py` `FixedPatchStepper.remap_child` |
-
-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` `prepare_fine_boundary` |
-| Level | not on L0; only on the finest level of a nested hierarchy | `lbm/refinement_stepper.py` `_check_levels` |
-| Jet condition | velocity only; `pressure` is reserved and raises NotImplementedError | `body/jets.py` `Jet.__post_init__` |
-| 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` `Jet.__post_init__`, `jet_link_shapes`, `_surface_links` |
-| Jets with shifted storage | only in the all-blocked stepper with SRT and no LES | `body/jets.py` `_surface_links` |
-| SurfaceActuation | unshifted storage only | `body/objects.py` `SimObject.validate_surface_actuation` |
-| Raw boundary exchange (force) | blocked body levels only; the window ledger requires `observe_raw_exchange` | `lbm/refinement_stepper.py` `FixedPatchStepper.__init__` |
-| Checkpoint with Jets | refused | `simulation.py` `Simulation.save_checkpoint` |
-
-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.
@@ -1,49 +0,0 @@
-# DFG 2D-1 (Re 20) against the official reference intervals
-
-`tests/validation/run_dfg_re20.py` runs the steady DFG 2D-1 case on the refined
-channel root (D40 root, D80 wide fine patch) and on the uniform D80 grid. Geometry,
-inflow, initial state, layout and observation are those of the pinned Re100 runner
-(`run_refined_dfg.py`, `re100_helpers.py`, both unchanged); only the lattice
-viscosity is set for Re 20 (root tau 0.56, fine 0.62, uniform 0.62, lattice speed 0.01).
-
-Label: "compared against the official reference bands", not a full benchmark
-certification: the outlet is pressure-NEQ (`neq_extrap`), not do-nothing, and the
-inlet is local Zou-He.
-
-## Quantities
-
- Cd = 2 Fx / (rho U^2 D), Cl = 2 Fy / (rho U^2 D), interval means over each sample.
- p_diff = p(0.15, 0.2) - p(0.25, 0.2), linear extrapolation to the exact surface
-  points (`re100_helpers.pressure_probes`). The helper returns dp / (rho U^2) in
-  scaled units; p_diff = dp * 0.04 for U = 0.2 m/s, rho = 1. Both are reported.
- Official intervals (Schaefer & Turek 1996): Cd [5.57, 5.59], Cl [0.0104, 0.0110],
-  p_diff [0.1172, 0.1176].
-
-## Bounds and steady rule (frozen before any run)
-
- End time t* = 60 (30 s physical): 240,000 refined root steps, 480,000 uniform steps.
- One sample every t* = 0.5 (0.25 s) at the end of a synchronized root step; Cd and
-  Cl are interval means. Trailing window t* 50..60 inclusive (21 samples).
- Steady rule (our engineering choice, not official): in the window, for each of Cd,
-  Cl, p_diff, max - min <= 10 % and |least-squares slope x window| <= 2 % of its
-  official interval width (range 2e-3 / 6e-5 / 4e-5; slope 4e-4 / 1.2e-5 / 8e-6).
-  Absolute limits, so the small Cl is never a divisor. Never relaxed after a run.
- The verdict uses the window mean; the distance to the nearest interval edge is
-  reported for each quantity (negative outside).
- Force sign: fluid on cylinder, x along the inflow, y up from the bottom wall; Cd > 0
-  and the official Cl > 0 (`cd_positive` is reported).
- Not steady at t* = 60: status `NOT_STEADY`, no interval verdict. Health limits
-  (Mach <= 0.2, rho in [0.5, 1.5]) stop the run with `UNHEALTHY`.
- Steady: `WITHIN_INTERVALS` or `OUTSIDE_INTERVALS`, with the per-quantity verdict.
-
-## Run
-
-```
-python tests/validation/run_dfg_re20.py --output <new-dir> --plan
-CUDA_VISIBLE_DEVICES=<n> python tests/validation/run_dfg_re20.py --case both \
-    --collision SRT --output <new-dir> --max-wall-seconds <cap>
-```
-
-The uniform D80 control separates method error from refinement error. `--plan` writes `plan.json` only. A GPU run writes `plan.json` and `result.json`
-(per case: lattice parameters, every sample, window ranges, status, verdict).
-Host contract tests: `tests/unit/test_dfg_re20.py`.
@@ -56,62 +56,3 @@ Root must independently review and admit any execution. An admitted paired pilot
 the existing watchdog, device selection, `--gpu-gates-approved`, positive
 `--max-wall-seconds` and a new output directory, adding only `--exchange-window` to the
 selected collision's pilot command. No GPU or remote action was performed for this patch.
-
-## Public Jet diagnostic option
-
-`--collision MRT --exchange-window --jet-scenario zero|fixed|reverse` selects
-unshifted FP32, no LES, constant transfer on both existing public backends. Default
-`none` and the historical manifests remain unchanged. `zero` registers both Jets at
-zero amplitude and retains every existing DFG verdict, including pressure. `fixed`
-uses outward radial parabolic sectors at pi/2 and 3pi/2, half-width pi/12, peaks
-(+.001,-.001). Both use the existing D40/D80 geometry and U=.01. Sector origins are
-(80.5,81) in root edge coordinates and (160,160.5) in uniform node coordinates;
-radial extent is [0,1.005R]. `reverse` keeps those peaks through t*=300, updates both
-public setters at that completed boundary, and continues to 305 with opposite signs.
-
-Fixed diagnostic windows are 250–260, 260–270, 270–280, 280–290 and 290–300; reversal
-adds 300–305. Histories retain exact interval endpoints and root/uniform lattice
-impulses. The refined window uses total exchange; uniform uses public `read_force`
-batch averages. Driven windows report mean/min/max/RMS Cd/Cl without applying DFG
-reference or periodicity gates. Exit zero means healthy execution, not qualification;
-`matched_case_pass` remains false. No independent CV or stress-load claim is made.
-
-This opt-in records current source/helper hashes with the existing manifest format,
-checkout revision/dirty state and runner hash. Pilot/full must match that snapshot
-and the exact scenario. It does not relabel current source as historical evidence.
-Use the existing bounded plan/pilot/full commands with the three option flags above;
-full requires the matching completed t*=5 paired pilot. `step_seconds` includes force
-readback; observation/overhead and total wall time are separate, not kernel throughput.
-
-Add `--observe-cv` to record independent scalar control-volume samples from the
-already downloaded public macros. The pilot exercises this path at t*=.02..5;
-full records 501 endpoints at 290..300. Each `cv_history.jsonl` row contains actual
-root time, preceding interval start/duration/impulse, and two inventories/outward
-fluxes ordered [mass,Px,Py]. Exclude the first row's preceding impulse: that row
-supplies the initial inventory. Uniform native impulse converts by .5² to root
-units; refined ledger impulse is already in root units. Explicit native-aligned
-contours differ by .25 root cells in x and are recorded in the plan. Cropping
-retains the two-cell face-gradient stencils. No fields or per-link arrays are saved.
-`cv_observation_seconds` is the CV portion of observation/overhead time. Helper hash
-and the observation flag must match pilot/full. Time integration, temporal
-coarsening and any physical assessment remain separate offline work.
-
-## Bounded resolution and placement controls
-
-Defaults remain `--case both --uniform-diameter 80 --placement wide`. Single-case
-runs use `--case uniform` or `--case refined` and never report a matched-case pass.
-Their own reference/periodicity or driven-diagnostic results remain available.
-A single zero-Jet full run exits successfully only when its periodicity and the
-unchanged complete DFG reference verdict pass; driven completion is not qualification.
-
-The D160 option requires `--case uniform --uniform-diameter 160` and an explicit
-public Jet scenario. U and Jet speeds stay .01 and ±.001; viscosity is .016,
-grid 3521×658, center (320,320.5), radius80. CV uses root spacing/time factor .25,
-origin (.375,.75), impulse factor .0625, root viscosity .004, and x-face shift .125.
-
-`--case refined --placement compact` selects root bounds (48,48,128,128), fine
-168×168 and origin (46,46), with the same D40/fineD80 body/Jet resolution. Its CV
-contours are (52,52,112,112) and (50,50,120,120); complete face-gradient stencils
-are clear of both solids and the transfer footprint. Compact is refined-only.
-CV metadata gives each grid's spacing/origin/contours explicitly. Case, uniform
-diameter and placement must match the newly completed pilot in every receipt.
@@ -1,9 +1,9 @@
 """Public API demo: fixed 2:1 patch with a stationary, optionally actuated circle.

 From this checkout, after checking the selected physical GPU is idle:
-    PYTHONPATH="$PWD/src" CUDA_VISIBLE_DEVICES=0 python examples/fixed_patch_circle.py
-    ... --speed -0.002 --mode slot_reservoir
-Both levels use blocked storage (--base-block, --fine-block tiles).
+    PYTHONPATH="$PWD/src" CUDA_VISIBLE_DEVICES=0 python examples/fixed_patch_circle.py --fine-block 16 20
+    ... --speed -0.002 --fine-block 16 20 --mode slot_reservoir
+Omit --fine-block for the (equivalent) dense fine storage.

 A short smoke run (default 128 coarse steps): it shows setup, stepping and
 fluid-only diagnostics, not a developed flow, accuracy or long-time stability.
@@ -71,10 +71,8 @@ def main():
    parser.add_argument("--mode", choices=("periodic", "slot_reservoir"), default="periodic")
    parser.add_argument("--speed", type=float, default=.002,
                        help="normal surface velocity, coarse lattice units (+ blows, - sucks, 0 passive)")
-    parser.add_argument("--base-block", type=int, nargs=2, metavar=("BY", "BX"), default=(12, 8),
-                        help="root tile; must divide the 24 x 32 root")
-    parser.add_argument("--fine-block", type=int, nargs=2, metavar=("BY", "BX"), default=(16, 20),
-                        help="fine tile; must divide the whole fine allocation (32 x 40 here)")
+    parser.add_argument("--fine-block", type=int, nargs=2, metavar=("BY", "BX"),
+                        help="blocked fine storage; must divide the whole fine allocation (32 x 40 here)")
    parser.add_argument("--steps", type=int, default=128)
    args = parser.parse_args()
    if args.steps < 0:
@@ -88,20 +86,20 @@ def main():
    body = SimObject(0, geometry=CircleGeometry(*CENTER, RADIUS), center=CENTER, radius=RADIUS,
                     surface_actuation=spec)
    cfg = config(args.mode)
+    fine_block = tuple(args.fine_block) if args.fine_block else None
    # 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=[tuple(args.base_block), tuple(args.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.
        rest = np.asarray(compute_feq_d2q9(1.0, 0.0, 0.0), np.float32)[:, None, None]
        run.initialize(np.broadcast_to(rest, (9, *p.coarse_shape)),
                       np.broadcast_to(rest, (9, *p.fine_shape)))
-        storage = f"blocked root {tuple(args.base_block)} fine {tuple(args.fine_block)}"
-        print(f"mode={args.mode} storage={storage} speed={args.speed:+g} "
+        storage = f"blocked {fine_block}" if fine_block else "dense"
+        print(f"mode={args.mode} fine storage={storage} speed={args.speed:+g} "
              f"(fine allocation {p.fine_shape[0]}x{p.fine_shape[1]}, fine origin {p.fine_origin})")
        masks = leaf_masks(run, args.mode)
        start = leaf_diagnostics(*run.download(), masks)
@@ -31,7 +31,6 @@ from CelerisLab.lbm.refinement import ACTIVE
 from CelerisLab.lbm.refinement_stepper import FixedPatchStepper

 BOUNDS, AMPLITUDE, WIDTH = (16, 4, 32, 28), .02, 12
-LEVEL_BLOCKS = [(12, 8), (8, 8)]  # blocked storage: 48x48 root, 56x40 fine window
 TIMES, MAX_MACH, MAX_SECONDS = (0, 300, 1200), .1, 120


@@ -133,8 +132,7 @@ def main():
                  lattice_model='D2Q9', collision='SRT', streaming='double_buffer',
                  store_precision='FP32', ddf_shifting=False, les_enabled=False)
    report = dict(config=dict(nx=48, ny=48, bounds=BOUNDS, W=WIDTH, A=AMPLITUDE, nu=.1,
-                              rho=1, tau_coarse=.8, tau_fine=1.1, coarse_boundary='slot_reservoir',
-                              level_blocks=LEVEL_BLOCKS),
+                              rho=1, tau_coarse=.8, tau_fine=1.1, coarse_boundary='slot_reservoir'),
                  guards=dict(check_every=50, positive_density=True, finite=True,
                              max_Mach=MAX_MACH, max_seconds=MAX_SECONDS,
                              timing='cooperative checks, not an exact interruption deadline'),
@@ -150,9 +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],
-                level_blocks=LEVEL_BLOCKS) 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 +207,22 @@ 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
-    from .preprocess.flag_overlay import validate_cut_link_ownership
-    validate_cut_link_ownership(flags, fluid_idx, dir, cfg.nq)
+        return None, None
+    from ..lbm.descriptors import FLUID, SOLID
+    if np.any((flags[fluid_idx] & FLUID) == 0) or np.any(flags[fluid_idx] & SOLID):
+        raise ValueError("Surface cut links must have active fluid receivers")
+    if len(np.unique(fluid_idx.astype(np.uint64)*cfg.nq+dir)) != len(dir):
+        raise ValueError("Surface boundary requires unique cut-link writers")
    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 +255,4 @@ 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
@@ -11,7 +11,7 @@ Responsibilities:

 Design::
  Packed ``obs`` layout matches ``generate_config(..., n_objects=count)`` and
-  ``config_obs.h`` macros. Host sizing uses :func:`~CelerisLab.cuda.compiler.obs_layout`.
+  ``config_obs.h`` macros. Host sizing uses :func:`~CelerisLab.cuda.compiler_v2.obs_layout`.

  Pending edits are lightweight: only the "intent" (add / remove) is stored.
  All derived quantities (flags, compact lists, GPU buffers) are built at
@@ -27,8 +27,8 @@ import pycuda.driver as cuda

 from .objects import SimObject
 from .registry import BodyRegistry
-from .preprocess.flag_overlay import merge_flag_masks, validate_cut_link_ownership
-from ..cuda.compiler import obs_layout
+from .preprocess.flag_overlay import merge_flag_masks
+from ..cuda.compiler_v2 import obs_layout
 from ..cuda.obs_layout import ObsLayout
 from ..lbm.descriptors import (
    FLUID, SOLID,
@@ -369,9 +369,9 @@ class ObjectManager:

        Args:
            objects: List of SimObject instances to process.
-            domain_flags: Optional uint16 flags for receiver/donor classification.
+            domain_flags: Optional uint16 flags for donor-cell classification.
            sensor_cell_counts_out: Int array to fill with per-object sensor
-                cell counts after the full geometry has passed validation.
+                cell counts.  If provided, ``fill(0)`` is called first.
            hits_out: List that receives one FP64 (n, 2) array of true hit
                points row-aligned with the cut-link columns (for Jets).

@@ -394,8 +394,8 @@ class ObjectManager:
        active_fluid = ((domain_flags & FLUID) != 0) & ((domain_flags & SOLID) == 0)
        force_owners: set[int] = set()

-        sensor_counts = (np.zeros_like(sensor_cell_counts_out)
-                         if sensor_cell_counts_out is not None else None)
+        if sensor_cell_counts_out is not None:
+            sensor_cell_counts_out.fill(0)

        ez = None
        if self.cfg and self.cfg.is_d3q19:
@@ -430,9 +430,9 @@ class ObjectManager:
                if len(cells) > 0:
                    s_cells.append(cells)
                    s_ids.append(ids)
-                    if (sensor_counts is not None
-                            and 0 <= obj.obj_id < sensor_counts.size):
-                        sensor_counts[obj.obj_id] = int(len(cells))
+                    if (sensor_cell_counts_out is not None
+                            and 0 <= obj.obj_id < sensor_cell_counts_out.size):
+                        sensor_cell_counts_out[obj.obj_id] = int(len(cells))
            if obj.is_force_region and hasattr(obj, 'get_sensor_list'):
                cells, ids = obj.get_sensor_list(self.nx, self.ny, self.nz)
                keep = active_fluid[cells]
@@ -461,9 +461,8 @@ class ObjectManager:
        r_fr_ids = np.concatenate(fr_ids) if fr_ids else np.zeros(0, dtype=np.int32)

        r_hit = np.concatenate(cl_hit) if cl_hit else np.zeros((0, 2))
-        # Passive walls need the same ownership guarantees as driven walls.
-        # Overlapping solids are not a supported union-boundary operation.
-        validate_cut_link_ownership(domain_flags, r_idx, r_dir, self.nq)
+        if hits_out is not None:
+            hits_out.append(r_hit)
        if self.jets or any(obj.surface_actuation is not None for obj in objects):
            # Reject unresolved apertures/ownership before sync or restart mutates state.
            from ..lbm.curved_links import CurvedLinkSoA
@@ -471,11 +470,6 @@ class ObjectManager:
            links.assign_host(r_idx, r_dir, r_q, r_bid, r_rx, r_ry, r_rz, r_fallback)
            links.assign_surface(objects, self.cfg, domain_flags, jets=self.jets, hits=r_hit)

-        if sensor_cell_counts_out is not None:
-            sensor_cell_counts_out[:] = sensor_counts
-        if hits_out is not None:
-            hits_out.append(r_hit)
-
        return (
            r_idx, r_dir, r_q, r_bid,
            r_rx, r_ry, r_rz, r_fallback,
@@ -493,6 +487,8 @@ class ObjectManager:
                the caller has already prepared and uploaded the final flag field
                for this geometry, such as during initialization.
        """
+        self._telemetry_field = field
+
        next_flags = self.build_flags(field.build_channel_flags()) if rebuild_flags else field.flag
        hits = []

@@ -503,7 +499,6 @@ class ObjectManager:
            fr_cells, fr_obj_id,
        ) = self.build_compact_lists(domain_flags=next_flags, hits_out=hits)

-        self._telemetry_field = field
        if rebuild_flags:
            field.flag = next_flags
            field.upload_flags()
@@ -1,6 +1,6 @@
 # CelerisLab/body/preprocess/flag_overlay.py
 """
-Flag overlay and cut-link ownership checks against the merged domain.
+Flag overlay: merge per-object flag masks onto a clean domain base.
 """

 from __future__ import annotations
@@ -12,15 +12,6 @@ import numpy as np
 from ...lbm.descriptors import FLUID, SOLID, SENSOR_FLAG, FRC_REGION


-def validate_cut_link_ownership(flags, fluid_idx, directions, nq):
-    """Reject solid receivers and multiple writers to one population."""
-    if np.any((flags[fluid_idx] & FLUID) == 0) or np.any(flags[fluid_idx] & SOLID):
-        raise ValueError("Cut links must have active fluid receivers")
-    writers = fluid_idx.astype(np.uint64) * nq + directions
-    if len(np.unique(writers)) != len(directions):
-        raise ValueError("Boundary requires unique cut-link writers")
-
-
 def merge_flag_masks(
    base: np.ndarray,
    masks: List[np.ndarray],
@@ -7,7 +7,7 @@ Two JSON files:
  config_body.json – object list

 LBMConfig / BodyConfig are plain dataclasses; they translate to
-macro dicts consumed by `cuda/compiler.py` for header generation.
+macro dicts consumed by `cuda/compiler_v2.py` for header generation.
 """

 import json
@@ -60,14 +60,14 @@ Python `config.py` 只负责读取和校验，不是配置位置。显式配置

 **`lbm/kernels/config/*.h` 由编译器根据 `LBMConfig` 自动生成，请勿手改。**

-仓库中检入的 `config/*.h` 可能是历史版本。`compiler.generate_config` 会复制 kernel 源码到独立临时构建目录，并在副本中生成配置；不会改写包内头文件或 PTX。返回目录须显式传给 `compile_kernel(build_dir=...)`，编译结果与配置摘要均保存在该目录。`Simulation` 负责目录清理；直接使用编译器的调用者须调用 `cleanup_build_dir()`。跳过生成配置直接编译仓库中的 `uniform.cu` 属不受支持用法。
+仓库中检入的 `config/*.h` 可能是历史版本。`compiler_v2.generate_config` 会复制 kernel 源码到独立临时构建目录，并在副本中生成配置；不会改写包内头文件或 PTX。返回目录须显式传给 `compile_kernel(build_dir=...)`，编译结果与配置摘要均保存在该目录。`Simulation` 负责目录清理；直接使用编译器的调用者须调用 `cleanup_build_dir()`。跳过生成配置直接编译仓库中的 `kernel_v2.cu` 属不受支持用法。

 ```
 config_lbm.json
  ↓  load_lbm_config()
 config.py:LBMConfig       (读取 + 校验)
  ↓  to_macros()
-cuda/compiler.py          (独立构建目录中生成 config/*.h)
+cuda/compiler_v2.py       (独立构建目录中生成 config/*.h)
  ↓
 config_grid.h             → NX, NY, NZ, NT, LATTICE_MODEL；
                            DIM / NQ 由 LATTICE_MODEL 推导写入（与 grid.lattice_model 一致，非 JSON 顶层字段）
@@ -1,4 +1,4 @@
 """CUDA build helpers (compilation itself does not need a live context)."""
-from . import compiler
+from . import compiler_v2 as compiler

 __all__ = ["compiler"]
@@ -1,14 +1,11 @@
-# CelerisLab/cuda/compiler.py
+# CelerisLab/cuda/compiler_v2.py
 """
 Kernel configuration, compilation, and module loading.

-Owners call build_module(cfg, entry, arch=...), then set_params(module, omega, ...).
-build_module runs, in a private directory it removes afterwards:
+Workflow:
  1. build_dir = generate_config(lbm_cfg, n_objects) — isolated source snapshot
-  2. compile_kernel(arch, source=entry, build_dir=build_dir) — nvcc -ptx
+  2. compile_kernel(arch, build_dir=build_dir)       — nvcc -ptx kernel_v2.cu
  3. load_module(ptx_path)              — PyCUDA module from PTX
-Entries: uniform.cu (uniform grid), blocked.cu (blocked level), refinement.cu
-(dense refinement level).
 """

 from __future__ import annotations
@@ -19,6 +16,7 @@ import shutil
 import tempfile
 import hashlib
 import json
+from contextvars import ContextVar
 from dataclasses import asdict
 from pathlib import Path
 from typing import Optional
@@ -35,6 +33,9 @@ _KERNEL_DIR = os.path.join(
 )


+_last_build_dir = ContextVar("celeris_last_build_dir", default=None)
+_last_ptx_path = ContextVar("celeris_last_ptx_path", default=None)
+

 def kernel_path(filename: str) -> str:
    return os.path.join(_KERNEL_DIR, filename)
@@ -53,16 +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 to compile_kernel(build_dir=...). The caller owns cleanup_build_dir() once the loaded module is no longer
+    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")
@@ -72,19 +71,20 @@ 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)
        raise
+    _last_build_dir.set(build_dir)
+    _last_ptx_path.set(None)
    return build_dir


@@ -96,9 +96,12 @@ def cleanup_build_dir(build_dir: Optional[str]) -> None:
    if path == Path(_KERNEL_DIR).resolve() or not (path / ".celeris-build").is_file():
        raise ValueError("Refusing to remove a directory not owned by the compiler")
    shutil.rmtree(path)
+    if _last_build_dir.get() == str(build_dir):
+        _last_build_dir.set(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
@@ -162,9 +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']}
@@ -241,9 +241,13 @@ def _render_config(m: dict, n_objects: int, cdir: str, *, block_root_bc: int = 0
 # ---------------------------------------------------------------------------
 # Compilation
 # ---------------------------------------------------------------------------
-def compile_kernel(arch: str = "sm_70", source: str = "uniform.cu",
-                   output: Optional[str] = None, *, build_dir: str) -> str:
-    """Compile the snapshot in build_dir (from generate_config); never package headers."""
+def compile_kernel(arch: str = "sm_70", source: str = "kernel_v2.cu",
+                   output: Optional[str] = None, *,
+                   build_dir: Optional[str] = None) -> str:
+    """Compile a generated private source snapshot; never use package headers."""
+    # A failed attempt must not make implicit load_module() reuse older code.
+    _last_ptx_path.set(None)
+    build_dir = build_dir or _last_build_dir.get()
    if not build_dir or not (Path(build_dir) / ".celeris-build").is_file():
        raise RuntimeError("Call generate_config() and pass its build_dir before compiling")
    root = Path(build_dir).resolve()
@@ -268,36 +272,23 @@ def compile_kernel(arch: str = "sm_70", source: str = "uniform.cu",
    finally:
        if os.path.exists(tmp):
            os.unlink(tmp)
+    _last_ptx_path.set(str(dst))
    return str(dst)


-def load_module(ptx_path: str):
-    """Load one compiled PTX file as a new PyCUDA module."""
+def load_module(ptx_path: Optional[str] = None):
+    """Load explicit PTX or the last PTX compiled in this Python context."""
+    ptx_path = ptx_path or _last_ptx_path.get()
+    if not ptx_path:
+        raise RuntimeError("No compiled PTX; call compile_kernel() first")
    import pycuda.driver as cuda
    return cuda.module_from_file(ptx_path)


-def build_module(cfg: LBMConfig, source: str, *, arch: str, n_objects: int = 0,
-                 block_root_bc: int = 0):
-    """Generate, compile and load one private module; the build directory is removed.
+# ---------------------------------------------------------------------------
+# Back-compat helpers (used by test scripts)
+# ---------------------------------------------------------------------------

-    The single build path of every owner (Simulation, FixedPatchStepper levels).
-    Each call returns a NEW module: callers must not share it, because its
-    globals (d_params, ...) are mutable per module.
-    """
-    build_dir = generate_config(cfg, n_objects=n_objects, block_root_bc=block_root_bc)
-    try:
-        return load_module(compile_kernel(arch, source=source, build_dir=build_dir))
-    finally:
-        cleanup_build_dir(build_dir)
-
-
-def set_params(module, omega: float, fx: float = 0.0, fy: float = 0.0, fz: float = 0.0,
-               n_objects: int = 0) -> None:
-    """Write the module's __constant__ LBMParams (core/params.cuh layout)."""
-    import struct
-    import pycuda.driver as cuda
-    ptr, size = module.get_global("d_params")
-    if size != struct.calcsize("=ffffI"):
-        raise RuntimeError("LBMParams host/device layout mismatch")
-    cuda.memcpy_htod(ptr, struct.pack("=ffffI", omega, fx, fy, fz, n_objects))
+def compile_kernel_v2(arch: str = "sm_70") -> str:
+    """Alias for compile_kernel() kept for test-script compatibility."""
+    return compile_kernel(arch=arch)
@@ -2,7 +2,7 @@
 """Packed ``obs`` buffer layout for force / torque / sensor telemetry.

 Usage::
-    Host code (e.g. ``ObjectManager``) and ``compiler.generate_config`` must use
+    Host code (e.g. ``ObjectManager``) and ``compiler_v2.generate_config`` must use
    the same ``dim`` and ``n_objects`` so allocation sizes match device macros.

 Design::
@@ -0,0 +1,286 @@
+# CelerisLab/lbm/block_stepper.py
+"""Opt-in periodic backend for one BlockLayout2D level, optional static circles.
+
+D2Q9/SRT/FP32 unforced double buffers. Each step refreshes every halo from
+its owner core, then pulls/collides core cells into the spare buffer, then
+swaps. Only halo pair tables are uploaded; dense ownership stays on the host.
+The caller owns the CudaContext and must close this backend before it.
+Optional ``objects`` are stationary passive circles (static linear BFL via
+receiver-local staging: halo refresh -> cut links -> pull, no copy between).
+No force/actuation readout, motion, walls, refinement, checkpoint or runtime
+parameter mutation; wall/slot/inlet fields in cfg are ignored.
+"""
+from dataclasses import replace
+from numbers import Integral
+import struct
+from threading import RLock
+
+import numpy as np
+import pycuda.driver as cuda
+
+from ..cuda import compiler_v2 as compiler
+from .blocks import NQ, BlockLayout2D, blocked_link_tables
+from .descriptors import D2Q9_EX, D2Q9_EY, FLUID, SOLID
+from .population_storage import _StoredPopulations, _encode_physical, _decode_stored
+
+MAX_GRID_DIM = 65535  # CUDA gridDim.y/z limit (rows, blocks)
+
+
+def _static_circles(layout, objects):
+    """Host tables for stationary circles; rejects before any CUDA work.
+
+    Every periodic neighbor of every fluid core is inspected, including domain
+    edges that CircleGeometry does not enumerate, so clipped or incomplete
+    geometry cannot pass. Each physical link has one receiver-owning block.
+    """
+    from ..body.geometry.circle import CircleGeometry
+
+    ny, nx = layout.shape
+    flags = np.full(ny * nx, FLUID, np.uint16)
+    for obj in objects:
+        if (type(obj.geometry) is not CircleGeometry or obj.is_sensor or obj.is_force_region
+                or obj.surface_actuation is not None
+                or any(getattr(obj.state, name) != 0 for name in ("vx", "vy", "omega"))
+                or any(vars(obj.control).values())):
+            raise ValueError("Block bodies must be stationary passive circles")
+        cx, cy = obj.geometry.center
+        radius = obj.geometry._radius
+        if not np.isfinite([cx, cy, radius]).all() or radius <= 0:
+            raise ValueError("Block circle center/radius must be finite with radius > 0")
+        mask = obj.geometry.build_flag_mask(nx, ny)
+        solid = (mask & SOLID) != 0
+        if not solid.any() or np.any(flags[solid] & SOLID):
+            raise ValueError("Block circles must be resolved and disjoint")
+        flags[solid] = mask[solid]
+    solid = ((flags & SOLID) != 0).reshape(ny, nx)
+    if solid[[0, -1]].any() or solid[:, [0, -1]].any():
+        raise ValueError("Block circles must not touch the domain edge")
+    links = [link for obj in objects
+             for link in obj.geometry.build_cut_links(nx, ny, domain_flags=flags)]
+    def source(r, q):
+        y, x = divmod(r, nx)
+        return (y + D2Q9_EY[q]) % ny, (x + D2Q9_EX[q]) % nx
+    receivers = {(int(link.fluid_idx), int(link.dir)) for link in links}
+    required = {(int(r), q) for r in np.flatnonzero(~solid.ravel())
+                for q in range(1, NQ) if solid[source(r, q)]}
+    if len(receivers) != len(links) or receivers != required:
+        raise ValueError("Cut links must cover every fluid pull from a solid exactly once")
+    tables, _ = blocked_link_tables(
+        layout, flags, np.array([link.fluid_idx for link in links], np.uint32),
+        np.array([link.dir for link in links], np.uint8),
+        np.array([link.q for link in links], np.float32),
+        np.array([link.fallback for link in links], np.uint8))
+    return dict(solid=solid, **tables)
+
+
+class PeriodicBlockStepper:
+    """G->G stepping of Q-major (9, ny, nx) postcollision populations.
+
+    On a device/launch failure the instance becomes unusable: close and
+    recreate it rather than assuming a partially advanced buffer rolled back.
+    """
+    def __init__(self, cfg, layout, *, context, objects=()):
+        if not isinstance(layout, BlockLayout2D) or layout.periodic != (True, True):
+            raise ValueError("PeriodicBlockStepper requires a doubly periodic BlockLayout2D")
+        checked = replace(cfg)
+        checked.validate()
+        if (not checked.is_d2q9 or checked.collision != "SRT"
+                or checked.streaming != "double_buffer" or checked.store_precision != "FP32"
+                or checked.les_enabled
+                or (checked.ny, checked.nx) != layout.shape):
+            raise ValueError("PeriodicBlockStepper requires matching D2Q9/SRT/FP32/"
+                             "double_buffer config without LES")
+        ly, lx = layout.local_shape
+        pairs = len(layout.halo_dst)
+        tpb = checked.threads_per_block
+        if layout.nblocks > MAX_GRID_DIM or ly > MAX_GRID_DIM or not 0 < pairs < 2**31:
+            raise ValueError("block count, block rows or halo pairs exceed launch limits")
+        objects = tuple(objects)  # an empty iterable takes the body-free path
+        self.boundary = _static_circles(layout, objects) if objects else None
+        links = 0 if self.boundary is None else len(self.boundary["cell"])
+        if links >= 2**31:
+            raise ValueError("cut links exceed launch limits")
+        self._ddf_shifting = bool(checked.ddf_shifting)
+        self.layout = layout
+        self.ctx = context
+        self._links = links
+        self._link_grid = ((links + tpb - 1) // tpb, 1)
+        # Wall/slot fields are not applied; neutralize them like the fine patch level.
+        self._local_cfg = replace(checked, nx=lx, ny=ly, y_wall_bc="bounce_back", top_wall_bc="velocity",
+                                  wall_slot_width=0, wall_normal_velocity=0.0, velocity=0.0)
+        self._block = (tpb, 1, 1)
+        self._grid = ((lx + tpb - 1) // tpb, ly, layout.nblocks)
+        self._copy_grid = ((pairs + tpb - 1) // tpb, 1)
+        self._bytes = int(np.prod(layout.blocked_shape)) * 4
+        self._lock = RLock()
+        self._status = "new"
+        self._step_count = 0
+        self._allocations = []
+        self._stream = self._module = self._copy = self._step = self._curved = None
+        self._tables = {}
+        with self.ctx.activate():
+            try:
+                free, _ = cuda.mem_get_info()
+                tables = sum(a.nbytes for k, a in (self.boundary or {}).items() if k != "solid")
+                if 2 * self._bytes + layout.halo_dst.nbytes + layout.halo_src.nbytes + tables > free:
+                    raise MemoryError("blocked buffers exceed free device memory")
+                self._stream = cuda.Stream()
+                config = self._local_cfg
+                config.validate()
+                if not np.isclose(config.omega, 1 / (3 * checked.viscosity + .5), rtol=1e-14, atol=0):
+                    raise RuntimeError("block omega/tau mismatch")
+                build = compiler.generate_config(config)
+                try:
+                    ptx = compiler.compile_kernel(self.ctx.sm_arch, source="blocks.cu", build_dir=build)
+                    module = compiler.load_module(ptx)
+                finally:
+                    compiler.cleanup_build_dir(build)
+                ptr, size = module.get_global("d_params")
+                if size != struct.calcsize("=ffffI"):
+                    raise RuntimeError("LBMParams host/device layout mismatch")
+                cuda.memcpy_htod(ptr, struct.pack("=ffffI", config.omega, 0, 0, 0, 0))
+                self._module = module
+                self._current = self._allocate(self._bytes)
+                self._spare = self._allocate(self._bytes)
+                self._dst = self._upload(layout.halo_dst)
+                self._src = self._upload(layout.halo_src)
+                self._copy = module.get_function("BlockHaloCopy")
+                self._step = module.get_function("BlockStep")
+                if self.boundary is not None:
+                    self._tables = {k: self._upload(a) for k, a in self.boundary.items() if k != "solid"}
+                    self._curved = module.get_function("BlockCurvedBoundary")
+            except BaseException:
+                try:
+                    self.close()
+                except Exception:
+                    pass  # Preserve the original construction failure.
+                raise
+
+    def _allocate(self, size):
+        pointer = cuda.mem_alloc(size)
+        self._allocations.append(pointer)
+        return pointer
+
+    def _upload(self, array):
+        array = np.ascontiguousarray(array)
+        pointer = self._allocate(array.nbytes)
+        cuda.memcpy_htod(pointer, array)
+        return pointer
+
+    def _require(self, *states):
+        if self._status not in states:
+            raise RuntimeError(f"Block stepper is {self._status}; expected {' or '.join(states)}")
+
+    @property
+    def step_count(self):
+        return self._step_count
+
+    def initialize(self, g):
+        """Upload dense G_0; the spare buffer starts NaN so stale halos cannot hide."""
+        with self._lock, self.ctx.activate():
+            self._require("new", "ready")
+            dense = np.array(g, dtype=np.float64 if self._ddf_shifting else np.float32,
+                             order="C", copy=True)
+            if dense.shape != (NQ, *self.layout.shape):
+                raise ValueError("Expected a Q-major (9, ny, nx) array")
+            fluid = np.ones(self.layout.shape, bool) if self.boundary is None else ~self.boundary["solid"]
+            if not np.isfinite(dense[:, fluid]).all() or (dense[:, fluid].sum(axis=0) <= 0).any():
+                raise ValueError("Fluid populations must be finite with positive density")
+            dense[:, ~fluid] = np.nan  # Solid cores are deliberately invalid.
+            encoded = _encode_physical(dense, self._ddf_shifting)
+            values = encoded[:, fluid]
+            if (not np.isfinite(values).all()
+                    or (values.sum(axis=0, dtype=np.float64) + int(self._ddf_shifting) <= 0).any()):
+                raise ValueError("Stored fluid populations must be finite with positive density")
+            blocked = self.layout.to_blocked(encoded)
+            spare = np.full_like(blocked, np.nan)
+            try:
+                cuda.memcpy_htod(self._current, blocked)
+                cuda.memcpy_htod(self._spare, spare)
+                self._step_count = 0
+                self._status = "ready"
+            except BaseException:
+                self._status = "failed"
+                raise
+
+    def step(self, n=1):
+        """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")
+            kw = dict(block=self._block, stream=self._stream)
+            try:
+                self._status = "advancing"
+                for _ in range(n):
+                    self._copy(self._current, self._dst, self._src,
+                               np.uint32(len(self.layout.halo_dst)), grid=self._copy_grid, **kw)
+                    if self._curved is not None:
+                        t = self._tables
+                        self._curved(self._current, t["block"], t["cell"], t["dir"], t["q"],
+                                     t["fallback"], np.uint32(self._links), np.uintp(0),  # no actuation
+                                     np.uintp(0), np.uintp(0), np.uintp(0),  # no observation
+                                     grid=self._link_grid, **kw)
+                    self._step(self._current, self._spare, np.uint32(self.layout.halo),
+                               self._tables.get("flags", np.uintp(0)), np.uintp(0),  # no kind
+                               grid=self._grid, **kw)
+                    self._stream.synchronize()
+                    self._current, self._spare = self._spare, self._current
+                    self._step_count += 1
+                self._status = "ready"
+            except BaseException:
+                self._status = "failed"
+                raise
+
+    def download(self):
+        """Return physical core populations (FP64 when shifted); no host cache."""
+        snapshot = self._download_raw()
+        return _decode_stored(snapshot.values[0], snapshot.shifted)
+
+    def _download_raw(self):
+        """Return one tagged dense FP32 population array without conversion."""
+        with self._lock, self.ctx.activate():
+            self._require("ready")
+            blocked = np.empty(self.layout.blocked_shape, np.float32)
+            try:
+                cuda.memcpy_dtoh(blocked, self._current)
+            except BaseException:
+                self._status = "failed"
+                raise
+            return _StoredPopulations((self.layout.to_dense(blocked),), self._ddf_shifting)
+
+    def close(self):
+        """Release owned resources; retain them for retry if context activation fails."""
+        with self._lock:
+            if self._status == "closed":
+                return
+            self._status = "failed"
+            with self.ctx.activate():
+                self._status = "closed"
+                error = None
+                try:
+                    if self._stream is not None:
+                        self._stream.synchronize()
+                except Exception as exc:
+                    error = exc
+                self._copy = self._step = self._curved = self._module = None
+                self._tables = {}
+                for pointer in self._allocations:
+                    try:
+                        pointer.free()
+                    except Exception as exc:
+                        error = error or exc
+                self._allocations.clear()
+                self._stream = None
+                if error is not None:
+                    raise error
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, *exc):
+        try:
+            self.close()
+        except Exception:
+            if exc[0] is None:
+                raise
@@ -31,7 +31,7 @@ receiver-local boundary values: the solid's owner-core copy of that slot may
 be stale, which is distinct from the unique core ownership of stored state.
 No moving geometry is implied.
 """
-from dataclasses import dataclass, replace
+from dataclasses import dataclass
 from numbers import Integral
 from types import SimpleNamespace

@@ -373,84 +373,3 @@ def blocked_link_tables(layout, flags, fluid_idx, dir, q, fallback):
                  dir=columns[1].astype(np.uint8), q=columns[2].astype(np.float32),
                  fallback=columns[3].astype(np.uint8))
    return tables, mapped
-
-
-# One blocked level as FixedPatchStepper builds and launches it (any depth). Raw argument orders of the blocked.cu kernels live only here.
-
-def level_config(cfg, layout, tau):
-    """Kernel config of one blocked level: NX/NY = block window incl. halo.
-
-    Physical wall/slot/inlet fields are neutralized; a blocked root gets them
-    from its module globals (d_block_wall/d_block_channel) instead.
-    """
-    ly, lx = layout.local_shape
-    local = replace(cfg, nx=lx, ny=ly, y_wall_bc="bounce_back", top_wall_bc="velocity",
-                    wall_slot_width=0, wall_normal_velocity=0.0, velocity=0.0)
-    local.validate()
-    if not np.isclose(local.omega, 1 / tau, rtol=1e-14, atol=0):
-        raise RuntimeError("block level omega/tau mismatch")
-    return local
-
-
-def launch_halo_copy(kernel, buffer, dst, src, count, *, block, stream):
-    """BlockHaloCopy over ``count`` uploaded (dst, src) block-cell pairs."""
-    kernel(buffer, dst, src, np.uint32(count),
-           grid=((count + block[0] - 1) // block[0], 1), block=block, stream=stream)
-
-
-def launch_curved_boundary(kernel, buffer, tables, count, *, block, stream,
-                           velocity=None, rx=None, ry=None, raw=None):
-    """BlockCurvedBoundary on uploaded link tables; None = no actuation/observation."""
-    none = np.uintp(0)
-    kernel(buffer, tables["block"], tables["cell"], tables["dir"], tables["q"], tables["fallback"],
-           np.uint32(count), none if velocity is None else velocity,
-           none if rx is None else rx, none if ry is None else ry, none if raw is None else raw,
-           grid=((count + block[0] - 1) // block[0], 1), block=block, stream=stream)
-
-
-def static_circle_tables(layout, objects):
-    """Host tables for stationary circles; rejects before any CUDA work.
-
-    Every periodic neighbor of every fluid core is inspected, including domain
-    edges that CircleGeometry does not enumerate, so clipped or incomplete
-    geometry cannot pass. Each physical link has one receiver-owning block.
-    """
-    from ..body.geometry.circle import CircleGeometry
-    from .descriptors import FLUID, SOLID
-
-    ny, nx = layout.shape
-    flags = np.full(ny * nx, FLUID, np.uint16)
-    for obj in objects:
-        if (type(obj.geometry) is not CircleGeometry or obj.is_sensor or obj.is_force_region
-                or obj.surface_actuation is not None
-                or any(getattr(obj.state, name) != 0 for name in ("vx", "vy", "omega"))
-                or any(vars(obj.control).values())):
-            raise ValueError("Block bodies must be stationary passive circles")
-        cx, cy = obj.geometry.center
-        radius = obj.geometry._radius
-        if not np.isfinite([cx, cy, radius]).all() or radius <= 0:
-            raise ValueError("Block circle center/radius must be finite with radius > 0")
-        mask = obj.geometry.build_flag_mask(nx, ny)
-        solid = (mask & SOLID) != 0
-        if not solid.any() or np.any(flags[solid] & SOLID):
-            raise ValueError("Block circles must be resolved and disjoint")
-        flags[solid] = mask[solid]
-    solid = ((flags & SOLID) != 0).reshape(ny, nx)
-    if solid[[0, -1]].any() or solid[:, [0, -1]].any():
-        raise ValueError("Block circles must not touch the domain edge")
-    links = [link for obj in objects
-             for link in obj.geometry.build_cut_links(nx, ny, domain_flags=flags)]
-    def source(r, q):
-        y, x = divmod(r, nx)
-        return (y + D2Q9_EY[q]) % ny, (x + D2Q9_EX[q]) % nx
-    receivers = {(int(link.fluid_idx), int(link.dir)) for link in links}
-    required = {(int(r), q) for r in np.flatnonzero(~solid.ravel())
-                for q in range(1, NQ) if solid[source(r, q)]}
-    if len(receivers) != len(links) or receivers != required:
-        raise ValueError("Cut links must cover every fluid pull from a solid exactly once")
-    tables, _ = blocked_link_tables(
-        layout, flags, np.array([link.fluid_idx for link in links], np.uint32),
-        np.array([link.dir for link in links], np.uint8),
-        np.array([link.q for link in links], np.float32),
-        np.array([link.fallback for link in links], np.uint8))
-    return dict(solid=solid, **tables)
@@ -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.
@@ -1,49 +0,0 @@
-// CelerisLab/lbm/kernels/blocked.cu
-// One fixed-size blocked level (lbm/blocks.py layout), specialized at compile
-// time for periodic/fine, slot/reservoir or channel stepping. 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).
-#include <stdint.h>
-#include <math.h>
-#include "config.h"
-#include "core/precision.cuh"
-#include "core/descriptors.cuh"
-#include "core/layout.cuh"
-#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
-#include "operators/collision_mrt.cuh"
-#endif
-#include "streaming/pull_double_buffer.cuh"
-#include "boundary/curved_boundary.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
-
-// 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"
-#else
-#include "step/block_channel.cu"
-#endif
@@ -0,0 +1,206 @@
+// CelerisLab/lbm/kernels/blocks.cu
+// 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).
+#include <stdint.h>
+#include <math.h>
+#include "config.h"
+#include "core/precision.cuh"
+#include "core/descriptors.cuh"
+#include "core/layout.cuh"
+#include "core/params.cuh"
+#include "core/flags.cuh"
+#include "core/obs.cuh"
+#include "operators/macro.cuh"
+#include "operators/collision_srt.cuh"
+#if COLLISION_MODEL == 2
+#include "operators/collision_mrt.cuh"
+#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
+
+// Fixed-patch cell kinds, matching refinement.py ACTIVE/INNER_GHOST/OUTER_GHOST.
+constexpr unsigned char KIND_ACTIVE = 0u, KIND_INNER = 1u, KIND_OUTER = 2u;
+
+// 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
+            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)
 // ---------------------------------------------------------------------------
@@ -1,4 +1,4 @@
-// CelerisLab – uniform.cu
+// CelerisLab – kernel_v2.cu
 // ============================================================================
 // Compilation entry point (Stage 2 Architecture).
 //
@@ -7,7 +7,7 @@
 //
 // File layout (each <300 lines):
 //   operators/helpers.cuh  — bounce_back_swap, collide_dispatch
-//   step/init_flow.cu      — InitTubeFlow, InitEsoPull
+//   step/init_flow.cu      — InitTubeFlow_v2, InitEsoPull
 //   step/one_step_double.cu — OneStep (pull double-buffer)
 //   step/one_step_esopull.cu — EsoPullStep (single-buffer)
 //   step/aux_kernels.cu    — CurvedBoundaryKernel, SensorKernel
@@ -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);
+}
@@ -3,7 +3,7 @@
 // ApplyEsoPullCurvedKernel, SensorKernel, ForceRegionKernel.
 //
 // Launched on compact lists (n_curved / n_sensor / n_cells threads).
-// Included by uniform.cu.  No standalone compilation.
+// Included by kernel_v2.cu.  No standalone compilation.
 //
 // Double-buffer mode:
 //   CurvedBoundaryKernel runs BEFORE OneStep.
@@ -1,42 +0,0 @@
-// CelerisLab/lbm/kernels/step/block_boundary.cu
-// Receiver-local curved-boundary staging and its raw-exchange accumulation.
-// Part of the blocked.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 blocked.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 blocked.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]]);
-}
@@ -3,7 +3,7 @@
 //
 // Decodes the EsoPull backing layout into physical distributions, then
 // computes rho/ux/uy.  Output is SoA: rho_out[N], ux_out[N], uy_out[N].
-// Included by uniform.cu.  No standalone compilation.
+// Included by kernel_v2.cu.  No standalone compilation.
 //
 // This kernel is the sole path for macroscopic diagnostics in EsoPull mode.
 // It uses the shared semantic helper layer (esopull_semantic_helpers.cuh).
@@ -5,7 +5,7 @@
 // or encodes physical DDF back to EsoPull backing layout.
 // Each thread handles one cell from a compact index list.
 //
-// Included by uniform.cu.  No standalone compilation.
+// Included by kernel_v2.cu.  No standalone compilation.
 // ============================================================================

 #ifndef CELERIS_STEP_ESOPULL_SYNC_CU
@@ -1,6 +1,6 @@
 // CelerisLab – step/init_flow.cu
 // Channel-flow initialization kernels (double-buffer and EsoPull).
-// Included by uniform.cu after all headers.  No standalone compilation.
+// Included by kernel_v2.cu after all headers.  No standalone compilation.
 // ============================================================================

 #ifndef CELERIS_STEP_INIT_FLOW_CU
@@ -73,9 +73,9 @@ __device__ __forceinline__ uint16_t finalize_domain_flag(
 }

 // ============================================================================
-// InitTubeFlow — double-buffer channel initialization
+// InitTubeFlow_v2 — double-buffer channel initialization
 // ============================================================================
-__global__ void InitTubeFlow(uint16_t* flag, fpxx* fi)
+__global__ void InitTubeFlow_v2(uint16_t* flag, fpxx* fi)
 {
 #if DIM == 2
    unsigned int x, y; unsigned long k;
@@ -1,6 +1,6 @@
 // CelerisLab – step/one_step_double.cu
 // Double-buffer PULL streaming step kernel.
-// Included by uniform.cu.  No standalone compilation.
+// Included by kernel_v2.cu.  No standalone compilation.
 // ============================================================================

 #ifndef CELERIS_STEP_ONE_STEP_DOUBLE_CU
@@ -1,6 +1,6 @@
 // CelerisLab – step/one_step_esopull.cu
 // Esoteric-Pull single-buffer step kernel.
-// Included by uniform.cu.  No standalone compilation.
+// Included by kernel_v2.cu.  No standalone compilation.
 //
 // CURVED BC: supported via PrepareEsoPullCurvedKernel + ApplyEsoPullCurvedKernel
 // in aux_kernels.cu, launched by stepper.py before EsoPullStep.
@@ -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,
@@ -14,16 +14,15 @@ from threading import RLock
 import numpy as np
 import pycuda.driver as cuda

-from ..cuda import compiler
-from .blocks import (BlockLayout2D, launch_curved_boundary, launch_halo_copy, level_config,
-                     static_circle_tables)
+from ..cuda import compiler_v2 as compiler
+from .blocks import BlockLayout2D
 from .channel import channel_masks, validate_channel_config, validate_channel_transfers
 from ..body.jets import jet_link_velocity
+from .block_stepper import MAX_GRID_DIM
 from .hierarchy import build_hierarchy, is_rectangle
 from .refinement import ACTIVE, HALO, FixedPatch2D, FixedPatchSet2D, prepare_fine_boundary
 from .refinement_tables import (blocked_base_tables, blocked_fine_tables,  # noqa: F401 (re-export)
                                blocked_kind, projected_explosion_tables, _prepare_blocked_boundary,
-                                _BlockedBoundary,
                                BLOCKED_BOUNDARY_DEVICE_COLUMNS)
 from .descriptors import SOLID
 from .raw_exchange import summarize_exchange
@@ -66,27 +65,67 @@ def _level_name(level):
    return ("base", "fine", "child")[level] if level < 3 else f"level {level}"


-MAX_GRID_DIM = 65535  # CUDA gridDim.y/z limit (rows, blocks)
+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")
    for name, values in (("level_blocks", blocks), ("level_objects", objects), ("level_jets", jets)):
        if len(values) != depth:
            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)")
-    if depth == 1:  # one blocked level: the root carries the static circles
-        if blocks[0] is None or jets[0]:
-            raise ValueError("a single level must be blocked and has no Jets")
-        return
+            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")
@@ -95,17 +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).
-    ``refinements=[]`` is one blocked level: periodic SRT root without LES,
-    Jets or exchange observation; its ``level_objects[0]`` are stationary
-    passive circles (static BFL).
+    """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``.
@@ -116,55 +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 blocked.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.
@@ -172,21 +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]
@@ -204,11 +268,6 @@ class FixedPatchStepper:
        self._ddf_shifting = bool(cfg.ddf_shifting)
        if self._ddf_shifting and any(b is None for b in level_blocks):
            raise ValueError("shifted populations require all-blocked levels; dense/mixed is unsupported")
-        if depth == 1 and (coarse_boundary != "periodic" or cfg.collision != "SRT" or cfg.les_enabled
-                           or explosion != "constant"
-                           or observe_raw_exchange or observe_window_exchange):
-            raise ValueError("a single level requires a periodic SRT root without LES, projection "
-                             "or exchange observation")
        self._channel = coarse_boundary == "channel"
        if self._channel:
            validate_channel_config(cfg, level_blocks)
@@ -242,14 +301,12 @@ class FixedPatchStepper:
            base = blocked_base_tables(pairs[0], self._layouts[0], np.argsort(pairs[0].coalesce_coarse))
            validate_channel_transfers(pairs[0], self._layouts[0], base[1])
        # Kernel configurations per level (geometry configs live in self.hierarchy).
-        self._level_cfgs = [replace(cfg)]
-        if pairs:
-            fine_cfg = replace(cfg, nx=pairs[0].fine_shape[1], ny=pairs[0].fine_shape[0],
-                               viscosity=2 * cfg.viscosity)
-            if self._wall_aware:
-                fine_cfg = replace(fine_cfg, y_wall_bc="bounce_back", top_wall_bc="velocity",
-                                   wall_slot_width=0, wall_normal_velocity=0.0, velocity=0.0)
-            self._level_cfgs.append(fine_cfg)
+        fine_cfg = replace(cfg, nx=pairs[0].fine_shape[1], ny=pairs[0].fine_shape[0],
+                           viscosity=2 * cfg.viscosity)
+        if self._wall_aware:
+            fine_cfg = replace(fine_cfg, y_wall_bc="bounce_back", top_wall_bc="velocity",
+                               wall_slot_width=0, wall_normal_velocity=0.0, velocity=0.0)
+        self._level_cfgs = [replace(cfg), fine_cfg]
        for pair in pairs[1:]:
            parent = self._level_cfgs[-1]
            self._level_cfgs.append(replace(parent, nx=pair.fine_shape[1], ny=pair.fine_shape[0],
@@ -290,18 +347,12 @@ class FixedPatchStepper:
        self._exchange_centers = tuple(tuple(tuple(o.geometry.center) for o in objects)
                                       for objects in level_objects)
        self._level_jets = level_jets
-        root = None
-        if depth == 1 and level_objects[0]:
-            tables = static_circle_tables(self._layouts[0], level_objects[0])
-            root = _BlockedBoundary(None, tables, (), False)
-        self._level_boundaries = [root] + [
+        self._level_boundaries = [None] + [
            _prepare_blocked_boundary(self._boundary_hosts[level], self._layouts[level],
                                      self._level_cfgs[level], level_jets[level],
                                      _shifted_blocked=self._ddf_shifting)
            for level in range(1, depth)]
        self._leaf = [kind == ACTIVE for kind in self.hierarchy.kinds]
-        if root is not None:
-            self._leaf[0] &= ~root.tables["solid"]
        for level in range(1, depth):
            host = self._boundary_hosts[level]
            if host is not None:
@@ -324,9 +375,6 @@ class FixedPatchStepper:
        self._block = (cfg.threads_per_block, 1, 1)
        with self.ctx.activate():
            try:
-                free, _ = cuda.mem_get_info()
-                if self._planned_bytes() > free:  # before any stream, module or buffer
-                    raise MemoryError("level buffers exceed free device memory")
                self._stream = cuda.Stream()
                for level in range(depth):
                    self._levels.append(self._build_level(level))
@@ -348,9 +396,7 @@ class FixedPatchStepper:
                                b.window_integral = self._allocate(count * 4 * 8)
                            b.accumulate = level.module.get_function("BlockAccumulateExchange")
                        b.kernel = level.module.get_function("BlockCurvedBoundary")
-                if depth == 1:
-                    pass
-                elif self._level_boundaries[1] is not None:
+                if self._level_boundaries[1] is not None:
                    b = self._level_boundaries[1]
                    self._fine_flags, self._link_tables, self._curved = b.flags, b.device, b.kernel
                elif self._boundary_hosts[1] is not None:
@@ -372,47 +418,32 @@ class FixedPatchStepper:
                    pass  # Preserve the original construction failure.
                raise

-    def _planned_bytes(self):
-        """Both G buffers, halo pairs and boundary columns of every level (transfer tables excluded).
-
-        A fail-fast lower bound only: passing it cannot guarantee that later
-        allocations succeed (other consumers, fragmentation, races).
-        """
-        total = 0
-        for index, layout in enumerate(self._layouts):
-            cells = int(np.prod(layout.blocked_shape if layout is not None
-                                else (9, *self.hierarchy.kinds[index].shape)))
-            total += 2 * 4 * cells
-            if layout is not None:
-                total += layout.halo_dst.nbytes + layout.halo_src.nbytes
-            b = self._level_boundaries[index]
-            if b is not None:
-                total += sum(np.asarray(v).nbytes for k, v in b.tables.items()
-                             if k == "flags" or k in BLOCKED_BOUNDARY_DEVICE_COLUMNS)
-        return total
-
    def _build_level(self, index):
        """Compile one level's step module and allocate its two G buffers."""
        layout, config = self._layouts[index], self._level_cfgs[index]
        pairs = self.hierarchy.pairs
-        tau = (pairs[0].tau_coarse if pairs else 3 * config.viscosity + .5) if index == 0 \
-            else pairs[index - 1].tau_fine
+        tau = pairs[0].tau_coarse if index == 0 else pairs[index - 1].tau_fine
        name, source = ("PatchCoarseStep" if index == 0 else "PatchFineStep"), "refinement.cu"
        if layout is not None:
-            config = level_config(config, layout, tau)
-            name, source = ("BlockChannelStep" if index == 0 and self._channel else "BlockStep"), "blocked.cu"
-        else:
-            config.validate()
-            if not np.isclose(config.omega, 1 / tau, rtol=1e-14, atol=0):
-                raise RuntimeError("level omega/tau mismatch")
+            config = replace(config, nx=layout.local_shape[1], ny=layout.local_shape[0],
+                             y_wall_bc="bounce_back", top_wall_bc="velocity",
+                             wall_slot_width=0, wall_normal_velocity=0.0, velocity=0.0)
+            name, source = ("BlockChannelStep" if index == 0 and self._channel else "BlockStep"), "blocks.cu"
+        config.validate()
+        if not np.isclose(config.omega, 1 / tau, rtol=1e-14, atol=0):
+            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
-        module = compiler.build_module(config, source, arch=self.ctx.sm_arch, n_objects=n_objects,
-                                       block_root_bc=block_root_bc)
-        compiler.set_params(module, config.omega, n_objects=n_objects)
+        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)
+        finally:
+            compiler.cleanup_build_dir(build)
+        ptr, size = module.get_global("d_params")
+        if size != struct.calcsize("=ffffI"):
+            raise RuntimeError("LBMParams host/device layout mismatch")
+        cuda.memcpy_htod(ptr, struct.pack("=ffffI", config.omega, 0, 0, 0, n_objects))
        shape = (9, *self.hierarchy.kinds[index].shape)
        size = int(np.prod(shape if layout is None else layout.blocked_shape)) * 4
        grid = ((config.nx + self._block[0] - 1) // self._block[0], config.ny,
@@ -509,13 +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()
@@ -557,9 +588,7 @@ class FixedPatchStepper:
            try:
                for level, array in zip(self._levels, arrays):
                    cuda.memcpy_htod(level.current, array)
-                    # A single level starts its spare NaN so stale halos cannot hide.
-                    cuda.memcpy_htod(level.spare, np.full_like(array, np.nan)
-                                     if len(self._levels) == 1 else array)
+                    cuda.memcpy_htod(level.spare, array)
                if self._fine_curved is not None and self._fine_curved.link_exchange_gpu is not None:
                    cuda.memset_d8(self._fine_curved.link_exchange_gpu, 0, self._fine_curved.count * 12)
                self._step_count = 0
@@ -641,9 +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:
@@ -723,12 +753,15 @@ class FixedPatchStepper:
            return
        if b.kernel is None or b.flags is None:
            raise RuntimeError("Boundary device buffers are missing")
-        t = b.device
+        t, count = b.device, len(b.tables["cell"])
        velocity = t.get("surface_velocity")
        if b.actuated and velocity is None:
            raise RuntimeError("Surface velocity device buffer is missing")
-        launch_curved_boundary(b.kernel, buffer, t, len(b.tables["cell"]), velocity=velocity,
-                               rx=t.get("rx"), ry=t.get("ry"), raw=b.last_raw, **kw)
+        b.kernel(buffer, t["block"], t["cell"], t["dir"], t["q"], t["fallback"],
+                 np.uint32(count), velocity if velocity is not None else np.uintp(0),
+                 t.get("rx", np.uintp(0)), t.get("ry", np.uintp(0)),
+                 b.last_raw if b.last_raw is not None else np.uintp(0),
+                 grid=((count + self._block[0] - 1) // self._block[0], 1), **kw)

    def _advance(self, index, parent_buffer, **kw):
        """Explode from the given parent buffer, then two hops of level ``index``."""
@@ -780,50 +813,36 @@ class FixedPatchStepper:
                             np.float64(h), np.float64(h),
                             grid=((count + self._block[0] - 1) // self._block[0], 1), **kw)
        flags = np.uintp(0) if level.boundary is None else level.boundary.flags
-        kind = np.uintp(0) if level.kind is None else level.kind  # single level: all ACTIVE
-        level.kernel(src, dst, np.uint32(level.layout.halo), flags, kind, grid=level.grid, **kw)
+        level.kernel(src, dst, np.uint32(level.layout.halo), flags, level.kind, grid=level.grid, **kw)

    def _gather_halo(self, level, buffer, **kw):
        pairs = len(level.layout.halo_dst)
        if pairs:
-            launch_halo_copy(level.halo_copy, buffer, level.halo_dst, level.halo_src, pairs, **kw)
+            level.halo_copy(buffer, level.halo_dst, level.halo_src, np.uint32(pairs),
+                            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
@@ -986,8 +1005,8 @@ class FixedPatchStepper:
            if exc[0] is None:
                raise

-    # Read-only compatibility views over the level lists, kept on purpose for the existing
-    # tests and docs. Internal code must not use them; it reads hierarchy/_layouts/_level_*.
+    # Read-only compatibility views over the level lists. Internal code must not use them;
+    # REMOVE AFTER the existing tests/docs migrate to hierarchy/_layouts/_level_* lists.
    patch = property(lambda self: self.hierarchy.pairs[0])
    child_patch = property(lambda self: self.hierarchy.pairs[1] if self.hierarchy.depth > 2 else None)
    base_layout = property(lambda self: self._layouts[0])
@@ -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)
@@ -28,7 +28,7 @@ class LBMStepper:
            self.boundary_values_gpu = cuda.mem_alloc((6 * cfg.nx + 2 * cfg.ny * cfg.nq) * 4)
        else:
            self.step_fn = module.get_function("OneStep")
-            self.init_fn = module.get_function("InitTubeFlow")
+            self.init_fn = module.get_function("InitTubeFlow_v2")

        self.curved_fn = module.get_function("CurvedBoundaryKernel")
        self.prepare_esopull_curved_fn = module.get_function("PrepareEsoPullCurvedKernel")
@@ -25,7 +25,7 @@ import pycuda.driver as cuda

 from .config import LBMConfig, BodyConfig, load_lbm_config, load_body_config
 from .cuda.context import CudaContext, context_bound
-from .cuda import compiler
+from .cuda import compiler_v2 as compiler
 from .lbm.field import LBMField
 from .lbm.stepper import LBMStepper
 from .body.objects import SimObject
@@ -46,6 +46,7 @@ class Simulation:
                 device_id: int = 0):
        # Internal stream for async DTOH coordination
        self._stream: Optional[cuda.Stream] = None
+        self._build_dir = None
        self._closed = False

        # Load configs
@@ -58,7 +59,9 @@ class Simulation:
        try:
            with self.ctx.activate():
                arch = self._resolve_compile_arch()
-                self._module = compiler.build_module(self.lbm_cfg, "uniform.cu", arch=arch)
+                self._build_dir = compiler.generate_config(self.lbm_cfg, n_objects=0)
+                self._ptx_path = compiler.compile_kernel(arch=arch, build_dir=self._build_dir)
+                self._module = compiler.load_module(self._ptx_path)
                self._compiled_n_objects = 0
                self._allocation_signature = self.lbm_cfg.allocation_signature()
                self._compiled_viscosity = self.lbm_cfg.viscosity
@@ -333,19 +336,13 @@ class Simulation:
    def read_surface_exchange(self, id: int):
        """Latest step's wall/aperture (Fx,Fy,Tz) exchange, not total nozzle force.

-        Supports SurfaceActuation and Jet-driven bodies, including zero-amplitude
-        apertures. Passive bodies without an aperture are rejected.
        Unlike read_body this is not accumulated/time-averaged. It resets after
        geometry sync or checkpoint load; advance before interpreting it.
        """
-        obj = self.bodies.get(id)
-        curved = self.field.curved
-        has_aperture = (curved.aperture is not None
-                        and np.any(curved.aperture & (curved.body_id == id)))
-        if obj.surface_actuation is None and not has_aperture:
+        if self.bodies.get(id).surface_actuation is None:
            raise ValueError("Body has no surface actuation")
        self.stream.synchronize()
-        return curved.surface_exchange(id)
+        return self.field.curved.surface_exchange(id)

    @context_bound
    def read_body(self, id: int, *,
@@ -409,8 +406,15 @@ class Simulation:
        self.lbm_cfg.validate_runtime()
        self._assert_allocation_contract()
        arch = self._resolve_compile_arch()
-        self._module = compiler.build_module(self.lbm_cfg, "uniform.cu", arch=arch,
-                                             n_objects=expected_n_objects)
+        next_dir = compiler.generate_config(self.lbm_cfg, n_objects=expected_n_objects)
+        try:
+            next_ptx = compiler.compile_kernel(arch=arch, build_dir=next_dir)
+            next_module = compiler.load_module(next_ptx)
+        except Exception:
+            compiler.cleanup_build_dir(next_dir)
+            raise
+        old_dir = self._build_dir
+        self._build_dir, self._ptx_path, self._module = next_dir, next_ptx, next_module
        self._compiled_n_objects = int(expected_n_objects)

        # Reconnect field and stepper to new module
@@ -428,6 +432,7 @@ class Simulation:
        self.stepper._step_count = _prev_step_count

        self._assert_object_count_contract(expected_count=expected_n_objects)
+        compiler.cleanup_build_dir(old_dir)

    def recompile(self):
        """Re-generate config headers and recompile kernel.
@@ -446,21 +451,18 @@ class Simulation:
    @context_bound
    def initialize(self):
        """Initialize flow field and sync objects to GPU."""
-        self._assert_allocation_contract()
-        # Validate the complete geometry before flags, populations or modules
-        # change. Compact-list construction publishes no outputs on failure.
-        next_flags = self.bodies.build_flags(self.field.build_channel_flags())
-        if self.bodies.jets and self.bodies.count == 0:
-            raise ValueError("Jets need bodies with cut links")
-        self.bodies.build_compact_lists_for(self.bodies.objects, next_flags)
-
        # Recompile if objects were added after construction.
+        self._assert_allocation_contract()
        if self._read_generated_n_objects() != self.bodies.count:
            self.recompile()

-        self.field.flag = next_flags
+        self.field.flag = self.field.build_channel_flags()
+        if self.bodies.count > 0:
+            self.field.flag = self.bodies.build_flags(self.field.flag)
        self.field.upload_flags()

+        if self.bodies.jets and self.bodies.count == 0:
+            raise ValueError("Jets need bodies with cut links")
        self.stepper.initialize()
        if self.bodies.count > 0:
            self.bodies.sync_to_gpu(self.field, rebuild_flags=False)
@@ -704,6 +706,8 @@ class Simulation:
                self._module = None
                self._stream = None
            ctx.close()
+        compiler.cleanup_build_dir(getattr(self, "_build_dir", None))
+        self._build_dir = None
        self._closed = True

    def __enter__(self):
@@ -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()
@@ -6,14 +6,14 @@ import pycuda.driver as cuda
 import pytest

 import CelerisLab
-from CelerisLab.cuda import compiler
+from CelerisLab.cuda import compiler_v2
 from ._cases import make_sim


 def test_source_provenance():
    root = Path(__file__).resolve().parents[2] / "src/CelerisLab"
    assert Path(CelerisLab.__file__).resolve().parent == root
-    assert Path(compiler.kernel_path("uniform.cu")).resolve() == root / "lbm/kernels/uniform.cu"
+    assert Path(compiler_v2.kernel_path("kernel_v2.cu")).resolve() == root / "lbm/kernels/kernel_v2.cu"


 def test_two_contexts_interleaved_and_non_lifo_close():
@@ -21,7 +21,7 @@ def test_two_contexts_interleaved_and_non_lifo_close():
    first = make_sim(nx=32, ny=16)
    second = make_sim(nx=48, ny=24, streaming="esopull", shifted=True)
    try:
-        assert first._module is not second._module
+        assert first._build_dir != second._build_dir
        assert cuda.Context.get_current() == before
        first.initialize()
        second.initialize()
@@ -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
@@ -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])
@@ -126,7 +100,8 @@ class BuildContracts(unittest.TestCase):
            def work(nx, count):
                build = compiler.generate_config(LBMConfig(nx=nx), count, build_root=root)
                barrier.wait()
-                output = compiler.compile_kernel(build_dir=build)
+                # Compatibility form is context-local even without explicit path.
+                output = compiler.compile_kernel()
                data = json.loads(Path(output).read_text())
                self.assertEqual(data, {"nx": nx, "objects": count})
                metadata = json.loads(Path(output + ".json").read_text())
@@ -155,7 +130,7 @@ class BuildContracts(unittest.TestCase):
            compiler.cleanup_build_dir(a)
            compiler.cleanup_build_dir(b)
            with self.assertRaises(RuntimeError):
-                compiler.compile_kernel(build_dir=a)  # removed snapshot is never compiled
+                compiler.compile_kernel()

    def test_failed_compile_cannot_implicitly_load_previous_artifact(self):
        with tempfile.TemporaryDirectory() as root:
@@ -168,7 +143,8 @@ class BuildContracts(unittest.TestCase):
                with self.assertRaises(subprocess.CalledProcessError):
                    compiler.compile_kernel(build_dir=build)
            self.assertEqual(Path(previous).read_bytes(), old_bytes)
-            self.assertEqual(sorted(Path(build).glob("uniform-*.ptx")), [])  # no partial output
+            with self.assertRaisesRegex(RuntimeError, "No compiled PTX"):
+                compiler.load_module()
            compiler.cleanup_build_dir(build)


@@ -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(int(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"):
@@ -74,14 +74,14 @@ def test_evolved_ghost_snapshot_and_physical_download():
    from .test_refinement_three_level_multipatch import host_module
    host = host_module()
    storage = {}
-    host.compiler.build_module.return_value.get_global.side_effect = lambda name: (name, 12 if name == "d_block_channel" else 20)
+    host.compiler.load_module.return_value.get_global.side_effect = lambda name: (name, 12 if name == "d_block_channel" else 20)
    host.cuda.mem_alloc.side_effect = lambda size: Mock()
    host.cuda.memcpy_htod.side_effect = lambda ptr, a: storage.__setitem__(id(ptr), np.array(a, copy=True))
    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]
@@ -96,7 +96,6 @@ def test_evolved_ghost_snapshot_and_physical_download():
        arrays[0][0, 0, 0] = np.nan
        with pytest.raises(ValueError, match="finite"):
            backend.initialize(*arrays)
-        assert backend._levels[0].kernel == host.compiler.build_module.return_value.get_function("BlockChannelStep")
-        assert [call.kwargs["block_root_bc"] for call in host.compiler.build_module.call_args_list] == [2, 0]
+        assert backend._levels[0].kernel == host.compiler.load_module.return_value.get_function("BlockChannelStep")
    finally:
        backend.close()
@@ -1,79 +0,0 @@
-"""CPU-only contract tests for run_dfg_re20. Not CUDA or DFG acceptance evidence."""
-
-import sys
-from pathlib import Path
-import unittest
-
-sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "validation"))
-import run_dfg_re20 as v  # noqa: E402
-import run_refined_dfg as rr  # noqa: E402
-
-h, _ = rr.helpers(rr.DEFAULT_SOURCE)
-
-
-def rows(values, tstar_end=v.TSTAR_MAX):
-    n = int(round(tstar_end / v.SAMPLE_TSTAR))
-    return [dict(tstar=(i + 1) * v.SAMPLE_TSTAR, **values(i)) for i in range(n)]
-
-
-class Re20Contract(unittest.TestCase):
-    def test_lattice_parameters_and_bounds(self):
-        root, uniform = v.lattice_parameters(40), v.lattice_parameters(80)
-        self.assertAlmostEqual(root["tau"], 0.56, places=12)
-        self.assertAlmostEqual(uniform["tau"], 0.62, places=12)
-        self.assertEqual((root["steps"], root["interval"]), (240000, 2000))
-        self.assertEqual((uniform["steps"], uniform["interval"]), (480000, 4000))
-        self.assertAlmostEqual(v.plan()["refined_fine_tau"], 0.62, places=12)
-
-    def test_config_only_changes_viscosity(self):
-        base = v._re100_config(h, 40, "SRT", "none")
-        cfg, body, p = v.config(h, 40, "SRT")
-        self.assertAlmostEqual(cfg["physics"]["viscosity"], 0.01 * 40 / 20, places=15)
-        self.assertEqual((p["re"], p["viscosity"]), (20.0, cfg["physics"]["viscosity"]))
-        base[0]["physics"]["viscosity"] = cfg["physics"]["viscosity"]
-        self.assertEqual(base[0], cfg)
-        self.assertEqual(base[1], body)
-        with self.assertRaisesRegex(ValueError, "no Jets"):
-            v.config(h, 40, "MRT", "zero")
-
-    def test_units(self):
-        s = v.sample([2.0, -0.5], 4, 40, 3.0)
-        den = rr.SPEED**2 * 40 / 2
-        self.assertAlmostEqual(s["cd"], 2.0 / 4 / den)
-        self.assertAlmostEqual(s["cl"], -0.5 / 4 / den)
-        self.assertAlmostEqual(s["p_diff"], 3.0 * 0.04)
-        self.assertEqual(s["dp_scaled"], 3.0)
-
-    def test_steady_and_verdict(self):
-        inside = dict(cd=5.58, cl=0.0106, p_diff=0.1174)
-        out = v.summarize(rows(lambda i: inside))
-        self.assertEqual((out["status"], out["steady"], out["window_samples"]),
-                         ("WITHIN_INTERVALS", True, 21))
-        self.assertTrue(out["cd_positive"])
-        self.assertAlmostEqual(out["edge_distance"]["cl"], 0.0002)
-        self.assertTrue(all(out["verdict"].values()))
-        low = v.summarize(rows(lambda i: dict(inside, cl=0.0100)))
-        self.assertEqual(low["status"], "OUTSIDE_INTERVALS")
-        self.assertFalse(low["verdict"]["cl"])
-
-    def test_slow_drift_gives_no_verdict(self):
-        # Range 2e-5 passes (limit 6e-5); slope * window 2e-5 exceeds 1.2e-5.
-        out = v.summarize(rows(lambda i: dict(cd=5.58, cl=0.0106 + 1e-6 * i, p_diff=0.1174)))
-        self.assertEqual((out["status"], out["verdict"]), ("NOT_STEADY", None))
-        self.assertLessEqual(out["ranges"]["cl"], out["range_limits"]["cl"])
-        self.assertGreater(out["drifts"]["cl"], out["slope_limits"]["cl"])
-
-    def test_noise_range(self):
-        quiet = v.summarize(rows(lambda i: dict(cd=5.58, cl=0.0106 + 2e-5 * (i % 2), p_diff=0.1174)))
-        self.assertTrue(quiet["steady"])  # within the range limit, no trend
-        noisy = v.summarize(rows(lambda i: dict(cd=5.58, cl=0.0106 + 1e-4 * (i % 2), p_diff=0.1174)))
-        self.assertEqual(noisy["status"], "NOT_STEADY")
-        self.assertGreater(noisy["ranges"]["cl"], noisy["range_limits"]["cl"])
-
-    def test_incomplete_run_gives_no_verdict(self):
-        out = v.summarize(rows(lambda i: dict(cd=5.58, cl=0.0106, p_diff=0.1174), tstar_end=30))
-        self.assertEqual((out["status"], out["verdict"]), ("INCOMPLETE", None))
-
-
-if __name__ == "__main__":
-    unittest.main()
@@ -1,65 +0,0 @@
-"""The public examples run all-blocked: their level tiles must reach the device unchanged.
-
-Host only: a context whose activation raises proves construction (layouts, tables,
-boundary checks) succeeded up to the first CUDA call.
-"""
-import ast
-from dataclasses import replace
-from pathlib import Path
-import unittest
-from unittest.mock import Mock
-
-from CelerisLab.body.geometry.circle import CircleGeometry
-from CelerisLab.body.objects import SimObject
-from CelerisLab.config import LBMConfig
-from CelerisLab.lbm.refinement_stepper import FixedPatchStepper
-
-EXAMPLES = Path(__file__).resolve().parents[2] / "examples"
-
-
-def literal(name, constant):
-    """Module-level literal from an example, read without importing it (no pycuda)."""
-    tree = ast.parse((EXAMPLES / name).read_text())
-    for node in tree.body:
-        if isinstance(node, ast.Assign):
-            for target in node.targets:
-                names = target.elts if isinstance(target, ast.Tuple) else [target]
-                for i, t in enumerate(names):
-                    if isinstance(t, ast.Name) and t.id == constant:
-                        value = node.value.elts[i] if isinstance(target, ast.Tuple) else node.value
-                        return ast.literal_eval(value)
-    raise KeyError(constant)
-
-
-def forbidden():
-    return Mock(activate=Mock(side_effect=AssertionError("CUDA reached")), sm_arch="sm_70")
-
-
-class ExampleTiles(unittest.TestCase):
-    def test_fixed_patch_jet_tiles(self):
-        bounds, blocks = literal("fixed_patch_jet.py", "BOUNDS"), literal("fixed_patch_jet.py", "LEVEL_BLOCKS")
-        width, amplitude = literal("fixed_patch_jet.py", "WIDTH"), literal("fixed_patch_jet.py", "AMPLITUDE")
-        cfg = LBMConfig(nx=48, ny=48, viscosity=.1, velocity=0., wall_slot_width=width,
-                        wall_normal_velocity=amplitude, y_wall_bc="on_site_velocity",
-                        top_wall_bc="reservoir")
-        with self.assertRaisesRegex(AssertionError, "CUDA reached"):
-            FixedPatchStepper(cfg, context=forbidden(), coarse_boundary="slot_reservoir",
-                              refinements=[bounds], level_blocks=[tuple(b) for b in blocks])
-
-    def test_fixed_patch_circle_default_tiles(self):
-        bounds = literal("fixed_patch_circle.py", "BOUNDS")
-        nx, ny = literal("fixed_patch_circle.py", "NX"), literal("fixed_patch_circle.py", "NY")
-        center, radius = literal("fixed_patch_circle.py", "CENTER"), literal("fixed_patch_circle.py", "RADIUS")
-        body = SimObject(0, geometry=CircleGeometry(*center, radius), center=center, radius=radius)
-        periodic = LBMConfig(nx=nx, ny=ny, viscosity=.1)
-        slot = replace(periodic, velocity=0, wall_normal_velocity=.001, wall_slot_width=8,
-                       y_wall_bc="on_site_velocity", top_wall_bc="reservoir")
-        for mode, cfg in (("periodic", periodic), ("slot_reservoir", slot)):
-            with self.subTest(mode=mode), self.assertRaisesRegex(AssertionError, "CUDA reached"):
-                FixedPatchStepper(cfg, context=forbidden(), coarse_boundary=mode,
-                                  refinements=[bounds], level_blocks=[(12, 8), (16, 20)],
-                                  level_objects=[(), (body,)])
-
-
-if __name__ == "__main__":
-    unittest.main()
@@ -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,
@@ -17,10 +16,8 @@ from run_jet_circle_cv import (
    case,
    state,
    cv,
-    cv_from_macros,
    aperture_probe,
    measured_aperture_flux,
-    PIN,
    verify,
 )

@@ -31,39 +28,6 @@ def eq(rho, u, v):


 class Host(unittest.TestCase):
-    def test_public_macros_pressure_advection_and_cropped_frames(self):
-        for h, origin, shape, rect in (
-            (.5, (0., 0.), (48, 64), (5., 4., 25., 20.)),
-            (.5, (.25, .5), (48, 64), (5.25, 4., 25.25, 20.)),
-            (.25, (.375, .75), (96, 128), (5.125, 4., 25.125, 20.)),
-        ):
-            y, x = np.indices(shape)
-            x = origin[0] + h * (x + .5)
-            k, u, v = 1e-5, .02, -.01
-            rho = 1 + 3 * k * x  # p=(rho-1)/3=k*x
-            ux, uy, fluid = np.full(shape, u), np.full(shape, v), np.ones(shape, bool)
-            result = cv_from_macros(rho, ux, uy, fluid, origin, rect, .004, h)
-            expected = 320 * np.array([3*k*u, k + 3*k*u*u, 3*k*u*v])
-            np.testing.assert_allclose(result[1], expected, rtol=1e-11, atol=1e-13)
-            np.testing.assert_allclose(result, cv(eq(rho, u, v), fluid, origin, rect, .004, h), atol=1e-12)
-            x0, y0, x1, y1 = np.rint((np.array(rect)-np.tile(origin, 2))/h).astype(int)
-            selection = np.s_[y0-2:y1+2, x0-2:x1+2]
-            cropped_origin = np.asarray(origin) + h*np.array([x0-2, y0-2])
-            cropped = cv_from_macros(rho[selection], ux[selection], uy[selection],
-                                    fluid[selection], cropped_origin, rect, .004, h)
-            np.testing.assert_array_equal(cropped, result)
-
-    def test_public_macros_full_normal_viscous_stress(self):
-        y, x = np.indices((48, 64))
-        x = (x + .5) * .5
-        rho, ux, uy, fluid = np.ones_like(x), 1e-4*x*x, np.zeros_like(x), np.ones(x.shape, bool)
-        args = (rho, ux, uy, fluid, (0., 0.), (5., 4., 25., 20.))
-        _, viscous = cv_from_macros(*args, .004)
-        _, inviscid = cv_from_macros(*args, 0.)
-        np.testing.assert_allclose(viscous-inviscid, [0, -4*.004*1e-4*320, 0], atol=1e-13)
-        with self.assertRaisesRegex(ValueError, "matching 2D"):
-            cv_from_macros(rho, ux, uy[:-1], fluid, (0, 0), (5, 4, 25, 20), .004)
-
    def test_descriptor_and_uniform_closed_flux(self):
        from CelerisLab.lbm.descriptors import D2Q9_EX, D2Q9_EY

@@ -168,13 +132,7 @@ 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__":
@@ -188,55 +188,6 @@ def jet_case(device, jets):
    return field, bodies


-def test_public_surface_exchange_for_jet_preserves_aperture_at_zero_and_reverse(device):
-    from CelerisLab.simulation import Simulation
-    jet = Jet(Sector(CENTER, 0., .6, 3.), Radial(CENTER, inward=False), "quartic", 2e-3)
-    field, bodies = jet_case(device, [jet])
-    sim = SimpleNamespace(bodies=bodies, field=field, _initialized=True,
-                          stream=SimpleNamespace(synchronize=device.synchronize))
-    cl = field.curved
-    assert bodies.get(0).surface_actuation is None
-    aperture, velocity = cl.aperture, cl.surface_velocity.copy()
-    assert aperture.any() and (~aperture).any()
-    # Synthetic per-link exchanges test readback/splitting, not kernel physics.
-    values = np.arange(cl.count * 3, dtype=np.float32).reshape(-1, 3)
-    device.htod(cl.link_exchange_gpu, values)
-    for amplitude in (2e-3, 0., -1e-3):
-        Simulation.set_jet_amplitude(sim, 0, amplitude)
-        result = Simulation.read_surface_exchange(sim, 0)
-        assert cl.aperture is aperture
-        np.testing.assert_array_equal(aperture, cl.jet_id >= 0)
-        np.testing.assert_allclose(cl.surface_velocity, velocity * (amplitude / 2e-3))
-        for name, mask in (("wall", ~aperture), ("aperture", aperture)):
-            np.testing.assert_array_equal(result[name], values[mask].sum(axis=0, dtype=np.float64))
-
-
-def test_public_surface_exchange_keeps_legacy_and_passive_guards(device):
-    from CelerisLab.simulation import Simulation
-    field = make_field(device)
-    bodies = manager(field, [circle(SurfaceActuation(0., .6, .002), radius=2.)])
-    bodies.sync_to_gpu(field)
-    sim = SimpleNamespace(bodies=bodies, field=field,
-                          stream=SimpleNamespace(synchronize=device.synchronize))
-    for value in Simulation.read_surface_exchange(sim, 0).values():
-        np.testing.assert_array_equal(value, 0.)
-    field.curved.free_gpu_columns()
-    with pytest.raises(RuntimeError, match="diagnostic is allocated"):
-        Simulation.read_surface_exchange(sim, 0)
-
-    # An exchange buffer elsewhere in the scene must not admit a passive body.
-    for jets in ([], [Jet(Sector(CENTER, 0., .6, 3.), Radial(CENTER))]):
-        field, bodies = jet_case(device, jets)
-        passive = bodies.add(circle(center=(2., 3.), radius=.6))
-        bodies.sync_to_gpu(field)
-        sim.bodies, sim.field = bodies, field
-        with pytest.raises(ValueError, match="Body has no surface actuation"):
-            Simulation.read_surface_exchange(sim, passive)
-        if not jets:
-            with pytest.raises(ValueError, match="Body has no surface actuation"):
-                Simulation.read_surface_exchange(sim, 0)
-
-
 def test_manager_passes_true_hits_and_reuploads_only_velocity(device):
    # CPU memory double only: checks host/device bookkeeping, not GPU numerics.
    jet = Jet(Sector(CENTER, 0., .6, 3.), Radial(CENTER, inward=False), "quartic", 2e-3)
@@ -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")
@@ -135,6 +135,6 @@ def test_d2_entrypoint_compiles_in_isolation(tmp_path, model, shift, storage):
            source=re.sub(r"(#define\s+"+key+r"\s+)\S+",lambda match: match[1]+str(value),source)
        path.write_text(source)
    result=subprocess.run([nvcc,"-ptx","-arch=sm_70","-std=c++17",
-                           str(copy/"uniform.cu"),"-o",str(tmp_path/"kernel.ptx")],
+                           str(copy/"kernel_v2.cu"),"-o",str(tmp_path/"kernel.ptx")],
                          capture_output=True,text=True)
    assert result.returncode == 0, result.stderr
@@ -9,7 +9,7 @@ import pytest

 import CelerisLab
 from CelerisLab.config import LBMConfig, load_lbm_config
-from CelerisLab.cuda import compiler
+from CelerisLab.cuda import compiler_v2 as compiler
 from CelerisLab.common.checkpoint import save_checkpoint, load_checkpoint
 from .test_numerical_operators import compile_run
 from .test_state_regressions import device, make_field, manager
@@ -18,7 +18,7 @@ from .test_state_regressions import device, make_field, manager
 def test_planar_helper_moments_and_known_populations(tmp_path):
    root = Path(__file__).resolve().parents[2]
    assert Path(CelerisLab.__file__).resolve() == root/'src/CelerisLab/__init__.py'
-    assert Path(compiler.kernel_path('uniform.cu')).resolve() == root/'src/CelerisLab/lbm/kernels/uniform.cu'
+    assert Path(compiler.kernel_path('kernel_v2.cu')).resolve() == root/'src/CelerisLab/lbm/kernels/kernel_v2.cu'
    lines = compile_run(tmp_path, 'planar_velocity.cpp', dict(WALL_NORMAL_VELOCITY='0.0f'))
    cx = np.array([0,1,-1,0,0,1,-1,1,-1])
    cy = np.array([0,0,0,1,-1,1,-1,-1,1])
@@ -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):
@@ -29,7 +29,7 @@ def backend(**options):
            name=name, side_effect=lambda *a, **kw: calls.append((name, a, kw)))
        return module

-    host.compiler.build_module.side_effect = lambda *a, **k: load(None)
+    host.compiler.load_module.side_effect = load
    host.cuda.memcpy_htod.side_effect = lambda ptr, a: storage.__setitem__(id(ptr), np.array(a, copy=True))
    host.cuda.memcpy_dtoh.side_effect = lambda a, ptr: np.copyto(a, storage[id(ptr)])
    cfg = options.pop('cfg', CFG)
@@ -25,7 +25,7 @@ def backend(observe=True, obj=None):
    module = Mock()
    module.get_global.return_value = (Mock(), 20)
    module.get_function.side_effect = lambda name: Mock(side_effect=lambda *a, **k: calls.append((name, a, k)))
-    host.compiler.build_module.return_value = module
+    host.compiler.load_module.return_value = module
    host.cuda.mem_alloc.side_effect = lambda n: Mock(size=n)
    host.cuda.memcpy_dtoh.side_effect = lambda array, pointer: array.fill(0)
    ctx = Mock(activate=nullcontext, sm_arch='sm_70')
@@ -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 +141,28 @@ 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):
-    """The frozen manifest verify_source selects for (collision, observation_mode).
-
-    Source identity is owned by test_source_pin; this reads no checkout files.
-    """
-    return r.source_manifest(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"):
+def pilot_fixture(path, observation_mode="window"):
    """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))
-    selection = dict(case_selection=case_selection, uniform_diameter=uniform_diameter, placement=placement)
+    manifest = (r.verify_source(r.DEFAULT_SOURCE, "MRT", "window")
+                if observation_mode == "window" else
+                json.loads((r.HERE / "data/refined_dfg/source_manifest_mrt.json").read_text()))
    (path / "plan.json").write_text(
        json.dumps(
            dict(
                source_manifest=manifest,
-                **selection,
                collision="MRT",
-                jet_scenario=jet_scenario,
                observation_mode=observation_mode,
-                bounds_root_edge=list(r.PLACEMENTS[placement]),
+                bounds_root_edge=list(r.BOUNDS),
                runner_sha256=r.runner_hash(),
            )
        )
    )
-    for case, diameter in r.selected_cases(case_selection, uniform_diameter):
+    for case, diameter in (("uniform", 80), ("refined", 40)):
        dest = path / case
        dest.mkdir()
        interval = round(0.02 * diameter / r.SPEED)
@@ -224,9 +189,7 @@ def pilot_fixture(path, observation_mode="window", jet_scenario="none", case_sel
            json.dumps(
                dict(
                    case=case,
-                    **selection,
                    collision="MRT",
-                    jet_scenario=jet_scenario,
                    observation_mode=observation_mode,
                    mode="pilot",
                    status="pilot_complete",
@@ -243,9 +206,7 @@ def pilot_fixture(path, observation_mode="window", jet_scenario="none", case_sel
            json.dumps(
                dict(
                    case=case,
-                    **selection,
                    collision="MRT",
-                    jet_scenario=jet_scenario,
                    observation_mode=observation_mode,
                    mode="pilot",
                    step=interval,
@@ -380,7 +341,7 @@ 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():
@@ -390,7 +351,7 @@ 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")

@@ -490,169 +451,6 @@ def test_window_contract_rejection():
    assert not backend.events


-def test_public_jet_configuration_and_geometry():
-    for diameter, center, radius in ((40, (80.5, 81), 20), (80, (160, 160.5), 40)):
-        cfg, _, _ = r.config(h, diameter, "MRT", "fixed")
-        assert not cfg["method"]["ddf_shifting"] and not cfg["method"]["les"]["enabled"]
-        jets = r.public_jets(center, radius, "fixed")
-        assert [j.amplitude for j in jets] == [.001, -.001]
-        assert all(j.field.inward is False and j.profile == "parabolic" for j in jets)
-        assert all(j.region.r_max == radius * 1.005 for j in jets)
-        assert all(j.amplitude == 0 for j in r.public_jets(center, radius, "zero"))
-    cfg, _, _, host = r.host_geometry(r.DEFAULT_SOURCE, h, "MRT", "fixed")
-    assert not cfg.ddf_shifting and len(host.boundary_cells) > 0
-    assert r.public_jets((0, 0), 1, "none") == ()
-    with unittest.TestCase().assertRaises(ValueError):
-        r.config(h, 40, "SRT", "fixed")
-
-
-def test_public_jet_reversal_boundary_and_windows():
-    from types import SimpleNamespace
-
-    calls = []
-    handle = SimpleNamespace(set_jet_amplitude=lambda i, a: calls.append((i, a)))
-    for diameter in (40, 80):
-        boundary = round(250 * diameter / r.SPEED)
-        assert r.jet_interval(handle, "fixed", boundary - 3, 80, diameter) == (3, None)
-        switch = round(300 * diameter / r.SPEED)
-        assert r.jet_interval(handle, "reverse", switch - 3, 80, diameter) == (3, None)
-        assert not calls
-        n, event = r.jet_interval(handle, "reverse", switch, 80, diameter)
-        assert n == 80 and event["step"] == switch and event["tstar"] == 300
-        assert calls == [(0, -.001), (1, .001)]
-        calls.clear()
-        assert r.jet_interval(handle, "reverse", switch + 80, 80, diameter) == (80, None)
-        assert r.jet_interval(handle, "fixed", switch, 80, diameter) == (80, None)
-        assert not calls
-    rows = [dict(tstar=t, tstar_force=t - .5, cd=2.0, cl=-.1) for t in range(251, 306)]
-    windows = r.jet_diagnostics(rows, "reverse")
-    assert len(windows) == 6 and all(w["complete"] for w in windows)
-    assert all(w["cd"]["mean"] == 2 and np.isclose(w["cl"]["mean"], -.1) for w in windows)
-    assert windows[-1]["covered_tstar"] == 5
-    with unittest.TestCase().assertRaisesRegex(ValueError, "crosses"):
-        r.jet_diagnostics([dict(tstar=250.5, tstar_force=250, cd=1, cl=0)], "fixed")
-    assert r.plan(h, "MRT", "window", "reverse")["modes"]["full_tstar"] == 305
-
-
-def test_public_jet_source_and_pilot_separation():
-    from tempfile import TemporaryDirectory
-
-    with TemporaryDirectory() as tmp:
-        path = Path(tmp)
-        manifest = pilot_fixture(path, jet_scenario="fixed")
-        assert manifest["source_capture"].startswith("current checkout")
-        assert len(manifest["checkout_revision"]) == 40
-        assert r.verify_pilot(path, manifest, "MRT", "window", "fixed") == 3606.0
-        for scenario in ("none", "zero", "reverse"):
-            with unittest.TestCase().assertRaisesRegex(ValueError, "Jet scenario"):
-                r.verify_pilot(path, manifest, "MRT", "window", scenario)
-        for relative in ("uniform/summary.json", "refined/ready.json"):
-            receipt = path / relative
-            record = json.loads(receipt.read_text())
-            receipt.write_text(json.dumps(dict(record, jet_scenario="zero")))
-            with unittest.TestCase().assertRaises(ValueError):
-                r.verify_pilot(path, manifest, "MRT", "window", "fixed")
-            receipt.write_text(json.dumps(record))
-    with unittest.TestCase().assertRaises(ValueError):
-        r.verify_source(r.DEFAULT_SOURCE, "MRT", "last_base_step", "fixed")
-
-
-def test_cv_snapshot_common_units_and_window_endpoints():
-    records = []
-    for refined, shape, origin, diameter, impulse in (
-        (True, (240, 568), (38., 22.), 40, [4., -8.]),
-        (False, (330, 1761), (.25, .5), 80, [16., -32.]),
-        (False, (658, 3521), (.375, .75), 160, [64., -128.]),
-    ):
-        rho, ux, uy, fluid = np.ones(shape), np.full(shape, .01), np.zeros(shape), np.ones(shape, bool)
-        begin, n = round(290*diameter/r.SPEED), round(.02*diameter/r.SPEED)
-        record = r.cv_snapshot(rho, ux, uy, fluid, origin, refined, begin, n, diameter, impulse)
-        records.append(record)
-        np.testing.assert_allclose(record["outward_flux"], 0, atol=1e-12)
-        assert r.cv_selected(begin, diameter, "full") and not r.cv_selected(begin-n, diameter, "full")
-        end = round(300*diameter/r.SPEED)
-        assert r.cv_selected(end, diameter, "full") and not r.cv_selected(end+n, diameter, "full")
-        assert r.cv_selected(n, diameter, "pilot")
-        assert sum(r.cv_selected(step, diameter, "full") for step in range(begin-n, end+n+1, n)) == 501
-    for key in ("time_root", "interval_start_root", "interval_dt_root", "interval_impulse_root", "inventory"):
-        for record in records[1:]:
-            np.testing.assert_allclose(records[0][key], record[key], rtol=0, atol=1e-10)
-    assert records[0]["interval_dt_root"] == 80 and np.isclose(records[0]["tstar"], 290.02)
-    np.testing.assert_array_equal(records[0]["interval_impulse_root"], [4, -8])
-
-
-def test_cv_pilot_mode_and_helper_provenance():
-    from tempfile import TemporaryDirectory
-
-    manifest = r.verify_source(r.DEFAULT_SOURCE, "MRT", "window", "fixed", True)
-    assert "tests/validation/run_jet_circle_cv.py" in manifest["sha256"]
-    with TemporaryDirectory() as tmp:
-        path = Path(tmp)
-        old = pilot_fixture(path, jet_scenario="fixed")
-        with unittest.TestCase().assertRaisesRegex(ValueError, "CV observation mode"):
-            r.verify_pilot(path, old, "MRT", "window", "fixed", True)
-        for relative in ("plan.json", "uniform/summary.json", "refined/summary.json",
-                         "uniform/ready.json", "refined/ready.json"):
-            file = path / relative
-            record = json.loads(file.read_text())
-            record.update(observe_cv=True, cv_samples=250)
-            if relative == "plan.json":
-                record["source_manifest"] = manifest
-            file.write_text(json.dumps(record))
-        assert r.verify_pilot(path, manifest, "MRT", "window", "fixed", True) == 3606
-
-
-def test_compact_geometry_and_cv_stencils():
-    from CelerisLab.lbm.refinement import ACTIVE
-    from CelerisLab.lbm.descriptors import SOLID
-
-    _, pair, _, host = r.host_geometry(r.DEFAULT_SOURCE, h, "MRT", "fixed", "compact")
-    assert pair.fine_shape == (168, 168) and tuple(pair.fine_origin) == (46, 46)
-    fluid = (pair.fine_kind == ACTIVE) & ((host.flags.reshape(pair.fine_shape) & SOLID) == 0)
-    rho, ux, uy = np.ones(pair.fine_shape), np.full(pair.fine_shape, .01), np.zeros(pair.fine_shape)
-    record = r.cv_snapshot(rho, ux, uy, fluid, pair.fine_origin, True, 1160000, 80, 40, [1, 2], "compact")
-    np.testing.assert_allclose(record["outward_flux"], 0, atol=1e-12)
-    stencil = np.zeros(pair.fine_shape, bool)
-    for rect in r.cv_contours(True, 40, "compact"):
-        x0, y0, x1, y1 = np.rint((rect - np.tile(pair.fine_origin, 2))/.5).astype(int)
-        stencil[y0-2:y1+2, x0-2:x0+2] = stencil[y0-2:y1+2, x1-2:x1+2] = True
-        stencil[y0-2:y0+2, x0-2:x1+2] = stencil[y1-2:y1+2, x0-2:x1+2] = True
-    assert fluid[stencil].all() and not stencil.ravel()[host.transfer_fine_cells].any()
-
-
-def test_d160_config_and_single_case_receipts():
-    from tempfile import TemporaryDirectory
-    from unittest.mock import patch
-
-    cfg, _, p = r.config(h, 160, "MRT", "fixed")
-    assert (p["nx"], p["ny"], p["center"], p["radius"]) == (3521, 658, [320, 320.5], 80)
-    assert p["viscosity"] == .016 and p["mean_speed"] == .01 and not cfg["method"]["ddf_shifting"]
-    assert r.uniform_origin(160) == (.375, .75)
-    np.testing.assert_array_equal(r.cv_contours(False, 160), r.CV_CONTOURS + [.125, 0, .125, 0])
-    for scenario, expected_exit in (("fixed", 0), ("zero", 2)):
-        with TemporaryDirectory() as tmp:
-            path = Path(tmp)
-            manifest = pilot_fixture(path, jet_scenario=scenario, case_selection="uniform", uniform_diameter=160)
-            assert r.verify_pilot(path, manifest, "MRT", "window", scenario, False, "uniform", 160) == 1803
-            for selection, diameter, placement in (("both", 160, "wide"), ("uniform", 80, "wide"), ("uniform", 160, "compact")):
-                with unittest.TestCase().assertRaises(ValueError):
-                    r.verify_pilot(path, manifest, "MRT", "window", scenario, False, selection, diameter, placement)
-            # Synthetic dispatch/result check: no CUDA imports or execution.
-            output = path / "full"
-            argv = ["runner", "--collision", "MRT", "--exchange-window", "--jet-scenario", scenario,
-                    "--case", "uniform", "--uniform-diameter", "160", "--mode", "full",
-                    "--pilot-results", str(path), "--output", str(output), "--max-wall-seconds", "10", "--gpu-gates-approved"]
-            result = dict(case="uniform", healthy=True, periodic=scenario == "zero", jet_diagnostic_windows=[],
-                          status="driven_diagnostics_complete" if scenario == "fixed" else "periodic",
-                          reference_comparison=dict(reference_agreement=False))
-            with patch.object(sys, "argv", argv), patch.dict(r.os.environ, CUDA_VISIBLE_DEVICES="mock-no-gpu"), \
-                    patch.object(r, "run_case", return_value=result) as run:
-                assert r.main() == expected_exit and run.call_count == 1
-            comparison = json.loads((output / "comparison.json").read_text())
-            assert comparison["matched_case_pass"] is False and "refined_vs_uniform" not in comparison
-            assert comparison["status"].startswith("single_case_")
-
-
 if __name__ == "__main__":
    suite = unittest.TestSuite(
        unittest.FunctionTestCase(fn)
@@ -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 / "blocked.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()
@@ -22,13 +22,12 @@ def host_module():
    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 in (
-            'cuda','curved_links'))]
+            'cuda','block_stepper','curved_links'))]
    module=types.ModuleType('CelerisLab.lbm._test_host_refinement')
    module.__package__='CelerisLab.lbm'
    from CelerisLab.body.jets import surface_link_velocity
-    module.__dict__.update(cuda=Mock(),compiler=Mock(),
+    module.__dict__.update(cuda=Mock(),compiler=Mock(),MAX_GRID_DIM=65535,
                           surface_link_velocity=surface_link_velocity)
-    module.cuda.mem_get_info.return_value=(1<<40,1<<40)  # free-memory preflight passes
    exec(compile(tree,str(path),'exec'),module.__dict__)
    return module

@@ -174,10 +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):
@@ -194,9 +191,9 @@ def mock_backend(*, children=CHILDREN, bodies=False, fail_compile=False, fail_up
        gpu.get_function.side_effect=lambda name: Mock(name=name)
        gpu.get_global.side_effect=lambda name: (Mock(),20 if name=='d_params' else 16)
        return gpu
-    module.compiler.build_module.side_effect=lambda *a,**k: load(None)
+    module.compiler.load_module.side_effect=load
    if fail_compile:
-        module.compiler.build_module.side_effect=[load(None),load(None),RuntimeError('L2 compile failed')]
+        module.compiler.compile_kernel.side_effect=['first','second',RuntimeError('L2 compile failed')]
    if fail_upload:
        def upload(*args):
            if len(allocations)>20:
@@ -204,8 +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()
@@ -216,29 +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()

@@ -316,23 +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__':
@@ -86,7 +86,7 @@ class RuntimeChildRemap(unittest.TestCase):
            before = run.download()
            old_allocations = list(allocations)
            if failure == 'construction':
-                operation = patch.object(module.compiler, 'build_module', side_effect=RuntimeError('candidate compile'))
+                operation = patch.object(module.compiler, 'compile_kernel', side_effect=RuntimeError('candidate compile'))
            else:
                initialize = type(run).initialize
                def fail(candidate, *arrays):
@@ -54,15 +54,16 @@ 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.build_module.assert_not_called()
+        module.compiler.compile_kernel.assert_not_called()

    def test_switch_upload_only_then_raw_remap_keeps_live_velocity(self):
        run,module,allocations,storage,objects=ready();clone=None
@@ -1,4 +1,7 @@
 """CPU host contracts; mocked CUDA executes real lifecycle, not numerical kernels."""
+import ast
+import types
+from pathlib import Path
 from contextlib import nullcontext
 from dataclasses import replace
 import unittest
@@ -76,7 +79,7 @@ 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
+                  for m in old.leaf_masks)  # FP32 under numpy 1 and 2 promotion rules
        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))
@@ -128,21 +131,30 @@ 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)
-        module.compiler.build_module.assert_not_called()
+        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):
-        module = backend.host_module()  # single blocked level: FixedPatchStepper(refinements=[])
-        cuda, compiler = module.cuda, module.compiler
+        path = Path(backend.r.__file__).with_name('block_stepper.py')
+        tree = ast.parse(path.read_text())
+        tree.body = [n for n in tree.body if not (
+            isinstance(n, ast.Import) and any(a.name == 'pycuda.driver' for a in n.names)
+            or isinstance(n, ast.ImportFrom) and n.module == 'cuda')]
+        module = types.ModuleType('CelerisLab.lbm._test_block_host')
+        module.__package__ = 'CelerisLab.lbm'
+        cuda, compiler = Mock(), Mock()
+        module.__dict__.update(cuda=cuda,compiler=compiler)
+        exec(compile(tree,str(path),'exec'),module.__dict__)
+        cuda.mem_get_info.return_value=(10**9,10**9)
        cuda.mem_alloc.side_effect=lambda size: Mock()
        gpu=Mock();gpu.get_global.return_value=(Mock(),20)
-        compiler.build_module.return_value=gpu
+        compiler.load_module.return_value=gpu
        context=Mock(activate=nullcontext,sm_arch='sm_70')
+        layout=module.BlockLayout2D.build(16,16,4,4)
        cfg=replace(backend.CFG,nx=16,ny=16,ddf_shifting=True)
-        run=module.FixedPatchStepper(cfg,context=context,refinements=[],level_blocks=[(4,4)])
+        run=module.PeriodicBlockStepper(cfg,layout,context=context)
        storage={}
        cuda.memcpy_htod.side_effect=lambda p,a: storage.__setitem__(id(p),np.array(a,copy=True))
        cuda.memcpy_dtoh.side_effect=lambda a,p: np.copyto(a,storage[id(p)])
@@ -153,8 +165,7 @@ class ShiftedStorage(unittest.TestCase):
            self.assertTrue(raw.shifted)
            self.assertEqual(len(raw.values),1)
            self.assertTrue((raw.values[0][1]==np.float32(2**-35)).all())
-            (down,)=run.download()
-            np.testing.assert_array_equal(down,physical)
+            np.testing.assert_array_equal(run.download(),physical)
        finally: run.close()

    def test_passive_shifted_body_raw_remap_preserves_support(self):
@@ -36,10 +36,12 @@ def make_simulation(monkeypatch):
    sim = module.Simulation.__new__(module.Simulation)
    sim.ctx = Owner()
    sim._closed = False
+    sim._build_dir = "private-build"
    for name in ("stepper", "bodies", "field", "_module", "_stream"):
        setattr(sim, name, object())
    monkeypatch.setattr(module, "cuda", SimpleNamespace(
        Context=SimpleNamespace(synchronize=lambda: None)))
+    monkeypatch.setattr(module.compiler, "cleanup_build_dir", lambda path: None)
    return sim


@@ -55,7 +57,7 @@ def test_close_inside_activation_preserves_resources(monkeypatch):
    assert sim._closed and sim.ctx.is_closed


-@pytest.mark.parametrize("failure", ["synchronize", "detach"])
+@pytest.mark.parametrize("failure", ["synchronize", "detach", "directory"])
 def test_close_failure_is_retryable(monkeypatch, failure):
    sim = make_simulation(monkeypatch)
    if failure == "detach":
@@ -66,12 +68,17 @@ def test_close_failure_is_retryable(monkeypatch, failure):
            calls.append(args)
            if len(calls) == 1:
                raise RuntimeError(failure + " failed")
-        monkeypatch.setattr(module.cuda.Context, "synchronize", fail_once)
+        if failure == "synchronize":
+            monkeypatch.setattr(module.cuda.Context, "synchronize", fail_once)
+        else:
+            monkeypatch.setattr(module.compiler, "cleanup_build_dir", fail_once)
    with pytest.raises(RuntimeError, match="failed"):
        sim.close()
    assert not sim._closed
+    assert sim._build_dir == "private-build"
    sim.close()
    assert sim._closed and sim.ctx.is_closed
+    assert sim._build_dir is None
    sim.close()


@@ -1,218 +0,0 @@
-"""Host contract of FixedPatchStepper(refinements=[]): one blocked level (mocked driver).
-
-Per step: halo refresh -> static BFL (circles only) -> BlockStep with a null
-kind, one stream wait per step(n) call, NaN spare after initialize. An upload,
-launch, wait or download failure fails the instance and keeps its step count;
-close retains resources for retry when context activation fails.
-"""
-from contextlib import nullcontext
-from unittest.mock import MagicMock, Mock
-import unittest
-
-import numpy as np
-
-from CelerisLab.body.geometry.circle import CircleGeometry
-from CelerisLab.body.objects import SimObject
-from CelerisLab.config import LBMConfig
-from tests.unit.test_refinement_three_level_multipatch import host_module
-
-
-def circle(center=(15.5, 11.5), radius=4.3):
-    return SimObject(0, geometry=CircleGeometry(*center, radius), center=center, radius=radius)
-
-
-def backend(objects=(), failing_kernel=None, initialize=True):
-    host, log = host_module(), []
-    host.armed = False  # set True to make failing_kernel raise
-
-    def launch(name):
-        def run(*a, **k):
-            log.append((name, a))
-            if name == failing_kernel and host.armed:
-                raise RuntimeError(name + " launch failed")
-        return run
-
-    module = Mock()
-    module.get_global.return_value = (Mock(), 20)
-    module.get_function.side_effect = lambda name: Mock(side_effect=launch(name))
-    host.compiler.build_module.return_value = module
-    host.cuda.mem_alloc.side_effect = lambda size: Mock(size=size)
-    host.cuda.memcpy_htod.side_effect = lambda pointer, array: log.append(("upload", (pointer, array)))
-    run = host.FixedPatchStepper(LBMConfig(nx=32, ny=24, viscosity=.1),
-                                 context=Mock(activate=nullcontext, sm_arch="sm_70"),
-                                 refinements=[], level_blocks=[(12, 16)], level_objects=[objects])
-    run._stream.synchronize.side_effect = lambda: log.append(("sync", ()))
-    log.clear()
-    if initialize:
-        run.initialize(np.full(run._levels[0].shape, 1 / 9, np.float32))
-    return run, log, host
-
-
-def state():
-    return np.full((9, 24, 32), 1 / 9, np.float32)
-
-
-class SingleLevel(unittest.TestCase):
-    def test_spare_starts_nan_and_current_holds_state(self):
-        run, log, _ = backend()
-        level = run._levels[0]
-        uploads = {id(a[0]): a[1] for name, a in log if name == "upload"}
-        self.assertTrue(np.isnan(uploads[id(level.spare)]).all())
-        self.assertTrue(np.isfinite(level.layout.to_dense(uploads[id(level.current)])).all())
-
-    def test_launch_order_per_step(self):
-        for objects, order in (((), ["BlockHaloCopy", "BlockStep"]),
-                               ((circle(),), ["BlockHaloCopy", "BlockCurvedBoundary", "BlockStep"])):
-            with self.subTest(bodies=len(objects)):
-                run, log, _ = backend(objects)
-                log.clear()
-                run.step(2)
-                self.assertEqual([name for name, _ in log], order * 2 + ["sync"])
-                step = [a for name, a in log if name == "BlockStep"][0]
-                self.assertEqual(int(step[4]), 0)  # null kind: every core cell ACTIVE
-
-    def test_circle_solids_are_not_state(self):
-        run, _, _ = backend((circle(),))
-        solid = run._level_boundaries[0].tables["solid"]
-        self.assertTrue(solid.any())
-        np.testing.assert_array_equal(run._state[0], ~solid)
-
-    def test_initialize_upload_failure_fails_instance(self):
-        run, _, host = backend(initialize=False)
-        host.cuda.memcpy_htod.side_effect = RuntimeError("upload failed")
-        with self.assertRaisesRegex(RuntimeError, "upload failed"):
-            run.initialize(state())
-        with self.assertRaisesRegex(RuntimeError, "failed"):
-            run.step(1)
-
-    def test_launch_failure_fails_instance_and_keeps_step_count(self):
-        for kernel, objects in (("BlockHaloCopy", ()), ("BlockCurvedBoundary", (circle(),)),
-                                ("BlockStep", ())):
-            with self.subTest(kernel=kernel):
-                run, log, host = backend(objects, failing_kernel=kernel)
-                run.step(1)
-                host.armed = True
-                log.clear()
-                with self.assertRaisesRegex(RuntimeError, kernel + " launch failed"):
-                    run.step(2)
-                self.assertEqual(run.step_count, 1)
-                self.assertNotIn("sync", [name for name, _ in log])
-                with self.assertRaisesRegex(RuntimeError, "failed"):
-                    run.download()
-
-    def test_free_memory_preflight_before_stream_and_buffers(self):
-        for cfg, options in ((LBMConfig(nx=32, ny=24, viscosity=.1),
-                              dict(refinements=[], level_blocks=[(12, 16)])),
-                             (LBMConfig(nx=48, ny=48, viscosity=.02),  # every level counts
-                              dict(refinements=[[(6, 6, 26, 26)]], level_blocks=[(4, 4)] * 2))):
-            with self.subTest(depth=len(options["refinements"]) + 1):
-                host = host_module()
-                host.cuda.mem_get_info.return_value = (1024, 1 << 30)
-                with self.assertRaisesRegex(MemoryError, "exceed free device memory"):
-                    host.FixedPatchStepper(cfg, context=Mock(activate=nullcontext, sm_arch="sm_70"),
-                                           **options)
-                host.cuda.Stream.assert_not_called()
-                host.cuda.mem_alloc.assert_not_called()
-                host.compiler.build_module.assert_not_called()
-
-    def test_wait_failure_after_a_good_step_keeps_its_count(self):
-        run, _, _ = 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_final_wait_failure_fails_instance_and_keeps_step_count(self):
-        run, _, _ = backend()
-        run._stream.synchronize.side_effect = RuntimeError("device error")
-        with self.assertRaisesRegex(RuntimeError, "device error"):
-            run.step(3)
-        self.assertEqual(run.step_count, 0)
-        with self.assertRaisesRegex(RuntimeError, "failed"):
-            run.step(1)
-
-    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)
-
-        def roles(run, log):  # same launch order and buffer roles as three step(1) calls
-            level = run._levels[0]
-            tags = {id(level.current): "c", id(level.spare): "s"}
-            return [(n, tuple(tags.get(id(x), "-") for x in a)) for n, a in log if n != "sync"]
-        self.assertEqual(roles(many, log_many), roles(single, log_single))
-        self.assertIsNot(many._levels[0].current, many._levels[0].spare)
-        self.assertEqual((many.step_count, single.step_count), (3, 3))
-
-    def test_step_zero_launches_and_waits_for_nothing(self):
-        run, log, _ = backend()
-        log.clear()
-        run.step(0)
-        self.assertEqual((log, run.step_count), ([], 0))
-
-    def test_launch_failure_mid_batch_fails_without_waiting(self):
-        run, log, host = backend()
-        step = run._levels[0].kernel
-        calls = []
-
-        def failing(*args, **kwargs):
-            calls.append(1)
-            if len(calls) == 2:
-                raise RuntimeError("launch failure")
-            return step(*args, **kwargs)
-
-        run._levels[0].kernel = failing
-        log.clear()
-        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()
-
-    def test_initialize_rejects_bad_state_before_upload(self):
-        run, log, _ = backend(initialize=False)
-        good = state()
-        for bad in (good[:, :-1], np.where(np.arange(32) == 3, np.nan, good), -good):
-            with self.assertRaises(ValueError):
-                run.initialize(bad)
-        self.assertNotIn("upload", [name for name, _ in log])
-        run.initialize(good)
-        self.assertEqual([name for name, _ in log].count("upload"), 2)
-
-    def test_download_failure_fails_instance(self):
-        run, _, host = backend()
-        host.cuda.memcpy_dtoh.side_effect = RuntimeError("read failed")
-        with self.assertRaisesRegex(RuntimeError, "read failed"):
-            run.download()
-        for operation in (run.download, run.step):
-            with self.assertRaisesRegex(RuntimeError, "failed"):
-                operation()
-
-    def test_activation_failure_retains_resources_for_retry(self):
-        run, _, _ = backend()
-        allocations, stream = run._allocations[:], run._stream
-        unavailable = MagicMock()
-        unavailable.__enter__.side_effect = RuntimeError("activation failed")
-        run.ctx.activate = Mock(side_effect=[unavailable, nullcontext()])
-        with self.assertRaisesRegex(RuntimeError, "activation failed"):
-            run.close()
-        self.assertEqual(run._status, "failed")
-        self.assertEqual(run._allocations, allocations)
-        self.assertIs(run._stream, stream)
-        run.close()
-        self.assertEqual(run._status, "closed")
-        self.assertEqual(run._levels, [])
-        for allocation in allocations:
-            allocation.free.assert_called_once()
-
-
-if __name__ == "__main__":
-    unittest.main()
@@ -238,81 +238,6 @@ def test_overlapping_force_regions_rejected(device):
        bodies.build_compact_lists(bodies.build_flags(field.flag))


-@pytest.mark.parametrize("second_x,error", [(14., "unique cut-link writers"),
-                                           (17., "active fluid receivers")])
-def test_passive_overlap_rejected_before_publishing_lists(second_x, error):
-    cfg = LBMConfig(nx=32, ny=24)
-    cfg.validate()
-    bodies = ObjectManager(cfg.nx, cfg.ny, cfg.nz, cfg.nq, cfg)
-    for x in (14., second_x):
-        bodies.add(obj(x=x, y=12., r=4.3))
-    bodies.add(obj(x=4., y=4., r=2., is_sensor=True))
-    counts = np.full(bodies.count, 91, np.int32)
-    hits = []
-    flags = bodies.build_flags(np.full(cfg.nx * cfg.ny, FLUID, np.uint16))
-    for domain_flags in (flags, None):
-        with pytest.raises(ValueError, match=error):
-            bodies.build_compact_lists_for(bodies.objects, domain_flags,
-                                          sensor_cell_counts_out=counts, hits_out=hits)
-        np.testing.assert_array_equal(counts, 91)
-        assert hits == []
-
-
-@pytest.mark.parametrize("centers", [((10., 12.), (22., 12.)),
-                                    ((10.5, 12.), (19.5, 12.))])
-def test_separated_passive_bodies_keep_valid_writers(centers):
-    # The second case has a subcell physical gap with a resolved fluid column.
-    cfg = LBMConfig(nx=32, ny=24)
-    cfg.validate()
-    bodies = ObjectManager(cfg.nx, cfg.ny, cfg.nz, cfg.nq, cfg)
-    for x, y in centers:
-        bodies.add(obj(x=x, y=y, r=4.3))
-    flags = bodies.build_flags(np.full(cfg.nx * cfg.ny, FLUID, np.uint16))
-    indices, directions, _, ids, *_ = bodies.build_compact_lists(flags)
-    assert set(ids) == {0, 1}
-    assert np.all(flags[indices] & FLUID) and not np.any(flags[indices] & SOLID)
-    assert len(np.unique(indices.astype(np.uint64) * cfg.nq + directions)) == len(indices)
-
-
-@pytest.mark.parametrize("entry", ["sync", "initialize", "runtime_edit"])
-@pytest.mark.parametrize("second_x", [5., 6.])
-def test_passive_overlap_failure_keeps_live_state(device, entry, second_x):
-    from CelerisLab.simulation import Simulation
-    field = make_field(device)
-    bodies = manager(field, [obj(), obj(x=9., y=3., r=1., is_sensor=True)])
-    bodies.sync_to_gpu(field)
-    overlapping = obj(x=second_x)
-    if entry == "runtime_edit":
-        bodies.stage_add(overlapping)
-    else:
-        bodies.add(overlapping)
-    objects = bodies.objects
-    flags, curved, counts = field.flag.copy(), field.curved.fluid_idx.copy(), bodies.sensor_cell_counts.copy()
-    action = bodies.action.copy()
-    buffers = [(block, bytes(block.data), block.freed) for block in device.blocks]
-    writes = device.writes
-    sim = SimpleNamespace(bodies=bodies, field=field, lbm_cfg=field.cfg,
-                          _initialized=entry == "runtime_edit",
-                          _assert_allocation_contract=lambda: None,
-                          stream=SimpleNamespace(synchronize=device.synchronize))
-    with pytest.raises(ValueError, match="active fluid receivers|unique cut-link writers"):
-        if entry == "sync":
-            bodies.sync_to_gpu(field)
-        elif entry == "initialize":
-            Simulation.initialize(sim)
-        else:
-            Simulation.sync_bodies(sim)
-    assert bodies.objects == objects
-    assert bodies.has_pending_edit() == (entry == "runtime_edit")
-    assert sim._initialized == (entry == "runtime_edit")
-    assert device.writes == writes and len(device.blocks) == len(buffers)
-    assert all(bytes(block.data) == data and block.freed == freed for block, data, freed in buffers)
-    np.testing.assert_array_equal(field.flag, flags)
-    np.testing.assert_array_equal(field.curved.fluid_idx, curved)
-    np.testing.assert_array_equal(bodies.sensor_cell_counts, counts)
-    np.testing.assert_array_equal(bodies.action, action)
-
-
 def test_action_upload_and_scratch_are_pinned(device):
    field = make_field(device, streaming="esopull")
    bodies = manager(field, [obj(is_force_region=True)])
@@ -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.build_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):
@@ -30,7 +30,7 @@ original_module = gate.compile_module
 cache = {}
 def retain_compile(*args, **kwargs):
    result = original_compile(*args, **kwargs)
-    source = kwargs.get('source', 'uniform.cu')
+    source = kwargs.get('source', 'kernel_v2.cu')
    shutil.copyfile(result, a.output / (Path(source).stem + '.ptx'))
    metadata = Path(result + '.json')
    if metadata.exists(): shutil.copyfile(metadata, a.output / (Path(source).stem + '.ptx.json'))
@@ -1,4 +1,4 @@
-"""Single blocked level, FixedPatchStepper(refinements=[]): CPU contracts plus short GPU cases.
+"""Periodic body-free block backend: CPU contract doubles plus one short GPU case.

 Frozen GPU gates (32x24, 8 steps, positive low-Mach non-equilibrium state):
 finite cores; bit-identical 1x1, 2x2 and 4x2 splits; max |G - FP64 oracle|
@@ -11,8 +11,9 @@ Mass/momentum drift is reported, not gated.
 from contextlib import nullcontext
 from pathlib import Path
 import resource
+from threading import RLock
 import unittest
-from unittest.mock import Mock, patch
+from unittest.mock import MagicMock, Mock, patch

 import numpy as np
 import pycuda.driver as cuda
@@ -20,10 +21,10 @@ import pycuda.driver as cuda
 from CelerisLab.body.geometry.circle import CircleGeometry
 from CelerisLab.body.objects import SimObject
 from CelerisLab.config import LBMConfig
-from CelerisLab.cuda import compiler
-from CelerisLab.lbm import refinement_stepper as implementation
-from CelerisLab.lbm.blocks import NO_DONOR, BlockLayout2D, static_circle_tables
-from CelerisLab.lbm.refinement_stepper import FixedPatchStepper
+from CelerisLab.cuda import compiler_v2 as compiler
+from CelerisLab.lbm import block_stepper as implementation
+from CelerisLab.lbm.blocks import NO_DONOR, BlockLayout2D
+from CelerisLab.lbm.block_stepper import PeriodicBlockStepper
 from CelerisLab.lbm.descriptors import D2Q9_EX, D2Q9_EY

 ROOT = Path(__file__).resolve().parents[3]
@@ -111,78 +112,72 @@ def totals(g):
    return g.sum(), (CX[:, None, None] * g).sum(), (CY[:, None, None] * g).sum()


-def single(cfg=None, *, context, block=(12, 16), objects=(), **kw):
-    """One periodic blocked level (the former PeriodicBlockStepper capability)."""
-    return FixedPatchStepper(cfg or config(), context=context, refinements=[], level_blocks=[block],
-                             level_objects=[tuple(objects)], **kw)
-
-
 class CpuContracts(unittest.TestCase):
-    """No device: driver doubles prove rejection before allocation."""
+    """No device: driver doubles prove rejection before allocation and lifecycle."""

    def forbidden_context(self):
        return Mock(activate=Mock(side_effect=AssertionError("CUDA reached")), sm_arch="sm_70")

    def test_unsupported_inputs_rejected_before_cuda(self):
-        for cfg, kw in ((None, dict(block=None)),
-                        (None, dict(coarse_boundary="channel")),
-                        (None, dict(coarse_boundary="slot_reservoir")),
-                        (config(collision="MRT"), {}),
-                        (config(les_enabled=True), {}),
-                        (None, dict(explosion="projected_linear")),
-                        (None, dict(observe_raw_exchange=True)),
-                        (None, dict(observe_raw_exchange=True, observe_window_exchange=True)),
-                        (None, dict(level_jets=[(object(),)]))):
-            with self.subTest(kw=kw), self.assertRaises(ValueError):
-                single(cfg, context=self.forbidden_context(), **kw)
+        layout = BlockLayout2D.build(NY, NX, 12, 16)
+        cases = ((config(), BlockLayout2D.build(NY, NX, 12, 16, periodic=(True, False))),
+                 (config(), BlockLayout2D.build(NY, NX * 2, 12, 16)),
+                 (config(collision="MRT"), layout),
+                 (config(), "layout"))
+        for cfg, lay in cases:
+            with self.subTest(cfg=cfg.collision, layout=getattr(lay, "periodic", lay)):
+                with self.assertRaises(ValueError):
+                    PeriodicBlockStepper(cfg, lay, context=self.forbidden_context())
        moving = circle()
        moving.state.vx = .01
        build_links = CircleGeometry.build_cut_links
        for objects in ([moving], [circle((1.5, 11.5), 2.0)], [circle(), circle()]):
            with self.assertRaises(ValueError):
-                single(context=self.forbidden_context(), objects=objects)
+                PeriodicBlockStepper(config(), layout, context=self.forbidden_context(), objects=objects)
        for center, radius in (((16.0, 12.0), -.1), ((16.0, 12.0), -.5), ((15.5, 11.5), np.nan),
                               ((np.inf, 11.5), 4.3), ((15.5, np.nan), 4.3)):
            with self.subTest(center=center, radius=radius), self.assertRaises(ValueError):
-                single(context=self.forbidden_context(), objects=[circle(center, radius)])
-        with patch.object(implementation, "static_circle_tables") as prepare:
+                PeriodicBlockStepper(config(), layout, context=self.forbidden_context(),
+                                     objects=[circle(center, radius)])
+        with patch.object(implementation, "_static_circles") as prepare:
            with self.assertRaisesRegex(AssertionError, "CUDA reached"):  # body-free path
-                single(context=self.forbidden_context(), objects=iter(()))
+                PeriodicBlockStepper(config(), layout, context=self.forbidden_context(), objects=iter(()))
            prepare.assert_not_called()
-        with self.assertRaisesRegex(AssertionError, "CUDA reached"):
-            single(context=self.forbidden_context(), objects=[circle()])
        with patch.object(CircleGeometry, "build_cut_links",
                          lambda geometry, *a, **k: build_links(geometry, *a, **k)[1:]):
            with self.assertRaisesRegex(ValueError, "cover every fluid pull"):
-                single(context=self.forbidden_context(), objects=[circle()])
+                PeriodicBlockStepper(config(), layout, context=self.forbidden_context(),
+                                     objects=[circle()])
        with patch.object(implementation, "MAX_GRID_DIM", 3):
            with self.assertRaisesRegex(ValueError, "launch limits"):
-                single(context=self.forbidden_context())
+                PeriodicBlockStepper(config(), layout, context=self.forbidden_context())

    def test_memory_and_param_layout_rejected_before_allocation(self):
+        layout = BlockLayout2D.build(NY, NX, 12, 16)
        context = Mock(activate=nullcontext, sm_arch="sm_70")
        with patch.object(cuda, "mem_get_info", return_value=(1024, 1 << 30)), \
                patch.object(cuda, "Stream") as stream, patch.object(cuda, "mem_alloc") as alloc:
-            with self.assertRaisesRegex(MemoryError, "exceed free device memory"):
-                single(context=context, objects=[circle()])
+            with self.assertRaises(MemoryError):
+                PeriodicBlockStepper(config(), layout, context=context)
            stream.assert_not_called()
            alloc.assert_not_called()
        module = Mock()
        module.get_global.return_value = (Mock(), 16)
-        with patch.object(cuda, "Stream"), patch.object(cuda, "mem_get_info", return_value=(1 << 40, 1 << 40)), patch.object(compiler, "generate_config"), \
+        with patch.object(cuda, "mem_get_info", return_value=(1 << 30, 1 << 30)), \
+                patch.object(cuda, "Stream"), patch.object(compiler, "generate_config"), \
                patch.object(compiler, "compile_kernel") as compile_kernel, \
                patch.object(compiler, "cleanup_build_dir"), \
                patch.object(compiler, "load_module", return_value=module), \
                patch.object(cuda, "mem_alloc") as alloc, patch.object(cuda, "memcpy_htod") as upload:
            with self.assertRaisesRegex(RuntimeError, "layout mismatch"):
-                single(context=context)
-            self.assertEqual(compile_kernel.call_args.kwargs["source"], "blocked.cu")
+                PeriodicBlockStepper(config(), layout, context=context)
+            self.assertEqual(compile_kernel.call_args.kwargs["source"], "blocks.cu")
            alloc.assert_not_called()
            upload.assert_not_called()

    def test_static_circle_tables(self):
        layout = BlockLayout2D.build(NY, NX, 12, 16)
-        tables = static_circle_tables(layout, (circle(),))
+        tables = implementation._static_circles(layout, (circle(),))
        links = CircleGeometry(*CENTER, RADIUS).build_cut_links(NX, NY, domain_flags=dense_flags())
        self.assertEqual(len(tables["cell"]), len(links))
        np.testing.assert_array_equal(tables["q"], np.array([l.q for l in links], np.float32))
@@ -190,11 +185,85 @@ class CpuContracts(unittest.TestCase):
        self.assertTrue((tables["flags"][solid_cells] & 2).all())
        self.assertEqual(int(np.count_nonzero(tables["flags"] & 2)), int(tables["solid"].sum()))

+    def fake_backend(self):
+        backend = PeriodicBlockStepper.__new__(PeriodicBlockStepper)
+        backend.layout = BlockLayout2D.build(NY, NX, 12, 16)
+        backend.ctx = Mock(activate=nullcontext)
+        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()
+        backend.boundary, backend._curved, backend._tables, backend._links = None, None, {}, 0
+        backend._dst, backend._src = Mock(), Mock()
+        backend._block, backend._grid, backend._copy_grid = (32, 1, 1), (1, 1, 1), (1, 1)
+        backend._allocations = [Mock(), Mock()]
+        backend._current, backend._spare = backend._allocations
+        return backend

-class SingleLevelGPU(unittest.TestCase):
+    def test_initialize_rejects_bad_state_before_upload(self):
+        backend = self.fake_backend()
+        good = initial_state()
+        bad = (good[:, :-1], np.where(np.arange(NX) == 3, np.nan, good), -good)
+        with patch.object(cuda, "memcpy_htod") as upload:
+            for g in bad:
+                with self.assertRaises(ValueError):
+                    backend.initialize(g)
+            upload.assert_not_called()
+            backend.initialize(good)
+            self.assertEqual(upload.call_count, 2)
+            self.assertTrue(np.isnan(upload.call_args_list[1].args[1]).all())
+        backend.close()
+
+    def test_failed_launch_and_download_make_backend_unusable(self):
+        for failure in ("step", "download"):
+            backend = self.fake_backend()
+            if failure == "step":
+                backend._step = Mock(side_effect=RuntimeError("launch failed"))
+                with self.assertRaisesRegex(RuntimeError, "launch failed"):
+                    backend.step()
+            else:
+                with patch.object(cuda, "memcpy_dtoh", side_effect=RuntimeError("read failed")):
+                    with self.assertRaisesRegex(RuntimeError, "read failed"):
+                        backend.download()
+            for operation in (backend.download, backend.step):
+                with self.assertRaisesRegex(RuntimeError, "failed"):
+                    operation()
+            backend.close()
+            for allocation in backend_allocations(backend):
+                allocation.free.assert_called_once()
+
+    def test_activation_failure_retains_resources_for_retry(self):
+        backend = self.fake_backend()
+        allocations, stream, module = backend._allocations[:], backend._stream, backend._module
+        unavailable = MagicMock()
+        unavailable.__enter__.side_effect = RuntimeError("activation failed")
+        backend.ctx.activate = Mock(side_effect=[unavailable, nullcontext()])
+        with self.assertRaisesRegex(RuntimeError, "activation failed"):
+            backend.close()
+        self.assertEqual(backend._status, "failed")
+        self.assertEqual(backend._allocations, allocations)
+        self.assertIs(backend._stream, stream)
+        self.assertIs(backend._module, module)
+        backend.close()
+        self.assertEqual(backend._status, "closed")
+        self.assertIsNone(backend._module)
+        self.assertIsNone(backend._copy)
+        self.assertIsNone(backend._step)
+        for allocation in allocations:
+            allocation.free.assert_called_once()
+
+
+def backend_allocations(backend):
+    return (backend._current, backend._spare)
+
+
+class PeriodicBlockGPU(unittest.TestCase):
    def setUp(self):
        self.assertEqual(Path(implementation.__file__).resolve(),
-                         ROOT / "src/CelerisLab/lbm/refinement_stepper.py")
+                         ROOT / "src/CelerisLab/lbm/block_stepper.py")

    def tearDown(self):
        rss = resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1024
@@ -205,13 +274,13 @@ class SingleLevelGPU(unittest.TestCase):
        g0 = initial_state()
        results = []
        with CudaContext(0) as context:
-            for split in SPLITS:
-                with single(context=context, block=split) as backend:
+            for by, bx in SPLITS:
+                layout = BlockLayout2D.build(NY, NX, by, bx)
+                with PeriodicBlockStepper(config(), layout, context=context) as backend:
                    backend.initialize(g0)
                    backend.step(STEPS)
                    self.assertEqual(backend.step_count, STEPS)
-                    (g,) = backend.download()
-                    results.append(g)
+                    results.append(backend.download())
        for (by, bx), g in zip(SPLITS, results):
            self.assertTrue(np.isfinite(g).all(), (by, bx))
            np.testing.assert_array_equal(g, results[0], err_msg=f"split {(by, bx)}")
@@ -238,17 +307,16 @@ class SingleLevelGPU(unittest.TestCase):
        g0 = initial_state()
        results = []
        with CudaContext(0) as context:
-            for split in SPLITS:
-                with single(context=context, block=split, objects=[circle()]) as backend:
-                    tables = backend._level_boundaries[0].tables
+            for by, bx in SPLITS:
+                layout = BlockLayout2D.build(NY, NX, by, bx)
+                with PeriodicBlockStepper(config(), layout, context=context, objects=[circle()]) as backend:
                    for key, values, dtype in (("q", [l.q for l in links], np.float32),
                                               ("dir", [l.dir for l in links], np.uint8),
                                               ("fallback", [l.fallback for l in links], np.uint8)):
-                        np.testing.assert_array_equal(tables[key], np.array(values, dtype))
+                        np.testing.assert_array_equal(backend.boundary[key], np.array(values, dtype))
                    backend.initialize(g0)
                    backend.step(STEPS)
-                    (g,) = backend.download()
-                    results.append(g)
+                    results.append(backend.download())
        for (by, bx), g in zip(SPLITS, results):
            self.assertTrue(np.isfinite(g[:, ~solid]).all(), (by, bx))
            self.assertTrue(np.isnan(g[:, solid]).all(), (by, bx))
@@ -11,7 +11,7 @@ import numpy as np
 import pycuda.driver as cuda

 from CelerisLab.config import LBMConfig
-from CelerisLab.cuda import compiler
+from CelerisLab.cuda import compiler_v2 as compiler
 from CelerisLab.cuda.context import CudaContext
 from CelerisLab.lbm.blocks import BlockLayout2D
 from CelerisLab.lbm.descriptors import FLUID, SOLID, BC_WALL, BC_INLET, BC_OUTLET
@@ -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 == "blocked.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:
@@ -46,7 +46,7 @@ def run_root(cfg, context, initial, block=None, steps=8):
    try:
        layout = None if block is None else BlockLayout2D.build(cfg.ny, cfg.nx, *block)
        local = cfg if layout is None else replace(cfg, nx=layout.local_shape[1], ny=layout.local_shape[0])
-        module = compile_module(local, context, "uniform.cu" if layout is None else "blocked.cu")
+        module = compile_module(local, context, "kernel_v2.cu" if layout is None else "blocks.cu")
        data = initial if layout is None else layout.to_blocked(initial)
        current, spare = upload(data), upload(np.full_like(data, np.nan))
        tpb = cfg.threads_per_block
@@ -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)
@@ -18,7 +18,7 @@ import CelerisLab
 from CelerisLab.body.geometry.circle import CircleGeometry
 from CelerisLab.body.objects import SimObject
 from CelerisLab.config import LBMConfig
-from CelerisLab.cuda import compiler
+from CelerisLab.cuda import compiler_v2 as compiler
 from CelerisLab.cuda.context import CudaContext
 from CelerisLab.lbm import refinement_stepper as implementation
 from CelerisLab.lbm.descriptors import FLUID, SOLID
@@ -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
@@ -327,7 +326,6 @@ 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)
@@ -224,13 +221,16 @@ class RawExchangeGPU(unittest.TestCase):
        Eight local hops are a short-time equivalence check, not convergence.
        The test adapter only enables the standalone kernel's optional inputs.
        """
+        from CelerisLab.lbm.blocks import BlockLayout2D
+        from CelerisLab.lbm.block_stepper import PeriodicBlockStepper
        fine_cfg = replace(CFG, nx=64, ny=48, viscosity=.2)
        obj = SimObject(0, geometry=CircleGeometry(31.5, 23.5, 4.3),
                        center=(31.5, 23.5), radius=4.3)
+        layout = BlockLayout2D.build(48, 64, 8, 8)
        with CudaContext(0) as ctx:
-            with FixedPatchStepper(fine_cfg, context=ctx, refinements=[], level_blocks=[(8, 8)],
-                                   level_objects=[(obj,)]) as uniform, \
-                 FixedPatchStepper(CFG, context=ctx, **fine((16, 20)), observe_raw_exchange=True) as amr:
+            with PeriodicBlockStepper(fine_cfg, layout, context=ctx, objects=[obj]) as uniform, \
+                 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]
@@ -238,21 +238,18 @@ class RawExchangeGPU(unittest.TestCase):
                links = obj.geometry.build_cut_links(64, 48)
                np.testing.assert_array_equal([v.dir for v in links], b.tables['dir'])
                np.testing.assert_allclose([v.q for v in links], b.tables['q'], atol=2e-7, rtol=0)
-                # Same fine-grid force arms after translation to the same center: the
-                # single level's static BFL gets the AMR Jet column and force arms; the raw
-                # output pointer is substituted at launch (no stepper-side accumulation).
-                root = uniform._level_boundaries[0]
+                # Same fine-grid force arms after translation to the same center.
+                rx = uniform._upload(b.tables['rx'])
+                ry = uniform._upload(b.tables['ry'])
                velocity = uniform._upload(b.tables['surface_velocity'])
-                root.device.update(surface_velocity=velocity, rx=uniform._upload(b.tables['rx']),
-                                   ry=uniform._upload(b.tables['ry']))
                raw = uniform._allocate(count*16)
-                original = root.kernel
+                original = uniform._curved
                samples = []
                def measured_boundary(*args, **kw):
-                    original(*args[:10], raw, **kw)  # BlockCurvedBoundary raw-exchange output
+                    original(*args[:7], velocity, rx, ry, raw, **kw)
                    uniform._stream.synchronize()
                    samples.append(download(raw, (count, 4)))
-                root.kernel = measured_boundary
+                uniform._curved = measured_boundary
                for speed in (0., .002, -.001, 0.):
                    amr.set_jet_amplitude(0, speed)
                    cuda.memcpy_htod(velocity, b.tables['surface_velocity'])
@@ -2,34 +2,6 @@

 Run CPU and GPU classes in separate processes. GPU callers must first check
 resources/device availability; this file never selects or reserves a GPU.
-
-Dense/blocked route parity (DenseBlockedRouteParity): the same configuration,
-initial state, body/Jet schedule and tilings on three storage routes, only
-level_blocks varying: D/D [None, None], D/B [None, FINE_BLOCK] (dense root,
-the mixed pattern of current examples) and B/B [(12, 8), FINE_BLOCK]. Gate:
-every public and owner array identical in FP32 bits and NaN masks at steps
-0, 1, 2, 8 and after re-initialize; D/B and B/B raw-exchange ledgers equal.
-No tolerance. A mismatch is reported with route pair/level/step and diagnosed
-(boundary semantics vs arithmetic ordering), never widened.
-
-Route capabilities (rejections checked before CUDA by test_route_capability_matrix):
-
-  combination                                   D/D       D/B       B/B
-  periodic / slot_reservoir root, fine circle   yes       yes       yes   (parity gate)
-  actuated circle, velocity Jet + amplitude     yes       yes       yes   (parity gate)
-  raw/window exchange on a body level           rejected  yes       yes
-  shifted storage                               rejected  rejected  yes
-  projected explosion                           rejected  rejected  yes
-  channel root                                  rejected  rejected  yes
-  several L1 rectangles                         rejected  rejected  yes
-  depth >= 3 with a dense level                 rejected  rejected  yes
-Slot/reservoir walls are compile-time WALL_* macros on a dense root and the
-d_block_wall constant on a blocked root: BC-encoding parity, bit-identical by
-this gate. Dense fine bodies use CurvedLinkSoA + CurvedBoundaryKernel
-(n_objects > 0), blocked ones BlockCurvedBoundary; same links and physics,
-compared through the population rows. Parked here: MRT (covered by
-test_refinement_mrt_gpu::test_dense_versus_blocked_mrt_two_level), shifted and
-depth >= 3 (no dense route to compare), several bodies (later slice).
 """
 from contextlib import ExitStack, contextmanager, nullcontext
 from dataclasses import replace
@@ -41,14 +13,13 @@ from unittest.mock import Mock, patch
 import numpy as np
 import pycuda.driver as cuda

-from CelerisLab.cuda import compiler
+from CelerisLab.cuda import compiler_v2 as compiler
 from CelerisLab.lbm import refinement_stepper
 from CelerisLab.lbm.blocks import BlockLayout2D
 from CelerisLab.lbm.descriptors import D2Q9_EX, D2Q9_EY
 from CelerisLab.lbm.refinement import ACTIVE, OUTER_GHOST, FixedPatch2D
 from CelerisLab.lbm.refinement_stepper import FixedPatchStepper, blocked_base_tables
 from test_refinement_blocked_fine import NX, NY, BOUNDS, config, state, circle, actuation
-from test_refinement_jets import SPEED, jet

 BASE_BLOCKS = ((24, 32), (12, 8), (3, 4), (1, 1))
 FINE_BLOCK = (16, 20)
@@ -102,7 +73,6 @@ def mocked_backend(mode="periodic", fail_alloc=None):
            stack.enter_context(patch.object(compiler, name))
        stack.enter_context(patch.object(compiler, "load_module", return_value=module))
        stack.enter_context(patch.object(cuda, "Stream", return_value=stream))
-        stack.enter_context(patch.object(cuda, "mem_get_info", return_value=(1 << 40, 1 << 40)))
        stack.enter_context(patch.object(cuda, "mem_alloc", side_effect=allocate))
        stack.enter_context(patch.object(cuda, "memcpy_htod",
                                        side_effect=lambda p, a: uploads.append((p, a))))
@@ -113,10 +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):
@@ -222,10 +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
@@ -253,8 +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)
@@ -268,16 +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
@@ -321,10 +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:
@@ -353,128 +320,5 @@ class BlockedBaseGPU(unittest.TestCase):
                            print(f"PASS {label}: full finite bits/NaN masks at 0,1,2,8 + reset", flush=True)


-ROUTES = (("D/D", [None, None]), ("D/B", [None, FINE_BLOCK]), ("B/B", [(12, 8), FINE_BLOCK]))
-
-
-def same_summary(a, b):
-    """Exact equality of nested exchange summaries (dicts, sequences, arrays, numbers)."""
-    if isinstance(a, dict):
-        return a.keys() == b.keys() and all(same_summary(a[k], b[k]) for k in a)
-    if isinstance(a, (list, tuple)):
-        return len(a) == len(b) and all(same_summary(x, y) for x, y in zip(a, b))
-    a, b = np.asarray(a), np.asarray(b)
-    if a.dtype.kind in "biufc" and b.dtype.kind in "biufc":
-        return a.shape == b.shape and np.array_equal(a, b, equal_nan=True)
-    return a.dtype == b.dtype and np.array_equal(a, b)  # labels such as the window name
-
-
-class DenseBlockedRouteCPU(unittest.TestCase):
-    def test_same_summary_compares_labels_and_every_number(self):
-        ledger = {"window": "last_base_step", "time_start": 3, "total": {"force": [1.0, -2.0],
-                  "torque": 0.5}, "aperture": {"force": np.array([np.nan, 1.0])}}
-        self.assertTrue(same_summary(ledger, replace_value(ledger, ())))
-        for path, value in ((("window",), "last_substep"), (("time_start",), 4),
-                            (("total", "force"), [1.0, -2.000001]), (("total", "torque"), 0.25),
-                            (("aperture", "force"), np.array([0.0, 1.0]))):
-            with self.subTest(path=path):
-                self.assertFalse(same_summary(ledger, replace_value(ledger, path, value)))
-                self.assertFalse(same_summary(replace_value(ledger, path, value), ledger))
-
-    def test_route_capability_matrix(self):
-        context = Mock(activate=Mock(side_effect=AssertionError("CUDA reached")))
-        periodic = config("periodic")
-        inner = (BOUNDS[0] + 2, BOUNDS[1] + 2, BOUNDS[2] - 2, BOUNDS[3] - 2)
-        second = (BOUNDS[0], BOUNDS[1], BOUNDS[0] + 2, BOUNDS[1] + 2)
-        cases = (
-            ("raw exchange on dense body level", periodic, dict(
-                level_blocks=[None, None], level_objects=[(), (circle(),)], observe_raw_exchange=True)),
-            ("shifted D/D", replace(periodic, ddf_shifting=True), dict(level_blocks=[None, None])),
-            ("shifted D/B", replace(periodic, ddf_shifting=True), dict(level_blocks=[None, FINE_BLOCK])),
-            ("projected D/D", periodic, dict(level_blocks=[None, None], explosion="projected_linear")),
-            ("projected D/B", periodic, dict(level_blocks=[None, FINE_BLOCK], explosion="projected_linear")),
-            ("channel D/B", periodic, dict(level_blocks=[None, FINE_BLOCK], coarse_boundary="channel")),
-            ("several L1 rectangles", periodic, dict(refinements=[[BOUNDS, second]], level_blocks=[None, None])),
-            ("depth 3 dense", periodic, dict(refinements=[BOUNDS, inner], level_blocks=[None, None, None])),
-        )
-        for label, cfg, kw in cases:
-            kw.setdefault("refinements", [BOUNDS])
-            with self.subTest(label), self.assertRaises(ValueError):
-                FixedPatchStepper(cfg, context=context, **kw)
-        context.activate.assert_not_called()
-
-
-def replace_value(tree, path, value=None):
-    """Deep copy of a nested dict with the item at ``path`` replaced (no change for ())."""
-    if isinstance(tree, dict):
-        return {k: (value if path == (k,) else replace_value(v, path[1:], value) if path[:1] == (k,)
-                    else replace_value(v, (), None)) for k, v in tree.items()}
-    return np.array(tree, copy=True) if isinstance(tree, np.ndarray) else tree
-
-
-class DenseBlockedRouteParity(unittest.TestCase):
-    """D/D vs D/B vs B/B, unshifted SRT, one circle or one velocity Jet; see module docstring."""
-
-    def run_routes(self, mode, objects=(), jets=(), switch=None):
-        from CelerisLab.cuda.context import CudaContext
-        cfg = config(mode)
-        p = FixedPatch2D.from_config(cfg, BOUNDS)
-        arrays = state(NY, NX, 1), state(*p.fine_shape, 2)
-        results = {}
-        with CudaContext(0) as context:
-            for name, blocks in ROUTES:
-                observe = bool(objects) and blocks[1] is not None
-                snapshots, ledgers = [], []
-                with FixedPatchStepper(cfg, context=context, coarse_boundary=mode, refinements=[BOUNDS],
-                                       level_blocks=blocks, level_objects=[(), tuple(objects)],
-                                       level_jets=[(), tuple(jets)],
-                                       observe_raw_exchange=observe) as backend:
-                    backend.initialize(*arrays)
-                    for step in (0, 1, 2, 8):
-                        if step == 8 and switch is not None:
-                            backend.set_jet_amplitude(0, switch)
-                        backend.step(step - backend.step_count)
-                        snapshots.append(backend.download() + raw(backend))
-                        if observe and step:
-                            ledgers.append(tuple(backend.read_raw_exchange(0, window=window)
-                                                 for window in ("last_base_step", "last_substep")))
-                    backend.initialize(*arrays)
-                    snapshots.append(backend.download() + raw(backend))
-                results[name] = snapshots, ledgers
-        return results
-
-    def check(self, label, results):
-        reference, _ = results["D/D"]
-        for name in ("D/B", "B/B"):
-            for step, actual, expected in zip((0, 1, 2, 8, "reset"), results[name][0], reference):
-                for index, (a, b) in enumerate(zip(actual, expected)):
-                    exact(self, a, b, f"{label} {name} vs D/D step={step} array={index}")
-        if results["D/B"][1]:
-            for step, a, b in zip((1, 2, 8), results["D/B"][1], results["B/B"][1]):
-                self.assertTrue(same_summary(a, b), f"{label} raw exchange D/B vs B/B step={step}")
-        for name, (snapshots, _) in results.items():
-            masses = [float(np.nansum(level.astype(np.float64))) for level in snapshots[3][:2]]
-            print(f"{label} {name}: step 8 mass by level {masses}", flush=True)
-        print(f"PASS {label}: D/D = D/B = B/B bits/NaN masks at 0,1,2,8 + reset", flush=True)
-
-    def test_body_free(self):
-        for mode in ("periodic", "slot_reservoir"):
-            self.check(f"{mode} body-free", self.run_routes(mode))
-
-    def test_passive_circle(self):
-        for mode in ("periodic", "slot_reservoir"):
-            self.check(f"{mode} circle", self.run_routes(mode, objects=[circle()]))
-
-    def test_actuated_circle(self):
-        for mode in ("periodic", "slot_reservoir"):
-            for speed in (SPEED, -SPEED):
-                self.check(f"{mode} actuated {speed}",
-                           self.run_routes(mode, objects=[circle(actuation(speed))]))
-
-    def test_velocity_jet_with_amplitude_switch(self):
-        for mode in ("periodic", "slot_reservoir"):
-            self.check(f"{mode} jet switch",
-                       self.run_routes(mode, objects=[circle()], jets=[jet()], switch=-SPEED))
-
-
 if __name__ == "__main__":
    unittest.main()
@@ -15,7 +15,7 @@ import pycuda.driver as cuda
 from CelerisLab.body.geometry.circle import CircleGeometry
 from CelerisLab.body.objects import SimObject, SurfaceActuation
 from CelerisLab.config import LBMConfig
-from CelerisLab.cuda import compiler
+from CelerisLab.cuda import compiler_v2 as compiler
 from CelerisLab.lbm import curved_links
 from CelerisLab.lbm.blocks import NO_DONOR, BlockLayout2D, blocked_link_tables
 from CelerisLab.lbm.descriptors import D2Q9_EX, D2Q9_EY
@@ -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).
@@ -122,12 +121,12 @@ class BlockedFineCPU(unittest.TestCase):
                raise AssertionError("zero-byte device allocation")
            sizes.append(size)
            return Mock()
-        with patch.object(cuda, "Stream"), patch.object(cuda, "mem_get_info", return_value=(1 << 40, 1 << 40)), patch.object(compiler, "generate_config"), \
+        with patch.object(cuda, "Stream"), patch.object(compiler, "generate_config"), \
                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
@@ -172,15 +171,14 @@ class BlockedFineCPU(unittest.TestCase):
            return functions.setdefault(name, Mock(side_effect=lambda *a, **k: calls.append((name, a))))
        module = Mock(get_function=Mock(side_effect=get_function))
        module.get_global.return_value = (Mock(), 20)
-        with patch.object(cuda, "Stream"), patch.object(cuda, "mem_get_info", return_value=(1 << 40, 1 << 40)), patch.object(compiler, "generate_config"), \
+        with patch.object(cuda, "Stream"), patch.object(compiler, "generate_config"), \
                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=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.
@@ -103,8 +102,7 @@ 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)
@@ -158,31 +156,22 @@ 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"), patch.object(cuda, "mem_get_info", return_value=(1 << 40, 1 << 40)), bad, patch.object(cuda, "mem_alloc") as alloc, \
-                patch.object(cuda, "memcpy_htod") as upload:
+        with patch.object(cuda, "Stream"), patch.object(implementation.FixedPatch2D, "from_config",
+                                                       return_value=replace(p, tau_coarse=.9)):
+            # The hierarchy rejects a pair tau that disagrees with its level config
+            # (hierarchy.py) before the per-level omega/tau check can be reached.
            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()
+                PeriodicPatchStepper(cfg, p.bounds, context=context)
        module = Mock()
        module.get_global.return_value = (Mock(), 16)
-        with patch.object(cuda, "Stream"), patch.object(cuda, "mem_get_info", return_value=(1 << 40, 1 << 40)), patch.object(compiler, "generate_config"), \
+        with patch.object(cuda, "Stream"), patch.object(compiler, "generate_config"), \
                patch.object(compiler, "compile_kernel"), patch.object(compiler, "cleanup_build_dir"), \
                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 +245,7 @@ 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 +315,7 @@ 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 +346,7 @@ 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
@@ -20,7 +20,7 @@ import pycuda.driver as cuda

 import CelerisLab
 from CelerisLab.config import LBMConfig
-from CelerisLab.cuda import compiler
+from CelerisLab.cuda import compiler_v2 as compiler
 from CelerisLab.cuda.context import CudaContext
 from CelerisLab.lbm.refinement_stepper import FixedPatchStepper, PeriodicPatchStepper

@@ -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()
@@ -16,7 +16,7 @@ from unittest.mock import Mock, patch
 import numpy as np
 import pycuda.driver as cuda

-from CelerisLab.cuda import compiler
+from CelerisLab.cuda import compiler_v2 as compiler
 from CelerisLab.lbm.descriptors import SOLID
 from CelerisLab.lbm.refinement import ACTIVE, FixedPatch2D, prepare_fine_boundary
 from CelerisLab.lbm.refinement_stepper import FixedPatchStepper
@@ -36,14 +36,13 @@ def mocked(objects, jets, fine_block):
    module = Mock(get_function=Mock(return_value=Mock()))
    module.get_global.return_value = (Mock(), 20)
    htod = Mock()
-    with patch.object(cuda, "Stream"), patch.object(cuda, "mem_get_info", return_value=(1 << 40, 1 << 40)), patch.object(compiler, "generate_config"), \
+    with patch.object(cuda, "Stream"), patch.object(compiler, "generate_config"), \
            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=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):
@@ -52,38 +43,35 @@ def child_jet(speed=.002):


 def mocked_child():
-    from CelerisLab.cuda import compiler
+    from CelerisLab.cuda import compiler_v2 as compiler
    context = Mock(activate=nullcontext, sm_arch="sm_70")
    module = Mock(get_function=Mock(side_effect=lambda name: Mock(name=name)))
    module.get_global.return_value = (Mock(), 20)
-    with patch.object(cuda, "Stream"), patch.object(cuda, "mem_get_info", return_value=(1 << 40, 1 << 40)), patch.object(compiler, "generate_config"), \
+    with patch.object(cuda, "Stream"), patch.object(compiler, "generate_config"), \
            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=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):
@@ -92,12 +80,11 @@ class ThreeLevelCPU(unittest.TestCase):
        f, g = run._levels[1:]
        b = g.boundary
        events, feeds = [], []
-        advance, gather = run._advance, run._gather_halo
-        def record_feed(index, buffer, **kw):  # index 2: L1 hop feeds L2
-            if index == 2:
-                self.assertIs(buffer, (f.current, f.spare)[len(feeds)])
-                feeds.append(buffer)
-            advance(index, buffer, **kw)
+        advance, gather = run._advance_child, run._gather_halo
+        def record_feed(buffer, **kw):
+            self.assertIs(buffer, (f.current, f.spare)[len(feeds)])
+            feeds.append(buffer)
+            advance(buffer, **kw)
        def record_halo(level, buffer, **kw):
            if level is g:
                events.append(("halo", buffer))
@@ -108,7 +95,7 @@ class ThreeLevelCPU(unittest.TestCase):
            self.assertIs(kind, g.kind)
            events.append(("step", src))
        g.kernel.side_effect = record_step
-        with patch.object(run, "_advance", side_effect=record_feed), \
+        with patch.object(run, "_advance_child", side_effect=record_feed), \
                patch.object(run, "_gather_halo", side_effect=record_halo):
            run.step()
        self.assertEqual(feeds, [f.current, f.spare])
@@ -118,8 +105,8 @@ class ThreeLevelCPU(unittest.TestCase):
        self.assertGreater(len(np.unique(b.tables["block"])), 1)
        # Negative control: reusing L1's old source at the midpoint must fail.
        feeds.clear()
-        with patch.object(run, "_advance", side_effect=lambda index, buffer, **kw:
-                          record_feed(index, f.current if index == 2 else buffer, **kw)):
+        with patch.object(run, "_advance_child", side_effect=lambda buffer, **kw:
+                          record_feed(f.current, **kw)):
            with self.assertRaises(AssertionError):
                run.step()
        run.close()
@@ -168,7 +155,7 @@ 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)
@@ -181,16 +168,15 @@ 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]
-            feeds, original = [], run._advance
-            def record(index, buffer, **kw):  # index 2: L1 hop feeds L2
-                if index == 2:
-                    feeds.append(int(buffer))
-                original(index, buffer, **kw)
-            with patch.object(run, "_advance", side_effect=record):
+            feeds, original = [], run._advance_child
+            def record(buffer, **kw):
+                feeds.append(int(buffer))
+                original(buffer, **kw)
+            with patch.object(run, "_advance_child", side_effect=record):
                cur, spare = int(f.current), int(f.spare)
                run.step(1)
            self.assertEqual(feeds, [cur, spare])  # current G, then the new G of hop 1
@@ -217,9 +203,8 @@ 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
--- a/Show More
+++ b/Show More