fix: normalize closed-form Smagorinsky strain magnitude

README.md

@@ -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)),
@@ -124,9 +123,7 @@ 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.
+- D2Q9, SRT, FP32, double buffer, unshifted, no LES or forcing; fixed 2:1 patch(es), two levels (or one nested third).
 - `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 +131,46 @@ 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
-  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)`:
+- Several separated patches: pass a sequence of `(x0, y0, x1, y1)`
+  rectangles as `bounds`, at least 4 coarse cells apart, with both `fine_block`
+  and `base_block`. 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
-  as for one patch: each circle (same coarse cell-edge frame) must lie wholly
-  inside the union's active region with
+  patch windows (active region plus 4-cell ghost band, origin `(2*y0-4, 2*x0-4)`)
+  are stored; each window must align with `fine_block`. 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 one patch'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.
+  different bodies, even across patches. No wall-touching patches or nesting yet.
 
   ```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.
+- Three levels (one nested 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 +182,9 @@ 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)
@@ -200,30 +192,14 @@ 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.
-- 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,
-  torque and mass exchange in base-lattice units per unit depth, for the last
-  base interval (default) or `window="last_substep"`.
-  `observe_window_exchange=True`, alongside `observe_raw_exchange=True`, enables
-  `start_exchange_window()` / `read_exchange_window(body_id, level=...)` across
-  completed base intervals. These are raw boundary-reaction diagnostics, not a general
-  stress or nozzle-load accuracy claim; dense body layouts are unsupported.
-- Not available: checkpoints, moving bodies, L1 bodies/Jets in a three-level
-  chain, automatic dynamic refinement, `Simulation` integration. Qualification
-  depends on the tested configuration; see [the validation scope](docs/validation/2d_scope.md).
-  CPU topology/schedule tests alone do not establish GPU numerical correctness,
-  general convergence or long-time stability.
+- Not available: per-link surface exchange/force readout in blocked mode,
+  checkpoints, moving bodies, L1 bodies/Jets in a three-level chain,
+  several patches per level with nesting, dynamic refinement, `Simulation`
+  integration. Validation so far is storage/operator equivalence and short runs,
+  not accuracy, convergence or long-time stability. The new L2-body GPU gates
+  (layouts, masks, amplitude reversal, legacy equivalence) and independent
+  every-substep numerical replay remain required acceptance checks; CPU tests
+  alone do not establish GPU numerical correctness.
 
 ## Installation
 

docs/compatibility.md

@@ -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.

docs/development/les_dev8403956_integration.md

@@ -1,62 +0,0 @@
-# Selective LES normalization integration on dev8403956
-
-This change reuses the reviewed correction from 5465832 without merging its
-branch history. The only production change is the two closed-form coefficients
-18 -> 18 sqrt(2) and their explanatory comments in turbulence_smag.cuh. Its SHA256
-is a3db46c2e7d27530b2d1436e65cdbed0b72cc7e047bfbeef2a640877271b51aa.
-Defaults, iterative/deviatoric/capped closure, collision dispatch, AMR guards,
-and all other production source files are unchanged.
-
-## Separate source contract; unchanged experiment
-
-The single existing flow runner now accepts `--experiment dev8403956`.
-Its separate source_pins_dev8403956.json pins all 101 production files from the
-committed 8403956 baseline; corrected mode permits only the exact reviewed
-header substitution. Results record the actual checkout commit, import path,
-experiment name and manifest SHA256. No arbitrary manifest-path override exists.
-
-Omitting the option still selects the original historical source manifest.
-That manifest, the original paired receipts, scalar preparation manifests and
-independent continuum oracle are unchanged. Historical baseline and corrected
-receipts remain evidence for their own exact sources, not new dev receipts.
-Historical guards intentionally reject this different dev source tree. Eight
-production files already differed between the historical source snapshot and
-8403956; neither the old manifest nor its acceptance is silently regenerated.
-
-The physical experiment and every numerical acceptance threshold are unchanged:
-8 x 34 nodes, halfway y walls, periodic x, unforced D2Q9/SRT, shifted FP32,
-double-buffer streaming, Cs=0/.16/1, checkpoints 519/1038/2075. Each case has one
-actual advancing warm-up followed by complete initial-state restoration before
-READY. Total launches are 6,225 measured plus three warm-ups. Cs=1 remains an
-amplified diagnostic, not a physical coefficient recommendation.
-
-## Host checks
-
-    PYTHONDONTWRITEBYTECODE=1 python -m unittest discover -s tests/unit -p 'test_smagorinsky_normalization.py' -v
-    PYTHONDONTWRITEBYTECODE=1 python -m unittest discover -s tests/unit -p 'test_les_flow_*.py' -v
-
-The direct-current-header test is copied unchanged from reviewed 5465832:
-120 tensor parameter cases, Cs=0/equilibrium and omega guards, converged
-trace-free iterative comparison, and mutation detection in both lattice
-algebras. This is scalar D2/D3 algebra coverage, not 3D-flow qualification.
-Flow tests retain analytic/reference checks and add current named-source,
-reverse-patched baseline, variant rejection, unrelated-source tampering and
-immutable historical-default checks. The temporary baseline is constructed
-only inside a test directory; production is never reverse-patched.
-
-## Pending final-commit GPU gate
-
-After independent review and explicit executor authorization, run from the
-exact committed candidate checkout, selecting the authorized physical GPU:
-
-    CUDA_VISIBLE_DEVICES=<physical-GPU> PYTHONDONTWRITEBYTECODE=1 python tests/validation/run_uniform_les_flow.py --root "$PWD" --experiment dev8403956 --variant corrected --run-gpu --device 0 --output <new-evidence-directory>/corrected.json
-
-Retain all source hashes, exact commit/import/device identity, manifest hash,
-three READY/reset records, complete result JSON, stdout/stderr and actual exit.
-Require all frozen gates, DONE passed=true and exit 0. Compare with historical
-corrected evidence without relabeling it as current evidence. The old-vs-new
-normalization discrimination already exists; no new baseline GPU run is needed
-unless review finds a changed exercised uniform solver path.
-
-No GPU result is claimed by this integration preparation. This does not expand
-LES qualification to MRT, forcing, AMR LES or three-dimensional turbulent flows.

docs/development/les_normalization_candidate.md

@@ -0,0 +1,70 @@
+# Minimal Smagorinsky normalization integration candidate
+
+This local candidate changes only the two closed-form D2Q9/D3Q19 coefficients
+from 18 to 18 sqrt(2), plus their convention comments. The intended convention
+is |S| = sqrt(2 S:S), with self-consistent effective tau. No Cs default,
+iterative formula/cap/iteration count, collision dispatch, AMR guard, inlet,
+channel-parity rule, or unrelated source file changes.
+
+The resulting turbulence_smag.cuh SHA256 is
+`a3db46c2e7d27530b2d1436e65cdbed0b72cc7e047bfbeef2a640877271b51aa`,
+exactly the independently reviewed temporary correction used in the paired
+scalar and end-to-end flow experiments. Its uncorrected baseline remains at
+validation checkpoint `9805383f9c50d867e8555471baf5dbda8333a652`.
+
+## Evidence and limits
+
+The separately audited scalar-helper GPU diagnostic on the cd3 source campaign
+covered 48 cases per variant. All 32 paired iterative results were bit-identical;
+maximum patched closed-form error was approximately 1.19e-7, versus 0.06454 for
+the baseline against the same standard convention. This is scalar evidence,
+not full-collision or turbulence qualification.
+
+The independently reviewed wall-bounded, x-periodic SRT/shifted-FP32/double-buffer
+shear experiment distinguished baseline from corrected source under identical
+predeclared criteria. Baseline Cs=1 SGS decrement errors at the last two
+checkpoints were approximately 28.50% and 28.05%; corrected errors were 0.0628%
+and 0.00612%. Corrected maximum Cs=1 profile error was approximately 0.11344%,
+and the Cs=0 observations were identical between variants. Cs=1 is an amplified
+normalization diagnostic, not a recommended physical coefficient. These data
+qualify this bounded normalization comparison, not general turbulence accuracy.
+
+The current direct-header host regression uses the existing independent
+Hermite tensor construction and quadratic bisection oracle. It covers 120
+parameter subcases across D2/D3, Cs=0/.16, rho=.7/1/1.3, tau0=.56/.8,
+equilibrium, both signs of shear and trace-free extension, including a 3D axis.
+It also checks converged iterative agreement, Cs=0 omega guard bounds, and
+explicitly proves that removing sqrt(2) in temporary headers fails the oracle.
+No stored candidate header or full solver fixture is added.
+
+MRT full-trace/bulk coupling, forcing/Guo correction, other streaming/storage
+paths, three-dimensional turbulent flows, and AMR LES remain uncertified.
+Full-stress closed form and deviatoric/capped iteration intentionally need not
+agree on isotropic or cap-active stresses. Existing guards remain unchanged.
+
+## Run and retain provenance
+
+From this candidate checkout:
+
+    PYTHONPATH=src python tests/unit/test_smagorinsky_normalization.py -v
+    PYTHONPATH=src python tests/unit/test_les_flow_runner.py -v
+
+The flow runner already supports `--variant corrected` against the exact
+reviewed helper hash. Its source-pin tests now exercise that current variant;
+they still verify that the archived baseline variant rejects the corrected
+source and that unrelated source tampering is rejected.
+
+Historical Re100, Jet, matched-DFG and paired-scalar manifests/runners are not
+repinned or weakened. Their baseline-source guards are expected to reject this
+changed production tree. Run those archived source-specific checks on the clean
+9805383 checkpoint; their old GPU evidence does not become evidence for this
+candidate. The new direct-current-header test is the regression for corrected
+production. Do not describe the historical full suite as passing on this tree.
+
+Before publication or main integration, obtain final independent diff review
+and rerun the applicable scalar/flow GPU commands on the exact final candidate
+commit after the executor reconnects. Retain new checkout/import/source-hash
+receipts and compare against the frozen baseline using separate processes.
+A new commit receipt is required even though its corrected header matches the
+previously tested temporary correction. No GPU rerun, publication, or main
+merge is claimed by this candidate preparation.

docs/development/projected_pair_explosion.md

@@ -1,57 +0,0 @@
-# Experimental projected G explosion
-
-`FixedPatchStepper(..., explosion="projected_linear")` changes only the existing
-G-to-G explosion reconstruction. The omitted/default `"constant"` selector retains
-the same kernel, launch arguments and device allocations. Projected mode adds two
-compact tables per adjacent pair; recursion, collision, BFL, restriction, buffer
-ownership and synchronized publication are unchanged. `remap_child` preserves it.
-
-Runtime eligibility is periodic-root, fully blocked D2Q9/SRT/FP32, body/Jet-free,
-without LES; the fixed-patch backend has no forcing interface. Shifted and unshifted
-storage use the same reconstruction. One generic builder handles scalar windows,
-unique union rows and all adjacent hierarchy pairs without depth/rectangle caps.
-Donors are original explosion donors intersected with owned, uncovered ACTIVE
-cells. An axis uses centered differences only if both neighbors are legal;
-otherwise both addresses repeat the center. Nested layout periodicity is explicit.
-No covered cells, holes, inactive cells or stale halo copies enter the stencil.
-
-The 33-line kernel is unchanged from our `519473a` experiment and retains its
-mathematical attribution. Host tests cover union decomposition, concavity, narrow
-gaps, grazing packet paths, offsets, sparse/nested owner addresses, three/four-level
-source timing, unchanged constant dispatch, remapping and shifted/unshifted actual
-kernel arithmetic compiled as host C++. These are not CUDA or flow validation.
-
-## Reviewed bounded evidence
-
-The `1aa8110` CUDA gate, with production exactly `a135252`, passed exact-dev
-omitted/default and explicit-constant equivalence, per-population reconstruction,
-scalar/union/four-level scheduling, alternate layouts, and changed remapping in
-both storage modes. Operator maximum error was 2.98023224e-8; the eight-step
-concave replay maximum was 1.58037614e-7. Whole-step mass/momentum remain
-finite diagnostics, not an FP32 conservation certificate. Reviewed evidence:
-`7aa66ff0542175092753ea099f40b903ece0527e`.
-
-The fresh four-case `2cf9853` N128/256 Taylor–Green repeat retained all `11901a7`
-settings and gates. All 20 main scalar rows and 260 early-pressure samples matched
-the older receipts exactly; this is not field-array equality. Projected worst
-velocity was 0.001995299260844 versus 0.002 (only 0.235% margin), pressure
-0.012157174904932 and energy 0.001184362645162. Constant velocity
-0.004418076615223 failed its gate, so the aggregate verdict remains false.
-The projected early sampled pressure peak was 0.021621453573334; it remains a
-descriptive sampled maximum. Reviewed evidence: `90849a55cad4a0da9b72747da7bfe6eb75962a44`.
-
-The old N64 projected failures remain relevant. These results support only this
-bounded plumbing gate and short periodic Re100 smooth-decay experiment. They do
-not establish union/multilevel physics accuracy, convergence, long-time stability,
-body/Jet, boundary, forcing, MRT or LES suitability. Constant remains the default.
-
-## Separate LES source profile
-
-The two older LES source manifests and the historical default are unchanged and
-correctly reject this different source tree. The existing LES runner now offers
-`--experiment a135252`, pinning all 101 actual committed corrected source files.
-Its explicit baseline-header override describes only a synthetic isolated reverse
-control, never the committed a135252 header. The unchanged corrected-only uniform
-LES regression (Cs=0/.16/1) is the remaining integration gate; no LES result is
-inherited from the projected evidence. The separate historical jet-CV `channel.py`
-pin mismatch predates this port and is not addressed here.

docs/development/refinement_mrt.md

@@ -1,34 +0,0 @@
-# MRT reuse in blocked/refined stepping (candidate)
-
-Base `9805383`. Opt-in by `LBMConfig(collision="MRT")`; SRT remains the default and its
-kernel statements, including the shifted retained-delta/direct-momentum path, are unchanged
-under the alternate compile branch.
-
-## What changes
-- `blocks.cu` (`BlockStep`), `step/block_channel.cu` (`BlockChannelStep`) and `refinement.cu`
-  (`patch_collide`) gain a compile-time `COLLISION_MODEL == 2` branch that repeats the uniform
-  `collide_dispatch` sequence with zero forcing: `compute_rho_u`, omega clamp to
-  `[OMEGA_COLLISION_MIN, OMEGA_COLLISION_MAX]`, `collide_mrt_no_force`.
-- Kernel and host guards accept SRT or MRT only. TRT, LES, non-FP32 storage, non-double-buffer
-  streaming, and shifted dense/mixed refinement remain rejected.
-- Transfers, subcycling, BFL, raw exchange ledgers and channel closures are untouched. The
-  existing pressure-NEQ outlet selects its MRT branch (unknowns-only NEQ extrapolation) from
-  `COLLISION_MODEL`, so MRT channel parity must use uniform MRT as reference.
-
-## Contracts (existing operator, not redefined here)
-- Shifted storage uses the existing MRT representation (equilibrium moments from `rho - 1`),
-  not the SRT retained-delta/direct-momentum precision. Mass and momentum are conserved
-  moments (relaxation rate 0).
-- Kinetic rates are the operator's fixed `s_e = s_eps = s_q = 1.2` on every level; the shear
-  rate is the existing per-level omega. Under acoustic 2:1 scaling the physical bulk viscosity
-  therefore halves on each finer level. No rate rescaling is applied.
-- 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) remains SRT-only.
-
-## Evidence status
-CPU: `tests/unit/test_refinement_mrt.py` (host guards, source contract). GPU:
-`tests/validation/multigrid/test_refinement_mrt_gpu.py` (uniform-MRT channel parity, AMR MRT
-smoke) and unchanged SRT GPU tests. Strict parity may be subject to cross-kernel FMA
-contraction differences already documented for SRT. Not a DFG/benchmark validation.

docs/development/root_channel_candidate.md

@@ -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`:
 

docs/fixed_three_level_multipatch.md

@@ -1,26 +1,23 @@
-# Fixed three-level rectangle unions
+# Fixed three-level separated patches
 
-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
-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.
+`FixedPatchStepper` supports exactly three static, blocked levels with separated
+rectangle sets on either adjacent pair. This is not general AMR: there is no
+per-region timestep, moving geometry, dynamic refinement or L1 body support.
 All regions share one current/spare buffer pair per level. The existing schedule
 advances L0 once, L1 twice and L2 four times per base step, with aggregate transfers.
 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)`.
@@ -33,23 +30,20 @@ are physically equivalent to parent set `[(4,4,12,12)]` with child set
 `[(8,8,16,16)]`. Reusing the same numbers after changing the parent frame can
 move the physical region.
 
-Both adjacent pairs are built from their unions, without a fixed rectangle-gap
-rule. Adjacent, overlapping and concave unions are accepted only when their
-actual transfer dependencies close. The whole child union must preserve
-inherited ACTIVE coverage, uncovered ACTIVE donors/receivers, surviving pulls, and the upstream
+Both adjacent pairs require a Chebyshev gap of at least four in their own
+parent-cell units. The whole child union must preserve inherited ACTIVE
+coverage, uncovered ACTIVE donors/receivers, surviving pulls, and the upstream
 restriction footprint. Sparse holes remain unowned; inherited INNER remains
-stream-only and OUTER remains invalid. Block sizes must divide their allocated
-level grids. Sparse storage owns every grid-aligned tile intersecting the union
-plus its four-cell ghost band; rectangle and support edges need not align with
-tile edges.
+stream-only and OUTER remains invalid. Block sizes must align with every
+support edge, including its four-cell ghost band.
 
 ## Example
 
 ```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 +51,7 @@ 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
@@ -71,12 +65,6 @@ CPU geometry, table, pre-CUDA rejection, schedule and cleanup tests:
 PYTHONPATH=src python -m unittest discover -s tests/unit -p 'test_refinement*.py' -v
 ```
 
-`tests/unit/test_union_refinement.py` covers union dependencies and tile
-ownership; `tests/unit/test_hierarchy.py` covers composed geometry through four
-levels. `tests/unit/test_raw_exchange.py` checks the four-level host schedule
-with CUDA mocks. These establish topology/control-flow coverage, not numerical
-qualification at every depth or interface shape.
-
 Explicit GPU gates are in
 `tests/validation/multigrid/test_refinement_three_level_multipatch_gpu.py`.
 They cover physical-frame equivalence, twins, asymmetric refinement, multiple

docs/supported_settings.md

@@ -1,87 +0,0 @@
-# Supported settings: 2D Jet + fixed multilevel refinement (candidate c95a7ba)
-
-Every entry names the guard that enforces it (file:line at c95a7ba) and, where one
-exists, an existing test that exercises it. A setting not listed here is not
-claimed. Observations at the end are tied to the exact case in which they were
-measured; they are not general bounds.
-
-## Lattice, storage, collision
-
-| Setting | Supported | Guard |
-|---|---|---|
-| Dimension / lattice | 2D D2Q9 only (3D refinement is future work) | `lbm/refinement.py:65`, `lbm/kernels/blocks.cu:25`, `lbm/kernels/refinement.cu:26` |
-| Precision / streaming | FP32 storage, double buffer | same guards |
-| Collision on refinement levels | SRT or MRT; TRT and LES rejected | `lbm/refinement.py:65` (re-checked for fine boundaries at `lbm/refinement.py:457`) |
-| Shifted (ddf_shifting) storage | only when every level is blocked; dense or mixed rejected | `lbm/refinement_stepper.py:198`, `:469`; `lbm/kernels/refinement.cu:26` (dense patch kernel unshifted only) |
-| Fine relaxation | 1/tau_fine must lie inside the configured omega guards | `lbm/refinement.py:80` |
-| Uniform blocked backend `PeriodicBlockStepper` | doubly periodic, SRT only, stationary passive circles | `lbm/block_stepper.py:84`, `:91`, `:45`-`:67` |
-
-Tests: `tests/unit/test_refinement_mrt.py`, `tests/validation/multigrid/test_refinement_mrt_gpu.py`,
-`tests/unit/test_shifted_storage.py`, `tests/unit/test_shifted_block_operators.py`.
-
-## Refinement hierarchy (`FixedPatchStepper(cfg, *, context, refinements, ...)`)
-
-| Setting | Supported | Guard |
-|---|---|---|
-| Depth | at least one refinement level; one entry per level in `level_blocks`/`level_objects`/`level_jets` | `lbm/refinement_stepper.py:72`, `:75` |
-| Single L1 rectangle | two-coarse-cell margin to the domain edge | `lbm/refinement.py:73` |
-| Several L1 rectangles (union) | require `level_blocks[0]` and `level_blocks[1]`; transfers must close (dependency checks, no fixed gap rule) | `lbm/refinement_stepper.py:84`; `lbm/refinement.py:283`-`:295` |
-| Nested levels | depth >= 3 must be all blocked; a blocked level requires blocked levels below; a scalar child needs a scalar parent | `lbm/refinement_stepper.py:82`, `:87`; `lbm/hierarchy.py:54` |
-| Nested transfer support | child only over inherited ACTIVE cells, donors/receivers uncovered ACTIVE, no child over the parent restriction footprint | `lbm/refinement.py:391`-`:407` |
-| Tile shape | positive `(by, bx)`; the level allocation must be divisible by the tile (no partial tiles yet) | `lbm/refinement_stepper.py:78`, `lbm/refinement.py:246` (shape); `lbm/blocks.py:134` (divisibility) |
-| Coarse boundary | `periodic`, `slot_reservoir` or `channel` | `lbm/refinement_stepper.py:177` |
-| `slot_reservoir` | on-site velocity bottom slot, reservoir top, velocity 0, 2 <= slot width < nx, patch rows 4..ny-4 | `lbm/refinement_stepper.py:205`, `:212`; `lbm/refinement.py:546` |
-| `channel` | all levels blocked; Zou-He inlet, pressure-NEQ outlet, stationary bounce-back walls; transfers away from the closure | `lbm/channel.py:22`, `:26`, `:43`, `:54` |
-| Explosion | `constant` (default); `projected_linear` only periodic, all-blocked SRT, no bodies/Jets, no LES (experimental) | `lbm/refinement_stepper.py:188`, `:193` |
-| L2 runtime remap (`remap_child`) | periodic three-level L2 sets only, no L0/L1 bodies, identical pinned boundary | `lbm/refinement_stepper.py:557`, `:567`-`:581` |
-
-Tests: `tests/unit/test_refinement_three_level_multipatch.py`, `tests/validation/multigrid/test_refinement_multipatch.py`,
-`test_refinement_three_level.py`, `test_refinement_three_level_multipatch_gpu.py`, `test_refinement_blocked_base.py`,
-`test_refinement_blocked_fine.py`, `test_channel_root_gpu.py`, `tests/unit/test_channel_root.py`,
-`tests/unit/test_projected_pair_stepper.py`, `test_runtime_child_remap_gpu.py`, `test_pinned_body_remap_gpu.py`.
-
-## Bodies and Jets on refined levels
-
-| Setting | Supported | Guard |
-|---|---|---|
-| Bodies | stationary circles without sensor/force-region roles, entirely inside the patch union, fully resolved, disjoint, stencil away from the two-hop transfer footprint | `lbm/refinement.py:474`-`:542` |
-| Level | not on L0; only on the finest level of a nested hierarchy | `lbm/refinement_stepper.py:80`, `:89` |
-| Jet condition | velocity only; `pressure` is reserved and raises NotImplementedError | `body/jets.py:148`, `:150` |
-| Jet geometry | each Jet selects resolved links of exactly one stationary body; no Jet/Jet or Jet/SurfaceActuation overlap; abs(amplitude) < 1 lattice | `body/jets.py:155`, `:175`, `:177`, `:255`, `:261`, `:263` |
-| Jets with shifted storage | only in the all-blocked stepper with SRT and no LES | `body/jets.py:249` |
-| SurfaceActuation | unshifted storage only | `body/objects.py:155` |
-| Raw boundary exchange (force) | blocked body levels only; the window ledger requires `observe_raw_exchange` | `lbm/refinement_stepper.py:264`, `:269` |
-| Checkpoint with Jets | refused | `simulation.py:687` |
-
-Raw exchange is the cut-link momentum reaction (wall + aperture), not a validated
-nozzle thrust or stress load. Jet amplitude is a lattice velocity, not a flow rate.
-
-Tests: `tests/unit/test_jets.py`, `test_jets_review.py`, `test_shifted_jets.py`, `test_raw_exchange.py`,
-`tests/validation/multigrid/test_refinement_jets.py`, `test_shifted_jets_gpu.py`, `test_raw_exchange_gpu.py`,
-`test_exchange_window.py`, `test_fine_surface_gpu.py`.
-
-## Observations from specific tested cases (not general bounds)
-
-- SRT channel root vs uniform OneStep, strict-parity test
-  `tests/validation/multigrid/test_channel_root_gpu.py::ChannelRootGPU::test_uniform_matched_root`:
-  in one of its 18 sub-cases (2 storage modes x 3 profile/clamp/damp settings x 3 blocks; which
-  one is not recorded), 1 of the 4320 compared values differs, max abs 2.33e-10, max rel 1.77e-7
-  (about 2 ULP). The test remains failed; its cause and any general bound are unresolved.
-- MRT root parity test
-  `tests/validation/multigrid/test_refinement_mrt_gpu.py::RefinementMRTGPU::test_uniform_matched_mrt_root`
-  (12 sub-cases: 2 storage modes x 2 profiles x 3 blocks, default outlet settings) passed bitwise
-  in the Horsea focused GPU run at K1 7813334 (2026-10-21).
-- Periodic Taylor-Green Re 100, measured at 36ffc8b1 (V3 matched pair, N128 depth 2):
-  every per-sample screen passed; the constant explosion's aggregate worst velocity L2,
-  0.004418, exceeds its preregistered 0.002 budget, while projected_linear passed that budget.
-- Curved-wall pressure (pilot harness, exact-q analytic annulus, tau 0.8): the coarse swirl r1
-  case exceeded its terminal density-gain cap (1.105e-4 vs 1e-4), so the frozen 9-case matrix
-  is NOT_ESTABLISHED. No validated fix exists. This is a pilot harness, not production code.
-- DFG 2D-1 Re 20 (V4, SRT, t* 60, pressure-NEQ outlet and local Zou-He inlet): refined and uniform
-  runs were NOT_STEADY under the frozen steady rule, so no interval verdict was given.
-
-## Not supported in this release
-
-3D, dynamic/automatic AMR (tagging, time-varying hierarchies beyond `remap_child`),
-moving bodies on refined levels, pressure Jets, Jet checkpoints, LES or TRT on refined
-levels, partial (non-dividing) tiles.

docs/synchronized_leaf_remap.md

@@ -1,15 +1,11 @@
 # Synchronized leaf G remap and manual continuation
 
 This is a CPU state-transfer component, **not a runtime adaptive solver**.
-It changes only an L2 rectangle union in a three-level periodic hierarchy.
-The body-free case is shown first; stationary L2 bodies/Jets follow the bounded
-support contract below. L0/L1 topology, relaxation parameters, direction order,
+It changes only a separated L2 rectangle set in a three-level, body-free,
+periodic hierarchy. L0/L1 topology, relaxation parameters, direction order,
 physical frame and completed time remain unchanged. Existing geometry checks
-validate child support/nesting and actual transfer dependencies, without a fixed
-rectangle-gap rule. The three-level remap limit is unchanged by the stepper's
-arbitrary-depth level-list support. The CPU helper itself adds no CUDA,
-scheduler, allocator, boundary handling, collision or ghost refill. A bounded
-runtime adapter is described below.
+validate child support/nesting and separation. The CPU helper itself adds no CUDA, scheduler, allocator, boundary handling,
+collision or ghost refill. A bounded runtime adapter is described below.
 
 ```python
 from CelerisLab.lbm.refinement import FixedPatchSet2D
@@ -33,13 +29,11 @@ origin is retained. Physical lower edges are `origin + spacing*(x,y)` on L0,
 `origin + spacing*(parent.fine_origin + (x,y)/4)` on L2.
 
 Factory options `coarse_boundary` and `objects` must declare `"periodic"` and
-an empty collection; L2 bodies use `child_objects` as described below.
-LBMConfig's channel settings do not select this operator's boundary mode.
-Geometry metadata is factory-created;
+an empty body collection (all levels). LBMConfig's channel settings do not
+select this operator's boundary mode. Geometry metadata is factory-created;
 manual mutation/forging of metadata is unsupported. Caller certifies the
-actual state matches the declared boundary and has no forcing, that all device
-work and old readers are quiescent, and that inputs are the **current owned-leaf
-postcollision G**.
+actual state has no bodies/forcing, that all device work and old readers are
+quiescent, and that inputs are the **current owned-leaf postcollision G**.
 Count/phase stamps check consistency, not freshness or active-buffer identity.
 
 `current_g` is three NumPy Q-major arrays `(9,ny,nx)`. For blocked inputs,
@@ -79,10 +73,9 @@ PYTHONPATH=src python -m unittest discover -s tests/unit -p 'test_synchronized_r
 
 `replacement = current.remap_child(rectangles)` returns a new ready
 `FixedPatchStepper` at the **same absolute step_count**. It supports only
-periodic three-level runs with no L0/L1 bodies and an existing L2
-`FixedPatchSet2D`; stationary L2 bodies/Jets follow the support contract below.
-Scalar or union L1 parents are supported; scalar `child=` is deliberately
-rejected. L0/L1, relaxation and block sizes stay fixed.
+body-free periodic three-level runs whose existing L2 uses
+`child_rectangles_in_parent`. Scalar or union L1 parents are supported; scalar
+`child=` is deliberately rejected. L0/L1, relaxation and block sizes stay fixed.
 No tagger, scheduler, in-place replacement, or general rollback is provided.
 
 The method holds the stepper lock, validates geometry, synchronizes its stream,
@@ -120,14 +113,13 @@ Per-population conservation is not an advancement target under collision.
 ### Bounded pinned-body extension
 
 `replacement = current.remap_child(rectangles, child_objects=original_objects)`
-also accepts stationary Circles inside the L2 union. Each body's **physical
-boundary, complete BFL support and current per-link velocity must remain
-identical**. Rectangles are not pinned: they may be split, merged or resized,
-and other fluid coverage may change, including within the same connected union,
-provided that physical support is unchanged. Existing nesting, union transfer
-dependencies, full-circle containment, reverse cut-link
-coverage and two-hop BFL transfer-footprint checks still apply. This is manual
-remapping, not adaptive body tracking or runtime body editing.
+also accepts stationary Circles in separated L2 rectangles. Every body’s
+**complete containing rectangle must remain identical**. Several bodies may
+share one pinned rectangle; there need not be any fluid-only rectangles.
+Separated fluid-only rectangles may be added, removed or moved. Existing
+nesting, four-cell gap, full-circle containment, reverse cut-link coverage and two-hop BFL
+transfer-footprint checks still apply. This is manual remapping, not adaptive
+body tracking or runtime body editing.
 
 Supply all original root edge-frame definitions in their construction order.
 Do not pass `current.child_boundary.objects`: those are projected fine-local copies.
@@ -136,8 +128,8 @@ state, remapping reprojects the supplied definition onto the old topology and
 compares exact ordered circle centers/radii, flags, physical cut links, body
 IDs, q, lever arms, hits, BFL support,
 legacy SurfaceActuation specification and current per-link velocity against
-the existing boundary. Omission, changed geometry/actuation or changed physical
-boundary/BFL support fail without device reads or allocations; reordered bodies fail
+the existing boundary. Omission, changed geometry/actuation and changed body
+rectangle fail without device reads or allocations; reordered bodies fail
 too. Root object IDs are still assigned by list position, as in the constructor.
 
 Jets are taken from the live L2 boundary, including the most recent successful
@@ -149,16 +141,12 @@ boundary and velocities must match exactly.
 typed `FineBoundary2D`; it derives L2 fluid leaves as ACTIVE minus SOLID. No
 caller mask is accepted. Solids, ghosts and holes are never donors and remain
 NaN, physical-fluid overlap is exact, and exposed L1 still restricts all four
-old fluid children. The helper checks old/new physical boundary and velocity
-equality too. Its immutable `pinned_rectangles` is legacy containment metadata,
-not a remap eligibility constraint; it may be empty for a seam-spanning body.
-Scalar-parent window offsets remain part of the coordinate conversion.
+old fluid children. The helper checks the old/new body pins and boundary too.
+Its immutable `pinned_rectangles` is a canonical, deduplicated tuple, empty for body-free layouts; rectangle input
+order does not affect it. Scalar-parent window offsets remain part of the
+coordinate conversion.
 
-Focused CPU mocks: `tests/unit/test_pinned_body_remap.py`.
-`tests/unit/test_union_body_support.py` also checks seam-spanning circles,
-rectangle repartition/resize, unchanged physical support and live-Jet
-preservation. These host checks do not establish GPU evolution accuracy.
-GPU declarations:
+Focused CPU mocks: `tests/unit/test_pinned_body_remap.py`. GPU declarations:
 `tests/validation/multigrid/test_pinned_body_remap_gpu.py`, covering no-op
 next-step bitwise identity, moved-fluid A→B→A, current-amplitude preservation,
 physical boundary/velocity equality, source independence and absolute counts.

docs/validation/2d_scope.md

@@ -1,53 +0,0 @@
-# Bounded 2D implementation and validation scope
-
-This inventory starts from dev `8403956a9afc0b0bb89265cec374392013d89016` and
-integrates only the reviewed LES normalization production correction from
-`95cb6d2b9f43c1bdd46cbf27f03f0dfc0877cfb0`. The merged production bytes match that
-tested candidate exactly; the scope-test changes are retained from `53fad767`.
-GPU receipts remain associated with their exact tested commits, not relabeled as
-a new merged-commit run. Historical source identities and gates remain unchanged.
-
-## Implementation boundaries
-
-- Uniform D2Q9 supports SRT, TRT and MRT. An available collision selector does not
-  qualify every wall, inlet/outlet, forcing, storage or LES combination.
-- Fixed refinement supports SRT/MRT, FP32 and double-buffer streaming; TRT and LES
-  are rejected. Shifted refinement requires all-blocked storage. Refined channel
-  boundaries have narrower configuration guards than uniform boundaries.
-- Uniform checkpoints support compatible same-method continuation. Changing
-  collision or LES parameters is a different evolution, not exact continuation.
-  Jet checkpoints and refined checkpoints are unsupported; synchronized remapping
-  is not persistent restart.
-- Keep these conclusions 2D. Local D3Q19 operator tests do not establish a supported
-  3D Simulation runtime.
-
-## Evidence and remaining gaps
-
-| Area | Available evidence | Boundary of the conclusion |
-|---|---|---|
-| MRT cylinder flow and observation windows | Full matched uniform/refined MRT DFG and the window-ledger campaign passed their frozen periodicity, reference and matched-comparison gates. The window campaign used `185a919`; its MRT/no-LES numerical path remains unchanged. Current dev also contains independently scoped test/documentation changes and the LES correction, which do not extend MRT qualification. | This does not qualify other collision/boundary combinations or every refinement interface. Timing improvements are not additional accuracy evidence. |
-| Uniform forced channel | Six Poiseuille GPU cases on `8403956`: SRT/TRT/MRT at wall-normal resolutions H16/H32 passed. | This is the tested analytic channel configuration, not open-boundary or all-layout qualification. |
-| Uniform restart | Ten SRT/MRT checkpoint GPU tests passed on `8403956`; the separate representative TRT same-method double-buffer continuation GPU case also passed (one test). | This covers the tested same-method continuation configurations. No LES, Jet or refined checkpoint claim follows. |
-| Taylor–Green refinement | Independent topology checks are available. The actual-rate phase GPU regression passed one test across two layouts, with errors 1.584e-7 and 4.500e-9. | The physical interface-accuracy gap remains open. Passing topology and phase checks does not establish convergence or close that accuracy gate. |
-| Porous Couette and annulus | Prior campaign evidence exists and must remain associated with its original setup and source. | The reconstructed annulus is a validation helper, not qualification of a public boundary-condition API. Do not infer absence of evidence from a missing current rerun. |
-| LES normalization | The reviewed correction is integrated. Exact `95cb6d2` GPU validation passed all nine observations and frozen gates, with three warm-up/reset records, verified 101-source/import identity, DONE and exit 0. Last two SGS decrement relative errors were 6.276e-4 and 6.124e-5 against the unchanged 0.15 gate. | Scope is unforced uniform D2Q9/SRT, shifted FP32, double-buffer streaming and the tested wall-bounded x-periodic shear. No TRT/MRT LES, forcing, EsoPull, objects, refinement or 3D turbulence qualification follows. |
-
-Historical uniform SRT cylinder-startup and inlet-rounding findings remain separate
-from the passed MRT DFG result. Raw exchange/window consistency is a measurement
-contract, not a general stress or force-accuracy certification. Existing source-pinned
-runners may intentionally reject a newer checkout; never silently repin old receipts.
-
-## Remaining work
-
-The related host checks passed (67 checks); they do not replace the GPU or
-physical-accuracy evidence above. Preserve the existing SRT checkpoint cases,
-historical LES manifests and all frozen numerical criteria.
-
-Continue the TG accuracy investigation using its actual fine-level rates and
-the established analytic convention. Keep the physical accuracy gate open until
-the relevant comparison passes. Review this integration independently before
-publication; no new merged-commit GPU run is claimed here.
-
-No repeat of the accepted full MRT DFG or Cartesian expansion across unsupported
-combinations is required by this document. Main integration remains a separate
-review of complete, bounded feature scope.

docs/validation/dfg_re20.md

@@ -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`.

docs/validation/refined_dfg_mrt.md

@@ -1,71 +0,0 @@
-# Matched MRT DFG pilot preparation
-
-Preparation only: this test-only extension reuses the existing runner and existing MRT
-operator. GPU admission awaits reviewed MRT capability results; no pilot/full execution
-is implied by CPU preflight. No production, historical SRT manifest, reference data,
-periodic gate, geometry, initialization or observation algorithm is changed here.
-
-## Selection and provenance
-
-Use `--collision MRT` for **both** uniform D80 and refined root D40/fine D80. There are
-no independently selectable collision models per case. Default remains SRT.
-
-MRT verifies `data/refined_dfg/source_manifest_mrt.json`, pinned to reviewed numerical
-source snapshot `3ea131e92c057843034f11a1c574301a2430dfce`, including the shared geometry,
-pressure/cycle helpers and official reference. Test-only commits may change HEAD without
-changing this numerical source pin. Plan, READY, case summaries and comparison separately
-record `checkout_revision` and `checkout_dirty` using existing source-provenance helper;
-the runner hash remains separate. Collision is recorded in every receipt, and full-mode
-validation rejects missing or different collision labels in plan, either summary or either
-READY receipt, in addition to existing source/runner/health/time checks.
-
-The historical SRT manifest remains byte-for-byte unchanged. SRT on the MRT candidate
-checkout deliberately fails that source pin; use a matching historical checkout via
-`--source` for SRT. No fallback or automatic repinning is permitted. Historical SRT
-failure/diagnostic evidence remains attached to its original source and runner hashes;
-it cannot authorize an MRT full run. The existing failed-observation step-reporting
-undercount is not changed in this narrowly scoped selection patch.
-
-## Frozen physical comparison
-
-All settings remain those documented in `refined_dfg.md`: U_lattice=.01, physical mean
-U=1 m/s, D=.1 m, shear ν=.001 m²/s, fixed physical domain/body/wall planes, patch
-(40,24,320,140), shifted FP32 double buffers, no LES/forcing/Jets, finest dx=.00125 m,
-finest dt=.0000125 s, unchanged half-cell frame conversion and axis-specific phase.
-Force interval accumulation, physical leaf mass, pressure interpolation, flux sampling,
-safety thresholds, t*=5 pilot and t*=300 cap are unchanged. Existing accuracy/periodicity
-criteria are imported unchanged. Both MRT cases are fresh runs; old MRT or SRT results
-are not substituted as controls.
-
-Both cases use the **existing MRT pressure-NEQ branch**: only unknown directions q2/6/8
-are extrapolated. This differs from SRT's all-nine .5-damped branch; the retained
-`srt_neq_damp=.5` configuration value is inactive under MRT. Backflow clamp remains off.
-The outlet is still noncanonical relative to exact DFG do-nothing conditions.
-
-The reused MRT operator keeps fixed kinetic rates `s_e=s_eps=s_q=1.2` on all levels;
-only the shear rate follows existing per-level viscosity. Physical bulk relaxation
-therefore differs between coarse and fine levels. Transfer operators and subcycling
-are unchanged. This is the candidate's declared behavior, not a new fully mode-scaled
-MRT transfer scheme. Do not tune rates, the patch or gates after seeing outcomes.
-Capability smoke/parity gates do not establish DFG accuracy or speedup.
-
-## CPU and admission commands
-
-From this checkout:
-
-```sh
-python tests/unit/test_refined_dfg.py
-python tests/validation/run_refined_dfg.py --collision MRT --mode plan --output /tmp/new-mrt-dfg-plan
-```
-
-After root verifies the candidate MRT root/parity/refinement capability results and admits
-an idle device, the paired pilot may use the existing bounds and external watchdog:
-
-```sh
-CUDA_VISIBLE_DEVICES=<admitted-device> timeout --signal=TERM --kill-after=30s <hard-budget>s python tests/validation/run_refined_dfg.py --collision MRT --mode pilot --gpu-gates-approved --max-wall-seconds <soft-budget> --output <new-mrt-pilot-directory>
-```
-
-The flag is caller attestation, not evidence. An unhealthy first case prevents the second.
-Existing strict pilot receipt validation and calibrated wall-time controls remain; full
-mode is not being admitted as part of this preparation. Root must review both healthy
-pilot outcomes and separately decide any full-run admission.

docs/validation/refined_dfg_timing.md

@@ -1,58 +0,0 @@
-# Refined DFG MRT timing harness (measurement only)
-
-`tests/validation/time_refined_dfg.py` times the matched MRT refined/uniform DFG Re100 setup of
-`run_refined_dfg.py` (same configuration, geometry and initial state functions). No numerical,
-physics-gate or production change; no force or accuracy result is produced.
-
-| Variant | Loop | Force reads |
-|---|---|---|
-| A | refined `step(1)` + `read_raw_exchange` per base step | runner-like force-read workload (values discarded) |
-| B | refined `step(1)` only, no host reads (`observe_raw_exchange` stays on) | timing-only |
-| C | refined single `step(N)` | timing-only; ledger keeps the final base interval only |
-| E | uniform `sim.run(<=100)` + `read_force` | runner-like force-read workload (values discarded) |
-| E' | uniform single `sim.run(2N)` | timing-only; at most a whole-window average, different summation order |
-
-- No variant retains a valid force history; A/E omit the runner's interval aggregation and
-  validation, and no variant includes macro/probe/CSV costs. Results are not full benchmark
-  throughput.
-- Status lines: `CONSTRUCTED` (construction/JIT complete) and `WARM_READY` (first warm-up and
-  health check passed) per case.
-- Equal simulated duration: N refined base steps vs 2N uniform D80 steps.
-- Every repeat starts from the same fresh state (refined `initialize`, uniform `snapshot/restore`)
-  and the same warm-up; construction/JIT, warm-up, downloads and parity checks are untimed.
-- The actual stepping stream is synchronized explicitly before and after each timed loop; the
-  wall timer (`time.perf_counter`) is the only source. No CUDA-event span is called kernel time.
-- `--max-wall-seconds` is required for GPU runs (outer timeout, checked between variants and
-  every 100 steps in per-step loops).
-- Final populations and NaN masks must be bitwise identical to the first A repeat (A/B/C) or the
-  first E repeat (E/E'); refined and uniform grids are never compared. Leaf/fluid populations
-  must be finite. Physical health (finite leaf/fluid macros, rho in [0.5, 1.5], max Mach <= 0.2,
-  the existing runner limits) is checked after warm-up and after each timed window. Matching NaN
-  is accepted only as a storage mask; any infinity or level-count mismatch fails parity. All
-  parity/health checks are untimed.
-- Cases run sequentially (uniform, then refined) in one process with startup serialized;
-  variants are interleaved within each repeat. A-B and B-C are measured comparative
-  differences under GPU variability, not exact causal decompositions.
-
-Usage (root selects one verified idle GPU):
-
-    PYTHONPATH=src python -m unittest tests/unit/test_time_refined_dfg.py
-    python tests/validation/time_refined_dfg.py --output <new> --plan
-    CUDA_VISIBLE_DEVICES=<gpu> python tests/validation/time_refined_dfg.py --output <new> --max-wall-seconds <s>
-
-Defaults: 2000 base steps, 200 warm-up base steps, 3 repeats. Profiler capture and the
-`observe_raw_exchange=False` variant are deferred until these measurements exist.
-
-## A versus observation-window ledger (`tests/validation/time_window_dfg.py`)
-
-Measurement-only comparison on the same shifted-MRT refined setup: A (per-base `step(1)` +
-`read_raw_exchange`, summed per 80-base-step interval), W (`start_exchange_window`, `step(80)`,
-one window read) and W1 (window with 80 x `step(1)`, isolating the read pattern from call
-batching). Same fresh state, warm-up and simulated duration; populations must be bitwise equal
-to the first A repeat and per-interval total impulses within the documented engineering
-tolerance, all outside timing. The candidate source is recorded (checkout revision, dirty flag,
-file hashes); frozen refined-DFG manifests/results are not used or changed.
-
-    PYTHONPATH=src python -m unittest tests/unit/test_time_window_dfg.py
-    python tests/validation/time_window_dfg.py --output <new> --plan
-    CUDA_VISIBLE_DEVICES=<gpu> python tests/validation/time_window_dfg.py --output <new> --max-wall-seconds <s>

docs/validation/refined_dfg_window.md

@@ -1,117 +0,0 @@
-# Opt-in observation-window ledger in the DFG runner
-
-This test-only integration adds `--exchange-window` to `run_refined_dfg.py`. It uses the
-existing production ledger; no collision, boundary, transfer, physical setup, reference,
-periodicity gate or acceptance threshold changes. Default remains the historical
-per-base-step observation path. Uniform stepping/force accumulation is unchanged.
-
-For the refined case, each existing observation interval opens a new ledger at completed
-base step `begin`, advances exactly the same `n` base intervals, and reads the integrated
-root-lattice impulse for `[begin, begin+n]`. The contract requires root units, `window`
-kind, `2*n` fine samples, matching endpoints, and fine dt=.5. The existing coefficient
-calculation still divides this impulse by `n` and `.5*U_lattice**2*D_root`; force timestamps
-remain `(begin+n/2)*U_lattice/D_root`. It does not divide an already averaged force again.
-Pressure/macro/physical-leaf mass measurements and safety checks remain at the original
-interval end. Pilot interval is 80 root steps; early full-run intervals remain 2000, and
-any final shortened interval uses its actual `n`.
-
-The opt-in uses one `step(n)` call and one window read per observation, rather than `n`
-Python calls/readbacks. Internal subcycling and per-base synchronization remain owned by
-the same backend. Cooperative deadline checks surround that complete interval; unlike
-the default path they cannot interrupt between base steps inside `step(n)`. The existing
-external hard watchdog is still required. The full-run cadence/cap is documented here,
-but this preparation does not admit a full run or a GPU operation.
-
-## Provenance and receipt separation
-
-`source_manifest_window.json` pins the reviewed a233c9032487a6006e950d1e327079b00466c410
-snapshot (production ledger origin d930) plus existing helper/reference files. Both SRT
-and MRT are supported by this explicit opt-in source pin; collision selection remains
-independent and shared by the two cases. Existing SRT and MRT manifests are untouched.
-Default mode continues to reject the changed candidate under those historical pins;
-use a matching historical `--source` checkout to run its default path. There is no
-silent repinning, source fallback, or reuse of historical outputs as candidate evidence.
-
-Plan, READY, summaries, timeout/comparison receipts now record `observation_mode` as
-`last_base_step` or `window`, alongside collision and actual checkout provenance. On a
-uniform receipt this labels its **paired campaign's refined observation mode**, not a
-change to uniform observation. Full-mode pilot validation rejects missing or mismatched
-mode labels in the plan, either case summary, and either READY receipt. Source/runner
-hash, collision, completeness and health checks remain. Cross-mode pilot reuse is denied.
-
-The earlier short A/W/W1 timing/capability evidence is not a full-run speedup or accuracy
-claim. Mathematical impulse integration/units are unchanged; floating-point reduction
-order can differ, so bitwise equality of force sums is not promised. Physics acceptance
-continues to use the existing frozen gates. Historical failures/results are untouched.
-
-CPU preparation commands, from the repository root:
-
-```sh
-python tests/unit/test_refined_dfg.py
-PYTHONPATH=src python -m unittest tests.unit.test_raw_exchange_window tests.unit.test_time_window_dfg -v
-python tests/validation/run_refined_dfg.py --collision MRT --exchange-window --mode plan --output /tmp/new-window-dfg-plan
-```
-
-Root must independently review and admit any execution. An admitted paired pilot uses
-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.

examples/fixed_patch_circle.py

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

examples/fixed_patch_jet.py

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

examples/fixed_periodic_patch.py

@@ -48,7 +48,7 @@ def main():
                   nx=16, ny=16, viscosity=.1, velocity=1e-3, rho=1.0,
                   lattice_model="D2Q9", collision="SRT", streaming="double_buffer",
                   store_precision="FP32", ddf_shifting=False, les_enabled=False)
-    with CudaContext(0) as context, PeriodicPatchStepper(cfg, 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)

src/CelerisLab/body/jets.py

@@ -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

src/CelerisLab/body/manager.py

@@ -27,7 +27,7 @@ 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 .preprocess.flag_overlay import merge_flag_masks
 from ..cuda.compiler_v2 import obs_layout
 from ..cuda.obs_layout import ObsLayout
 from ..lbm.descriptors import (
@@ -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()

src/CelerisLab/body/preprocess/flag_overlay.py

@@ -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],

src/CelerisLab/cuda/compiler_v2.py

@@ -54,18 +54,14 @@ def _write(path: str, content: str):
 
 
 def generate_config(cfg: LBMConfig, n_objects: int = 0,
-                    *, build_root: Optional[str] = None, block_root_bc: int = 0) -> str:
+                    *, build_root: Optional[str] = None) -> str:
     """Snapshot kernels and render headers in a fresh private directory.
 
     Returns its path. Pass it explicitly to compile_kernel for interleaved
     builds. Legacy generate_config(); compile_kernel() remains context-local.
     The caller owns cleanup_build_dir() once the loaded module is no longer
     needed for recompilation/debugging. No package files are changed.
-    block_root_bc specializes a blocked root module; fine/dense builds use 0.
     """
-    if (isinstance(block_root_bc, bool) or not isinstance(block_root_bc, int)
-            or block_root_bc not in (0, 1, 2)):
-        raise ValueError("block_root_bc must be an integer mode 0, 1 or 2")
     macros = cfg.to_macros()
     if isinstance(n_objects, bool) or not isinstance(n_objects, int) or n_objects < 0:
         raise ValueError("n_objects must be a nonnegative integer")
@@ -75,15 +71,14 @@ def generate_config(cfg: LBMConfig, n_objects: int = 0,
     try:
         shutil.copytree(_KERNEL_DIR, build_dir, dirs_exist_ok=True,
                         ignore=shutil.ignore_patterns("*.ptx", "*.cubin", "*.tmp"))
-        _render_config(macros, n_objects, os.path.join(build_dir, "config"),
-                       block_root_bc=block_root_bc)
+        _render_config(macros, n_objects, os.path.join(build_dir, "config"))
         digest = hashlib.sha256()
         for path in sorted(Path(build_dir).rglob("*")):
             if path.is_file():
                 digest.update(str(path.relative_to(build_dir)).encode())
                 digest.update(path.read_bytes())
         metadata = {"source_sha256": digest.hexdigest(), "config": asdict(cfg),
-                    "n_objects": n_objects, "block_root_bc": block_root_bc}
+                    "n_objects": n_objects}
         _write(os.path.join(build_dir, ".celeris-build"), json.dumps(metadata, sort_keys=True))
     except BaseException:
         shutil.rmtree(build_dir)
@@ -106,7 +101,7 @@ def cleanup_build_dir(build_dir: Optional[str]) -> None:
         _last_ptx_path.set(None)
 
 
-def _render_config(m: dict, n_objects: int, cdir: str, *, block_root_bc: int = 0):
+def _render_config(m: dict, n_objects: int, cdir: str):
     _write(os.path.join(cdir, "config_grid.h"), f"""{_HEADER}\
 // Layer: Global / Grid
 #ifndef CELERIS_CONFIG_GRID_H
@@ -170,9 +165,6 @@ def _render_config(m: dict, n_objects: int, cdir: str, *, block_root_bc: int = 0
 #define STORE_PRECISION  {m['STORE_PRECISION']}
 #define USE_DDF_SHIFTING {m['USE_DDF_SHIFTING']}
 
-// Internal blocked root mode: 0=periodic/fine, 1=slot/reservoir, 2=channel.
-#define BLOCK_ROOT_BC {block_root_bc}
-
 #define USE_LES {m['USE_LES']}
 #define LES_CS  {m['LES_CS']}
 #define LES_CLOSED_FORM {m['LES_CLOSED_FORM']}

src/CelerisLab/lbm/block_stepper.py

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

src/CelerisLab/lbm/channel.py

@@ -1,4 +1,4 @@
-"""Host contract for the blocked root's uniform SRT/MRT channel boundary.
+"""Host contract for the blocked root's uniform-SRT channel boundary.
 
 Boundary ghosts are evolved state, but are not physical fluid leaves. Halo
 ownership remains periodic to reproduce the uniform kernel's wrapped pulls.
@@ -29,7 +29,7 @@ def validate_channel_config(cfg, blocks):
 def validate_channel_transfers(pair, layout, targets):
     """Reject actual exchange/closure overlap, not a padded geometric envelope.
 
-    Explosion donors and restriction receivers must use ordinary bulk collision
+    Explosion donors and restriction receivers must use ordinary bulk SRT
     semantics. Restriction writes receiver-local source slots; these may not
     overwrite the channel's extra immutable-input reads (pressure donor and
     same-node halfway-wall corrections). The slot check deliberately respects

src/CelerisLab/lbm/curved_links.py

@@ -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.

src/CelerisLab/lbm/kernels/blocks.cu

@@ -1,6 +1,5 @@
 // CelerisLab/lbm/kernels/blocks.cu
-// One fixed-size blocked level (lbm/blocks.py layout), specialized at compile
-// time for periodic/fine, slot/reservoir or channel stepping. Separate
+// One periodic level of fixed-size blocks (lbm/blocks.py layout). Separate
 // compilation entry: NX, NY are the block window including halo, so index_f
 // and linear_index address one block; blockIdx.z selects the block, whose
 // populations start at b*NQ*TOTAL_CELLS (block-contiguous, Q-major inside).
@@ -13,37 +12,151 @@
 #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"
+#include "boundary/planar_velocity.cuh"
 
-#if DIM != 2 || NQ != 9 || (COLLISION_MODEL != 0 && COLLISION_MODEL != 2) || STORE_PRECISION != 0 || USE_LES || STREAMING_MODEL != 0
-#error "Blocks require FP32 D2Q9 SRT or MRT double buffers without LES"
-#endif
-#ifndef BLOCK_ROOT_BC
-#error "Blocks require a generated BLOCK_ROOT_BC mode"
-#elif BLOCK_ROOT_BC < 0 || BLOCK_ROOT_BC > 2
-#error "BLOCK_ROOT_BC must be 0, 1 or 2"
+#if DIM != 2 || NQ != 9 || COLLISION_MODEL != 0 || STORE_PRECISION != 0 || USE_LES || STREAMING_MODEL != 0
+#error "Blocks require FP32 D2Q9 SRT double buffers without LES"
 #endif
 
-#if BLOCK_ROOT_BC == 1
-#include "boundary/block_wall.cuh"
-#endif
-#if BLOCK_ROOT_BC != 2
-#include "operators/block_collision.cuh"
-#endif
+// Fixed-patch cell kinds, matching refinement.py ACTIVE/INNER_GHOST/OUTER_GHOST.
+constexpr unsigned char KIND_ACTIVE = 0u, KIND_INNER = 1u, KIND_OUTER = 2u;
 
-// Kernels, in definition order: transfers, boundary staging, then the one full
-// step selected for this module (BlockStep, or BlockChannelStep for a channel root).
-#include "step/block_transfer.cu"
-#include "step/block_boundary.cu"
-#if BLOCK_ROOT_BC != 2
-#include "step/block_step.cu"
+// Zero-initialized for ordinary blocks/fine levels. Set only for parent walls;
+// NX/NY remain local storage strides, never physical wall coordinates.
+struct BlockWall { unsigned int nx, ny, slot_width; float amplitude; };
+extern "C" { __constant__ BlockWall d_block_wall; }
+
+// Halo refresh: block cell ids b*TOTAL_CELLS+c, sources are always core cells.
+extern "C" __global__ void BlockHaloCopy(
+    fpxx* f, const uint64_t* dst, const uint64_t* src, unsigned int count)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    const uint64_t d = dst[row], s = src[row];
+    fpxx* to = f + (d / TOTAL_CELLS) * NQ * TOTAL_CELLS;
+    const fpxx* from = f + (s / TOTAL_CELLS) * NQ * TOTAL_CELLS;
+    for (unsigned int q = 0; q < NQ; ++q)
+        to[index_f(d % TOTAL_CELLS, q)] = from[index_f(s % TOTAL_CELLS, q)];
+}
+
+// Fixed-patch explosion into blocked fine storage: target = owner block cell
+// id of a patch-ghost cell; donors are parent block cell ids. Dense parent
+// storage is the one-window case with coarse_cells = full domain size.
+extern "C" __global__ void BlockExplode(
+    const fpxx* coarse, fpxx* fine, const uint64_t* target, const uint64_t* donor,
+    unsigned int count, unsigned long coarse_cells)
+{
+    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
+    if (row >= count) return;
+    const uint64_t t = target[row];
+    fpxx* to = fine + (t / TOTAL_CELLS) * NQ * TOTAL_CELLS;
+    const uint64_t d = donor[row];
+    const fpxx* from = coarse + (d / coarse_cells) * NQ * coarse_cells;
+    for (unsigned int q = 0; q < NQ; ++q)
+        to[index_f(t % TOTAL_CELLS, q)] = from[q * coarse_cells + d % coarse_cells];
+}
+
+// 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);
+            }
+            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
-#include "step/block_channel.cu"
+            compute_feq(rho, ux, uy, feq);
 #endif
+            collide_srt_no_force(f, feq, d_params.omega);
+        }
+    }
+    stream_pull_store(k, f, out + base);
+}
+
+// Root channel closure; fine and periodic levels keep BlockStep.
+#include "step/block_channel.cu"

src/CelerisLab/lbm/kernels/boundary/block_wall.cuh

@@ -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

src/CelerisLab/lbm/kernels/boundary/bounce_back.cuh

@@ -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.
 //

src/CelerisLab/lbm/kernels/config/config_method.h

@@ -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

src/CelerisLab/lbm/kernels/core/cell_kind.cuh

@@ -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

src/CelerisLab/lbm/kernels/core/layout.cuh

@@ -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)
 // ---------------------------------------------------------------------------

src/CelerisLab/lbm/kernels/operators/block_collision.cuh

@@ -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

src/CelerisLab/lbm/kernels/operators/bounce_back_swap.cuh

@@ -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

src/CelerisLab/lbm/kernels/operators/collision_mrt.cuh

@@ -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,

src/CelerisLab/lbm/kernels/operators/helpers.cuh

@@ -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,

src/CelerisLab/lbm/kernels/refinement.cu

@@ -9,12 +9,8 @@
 #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/planar_velocity.cuh"
 #include "boundary/curved_boundary.cuh"
@@ -23,8 +19,8 @@ extern "C" {
 #include "step/curved_double.cu"
 }
 
-#if DIM != 2 || NQ != 9 || (COLLISION_MODEL != 0 && COLLISION_MODEL != 2) || STORE_PRECISION != 0 || USE_DDF_SHIFTING || USE_LES || STREAMING_MODEL != 0
-#error "Refinement requires unshifted FP32 D2Q9 SRT or MRT double buffers without LES"
+#if DIM != 2 || NQ != 9 || COLLISION_MODEL != 0 || STORE_PRECISION != 0 || USE_DDF_SHIFTING || USE_LES || STREAMING_MODEL != 0
+#error "Refinement requires unshifted FP32 D2Q9 SRT double buffers without LES"
 #endif
 
 // Enabled only in the validation build; no diagnostic arrays in normal builds.
@@ -37,14 +33,10 @@ __device__ unsigned int incoming_counts[NQ * TOTAL_CELLS];
 #endif
 
 __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
@@ -72,7 +64,7 @@ extern "C" __global__ void PatchFineStep(const float* in, float* out, const uint
     // 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);
+        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.

src/CelerisLab/lbm/kernels/step/block_boundary.cu

@@ -1,42 +0,0 @@
-// CelerisLab/lbm/kernels/step/block_boundary.cu
-// Receiver-local curved-boundary staging and its raw-exchange accumulation.
-// Part of the blocks.cu compilation entry; relies on its includes and guards.
-
-// Static cut links, receiver-local staging: cell is the receiver's local core
-// cell, so the existing BFL writes the solid-source window image that this
-// block's next pull reads (no halo copy between this kernel and BlockStep).
-// surface_velocity (nullable, 2 floats per link): prescribed fluid velocity on
-// fixed geometry, same convention as CurvedBoundaryKernel. Optional raw rows
-// (jx,jy,torque,dm) are unique physical links, never body-observation slots.
-extern "C" __global__ void BlockCurvedBoundary(
-    fpxx* f, const uint32_t* block, const uint32_t* cell, const unsigned char* dir,
-    const float* q, const unsigned char* fallback, unsigned int count,
-    const float* surface_velocity, const float* rx, const float* ry, float* raw)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    float Uw = 0.0f, Vw = 0.0f;
-    if (surface_velocity != nullptr) {
-        const float u = surface_velocity[2 * row], v = surface_velocity[2 * row + 1];
-        if (u != 0.0f || v != 0.0f) { Uw = u; Vw = v; }
-    }
-    apply_bouzidi_link(dir[row], q[row], cell[row], f + (unsigned long)block[row] * NQ * TOTAL_CELLS,
-                       Uw, Vw, rx ? rx[row] : 0.0f, ry ? ry[row] : 0.0f,
-                       fallback[row], nullptr, -1, raw ? raw + 4ul * row : nullptr,
-                       raw ? raw + 4ul * row + 3 : nullptr);
-}
-
-// Same-stream BFL -> this row-owned accumulation -> pull step. No atomics,
-// no cross-row reduction and no history allocation proportional to substeps.
-extern "C" __global__ void BlockAccumulateExchange(
-    const float* raw, double* integral, unsigned int count, double h, double dt)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const unsigned long k = 4ul * row;
-    const double impulse = h * dt;
-    integral[k] += impulse * (double)raw[k];
-    integral[k + 1] += impulse * (double)raw[k + 1];
-    integral[k + 2] += h * impulse * (double)raw[k + 2];
-    integral[k + 3] += h * h * (double)raw[k + 3];
-}

src/CelerisLab/lbm/kernels/step/block_channel.cu

@@ -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);
@@ -36,29 +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);
-#else
             // Match uniform SRT arithmetic, including its shifted equilibrium path.
             float rho, ux, uy, feq[NQ], forcing[NQ] = {};
             compute_rho_u(f, rho, ux, uy);
             compute_feq(rho, ux, uy, feq);
             const float omega = fminf(OMEGA_COLLISION_MAX, fmaxf(OMEGA_COLLISION_MIN, d_params.omega));
             collide_srt(f, feq, forcing, omega);
-#endif
         }
     }
     stream_pull_store(k, f, out + base);

src/CelerisLab/lbm/kernels/step/block_step.cu

@@ -1,35 +0,0 @@
-// CelerisLab/lbm/kernels/step/block_step.cu
-// Generic blocked pull/collide/store for periodic/fine and slot/reservoir levels.
-// Part of the blocks.cu compilation entry; relies on its includes and guards.
-#if BLOCK_ROOT_BC == 2
-#error "BlockStep is not built for the channel root (BLOCK_ROOT_BC == 2)"
-#endif
-
-// Pull/collide/store core cells only; halo cells of out are left untouched.
-// flags (block cell ids, nullable): solid cores store NaN and never collide.
-// kind (block cell ids, nullable = all ACTIVE): OUTER skips the pull and
-// stores NaN, INNER pulls without collision, ACTIVE pulls and collides.
-extern "C" __global__ void BlockStep(const fpxx* in, fpxx* out, unsigned int halo,
-                                     const uint16_t* flags, const unsigned char* kind) {
-    unsigned int x, y; unsigned long k;
-    index_from_thread(x, y, k);
-    if (x < halo || y < halo || x >= NX - halo || y >= NY - halo) return;
-    const unsigned long base = (unsigned long)blockIdx.z * NQ * TOTAL_CELLS;
-    const unsigned long cell = (unsigned long)blockIdx.z * TOTAL_CELLS + k;
-    const unsigned char cell_kind = kind != nullptr ? kind[cell] : KIND_ACTIVE;
-    float f[NQ];
-    if (cell_kind == KIND_OUTER || (flags != nullptr && is_solid(flags[cell]))) {
-        fill_invalid(f);
-    } else {
-        unsigned long j[NQ];
-        compute_neighbors(x, y, j);  // Core neighbors stay inside the window: no wrap.
-        stream_pull_load(k, f, in + base, j);
-        if (cell_kind == KIND_ACTIVE) {
-#if BLOCK_ROOT_BC == 1
-            block_wall(f, x, y, halo);
-#endif
-            block_collide(f);
-        }
-    }
-    stream_pull_store(k, f, out + base);
-}

src/CelerisLab/lbm/kernels/step/block_transfer.cu

@@ -1,78 +0,0 @@
-// CelerisLab/lbm/kernels/step/block_transfer.cu
-// Same-level halo refresh and 2:1 explosion/coalescence between blocked levels.
-// Part of the blocks.cu compilation entry; relies on its includes and guards.
-
-// Halo refresh: block cell ids b*TOTAL_CELLS+c, sources are always core cells.
-extern "C" __global__ void BlockHaloCopy(
-    fpxx* f, const uint64_t* dst, const uint64_t* src, unsigned int count)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const uint64_t d = dst[row], s = src[row];
-    fpxx* to = f + (d / TOTAL_CELLS) * NQ * TOTAL_CELLS;
-    const fpxx* from = f + (s / TOTAL_CELLS) * NQ * TOTAL_CELLS;
-    for (unsigned int q = 0; q < NQ; ++q)
-        to[index_f(d % TOTAL_CELLS, q)] = from[index_f(s % TOTAL_CELLS, q)];
-}
-
-// Fixed-patch explosion into blocked fine storage: target = owner block cell
-// id of a patch-ghost cell; donors are parent block cell ids. Dense parent
-// storage is the one-window case with coarse_cells = full domain size.
-extern "C" __global__ void BlockExplode(
-    const fpxx* coarse, fpxx* fine, const uint64_t* target, const uint64_t* donor,
-    unsigned int count, unsigned long coarse_cells)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const uint64_t t = target[row];
-    fpxx* to = fine + (t / TOTAL_CELLS) * NQ * TOTAL_CELLS;
-    const uint64_t d = donor[row];
-    const fpxx* from = coarse + (d / coarse_cells) * NQ * coarse_cells;
-    for (unsigned int q = 0; q < NQ; ++q)
-        to[index_f(t % TOTAL_CELLS, q)] = from[q * coarse_cells + d % coarse_cells];
-}
-
-// Experimental Schornbaum--Ruede (arXiv:1508.07982, Algorithm 2)
-// and Chen et al. (doi:10.1016/j.physa.2005.09.036) population interpolation.
-// Independent implementation of the mathematical stencil; no upstream source copied.
-// Stencil cells are owner cores; a disabled axis repeats its center twice.
-extern "C" __global__ void BlockExplodeProjected(
-    const fpxx* coarse, fpxx* fine, const uint64_t* target, const uint64_t* donor,
-    unsigned int count, unsigned long coarse_cells,
-    const uint64_t* neighbors, const float* offsets)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const uint64_t t = target[row], d = donor[row];
-    fpxx* to = fine + (t / TOTAL_CELLS) * NQ * TOTAL_CELLS;
-    for (unsigned int q = 0; q < NQ; ++q) {
-        float v[4];
-        for (unsigned int a = 0; a < 4; ++a) {
-            const uint64_t n = neighbors[4ul * row + a];
-            v[a] = coarse[(n / coarse_cells) * NQ * coarse_cells
-                          + q * coarse_cells + n % coarse_cells];
-        }
-        float gx = .5f * (v[1] - v[0]), gy = .5f * (v[3] - v[2]);
-        const float ex = d_cx[q], ey = d_cy[q];
-        if (q != 0) {
-            const float along = (ex * gx + ey * gy) / (ex * ex + ey * ey);
-            gx -= ex * along;
-            gy -= ey * along;
-        }
-        to[index_f(t % TOTAL_CELLS, q)] =
-            coarse[(d / coarse_cells) * NQ * coarse_cells + q * coarse_cells + d % coarse_cells]
-            + offsets[2ul * row] * gx + offsets[2ul * row + 1] * gy;
-    }
-}
-
-// Targets are receiver-local SOURCE slots for the immediately following pull.
-// Keep child summation order identical to PatchCoarseStep; no collision here.
-extern "C" __global__ void BlockCoalesce(
-    const fpxx* fine, fpxx* coarse, const uint64_t* target, const uint64_t* children,
-    unsigned int count)
-{
-    unsigned int row = blockIdx.x * blockDim.x + threadIdx.x;
-    if (row >= count) return;
-    const uint64_t* s = children + 4ul * row;
-    coarse[target[row]] = 0.25f * (fine[s[0]] + fine[s[1]] + fine[s[2]] + fine[s[3]]);
-}

src/CelerisLab/lbm/kernels/streaming/pull_double_buffer.cuh

@@ -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,

src/CelerisLab/lbm/raw_exchange.py

@@ -7,26 +7,16 @@ import numpy as np
 
 
 def summarize_exchange(rows, body_ids, aperture, *, body_id, level, h,
-                       time_end, window, reference_center, duration=None):
+                       time_end, window, reference_center):
     """Reduce FP64 interval integrals or convert FP32 last-substep raw rows.
 
     dt_l=h_l under acoustic 2:1 refinement. Local momentum j -> base force
     h*j -> impulse h*dt*j; torque adds one h; mass is h**2*dm.
-    window="window" reduces an FP64 observation-window ledger spanning
-    ``duration`` (integer >= 1) base intervals; rates divide by that duration.
     """
-    if window not in ("last_base_step", "last_substep", "window"):
+    if window not in ("last_base_step", "last_substep"):
         raise ValueError("unknown exchange window")
-    if window == "window":
-        if isinstance(duration, bool) or not isinstance(duration, (int, np.integer)) or duration < 1:
-            raise ValueError("window duration must be an integer number of base intervals >= 1")
-    elif duration is not None:
-        raise ValueError("duration applies only to window='window'")
     values = np.array(rows, dtype=np.float64, copy=True)
-    if window == "window":
-        duration = float(duration)
-    else:
-        duration = 1.0 if window == "last_base_step" else h
+    duration = 1.0 if window == "last_base_step" else h
     if window == "last_substep":
         values *= np.array([h*h, h*h, h*h*h, h*h])
     selected = np.asarray(body_ids) == body_id
@@ -41,7 +31,6 @@ def summarize_exchange(rows, body_ids, aperture, *, body_id, level, h,
     return dict(wall=reduce(selected & ~aperture), aperture=reduce(selected & aperture),
                 total=reduce(selected), body_id=int(body_id), level=int(level),
                 time_start=time_end-duration, time_end=time_end, dt=h,
-                sample_count=(round(duration/h) if window == "window"
-                              else round(1/h) if window == "last_base_step" else 1),
+                sample_count=round(1/h) if window == "last_base_step" else 1,
                 window=window, units="base_lattice_per_unit_depth",
                 definition="raw_boundary_exchange", reference_center=tuple(reference_center), valid=True)

src/CelerisLab/lbm/refinement.py

@@ -52,17 +52,17 @@ class FixedPatch2D:
     def from_config(cls, cfg: LBMConfig, bounds) -> "FixedPatch2D":
         """Prepare maps without changing cfg or allocating coarse-sized tables.
 
-        The backend contract is D2Q9/SRT or MRT/FP32/double_buffer,
+        The initial backend contract is D2Q9/SRT/FP32/double_buffer,
         without LES. Two coarse cells of margin keep all halo donors in bounds;
         this does NOT certify that those donors are fluid or periodic.
         """
         checked = replace(cfg)
         checked.validate()
-        if (not checked.is_d2q9 or checked.collision not in ("SRT", "MRT")
+        if (not checked.is_d2q9 or checked.collision != "SRT"
                 or checked.streaming != "double_buffer"
                 or checked.store_precision != "FP32"
                 or checked.les_enabled):
-            raise ValueError("FixedPatch2D requires D2Q9/SRT or MRT/FP32/double_buffer without LES")
+            raise ValueError("FixedPatch2D requires D2Q9/SRT/FP32/double_buffer without LES")
         bounds = tuple(bounds)
         if len(bounds) != 4 or any(isinstance(v, (bool, np.bool_))
                                    or not isinstance(v, Integral) for v in bounds):
@@ -451,7 +451,7 @@ def prepare_fine_boundary(cfg, patch, objects, *, wall_aware=False, jets=(),
     checked = replace(cfg)
     checked.validate()
     if (patch.coarse_shape != (cfg.ny, cfg.nx) or not checked.is_d2q9
-            or checked.collision not in ("SRT", "MRT") or checked.streaming != "double_buffer"
+            or checked.collision != "SRT" or checked.streaming != "double_buffer"
             or checked.store_precision != "FP32" or checked.les_enabled
             or patch.tau_coarse != 3*checked.viscosity+.5):
         raise ValueError("Fine boundary requires the matching fixed-patch configuration")

src/CelerisLab/lbm/refinement_stepper.py

@@ -22,7 +22,7 @@ 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,
+                                blocked_kind, _prepare_blocked_boundary,
                                 BLOCKED_BOUNDARY_DEVICE_COLUMNS)
 from .descriptors import SOLID
 from .raw_exchange import summarize_exchange
@@ -41,8 +41,6 @@ class _Pair:
     n_ghosts: int
     n_rows: int
     parent_cells: int    # parent block window cells (explode donor stride)
-    neighbors: object = None  # projected-only owner-core cells; constant allocates neither
-    offsets: object = None
 
 
 @dataclass
@@ -65,8 +63,52 @@ def _level_name(level):
     return ("base", "fine", "child")[level] if level < 3 else f"level {level}"
 
 
+def _legacy_levels(bounds, *, fine_block, base_block, child, child_block, child_rectangles_in_parent,
+                   fine_objects, jets, child_objects, child_jets):
+    """Normalise the original two/three-level keywords to per-level lists (original errors)."""
+    if child is not None and child_rectangles_in_parent is not None:
+        raise ValueError("child and child_rectangles_in_parent are mutually exclusive")
+    nested = child is not None or child_rectangles_in_parent is not None
+    bounds = tuple(bounds)
+    if not is_rectangle(bounds) and (fine_block is None or base_block is None):
+        raise ValueError("several patches require fine_block and base_block")
+    fine_objects, jets = tuple(fine_objects), tuple(jets)
+    child_objects, child_jets = tuple(child_objects), tuple(child_jets)
+    if not nested and (child_objects or child_jets):
+        raise ValueError("child_objects/child_jets require a nested child")
+    if base_block is not None and fine_block is None:
+        raise ValueError("base_block requires fine_block")
+    refinements, blocks = [bounds], [base_block, fine_block]
+    objects, level_jets = [(), fine_objects], [(), jets]
+    if nested:
+        if child is not None and not is_rectangle(bounds):
+            raise ValueError("scalar child requires one parent patch; use child_rectangles_in_parent")
+        if fine_block is None or base_block is None or child_block is None:
+            raise ValueError("a nested child needs fine_block, base_block and child_block")
+        if fine_objects or jets:
+            raise ValueError("a nested child supports bodies/Jets only on L2; use child_objects/child_jets")
+        refinements.append(tuple(child) if child is not None else tuple(child_rectangles_in_parent))
+        blocks.append(child_block)
+        objects.append(child_objects)
+        level_jets.append(child_jets)
+    return refinements, blocks, objects, level_jets
+
+
+def _initial_levels(level_g, coarse_g, fine_g, child_g):
+    """One tuple of per-level arrays from initialize()'s positional or legacy named form."""
+    if coarse_g is None and fine_g is None:
+        if child_g is not None and len(level_g) != 2:
+            raise TypeError("child_g needs exactly the coarse and fine arrays before it")
+        return tuple(level_g) + (() if child_g is None else (child_g,))
+    if level_g:
+        raise TypeError("pass level arrays positionally or as coarse_g/fine_g/child_g, not both")
+    if coarse_g is None or fine_g is None:
+        raise TypeError("coarse_g and fine_g are both required in the named form")
+    return (coarse_g, fine_g) + (() if child_g is None else (child_g,))
+
+
 def _check_levels(refinements, blocks, objects, jets):
-    """Candidate limits of the level lists, checked before any device work."""
+    """Candidate limits shared by the list and the legacy entry points."""
     depth = len(refinements) + 1
     if depth < 2:
         raise ValueError("at least one refinement level is required")
@@ -75,13 +117,13 @@ def _check_levels(refinements, blocks, objects, jets):
             raise ValueError(f"{name} needs one entry per level ({depth})")
     for level, block in enumerate(blocks):
         if block is not None and len(block) != 2:
-            raise ValueError(f"level_blocks[{level}] must be (by, bx)")
+            raise ValueError(f"{_level_name(level)}_block must be (by, bx)")
     if objects[0] or jets[0]:
         raise ValueError("base-level bodies/Jets are not supported")
     if any(blocks[level - 1] is not None and blocks[level] is None for level in range(1, depth)):
         raise ValueError("a blocked level requires blocked refined levels below it")
     if not is_rectangle(refinements[0]) and (blocks[0] is None or blocks[1] is None):
-        raise ValueError("several L1 patches require level_blocks[0] and level_blocks[1]")
+        raise ValueError("several patches require fine_block and base_block")
     if depth > 2:
         if any(block is None for block in blocks):
             raise ValueError("three or more levels must all be blocked")
@@ -90,14 +132,7 @@ def _check_levels(refinements, blocks, objects, jets):
 
 
 class FixedPatchStepper:
-    """D2Q9 SRT/MRT FP32 fixed 2:1 refinement hierarchy, built from level lists.
-
-    ``refinements[l]`` gives level l+1 in level-l integer cells: one rectangle
-    (x0, y0, x1, y1) (FixedPatch2D, a fine window with its own origin) or a
-    sequence of rectangles (FixedPatchSet2D, a dependency-validated union on one
-    level-wide grid, public fine arrays (2*ny, 2*nx), NaN outside ACTIVE cells);
-    see lbm.hierarchy. ``level_blocks``, ``level_objects`` and ``level_jets``
-    hold one entry per level, L0 included (L0 bodies/Jets are not supported).
+    """D2Q9/SRT/FP32, one unforced internal 2:1 patch in an x-periodic box.
 
     ``coarse_boundary`` is ``periodic`` (default) or ``slot_reservoir``:
     a bottom on-site slot and top fixed-density reservoir from ``cfg``.
@@ -108,91 +143,108 @@ class FixedPatchStepper:
     actual channel closure footprint. Channel remapping is not supported.
     Periodic mode does not apply the wall/slot boundary fields in ``cfg``.
     Outer walls remain coarse; fine halo donors must be ordinary fluid.
+    ``fine_objects`` accepts fixed circles in coarse physical coordinates;
+    velocities are in coarse lattice units (dx=dt=1). Independent local copies
+    are projected at fine cell centers. Their complete stencil must be active
+    and disjoint from the actual two-hop transfer footprint.
+    These use the edge/cell-center frame (coarse centers I+.5), whereas ordinary Simulation objects use the integer-node frame.
 
-    Bodies are fixed circles in root (L0) physical coordinates; velocities are
-    in root lattice units (dx=dt=1). Independent local copies are projected at
-    fine cell centers; their complete stencil must be active and disjoint from
-    the actual two-hop transfer footprint. These use the edge/cell-center frame
-    (coarse centers I+.5), whereas ordinary Simulation objects use the
-    integer-node frame. Jets (body.jets.Jet) use the same frame and drive cut
-    links selected at their true hits; ``set_jet_amplitude(index, amplitude,
-    level=l)`` re-uploads the per-link velocity column only.
-
-    ``initialize(*level_g)`` accepts one physical Q-major (9, ny, nx) array per
-    level, already in postcollision phase. It does not collide or build channel
-    flags. Every ``step()`` publishes only after all levels complete on one
-    stream. On a device/launch failure the instance becomes unusable: close and
-    recreate it, rather than pretending a partially advanced buffer rolled back.
-
-    A ``level_blocks`` entry (by, bx) stores that level in blocks.cu storage:
-    the ENTIRE level shape, including the four-cell patch ghost band, is
-    partitioned by a non-periodic BlockLayout2D with one-cell same-level halos.
-    Patch kinds stay per cell (OUTER invalid, INNER stream only, ACTIVE
-    collide); halos are gathered before each hop. Public arrays keep the dense
-    shapes; only the allocation differs. A blocked level requires blocked
-    refined levels below it; several L1 rectangles and depth >= 3 require all
-    levels blocked. Blocked bodies are stationary circles, optionally
-    surface-actuated: prepare_fine_boundary decides legality on the dense grid,
-    then cut links are staged receiver-local per hop: halo -> BFL -> step, same
-    buffer. A blocked parent gathers halos before receiver-local coalescence
-    staging and pull/collision; covered cells are poisoned on every step.
+    ``initialize(coarse_g, fine_g)`` accepts physical Q-major (9,ny,nx) arrays
+    already in postcollision phase. It does not collide or build channel flags.
+    Every ``step()`` publishes only after both levels complete on one stream.
+    On a device/launch failure the instance becomes unusable: close and recreate
+    it, rather than pretending the partially advanced fine buffer rolled back.
 
+    ``fine_block=(by, bx)`` (opt-in) stores the fine level in
+    blocks.cu storage: the ENTIRE fine_shape, including the four-cell patch
+    ghost band, is partitioned by a non-periodic BlockLayout2D with one-cell
+    same-level halos. Patch kinds stay per cell (OUTER invalid, INNER stream
+    only, ACTIVE collide); halos are gathered before each fine hop. Public
+    arrays keep the dense (9, ny, nx) fine shape; only the allocation differs.
+    Blocked fine_objects are stationary circles, optionally surface-actuated:
+    prepare_fine_boundary decides legality on the dense fine grid, then cut
+    links are staged receiver-local per hop: halo -> BFL -> step, same buffer.
+    ``base_block=(by, bx)`` also blocks the parent; it requires ``fine_block``.
+    Parent halos precede receiver-local coalescence staging and pull/collision;
+    covered cells are explicitly poisoned on every step. Public shapes stay dense.
     ``observe_raw_exchange=True`` records blocked physical cut-link exchange
     without changing populations. read_raw_exchange reports the last complete
     base interval or last substep in base-lattice units per unit depth. This
     is boundary momentum reaction, not a validated nozzle/stress load. Dense
-    body levels are not supported by this diagnostic.
-    ``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.
+    body layouts are not supported by this new diagnostic in this candidate.
+    ``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.
 
-    ``explosion="projected_linear"`` selects experimental transverse linear
-    reconstruction on each adjacent pair. Default "constant" is unchanged.
-    Projected mode requires periodic root, all-blocked SRT levels without
-    bodies/Jets or LES; this backend supplies no forcing. Geometry is generic,
-    but union/multilevel GPU and matched-physics qualification remain pending.
+    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.
 
-    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.
+    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)``.
+
+    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,
-                 observe_raw_exchange=False, observe_window_exchange=False, explosion="constant"):
+    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):
         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]
         _check_levels(refinements, level_blocks, level_objects, level_jets)
         depth = len(refinements) + 1
-        if explosion not in ("constant", "projected_linear"):
-            raise ValueError("explosion must be constant or projected_linear")
-        if explosion == "projected_linear" and (
-                coarse_boundary != "periodic" or any(b is None for b in level_blocks)
-                or any(level_objects) or any(level_jets)
-                or cfg.collision != "SRT" or cfg.les_enabled):
-            raise ValueError("projected explosion requires periodic all-blocked SRT levels "
-                             "without bodies/Jets or LES")
-        self._explosion = explosion
         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")
@@ -263,13 +315,6 @@ class FixedPatchStepper:
                                       for b, layout in zip(self._boundary_hosts, self._layouts)):
             raise ValueError("raw exchange currently requires blocked body levels")
         self._observe_raw_exchange = observe_raw_exchange
-        if not isinstance(observe_window_exchange, bool):
-            raise ValueError("observe_window_exchange must be bool")
-        if observe_window_exchange and not observe_raw_exchange:
-            raise ValueError("observe_window_exchange requires observe_raw_exchange")
-        self._observe_window = observe_window_exchange
-        self._window_valid = False
-        self._window_start = None
         self._exchange_valid = False
         self._exchange_spacing = tuple(spacings)
         self._exchange_centers = tuple(tuple(tuple(o.geometry.center) for o in objects)
@@ -320,8 +365,6 @@ class FixedPatchStepper:
                             count = len(b.tables["cell"])
                             b.last_raw = self._allocate(count * 4 * 4)
                             b.interval_integral = self._allocate(count * 4 * 8)
-                            if self._observe_window:
-                                b.window_integral = self._allocate(count * 4 * 8)
                             b.accumulate = level.module.get_function("BlockAccumulateExchange")
                         b.kernel = level.module.get_function("BlockCurvedBoundary")
                 if self._level_boundaries[1] is not None:
@@ -362,10 +405,7 @@ class FixedPatchStepper:
             raise RuntimeError("level omega/tau mismatch")
         host = self._boundary_hosts[index]
         n_objects = len(host.objects) if name == "PatchFineStep" and host is not None else 0
-        block_root_bc = 0
-        if index == 0 and layout is not None:
-            block_root_bc = 2 if self._channel else 1 if self._wall_aware else 0
-        build = compiler.generate_config(config, n_objects=n_objects, block_root_bc=block_root_bc)
+        build = compiler.generate_config(config, n_objects=n_objects)
         try:
             ptx = compiler.compile_kernel(self.ctx.sm_arch, source=source, build_dir=build)
             module = compiler.load_module(ptx)
@@ -427,11 +467,6 @@ class FixedPatchStepper:
                        self._upload(children), len(ghosts), len(targets),
                        int(np.prod(pair.coarse_shape if parent.layout is None
                                    else parent.layout.local_shape)))
-        if self._explosion == "projected_linear":
-            neighbors, offsets = projected_explosion_tables(
-                pair, parent.layout, self.hierarchy.kinds[index])
-            result.explode = child.module.get_function("BlockExplodeProjected")
-            result.neighbors, result.offsets = self._upload(neighbors), self._upload(offsets)
         if child.layout is not None:
             child.kind = self._upload(blocked_kind(child.layout, self.hierarchy.kinds[index + 1]))
         if index == 0 and base is not None:
@@ -471,13 +506,13 @@ 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()
@@ -524,7 +559,6 @@ class FixedPatchStepper:
                     cuda.memset_d8(self._fine_curved.link_exchange_gpu, 0, self._fine_curved.count * 12)
                 self._step_count = 0
                 self._exchange_valid = False
-                self._window_valid = False
                 self._status = "ready"
             except BaseException:
                 self._status = "failed"
@@ -601,11 +635,11 @@ 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],
-                observe_raw_exchange=self._observe_raw_exchange,
-                observe_window_exchange=self._observe_window, explosion=self._explosion)
+                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)
             try:
                 if self._ddf_shifting:
                     candidate._initialize_raw(_StoredPopulations(transferred.g, transferred.shifted))
@@ -698,7 +732,6 @@ class FixedPatchStepper:
         pair, level = self._pairs[index - 1], self._levels[index]
         pair.explode(parent_buffer, level.current, pair.ghosts, pair.donors, np.uint32(pair.n_ghosts),
                      np.uint64(pair.parent_cells),
-                     *((pair.neighbors, pair.offsets) if pair.neighbors is not None else ()),
                      grid=((pair.n_ghosts + self._block[0] - 1) // self._block[0], 1), **kw)
         self._hop(index, level.current, level.spare, **kw)
         self._hop(index, level.spare, level.current, **kw)
@@ -738,10 +771,6 @@ class FixedPatchStepper:
             b.accumulate(b.last_raw, b.interval_integral, np.uint32(count),
                          np.float64(h), np.float64(h),
                          grid=((count + self._block[0] - 1) // self._block[0], 1), **kw)
-            if self._window_valid and b.window_integral is not None:
-                b.accumulate(b.last_raw, b.window_integral, np.uint32(count),
-                             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
         level.kernel(src, dst, np.uint32(level.layout.halo), flags, level.kind, grid=level.grid, **kw)
 
@@ -752,94 +781,32 @@ class FixedPatchStepper:
                             grid=((pairs + self._block[0] - 1) // self._block[0], 1), **kw)
 
     def step(self, n=1):
-        """Advance G→G by n base intervals: level l takes 2**l hops per interval.
-
-        All n intervals are enqueued in order on the one stream, and the host waits
-        once, before returning; step(0) launches and waits for nothing. On return
-        the device work is complete, step_count and an open window cover all n
-        intervals, and the raw-exchange ledger holds the final interval only.
-
-        Asynchronous device errors surface at that single wait, so they are not
-        attributed to the interval that caused them; call step(1) repeatedly to
-        localize one (same launches, same bits). On any failure the instance is
-        failed, the exchange ledger and window are invalid, and step_count keeps
-        its value from entry to the failing call.
-        """
+        """Advance G→G by n base intervals: level l takes 2**l hops per interval."""
         if isinstance(n, bool) or not isinstance(n, Integral) or n < 0:
             raise ValueError("n must be a nonnegative integer")
         with self._lock, self.ctx.activate():
             self._require("ready")
-            if n == 0:
-                return
             root = self._levels[0]
             kw = dict(block=self._block, stream=self._stream)
             try:
                 self._status = "advancing"
-                self._exchange_valid = False
                 for _ in range(n):
-                    if self._observe_raw_exchange:  # stream-ordered: holds the last interval only
+                    if self._observe_raw_exchange:
+                        self._exchange_valid = False
                         for b in self._level_boundaries:
                             if b is not None:
                                 cuda.memset_d8_async(b.interval_integral, 0,
                                                      len(b.tables["cell"]) * 32, self._stream)
                     self._hop(0, root.current, root.spare, **kw)
-                    root.current, root.spare = root.spare, root.current  # host handles only
-                self._stream.synchronize()
-                self._step_count += n
-                self._exchange_valid = self._observe_raw_exchange
+                    self._stream.synchronize()
+                    root.current, root.spare = root.spare, root.current
+                    self._step_count += 1
+                    self._exchange_valid = self._observe_raw_exchange
                 self._status = "ready"
             except BaseException:
-                self._window_valid = False
                 self._status = "failed"
                 raise
 
-    def start_exchange_window(self):
-        """Zero the window ledgers and open a window at the current completed step count."""
-        with self._lock, self.ctx.activate():
-            self._require("ready")
-            if not self._observe_window:
-                raise RuntimeError("window exchange observation is disabled")
-            self._window_valid = False
-            try:
-                for b in self._level_boundaries:
-                    if b is not None and b.window_integral is not None:
-                        cuda.memset_d8(b.window_integral, 0, len(b.tables["cell"]) * 32)
-            except BaseException:
-                self._status = "failed"
-                raise
-            self._window_start = self._step_count
-            self._window_valid = True
-
-    def read_exchange_window(self, body_id, *, level=1):
-        """Non-destructive read of [window start, current step count] in base-lattice units."""
-        with self._lock, self.ctx.activate():
-            self._require("ready")
-            if not self._observe_window:
-                raise RuntimeError("window exchange observation is disabled")
-            if not self._window_valid:
-                raise RuntimeError("no valid exchange window; call start_exchange_window()")
-            duration = self._step_count - self._window_start
-            if duration < 1:
-                raise RuntimeError("exchange window requires at least one completed base interval")
-            if (isinstance(level, bool) or not isinstance(level, Integral)
-                    or not 0 <= level < len(self._levels)):
-                raise ValueError("level must name an existing level")
-            b = self._level_boundaries[level]
-            if (b is None or isinstance(body_id, bool) or not isinstance(body_id, Integral)
-                    or not 0 <= body_id < len(b.host.objects)):
-                raise ValueError("body_id must name a body on this level")
-            rows = np.empty((len(b.tables["cell"]), 4), np.float64)
-            try:
-                cuda.memcpy_dtoh(rows, b.window_integral)
-            except BaseException:
-                self._status = "failed"
-                raise
-            return summarize_exchange(rows, b.tables["body_id"], b.tables["aperture"],
-                                      body_id=body_id, level=level, h=self._exchange_spacing[level],
-                                      time_end=self._step_count, window="window",
-                                      reference_center=self._exchange_centers[level][body_id],
-                                      duration=duration)
-
     def read_raw_exchange(self, body_id, *, level=1, window="last_base_step"):
         """Read raw boundary reaction about its geometric center in the root edge frame.
 
@@ -918,7 +885,6 @@ class FixedPatchStepper:
                     if b is not None:
                         b.flags = b.device = b.kernel = None
                         b.last_raw = b.interval_integral = b.accumulate = None
-                        b.window_integral = None
                 self._levels.clear()
                 self._pairs = []
                 if getattr(self, "_fine_curved", None) is not None:

src/CelerisLab/lbm/refinement_tables.py

@@ -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
 
@@ -66,50 +66,6 @@ def blocked_base_tables(patch, layout, order, wall_aware=False, *, composed_kind
             blocked_kind(layout, dense_kind))
 
 
-def projected_explosion_tables(pair, parent_layout, composed_parent_kind):
-    """Experimental transverse linear explosion, in the pair's existing row order.
-
-    Schornbaum & Rüde (2016), arXiv:1508.07982, Algorithm 2, following
-    Chen et al., doi:10.1016/j.physa.2005.09.036. Independently implemented
-    from the mathematics: centered gradients, perpendicular projection and
-    child offsets +/-1/4. The kernel applies the projection per population.
-
-    Only original explosion donors that are owned, uncovered ACTIVE cells
-    may supply gradients. Both axis neighbors must be legal; otherwise repeat
-    the center twice for zero slope. Owner-core addresses avoid stale halos.
-    The same rule applies to scalar windows, unions and every adjacent pair;
-    nested layouts retain their own per-axis (usually nonperiodic) topology.
-    """
-    ny, nx = pair.coarse_shape
-    kind = np.asarray(composed_parent_kind)
-    if parent_layout.shape != pair.coarse_shape or kind.shape != pair.coarse_shape:
-        raise ValueError("projected explosion parent layout/kind has the wrong shape")
-    donor = pair.ghost_coarse.astype(np.intp)
-    legal = np.zeros(ny * nx, bool)
-    legal[donor] = True
-    legal &= (parent_layout.owned.ravel() & ~pair.covered.ravel()
-              & (kind.ravel() == ACTIVE))
-    if not legal[donor].all():
-        raise ValueError("projected explosion donors need owned uncovered parent ACTIVE cells")
-    y, x = np.divmod(donor, nx)
-    neighbors = np.repeat(donor[:, None], 4, axis=1)
-    for axis, (dx, dy) in enumerate(((1, 0), (0, 1))):
-        minus = ((y - dy) % ny) * nx + (x - dx) % nx
-        plus = ((y + dy) % ny) * nx + (x + dx) % nx
-        valid = legal[minus] & legal[plus]
-        if not parent_layout.periodic[axis]:
-            coordinate, extent = (x, nx) if axis == 0 else (y, ny)
-            valid &= (coordinate > 0) & (coordinate < extent - 1)
-        neighbors[valid, 2 * axis] = minus[valid]
-        neighbors[valid, 2 * axis + 1] = plus[valid]
-    fy, fx = np.divmod(pair.ghost_fine, pair.fine_shape[1])
-    ox, oy = pair.fine_origin
-    offsets = np.column_stack((ox + (fx + .5) / 2 - (x + .5),
-                               oy + (fy + .5) / 2 - (y + .5)))
-    return (np.ascontiguousarray(parent_layout.owner.ravel()[neighbors], dtype=np.uint64),
-            np.ascontiguousarray(offsets, dtype=np.float32))
-
-
 # Required device columns plus optional actuation; observation arms are uploaded
 # separately only when enabled. body_id/aperture remain host reduction metadata.
 BLOCKED_BOUNDARY_DEVICE_COLUMNS = ("block", "cell", "dir", "q", "fallback", "surface_velocity")
@@ -129,7 +85,6 @@ class _BlockedBoundary:
     last_raw: object = None
     interval_integral: object = None
     accumulate: object = None
-    window_integral: object = None  # optional observation-window FP64 ledger
 
 
 def _prepare_blocked_boundary(boundary, layout, cfg, jets, *, _shifted_blocked=False):
@@ -142,13 +97,11 @@ 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)

src/CelerisLab/simulation.py

@@ -336,19 +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, *,
@@ -457,21 +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)

tests/integration/test_checkpoint_bodies_gpu.py

@@ -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()

tests/integration/test_state_gpu.py

@@ -65,14 +65,9 @@ def test_shifted_topology_add_remove_preserves_cache_and_finite_flow(streaming,p
         assert np.max(macro['rho'][fluid]) < 1.5
 
 
-@pytest.mark.parametrize('collision,streaming', [
-    pytest.param('SRT', 'double_buffer', id='double_buffer'),
-    pytest.param('SRT', 'esopull', id='esopull'),
-    pytest.param('TRT', 'double_buffer', id='trt-double_buffer'),
-])
-def test_checkpoint_exact_continuation_and_controls(collision,streaming,tmp_path):
-    # Same collision throughout save/load/continue; this is not a method-switch restart.
-    with make_sim(nx=48,ny=24,streaming=streaming,shifted=True,collision=collision) as sim:
+@pytest.mark.parametrize('streaming',['double_buffer','esopull'])
+def test_checkpoint_exact_continuation_and_controls(streaming,tmp_path):
+    with make_sim(nx=48,ny=24,streaming=streaming,shifted=True) as sim:
         sim.add_body('circle',center=(14,12),radius=3)
         sim.add_body('force_region',center=(30,12),radius=2)
         sim.initialize()

tests/unit/cpp/channel_root.cpp

@@ -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(){

tests/unit/historical_tree.py

@@ -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

tests/unit/test_block_step_sync.py

@@ -1,104 +0,0 @@
-"""Host contract of PeriodicBlockStepper.step(n): one stream wait per call (mocked driver)."""
-import ast
-from contextlib import nullcontext
-import importlib.util
-from pathlib import Path
-import types
-from unittest.mock import Mock
-import unittest
-
-import numpy as np
-
-from CelerisLab.config import LBMConfig
-from CelerisLab.lbm.blocks import BlockLayout2D
-
-
-def host_module():
-    """block_stepper with pycuda/compiler replaced by mocks; no GPU context."""
-    # Locate the source without importing it: importing block_stepper loads pycuda.driver,
-    # which CPU-only import-boundary tests (test_build_contracts) must never see.
-    path = Path(importlib.util.find_spec("CelerisLab.lbm.block_stepper").origin)
-    tree = ast.parse(path.read_text())
-    tree.body = [node for node in tree.body if not (
-        isinstance(node, ast.Import) and any(a.name == "pycuda.driver" for a in node.names)
-        or isinstance(node, ast.ImportFrom) and node.module == "cuda")]
-    module = types.ModuleType("CelerisLab.lbm._test_host_block_stepper")
-    module.__package__ = "CelerisLab.lbm"
-    module.__dict__.update(cuda=Mock(), compiler=Mock())
-    exec(compile(tree, str(path), "exec"), module.__dict__)
-    return module
-
-
-def backend():
-    host, log = host_module(), []
-    host.cuda.mem_get_info.return_value = (1 << 40, 1 << 40)
-    host.cuda.mem_alloc.side_effect = lambda size: Mock(size=size)  # distinct buffers
-    module = Mock()
-    module.get_global.return_value = (Mock(), 20)
-    module.get_function.side_effect = lambda name: Mock(
-        side_effect=lambda *a, **k: log.append((name, a[:2])))
-    host.compiler.load_module.return_value = module
-    cfg = LBMConfig(nx=16, ny=16, viscosity=.1)
-    run = host.PeriodicBlockStepper(cfg, BlockLayout2D.build(16, 16, 8, 8),
-                                    context=Mock(activate=nullcontext, sm_arch="sm_70"))
-    run._stream.synchronize.side_effect = lambda: log.append(("sync", ()))
-    run.initialize(np.full((9, 16, 16), 1 / 9))
-    log.clear()
-    return run, log
-
-
-class BlockStepSync(unittest.TestCase):
-    def test_step_n_waits_once_and_matches_n_single_steps(self):
-        many, log_many = backend()
-        many.step(3)
-        single, log_single = backend()
-        for _ in range(3):
-            single.step(1)
-        names = [name for name, _ in log_many]
-        self.assertEqual(names.count("sync"), 1)
-        self.assertEqual(names[-1], "sync")
-        self.assertEqual(names.count("BlockStep"), 3)
-        # Same launch order and buffer roles as three step(1) calls.
-        strip = lambda log: [(n, tuple(id(x) for x in a)) for n, a in log if n != "sync"]
-        roles = lambda run, log: [(n, tuple({id(run._current): "c", id(run._spare): "s"}.get(x, "-")
-                                            for x in ids)) for n, ids in strip(log)]
-        self.assertEqual([n for n, _ in strip(log_many)], [n for n, _ in strip(log_single)])
-        self.assertEqual(roles(many, log_many), roles(single, log_single))
-        self.assertIsNot(many._current, many._spare)
-        self.assertEqual((many.step_count, single.step_count), (3, 3))
-
-    def test_step_zero_launches_and_waits_for_nothing(self):
-        run, log = backend()
-        run.step(0)
-        self.assertEqual((log, run.step_count), ([], 0))
-
-    def test_failure_keeps_entry_step_count(self):
-        run, log = backend()
-        run.step(1)
-        run._stream.synchronize.side_effect = RuntimeError("device fault")
-        with self.assertRaises(RuntimeError):
-            run.step(2)
-        self.assertEqual((run.step_count, run._status), (1, "failed"))
-
-    def test_launch_failure_mid_batch_fails_closed_without_waiting(self):
-        run, log = backend()
-        calls = []
-        step = run._step
-
-        def failing(*args, **kwargs):
-            calls.append(1)
-            if len(calls) == 2:
-                raise RuntimeError("launch failure")
-            return step(*args, **kwargs)
-
-        run._step = failing
-        with self.assertRaises(RuntimeError):
-            run.step(3)
-        self.assertNotIn("sync", [name for name, _ in log])
-        self.assertEqual((run.step_count, run._status), (0, "failed"))
-        with self.assertRaises(RuntimeError):
-            run.download()
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_build_contracts.py

@@ -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])

tests/unit/test_channel_root.py

@@ -50,7 +50,7 @@ def test_masks_and_minimal_footprint():
 def test_actual_closure_read_conflicts():
     pair, layout, targets = transfer((6, 6, 18, 14))
     validate_channel_transfers(pair, layout, targets)
-    for target in (layout.slot(int(layout.owner[5, -1]) - 1, 2),  # integer under NumPy 1 and 2
+    for target in (layout.slot(layout.owner[5, -1]-1, 2),
                    layout.slot(layout.owner[1, 4], 4),
                    layout.slot(layout.owner[-2, 4], 3)):
         with pytest.raises(ValueError, match="immutable"):
@@ -80,8 +80,8 @@ def test_evolved_ghost_snapshot_and_physical_download():
     host.cuda.memcpy_dtoh.side_effect = lambda a, ptr: np.copyto(a, storage[id(ptr)])
     context = Mock(activate=nullcontext, sm_arch="sm_70")
     cfg = LBMConfig(nx=24, ny=20, viscosity=.1, velocity=.025)
-    backend = host.FixedPatchStepper(cfg, context=context, coarse_boundary="channel",
-                                    refinements=[(6, 6, 18, 14)], level_blocks=[(4, 6), (4, 4)])
+    backend = host.FixedPatchStepper(cfg, (6, 6, 18, 14), context=context,
+                                    coarse_boundary="channel", base_block=(4, 6), fine_block=(4, 4))
     try:
         weights = np.array([4/9]+[1/9]*4+[1/36]*4)[:, None, None]
         arrays = [np.broadcast_to(weights, level.shape).copy() for level in backend._levels]
@@ -97,6 +97,5 @@ def test_evolved_ghost_snapshot_and_physical_download():
         with pytest.raises(ValueError, match="finite"):
             backend.initialize(*arrays)
         assert backend._levels[0].kernel == host.compiler.load_module.return_value.get_function("BlockChannelStep")
-        assert [call.kwargs["block_root_bc"] for call in host.compiler.generate_config.call_args_list] == [2, 0]
     finally:
         backend.close()

tests/unit/test_dfg_re20.py

@@ -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()

tests/unit/test_jet_circle_cv.py

@@ -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__":

tests/unit/test_jets.py

@@ -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)

tests/unit/test_les_flow_runner.py

@@ -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):
@@ -46,80 +42,31 @@ 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")["base_commit"],
+            "cd3a657f9d3833e812c3cca173525f165b48710a",
+        )
 
     def test_corrected_and_tamper_guard(self):
-        pins = json.loads((HERE / "data/les_flow/source_pins_a135252.json").read_text())
+        pins = json.loads((HERE / "data/les_flow/source_pins.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)
+            # Current production is the corrected variant; archived baseline pins stay frozen.
             with patch(
                 "run_uniform_les_flow.subprocess.check_output",
                 return_value="isolated-fixture\n",
             ):
-                source_guard(root, "corrected", "a135252")
+                source_guard(root, "corrected")
                 with self.assertRaisesRegex(RuntimeError, "Source pin mismatch"):
-                    source_guard(root, "baseline", "a135252")
-                for name in ("kernels/step/one_step_double.cu", "kernels/blocks.cu",
-                             "refinement_stepper.py", "refinement_tables.py"):
-                    target = root / "src/CelerisLab/lbm" / name
-                    original = target.read_bytes()
-                    target.write_bytes(original + b"\n// tamper\n")
-                    with self.assertRaisesRegex(RuntimeError, "Source pin mismatch"):
-                        source_guard(root, "corrected", "a135252")
-                    target.write_bytes(original)
-
-    def test_historical_default_and_manifest_unchanged(self):
-        historical = {
-            "historical": ("source_pins.json", "87ca033619da1fc02bee822bfc5681b518a92a155c3c3d1dbbe5265c96066b39"),
-            "dev8403956": ("source_pins_dev8403956.json", "58187908485f2af7c78677d53de98015878372444265ce9e667683b8ef5d410f"),
-        }
-        for experiment, (name, expected) in historical.items():
-            manifest = HERE / "data/les_flow" / name
-            self.assertEqual(hashlib.sha256(manifest.read_bytes()).hexdigest(), expected)
-            for variant in ("baseline", "corrected"):
+                    source_guard(root, "baseline")
+                target = root / "src/CelerisLab/lbm/kernels/step/one_step_double.cu"
+                target.write_bytes(target.read_bytes() + b"\n// tamper\n")
                 with self.assertRaisesRegex(RuntimeError, "Source pin mismatch"):
-                    source_guard(ROOT, variant, experiment)
-        with self.assertRaisesRegex(RuntimeError, "Source pin mismatch"):
-            source_guard(ROOT, "corrected")  # Omission still uses the historical profile.
-
-    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")
-
-    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"
-            for name in pins["sources"]:
-                dest = root / name
-                dest.parent.mkdir(parents=True, exist_ok=True)
-                shutil.copyfile(origin / 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")
-                with self.assertRaisesRegex(RuntimeError, "Source pin mismatch"):
-                    source_guard(root, "corrected", "a135252")
+                    source_guard(root, "corrected")
 
     def test_gpu_requires_opt_in_before_import(self):
         with TemporaryDirectory() as directory:

tests/unit/test_projected_explosion.py

@@ -1,394 +0,0 @@
-"""CPU stencil and actual closed-interface packet budgets; no CUDA claims."""
-import numpy as np
-import unittest
-from pathlib import Path
-from dataclasses import replace
-import shutil
-import subprocess
-import tempfile
-
-from CelerisLab.config import LBMConfig
-from CelerisLab.lbm.blocks import BlockLayout2D
-from CelerisLab.lbm.descriptors import D2Q9_EX, D2Q9_EY
-from CelerisLab.lbm.refinement import FixedPatch2D, FixedPatchSet2D, ACTIVE, OUTER_GHOST
-from CelerisLab.lbm.refinement_tables import projected_explosion_tables
-from CelerisLab.lbm.hierarchy import build_hierarchy
-from tests.unit.test_hierarchy import CFG, FOUR
-
-E = np.array([D2Q9_EX, D2Q9_EY]).T
-W = np.array([4/9] + [1/9]*4 + [1/36]*4)
-
-
-def setup(union=False, bounds=(4, 4, 12, 12)):
-    cfg = LBMConfig(nx=16, ny=16, viscosity=.1)
-    p = (FixedPatchSet2D.from_config(cfg, [bounds]) if union else
-         FixedPatch2D.from_config(cfg, bounds))
-    layout = BlockLayout2D.build(16, 16, 4, 4, periodic=(True, True))
-    neighbors, offsets = projected_explosion_tables(p, layout, np.where(p.covered, OUTER_GHOST, ACTIVE))
-    inverse = np.full(layout.nblocks * np.prod(layout.local_shape), -1, dtype=int)
-    inverse[layout.owner.ravel()] = np.arange(256)
-    return p, inverse[neighbors], offsets
-
-
-def reconstruct(c, p, neighbors, offsets, project=True):
-    # Independent NumPy evaluation of the documented stencil; neighbors have
-    # been decoded from actual blocked owner IDs, not recomputed geometry.
-    values = c.reshape(9, -1)[:, neighbors]
-    g = .5 * (values[:, :, 1::2] - values[:, :, ::2])
-    if project:
-        g[1:] -= (np.einsum('qra,qa->qr', g[1:], E[1:]) /
-                  np.sum(E[1:]**2, axis=1)[:, None])[:, :, None] * E[1:, None, :]
-    out = c.reshape(9, -1)[:, p.ghost_coarse] + np.einsum('qra,ra->qr', g, offsets)
-    return out, g
-
-
-def check_legal_footprint_mean_and_characteristic(union, bounds):
-    p, neighbors, offsets = setup(union, bounds)
-    assert set(neighbors.ravel()) <= set(p.ghost_coarse)
-    assert not p.covered.ravel()[neighbors].any()
-    assert (neighbors >= 0).all()
-    c = np.random.default_rng(72).normal(size=(9,16,16))
-    c[:, p.covered] = np.nan  # poison every forbidden donor
-    out, g = reconstruct(c, p, neighbors, offsets)
-    assert np.isfinite(out).all()
-    np.testing.assert_allclose(np.einsum('qra,qa->qr', g, E), 0, atol=5e-16)
-    for d in np.unique(p.ghost_coarse):
-        rows = p.ghost_coarse == d
-        assert rows.sum() == 4
-        np.testing.assert_allclose(out[:, rows].mean(axis=1), c.reshape(9,-1)[:,d], atol=5e-16)
-        for q in range(1,9):
-            delta = offsets[rows, None, :] - offsets[None, rows, :]
-            # Parallel displacements have zero 2D cross product.
-            parallel = np.isclose(delta[...,0]*E[q,1]-delta[...,1]*E[q,0], 0)
-            diff = out[q, rows][:,None]-out[q, rows][None,:]
-            np.testing.assert_allclose(diff[parallel], 0, atol=5e-16)
-    const = np.broadcast_to(W[:,None,None], (9,16,16)).copy()
-    constant, _ = reconstruct(const,p,neighbors,offsets)
-    np.testing.assert_array_equal(constant, np.broadcast_to(W[:,None], constant.shape))
-
-
-def collide(f, tau):
-    rho = f.sum(axis=0)
-    u = np.einsum('qa,q...->a...', E, f) / rho
-    cu = np.einsum('qa,a...->q...', E, u)
-    eq = W[:,None] * rho * (1 + 3*cu + 4.5*cu**2 - 1.5*np.sum(u*u,axis=0))
-    return f + (eq-f)/tau
-
-
-def totals(c, f, p):
-    q = c[:,~p.covered].sum(axis=1)+.25*f[:,p.fine_kind==ACTIVE].sum(axis=1)
-    return np.r_[q.sum(), E.T@q]
-
-
-def check_full_two_hop_closed_corner_budget(union, collision, bounds):
-    p, neighbors, offsets = setup(union,bounds)
-    rng=np.random.default_rng(17)
-    c=W[:,None,None]*(1+rng.normal(0,.002,(9,16,16)))
-    f=W[:,None,None]*(1+rng.normal(0,.002,(9,*p.fine_shape)))
-    start=totals(c,f,p)
-    # Count exactly the eight coarse diagonal links whose source is also
-    # uncovered, but whose midpoint lies on the closed rectangular interface.
-    q, k=np.divmod(p.coalesce_coarse.astype(np.int64),256)
-    y,x=np.divmod(k,16)
-    grazing=~p.covered[y-E[q,1],x-E[q,0]]
-    assert grazing.sum()==8
-    c[:,p.covered]=np.nan
-    for _ in range(8):
-        f.reshape(9,-1)[:,p.ghost_fine]=reconstruct(c,p,neighbors,offsets)[0]
-        for _ in range(2):
-            f=np.array([np.roll(f[q],(ey,ex),(0,1)) for q,(ex,ey) in enumerate(E)])
-            f[:,p.fine_kind==OUTER_GHOST]=np.nan
-            if collision:
-                f[:,p.fine_kind==ACTIVE]=collide(f[:,p.fine_kind==ACTIVE],p.tau_fine)
-        out=np.array([np.roll(c[q],(ey,ex),(0,1)) for q,(ex,ey) in enumerate(E)])
-        packets=f.reshape(-1)[p.coalesce_fine].mean(axis=1)
-        assert np.isfinite(packets[grazing]).all()
-        out.reshape(-1)[p.coalesce_coarse]=packets
-        if collision:out[:,~p.covered]=collide(out[:,~p.covered],p.tau_coarse)
-        out[:,p.covered]=np.nan
-        c=out
-        np.testing.assert_allclose(totals(c,f,p),start,rtol=0,atol=2e-12)
-
-
-def check_projection_is_distinguished_by_characteristic_not_global_mass():
-    p,n,o=setup()
-    c=np.random.default_rng(8).normal(size=(9,16,16))
-    _,g=reconstruct(c,p,n,o,project=False)
-    assert np.max(abs(np.einsum('qra,qa->qr',g,E))) > .1
-
-
-
-
-class ProjectedExplosionTests(unittest.TestCase):
-    def test_stencil(self):
-        for union in (False, True):
-            for bounds in ((4,4,12,12),(2,3,9,10),(2,2,3,3)):
-                with self.subTest(union=union,bounds=bounds):
-                    check_legal_footprint_mean_and_characteristic(union,bounds)
-
-    def test_closed_interface(self):
-        for union in (False,True):
-            for collision in (False,True):
-                for bounds in ((4,4,12,12),(2,3,14,12),(2,2,3,3)):
-                    with self.subTest(union=union,collision=collision,bounds=bounds):
-                        check_full_two_hop_closed_corner_budget(union,collision,bounds)
-
-    def test_projection(self):
-        check_projection_is_distinguished_by_characteristic_not_global_mass()
-
-    def test_affine_and_shift_invariance(self):
-        p,n,o=setup()
-        y,x=np.indices((16,16))
-        c=np.array([.7+q*.01+x*.03+y*.05 for q in range(9)])
-        out,g=reconstruct(c,p,n,o)
-        available=n[:,::2]!=n[:,1::2]
-        gradient=np.array([.03,.05])*available
-        expected=np.broadcast_to(gradient,(9,*gradient.shape)).copy()
-        expected[1:]-=(np.einsum('qra,qa->qr',expected[1:],E[1:])/
-                       np.sum(E[1:]**2,axis=1)[:,None])[:,:,None]*E[1:,None,:]
-        np.testing.assert_allclose(g,expected,atol=2e-16)
-        shifted,_=reconstruct(c-W[:,None,None],p,n,o)
-        np.testing.assert_allclose(out-W[:,None],shifted,atol=5e-16)
-
-
-class ProjectedKernelTests(unittest.TestCase):
-    @unittest.skipUnless(shutil.which("g++"), "g++ is required for actual-kernel CPU arithmetic")
-    def test_actual_kernel_fp32_shifted_and_unshifted(self):
-        p, neighbors, offsets = setup(True)
-        parent = BlockLayout2D.build(16,16,4,4,periodic=(True,True))
-        child = p.fine_layout((8,4))  # deliberately unequal parent/child strides
-        ids, offsets = projected_explosion_tables(p,parent,np.where(p.covered,OUTER_GHOST,ACTIVE))
-        cells = int(np.prod(parent.local_shape))
-        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()
-        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):
-            v = np.asarray(values).ravel()
-            text = ','.join(str(int(x)) if kind=='uint64_t' else float(x).hex()+'f' for x in v)
-            return f"{kind} {name}[] = {{{text}}};\n"
-        for shifted in (False,True):
-            c=np.random.default_rng(11).normal(0,.001,(9,16,16))
-            if not shifted:c+=W[:,None,None]
-            c=c.astype(np.float32)
-            packed=np.full(parent.nblocks*9*cells,np.nan,np.float32)
-            for q in range(9):packed[parent.slot(parent.owner.ravel(),q)]=c[q].ravel()
-            # All halo/covered inputs are poisoned; kernel must use legal cores.
-            for q in range(9):packed[parent.slot(parent.owner.ravel()[p.covered.ravel()],q)]=np.nan
-            # Hex initializer needs a portable expression for poisoned NaNs.
-            data=array('coarse',packed,'float').replace('nanf','NAN')
-            code = '#include <cstdint>\n#include <cmath>\n#include <cstdio>\nusing fpxx=float;\n'
-            code += f'constexpr unsigned NQ=9, TOTAL_CELLS={int(np.prod(child.local_shape))};\n'
-            code += 'struct Id {unsigned x;}; Id blockIdx{0},blockDim{1},threadIdx{0};\n'
-            code += 'unsigned index_f(unsigned k,unsigned q){return q*TOTAL_CELLS+k;}\n'
-            code += 'int d_cx[]={0,1,-1,0,0,1,-1,1,-1},d_cy[]={0,0,0,1,-1,1,-1,-1,1};\n'+kernel
-            code += data+array('target',targets,'uint64_t')+array('donor',donors,'uint64_t')
-            code += array('neighbor',ids,'uint64_t')+array('offset',offsets,'float')
-            code += f'float fine[{child.nblocks*9*int(np.prod(child.local_shape))}]={{}};\n'
-            code += f'int main(){{for(unsigned r=0;r<{len(targets)};++r){{threadIdx.x=r;BlockExplodeProjected(coarse,fine,target,donor,{len(targets)},{cells},neighbor,offset);}}'
-            code += f'for(unsigned q=0;q<9;++q)for(unsigned r=0;r<{len(targets)};++r){{auto t=target[r];printf("%.9g\\n",fine[(t/TOTAL_CELLS)*9*TOTAL_CELLS+q*TOTAL_CELLS+t%TOTAL_CELLS]);}}}}'
-            with tempfile.TemporaryDirectory() as folder:
-                src=Path(folder)/'kernel.cpp'; binary=Path(folder)/'kernel'
-                src.write_text(code)
-                subprocess.run(['g++','-std=c++17','-O2',str(src),'-o',str(binary)],check=True,capture_output=True)
-                result=np.fromstring(subprocess.check_output([str(binary)],text=True),sep=' ').reshape(9,-1)
-            expected,_=reconstruct(c.astype(float),p,neighbors,offsets)
-            np.testing.assert_allclose(result,expected,atol=6e-8,rtol=2e-7)
-
-
-UNIONS = [
-    [(8, 8, 24, 20)],
-    [(8, 8, 16, 20), (16, 8, 24, 20)],       # abutting
-    [(8, 8, 18, 20), (14, 8, 24, 20)],       # overlap
-    [(8, 8, 16, 20), (17, 8, 24, 20)],       # gap 1
-    [(8, 8, 16, 20), (18, 8, 24, 20)],       # gap 2
-    [(8, 8, 16, 20), (19, 8, 24, 20)],       # gap 3
-    [(8, 8, 20, 14), (8, 14, 14, 22)],       # L concavity
-    [(4, 4, 10, 10), (18, 16, 26, 26)],      # separated
-    [(4, 4, 5, 7), (4, 5, 7, 7)],           # known concave exit/re-entry path
-]
-
-
-def decode(layout, neighbors):
-    inverse = np.full(layout.hole, -1, dtype=int)
-    inverse[layout.owner[layout.owned]] = np.flatnonzero(layout.owned)
-    return inverse[neighbors]
-
-
-def check_pair_stencil(pair, layout, kind):
-    ids, offsets = projected_explosion_tables(pair, layout, kind)
-    neighbors = decode(layout, ids)
-    legal = set(map(int, pair.ghost_coarse))
-    assert len(np.unique(pair.ghost_fine)) == len(pair.ghost_fine)
-    assert set(neighbors.ravel()) <= legal
-    assert layout.owned.ravel()[neighbors].all()
-    assert (kind.ravel()[neighbors] == ACTIVE).all()
-    assert not pair.covered.ravel()[neighbors].any()
-    ny, nx = pair.coarse_shape
-    for row, donor in enumerate(pair.ghost_coarse):
-        y, x = divmod(int(donor), nx)
-        for axis, (dx, dy) in enumerate(((1, 0), (0, 1))):
-            ends = [(x - dx, y - dy), (x + dx, y + dy)]
-            expected = []
-            for xx, yy in ends:
-                outside = not (0 <= xx < nx and 0 <= yy < ny)
-                if outside and not layout.periodic[axis]:
-                    break
-                cell = (yy % ny) * nx + xx % nx
-                if cell not in legal:
-                    break
-                expected.append(cell)
-            if len(expected) != 2:
-                expected = [int(donor)] * 2
-            np.testing.assert_array_equal(neighbors[row, 2*axis:2*axis+2], expected)
-        fy, fx = divmod(int(pair.ghost_fine[row]), pair.fine_shape[1])
-        expected = [pair.fine_origin[0]+(fx+.5)/2-(x+.5),
-                    pair.fine_origin[1]+(fy+.5)/2-(y+.5)]
-        np.testing.assert_array_equal(offsets[row], expected)
-    assert set(offsets.ravel()) == {-.25, .25}
-    assert ids.dtype == np.uint64 and ids.flags.c_contiguous
-    assert offsets.dtype == np.float32 and offsets.flags.c_contiguous
-    return neighbors, offsets
-
-
-class GenericProjectedPairs(unittest.TestCase):
-    def test_single_window_and_singleton_union_exact_stencils(self):
-        for bounds in ((4,4,12,12), (2,3,9,10), (2,2,3,3)):
-            a, an, ao = setup(False, bounds)
-            b, bn, bo = setup(True, bounds)
-            np.testing.assert_array_equal(a.ghost_coarse, b.ghost_coarse)
-            np.testing.assert_array_equal(an, bn)
-            np.testing.assert_array_equal(ao, bo)
-            # Coordinates differ between scalar and union arrays; physical rows don't.
-            ay, ax = np.divmod(a.ghost_fine, a.fine_shape[1])
-            by, bx = np.divmod(b.ghost_fine, b.fine_shape[1])
-            np.testing.assert_array_equal(ax + 2*a.fine_origin[0], bx)
-            np.testing.assert_array_equal(ay + 2*a.fine_origin[1], by)
-
-    def test_union_decomposition_permutation_and_topologies(self):
-        cfg = LBMConfig(nx=30, ny=30, viscosity=.1)
-        layout = BlockLayout2D.build(30,30,6,5,periodic=(True,True))
-        stencils = []
-        for rectangles in UNIONS:
-            pair = FixedPatchSet2D.from_config(cfg, rectangles)
-            kind = np.where(pair.covered, OUTER_GHOST, ACTIVE)
-            n, o = check_pair_stencil(pair, layout, kind)
-            other = FixedPatchSet2D.from_config(cfg, rectangles[::-1])
-            on, oo = projected_explosion_tables(other, layout, kind)
-            np.testing.assert_array_equal(n, decode(layout, on))
-            np.testing.assert_array_equal(o, oo)
-            stencils.append((pair.ghost_fine, pair.ghost_coarse, n, o))
-            c = np.random.default_rng(92).normal(size=(9,30,30))
-            c[:, pair.covered] = np.nan
-            values, gradients = reconstruct(c, pair, n, o)
-            self.assertTrue(np.isfinite(values).all())
-            np.testing.assert_allclose(np.einsum('qra,qa->qr', gradients, E),0,atol=1e-15)
-            # q0 keeps its full gradient; no division by zero or forced zero.
-            expected_q0 = .5*(c[0].ravel()[n[:,1::2]]-c[0].ravel()[n[:,::2]])
-            np.testing.assert_array_equal(gradients[0], expected_q0)
-            self.assertGreater(np.max(abs(gradients[0])), .1)
-            for donor in np.unique(pair.ghost_coarse):
-                rows = pair.ghost_coarse == donor
-                self.assertEqual(rows.sum(),4)
-                np.testing.assert_allclose(values[:,rows].mean(axis=1),c.reshape(9,-1)[:,donor],atol=1e-15)
-                for q in range(1,9):
-                    delta = o[rows,None,:]-o[None,rows,:]
-                    parallel = delta[...,0]*E[q,1] == delta[...,1]*E[q,0]
-                    diff = values[q,rows][:,None]-values[q,rows][None,:]
-                    np.testing.assert_allclose(diff[parallel],0,atol=1e-15)
-        for split in stencils[1:3]:
-            for expected, actual in zip(stencils[0],split):
-                np.testing.assert_array_equal(actual,expected)
-
-    def test_nested_scalar_origins_sparse_holes_and_unequal_strides(self):
-        cases = [(CFG, FOUR), (LBMConfig(nx=16,ny=16,viscosity=.02),
-                               [(4,4,12,12),(8,8,16,16),(8,8,16,16)])]
-        for cfg, refs in cases:
-            hierarchy = build_hierarchy(cfg,refs)
-            for index,pair in enumerate(hierarchy.pairs):
-                if index == 0:
-                    layout = BlockLayout2D.build(cfg.ny,cfg.nx,4,4,periodic=(True,True))
-                else:
-                    prior = hierarchy.pairs[index-1]
-                    layout = (prior.fine_layout((4,8)) if isinstance(prior,FixedPatchSet2D)
-                              else BlockLayout2D.build(*prior.fine_shape,4,8,periodic=(False,False)))
-                kind = hierarchy.kinds[index]
-                n,o = check_pair_stencil(pair,layout,kind)
-                c = np.random.default_rng(index).normal(size=(9,*pair.coarse_shape))
-                c[:,~layout.owned | (kind != ACTIVE)] = np.nan
-                self.assertTrue(np.isfinite(reconstruct(c,pair,n,o)[0]).all())
-                if index and isinstance(pair,FixedPatchSet2D):
-                    self.assertTrue((~layout.owned).any())
-                self.assertEqual(layout.periodic, (index == 0, index == 0))
-
-    def test_periodicity_is_per_axis_and_missing_pairs_repeat_center(self):
-        cfg=LBMConfig(nx=16,ny=16,viscosity=.1)
-        p=FixedPatch2D.from_config(cfg,(2,2,14,14))
-        kind=np.where(p.covered,OUTER_GHOST,ACTIVE)
-        results=[]
-        for periodic in ((False,False),(True,False),(False,True),(True,True)):
-            layout=BlockLayout2D.build(16,16,4,4,periodic=periodic)
-            n,_=check_pair_stencil(p,layout,kind)
-            results.append(n)
-            y,x=np.divmod(p.ghost_coarse,16)
-            for axis,coordinate in enumerate((x,y)):
-                edge=(coordinate==0)|(coordinate==15)
-                if not periodic[axis]:
-                    np.testing.assert_array_equal(n[edge,2*axis:2*axis+2],
-                        np.repeat(p.ghost_coarse[edge,None],2,axis=1))
-        self.assertTrue((results[0]!=results[1]).any())
-        self.assertTrue((results[0]!=results[2]).any())
-        self.assertTrue((results[1]!=results[3]).any())
-
-    def test_invalid_parent_donors_reject_before_owner_lookup(self):
-        p,_,_=setup()
-        layout=BlockLayout2D.build(16,16,4,4)
-        kind=np.where(p.covered,OUTER_GHOST,ACTIVE)
-        for nonactive in (1,2,255):
-            bad=kind.copy(); bad.ravel()[p.ghost_coarse[0]]=nonactive
-            with self.assertRaisesRegex(ValueError,'ACTIVE'):
-                projected_explosion_tables(p,layout,bad)
-        with self.assertRaisesRegex(ValueError,'shape'):
-            projected_explosion_tables(p,layout,kind[:1])
-        hole_layout=BlockLayout2D.build(16,16,4,4,origins=[(0,0)])
-        with self.assertRaisesRegex(ValueError,'owned'):
-            projected_explosion_tables(p,hole_layout,kind)
-
-    def test_generic_two_hop_mass_and_momentum_budget(self):
-        cfg=LBMConfig(nx=30,ny=30,viscosity=.1)
-        layout=BlockLayout2D.build(30,30,6,5)
-        grazing_counts=set()
-        for rectangles in UNIONS:
-            pair=FixedPatchSet2D.from_config(cfg,rectangles)
-            ids,o=projected_explosion_tables(pair,layout,np.where(pair.covered,OUTER_GHOST,ACTIVE))
-            n=decode(layout,ids)
-            q,k=np.divmod(pair.coalesce_coarse.astype(np.int64),900)
-            y,x=np.divmod(k,30)
-            grazing=~pair.covered[(y-E[q,1])%30,(x-E[q,0])%30]
-            grazing_counts.add(int(grazing.sum()))
-            self.assertTrue(grazing.any())
-            for collision in (False,True):
-                rng=np.random.default_rng(17)
-                c=W[:,None,None]*(1+rng.normal(0,.002,(9,30,30)))
-                f=W[:,None,None]*(1+rng.normal(0,.002,(9,*pair.fine_shape)))
-                start=totals(c,f,pair)
-                c[:,pair.covered]=np.nan
-                for _ in range(4):
-                    f.reshape(9,-1)[:,pair.ghost_fine]=reconstruct(c,pair,n,o)[0]
-                    for _ in range(2):
-                        f=np.array([np.roll(f[q],(ey,ex),(0,1)) for q,(ex,ey) in enumerate(E)])
-                        f[:,pair.fine_kind==OUTER_GHOST]=np.nan
-                        if collision:
-                            f[:,pair.fine_kind==ACTIVE]=collide(f[:,pair.fine_kind==ACTIVE],pair.tau_fine)
-                    out=np.array([np.roll(c[q],(ey,ex),(0,1)) for q,(ex,ey) in enumerate(E)])
-                    packets=f.reshape(-1)[pair.coalesce_fine].mean(axis=1)
-                    self.assertTrue(np.isfinite(packets[grazing]).all())
-                    out.reshape(-1)[pair.coalesce_coarse]=packets
-                    if collision:
-                        out[:,~pair.covered]=collide(out[:,~pair.covered],pair.tau_coarse)
-                    out[:,pair.covered]=np.nan
-                    c=out
-                    np.testing.assert_allclose(totals(c,f,pair),start,rtol=0,atol=4e-12)
-        self.assertGreater(len(grazing_counts),1)  # not a hard-coded eight-corner oracle

tests/unit/test_projected_pair_gate.py

@@ -1,162 +0,0 @@
-"""Host-only checks for the opt-in CUDA gate; never imports or compiles CUDA."""
-from copy import deepcopy
-import importlib.util
-from pathlib import Path
-import unittest
-from unittest.mock import patch
-
-import numpy as np
-
-from CelerisLab.config import LBMConfig
-from CelerisLab.lbm.blocks import BlockLayout2D
-from CelerisLab.lbm.hierarchy import build_hierarchy
-from CelerisLab.lbm.refinement import ACTIVE, OUTER_GHOST, FixedPatch2D, FixedPatchSet2D
-from CelerisLab.lbm.refinement_tables import projected_explosion_tables
-from tests.unit.test_hierarchy import CFG, FOUR
-from tests.unit.test_projected_explosion import decode, reconstruct, totals
-
-PATH = Path(__file__).resolve().parents[1] / 'validation/multigrid/check_projected_pairs.py'
-spec = importlib.util.spec_from_file_location('projected_pair_gate', PATH)
-gate = importlib.util.module_from_spec(spec)
-spec.loader.exec_module(gate)
-
-
-class ProjectedGateOracle(unittest.TestCase):
-    def check_pair(self, pair, layout, kind):
-        ids, offsets = projected_explosion_tables(pair, layout, kind)
-        neighbors = decode(layout, ids)
-        coarse = np.random.default_rng(731).normal(size=(9, *pair.coarse_shape))
-        legal = np.zeros(pair.coarse_shape, bool)
-        legal.ravel()[pair.ghost_coarse] = True
-        coarse[:, ~legal] = np.nan
-        expected, _ = reconstruct(coarse, pair, neighbors, offsets)
-        # The coordinate oracle must not accidentally share production tables.
-        with patch('CelerisLab.lbm.refinement_tables.projected_explosion_tables',
-                   side_effect=AssertionError('oracle used production stencil')):
-            actual = gate.independent_explosion(coarse, pair, layout, kind)
-        np.testing.assert_allclose(actual, expected, rtol=0, atol=2e-15)
-        center = coarse.reshape(9, -1)[:, pair.ghost_coarse]
-        self.assertTrue(np.isfinite(actual).all())
-        self.assertGreater(np.max(abs(actual[0] - center[0])), .01)
-        self.assertGreater(np.max(abs(actual[1:] - center[1:])), .01)
-        return coarse, neighbors, offsets, actual
-
-    def test_scalar_union_nested_sparse_and_unequal_strides(self):
-        def fine_layout(pair, block):
-            return (pair.fine_layout(block) if isinstance(pair, FixedPatchSet2D) else
-                    BlockLayout2D.build(*pair.fine_shape, *block, periodic=(False,False)))
-        small = LBMConfig(nx=16, ny=16, viscosity=.02)
-        fixtures = [(small, [(4,4,12,12), (8,8,16,16), (8,8,16,16)]),
-                    (CFG, FOUR), (small, [[(4,4,5,7), (4,5,7,7)]])]
-        for cfg, refs in fixtures:
-            hierarchy = build_hierarchy(cfg, refs)
-            for index, pair in enumerate(hierarchy.pairs):
-                block, child_block = ((4,4), (4,8)) if index % 2 == 0 else ((4,8), (4,4))
-                layout = (BlockLayout2D.build(cfg.ny, cfg.nx, *block) if index == 0
-                          else fine_layout(hierarchy.pairs[index-1], block))
-                with self.subTest(refs=refs, pair=index):
-                    self.assertNotEqual(np.prod(layout.local_shape),
-                                        np.prod(fine_layout(pair, child_block).local_shape))
-                    if index and isinstance(pair, FixedPatchSet2D):
-                        self.assertTrue((~layout.owned).any())
-                    self.check_pair(pair, layout, hierarchy.kinds[index])
-
-    def test_axis_periodicity_and_mean_preserving_mutants(self):
-        pair = FixedPatch2D.from_config(LBMConfig(nx=16,ny=16,viscosity=.1), (2,2,14,14))
-        kind = np.where(pair.covered, OUTER_GHOST, ACTIVE)
-        outputs = []
-        for periodic in ((False,False), (True,False), (False,True), (True,True)):
-            layout = BlockLayout2D.build(16,16,4,4,periodic=periodic)
-            coarse, neighbors, offsets, actual = self.check_pair(pair, layout, kind)
-            outputs.append(actual)
-            donors, first, inverse = np.unique(pair.ghost_coarse, return_index=True, return_inverse=True)
-            wrong = neighbors[first[np.roll(np.arange(len(donors)), 1)]][inverse]
-            for bad_neighbors, bad_offsets in ((neighbors, -offsets), (wrong, offsets)):
-                mutant, _ = reconstruct(coarse, pair, bad_neighbors, bad_offsets)
-                self.assertGreater(np.max(abs(mutant - actual)), .01)
-                for donor in donors:
-                    rows = pair.ghost_coarse == donor
-                    self.assertEqual(rows.sum(), 4)
-                    np.testing.assert_allclose(mutant[:,rows].mean(axis=1),
-                                               coarse.reshape(9,-1)[:,donor], rtol=0, atol=1e-15)
-            bad_kind = kind.copy(); bad_kind.ravel()[pair.ghost_coarse[0]] = OUTER_GHOST
-            with self.assertRaisesRegex(AssertionError, 'illegal center donor'):
-                gate.independent_explosion(coarse, pair, layout, bad_kind)
-        for i, j in ((0,1), (0,2), (1,3), (2,3)):
-            self.assertGreater(np.max(abs(outputs[i] - outputs[j])), .01)
-
-    def test_concave_replay_preserves_existing_fp64_budget(self):
-        cfg, refs, blocks = gate.cases()['concave']
-        hierarchy = build_hierarchy(cfg, refs); pair = hierarchy.pairs[0]
-        layout = BlockLayout2D.build(cfg.ny, cfg.nx, *blocks[0])
-        rng = np.random.default_rng(17)
-        values = tuple(gate.W[:,None,None] * (1 + rng.normal(0,.002,(9,*shape)))
-                       for shape in (pair.coarse_shape, pair.fine_shape))
-        start = totals(*values, pair)
-        values[0][:,pair.covered] = np.nan
-        for _ in range(8):
-            values = gate.replay_two_hops(values, pair, layout, hierarchy.kinds[0])
-            np.testing.assert_allclose(totals(*values, pair), start, rtol=0, atol=4e-12)
-        self.assertEqual(gate.REPLAY_ATOL, 3e-6)  # CUDA replay bound is separate.
-
-
-class ProjectedGateReceipts(unittest.TestCase):
-    def test_digest_exact_finite_bits_and_nan_masks(self):
-        values = np.array([0., -0., np.nan, 1.], dtype=np.float32)
-        self.assertEqual(gate.digest(values), gate.digest(values.copy()))
-        payload = values.copy(); payload.view(np.uint32)[2] = 0x7fc00001
-        self.assertEqual(gate.digest(values), gate.digest(payload))
-        variants = [np.array([-0., -0., np.nan, 1.], np.float32),
-                    np.array([0., np.nan, -0., 1.], np.float32),
-                    np.array([0., -0., np.nan, np.nextafter(np.float32(1), np.float32(2))], np.float32),
-                    values.reshape(2,2), values.astype(np.float64)]
-        for changed in variants:
-            self.assertNotEqual(gate.digest(values), gate.digest(changed))
-        with self.assertRaisesRegex(AssertionError, 'infinite'):
-            gate.digest(np.array([np.inf]))
-
-    def test_snapshot_negative_controls_and_exact_dev_options(self):
-        snapshot = [dict(step=0, levels=[dict(raw='raw',public='public',active=4)],
-                         mass_momentum=[1.,0.,0.],observed_level_hops=[0,0])]
-        gate.compare_snapshots(snapshot, deepcopy(snapshot))
-        diagnostic = deepcopy(snapshot); diagnostic[0]['mass_momentum'][0] = 2.
-        gate.compare_snapshots(snapshot, diagnostic)  # Diagnostics are not bitwise gate fields.
-        mutants = [[]]
-        for key, value in (('raw','changed'), ('public','changed'), ('active',3)):
-            changed = deepcopy(snapshot); changed[0]['levels'][0][key] = value
-            mutants.append(changed)
-        changed = deepcopy(snapshot); changed[0]['step'] = 1; mutants.append(changed)
-        changed = deepcopy(snapshot); changed[0]['observed_level_hops'] = [0,1]; mutants.append(changed)
-        for changed in mutants:
-            with self.assertRaises(AssertionError):
-                gate.compare_snapshots(snapshot, changed)
-        self.assertEqual(gate.default_options('omitted'), {})
-        self.assertEqual(gate.default_options('constant'), {'explosion':'constant'})
-        self.assertEqual(gate.default_options('projected_linear'), {'explosion':'projected_linear'})
-
-    def test_baseline_receipt_rejects_provenance_and_contract_mutants(self):
-        keys = [f'{name}:shifted={shifted}' for name in gate.cases() for shifted in (False,True)]
-        good = dict(completed=True,dry_run=False,mode='baseline',production_revision=gate.BASE,
-                    source=dict(revision=gate.BASE,dirty=False),driver_sha256='driver',
-                    stops=list(gate.STOPS),operator_tolerance=[6e-8,2e-7],
-                    rest_tolerance=[3e-7,1e-6],replay_tolerance=[3e-6,0],default_snapshots=dict.fromkeys(keys, []),
-                    actual_build_sidecars=[{'ptx_sha256':'captured'}])
-        self.assertIs(gate.baseline_receipt(good, 'driver', keys), good)
-        mutants = dict(completed=False,dry_run=True,mode='candidate',production_revision='wrong',
-                       driver_sha256='wrong',stops=[0,1,2],operator_tolerance=[1e-6,2e-7],
-                       rest_tolerance=[3e-7,1e-5],replay_tolerance=[3e-6,1e-7],actual_build_sidecars=[],default_snapshots={})
-        for field, value in mutants.items():
-            bad = deepcopy(good); bad[field] = value
-            with self.subTest(field=field), self.assertRaises(ValueError):
-                gate.baseline_receipt(bad, 'driver', keys)
-        for changes in (dict(revision='wrong'), dict(dirty=True), dict(dirty=None)):
-            bad = deepcopy(good); bad['source'].update(changes)
-            with self.assertRaises(ValueError):
-                gate.baseline_receipt(bad, 'driver', keys)
-        bad = deepcopy(good); bad['default_snapshots']['unexpected'] = []
-        with self.assertRaises(ValueError):
-            gate.baseline_receipt(bad, 'driver', keys)
-
-
-if __name__ == '__main__':
-    unittest.main()

tests/unit/test_projected_pair_stepper.py

@@ -1,198 +0,0 @@
-"""Production host dispatch with CUDA doubles; no CUDA compilation or flow runs."""
-from contextlib import nullcontext
-from dataclasses import replace
-from unittest.mock import Mock
-import unittest
-
-import numpy as np
-
-from CelerisLab.config import LBMConfig
-from tests.unit.test_hierarchy import CFG, FOUR
-from tests.unit.test_refinement_three_level_multipatch import host_module
-
-
-def backend(**options):
-    host = host_module()
-    calls, allocations, storage = [], [], {}
-    context = Mock(activate=nullcontext, sm_arch='sm_70')
-    host.cuda.mem_alloc.side_effect = lambda size: allocate(size)
-
-    def allocate(size):
-        pointer = Mock(name=f'buffer{len(allocations)}', size=size)
-        allocations.append(pointer)
-        return pointer
-
-    def load(_):
-        module = Mock()
-        module.get_global.return_value = (Mock(), 20)
-        module.get_function.side_effect = lambda name: Mock(
-            name=name, side_effect=lambda *a, **kw: calls.append((name, a, kw)))
-        return module
-
-    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)
-    refinements = options.pop('refinements', FOUR)
-    blocks = options.pop('level_blocks', [(4, 4)] * (len(refinements) + 1))
-    run = host.FixedPatchStepper(cfg, context=context, refinements=refinements,
-                                level_blocks=blocks, **options)
-    run.initialize(*(np.full(level.shape, 1/9, np.float32) for level in run._levels))
-    return run, host, calls, allocations, storage
-
-
-def trace(run, calls, allocations, storage):
-    """Stable pointer identities expose allocations/arguments, not just kernel names."""
-    pointer = {id(value): index for index, value in enumerate(allocations)}
-    launches = [(name, tuple(('ptr', pointer[id(a)]) if id(a) in pointer else int(a)
-                            for a in args), kw['grid'], kw['block'])
-                for name, args, kw in calls]
-    uploads = [(index, value.dtype.str, value.shape, value.tobytes())
-               for index, ptr in enumerate(allocations) if (value := storage.get(id(ptr))) is not None]
-    return [p.size for p in allocations], uploads, launches
-
-
-class ProjectedPairDispatch(unittest.TestCase):
-    def test_omitted_and_constant_have_identical_allocations_uploads_and_launches(self):
-        results = []
-        for options in ({}, {'explosion': 'constant'}):
-            run, host, calls, allocations, storage = backend(**options)
-            self.assertEqual(run._explosion, 'constant')
-            self.assertTrue(all(p.neighbors is None and p.offsets is None for p in run._pairs))
-            run.step()
-            explosion = [args for name, args, _ in calls if name == 'BlockExplode']
-            self.assertEqual(len(explosion), 7)
-            self.assertTrue(all(len(args) == 6 for args in explosion))
-            self.assertFalse(any(name == 'BlockExplodeProjected' for name, _, _ in calls))
-            results.append(trace(run, calls, allocations, storage))
-            run.close()
-        self.assertEqual(*results)
-
-    def test_projected_adds_exactly_two_tables_per_adjacent_pair(self):
-        for depth in (2, 3, 4):
-            constant, _, _, ca, _ = backend(refinements=FOUR[:depth-1])
-            projected, _, calls, pa, storage = backend(
-                refinements=FOUR[:depth-1], explosion='projected_linear')
-            self.assertEqual(len(pa)-len(ca), 2*(depth-1))
-            for pair, geometry in zip(projected._pairs, projected.hierarchy.pairs):
-                self.assertEqual(storage[id(pair.neighbors)].shape, (len(geometry.ghost_fine), 4))
-                self.assertEqual(storage[id(pair.offsets)].shape, (len(geometry.ghost_fine), 2))
-                self.assertEqual(pair.neighbors.size, len(geometry.ghost_fine)*4*8)
-                self.assertEqual(pair.offsets.size, len(geometry.ghost_fine)*2*4)
-            projected.step()
-            explosions = [args for name, args, _ in calls if name == 'BlockExplodeProjected']
-            self.assertEqual(len(explosions), 2**(depth-1)-1)
-            self.assertTrue(all(len(args) == 8 for args in explosions))
-            self.assertFalse(any(name == 'BlockExplode' for name, _, _ in calls))
-            for args in explosions:
-                pair = next(p for p in projected._pairs if args[2] is p.ghosts)
-                self.assertIs(args[6], pair.neighbors)
-                self.assertIs(args[7], pair.offsets)
-                self.assertEqual(args[5], pair.parent_cells)
-            constant.close(); projected.close()
-
-    def test_three_and_four_level_schedule_has_fresh_midpoint_sources(self):
-        for depth in (3, 4):
-            for explosion in ('constant', 'projected_linear'):
-                run, host, calls, allocations, storage = backend(
-                    refinements=FOUR[:depth-1], explosion=explosion)
-                before = len(allocations)
-                events = []
-                for index, pair in enumerate(run._pairs):
-                    pair.explode.side_effect = lambda source, *a, index=index, **kw: events.append(('explode', index, source))
-                    pair.coalesce.side_effect = lambda child, source, *a, index=index, **kw: events.append(('restrict', index, source))
-                for index, level in enumerate(run._levels):
-                    level.kernel.side_effect = lambda source, *a, index=index, **kw: events.append(('step', index, source))
-                    level.halo_copy.side_effect = lambda source, *a, index=index, **kw: events.append(('halo', index, source))
-                expected = []
-
-                def hop(index, source):
-                    if index+1 < depth:
-                        expected.append(('explode', index, source))
-                        child = run._levels[index+1]
-                        hop(index+1, child.current)
-                        hop(index+1, child.spare)
-                    expected.append(('halo', index, source))
-                    if index+1 < depth:
-                        expected.append(('restrict', index, source))
-                    expected.append(('step', index, source))
-
-                hop(0, run._levels[0].current)
-                run.step()
-                self.assertEqual(events, expected)
-                self.assertEqual([level.kernel.call_count for level in run._levels], [2**i for i in range(depth)])
-                self.assertEqual(len(allocations), before)
-                self.assertEqual(run.step_count, 1)
-                for index in range(1, depth-1):
-                    feeds = [source for name, pair, source in events if name == 'explode' and pair == index]
-                    self.assertEqual(feeds, [run._levels[index].current, run._levels[index].spare] * (2**(index-1)))
-                run.close()
-
-    def test_scalar_windows_follow_the_same_pair_path(self):
-        run, _, _, _, _ = backend(cfg=LBMConfig(nx=16,ny=16,viscosity=.02),
-            refinements=[(4,4,12,12),(8,8,16,16),(8,8,16,16)],
-            level_blocks=[(4,4),(4,8),(8,4),(4,4)], explosion='projected_linear')
-        self.assertTrue(all(pair.neighbors is not None for pair in run._pairs))
-        self.assertEqual([pair.parent_cells for pair in run._pairs], [36,60,60])
-        run.step()
-        self.assertEqual([level.kernel.call_count for level in run._levels], [1,2,4,8])
-        run.close()
-
-    def test_physics_gate_precedes_context_and_allocations(self):
-        host = host_module()
-        context = Mock()
-        options = dict(refinements=FOUR[:1], level_blocks=[(4,4)]*2,
-                       explosion='projected_linear', context=context)
-        for cfg, changes in [(CFG, {'explosion':'unknown'}),
-                             (CFG, {'coarse_boundary':'slot_reservoir'}),
-                             (CFG, {'coarse_boundary':'channel'}),
-                             (CFG, {'level_blocks':[None,None], 'refinements':[(6,6,26,26)]}),
-                             (CFG, {'level_objects':[(),(object(),)]}),
-                             (CFG, {'level_jets':[(),(object(),)]}),
-                             (replace(CFG,collision='MRT'), {}),
-                             (replace(CFG,les_enabled=True), {})]:
-            with self.subTest(changes=changes, cfg=cfg), self.assertRaisesRegex(ValueError,'explosion'):
-                host.FixedPatchStepper(cfg, **dict(options, **changes))
-        context.activate.assert_not_called()
-        host.cuda.mem_alloc.assert_not_called()
-        # The legacy constant path still allows MRT and dense storage.
-        for options in ({'cfg':replace(CFG,collision='MRT')},
-                        {'level_blocks':[None,None], 'refinements':[(6,6,26,26)]}):
-            run, _, _, _, _ = backend(**options)
-            run.close()
-
-    def test_remap_preserves_selector_tables_and_constant_default(self):
-        for explosion in ('constant','projected_linear'):
-            run, host, _, _, storage = backend(refinements=FOUR[:2], explosion=explosion)
-            run._step_count = 7
-            old = run.download()
-            clone = run.remap_child(FOUR[1])
-            self.assertEqual(clone._explosion, explosion)
-            self.assertEqual(clone.step_count, 7)
-            for pair in clone._pairs:
-                self.assertEqual(pair.neighbors is None, explosion == 'constant')
-            for expected, actual in zip(old, clone.download()):
-                np.testing.assert_array_equal(actual,expected)
-            clone.step()
-            self.assertEqual((run.step_count,clone.step_count), (7,8))
-            clone.close(); run.close()
-
-    def test_changed_remap_geometry_keeps_projected_in_both_representations(self):
-        changed = [(22,22,42,42), (72,68,76,76)]
-        for shifted in (False, True):
-            run, _, _, _, _ = backend(cfg=replace(CFG,ddf_shifting=shifted),
-                refinements=FOUR[:2], explosion='projected_linear')
-            run._step_count = 3
-            before = run.download()
-            clone = run.remap_child(changed)
-            self.assertEqual(clone._explosion, 'projected_linear')
-            self.assertEqual(clone.hierarchy.pairs[1].bounds, tuple(changed))
-            self.assertNotEqual(clone._pairs[1].n_ghosts, run._pairs[1].n_ghosts)
-            for old, new in zip(run._pairs, clone._pairs):
-                self.assertIsNot(old.neighbors, new.neighbors)
-                self.assertIsNotNone(new.neighbors)
-            for expected, actual in zip(before, run.download()):
-                np.testing.assert_array_equal(actual, expected)
-            clone.step()
-            self.assertEqual((run.step_count, clone.step_count), (3, 4))
-            clone.close(); run.close()

tests/unit/test_raw_exchange.py

@@ -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):

tests/unit/test_raw_exchange_window.py

@@ -1,45 +0,0 @@
-"""Host reduction contract for the optional observation-window exchange ledger."""
-import unittest
-
-import numpy as np
-
-from CelerisLab.lbm.raw_exchange import summarize_exchange
-
-
-def reduce(rows, window, duration=None, h=.5, time_end=10):
-    return summarize_exchange(rows, np.array([0, 0, 1]), np.array([False, True, False]),
-                              body_id=0, level=1, h=h, time_end=time_end, window=window,
-                              reference_center=(0., 0.), duration=duration)
-
-
-class ExchangeWindowReduction(unittest.TestCase):
-    def test_window_duration_scaling(self):
-        rows = np.array([[1., 2., 3., 4.], [.5, -1., 0., 1.], [9., 9., 9., 9.]])
-        out = reduce(rows, "window", duration=4)
-        np.testing.assert_array_equal(out["total"]["impulse"], [1.5, 1.])
-        np.testing.assert_array_equal(out["total"]["force"], [1.5 / 4, 1. / 4])
-        self.assertEqual(out["total"]["torque"], 3. / 4)
-        self.assertEqual(out["total"]["mass_rate"], 5. / 4)
-        np.testing.assert_array_equal(out["aperture"]["impulse"], [.5, -1.])
-        self.assertEqual((out["time_start"], out["time_end"]), (6., 10))
-        self.assertEqual(out["sample_count"], 8)  # duration / h fine substeps
-        self.assertEqual(out["window"], "window")
-
-    def test_existing_windows_unchanged(self):
-        rows = np.array([[1., 2., 3., 4.], [0., 0., 0., 0.], [0., 0., 0., 0.]])
-        base = reduce(rows, "last_base_step")
-        self.assertEqual((base["time_start"], base["sample_count"]), (9., 2))
-        np.testing.assert_array_equal(base["total"]["force"], [1., 2.])
-        sub = reduce(rows, "last_substep")
-        self.assertEqual(sub["sample_count"], 1)
-
-    def test_duration_validation(self):
-        rows = np.zeros((3, 4))
-        for bad in (None, 0, -1, 1.5, True):
-            with self.subTest(duration=bad), self.assertRaises(ValueError):
-                reduce(rows, "window", duration=bad)
-        with self.assertRaises(ValueError):
-            reduce(rows, "last_base_step", duration=2)
-
-
-if __name__ == "__main__": unittest.main()

tests/unit/test_re100.py

@@ -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():

tests/unit/test_refined_dfg.py

@@ -7,37 +7,13 @@ 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)
 
 
 def test_source_pin():
-    historical = json.loads((r.HERE / "data/refined_dfg/source_manifest.json").read_text())
-    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")
-    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
+    assert r.verify_source(r.DEFAULT_SOURCE)["commit"].startswith("cd3a657")
 
 
 def test_matched_units_and_planes():
@@ -157,62 +133,24 @@ def test_axis_specific_sampling_phase():
     np.testing.assert_allclose(fine_y - ((k + 43) - 0.5) * 0.00125, 0, atol=1e-15)
 
 
-def frozen_manifest(observation_mode):
-    """Frozen MRT manifest JSON as recorded, without hashing the working tree."""
-    name = "source_manifest_window.json" if observation_mode == "window" else "source_manifest_mrt.json"
-    return json.loads((r.HERE / "data/refined_dfg" / name).read_text())
-
-
-def selected_manifest(collision, observation_mode):
-    """verify_source's manifest selection with its working-tree hash comparison neutralised.
-
-    Source identity is owned by test_source_pin; this exercises only which frozen manifest
-    verify_source selects and returns for (collision, observation_mode).
-    """
-    from unittest.mock import patch
-
-    class Digest(str):
-        def __ne__(self, other):
-            return False
-
-    class Hash:
-        def __init__(self, data=b""):
-            pass
-
-        def hexdigest(self):
-            return Digest()
-
-    with patch.object(r.hashlib, "sha256", Hash):
-        return r.verify_source(r.DEFAULT_SOURCE, collision, observation_mode)
-
-
 def test_full_requires_completed_pilot():
     with unittest.TestCase().assertRaisesRegex(ValueError, "pilot-results"):
-        r.verify_pilot(None, frozen_manifest("window"))
+        r.verify_pilot(None, r.verify_source(r.DEFAULT_SOURCE))
 
 
-def pilot_fixture(path, observation_mode="window", jet_scenario="none", case_selection="both", uniform_diameter=80, placement="wide"):
+def pilot_fixture(path):
     """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)
     (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)
@@ -239,10 +177,6 @@ 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",
                     healthy=True,
@@ -258,10 +192,6 @@ 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,
                     runner_sha256=r.runner_hash(),
@@ -278,7 +208,7 @@ def test_pilot_validation_and_calibration():
     with TemporaryDirectory() as tmp:
         path = Path(tmp)
         manifest = pilot_fixture(path)
-        assert r.verify_pilot(path, manifest, "MRT", "window") == 3606.0
+        assert r.verify_pilot(path, manifest) == 3606.0
 
 
 def test_reject_malformed_pilot_receipts():
@@ -308,7 +238,7 @@ def test_reject_malformed_pilot_receipts():
             mutate(bad)
             receipt.write_text(json.dumps(bad))
             with unittest.TestCase().assertRaises(ValueError):
-                r.verify_pilot(path, manifest, "MRT", "window")
+                r.verify_pilot(path, manifest)
         # Exact reviewer regression: previously accepted NaN endpoint.
         receipt.write_text(
             json.dumps(
@@ -320,11 +250,11 @@ def test_reject_malformed_pilot_receipts():
             )
         )
         with unittest.TestCase().assertRaises(ValueError):
-            r.verify_pilot(path, manifest, "MRT", "window")
+            r.verify_pilot(path, manifest)
         receipt.write_text(json.dumps(valid))
         (path / "uniform/ready.json").write_text("{}")
         with unittest.TestCase().assertRaises(ValueError):
-            r.verify_pilot(path, manifest, "MRT", "window")
+            r.verify_pilot(path, manifest)
 
 
 def test_strict_finite_json_and_deadline():
@@ -353,321 +283,6 @@ def test_pressure_probes_actual_body_mask():
     assert h.pressure_probes(np.ones(pair.fine_shape), fluid, p)["dp"] == 0.0
 
 
-def test_matched_mrt_selection():
-    for diameter in (40, 80):
-        srt, sbody, sp = r.config(h, diameter)
-        mrt, mbody, mp = r.config(h, diameter, "MRT")
-        assert mrt["method"]["collision"] == "MRT"
-        mrt["method"]["collision"] = "SRT"
-        assert mrt == srt and mbody == sbody and mp == sp
-    srt_plan, mrt_plan = r.plan(h), r.plan(h, "MRT")
-    for key in ("root", "uniform", "bounds_root_edge", "finest_dx_m", "finest_dt_s"):
-        assert srt_plan[key] == mrt_plan[key]
-    assert "q2/6/8" in mrt_plan["outlet"] and "all nine" in srt_plan["outlet"]
-    cfg, pair, _, host = r.host_geometry(r.DEFAULT_SOURCE, h, "MRT")
-    assert cfg.collision == "MRT" and pair.fine_shape == (240, 568)
-    assert len(host.boundary_cells) > 0
-
-
-def test_reject_collision_receipts():
-    from tempfile import TemporaryDirectory
-
-    for rel in ("plan.json", "uniform/summary.json", "refined/summary.json",
-                "uniform/ready.json", "refined/ready.json"):
-        for invalid in ("SRT", None):
-            with TemporaryDirectory() as tmp:
-                path = Path(tmp)
-                manifest = pilot_fixture(path)
-                receipt = path / rel
-                record = json.loads(receipt.read_text())
-                if invalid is None:
-                    record.pop("collision")
-                else:
-                    record["collision"] = invalid
-                receipt.write_text(json.dumps(record))
-                with unittest.TestCase().assertRaises(ValueError):
-                    r.verify_pilot(path, manifest, "MRT", "window")
-
-
-def test_record_actual_checkout_separately():
-    from source_provenance import checkout_provenance
-
-    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")
-
-
-def test_window_plan_preserves_physics():
-    for collision in ("SRT", "MRT"):
-        baseline = r.plan(h, collision)
-        window = r.plan(h, collision, "window")
-        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"
-    with unittest.TestCase().assertRaises(ValueError):
-        r.verify_source(r.DEFAULT_SOURCE, "MRT", "unknown")
-
-
-def test_reject_observation_mode_receipts():
-    from tempfile import TemporaryDirectory
-
-    for mode, other in (("window", "last_base_step"), ("last_base_step", "window")):
-        with TemporaryDirectory() as tmp:
-            path = Path(tmp)
-            manifest = pilot_fixture(path, mode)
-            assert r.verify_pilot(path, manifest, "MRT", mode) == 3606.0
-            with unittest.TestCase().assertRaises(ValueError):
-                r.verify_pilot(path, manifest, "MRT", other)
-        for rel in ("plan.json", "uniform/summary.json", "refined/summary.json",
-                    "uniform/ready.json", "refined/ready.json"):
-            for invalid in (other, None):
-                with TemporaryDirectory() as tmp:
-                    path = Path(tmp)
-                    manifest = pilot_fixture(path, mode)
-                    receipt = path / rel
-                    record = json.loads(receipt.read_text())
-                    if invalid is None:
-                        record.pop("observation_mode")
-                    else:
-                        record["observation_mode"] = invalid
-                    receipt.write_text(json.dumps(record))
-                    with unittest.TestCase().assertRaises(ValueError):
-                        r.verify_pilot(path, manifest, "MRT", mode)
-
-
-class ExchangeFixture:
-    """Synthetic interval ledger for orchestration tests, not a solver or GPU result."""
-    def __init__(self):
-        self.step_count = 11
-        self.events = []
-        self.begin = None
-        self.override = {}
-
-    def start_exchange_window(self):
-        self.begin = self.step_count
-        self.events.append(("start", self.step_count))
-
-    def step(self, n):
-        self.events.append(("step", n))
-        self.step_count += n
-
-    def result(self, start, window):
-        from CelerisLab.lbm.raw_exchange import summarize_exchange
-
-        total = sum(range(start + 1, self.step_count + 1))
-        result = summarize_exchange([[total, -2*total, 0., 0.]], [0], [False],
-            body_id=0, level=1, h=.5, time_end=self.step_count, window=window,
-            reference_center=(80.5, 81.),
-            **({"duration": self.step_count-start} if window == "window" else {}))
-        result.update(self.override)
-        return result
-
-    def read_exchange_window(self, body_id, *, level):
-        assert body_id == 0 and level == 1
-        self.events.append(("read_window", self.step_count))
-        return self.result(self.begin, "window")
-
-    def read_raw_exchange(self, body_id, *, level, window):
-        assert body_id == 0 and level == 1 and window == "last_base_step"
-        self.events.append(("read_raw", self.step_count))
-        return self.result(self.step_count-1, window)
-
-
-def test_window_interval_impulse_sampling_and_units():
-    base, window = ExchangeFixture(), ExchangeFixture()
-    for n in (80, 2000, 3):  # Pilot/dense, early full, and final partial interval.
-        begin = base.step_count
-        a = r.advance_refined_interval(base, n, float("inf"), "last_base_step")
-        w = r.advance_refined_interval(window, n, float("inf"), "window")
-        np.testing.assert_array_equal(w, a)
-        expected = sum(range(begin+1, begin+n+1))
-        np.testing.assert_array_equal(w, [expected, -2*expected])
-        den = .5 * r.SPEED**2 * 40
-        np.testing.assert_array_equal(w/n/den, a/n/den)
-        assert window.step_count == base.step_count == begin+n
-        assert window.events[-3:] == [("start", begin), ("step", n), ("read_window", begin+n)]
-        assert (begin+n/2)*r.SPEED/40 == (window.step_count-n/2)*r.SPEED/40
-    assert not any(event[0] == "read_raw" for event in window.events)
-
-
-def test_window_contract_rejection():
-    for key, value in (("units", "local"), ("window", "last_base_step"),
-                       ("sample_count", 2), ("time_start", 0), ("time_end", 0), ("dt", 1.)):
-        backend = ExchangeFixture()
-        backend.override[key] = value
-        with unittest.TestCase().assertRaisesRegex(RuntimeError, "window force"):
-            r.advance_refined_interval(backend, 80, float("inf"), "window")
-    backend = ExchangeFixture()
-    with unittest.TestCase().assertRaises(TimeoutError):
-        r.advance_refined_interval(backend, 80, 0, "window")
-    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)

tests/unit/test_refinement.py

@@ -142,7 +142,7 @@ class FixedPatchTests(unittest.TestCase):
                 FixedPatch2D.from_config(LBMConfig(nx=nx, ny=ny, viscosity=.1), bounds)
 
     def test_unsupported_backend_and_fine_relaxation_rejected(self):
-        for kwargs in ({"collision": "TRT"}, {"streaming": "esopull"},
+        for kwargs in ({"collision": "TRT"}, {"collision": "MRT"}, {"streaming": "esopull"},
                        {"les_enabled": True},
                        {"store_precision": "FP16S"}, {"lattice_model": "D3Q19"},
                        {"data_type": "FP64"}, {"omega_min": 1.0}):

tests/unit/test_refinement_mrt.py

@@ -1,53 +0,0 @@
-"""Host guards and source contract for MRT reuse in refined/blocked stepping (no CUDA)."""
-from pathlib import Path
-import unittest
-
-from CelerisLab.config import LBMConfig
-from CelerisLab.lbm.refinement import FixedPatch2D
-
-KERNELS = Path(__file__).resolve().parents[2] / "src/CelerisLab/lbm/kernels"
-BOUNDS = (8, 6, 16, 14)
-
-
-class RefinementMRTHost(unittest.TestCase):
-    def test_patch_accepts_implemented_models(self):
-        for collision in ("SRT", "MRT"):
-            with self.subTest(collision=collision):
-                FixedPatch2D.from_config(LBMConfig(nx=24, ny=20, viscosity=.1, collision=collision), BOUNDS)
-
-    def test_patch_rejects_unimplemented(self):
-        for options in (dict(collision="TRT"), dict(collision="MRT", les_enabled=True)):
-            with self.subTest(options=options), self.assertRaises(ValueError):
-                FixedPatch2D.from_config(LBMConfig(nx=24, ny=20, viscosity=.1, **options), BOUNDS)
-
-    def test_srt_statements_and_guards_preserved(self):
-        """MRT is an additive compile-time branch; SRT statements and other guards remain."""
-        blocks = (KERNELS / "blocks.cu").read_text() + (KERNELS / "step/block_step.cu").read_text()
-        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()
-        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("collide_srt(f, feq, forcing, omega);", channel)
-        self.assertIn("collide_srt_no_force(f, feq, d_params.omega);", refinement)
-        for source in (blocks, refinement):
-            self.assertIn("(COLLISION_MODEL != 0 && COLLISION_MODEL != 2)", source)
-            self.assertIn("USE_LES", source)
-            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")
-
-
-if __name__ == "__main__": unittest.main()

tests/unit/test_refinement_three_level_multipatch.py

@@ -173,10 +173,8 @@ def bodies_and_jets(speed=.002):
     return bodies,jets
 
 
-def levels(parents=PARENTS,children=CHILDREN,blocks=((4,4),)*3,objects=((),(),()),jets=((),(),())):
-    """Level-list constructor keywords for the L0 set, L1 set and L2 set used here."""
-    return dict(refinements=[parents,children],level_blocks=list(blocks),
-                level_objects=list(objects),level_jets=list(jets))
+KW=dict(base_block=(4,4),fine_block=(4,4),child_block=(4,4),
+        child_rectangles_in_parent=CHILDREN)
 
 
 def mock_backend(*, children=CHILDREN, bodies=False, fail_compile=False, fail_upload=False):
@@ -203,8 +201,9 @@ def mock_backend(*, children=CHILDREN, bodies=False, fail_compile=False, fail_up
         module.cuda.memcpy_htod.side_effect=upload
     objects,jets=bodies_and_jets() if bodies else ((),())
     try:
-        run=module.FixedPatchStepper(CFG,context=context,
-            **levels(children=children,objects=((),(),objects),jets=((),(),jets)))
+        run=module.FixedPatchStepper(CFG,PARENTS,context=context,
+            child_objects=objects,child_jets=jets,
+            **dict(KW,child_rectangles_in_parent=children))
     except RuntimeError:
         for allocation in allocations:
             allocation.free.assert_called_once_with()
@@ -215,29 +214,28 @@ def mock_backend(*, children=CHILDREN, bodies=False, fail_compile=False, fail_up
 class ConstructorAndSchedule(unittest.TestCase):
     def test_invalid_inputs_fail_before_context_or_allocations(self):
         context=Mock()
-        b=(4,4)
-        cases=[dict(children=(8,8,16,16)),dict(children=[]),
-               dict(children=[(16,16,32)]),
-               dict(children=[(16.5,16,32,40)]),
-               dict(children=[(16,16,32,24),(16,27,32,55)]),
-               dict(children=[(40,16,48,40)]),
-               dict(children=[(8,16,32,40)]),
-               dict(blocks=(b,b,None)),dict(blocks=(b,None,b)),dict(blocks=(None,b,b)),
-               dict(blocks=(b,b,(5,4))),dict(blocks=(b,(5,4),b)),
-               dict(blocks=(b,b,(4,))),dict(children=(16,16,32,40))]
+        cases=[dict(child=(8,8,16,16)),dict(child_rectangles_in_parent=[]),
+               dict(child_rectangles_in_parent=[(16,16,32)]),
+               dict(child_rectangles_in_parent=[(16.5,16,32,40)]),
+               dict(child_rectangles_in_parent=[(16,16,32,24),(16,27,32,55)]),
+               dict(child_rectangles_in_parent=[(40,16,48,40)]),
+               dict(child_rectangles_in_parent=[(8,16,32,40)]),
+               dict(child_block=None),dict(fine_block=None),dict(base_block=None),
+               dict(child_block=(5,4)),dict(fine_block=(5,4)),
+               dict(child_block=(4,)),dict(child_rectangles_in_parent=(16,16,32,40))]
         for changes in cases:
             with self.subTest(changes=changes),self.assertRaises((ValueError,TypeError)):
-                host.FixedPatchStepper(CFG,context=context,**levels(**changes))
+                host.FixedPatchStepper(CFG,PARENTS,context=context,**dict(KW,**changes))
         with self.assertRaisesRegex(ValueError,'margin'):
-            host.FixedPatchStepper(CFG,context=context,**levels(parents=[(1,4,20,28),(23,4,44,28)]))
+            host.FixedPatchStepper(CFG,[(1,4,20,28),(23,4,44,28)],context=context,**KW)
         objects,jets=bodies_and_jets()
-        with self.assertRaisesRegex(ValueError,'only on the finest level'):
-            host.FixedPatchStepper(CFG,context=context,**levels(objects=((),objects,())))
+        with self.assertRaisesRegex(ValueError,'only on L2'):
+            host.FixedPatchStepper(CFG,PARENTS,context=context,fine_objects=objects,**KW)
         from CelerisLab.body.jets import Jet,Tube,Parallel
         spanning=Jet(Tube((10.5,14.),0.,25.,.3),Parallel(0.),amplitude=0.)
         with self.assertRaisesRegex(ValueError,'one jet'):
-            host.FixedPatchStepper(CFG,context=context,
-                                  **levels(objects=((),(),objects),jets=((),(),[spanning])))
+            host.FixedPatchStepper(CFG,PARENTS,context=context,child_objects=objects,
+                                  child_jets=[spanning],**KW)
         context.activate.assert_not_called()
         host.cuda.mem_alloc.assert_not_called()
 
@@ -315,23 +313,21 @@ class ConstructorAndSchedule(unittest.TestCase):
 
 
 
-class RemovedLegacyAPI(unittest.TestCase):
-    """The pre-level-list constructor/initialize forms are gone and fail loudly."""
+class InitialLevels(unittest.TestCase):
+    """initialize() entry adapter: positional per-level arrays or the legacy names, never both."""
 
-    def test_removed_constructor_forms_raise_type_error(self):
-        import inspect
-        context = Mock()
-        with self.assertRaises(TypeError):  # positional bounds
-            host.FixedPatchStepper(CFG, PARENTS, context=context)
-        removed = dict(bounds=PARENTS, fine_block=(4, 4), base_block=(4, 4), fine_objects=(),
-                       jets=(), child=(8, 8, 16, 16), child_block=(4, 4), child_objects=(),
-                       child_jets=(), child_rectangles_in_parent=CHILDREN)
-        for name, value in removed.items():
-            with self.subTest(keyword=name), self.assertRaises(TypeError):
-                host.FixedPatchStepper(CFG, context=context, **levels(), **{name: value})
-        context.activate.assert_not_called()
-        self.assertEqual(list(inspect.signature(host.FixedPatchStepper.initialize).parameters),
-                         ["self", "level_g"])  # no coarse_g/fine_g/child_g
+    def test_forms(self):
+        a, b, c = object(), object(), object()
+        f = host._initial_levels
+        self.assertEqual(f((a, b), None, None, None), (a, b))
+        self.assertEqual(f((a, b, c), None, None, None), (a, b, c))
+        self.assertEqual(f((a, b), None, None, c), (a, b, c))      # old initialize(c, f, child_g=g)
+        self.assertEqual(f((), a, b, None), (a, b))
+        self.assertEqual(f((), a, b, c), (a, b, c))
+        for args in (((a,), None, None, c), ((a, b, c), None, None, c), ((a,), a, b, None),
+                     ((), a, None, None), ((), None, b, c)):
+            with self.subTest(args=args), self.assertRaises(TypeError):
+                f(*args)
 
 
 if __name__=='__main__':

tests/unit/test_shifted_jets.py

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

tests/unit/test_shifted_storage.py

@@ -78,15 +78,13 @@ class ShiftedStorage(unittest.TestCase):
 
     def test_shifted_density_and_tag_validation(self):
         old,new = topology(A),topology(B)
-        a = tuple(np.where(m[None], np.float32(-.001), np.float32(np.nan)).repeat(9,axis=0)
-                  for m in old.leaf_masks)  # FP32 under NumPy 1 and 2 promotion rules
+        a = tuple(np.where(m[None], np.float32(-.001), np.nan).repeat(9,axis=0) for m in old.leaf_masks)
         remap(old,new,a)
         with self.assertRaisesRegex(ValueError,'representation'): remap(old,new,a,False)
         with self.assertRaisesRegex(ValueError,'FP32'): remap(old,new,tuple(x.astype(np.float64) for x in a))
         a[0][:,old.leaf_masks[0]] = -1
         with self.assertRaisesRegex(ValueError,'positive density'): remap(old,new,a)
-        rest = tuple(np.where(m[None],np.float32(0),np.float32(np.nan)).repeat(9,axis=0)
-                     for m in old.leaf_masks)
+        rest = tuple(np.where(m[None],np.float32(0),np.nan).repeat(9,axis=0) for m in old.leaf_masks)
         remap(old,new,rest)
         with self.assertRaisesRegex(ValueError,'positive density'):
             remap_synchronized(old,new,rest,base_count=7,level_steps=(7,14,28),phase='postcollision_g')
@@ -131,10 +129,9 @@ class ShiftedStorage(unittest.TestCase):
     def test_dense_or_mixed_shifted_rejected_before_compilation(self):
         module=backend.host_module()
         cfg=replace(backend.CFG,ddf_shifting=True)
-        for blocks in ([None,None],[(4,4),None],[None,(4,4)]):
-            with self.assertRaisesRegex(ValueError,'all-blocked|blocked refined levels below'):
-                module.FixedPatchStepper(cfg,context=None,refinements=[(4,4,20,28)],
-                                         level_blocks=blocks)
+        for kwargs in ({},dict(base_block=(4,4)),dict(fine_block=(4,4))):
+            with self.assertRaisesRegex(ValueError,'all-blocked|base_block requires fine_block'):
+                module.FixedPatchStepper(cfg,(4,4,20,28),context=None,**kwargs)
         module.compiler.compile_kernel.assert_not_called()
 
     def test_uniform_block_codec_and_raw_snapshot(self):

tests/unit/test_state_regressions.py

@@ -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)])

tests/unit/test_step_sync.py

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

tests/unit/test_time_refined_dfg.py

@@ -1,86 +0,0 @@
-"""CPU contract of the measurement-only refined DFG timing harness (no CUDA)."""
-from pathlib import Path
-import sys
-import unittest
-
-import numpy as np
-
-sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "validation"))
-import time_refined_dfg as t  # noqa: E402
-
-
-class TimingHarnessContract(unittest.TestCase):
-    def test_equal_simulated_duration(self):
-        s = t.schedule(2000, 200)
-        self.assertEqual(s["refined"], (200, 2000))
-        self.assertEqual(s["uniform"], (400, 4000))  # one refined base step = two D80 steps
-        self.assertAlmostEqual(s["tstar_window"], 2000 * .01 / 40)
-        for bad in ((0, 1), (1, -1)):
-            with self.assertRaises(ValueError):
-                t.schedule(*bad)
-
-    def test_timing_only_labels(self):
-        for name in ("B", "C", "E'"):
-            self.assertFalse(t.VARIANTS[name]["force_history_valid"])
-            self.assertTrue(t.VARIANTS[name]["timing_only"])
-        for name in ("A", "E"):
-            self.assertFalse(t.VARIANTS[name]["force_history_valid"])  # reads discarded
-            self.assertTrue(t.VARIANTS[name]["force_reads"])
-            self.assertIn("runner-like", t.VARIANTS[name]["force_note"])
-        self.assertEqual({v["case"] for v in t.VARIANTS.values()}, {"refined", "uniform"})
-        self.assertIn("final base interval", t.VARIANTS["C"]["force_note"])
-        self.assertIn("whole-window", t.VARIANTS["E'"]["force_note"])
-
-    def test_deadline(self):
-        import time
-        with self.assertRaises(TimeoutError):
-            t.check_deadline(time.monotonic() - 1)
-        t.check_deadline(time.monotonic() + 60)
-
-    def test_parity_detects_bits_and_nan_masks(self):
-        a = np.array([[1., np.nan], [2., 3.]], np.float32)
-        self.assertIsNone(t.same_state([a], [a.copy()]))
-        b = a.copy(); b[1, 1] = np.nextafter(np.float32(3), np.float32(4))
-        self.assertIn("bits", t.same_state([a], [b]))
-        c = a.copy(); c[0, 0] = np.nan
-        self.assertIn("NaN", t.same_state([a], [c]))
-        self.assertIn("level count", t.same_state([a], [a, a]))
-        inf = a.copy(); inf[1, 0] = np.inf
-        self.assertIn("infinite", t.same_state([inf], [inf.copy()]))  # matching inf still fails
-        self.assertIn("infinite", t.same_state([a], [inf]))
-
-    def test_flat_uniform_ddf(self):
-        fluid = np.array([[True, False, True], [True, True, False]])
-        flat = np.ones(9 * fluid.size, np.float32)  # Simulation.get_ddf() layout
-        self.assertTrue(t.uniform_populations_finite(flat, fluid))
-        flat[1 * fluid.size + 1] = np.nan  # q=1, solid cell 1: ignored
-        self.assertTrue(t.uniform_populations_finite(flat, fluid))
-        flat[4 * fluid.size + 0] = np.nan  # q=4, fluid cell 0: detected
-        self.assertFalse(t.uniform_populations_finite(flat, fluid))
-        self.assertTrue(t.uniform_populations_finite(np.ones((9,) + fluid.shape), fluid))
-        with self.assertRaises(RuntimeError):
-            t.uniform_populations_finite(np.ones(9 * fluid.size + 1), fluid)
-
-    def test_physical_health_limits(self):
-        ok = (np.array([1., 1.01]), np.array([.01, .02]), np.array([0., .01]))
-        health = t.physical_health([ok])
-        self.assertAlmostEqual(health["rho_max"], 1.01)
-        for bad in ((np.array([1., np.nan]),) + ok[1:],
-                    (np.array([.4, 1.]),) + ok[1:],
-                    (ok[0], np.array([.2, 0.]), ok[2]),
-                    (np.array([]), np.array([]), np.array([]))):
-            with self.assertRaises(RuntimeError):
-                t.physical_health([bad])
-
-    def test_summary_reports_differences_without_claims(self):
-        rows = [dict(variant=v, seconds=s) for v, s in
-                (("A", 3.), ("A", 5.), ("B", 2.), ("C", 1.), ("E", 2.), ("E'", 1.5))]
-        s = t.summarize(rows, .5)
-        self.assertEqual(s["A"]["median_seconds"], 4.)
-        self.assertEqual(s["A_minus_B_seconds"], 2.)
-        self.assertEqual(s["B_minus_C_seconds"], 1.)
-        self.assertEqual(s["A_over_E"], 2.)
-        self.assertIn("not exact causal", s["interpretation"])
-
-
-if __name__ == "__main__": unittest.main()

tests/unit/test_time_window_dfg.py

@@ -1,38 +0,0 @@
-"""CPU contract of the A-versus-window timing harness (no CUDA)."""
-from pathlib import Path
-import sys
-import unittest
-
-import numpy as np
-
-sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "validation"))
-import time_window_dfg as w  # noqa: E402
-
-
-class WindowTimingContract(unittest.TestCase):
-    def test_interval_and_variants(self):
-        self.assertEqual(w.INTERVAL, 80)
-        self.assertEqual(w.VARIANTS, ("A", "W", "W1"))
-
-    def test_components(self):
-        obs = dict(total=dict(impulse=np.array([1., 2.]), angular_impulse=3., mass_into_fluid=4.))
-        np.testing.assert_array_equal(w.components(obs), [1., 2., 3., 4.])
-
-    def test_interval_comparison(self):
-        ref = np.array([[1., -1., 0., 0.]])
-        scale = np.array([[10., 10., 1., 1.]])
-        self.assertEqual(w.compare_intervals(ref, scale, ref.copy()), 0.)
-        near = ref + np.array([[5e-9, 0., 0., 0.]])
-        self.assertLessEqual(w.compare_intervals(ref, scale, near), 1.)
-        far = ref + np.array([[1e-7, 0., 0., 0.]])
-        self.assertGreater(w.compare_intervals(ref, scale, far), 1.)
-        zero = np.zeros((1, 4))
-        self.assertGreater(w.compare_intervals(zero, zero, zero + 1e-12), 1.)  # floor, no div-by-0
-
-    def test_candidate_identity_records_files(self):
-        identity = w.candidate_identity(Path(__file__).resolve().parents[2])
-        self.assertIn("checkout_revision", identity)
-        self.assertEqual(set(identity["sha256"]), set(w.CANDIDATE_FILES))
-
-
-if __name__ == "__main__": unittest.main()

tests/unit/test_validation_source_provenance.py

@@ -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):

tests/validation/data/les_flow/source_pins_a135252.json

@@ -1,110 +0,0 @@
-{
-  "base_commit": "a135252ae78b47b57d7e77d19001700b3bedac8b",
-  "production_origin_commit": "a135252ae78b47b57d7e77d19001700b3bedac8b",
-  "source_experiment": "Explicit a135252 uniform SRT LES regression. Sources pin the committed corrected tree; baseline is a synthetic isolated reverse-header control, not the committed a135252 source. Historical profiles and receipts remain unchanged.",
-  "sources": {
-    "src/CelerisLab/__init__.py": "21cc469bd6e970a1f9ff5970c8eea4602065e41fc881854759ee565ee55c10c6",
-    "src/CelerisLab/body/__init__.py": "e4e0e8f0769a94428d5b02fac790443997556cfc5515a5f1ed1595d2c694d69d",
-    "src/CelerisLab/body/action_smoother.py": "b1a23ee6bbd4850b172cb8738c5c3546ee465a54189e6af9d8044f023d4687dc",
-    "src/CelerisLab/body/coupling/__init__.py": "c931f7eb318d48408c3e2febcc6917c88c8dcc1697cbf4329b1f340d94c35763",
-    "src/CelerisLab/body/coupling/soa_packer.py": "8ec26fd55ef74801bbd5ab6bd3d0a7dabc750cbd498aaac2ca4c61a0108ad3c9",
-    "src/CelerisLab/body/ddf_patch.py": "60fcfb7441e73bf290bcff41ca3a83da3e7ddad765d7247464e8f02e3043b4e2",
-    "src/CelerisLab/body/geometry/__init__.py": "ada88980ab672959aca9aa3a4c4aade3219524b2ab68110cd2a2f41e3e0ca90a",
-    "src/CelerisLab/body/geometry/base.py": "cceca14361ca2f34d34a3e43730e1a79b8ca81be00f0dd62e884db32b479419f",
-    "src/CelerisLab/body/geometry/circle.py": "7605ca7c21103f1d801ac73ab8dd18dffbdac425b2dee7b8858b283628a9e436",
-    "src/CelerisLab/body/jets.py": "4104c24af4651f4bb4f8d8fd36fb6d88f41c6e4469822f36e22e74c9ede31dac",
-    "src/CelerisLab/body/manager.py": "01b653d25bd9b4333379c8bfd12383596b686d2029f2e91b1c91b618540ec6b3",
-    "src/CelerisLab/body/objects.py": "8e63cee8faa9cc6243bcff428be628dfad73a02a9a3b8ece7d78c0a63406a08d",
-    "src/CelerisLab/body/preprocess/__init__.py": "dfd9d58bc07f626ab23a70053e31b88a6d9165d2e4c76a4e9f48abe674d3d2ec",
-    "src/CelerisLab/body/preprocess/flag_overlay.py": "831fc9e9736b758847759a085ff133eb49ec91318ace4fda76f85960138ee300",
-    "src/CelerisLab/body/registry.py": "fbb7327780adbdc6da15ebdb799980daf32df22ee974af0893d7409f177bbb68",
-    "src/CelerisLab/body/sync_plan.py": "3a15bfe9ebeb91482dbfc68850761ef39c872cc12d2efc795babd0c01e392323",
-    "src/CelerisLab/common/__init__.py": "d4dbde78bc97fccc9eabac9abae8f0f15c112c10ff8e9b45bd9401d4723df1ef",
-    "src/CelerisLab/common/_types.py": "aad2ff1a9033d4fd68783ad7123afb47201ddc58785cb6dc0246947037072a5f",
-    "src/CelerisLab/common/checkpoint.py": "b2f960aecd5ac27a3a7130b809ffad4709c44d522edef0359ab952654625410b",
-    "src/CelerisLab/common/pathline.py": "a1b6efcc0a076d0f1dc8d49a595779426d7d5626b00072a59bac710ff02ad046",
-    "src/CelerisLab/common/preprocess.py": "7fc78a08857cf8e98519500b094a1d896af189b6b15658ff9b388ed51bed4515",
-    "src/CelerisLab/common/render.py": "0e055476257eb2bcd11e733766e52195de02f8fad228f570a3511a7c831bdc29",
-    "src/CelerisLab/common/streakline/__init__.py": "13ff1cfa416fdd721a08a659e76b5a5a99b8d3201add10a83b7b0bc654bc1eec",
-    "src/CelerisLab/common/streakline/_config.py": "a9185ef68e9c7b5d5a1dc0b04a28341e2ad91d13c145a7c106636a878cf0a605",
-    "src/CelerisLab/common/streakline/_integrate.py": "3fbd4368b2c8d0e7fda40dc65aac5df02b085008b4c68acd83cb7ae45d33a13b",
-    "src/CelerisLab/common/streakline/_render.py": "236cd637414ee318c4d66f9aed32110d8dc42a100d65fde06172f7cd0ba62c65",
-    "src/CelerisLab/common/streakline/_streakline.py": "1a3e08daa706b5f83cdeb337e9a945a36ddf7583c40af1d0bb9d825ac954df37",
-    "src/CelerisLab/config.py": "2f1bba7515f5bc08cb3a8d140bcafe7fa0689e01b3b06494697bb2956a71530e",
-    "src/CelerisLab/configs/CONFIG.md": "41cafdbe525366c08aa9d0416ea026ccf0026ba7123b8a9b65f968a80d928e3a",
-    "src/CelerisLab/configs/config_body.json": "055f261f0828ca1d4f2bb694bd15b72bbcabe31d552326208f28e37f761adab1",
-    "src/CelerisLab/configs/config_lbm.json": "17e4311f1f250c6ece59177a8b6ff856b69a016c7c10267e774b030a0a390865",
-    "src/CelerisLab/configs/config_lbm_flume_mrt_zouhe.json": "8f593321db05a563a42931603a228d61cbcba06dfbe113262d5cd0ad93c0fe79",
-    "src/CelerisLab/configs/config_lbm_flume_trt_regularized.json": "f4bba8e6a4339fc3c4eb14f6e2f57c4b22993c73703c773d853edfbe34736e56",
-    "src/CelerisLab/configs/config_lbm_three_cylinder_triangle.json": "eeb8e7149dbe4aa6b3a9562802735aa950750dfbe2d972a0727e788573afa817",
-    "src/CelerisLab/cuda/__init__.py": "0d01dff9f0399c8baba822aab5ca0122a135f011008ed8a499ebd9f7e5b06aea",
-    "src/CelerisLab/cuda/compiler_v2.py": "c4cc3ec4445c8d75e6a253dd87963877117a722bc73b9d4811806fc6045d08c1",
-    "src/CelerisLab/cuda/context.py": "013dd4ec6d01d2fbd11afdfb103eac6a273bd9f798d663d761b851eeb27885e9",
-    "src/CelerisLab/cuda/obs_layout.py": "5ffb2c3aeeaaaaeb64f2cd8febfbcf4ad9919e5414020ad753cfade0683b21c2",
-    "src/CelerisLab/lbm/__init__.py": "7f60fb3aaae81501b510d08c2fedff44fcb05657260eb10b6f5cc91e7204306b",
-    "src/CelerisLab/lbm/block_stepper.py": "00b313daddc6e63d8ab8423c9190ca7e92ad291de20a2f6b80eb53e3f2d85ec7",
-    "src/CelerisLab/lbm/blocks.py": "1e644c5719993f418185ad4a10b6950a30636fc912befd9eab41ff48b4cf85cd",
-    "src/CelerisLab/lbm/channel.py": "40d0354e5dc97bcdb7e7b5c1e7f9303a109b7134d8a3af88b8ff4cd75ab5a095",
-    "src/CelerisLab/lbm/curved_links.py": "b6957fa13d13f864dba4f7364e93a39905d062dbb3ee9b3f5191add81fff0732",
-    "src/CelerisLab/lbm/descriptors.py": "c9f025dfc14da43b989047b84cc22bd05d5cc92c9ec695c1da68fdfb788e3f2b",
-    "src/CelerisLab/lbm/equilibrium.py": "2fb2f2bb7ff326d23abce80fc2a4c0907b17740ea3e29fe6ae079c5044783826",
-    "src/CelerisLab/lbm/field.py": "0e727eacc3706add4d8d15c418e9b631050871f831698d3ac689dd5f2c701b9b",
-    "src/CelerisLab/lbm/hierarchy.py": "f234975074f6b6d289d573ff6ea6832feae0e27cb04f80b37fe81792b13a12e7",
-    "src/CelerisLab/lbm/initializers.py": "dacf9586963e862d6d0a98ef1a066036be6f91e9d423720661d8ef2c1fb2df6a",
-    "src/CelerisLab/lbm/kernels/blocks.cu": "668e5cf14e88bdcfa281c2fa6c75c0f8f8cdbbfb8ba2ca03064ae02ef7ad0057",
-    "src/CelerisLab/lbm/kernels/boundary/bounce_back.cuh": "aba3748c564ed91b161d268ef8b737b7c7be96a823063d201f3da684dd845233",
-    "src/CelerisLab/lbm/kernels/boundary/curved_boundary.cuh": "aeb16bfd483514fb03e15a2fed437d673c3b8b2fe68ab83edf4244ef593878ea",
-    "src/CelerisLab/lbm/kernels/boundary/esopull_curved_helpers.cuh": "b9b474bc4edaff05681c5443235472d04072d0d775fc0eb9c5967faef52b0258",
-    "src/CelerisLab/lbm/kernels/boundary/ibm_kernels.cuh": "e6909b547dc8d64cdd8a76a90660243a8f5fee535caa161b52b4dd8b7c29934b",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/channel_stabilized.cuh": "efe077afcbb6b731256a987c2fd79a1dbc470c902f87070d60421ea6cb13d4e2",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/common.cuh": "59b38a89439878e00de7de16b9c7b03feff443fcc5a421593f7d2536dcbb7ab8",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/equilibrium.cuh": "f0964c811b2c41a5aaa1c6d99c490b06e850c634eb8749f1f05ef61f93c2de1d",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/regularized.cuh": "943d4a571818bacb89c70bccfaac202691121e3e385803ce6309123a0a03ddaf",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/zou_he_local.cuh": "e73e66b853b1e4e0e30d8f4185d832aa414ce670a1813ce2b5459f2887f71f89",
-    "src/CelerisLab/lbm/kernels/boundary/inlet_outlet.cuh": "de8b213a6da42c2e5e9f8966199fc66ea4541b85144a90f3f5dbad3c6ab63b97",
-    "src/CelerisLab/lbm/kernels/boundary/outlet/pressure_neq.cuh": "c8b2adc66d12fe602076ddc9693c5c208711fcaddb58aa9a31401a269f51c4c4",
-    "src/CelerisLab/lbm/kernels/boundary/planar_velocity.cuh": "501b2759d0e2e4280cb6fdd127d66a50fa89f6de48fc2cae9a7eafb11ae90bed",
-    "src/CelerisLab/lbm/kernels/config.h": "7d1124125e0b354558297934460e64c760fb68cdd7bf6d01a1238bb2eaab8c37",
-    "src/CelerisLab/lbm/kernels/config/config_grid.h": "1db3e030ebdc116cd7f02362d1fd077daac55e8f0b4329f6285948c224d3ca5d",
-    "src/CelerisLab/lbm/kernels/config/config_method.h": "4374e04a130f90f97d17cc20c40d2f9ea0ed0dd8603817d07f215d02266e247c",
-    "src/CelerisLab/lbm/kernels/config/config_objects.h": "db793af052c756561a190a3ff2cb93ee5fe28462ee4f97c6af80882b4dc8b072",
-    "src/CelerisLab/lbm/kernels/config/config_obs.h": "c11e2249359145b5c4cbaaf0487506fa77c1f4b82c7c169ddc574aa0babcd727",
-    "src/CelerisLab/lbm/kernels/config/config_physics.h": "8ac0990b168e1058588676cc05c80df8634cfd671dbc92a89246c3c372d83a4e",
-    "src/CelerisLab/lbm/kernels/core/descriptors.cuh": "8440bc14857da9007982650f828a23608eec9f7cc4bf772e8c8dc1239cb45356",
-    "src/CelerisLab/lbm/kernels/core/flags.cuh": "0025705f24710330d9d9195f713879bfb650a85a3449baef0e196b831af104ab",
-    "src/CelerisLab/lbm/kernels/core/layout.cuh": "1fbd820021c89ac3efcde24145996cb0147769e607e498e61f308ed3e0b13706",
-    "src/CelerisLab/lbm/kernels/core/obs.cuh": "b742b77c9f61e1f020fe9922c3838ae9d855e17b381154958b58f10a22938922",
-    "src/CelerisLab/lbm/kernels/core/params.cuh": "6e18bf730d936d940e3d85452f0714a2eaae31bf41002f9fd520ec5b372878dd",
-    "src/CelerisLab/lbm/kernels/core/precision.cuh": "849df14b4cce50af52399e4b8f3e997196f3ae5f1163f68e28df3e6b2507a8c4",
-    "src/CelerisLab/lbm/kernels/kernel_v2.cu": "c7bd3fb705b77261ba2441c52a24a7e6a7865c165cba088a1b75201c4d29c408",
-    "src/CelerisLab/lbm/kernels/operators/collision_mrt.cuh": "aee444eb60c47a3fd518dca975d1af05425a0818a0ec6c3fb3f6150f60c2cb44",
-    "src/CelerisLab/lbm/kernels/operators/collision_srt.cuh": "6b7ff842f392c8f853d2d1a97cc69bfe50f21283f73e659404da07cf6c95f5e1",
-    "src/CelerisLab/lbm/kernels/operators/collision_trt.cuh": "9725b9840b9ad8b4ec7be61ff5d06d3151e86d1a87585c13f2fbf934d0d2c5f6",
-    "src/CelerisLab/lbm/kernels/operators/forcing_guo.cuh": "969a430c1af03f32e3bd0df95d805e64f56334717c44dd4ba208ba503062a24b",
-    "src/CelerisLab/lbm/kernels/operators/helpers.cuh": "0b3a4d95d7d19f5fec09e5423b8f4cc99f8a226b541967425967330da5a051ec",
-    "src/CelerisLab/lbm/kernels/operators/macro.cuh": "2be20eb2b7d7f5522daaad7f4b57b1ff8cdf883efe4a67846a96783b2fe846a3",
-    "src/CelerisLab/lbm/kernels/operators/turbulence_smag.cuh": "a3db46c2e7d27530b2d1436e65cdbed0b72cc7e047bfbeef2a640877271b51aa",
-    "src/CelerisLab/lbm/kernels/refinement.cu": "b45aad9c022cecb64f7e968ec3cae2d8385a3cc430ee409700c404a3f4dd8cf8",
-    "src/CelerisLab/lbm/kernels/step/aux_kernels.cu": "578a5b20a157241ee678547059abb1372dd5a589ad06bb2c15b987eb01ca1013",
-    "src/CelerisLab/lbm/kernels/step/block_channel.cu": "ee8a31398b8e5233d977c816e6b8e060c1eb2ec71320e594226dbca55593c0d0",
-    "src/CelerisLab/lbm/kernels/step/curved_double.cu": "bfa7a1df1e939020314d49755045f7a85fe4a19cc1c68dbe62653c66c5e7c2b3",
-    "src/CelerisLab/lbm/kernels/step/esopull_macro.cu": "c73116020ca217ede1e4de27c8269c31f9d91e33433ac8252a21e9b14187c50f",
-    "src/CelerisLab/lbm/kernels/step/esopull_sync.cu": "c0ff3e72900c3ab89a05dd03684e96d3b740cf1672d565727fc2af165933d087",
-    "src/CelerisLab/lbm/kernels/step/init_flow.cu": "305be3bb12fc0d039acec1701baabcf0e8a35e683c49c34f2af8ca9867d2b29c",
-    "src/CelerisLab/lbm/kernels/step/one_step_double.cu": "f9f8242b38e8e0cf8425b75e2b0215bc15363c62eaa0fb43c761b8e0931bfdc9",
-    "src/CelerisLab/lbm/kernels/step/one_step_esopull.cu": "aa223b2744ae6c9125673df311a96ce588032c1ba58bebb11fd33ecb990f8ed4",
-    "src/CelerisLab/lbm/kernels/streaming/esopull_semantic_helpers.cuh": "dd5a9091628b079efd97e53fd49e52d09dcee88529235db77a5648e02937af6e",
-    "src/CelerisLab/lbm/kernels/streaming/esopull_single_buffer.cuh": "77ed4ab9a0ebc5ff62a91a7c39066ef395391ae36e9040a69fb2bd8b1626dc79",
-    "src/CelerisLab/lbm/kernels/streaming/pull_double_buffer.cuh": "b65d741ed78b7b62f99531ba0c0ce1936663d8dc9640e7d7d16c707f1baf6549",
-    "src/CelerisLab/lbm/population_storage.py": "a6a86c29c52c892edfe4802fb773c387212e3f4cc86708d80e154986ddf88044",
-    "src/CelerisLab/lbm/raw_exchange.py": "9031a196006a0f74dee4028e6f3bb673bc19ef7959f9f04dde9e01f93293aeb3",
-    "src/CelerisLab/lbm/refinement.py": "100d5e46ac894f6008b61364cdad5d37c2ca7ed949d8d71405572d6366526417",
-    "src/CelerisLab/lbm/refinement_stepper.py": "536cd1d3482591e4ff57c4ae8e888c19e31701687d287aa509129df5b2a43be3",
-    "src/CelerisLab/lbm/refinement_tables.py": "0cbc0f29aabd0ab4ba1f912bd4d0ac2b430246584cb6ddf13dd28e10582accf3",
-    "src/CelerisLab/lbm/stepper.py": "0dcb7cd7ae87e33e3dc67a38b6aa43042fbe673e37d9ad165342ee1d695933ce",
-    "src/CelerisLab/lbm/synchronized_remap.py": "7400fc4beaffd4649d6a9c524d38ce5fd6fa7eeb32eb5332e4030a4b6648f197",
-    "src/CelerisLab/simulation.py": "0a03904dc6de88667d7af699005a289adf8b09f0976cb0d099b041f4830a8f4c"
-  },
-  "candidate_header_sha256": "a3db46c2e7d27530b2d1436e65cdbed0b72cc7e047bfbeef2a640877271b51aa",
-  "baseline_header_sha256": "ff7f000297ee0817e255ad9fcb6a13b647e3ddd5b206518d35f38d2895a9f501"
-}

tests/validation/data/les_flow/source_pins_dev8403956.json

@@ -1,109 +0,0 @@
-{
-  "base_commit": "8403956a9afc0b0bb89265cec374392013d89016",
-  "production_origin_commit": "8403956a9afc0b0bb89265cec374392013d89016",
-  "source_experiment": "Explicit dev8403956 uniform SRT LES experiment; historical 9805383/5465832 receipts remain historical. Corrected permits only the reviewed normalization header.",
-  "sources": {
-    "src/CelerisLab/__init__.py": "21cc469bd6e970a1f9ff5970c8eea4602065e41fc881854759ee565ee55c10c6",
-    "src/CelerisLab/body/__init__.py": "e4e0e8f0769a94428d5b02fac790443997556cfc5515a5f1ed1595d2c694d69d",
-    "src/CelerisLab/body/action_smoother.py": "b1a23ee6bbd4850b172cb8738c5c3546ee465a54189e6af9d8044f023d4687dc",
-    "src/CelerisLab/body/coupling/__init__.py": "c931f7eb318d48408c3e2febcc6917c88c8dcc1697cbf4329b1f340d94c35763",
-    "src/CelerisLab/body/coupling/soa_packer.py": "8ec26fd55ef74801bbd5ab6bd3d0a7dabc750cbd498aaac2ca4c61a0108ad3c9",
-    "src/CelerisLab/body/ddf_patch.py": "60fcfb7441e73bf290bcff41ca3a83da3e7ddad765d7247464e8f02e3043b4e2",
-    "src/CelerisLab/body/geometry/__init__.py": "ada88980ab672959aca9aa3a4c4aade3219524b2ab68110cd2a2f41e3e0ca90a",
-    "src/CelerisLab/body/geometry/base.py": "cceca14361ca2f34d34a3e43730e1a79b8ca81be00f0dd62e884db32b479419f",
-    "src/CelerisLab/body/geometry/circle.py": "7605ca7c21103f1d801ac73ab8dd18dffbdac425b2dee7b8858b283628a9e436",
-    "src/CelerisLab/body/jets.py": "4104c24af4651f4bb4f8d8fd36fb6d88f41c6e4469822f36e22e74c9ede31dac",
-    "src/CelerisLab/body/manager.py": "01b653d25bd9b4333379c8bfd12383596b686d2029f2e91b1c91b618540ec6b3",
-    "src/CelerisLab/body/objects.py": "8e63cee8faa9cc6243bcff428be628dfad73a02a9a3b8ece7d78c0a63406a08d",
-    "src/CelerisLab/body/preprocess/__init__.py": "dfd9d58bc07f626ab23a70053e31b88a6d9165d2e4c76a4e9f48abe674d3d2ec",
-    "src/CelerisLab/body/preprocess/flag_overlay.py": "831fc9e9736b758847759a085ff133eb49ec91318ace4fda76f85960138ee300",
-    "src/CelerisLab/body/registry.py": "fbb7327780adbdc6da15ebdb799980daf32df22ee974af0893d7409f177bbb68",
-    "src/CelerisLab/body/sync_plan.py": "3a15bfe9ebeb91482dbfc68850761ef39c872cc12d2efc795babd0c01e392323",
-    "src/CelerisLab/common/__init__.py": "d4dbde78bc97fccc9eabac9abae8f0f15c112c10ff8e9b45bd9401d4723df1ef",
-    "src/CelerisLab/common/_types.py": "aad2ff1a9033d4fd68783ad7123afb47201ddc58785cb6dc0246947037072a5f",
-    "src/CelerisLab/common/checkpoint.py": "b2f960aecd5ac27a3a7130b809ffad4709c44d522edef0359ab952654625410b",
-    "src/CelerisLab/common/pathline.py": "a1b6efcc0a076d0f1dc8d49a595779426d7d5626b00072a59bac710ff02ad046",
-    "src/CelerisLab/common/preprocess.py": "7fc78a08857cf8e98519500b094a1d896af189b6b15658ff9b388ed51bed4515",
-    "src/CelerisLab/common/render.py": "0e055476257eb2bcd11e733766e52195de02f8fad228f570a3511a7c831bdc29",
-    "src/CelerisLab/common/streakline/__init__.py": "13ff1cfa416fdd721a08a659e76b5a5a99b8d3201add10a83b7b0bc654bc1eec",
-    "src/CelerisLab/common/streakline/_config.py": "a9185ef68e9c7b5d5a1dc0b04a28341e2ad91d13c145a7c106636a878cf0a605",
-    "src/CelerisLab/common/streakline/_integrate.py": "3fbd4368b2c8d0e7fda40dc65aac5df02b085008b4c68acd83cb7ae45d33a13b",
-    "src/CelerisLab/common/streakline/_render.py": "236cd637414ee318c4d66f9aed32110d8dc42a100d65fde06172f7cd0ba62c65",
-    "src/CelerisLab/common/streakline/_streakline.py": "1a3e08daa706b5f83cdeb337e9a945a36ddf7583c40af1d0bb9d825ac954df37",
-    "src/CelerisLab/config.py": "2f1bba7515f5bc08cb3a8d140bcafe7fa0689e01b3b06494697bb2956a71530e",
-    "src/CelerisLab/configs/CONFIG.md": "41cafdbe525366c08aa9d0416ea026ccf0026ba7123b8a9b65f968a80d928e3a",
-    "src/CelerisLab/configs/config_body.json": "055f261f0828ca1d4f2bb694bd15b72bbcabe31d552326208f28e37f761adab1",
-    "src/CelerisLab/configs/config_lbm.json": "17e4311f1f250c6ece59177a8b6ff856b69a016c7c10267e774b030a0a390865",
-    "src/CelerisLab/configs/config_lbm_flume_mrt_zouhe.json": "8f593321db05a563a42931603a228d61cbcba06dfbe113262d5cd0ad93c0fe79",
-    "src/CelerisLab/configs/config_lbm_flume_trt_regularized.json": "f4bba8e6a4339fc3c4eb14f6e2f57c4b22993c73703c773d853edfbe34736e56",
-    "src/CelerisLab/configs/config_lbm_three_cylinder_triangle.json": "eeb8e7149dbe4aa6b3a9562802735aa950750dfbe2d972a0727e788573afa817",
-    "src/CelerisLab/cuda/__init__.py": "0d01dff9f0399c8baba822aab5ca0122a135f011008ed8a499ebd9f7e5b06aea",
-    "src/CelerisLab/cuda/compiler_v2.py": "c4cc3ec4445c8d75e6a253dd87963877117a722bc73b9d4811806fc6045d08c1",
-    "src/CelerisLab/cuda/context.py": "013dd4ec6d01d2fbd11afdfb103eac6a273bd9f798d663d761b851eeb27885e9",
-    "src/CelerisLab/cuda/obs_layout.py": "5ffb2c3aeeaaaaeb64f2cd8febfbcf4ad9919e5414020ad753cfade0683b21c2",
-    "src/CelerisLab/lbm/__init__.py": "7f60fb3aaae81501b510d08c2fedff44fcb05657260eb10b6f5cc91e7204306b",
-    "src/CelerisLab/lbm/block_stepper.py": "00b313daddc6e63d8ab8423c9190ca7e92ad291de20a2f6b80eb53e3f2d85ec7",
-    "src/CelerisLab/lbm/blocks.py": "1e644c5719993f418185ad4a10b6950a30636fc912befd9eab41ff48b4cf85cd",
-    "src/CelerisLab/lbm/channel.py": "40d0354e5dc97bcdb7e7b5c1e7f9303a109b7134d8a3af88b8ff4cd75ab5a095",
-    "src/CelerisLab/lbm/curved_links.py": "b6957fa13d13f864dba4f7364e93a39905d062dbb3ee9b3f5191add81fff0732",
-    "src/CelerisLab/lbm/descriptors.py": "c9f025dfc14da43b989047b84cc22bd05d5cc92c9ec695c1da68fdfb788e3f2b",
-    "src/CelerisLab/lbm/equilibrium.py": "2fb2f2bb7ff326d23abce80fc2a4c0907b17740ea3e29fe6ae079c5044783826",
-    "src/CelerisLab/lbm/field.py": "0e727eacc3706add4d8d15c418e9b631050871f831698d3ac689dd5f2c701b9b",
-    "src/CelerisLab/lbm/hierarchy.py": "f234975074f6b6d289d573ff6ea6832feae0e27cb04f80b37fe81792b13a12e7",
-    "src/CelerisLab/lbm/initializers.py": "dacf9586963e862d6d0a98ef1a066036be6f91e9d423720661d8ef2c1fb2df6a",
-    "src/CelerisLab/lbm/kernels/blocks.cu": "2fa894b20a29f006911ac3e3aad0793cc4aaf9ccd7a67d01c6320a0836b1d8ef",
-    "src/CelerisLab/lbm/kernels/boundary/bounce_back.cuh": "aba3748c564ed91b161d268ef8b737b7c7be96a823063d201f3da684dd845233",
-    "src/CelerisLab/lbm/kernels/boundary/curved_boundary.cuh": "aeb16bfd483514fb03e15a2fed437d673c3b8b2fe68ab83edf4244ef593878ea",
-    "src/CelerisLab/lbm/kernels/boundary/esopull_curved_helpers.cuh": "b9b474bc4edaff05681c5443235472d04072d0d775fc0eb9c5967faef52b0258",
-    "src/CelerisLab/lbm/kernels/boundary/ibm_kernels.cuh": "e6909b547dc8d64cdd8a76a90660243a8f5fee535caa161b52b4dd8b7c29934b",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/channel_stabilized.cuh": "efe077afcbb6b731256a987c2fd79a1dbc470c902f87070d60421ea6cb13d4e2",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/common.cuh": "59b38a89439878e00de7de16b9c7b03feff443fcc5a421593f7d2536dcbb7ab8",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/equilibrium.cuh": "f0964c811b2c41a5aaa1c6d99c490b06e850c634eb8749f1f05ef61f93c2de1d",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/regularized.cuh": "943d4a571818bacb89c70bccfaac202691121e3e385803ce6309123a0a03ddaf",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/zou_he_local.cuh": "e73e66b853b1e4e0e30d8f4185d832aa414ce670a1813ce2b5459f2887f71f89",
-    "src/CelerisLab/lbm/kernels/boundary/inlet_outlet.cuh": "de8b213a6da42c2e5e9f8966199fc66ea4541b85144a90f3f5dbad3c6ab63b97",
-    "src/CelerisLab/lbm/kernels/boundary/outlet/pressure_neq.cuh": "c8b2adc66d12fe602076ddc9693c5c208711fcaddb58aa9a31401a269f51c4c4",
-    "src/CelerisLab/lbm/kernels/boundary/planar_velocity.cuh": "501b2759d0e2e4280cb6fdd127d66a50fa89f6de48fc2cae9a7eafb11ae90bed",
-    "src/CelerisLab/lbm/kernels/config.h": "7d1124125e0b354558297934460e64c760fb68cdd7bf6d01a1238bb2eaab8c37",
-    "src/CelerisLab/lbm/kernels/config/config_grid.h": "1db3e030ebdc116cd7f02362d1fd077daac55e8f0b4329f6285948c224d3ca5d",
-    "src/CelerisLab/lbm/kernels/config/config_method.h": "4374e04a130f90f97d17cc20c40d2f9ea0ed0dd8603817d07f215d02266e247c",
-    "src/CelerisLab/lbm/kernels/config/config_objects.h": "db793af052c756561a190a3ff2cb93ee5fe28462ee4f97c6af80882b4dc8b072",
-    "src/CelerisLab/lbm/kernels/config/config_obs.h": "c11e2249359145b5c4cbaaf0487506fa77c1f4b82c7c169ddc574aa0babcd727",
-    "src/CelerisLab/lbm/kernels/config/config_physics.h": "8ac0990b168e1058588676cc05c80df8634cfd671dbc92a89246c3c372d83a4e",
-    "src/CelerisLab/lbm/kernels/core/descriptors.cuh": "8440bc14857da9007982650f828a23608eec9f7cc4bf772e8c8dc1239cb45356",
-    "src/CelerisLab/lbm/kernels/core/flags.cuh": "0025705f24710330d9d9195f713879bfb650a85a3449baef0e196b831af104ab",
-    "src/CelerisLab/lbm/kernels/core/layout.cuh": "1fbd820021c89ac3efcde24145996cb0147769e607e498e61f308ed3e0b13706",
-    "src/CelerisLab/lbm/kernels/core/obs.cuh": "b742b77c9f61e1f020fe9922c3838ae9d855e17b381154958b58f10a22938922",
-    "src/CelerisLab/lbm/kernels/core/params.cuh": "6e18bf730d936d940e3d85452f0714a2eaae31bf41002f9fd520ec5b372878dd",
-    "src/CelerisLab/lbm/kernels/core/precision.cuh": "849df14b4cce50af52399e4b8f3e997196f3ae5f1163f68e28df3e6b2507a8c4",
-    "src/CelerisLab/lbm/kernels/kernel_v2.cu": "c7bd3fb705b77261ba2441c52a24a7e6a7865c165cba088a1b75201c4d29c408",
-    "src/CelerisLab/lbm/kernels/operators/collision_mrt.cuh": "aee444eb60c47a3fd518dca975d1af05425a0818a0ec6c3fb3f6150f60c2cb44",
-    "src/CelerisLab/lbm/kernels/operators/collision_srt.cuh": "6b7ff842f392c8f853d2d1a97cc69bfe50f21283f73e659404da07cf6c95f5e1",
-    "src/CelerisLab/lbm/kernels/operators/collision_trt.cuh": "9725b9840b9ad8b4ec7be61ff5d06d3151e86d1a87585c13f2fbf934d0d2c5f6",
-    "src/CelerisLab/lbm/kernels/operators/forcing_guo.cuh": "969a430c1af03f32e3bd0df95d805e64f56334717c44dd4ba208ba503062a24b",
-    "src/CelerisLab/lbm/kernels/operators/helpers.cuh": "0b3a4d95d7d19f5fec09e5423b8f4cc99f8a226b541967425967330da5a051ec",
-    "src/CelerisLab/lbm/kernels/operators/macro.cuh": "2be20eb2b7d7f5522daaad7f4b57b1ff8cdf883efe4a67846a96783b2fe846a3",
-    "src/CelerisLab/lbm/kernels/operators/turbulence_smag.cuh": "ff7f000297ee0817e255ad9fcb6a13b647e3ddd5b206518d35f38d2895a9f501",
-    "src/CelerisLab/lbm/kernels/refinement.cu": "b45aad9c022cecb64f7e968ec3cae2d8385a3cc430ee409700c404a3f4dd8cf8",
-    "src/CelerisLab/lbm/kernels/step/aux_kernels.cu": "578a5b20a157241ee678547059abb1372dd5a589ad06bb2c15b987eb01ca1013",
-    "src/CelerisLab/lbm/kernels/step/block_channel.cu": "ee8a31398b8e5233d977c816e6b8e060c1eb2ec71320e594226dbca55593c0d0",
-    "src/CelerisLab/lbm/kernels/step/curved_double.cu": "bfa7a1df1e939020314d49755045f7a85fe4a19cc1c68dbe62653c66c5e7c2b3",
-    "src/CelerisLab/lbm/kernels/step/esopull_macro.cu": "c73116020ca217ede1e4de27c8269c31f9d91e33433ac8252a21e9b14187c50f",
-    "src/CelerisLab/lbm/kernels/step/esopull_sync.cu": "c0ff3e72900c3ab89a05dd03684e96d3b740cf1672d565727fc2af165933d087",
-    "src/CelerisLab/lbm/kernels/step/init_flow.cu": "305be3bb12fc0d039acec1701baabcf0e8a35e683c49c34f2af8ca9867d2b29c",
-    "src/CelerisLab/lbm/kernels/step/one_step_double.cu": "f9f8242b38e8e0cf8425b75e2b0215bc15363c62eaa0fb43c761b8e0931bfdc9",
-    "src/CelerisLab/lbm/kernels/step/one_step_esopull.cu": "aa223b2744ae6c9125673df311a96ce588032c1ba58bebb11fd33ecb990f8ed4",
-    "src/CelerisLab/lbm/kernels/streaming/esopull_semantic_helpers.cuh": "dd5a9091628b079efd97e53fd49e52d09dcee88529235db77a5648e02937af6e",
-    "src/CelerisLab/lbm/kernels/streaming/esopull_single_buffer.cuh": "77ed4ab9a0ebc5ff62a91a7c39066ef395391ae36e9040a69fb2bd8b1626dc79",
-    "src/CelerisLab/lbm/kernels/streaming/pull_double_buffer.cuh": "b65d741ed78b7b62f99531ba0c0ce1936663d8dc9640e7d7d16c707f1baf6549",
-    "src/CelerisLab/lbm/population_storage.py": "a6a86c29c52c892edfe4802fb773c387212e3f4cc86708d80e154986ddf88044",
-    "src/CelerisLab/lbm/raw_exchange.py": "9031a196006a0f74dee4028e6f3bb673bc19ef7959f9f04dde9e01f93293aeb3",
-    "src/CelerisLab/lbm/refinement.py": "100d5e46ac894f6008b61364cdad5d37c2ca7ed949d8d71405572d6366526417",
-    "src/CelerisLab/lbm/refinement_stepper.py": "b6b835cf97f5aa045045bb4a47cfde34b89929d3872be410cb155727dfca2d33",
-    "src/CelerisLab/lbm/refinement_tables.py": "6eea593aaf791a2c644f1c74df0a41f6f5e62a2fce9feae76e19cf84b615607a",
-    "src/CelerisLab/lbm/stepper.py": "0dcb7cd7ae87e33e3dc67a38b6aa43042fbe673e37d9ad165342ee1d695933ce",
-    "src/CelerisLab/lbm/synchronized_remap.py": "7400fc4beaffd4649d6a9c524d38ce5fd6fa7eeb32eb5332e4030a4b6648f197",
-    "src/CelerisLab/simulation.py": "0a03904dc6de88667d7af699005a289adf8b09f0976cb0d099b041f4830a8f4c"
-  },
-  "candidate_header_sha256": "a3db46c2e7d27530b2d1436e65cdbed0b72cc7e047bfbeef2a640877271b51aa"
-}

tests/validation/data/refined_dfg/source_manifest_mrt.json

@@ -1,112 +0,0 @@
-{
-  "commit": "3ea131e92c057843034f11a1c574301a2430dfce",
-  "production_origin_commit": "3ea131e92c057843034f11a1c574301a2430dfce",
-  "collision": "MRT",
-  "sha256": {
-    "src/CelerisLab/__init__.py": "21cc469bd6e970a1f9ff5970c8eea4602065e41fc881854759ee565ee55c10c6",
-    "src/CelerisLab/body/__init__.py": "e4e0e8f0769a94428d5b02fac790443997556cfc5515a5f1ed1595d2c694d69d",
-    "src/CelerisLab/body/action_smoother.py": "b1a23ee6bbd4850b172cb8738c5c3546ee465a54189e6af9d8044f023d4687dc",
-    "src/CelerisLab/body/coupling/__init__.py": "c931f7eb318d48408c3e2febcc6917c88c8dcc1697cbf4329b1f340d94c35763",
-    "src/CelerisLab/body/coupling/soa_packer.py": "8ec26fd55ef74801bbd5ab6bd3d0a7dabc750cbd498aaac2ca4c61a0108ad3c9",
-    "src/CelerisLab/body/ddf_patch.py": "60fcfb7441e73bf290bcff41ca3a83da3e7ddad765d7247464e8f02e3043b4e2",
-    "src/CelerisLab/body/geometry/__init__.py": "ada88980ab672959aca9aa3a4c4aade3219524b2ab68110cd2a2f41e3e0ca90a",
-    "src/CelerisLab/body/geometry/base.py": "cceca14361ca2f34d34a3e43730e1a79b8ca81be00f0dd62e884db32b479419f",
-    "src/CelerisLab/body/geometry/circle.py": "7605ca7c21103f1d801ac73ab8dd18dffbdac425b2dee7b8858b283628a9e436",
-    "src/CelerisLab/body/jets.py": "4104c24af4651f4bb4f8d8fd36fb6d88f41c6e4469822f36e22e74c9ede31dac",
-    "src/CelerisLab/body/manager.py": "01b653d25bd9b4333379c8bfd12383596b686d2029f2e91b1c91b618540ec6b3",
-    "src/CelerisLab/body/objects.py": "8e63cee8faa9cc6243bcff428be628dfad73a02a9a3b8ece7d78c0a63406a08d",
-    "src/CelerisLab/body/preprocess/__init__.py": "dfd9d58bc07f626ab23a70053e31b88a6d9165d2e4c76a4e9f48abe674d3d2ec",
-    "src/CelerisLab/body/preprocess/flag_overlay.py": "831fc9e9736b758847759a085ff133eb49ec91318ace4fda76f85960138ee300",
-    "src/CelerisLab/body/registry.py": "fbb7327780adbdc6da15ebdb799980daf32df22ee974af0893d7409f177bbb68",
-    "src/CelerisLab/body/sync_plan.py": "3a15bfe9ebeb91482dbfc68850761ef39c872cc12d2efc795babd0c01e392323",
-    "src/CelerisLab/common/__init__.py": "d4dbde78bc97fccc9eabac9abae8f0f15c112c10ff8e9b45bd9401d4723df1ef",
-    "src/CelerisLab/common/_types.py": "aad2ff1a9033d4fd68783ad7123afb47201ddc58785cb6dc0246947037072a5f",
-    "src/CelerisLab/common/checkpoint.py": "b2f960aecd5ac27a3a7130b809ffad4709c44d522edef0359ab952654625410b",
-    "src/CelerisLab/common/pathline.py": "a1b6efcc0a076d0f1dc8d49a595779426d7d5626b00072a59bac710ff02ad046",
-    "src/CelerisLab/common/preprocess.py": "7fc78a08857cf8e98519500b094a1d896af189b6b15658ff9b388ed51bed4515",
-    "src/CelerisLab/common/render.py": "0e055476257eb2bcd11e733766e52195de02f8fad228f570a3511a7c831bdc29",
-    "src/CelerisLab/common/streakline/__init__.py": "13ff1cfa416fdd721a08a659e76b5a5a99b8d3201add10a83b7b0bc654bc1eec",
-    "src/CelerisLab/common/streakline/_config.py": "a9185ef68e9c7b5d5a1dc0b04a28341e2ad91d13c145a7c106636a878cf0a605",
-    "src/CelerisLab/common/streakline/_integrate.py": "3fbd4368b2c8d0e7fda40dc65aac5df02b085008b4c68acd83cb7ae45d33a13b",
-    "src/CelerisLab/common/streakline/_render.py": "236cd637414ee318c4d66f9aed32110d8dc42a100d65fde06172f7cd0ba62c65",
-    "src/CelerisLab/common/streakline/_streakline.py": "1a3e08daa706b5f83cdeb337e9a945a36ddf7583c40af1d0bb9d825ac954df37",
-    "src/CelerisLab/config.py": "2f1bba7515f5bc08cb3a8d140bcafe7fa0689e01b3b06494697bb2956a71530e",
-    "src/CelerisLab/configs/CONFIG.md": "41cafdbe525366c08aa9d0416ea026ccf0026ba7123b8a9b65f968a80d928e3a",
-    "src/CelerisLab/configs/config_body.json": "055f261f0828ca1d4f2bb694bd15b72bbcabe31d552326208f28e37f761adab1",
-    "src/CelerisLab/configs/config_lbm.json": "17e4311f1f250c6ece59177a8b6ff856b69a016c7c10267e774b030a0a390865",
-    "src/CelerisLab/configs/config_lbm_flume_mrt_zouhe.json": "8f593321db05a563a42931603a228d61cbcba06dfbe113262d5cd0ad93c0fe79",
-    "src/CelerisLab/configs/config_lbm_flume_trt_regularized.json": "f4bba8e6a4339fc3c4eb14f6e2f57c4b22993c73703c773d853edfbe34736e56",
-    "src/CelerisLab/configs/config_lbm_three_cylinder_triangle.json": "eeb8e7149dbe4aa6b3a9562802735aa950750dfbe2d972a0727e788573afa817",
-    "src/CelerisLab/cuda/__init__.py": "0d01dff9f0399c8baba822aab5ca0122a135f011008ed8a499ebd9f7e5b06aea",
-    "src/CelerisLab/cuda/compiler_v2.py": "c4cc3ec4445c8d75e6a253dd87963877117a722bc73b9d4811806fc6045d08c1",
-    "src/CelerisLab/cuda/context.py": "013dd4ec6d01d2fbd11afdfb103eac6a273bd9f798d663d761b851eeb27885e9",
-    "src/CelerisLab/cuda/obs_layout.py": "5ffb2c3aeeaaaaeb64f2cd8febfbcf4ad9919e5414020ad753cfade0683b21c2",
-    "src/CelerisLab/lbm/__init__.py": "7f60fb3aaae81501b510d08c2fedff44fcb05657260eb10b6f5cc91e7204306b",
-    "src/CelerisLab/lbm/block_stepper.py": "00b313daddc6e63d8ab8423c9190ca7e92ad291de20a2f6b80eb53e3f2d85ec7",
-    "src/CelerisLab/lbm/blocks.py": "1e644c5719993f418185ad4a10b6950a30636fc912befd9eab41ff48b4cf85cd",
-    "src/CelerisLab/lbm/channel.py": "40d0354e5dc97bcdb7e7b5c1e7f9303a109b7134d8a3af88b8ff4cd75ab5a095",
-    "src/CelerisLab/lbm/curved_links.py": "b6957fa13d13f864dba4f7364e93a39905d062dbb3ee9b3f5191add81fff0732",
-    "src/CelerisLab/lbm/descriptors.py": "c9f025dfc14da43b989047b84cc22bd05d5cc92c9ec695c1da68fdfb788e3f2b",
-    "src/CelerisLab/lbm/equilibrium.py": "2fb2f2bb7ff326d23abce80fc2a4c0907b17740ea3e29fe6ae079c5044783826",
-    "src/CelerisLab/lbm/field.py": "0e727eacc3706add4d8d15c418e9b631050871f831698d3ac689dd5f2c701b9b",
-    "src/CelerisLab/lbm/hierarchy.py": "f234975074f6b6d289d573ff6ea6832feae0e27cb04f80b37fe81792b13a12e7",
-    "src/CelerisLab/lbm/initializers.py": "dacf9586963e862d6d0a98ef1a066036be6f91e9d423720661d8ef2c1fb2df6a",
-    "src/CelerisLab/lbm/kernels/blocks.cu": "2fa894b20a29f006911ac3e3aad0793cc4aaf9ccd7a67d01c6320a0836b1d8ef",
-    "src/CelerisLab/lbm/kernels/boundary/bounce_back.cuh": "aba3748c564ed91b161d268ef8b737b7c7be96a823063d201f3da684dd845233",
-    "src/CelerisLab/lbm/kernels/boundary/curved_boundary.cuh": "aeb16bfd483514fb03e15a2fed437d673c3b8b2fe68ab83edf4244ef593878ea",
-    "src/CelerisLab/lbm/kernels/boundary/esopull_curved_helpers.cuh": "b9b474bc4edaff05681c5443235472d04072d0d775fc0eb9c5967faef52b0258",
-    "src/CelerisLab/lbm/kernels/boundary/ibm_kernels.cuh": "e6909b547dc8d64cdd8a76a90660243a8f5fee535caa161b52b4dd8b7c29934b",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/channel_stabilized.cuh": "efe077afcbb6b731256a987c2fd79a1dbc470c902f87070d60421ea6cb13d4e2",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/common.cuh": "59b38a89439878e00de7de16b9c7b03feff443fcc5a421593f7d2536dcbb7ab8",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/equilibrium.cuh": "f0964c811b2c41a5aaa1c6d99c490b06e850c634eb8749f1f05ef61f93c2de1d",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/regularized.cuh": "943d4a571818bacb89c70bccfaac202691121e3e385803ce6309123a0a03ddaf",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/zou_he_local.cuh": "e73e66b853b1e4e0e30d8f4185d832aa414ce670a1813ce2b5459f2887f71f89",
-    "src/CelerisLab/lbm/kernels/boundary/inlet_outlet.cuh": "de8b213a6da42c2e5e9f8966199fc66ea4541b85144a90f3f5dbad3c6ab63b97",
-    "src/CelerisLab/lbm/kernels/boundary/outlet/pressure_neq.cuh": "c8b2adc66d12fe602076ddc9693c5c208711fcaddb58aa9a31401a269f51c4c4",
-    "src/CelerisLab/lbm/kernels/boundary/planar_velocity.cuh": "501b2759d0e2e4280cb6fdd127d66a50fa89f6de48fc2cae9a7eafb11ae90bed",
-    "src/CelerisLab/lbm/kernels/config/config_grid.h": "1db3e030ebdc116cd7f02362d1fd077daac55e8f0b4329f6285948c224d3ca5d",
-    "src/CelerisLab/lbm/kernels/config/config_method.h": "4374e04a130f90f97d17cc20c40d2f9ea0ed0dd8603817d07f215d02266e247c",
-    "src/CelerisLab/lbm/kernels/config/config_objects.h": "db793af052c756561a190a3ff2cb93ee5fe28462ee4f97c6af80882b4dc8b072",
-    "src/CelerisLab/lbm/kernels/config/config_obs.h": "c11e2249359145b5c4cbaaf0487506fa77c1f4b82c7c169ddc574aa0babcd727",
-    "src/CelerisLab/lbm/kernels/config/config_physics.h": "8ac0990b168e1058588676cc05c80df8634cfd671dbc92a89246c3c372d83a4e",
-    "src/CelerisLab/lbm/kernels/config.h": "7d1124125e0b354558297934460e64c760fb68cdd7bf6d01a1238bb2eaab8c37",
-    "src/CelerisLab/lbm/kernels/core/descriptors.cuh": "8440bc14857da9007982650f828a23608eec9f7cc4bf772e8c8dc1239cb45356",
-    "src/CelerisLab/lbm/kernels/core/flags.cuh": "0025705f24710330d9d9195f713879bfb650a85a3449baef0e196b831af104ab",
-    "src/CelerisLab/lbm/kernels/core/layout.cuh": "1fbd820021c89ac3efcde24145996cb0147769e607e498e61f308ed3e0b13706",
-    "src/CelerisLab/lbm/kernels/core/obs.cuh": "b742b77c9f61e1f020fe9922c3838ae9d855e17b381154958b58f10a22938922",
-    "src/CelerisLab/lbm/kernels/core/params.cuh": "6e18bf730d936d940e3d85452f0714a2eaae31bf41002f9fd520ec5b372878dd",
-    "src/CelerisLab/lbm/kernels/core/precision.cuh": "849df14b4cce50af52399e4b8f3e997196f3ae5f1163f68e28df3e6b2507a8c4",
-    "src/CelerisLab/lbm/kernels/kernel_v2.cu": "c7bd3fb705b77261ba2441c52a24a7e6a7865c165cba088a1b75201c4d29c408",
-    "src/CelerisLab/lbm/kernels/operators/collision_mrt.cuh": "aee444eb60c47a3fd518dca975d1af05425a0818a0ec6c3fb3f6150f60c2cb44",
-    "src/CelerisLab/lbm/kernels/operators/collision_srt.cuh": "6b7ff842f392c8f853d2d1a97cc69bfe50f21283f73e659404da07cf6c95f5e1",
-    "src/CelerisLab/lbm/kernels/operators/collision_trt.cuh": "9725b9840b9ad8b4ec7be61ff5d06d3151e86d1a87585c13f2fbf934d0d2c5f6",
-    "src/CelerisLab/lbm/kernels/operators/forcing_guo.cuh": "969a430c1af03f32e3bd0df95d805e64f56334717c44dd4ba208ba503062a24b",
-    "src/CelerisLab/lbm/kernels/operators/helpers.cuh": "0b3a4d95d7d19f5fec09e5423b8f4cc99f8a226b541967425967330da5a051ec",
-    "src/CelerisLab/lbm/kernels/operators/macro.cuh": "2be20eb2b7d7f5522daaad7f4b57b1ff8cdf883efe4a67846a96783b2fe846a3",
-    "src/CelerisLab/lbm/kernels/operators/turbulence_smag.cuh": "ff7f000297ee0817e255ad9fcb6a13b647e3ddd5b206518d35f38d2895a9f501",
-    "src/CelerisLab/lbm/kernels/refinement.cu": "b45aad9c022cecb64f7e968ec3cae2d8385a3cc430ee409700c404a3f4dd8cf8",
-    "src/CelerisLab/lbm/kernels/step/aux_kernels.cu": "578a5b20a157241ee678547059abb1372dd5a589ad06bb2c15b987eb01ca1013",
-    "src/CelerisLab/lbm/kernels/step/block_channel.cu": "ee8a31398b8e5233d977c816e6b8e060c1eb2ec71320e594226dbca55593c0d0",
-    "src/CelerisLab/lbm/kernels/step/curved_double.cu": "bfa7a1df1e939020314d49755045f7a85fe4a19cc1c68dbe62653c66c5e7c2b3",
-    "src/CelerisLab/lbm/kernels/step/esopull_macro.cu": "c73116020ca217ede1e4de27c8269c31f9d91e33433ac8252a21e9b14187c50f",
-    "src/CelerisLab/lbm/kernels/step/esopull_sync.cu": "c0ff3e72900c3ab89a05dd03684e96d3b740cf1672d565727fc2af165933d087",
-    "src/CelerisLab/lbm/kernels/step/init_flow.cu": "305be3bb12fc0d039acec1701baabcf0e8a35e683c49c34f2af8ca9867d2b29c",
-    "src/CelerisLab/lbm/kernels/step/one_step_double.cu": "f9f8242b38e8e0cf8425b75e2b0215bc15363c62eaa0fb43c761b8e0931bfdc9",
-    "src/CelerisLab/lbm/kernels/step/one_step_esopull.cu": "aa223b2744ae6c9125673df311a96ce588032c1ba58bebb11fd33ecb990f8ed4",
-    "src/CelerisLab/lbm/kernels/streaming/esopull_semantic_helpers.cuh": "dd5a9091628b079efd97e53fd49e52d09dcee88529235db77a5648e02937af6e",
-    "src/CelerisLab/lbm/kernels/streaming/esopull_single_buffer.cuh": "77ed4ab9a0ebc5ff62a91a7c39066ef395391ae36e9040a69fb2bd8b1626dc79",
-    "src/CelerisLab/lbm/kernels/streaming/pull_double_buffer.cuh": "b65d741ed78b7b62f99531ba0c0ce1936663d8dc9640e7d7d16c707f1baf6549",
-    "src/CelerisLab/lbm/population_storage.py": "a6a86c29c52c892edfe4802fb773c387212e3f4cc86708d80e154986ddf88044",
-    "src/CelerisLab/lbm/raw_exchange.py": "8694202466eba848563e298656353b0f5db94e21a01fa05f51aad6dc2b9fd311",
-    "src/CelerisLab/lbm/refinement.py": "100d5e46ac894f6008b61364cdad5d37c2ca7ed949d8d71405572d6366526417",
-    "src/CelerisLab/lbm/refinement_stepper.py": "f2bb34fa90805ad21c3e7cf9f9a67d88d3ae3e249b4517d3898567b4bf9e364d",
-    "src/CelerisLab/lbm/refinement_tables.py": "fdd344024b89df3a83174dc810ca5e32db5e19eb8b1609f8f73b0821f56546b6",
-    "src/CelerisLab/lbm/stepper.py": "0dcb7cd7ae87e33e3dc67a38b6aa43042fbe673e37d9ad165342ee1d695933ce",
-    "src/CelerisLab/lbm/synchronized_remap.py": "7400fc4beaffd4649d6a9c524d38ce5fd6fa7eeb32eb5332e4030a4b6648f197",
-    "src/CelerisLab/simulation.py": "0a03904dc6de88667d7af699005a289adf8b09f0976cb0d099b041f4830a8f4c",
-    "tests/validation/re100_helpers.py": "289c6e01075ff361573f862b90cfd61e5980c9a8efcbc78aef69979b4004fd60",
-    "tests/validation/periodic.py": "a2212c0e2705126327a5019e9cafe64eeca398da1b75061ff23630c9843697a6",
-    "tests/validation/data/dfg_re100/reference_cycle.json": "073d1bda1629697efebad95667bfe80598e217d708dbffd7d5f6c6999379c55f",
-    "tests/validation/source_provenance.py": "6dfe8f2d819dba0e240ba761d31162a5033685d492d09db75eb2b8aaab3a5a4c"
-  }
-}

tests/validation/data/refined_dfg/source_manifest_window.json

@@ -1,116 +0,0 @@
-{
-  "commit": "a233c9032487a6006e950d1e327079b00466c410",
-  "production_origin_commit": "d9303234795fccf8591ba6274dfc544a84d956ff",
-  "observation_mode": "window",
-  "supported_collisions": [
-    "SRT",
-    "MRT"
-  ],
-  "sha256": {
-    "src/CelerisLab/__init__.py": "21cc469bd6e970a1f9ff5970c8eea4602065e41fc881854759ee565ee55c10c6",
-    "src/CelerisLab/body/__init__.py": "e4e0e8f0769a94428d5b02fac790443997556cfc5515a5f1ed1595d2c694d69d",
-    "src/CelerisLab/body/action_smoother.py": "b1a23ee6bbd4850b172cb8738c5c3546ee465a54189e6af9d8044f023d4687dc",
-    "src/CelerisLab/body/coupling/__init__.py": "c931f7eb318d48408c3e2febcc6917c88c8dcc1697cbf4329b1f340d94c35763",
-    "src/CelerisLab/body/coupling/soa_packer.py": "8ec26fd55ef74801bbd5ab6bd3d0a7dabc750cbd498aaac2ca4c61a0108ad3c9",
-    "src/CelerisLab/body/ddf_patch.py": "60fcfb7441e73bf290bcff41ca3a83da3e7ddad765d7247464e8f02e3043b4e2",
-    "src/CelerisLab/body/geometry/__init__.py": "ada88980ab672959aca9aa3a4c4aade3219524b2ab68110cd2a2f41e3e0ca90a",
-    "src/CelerisLab/body/geometry/base.py": "cceca14361ca2f34d34a3e43730e1a79b8ca81be00f0dd62e884db32b479419f",
-    "src/CelerisLab/body/geometry/circle.py": "7605ca7c21103f1d801ac73ab8dd18dffbdac425b2dee7b8858b283628a9e436",
-    "src/CelerisLab/body/jets.py": "4104c24af4651f4bb4f8d8fd36fb6d88f41c6e4469822f36e22e74c9ede31dac",
-    "src/CelerisLab/body/manager.py": "01b653d25bd9b4333379c8bfd12383596b686d2029f2e91b1c91b618540ec6b3",
-    "src/CelerisLab/body/objects.py": "8e63cee8faa9cc6243bcff428be628dfad73a02a9a3b8ece7d78c0a63406a08d",
-    "src/CelerisLab/body/preprocess/__init__.py": "dfd9d58bc07f626ab23a70053e31b88a6d9165d2e4c76a4e9f48abe674d3d2ec",
-    "src/CelerisLab/body/preprocess/flag_overlay.py": "831fc9e9736b758847759a085ff133eb49ec91318ace4fda76f85960138ee300",
-    "src/CelerisLab/body/registry.py": "fbb7327780adbdc6da15ebdb799980daf32df22ee974af0893d7409f177bbb68",
-    "src/CelerisLab/body/sync_plan.py": "3a15bfe9ebeb91482dbfc68850761ef39c872cc12d2efc795babd0c01e392323",
-    "src/CelerisLab/common/__init__.py": "d4dbde78bc97fccc9eabac9abae8f0f15c112c10ff8e9b45bd9401d4723df1ef",
-    "src/CelerisLab/common/_types.py": "aad2ff1a9033d4fd68783ad7123afb47201ddc58785cb6dc0246947037072a5f",
-    "src/CelerisLab/common/checkpoint.py": "b2f960aecd5ac27a3a7130b809ffad4709c44d522edef0359ab952654625410b",
-    "src/CelerisLab/common/pathline.py": "a1b6efcc0a076d0f1dc8d49a595779426d7d5626b00072a59bac710ff02ad046",
-    "src/CelerisLab/common/preprocess.py": "7fc78a08857cf8e98519500b094a1d896af189b6b15658ff9b388ed51bed4515",
-    "src/CelerisLab/common/render.py": "0e055476257eb2bcd11e733766e52195de02f8fad228f570a3511a7c831bdc29",
-    "src/CelerisLab/common/streakline/__init__.py": "13ff1cfa416fdd721a08a659e76b5a5a99b8d3201add10a83b7b0bc654bc1eec",
-    "src/CelerisLab/common/streakline/_config.py": "a9185ef68e9c7b5d5a1dc0b04a28341e2ad91d13c145a7c106636a878cf0a605",
-    "src/CelerisLab/common/streakline/_integrate.py": "3fbd4368b2c8d0e7fda40dc65aac5df02b085008b4c68acd83cb7ae45d33a13b",
-    "src/CelerisLab/common/streakline/_render.py": "236cd637414ee318c4d66f9aed32110d8dc42a100d65fde06172f7cd0ba62c65",
-    "src/CelerisLab/common/streakline/_streakline.py": "1a3e08daa706b5f83cdeb337e9a945a36ddf7583c40af1d0bb9d825ac954df37",
-    "src/CelerisLab/config.py": "2f1bba7515f5bc08cb3a8d140bcafe7fa0689e01b3b06494697bb2956a71530e",
-    "src/CelerisLab/configs/CONFIG.md": "41cafdbe525366c08aa9d0416ea026ccf0026ba7123b8a9b65f968a80d928e3a",
-    "src/CelerisLab/configs/config_body.json": "055f261f0828ca1d4f2bb694bd15b72bbcabe31d552326208f28e37f761adab1",
-    "src/CelerisLab/configs/config_lbm.json": "17e4311f1f250c6ece59177a8b6ff856b69a016c7c10267e774b030a0a390865",
-    "src/CelerisLab/configs/config_lbm_flume_mrt_zouhe.json": "8f593321db05a563a42931603a228d61cbcba06dfbe113262d5cd0ad93c0fe79",
-    "src/CelerisLab/configs/config_lbm_flume_trt_regularized.json": "f4bba8e6a4339fc3c4eb14f6e2f57c4b22993c73703c773d853edfbe34736e56",
-    "src/CelerisLab/configs/config_lbm_three_cylinder_triangle.json": "eeb8e7149dbe4aa6b3a9562802735aa950750dfbe2d972a0727e788573afa817",
-    "src/CelerisLab/cuda/__init__.py": "0d01dff9f0399c8baba822aab5ca0122a135f011008ed8a499ebd9f7e5b06aea",
-    "src/CelerisLab/cuda/compiler_v2.py": "c4cc3ec4445c8d75e6a253dd87963877117a722bc73b9d4811806fc6045d08c1",
-    "src/CelerisLab/cuda/context.py": "013dd4ec6d01d2fbd11afdfb103eac6a273bd9f798d663d761b851eeb27885e9",
-    "src/CelerisLab/cuda/obs_layout.py": "5ffb2c3aeeaaaaeb64f2cd8febfbcf4ad9919e5414020ad753cfade0683b21c2",
-    "src/CelerisLab/lbm/__init__.py": "7f60fb3aaae81501b510d08c2fedff44fcb05657260eb10b6f5cc91e7204306b",
-    "src/CelerisLab/lbm/block_stepper.py": "00b313daddc6e63d8ab8423c9190ca7e92ad291de20a2f6b80eb53e3f2d85ec7",
-    "src/CelerisLab/lbm/blocks.py": "1e644c5719993f418185ad4a10b6950a30636fc912befd9eab41ff48b4cf85cd",
-    "src/CelerisLab/lbm/channel.py": "40d0354e5dc97bcdb7e7b5c1e7f9303a109b7134d8a3af88b8ff4cd75ab5a095",
-    "src/CelerisLab/lbm/curved_links.py": "b6957fa13d13f864dba4f7364e93a39905d062dbb3ee9b3f5191add81fff0732",
-    "src/CelerisLab/lbm/descriptors.py": "c9f025dfc14da43b989047b84cc22bd05d5cc92c9ec695c1da68fdfb788e3f2b",
-    "src/CelerisLab/lbm/equilibrium.py": "2fb2f2bb7ff326d23abce80fc2a4c0907b17740ea3e29fe6ae079c5044783826",
-    "src/CelerisLab/lbm/field.py": "0e727eacc3706add4d8d15c418e9b631050871f831698d3ac689dd5f2c701b9b",
-    "src/CelerisLab/lbm/hierarchy.py": "f234975074f6b6d289d573ff6ea6832feae0e27cb04f80b37fe81792b13a12e7",
-    "src/CelerisLab/lbm/initializers.py": "dacf9586963e862d6d0a98ef1a066036be6f91e9d423720661d8ef2c1fb2df6a",
-    "src/CelerisLab/lbm/kernels/blocks.cu": "2fa894b20a29f006911ac3e3aad0793cc4aaf9ccd7a67d01c6320a0836b1d8ef",
-    "src/CelerisLab/lbm/kernels/boundary/bounce_back.cuh": "aba3748c564ed91b161d268ef8b737b7c7be96a823063d201f3da684dd845233",
-    "src/CelerisLab/lbm/kernels/boundary/curved_boundary.cuh": "aeb16bfd483514fb03e15a2fed437d673c3b8b2fe68ab83edf4244ef593878ea",
-    "src/CelerisLab/lbm/kernels/boundary/esopull_curved_helpers.cuh": "b9b474bc4edaff05681c5443235472d04072d0d775fc0eb9c5967faef52b0258",
-    "src/CelerisLab/lbm/kernels/boundary/ibm_kernels.cuh": "e6909b547dc8d64cdd8a76a90660243a8f5fee535caa161b52b4dd8b7c29934b",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/channel_stabilized.cuh": "efe077afcbb6b731256a987c2fd79a1dbc470c902f87070d60421ea6cb13d4e2",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/common.cuh": "59b38a89439878e00de7de16b9c7b03feff443fcc5a421593f7d2536dcbb7ab8",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/equilibrium.cuh": "f0964c811b2c41a5aaa1c6d99c490b06e850c634eb8749f1f05ef61f93c2de1d",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/regularized.cuh": "943d4a571818bacb89c70bccfaac202691121e3e385803ce6309123a0a03ddaf",
-    "src/CelerisLab/lbm/kernels/boundary/inlet/zou_he_local.cuh": "e73e66b853b1e4e0e30d8f4185d832aa414ce670a1813ce2b5459f2887f71f89",
-    "src/CelerisLab/lbm/kernels/boundary/inlet_outlet.cuh": "de8b213a6da42c2e5e9f8966199fc66ea4541b85144a90f3f5dbad3c6ab63b97",
-    "src/CelerisLab/lbm/kernels/boundary/outlet/pressure_neq.cuh": "c8b2adc66d12fe602076ddc9693c5c208711fcaddb58aa9a31401a269f51c4c4",
-    "src/CelerisLab/lbm/kernels/boundary/planar_velocity.cuh": "501b2759d0e2e4280cb6fdd127d66a50fa89f6de48fc2cae9a7eafb11ae90bed",
-    "src/CelerisLab/lbm/kernels/config.h": "7d1124125e0b354558297934460e64c760fb68cdd7bf6d01a1238bb2eaab8c37",
-    "src/CelerisLab/lbm/kernels/config/config_grid.h": "1db3e030ebdc116cd7f02362d1fd077daac55e8f0b4329f6285948c224d3ca5d",
-    "src/CelerisLab/lbm/kernels/config/config_method.h": "4374e04a130f90f97d17cc20c40d2f9ea0ed0dd8603817d07f215d02266e247c",
-    "src/CelerisLab/lbm/kernels/config/config_objects.h": "db793af052c756561a190a3ff2cb93ee5fe28462ee4f97c6af80882b4dc8b072",
-    "src/CelerisLab/lbm/kernels/config/config_obs.h": "c11e2249359145b5c4cbaaf0487506fa77c1f4b82c7c169ddc574aa0babcd727",
-    "src/CelerisLab/lbm/kernels/config/config_physics.h": "8ac0990b168e1058588676cc05c80df8634cfd671dbc92a89246c3c372d83a4e",
-    "src/CelerisLab/lbm/kernels/core/descriptors.cuh": "8440bc14857da9007982650f828a23608eec9f7cc4bf772e8c8dc1239cb45356",
-    "src/CelerisLab/lbm/kernels/core/flags.cuh": "0025705f24710330d9d9195f713879bfb650a85a3449baef0e196b831af104ab",
-    "src/CelerisLab/lbm/kernels/core/layout.cuh": "1fbd820021c89ac3efcde24145996cb0147769e607e498e61f308ed3e0b13706",
-    "src/CelerisLab/lbm/kernels/core/obs.cuh": "b742b77c9f61e1f020fe9922c3838ae9d855e17b381154958b58f10a22938922",
-    "src/CelerisLab/lbm/kernels/core/params.cuh": "6e18bf730d936d940e3d85452f0714a2eaae31bf41002f9fd520ec5b372878dd",
-    "src/CelerisLab/lbm/kernels/core/precision.cuh": "849df14b4cce50af52399e4b8f3e997196f3ae5f1163f68e28df3e6b2507a8c4",
-    "src/CelerisLab/lbm/kernels/kernel_v2.cu": "c7bd3fb705b77261ba2441c52a24a7e6a7865c165cba088a1b75201c4d29c408",
-    "src/CelerisLab/lbm/kernels/operators/collision_mrt.cuh": "aee444eb60c47a3fd518dca975d1af05425a0818a0ec6c3fb3f6150f60c2cb44",
-    "src/CelerisLab/lbm/kernels/operators/collision_srt.cuh": "6b7ff842f392c8f853d2d1a97cc69bfe50f21283f73e659404da07cf6c95f5e1",
-    "src/CelerisLab/lbm/kernels/operators/collision_trt.cuh": "9725b9840b9ad8b4ec7be61ff5d06d3151e86d1a87585c13f2fbf934d0d2c5f6",
-    "src/CelerisLab/lbm/kernels/operators/forcing_guo.cuh": "969a430c1af03f32e3bd0df95d805e64f56334717c44dd4ba208ba503062a24b",
-    "src/CelerisLab/lbm/kernels/operators/helpers.cuh": "0b3a4d95d7d19f5fec09e5423b8f4cc99f8a226b541967425967330da5a051ec",
-    "src/CelerisLab/lbm/kernels/operators/macro.cuh": "2be20eb2b7d7f5522daaad7f4b57b1ff8cdf883efe4a67846a96783b2fe846a3",
-    "src/CelerisLab/lbm/kernels/operators/turbulence_smag.cuh": "ff7f000297ee0817e255ad9fcb6a13b647e3ddd5b206518d35f38d2895a9f501",
-    "src/CelerisLab/lbm/kernels/refinement.cu": "b45aad9c022cecb64f7e968ec3cae2d8385a3cc430ee409700c404a3f4dd8cf8",
-    "src/CelerisLab/lbm/kernels/step/aux_kernels.cu": "578a5b20a157241ee678547059abb1372dd5a589ad06bb2c15b987eb01ca1013",
-    "src/CelerisLab/lbm/kernels/step/block_channel.cu": "ee8a31398b8e5233d977c816e6b8e060c1eb2ec71320e594226dbca55593c0d0",
-    "src/CelerisLab/lbm/kernels/step/curved_double.cu": "bfa7a1df1e939020314d49755045f7a85fe4a19cc1c68dbe62653c66c5e7c2b3",
-    "src/CelerisLab/lbm/kernels/step/esopull_macro.cu": "c73116020ca217ede1e4de27c8269c31f9d91e33433ac8252a21e9b14187c50f",
-    "src/CelerisLab/lbm/kernels/step/esopull_sync.cu": "c0ff3e72900c3ab89a05dd03684e96d3b740cf1672d565727fc2af165933d087",
-    "src/CelerisLab/lbm/kernels/step/init_flow.cu": "305be3bb12fc0d039acec1701baabcf0e8a35e683c49c34f2af8ca9867d2b29c",
-    "src/CelerisLab/lbm/kernels/step/one_step_double.cu": "f9f8242b38e8e0cf8425b75e2b0215bc15363c62eaa0fb43c761b8e0931bfdc9",
-    "src/CelerisLab/lbm/kernels/step/one_step_esopull.cu": "aa223b2744ae6c9125673df311a96ce588032c1ba58bebb11fd33ecb990f8ed4",
-    "src/CelerisLab/lbm/kernels/streaming/esopull_semantic_helpers.cuh": "dd5a9091628b079efd97e53fd49e52d09dcee88529235db77a5648e02937af6e",
-    "src/CelerisLab/lbm/kernels/streaming/esopull_single_buffer.cuh": "77ed4ab9a0ebc5ff62a91a7c39066ef395391ae36e9040a69fb2bd8b1626dc79",
-    "src/CelerisLab/lbm/kernels/streaming/pull_double_buffer.cuh": "b65d741ed78b7b62f99531ba0c0ce1936663d8dc9640e7d7d16c707f1baf6549",
-    "src/CelerisLab/lbm/population_storage.py": "a6a86c29c52c892edfe4802fb773c387212e3f4cc86708d80e154986ddf88044",
-    "src/CelerisLab/lbm/raw_exchange.py": "9031a196006a0f74dee4028e6f3bb673bc19ef7959f9f04dde9e01f93293aeb3",
-    "src/CelerisLab/lbm/refinement.py": "100d5e46ac894f6008b61364cdad5d37c2ca7ed949d8d71405572d6366526417",
-    "src/CelerisLab/lbm/refinement_stepper.py": "b6b835cf97f5aa045045bb4a47cfde34b89929d3872be410cb155727dfca2d33",
-    "src/CelerisLab/lbm/refinement_tables.py": "6eea593aaf791a2c644f1c74df0a41f6f5e62a2fce9feae76e19cf84b615607a",
-    "src/CelerisLab/lbm/stepper.py": "0dcb7cd7ae87e33e3dc67a38b6aa43042fbe673e37d9ad165342ee1d695933ce",
-    "src/CelerisLab/lbm/synchronized_remap.py": "7400fc4beaffd4649d6a9c524d38ce5fd6fa7eeb32eb5332e4030a4b6648f197",
-    "src/CelerisLab/simulation.py": "0a03904dc6de88667d7af699005a289adf8b09f0976cb0d099b041f4830a8f4c",
-    "tests/validation/data/dfg_re100/reference_cycle.json": "073d1bda1629697efebad95667bfe80598e217d708dbffd7d5f6c6999379c55f",
-    "tests/validation/periodic.py": "a2212c0e2705126327a5019e9cafe64eeca398da1b75061ff23630c9843697a6",
-    "tests/validation/re100_helpers.py": "289c6e01075ff361573f862b90cfd61e5980c9a8efcbc78aef69979b4004fd60",
-    "tests/validation/source_provenance.py": "6dfe8f2d819dba0e240ba761d31162a5033685d492d09db75eb2b8aaab3a5a4c"
-  }
-}

tests/validation/multigrid/check_projected_pairs.py

@@ -1,425 +0,0 @@
-"""Bounded exact-source CUDA plumbing gate; never a flow-accuracy certificate.
-
-Run this driver externally against exact dev with --mode baseline first, then
-against the experimental source with --mode candidate --baseline <receipt>.
-Only scalar receipts/hashes and actual compiler sidecars are retained. Whole-step
-mass/momentum are diagnostics: no verified FP32 conservation bound is claimed.
-"""
-import argparse
-from contextlib import contextmanager
-from dataclasses import replace
-import hashlib
-import json
-import os
-import shutil
-from pathlib import Path
-import subprocess
-import sys
-
-import numpy as np
-
-BASE = 'ed9d8c937d446b854d6963bd92d718bb4fb98b96'
-PRODUCTION = 'a135252ae78b47b57d7e77d19001700b3bedac8b'
-STOPS = (0, 1, 2, 8)
-OPERATOR_ATOL, OPERATOR_RTOL = 6e-8, 2e-7
-REST_ATOL, REST_RTOL = 3e-7, 1e-6
-REPLAY_ATOL = 3e-6
-E = np.array([(0,0),(1,0),(-1,0),(0,1),(0,-1),(1,1),(-1,-1),(1,-1),(-1,1)])
-W = np.array([4/9]+[1/9]*4+[1/36]*4)
-
-
-def digest(array):
-    """All finite bits (including signed zero) and exact NaN mask; no NaN payloads."""
-    array = np.asarray(array)
-    if np.isinf(array).any():
-        raise AssertionError('infinite population')
-    finite = np.isfinite(array)
-    h = hashlib.sha256()
-    h.update(str((array.shape, array.dtype.str)).encode())
-    h.update(np.ascontiguousarray(finite).tobytes())
-    h.update(np.ascontiguousarray(array[finite]).tobytes())
-    return h.hexdigest()
-
-
-def independent_explosion(coarse, pair, layout, kind):
-    """Coordinate oracle; never reads the production neighbor/offset tables."""
-    ny, nx = pair.coarse_shape
-    legal = np.zeros((ny,nx), bool)
-    legal.ravel()[pair.ghost_coarse] = True
-    legal &= layout.owned & ~pair.covered & (kind == 0)
-    if not legal.ravel()[pair.ghost_coarse].all():
-        raise AssertionError('illegal center donor')
-    out = np.empty((9,len(pair.ghost_fine)))
-    flat = np.asarray(coarse, np.float64).reshape(9,-1)
-    for row, (target, donor) in enumerate(zip(pair.ghost_fine,pair.ghost_coarse)):
-        y,x = divmod(int(donor),nx)
-        gradient = np.zeros((9,2))
-        for axis, (dx,dy) in enumerate(((1,0),(0,1))):
-            ends = [(x-dx,y-dy),(x+dx,y+dy)]
-            if not layout.periodic[axis] and any(not (0<=xx<nx and 0<=yy<ny) for xx,yy in ends):
-                continue
-            ends = [(xx%nx,yy%ny) for xx,yy in ends]
-            if all(legal[yy,xx] for xx,yy in ends):
-                (xm,ym),(xp,yp) = ends
-                gradient[:,axis] = (flat[:,yp*nx+xp]-flat[:,ym*nx+xm])/2
-        for q in range(1,9):
-            gradient[q] -= E[q]*np.dot(E[q],gradient[q])/np.dot(E[q],E[q])
-        fy,fx = divmod(int(target),pair.fine_shape[1])
-        offset = np.array([pair.fine_origin[0]+(fx+.5)/2-(x+.5),
-                           pair.fine_origin[1]+(fy+.5)/2-(y+.5)])
-        out[:,row] = flat[:,int(donor)] + gradient@offset
-    return out
-
-
-def default_options(selector):
-    # Exact dev has no explosion keyword. Baseline and omitted paths pass none.
-    return {} if selector == 'omitted' else {'explosion':selector}
-
-
-def snapshot(run, raw):
-    from CelerisLab.lbm.refinement import ACTIVE, OUTER_GHOST
-    stored, public = raw(run), run.download()
-    hashes, totals = [], np.zeros(3)
-    for level,(values,visible,kind) in enumerate(zip(stored,public,run.hierarchy.kinds)):
-        active = kind == ACTIVE
-        if not np.isfinite(visible[:,active]).all() or not np.isnan(visible[:,~active]).all():
-            raise AssertionError('public ACTIVE/invalid mask mismatch')
-        if not np.isnan(values[:,kind==OUTER_GHOST]).all():
-            raise AssertionError('OUTER owner core is not poisoned')
-        population = visible[:,active].sum(axis=1,dtype=np.float64)*(.25**level)
-        totals += np.r_[population.sum(), E.T@population]
-        hashes.append(dict(raw=digest(values), public=digest(visible), active=int(active.sum())))
-    if not np.isfinite(totals).all():
-        raise AssertionError('nonfinite mass/momentum diagnostic')
-    return dict(step=run.step_count, levels=hashes, mass_momentum=totals.tolist())
-
-
-def initialize(run, rest=False):
-    arrays, origin, spacing = [], np.zeros(2), 1.
-    for index,level in enumerate(run._levels):
-        if index:
-            origin += spacing*np.asarray(run.hierarchy.pairs[index-1].fine_origin)
-            spacing /= 2
-        y,x = np.indices(level.shape[1:],dtype=np.float64)
-        x,y = origin[0]+spacing*(x+.5),origin[1]+spacing*(y+.5)
-        q = np.arange(9)[:,None,None]
-        values = np.broadcast_to(W[:,None,None],level.shape).copy()
-        if not rest:
-            # q-distinct smooth non-equilibrium G; same physical frame on all levels.
-            values += 1e-4*np.sin(.17*x+.23*y+q)
-        arrays.append(values)
-    run.initialize(*arrays)
-
-
-def operator_case(run, index):
-    import pycuda.driver as cuda
-    parent,child = run._levels[index:index+2]
-    geometry,pair = run.hierarchy.pairs[index],run._pairs[index]
-    c = np.random.default_rng(19+index).normal(0,.001,(9,*geometry.coarse_shape))
-    if not run._ddf_shifting:
-        c += W[:,None,None]
-    c = c.astype(np.float32)
-    legal = np.zeros(geometry.coarse_shape,bool)
-    legal.ravel()[geometry.ghost_coarse] = True
-    c[:,~legal] = np.nan
-    packed = parent.layout.to_blocked(c)
-    output = np.full(child.layout.blocked_shape,np.nan,np.float32)
-    cuda.memcpy_htod(parent.current,packed)
-    cuda.memcpy_htod(child.current,output)
-    calls, hop = [],run._hop
-    try:
-        run._hop = lambda *a,**kw: calls.append(a)
-        run._advance(index+1,parent.current,block=run._block,stream=run._stream)
-        run._stream.synchronize()
-    finally:
-        run._hop = hop
-    if calls != [(index+1,child.current,child.spare),(index+1,child.spare,child.current)]:
-        raise AssertionError('explosion changed two-hop launch contract')
-    cuda.memcpy_dtoh(output,child.current)
-    target = child.layout.owner.ravel()[geometry.ghost_fine]
-    slots = np.array([child.layout.slot(target,q) for q in range(9)])
-    actual = output.ravel()[slots]
-    expected = independent_explosion(c,geometry,parent.layout,run.hierarchy.kinds[index])
-    constant = c.reshape(9,-1)[:,geometry.ghost_coarse]
-    if not np.isfinite(actual).all() or np.max(abs(expected-constant)) <= 1e-5:
-        raise AssertionError('operator must exercise finite nonzero projected slopes')
-    np.testing.assert_allclose(actual,expected,atol=OPERATOR_ATOL,rtol=OPERATOR_RTOL)
-    untouched = np.ones(output.size,bool); untouched[slots.ravel()] = False
-    if not np.isnan(output.ravel()[untouched]).all():
-        raise AssertionError('explosion wrote outside its targets')
-    return dict(pair=index,rows=len(target),parent_stride=pair.parent_cells,
-                child_stride=int(np.prod(child.layout.local_shape)),
-                max_error_by_q=np.max(abs(actual-expected),axis=1).tolist(),
-                nonzero_projection=True,poisoned_nondonors=True,untouched_preserved=True)
-
-
-def replay_two_hops(values, pair, layout, kind):
-    """Existing FP64 two-hop algebra, using the independent coordinate oracle."""
-    from tests.unit.test_projected_explosion import collide
-    coarse,fine = (a.copy() for a in values)
-    fine.reshape(9,-1)[:,pair.ghost_fine] = independent_explosion(coarse,pair,layout,kind)
-    for _ in range(2):
-        fine = np.array([np.roll(fine[q],(ey,ex),(0,1)) for q,(ex,ey) in enumerate(E)])
-        fine[:,pair.fine_kind==2] = np.nan
-        active = pair.fine_kind==0
-        fine[:,active] = collide(fine[:,active],pair.tau_fine)
-    out = np.array([np.roll(coarse[q],(ey,ex),(0,1)) for q,(ex,ey) in enumerate(E)])
-    out.reshape(-1)[pair.coalesce_coarse] = fine.reshape(-1)[pair.coalesce_fine].mean(axis=1)
-    out[:,~pair.covered] = collide(out[:,~pair.covered],pair.tau_coarse)
-    out[:,pair.covered] = np.nan
-    return out,fine
-
-
-def run_case(ctx, case, shifted, selector, raw, projected=False, replay=False):
-    from CelerisLab.lbm.refinement_stepper import FixedPatchStepper
-    cfg,refs,blocks = case
-    cfg = replace(cfg,velocity=0,ddf_shifting=shifted)
-    with FixedPatchStepper(cfg,context=ctx,refinements=refs,level_blocks=blocks,
-                           **default_options(selector)) as run:
-        operator = [operator_case(run,i) for i in range(len(run._pairs))] if projected else []
-        counts = [0]*len(run._levels)
-        for index,level in enumerate(run._levels):
-            def counted(*a, index=index, kernel=level.kernel, **kw):
-                counts[index] += 1
-                return kernel(*a,**kw)
-            level.kernel = counted
-        def check_counts(stop):
-            if counts != [stop*2**index for index in range(len(counts))]:
-                raise AssertionError('actual level hop counts differ from acoustic schedule')
-        rest = []
-        if projected:
-            initialize(run,rest=True)
-            for stop in STOPS:
-                run.step(stop-run.step_count)
-                check_counts(stop)
-                snapshot(run,raw)  # actual public and raw invalid masks at every stop
-                maximum = 0.
-                for values,kind in zip(run.download(),run.hierarchy.kinds):
-                    active = values[:,kind==0]
-                    np.testing.assert_allclose(active,np.broadcast_to(W[:,None],active.shape),
-                                               atol=REST_ATOL,rtol=REST_RTOL)
-                    maximum = max(maximum,float(np.max(abs(active-W[:,None]))))
-                rest.append(dict(step=stop,max_absolute_error=maximum))
-        counts[:] = [0]*len(counts)
-        initialize(run)
-        reference = tuple(a.astype(np.float64) for a in run.download()) if replay else None
-        snapshots,replay_errors,previous = [],[],0
-        for stop in STOPS:
-            run.step(stop-run.step_count)
-            if replay:
-                for _ in range(stop-previous):
-                    reference = replay_two_hops(reference,run.hierarchy.pairs[0],
-                                               run._levels[0].layout,run.hierarchy.kinds[0])
-                errors = []
-                for actual,expected,kind in zip(run.download(),reference,run.hierarchy.kinds):
-                    np.testing.assert_allclose(actual[:,kind==0],expected[:,kind==0],
-                                               atol=REPLAY_ATOL,rtol=0)
-                    errors.append(np.max(abs(actual[:,kind==0]-expected[:,kind==0]),axis=1).tolist())
-                replay_errors.append(dict(step=stop,max_error_by_level_q=errors))
-            check_counts(stop)
-            snapshots.append(dict(snapshot(run,raw),observed_level_hops=counts.copy())); previous = stop
-        change = (np.array(snapshots[-1]['mass_momentum'])-
-                  np.array(snapshots[0]['mass_momentum'])).tolist()
-        return dict(operator=operator,snapshots=snapshots,rest_fixed_point=rest,
-                    replay_max_errors=replay_errors,mass_momentum_change_diagnostic=change,
-                    conservation_status='diagnostic_only_no_FP32_bound')
-
-
-def compare_snapshots(actual,expected):
-    if len(actual) != len(expected):
-        raise AssertionError('snapshot count differs')
-    for got,want in zip(actual,expected):
-        if (got['step'] != want['step'] or got['levels'] != want['levels']
-                or got.get('observed_level_hops') != want.get('observed_level_hops')):
-            raise AssertionError('owner bits, public values or masks differ')
-
-
-def cases():
-    from CelerisLab.config import LBMConfig
-    from tests.unit.test_hierarchy import CFG, FOUR
-    scalar = (LBMConfig(nx=16,ny=16,viscosity=.02),
-              [(4,4,12,12),(8,8,16,16),(8,8,16,16)],
-              [(4,4),(4,8),(6,4),(4,6)])
-    four = (CFG,FOUR,[(6,8),(8,6),(12,8),(16,12)])
-    concave = (LBMConfig(nx=30,ny=30,viscosity=.1),
-               [[(4,4,5,7),(4,5,7,7)]],[(6,5),(4,6)])
-    return dict(scalar=scalar,four=four,concave=concave)
-
-
-def baseline_receipt(receipt, driver_hash, keys):
-    if (receipt.get('completed') is not True or receipt.get('dry_run') is not False
-            or receipt.get('mode') != 'baseline' or receipt.get('production_revision') != BASE
-            or receipt.get('source',{}).get('revision') != BASE
-            or receipt.get('source',{}).get('dirty') is not False
-            or receipt.get('driver_sha256') != driver_hash
-            or receipt.get('stops') != list(STOPS)
-            or receipt.get('operator_tolerance') != [OPERATOR_ATOL,OPERATOR_RTOL]
-            or receipt.get('rest_tolerance') != [REST_ATOL,REST_RTOL]
-            or receipt.get('replay_tolerance') != [REPLAY_ATOL,0]
-            or set(receipt.get('default_snapshots',{})) != set(keys)
-            or not receipt.get('actual_build_sidecars')):
-        raise ValueError('baseline receipt does not match the frozen exact-dev gate')
-    return receipt
-
-
-def remap_case(ctx, shifted, raw):
-    from CelerisLab.lbm.refinement_stepper import FixedPatchStepper
-    cfg,refs,blocks = cases()['four']
-    with FixedPatchStepper(replace(cfg,velocity=0,ddf_shifting=shifted),context=ctx,
-            refinements=refs[:2],level_blocks=blocks[:3],explosion='projected_linear') as run:
-        initialize(run); run.step(1)
-        before = snapshot(run,raw)
-        with run.remap_child([(22,22,42,42),(72,68,76,76)]) as clone:
-            if clone._explosion != 'projected_linear' or any(p.neighbors is None for p in clone._pairs):
-                raise AssertionError('remap lost projected selection')
-            if clone.step_count != 1: raise AssertionError('remap lost synchronized count')
-            initial = snapshot(clone,raw)
-            clone.step(1)
-            after = snapshot(clone,raw)
-            if clone.step_count != 2: raise AssertionError('remap did not continue count')
-        compare_snapshots([snapshot(run,raw)],[before])
-        return dict(shifted=shifted,source_unchanged=True,initial=initial,continued=after)
-
-
-@contextmanager
-def capture_builds(report, save, baseline=None):
-    from CelerisLab.cuda import compiler_v2 as compiler
-    original = compiler.load_module
-    def load(path):
-        path = Path(path)
-        metadata = json.loads(Path(str(path)+'.json').read_text())
-        if metadata['ptx_sha256'] != hashlib.sha256(path.read_bytes()).hexdigest():
-            raise AssertionError('actual PTX and build sidecar disagree')
-        if baseline and (metadata['arch'],metadata['flags']) not in [
-                (m['arch'],m['flags']) for m in baseline['actual_build_sidecars']]:
-            raise AssertionError('baseline build architecture or flags differ')
-        report['actual_build_sidecars'].append(metadata)
-        save()  # capture AMR metadata before production cleanup removes scratch
-        return original(str(path))
-    compiler.load_module = load
-    try:
-        yield
-    finally:
-        compiler.load_module = original
-
-
-def preflight(repo, revision, mode):
-    git = lambda *a: subprocess.check_output(['git','-C',str(repo),*a],text=True).strip()
-    if git('rev-parse','HEAD') != revision or git('status','--porcelain'):
-        raise ValueError('requires the exact expected clean checkout')
-    source = BASE if mode == 'baseline' else PRODUCTION
-    if mode == 'baseline' and revision != BASE:
-        raise ValueError('baseline must be exact ed9d8c9')
-    if subprocess.call(['git','-C',str(repo),'diff','--quiet',source,'--','src']):
-        raise ValueError('production source differs from the frozen source revision')
-    return source
-
-
-def main():
-    parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument('--repo',type=Path,required=True)
-    parser.add_argument('--expected-revision',required=True)
-    parser.add_argument('--mode',choices=('baseline','candidate'),required=True)
-    parser.add_argument('--baseline',type=Path)
-    parser.add_argument('--output',type=Path,required=True)
-    parser.add_argument('--run-gpu',action='store_true')
-    parser.add_argument('--dry-run',action='store_true')
-    args = parser.parse_args()
-    if args.output.exists(): parser.error('output already exists')
-    selected = os.environ.get('CUDA_VISIBLE_DEVICES','')
-    if not args.dry_run and (not args.run_gpu or not selected or ',' in selected or selected=='-1'):
-        parser.error('--run-gpu and exactly one explicit CUDA_VISIBLE_DEVICES are required')
-    repo = args.repo.resolve()
-    source = preflight(repo,args.expected_revision,args.mode)
-    baseline = None
-    if args.mode == 'candidate':
-        if args.baseline is None: parser.error('candidate requires --baseline receipt')
-        baseline = json.loads(args.baseline.read_text())
-    sys.path[:0] = [str(repo/'src'),str(repo),str(repo/'tests/validation/multigrid'),
-                   str(repo/'tests/validation/taylor_green')]
-    import CelerisLab
-    if Path(CelerisLab.__file__).resolve() != repo/'src/CelerisLab/__init__.py':
-        raise RuntimeError('wrong imported checkout')
-    from run_case import provenance
-    driver_hash = hashlib.sha256(Path(__file__).read_bytes()).hexdigest()
-    keys = [f'{name}:shifted={shifted}' for name in cases() for shifted in (False,True)]
-    if baseline is not None: baseline_receipt(baseline,driver_hash,keys)
-    report = dict(mode=args.mode,production_revision=source,source=provenance(repo),
-                  driver_sha256=driver_hash,
-                  device_selection=selected,completed=False,dry_run=args.dry_run,
-                  operator_tolerance=[OPERATOR_ATOL,OPERATOR_RTOL],
-                  rest_tolerance=[REST_ATOL,REST_RTOL],replay_tolerance=[REPLAY_ATOL,0],stops=STOPS,
-                  conservation_status='diagnostic_only_no_FP32_bound',
-                  actual_build_sidecars=[],default_snapshots={},default_equivalence=[],
-                  projected_operator=[],union_multilevel_smoke=[],changed_remap=[])
-    args.output.parent.mkdir(parents=True,exist_ok=True)
-    def save():
-        text = json.dumps(report,indent=2,allow_nan=False)+'\n'
-        if len(text.encode()) > 8*1024*1024: raise RuntimeError('receipt exceeds 8 MiB cap')
-        temporary = args.output.with_suffix(args.output.suffix+'.tmp')
-        temporary.write_text(text); os.replace(temporary,args.output)
-    save()
-    if args.dry_run:
-        print('Source preflight only; no CUDA imports or execution.'); return
-    try:
-        from CelerisLab.cuda.context import CudaContext
-        from test_refinement_blocked_base import raw
-        with CudaContext(0) as ctx, capture_builds(report,save,baseline):
-            import pycuda.driver as cuda
-            report['device'] = dict(name=ctx.device.name(),pci_bus_id=ctx.device.pci_bus_id(),
-                                    capability=list(ctx.device.compute_capability()),
-                                    driver=cuda.get_driver_version(),runtime=list(cuda.get_version()))
-            nvcc = shutil.which('nvcc') or '/usr/local/cuda/bin/nvcc'
-            report['nvcc_version'] = subprocess.check_output([nvcc,'--version'],text=True).strip()
-            if baseline and (report['device'] != baseline.get('device')
-                             or report['nvcc_version'] != baseline.get('nvcc_version')
-                             or selected != baseline.get('device_selection')):
-                raise ValueError('baseline GPU/device selection or toolchain differs')
-            for name,case in cases().items():
-                for shifted in (False,True):
-                    key = f'{name}:shifted={shifted}'
-                    report['active_case'] = f'default:{key}'
-                    result = run_case(ctx,case,shifted,'omitted',raw)
-                    report['default_snapshots'][key] = result['snapshots']
-                    if baseline:
-                        compare_snapshots(result['snapshots'],baseline['default_snapshots'][key])
-                        explicit = run_case(ctx,case,shifted,'constant',raw)
-                        compare_snapshots(explicit['snapshots'],result['snapshots'])
-                        report['default_equivalence'].append(dict(case=key,passed=True))
-                    save()
-            if baseline:
-                for name,case in cases().items():
-                    for shifted in (False,True):
-                        report['active_case'] = f'projected:{name}:shifted={shifted}'
-                        result = run_case(ctx,case,shifted,'projected_linear',raw,True,name=='concave')
-                        cfg,refs,blocks = case
-                        if name == 'four':
-                            variant_refs = [list(reversed(rects)) for rects in refs]
-                        elif name == 'concave':
-                            variant_refs = [[(4,5,7,7),(4,4,5,5)]]  # same union, disjoint decomposition
-                        else:
-                            variant_refs = refs
-                        variant = (cfg,variant_refs,[(2,2)]*len(blocks))
-                        alternate = run_case(ctx,variant,shifted,'projected_linear',raw,True)
-                        compare_snapshots(alternate['snapshots'],result['snapshots'])
-                        report['projected_operator'].append(dict(case=name,shifted=shifted,rows=result['operator']))
-                        report['union_multilevel_smoke'].append(dict(case=name,shifted=shifted,result=result,
-                                                                   alternate_bits_identical=True))
-                        save()
-                for shifted in (False,True):
-                    report['active_case'] = f'changed-remap:shifted={shifted}'
-                    report['changed_remap'].append(remap_case(ctx,shifted,raw)); save()
-                expected_builds = {(s['arch'],tuple(s['flags'])) for s in baseline['actual_build_sidecars']}
-                actual_builds = {(s['arch'],tuple(s['flags'])) for s in report['actual_build_sidecars']}
-                if actual_builds != expected_builds:
-                    raise AssertionError('baseline build architecture or compiler flags differ')
-            report['completed'] = True
-            save()
-    except Exception as error:
-        report['error'] = f'{type(error).__name__}: {error}'
-        save(); raise
-    print(json.dumps(dict(completed=True,mode=args.mode,receipt=str(args.output))))
-
-
-if __name__ == '__main__':
-    main()

tests/validation/multigrid/test_block_stepper.py

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

tests/validation/multigrid/test_channel_root_gpu.py

@@ -27,7 +27,7 @@ def state(ny, nx):
 
 def compile_module(cfg, context, source):
     cfg.validate()
-    build = compiler.generate_config(cfg, block_root_bc=2 if source == "blocks.cu" else 0)
+    build = compiler.generate_config(cfg)
     try:
         module = compiler.load_module(compiler.compile_kernel(context.sm_arch, source=source, build_dir=build))
     finally:
@@ -106,10 +106,9 @@ class ChannelRootGPU(unittest.TestCase):
                     cfg = LBMConfig(nx=48, ny=32, viscosity=.1, velocity=.015, ddf_shifting=shifted)
                     reference = None
                     for block in ((32,48), (8,8), (4,1)):
-                        with FixedPatchStepper(cfg, context=context, coarse_boundary="channel",
-                                refinements=[(8,6,40,26)], level_blocks=[block, (8,8)],
-                                level_objects=[(), (body,) if bodies else ()],
-                                level_jets=[(), (jet,) if bodies else ()]) as backend:
+                        with FixedPatchStepper(cfg, (8,6,40,26), context=context,
+                                coarse_boundary="channel", base_block=block, fine_block=(8,8),
+                                fine_objects=(body,) if bodies else (), jets=(jet,) if bodies else ()) as backend:
                             arrays = [state(*level.shape[1:]) for level in backend._levels]
                             backend.initialize(*arrays)
                             backend.step(4)

tests/validation/multigrid/test_exchange_window.py

@@ -1,261 +0,0 @@
-"""Optional observation-window exchange ledger: host contract (mocked driver) and GPU gate.
-
-Run CPU and GPU classes in separate processes; GPU callers select the device.
-ExchangeWindowGPU uses the SRT/unshifted Jet fixture; ExchangeWindowShiftedMRTGPU covers a
-shifted MRT, all-blocked, stationary-body case without Jets (no shifted-MRT Jet claim).
-GPU tolerance (conservative engineering tolerance, not a universal proof): the window ledger
-sums h*dt*raw per link over fine substeps, while the reference sums per-base interval ledgers
-over links and then over base steps. Both are FP64 reorderings of the same FP32-exact substep
-contributions, so the scale is the sum of the ACTUAL absolute substep contributions (read from
-last_raw after every fine hop), not of per-base totals that could hide substep cancellation:
-|window - reference| <= 4 * m * eps * sum|substep terms| + 1e-300, m = links * substeps.
-"""
-from contextlib import ExitStack
-import unittest
-from unittest.mock import patch
-
-import numpy as np
-import pycuda.driver as cuda
-
-from CelerisLab.lbm.refinement_stepper import FixedPatchStepper
-from test_refinement_blocked_base import mocked_backend
-from test_refinement_blocked_fine import BOUNDS, circle, config
-
-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(),)],
-                             observe_raw_exchange=raw, observe_window_exchange=window)
-
-
-def same_bits(test, a, b):
-    """Identical NaN masks, no infinities, identical finite FP32 bits (incl. signed zero)."""
-    a, b = np.asarray(a), np.asarray(b)
-    test.assertEqual(a.dtype, b.dtype)
-    test.assertFalse(np.isinf(a).any() or np.isinf(b).any())
-    np.testing.assert_array_equal(np.isnan(a), np.isnan(b))
-    finite = np.isfinite(a)
-    np.testing.assert_array_equal(a[finite].view(np.uint32), b[finite].view(np.uint32))
-
-
-def accumulations(m):
-    return [c for c in m["calls"] if c[0] == "BlockAccumulateExchange"]
-
-
-class ExchangeWindowCPU(unittest.TestCase):
-    def test_constructor_validation(self):
-        with mocked_backend() as m:
-            with self.assertRaisesRegex(ValueError, "requires observe_raw_exchange"):
-                build(m, window=True, raw=False)
-            with self.assertRaisesRegex(ValueError, "must be bool"):
-                build(m, window=1)
-
-    def test_state_machine_and_launches(self):
-        with mocked_backend() as m, ExitStack() as stack:
-            stack.enter_context(patch.object(cuda, "memset_d8"))
-            stack.enter_context(patch.object(cuda, "memset_d8_async"))
-            stack.enter_context(patch.object(cuda, "memcpy_dtoh",
-                                             side_effect=lambda out, src: out.fill(0)))
-            backend = build(m)
-            b = backend._level_boundaries[1]
-            self.assertIsNotNone(b.window_integral)
-            with self.assertRaises(RuntimeError):
-                backend.start_exchange_window()  # not initialized
-            arrays = [np.full(level.shape, 1 / 9, np.float32) for level in backend._levels]
-            backend.initialize(*arrays)
-            with self.assertRaisesRegex(RuntimeError, "no valid exchange window"):
-                backend.read_exchange_window(0)
-            backend.step(1)
-            self.assertEqual(len(accumulations(m)), 2)  # closed window: interval ledger only
-            backend.start_exchange_window()
-            with self.assertRaisesRegex(RuntimeError, "at least one completed"):
-                backend.read_exchange_window(0)
-            m["calls"].clear()
-            backend.step(2)
-            calls = accumulations(m)
-            self.assertEqual(len(calls), 8)  # two fine hops x two ledgers x two base steps
-            self.assertEqual({id(c[1][1]) for c in calls},
-                             {id(b.interval_integral), id(b.window_integral)})
-            out = backend.read_exchange_window(0)
-            self.assertEqual((out["time_start"], out["time_end"], out["sample_count"]), (1., 3, 4))
-            self.assertEqual(backend.read_exchange_window(0)["time_end"], 3)  # non-destructive
-            backend.initialize(*arrays)  # invalidates
-            with self.assertRaisesRegex(RuntimeError, "no valid exchange window"):
-                backend.read_exchange_window(0)
-            backend.start_exchange_window()
-            with patch.object(backend, "_hop", side_effect=RuntimeError("injected")):
-                with self.assertRaises(RuntimeError):
-                    backend.step(1)
-            self.assertFalse(backend._window_valid)
-            with self.assertRaises(RuntimeError):
-                backend.read_exchange_window(0)  # failed status
-
-    def test_disabled_default_has_no_window_cost(self):
-        with mocked_backend() as m, ExitStack() as stack:
-            stack.enter_context(patch.object(cuda, "memset_d8_async"))
-            backend = build(m, window=False)
-            self.assertIsNone(backend._level_boundaries[1].window_integral)
-            backend.initialize(*[np.full(l.shape, 1 / 9, np.float32) for l in backend._levels])
-            backend.step(1)
-            self.assertEqual(len(accumulations(m)), 2)
-            with self.assertRaisesRegex(RuntimeError, "disabled"):
-                backend.start_exchange_window()
-
-
-class ExchangeWindowGPU(unittest.TestCase):
-    def test_window_matches_summed_base_reads_and_populations_unchanged(self):
-        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(),)],
-                      observe_raw_exchange=True)
-            with FixedPatchStepper(CFG, observe_window_exchange=True, **kw) as windowed, \
-                 FixedPatchStepper(CFG, **kw) as plain:
-                arrays = [state(level.shape) for level in windowed._levels]
-                windowed.initialize(*arrays)
-                plain.initialize(*arrays)
-                windowed.step(2)
-                plain.step(2)
-                windowed.start_exchange_window()
-                b = windowed._level_boundaries[1]
-                count = len(b.tables["cell"])
-                factors = np.array([.25, .25, .125, .25])  # h*dt, h*h*dt, h*h for level-1 h=.5
-                scale = np.zeros(4)
-                substeps = 0
-                kernel = windowed._levels[1].kernel
-
-                def audited(src, dst, *args, **kw):
-                    nonlocal scale, substeps
-                    windowed._stream.synchronize()  # BFL and both accumulations are complete
-                    raw = np.empty((count, 4), np.float32)
-                    cuda.memcpy_dtoh(raw, b.last_raw)
-                    scale = scale + (np.abs(raw.astype(np.float64)) * factors).sum(axis=0)
-                    substeps += 1
-                    kernel(src, dst, *args, **kw)
-                windowed._levels[1].kernel = audited
-                keys = ("impulse", "angular_impulse", "mass_into_fluid")
-                summed = {part: [0., 0., 0., 0.] for part in ("total", "wall", "aperture")}
-                steps = 0
-                for speed in (0., .002, .002, -.001, 0., 0.):  # amplitude updates stay in-window
-                    windowed.set_jet_amplitude(0, speed)
-                    plain.set_jet_amplitude(0, speed)
-                    windowed.step(1)
-                    plain.step(1)
-                    steps += 1
-                    obs = windowed.read_raw_exchange(0)
-                    for part in summed:
-                        o = obs[part]
-                        summed[part] = [summed[part][0] + o["impulse"][0], summed[part][1] + o["impulse"][1],
-                                        summed[part][2] + o["angular_impulse"],
-                                        summed[part][3] + o["mass_into_fluid"]]
-                    for a, e in zip(windowed._download_raw().values, plain._download_raw().values):
-                        same_bits(self, a, e)
-                out = windowed.read_exchange_window(0)
-                self.assertEqual((out["time_end"] - out["time_start"], out["sample_count"]),
-                                 (steps, 2 * steps))
-                self.assertEqual(substeps, 2 * steps)
-                bound = 4 * (count * substeps) * EPS * scale + 1e-300
-                for part in summed:
-                    o = out[part]
-                    got = np.array([o["impulse"][0], o["impulse"][1], o["angular_impulse"],
-                                    o["mass_into_fluid"]])
-                    diff = np.abs(got - np.array(summed[part]))
-                    self.assertTrue((diff <= bound).all(), f"{part}: {diff} > {bound}")
-                    np.testing.assert_array_equal(o["force"], o["impulse"] / steps)
-                again = windowed.read_exchange_window(0)
-                np.testing.assert_array_equal(again["total"]["impulse"], out["total"]["impulse"])
-                windowed.initialize(*arrays)
-                with self.assertRaises(RuntimeError):
-                    windowed.read_exchange_window(0)
-
-
-def audit_substeps(stepper, b, count, record):
-    """Wrap the level-1 step kernel: after BFL and accumulation, add |substep terms| to record."""
-    factors = np.array([.25, .25, .125, .25])
-    kernel = stepper._levels[1].kernel
-
-    def audited(src, dst, *args, **kw):
-        stepper._stream.synchronize()
-        raw = np.empty((count, 4), np.float32)
-        cuda.memcpy_dtoh(raw, b.last_raw)
-        record["scale"] = record["scale"] + (np.abs(raw.astype(np.float64)) * factors).sum(axis=0)
-        record["substeps"] += 1
-        kernel(src, dst, *args, **kw)
-    stepper._levels[1].kernel = audited
-
-
-def components(obs):
-    o = obs["total"]
-    return np.array([o["impulse"][0], o["impulse"][1], o["angular_impulse"], o["mass_into_fluid"]])
-
-
-class ExchangeWindowShiftedMRTGPU(unittest.TestCase):
-    """Shifted MRT, all-blocked, stationary body, NO Jet (scoped separately from SRT/Jet)."""
-
-    def test_window_step0_reset_and_split_step(self):
-        from test_raw_exchange_gpu import BOUNDS as RB, circle as rc, state
-        from CelerisLab.config import LBMConfig
-        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:
-                arrays = [state(level.shape) for level in windowed._levels]
-                for run in (windowed, split, plain):
-                    run.initialize(*arrays)
-                    run.step(2)
-                    if run is not plain:
-                        run.start_exchange_window()
-                b = windowed._level_boundaries[1]
-                count = len(b.tables["cell"])
-                record = dict(scale=np.zeros(4), substeps=0)
-                audit_substeps(windowed, b, count, record)
-                steps, summed = 5, np.zeros(4)
-                for _ in range(steps):
-                    windowed.step(1)
-                    plain.step(1)
-                    summed += components(windowed.read_raw_exchange(0))
-                    for a, e in zip(windowed._download_raw().values, plain._download_raw().values):
-                        same_bits(self, a, e)
-                split.step(steps)  # one call: same ledger arithmetic as five step(1) calls
-                for a, e in zip(windowed._download_raw().values, split._download_raw().values):
-                    same_bits(self, a, e)
-                rows = [np.empty((count, 4), np.float64) for _ in range(2)]
-                cuda.memcpy_dtoh(rows[0], b.window_integral)
-                cuda.memcpy_dtoh(rows[1], split._level_boundaries[1].window_integral)
-                np.testing.assert_array_equal(rows[0].view(np.uint64), rows[1].view(np.uint64))
-
-                out = windowed.read_exchange_window(0)
-                self.assertEqual(record["substeps"], 2 * steps)
-                self.assertEqual((out["time_end"] - out["time_start"], out["sample_count"]),
-                                 (steps, 2 * steps))
-                bound = 4 * (count * record["substeps"]) * EPS * record["scale"] + 1e-300
-                diff = np.abs(components(out) - summed)
-                self.assertTrue((diff <= bound).all(), f"{diff} > {bound}")
-                np.testing.assert_array_equal(split.read_exchange_window(0)["total"]["impulse"],
-                                              out["total"]["impulse"])
-
-                windowed.step(0)  # no interval: window and its duration unchanged
-                again = windowed.read_exchange_window(0)
-                self.assertEqual(again["time_end"], out["time_end"])
-                np.testing.assert_array_equal(again["total"]["impulse"], out["total"]["impulse"])
-
-                windowed.start_exchange_window()  # reset after a window
-                with self.assertRaisesRegex(RuntimeError, "at least one completed"):
-                    windowed.read_exchange_window(0)
-                record.update(scale=np.zeros(4), substeps=0)
-                windowed.step(1)
-                single = components(windowed.read_raw_exchange(0))
-                reset = windowed.read_exchange_window(0)
-                self.assertEqual(reset["time_end"] - reset["time_start"], 1)
-                bound = 4 * (count * record["substeps"]) * EPS * record["scale"] + 1e-300
-                self.assertTrue((np.abs(components(reset) - single) <= bound).all())
-
-
-if __name__ == "__main__": unittest.main()

tests/validation/multigrid/test_fine_surface_gpu.py

@@ -140,8 +140,7 @@ def run_patch(speed, *, audit=True):
         build = (patch.object(compiler, "compile_kernel", audit_compiler(compiler.compile_kernel))
                  if audit else nullcontext())
         with build:
-            backend = implementation.FixedPatchStepper(cfg, context=context, refinements=[BOUNDS],
-                                             level_objects=[(), (source,)])
+            backend = implementation.FixedPatchStepper(cfg, BOUNDS, context=context, fine_objects=[source])
         with backend, context.activate():
             c, f = backend._levels
             cl = backend._fine_curved
@@ -282,8 +281,7 @@ def test_fine_surface_four_hops(speed):
 @pytest.mark.parametrize("missing", ["surface_velocity_gpu", "link_exchange_gpu"])
 def test_missing_surface_device_buffer_rejects_before_launch(missing):
     backend = implementation.FixedPatchStepper.__new__(implementation.FixedPatchStepper)
-    backend._boundary_hosts = [None, SimpleNamespace(objects=[object_spec(.002)])]
-    backend._level_jets = [(), ()]
+    backend.fine_boundary = SimpleNamespace(objects=[object_spec(.002)])
     backend._fine_curved = SimpleNamespace(fluid_idx_gpu=object(),
                                           surface_velocity_gpu=object(), link_exchange_gpu=object())
     setattr(backend._fine_curved, missing, None)
@@ -327,7 +325,6 @@ def test_cross_interface_donor_rejects_before_cuda():
     context.activate.side_effect = AssertionError("must reject before CUDA activation")
     with patch.object(cuda, "mem_alloc") as allocate:
         with pytest.raises(ValueError, match="donor crosses"):
-            implementation.FixedPatchStepper(cfg, context=context, refinements=[BOUNDS],
-                                             level_objects=[(), (source,)])
+            implementation.FixedPatchStepper(cfg, BOUNDS, context=context, fine_objects=[source])
         context.activate.assert_not_called()
         allocate.assert_not_called()

tests/validation/multigrid/test_multiple_pinned_remap_gpu.py

@@ -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
 

tests/validation/multigrid/test_pinned_body_remap_gpu.py

@@ -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,)
 
 

tests/validation/multigrid/test_raw_exchange_gpu.py

@@ -90,18 +90,14 @@ def census(run, index, buffer):
     return totals(dense, leaf), external, independent
 
 
-
-def fine(block):
-    """Two-level circle+jet construction on BOUNDS; block None keeps the dense fine level."""
-    return dict(refinements=[BOUNDS], level_blocks=[None, block],
-                level_objects=[(), (circle(),)], level_jets=[(), (jet(),)])
-
 class RawExchangeGPU(unittest.TestCase):
     def test_row_ledger_interval_jet_switch_and_no_population_effect(self):
         with CudaContext(0) as ctx:
             for block in ((32, 40), (16, 20), (8, 10)):
-                with FixedPatchStepper(CFG, context=ctx, **fine(block), observe_raw_exchange=True) as measured, \
-                     FixedPatchStepper(CFG, context=ctx, **fine(block)) as plain:
+                with FixedPatchStepper(CFG, BOUNDS, context=ctx, fine_block=block,
+                        fine_objects=[circle()], jets=[jet()], observe_raw_exchange=True) as measured, \
+                     FixedPatchStepper(CFG, BOUNDS, context=ctx, fine_block=block,
+                        fine_objects=[circle()], jets=[jet()]) as plain:
                     arrays = [state(l.shape) for l in measured._levels]
                     measured.initialize(*arrays)
                     plain.initialize(*arrays)
@@ -150,8 +146,9 @@ class RawExchangeGPU(unittest.TestCase):
         """Same fine resolution/initial data with dense storage: a numerical
         reference for cut-link rows, not a uniform-whole-domain convergence study."""
         with CudaContext(0) as ctx:
-            with FixedPatchStepper(CFG, context=ctx, **fine(None)) as dense, \
-                 FixedPatchStepper(CFG, context=ctx, **fine((16, 20)), observe_raw_exchange=True) as blocked:
+            with FixedPatchStepper(CFG, BOUNDS, context=ctx, fine_objects=[circle()], jets=[jet()]) as dense, \
+                 FixedPatchStepper(CFG, BOUNDS, context=ctx, fine_block=(16, 20),
+                    fine_objects=[circle()], jets=[jet()], observe_raw_exchange=True) as blocked:
                 arrays = [state(l.shape) for l in blocked._levels]
                 dense.initialize(*arrays)
                 blocked.initialize(*arrays)
@@ -232,7 +229,8 @@ class RawExchangeGPU(unittest.TestCase):
         layout = BlockLayout2D.build(48, 64, 8, 8)
         with CudaContext(0) as ctx:
             with PeriodicBlockStepper(fine_cfg, layout, context=ctx, objects=[obj]) as uniform, \
-                 FixedPatchStepper(CFG, context=ctx, **fine((16, 20)), observe_raw_exchange=True) as amr:
+                 FixedPatchStepper(CFG, BOUNDS, context=ctx, fine_block=(16, 20),
+                    fine_objects=[circle()], jets=[jet()], observe_raw_exchange=True) as amr:
                 amr.initialize(*(state(l.shape) for l in amr._levels))
                 uniform.initialize(state((9, 48, 64)))
                 b = amr._level_boundaries[1]

tests/validation/multigrid/test_refinement_blocked_base.py

@@ -83,10 +83,11 @@ def mocked_backend(mode="periodic", fail_alloc=None):
 class BlockedBaseCPU(unittest.TestCase):
     def test_reject_before_cuda(self):
         context = Mock(activate=Mock(side_effect=AssertionError("CUDA reached")))
-        for blocks in ([(12, 8), None], [(7, 8), FINE_BLOCK], [(12,), FINE_BLOCK]):
-            with self.subTest(blocks=blocks), self.assertRaises(ValueError):
-                FixedPatchStepper(config("periodic"), context=context, refinements=[BOUNDS],
-                                  level_blocks=blocks)
+        for kwargs in ({"base_block": (12, 8)},
+                       {"base_block": (7, 8), "fine_block": FINE_BLOCK},
+                       {"base_block": (12,), "fine_block": FINE_BLOCK}):
+            with self.subTest(kwargs=kwargs), self.assertRaises(ValueError):
+                FixedPatchStepper(config("periodic"), BOUNDS, context=context, **kwargs)
         context.activate.assert_not_called()
 
     def test_all_arrival_rows_donors_and_kind_masks(self):
@@ -192,10 +193,9 @@ class BlockedBaseCPU(unittest.TestCase):
 
     def test_launch_order_stream_wall_constants_and_buffer_swaps(self):
         with mocked_backend("slot_reservoir") as m:
-            backend = FixedPatchStepper(config("slot_reservoir"), context=m["context"],
-                                        coarse_boundary="slot_reservoir", refinements=[BOUNDS],
-                                        level_blocks=[(3, 4), FINE_BLOCK],
-                                        level_objects=[(), (circle(actuation(.002)),)])
+            backend = FixedPatchStepper(config("slot_reservoir"), BOUNDS, context=m["context"],
+                                        coarse_boundary="slot_reservoir", fine_block=FINE_BLOCK,
+                                        base_block=(3, 4), fine_objects=[circle(actuation(.002))])
             try:
                 backend.initialize(state(NY, NX, 1), state(*backend.patch.fine_shape, 2))
                 coarse, fine = backend._levels
@@ -223,8 +223,6 @@ class BlockedBaseCPU(unittest.TestCase):
                     self.assertIs(collide[4], coarse.kind)
                 walls = [a for ptr, a in m["uploads"] if isinstance(ptr, str) and ptr == "d_block_wall"]
                 self.assertEqual(len(walls), 1)
-                self.assertEqual([call.kwargs["block_root_bc"] for call in
-                                  compiler.generate_config.call_args_list], [1, 0])
                 width, height, slot, speed = struct.unpack("=IIIf", walls[0])
                 self.assertEqual((width, height, slot), (NX, NY, 8))
                 self.assertAlmostEqual(speed, .001)
@@ -238,16 +236,16 @@ class BlockedBaseCPU(unittest.TestCase):
         for fail_at in (1, 6, 10):
             with self.subTest(fail_at=fail_at), mocked_backend(fail_alloc=fail_at) as m:
                 with self.assertRaisesRegex(MemoryError, "injected allocation"):
-                    FixedPatchStepper(config("periodic"), context=m["context"], refinements=[BOUNDS],
-                                      level_blocks=[(3, 4), FINE_BLOCK])
+                    FixedPatchStepper(config("periodic"), BOUNDS, context=m["context"],
+                                      fine_block=FINE_BLOCK, base_block=(3, 4))
                 self.assertEqual(len(m["allocations"]), fail_at)
                 for allocation in m["allocations"]:
                     allocation.free.assert_called_once_with()
 
     def test_failed_parent_stage_cannot_publish_or_resume(self):
         with mocked_backend() as m:
-            backend = FixedPatchStepper(config("periodic"), context=m["context"], refinements=[BOUNDS],
-                                        level_blocks=[(3, 4), FINE_BLOCK])
+            backend = FixedPatchStepper(config("periodic"), BOUNDS, context=m["context"],
+                                        fine_block=FINE_BLOCK, base_block=(3, 4))
             backend.initialize(state(NY, NX, 1), state(*backend.patch.fine_shape, 2))
             m["functions"]["BlockCoalesce"].side_effect = RuntimeError("injected parent stage failure")
             current = backend._levels[0].current
@@ -291,10 +289,9 @@ class BlockedBaseGPU(unittest.TestCase):
                     for base_block in (None, *layouts):
                         label = f"{mode} width={width} speed={speed} base={base_block}"
                         snapshots = []
-                        with FixedPatchStepper(cfg, context=context, coarse_boundary=mode,
-                                               refinements=[BOUNDS], level_blocks=[base_block, FINE_BLOCK],
-                                               level_objects=[(), () if speed is None
-                                                              else (circle(actuation(speed)),)]) as backend:
+                        with FixedPatchStepper(cfg, BOUNDS, context=context, coarse_boundary=mode,
+                                               fine_block=FINE_BLOCK, base_block=base_block,
+                                               fine_objects=() if speed is None else [circle(actuation(speed))]) as backend:
                             backend.initialize(*arrays)
                             for step in (0, 1, 2, 8):
                                 if step == 1 and base_block is not None:

tests/validation/multigrid/test_refinement_blocked_fine.py

@@ -105,10 +105,9 @@ class BlockedFineCPU(unittest.TestCase):
         return Mock(activate=Mock(side_effect=AssertionError("CUDA reached")), sm_arch="sm_70")
 
     def test_rejections_before_cuda(self):
-        for kw in ({"level_blocks": [None, (7, 7)]}, {"level_blocks": [None, (16,)]}):
+        for kw in ({"fine_block": (7, 7)}, {"fine_block": (16,)}):
             with self.subTest(kw=kw), self.assertRaises(ValueError):
-                FixedPatchStepper(config("periodic"), context=self.forbidden_context(),
-                                  refinements=[BOUNDS], **kw)
+                FixedPatchStepper(config("periodic"), BOUNDS, context=self.forbidden_context(), **kw)
 
     def test_single_block_layout_allocates_no_empty_halo_tables(self):
         # A 1x1 non-periodic fine layout has zero halo pairs; CUDA rejects mem_alloc(0).
@@ -126,8 +125,8 @@ class BlockedFineCPU(unittest.TestCase):
                 patch.object(compiler, "compile_kernel"), patch.object(compiler, "cleanup_build_dir"), \
                 patch.object(compiler, "load_module", return_value=module), \
                 patch.object(cuda, "mem_alloc", side_effect=alloc), patch.object(cuda, "memcpy_htod"):
-            backend = FixedPatchStepper(config("periodic"), context=context, refinements=[BOUNDS],
-                                        level_blocks=[None, FINE_BLOCKS[0]])
+            backend = FixedPatchStepper(config("periodic"), BOUNDS, context=context,
+                                        fine_block=FINE_BLOCKS[0])
             self.assertEqual(len(backend.fine_layout.halo_dst), 0)
             self.assertIsNone(backend._levels[1].halo_dst)
             backend._gather_halo(backend._levels[1], Mock())  # no launch without pairs
@@ -178,9 +177,8 @@ class BlockedFineCPU(unittest.TestCase):
                 patch.object(cuda, "mem_alloc", side_effect=lambda size: Mock()), \
                 patch.object(cuda, "memcpy_htod"), \
                 patch.object(curved_links, "CurvedLinkSoA", side_effect=AssertionError("dense SoA built")):
-            backend = FixedPatchStepper(config("periodic"), context=context, refinements=[BOUNDS],
-                                        level_blocks=[None, FINE_BLOCKS[1]],
-                                        level_objects=[(), tuple(objects)])
+            backend = FixedPatchStepper(config("periodic"), BOUNDS, context=context,
+                                        fine_objects=objects, fine_block=FINE_BLOCKS[1])
             backend.initialize(state(NY, NX, 1), state(*backend.patch.fine_shape, 2))
         return backend, calls
 
@@ -291,9 +289,8 @@ class BlockedFineGPU(unittest.TestCase):
             results = []
             with CudaContext(0) as context:
                 for fine_block in (None, *FINE_BLOCKS):
-                    with FixedPatchStepper(cfg, context=context, coarse_boundary=mode,
-                                           refinements=[BOUNDS],
-                                           level_blocks=[None, fine_block]) as backend:
+                    with FixedPatchStepper(cfg, BOUNDS, context=context, coarse_boundary=mode,
+                                           fine_block=fine_block) as backend:
                         backend.initialize(g_coarse, g_fine)
                         backend.step(STEPS)
                         self.assertEqual(backend.step_count, STEPS)
@@ -321,9 +318,8 @@ class BlockedFineGPU(unittest.TestCase):
             results = []
             with CudaContext(0) as context:
                 for fine_block in (None, *FINE_BLOCKS):
-                    with FixedPatchStepper(cfg, context=context, coarse_boundary=mode,
-                                           refinements=[BOUNDS], level_blocks=[None, fine_block],
-                                           level_objects=[(), (circle(),)]) as backend:
+                    with FixedPatchStepper(cfg, BOUNDS, context=context, coarse_boundary=mode,
+                                           fine_objects=[circle()], fine_block=fine_block) as backend:
                         backend.initialize(g_coarse, g_fine)
                         backend.step(STEPS)
                         results.append((backend.download(), raw(backend)))
@@ -350,9 +346,9 @@ class BlockedFineGPU(unittest.TestCase):
                 results = []
                 with CudaContext(0) as context:
                     for fine_block in (None, *FINE_BLOCKS):
-                        with FixedPatchStepper(cfg, context=context, coarse_boundary=mode,
-                                               refinements=[BOUNDS], level_blocks=[None, fine_block],
-                                               level_objects=[(), (circle(actuation(speed)),)]) as backend:
+                        with FixedPatchStepper(cfg, BOUNDS, context=context, coarse_boundary=mode,
+                                               fine_objects=[circle(actuation(speed))],
+                                               fine_block=fine_block) as backend:
                             backend.initialize(g_coarse, g_fine)
                             backend.step(STEPS)
                             results.append((backend.download(), raw(backend)))

tests/validation/multigrid/test_refinement_followup.py

@@ -94,8 +94,7 @@ class FaultGuardsCPU(unittest.TestCase):
                              ("slot_reservoir", (12, 4, 20, 21))):
             with self.subTest(mode=mode, bounds=bounds):
                 with self.assertRaises(ValueError):
-                    implementation.FixedPatchStepper(cfg, context=context, coarse_boundary=mode,
-                                                     refinements=[bounds])
+                    implementation.FixedPatchStepper(cfg, bounds, context=context, coarse_boundary=mode)
                 context.activate.assert_not_called()
         # Both exact channel limits and the original periodic two-cell margin
         # must reach context activation, with no allocation or device required.
@@ -103,14 +102,11 @@ class FaultGuardsCPU(unittest.TestCase):
                              ("periodic", (2, 2, 6, 5))):
             with self.subTest(mode=mode, bounds=bounds):
                 with self.assertRaisesRegex(RuntimeError, "validated before CUDA"):
-                    implementation.FixedPatchStepper(cfg, context=context, coarse_boundary=mode,
-                                                     refinements=[bounds])
+                    implementation.FixedPatchStepper(cfg, bounds, context=context, coarse_boundary=mode)
 
     def fake_backend(self):
         backend = PeriodicPatchStepper.__new__(PeriodicPatchStepper)
-        backend._layouts = [None, None]  # dense storage on both levels
-        backend._ddf_shifting = False  # unshifted on every level, as _check_storage expects
-        backend._level_cfgs = [LBMConfig(nx=16, ny=16, viscosity=.1)] * 2  # ddf_shifting off
+        backend.fine_layout = None  # dense fine storage
         backend.ctx = Mock(activate=nullcontext)
         backend._lock = RLock()
         backend._status = "ready"
@@ -158,23 +154,12 @@ class FaultGuardsCPU(unittest.TestCase):
         context = Mock(activate=nullcontext, sm_arch="sm_70")
         with patch.object(implementation, "HALO", 2):
             with self.assertRaisesRegex(RuntimeError, "four-cell"):
-                PeriodicPatchStepper(cfg, context=context, refinements=[(4, 4, 12, 12)])
+                PeriodicPatchStepper(cfg, (4, 4, 12, 12), context=context)
         p = implementation.FixedPatch2D.from_config(cfg, (4, 4, 12, 12))
-        from CelerisLab.lbm import hierarchy
-        bad = patch.object(implementation.FixedPatch2D, "from_config",
-                           return_value=replace(p, tau_coarse=.9))
-        # A pair tau inconsistent with its level config is rejected twice over, both before
-        # any device allocation or upload: first by the hierarchy chain check, and, if that
-        # is bypassed, by the per-level omega/tau check in _build_level.
-        with patch.object(cuda, "Stream"), bad, patch.object(cuda, "mem_alloc") as alloc, \
-                patch.object(cuda, "memcpy_htod") as upload:
-            with self.assertRaisesRegex(RuntimeError, "config chain is inconsistent"):
-                PeriodicPatchStepper(cfg, context=context, refinements=[p.bounds])
-            with patch.object(hierarchy, "_check_chain"), \
-                    self.assertRaisesRegex(RuntimeError, "omega/tau"):
-                PeriodicPatchStepper(cfg, context=context, refinements=[p.bounds])
-            alloc.assert_not_called()
-            upload.assert_not_called()
+        with patch.object(cuda, "Stream"), patch.object(implementation.FixedPatch2D, "from_config",
+                                                       return_value=replace(p, tau_coarse=.9)):
+            with self.assertRaisesRegex(RuntimeError, "omega/tau"):
+                PeriodicPatchStepper(cfg, p.bounds, context=context)
         module = Mock()
         module.get_global.return_value = (Mock(), 16)
         with patch.object(cuda, "Stream"), patch.object(compiler, "generate_config"), \
@@ -182,7 +167,7 @@ class FaultGuardsCPU(unittest.TestCase):
                 patch.object(compiler, "load_module", return_value=module), \
                 patch.object(cuda, "memcpy_htod") as upload:
             with self.assertRaisesRegex(RuntimeError, "layout mismatch"):
-                PeriodicPatchStepper(cfg, context=context, refinements=[p.bounds])
+                PeriodicPatchStepper(cfg, p.bounds, context=context)
             upload.assert_not_called()
 
 
@@ -256,7 +241,7 @@ class NormalBuildGPU(unittest.TestCase):
         max_error = max_bc_error = 0.0
         with CudaContext(0) as context:
             with patch.object(compiler, "generate_config", side_effect=record_config):
-                backend = implementation.FixedPatchStepper(cfg, context=context, refinements=[bounds],
+                backend = implementation.FixedPatchStepper(cfg, bounds, context=context,
                                                             coarse_boundary="slot_reservoir")
             with backend:
                 self.assertEqual(len(generated), 2)
@@ -326,8 +311,7 @@ class NormalBuildGPU(unittest.TestCase):
                             for a in (initial.coarse_f, initial.fine_f)))
         max_pop = max_drift = max_moment = 0.0
         with CudaContext(0) as context, PeriodicPatchStepper(
-                LBMConfig(nx=16, ny=16, viscosity=.1), context=context,
-                refinements=[(4, 4, 12, 12)]) as backend:
+                LBMConfig(nx=16, ny=16, viscosity=.1), (4, 4, 12, 12), context=context) as backend:
             backend.initialize(*postcollision(state, spec, maps))
             before = totals(backend.download(), maps)
             for step in range(1, 9):
@@ -358,7 +342,7 @@ class NormalBuildGPU(unittest.TestCase):
         fine_mask[4:-4, 4:-4] = True
         initial[1][:, ~fine_mask] = np.nan
         expected = scalar_interval(*[a.astype(np.float64) for a in initial], bounds)
-        with CudaContext(0) as context, PeriodicPatchStepper(cfg, context=context, refinements=[bounds]) as backend:
+        with CudaContext(0) as context, PeriodicPatchStepper(cfg, bounds, context=context) as backend:
             self.assertEqual(backend.patch.fine_shape, (14, 16))
             p = backend.patch
             allocated = 2 * 9 * (17*13+16*14) * 4 + sum(a.nbytes for a in

tests/validation/multigrid/test_refinement_gpu.py

@@ -7,7 +7,6 @@ At most eight coarse steps per case. No files, plots or flow arrays are saved.
 import hashlib
 import importlib.util
 from contextlib import nullcontext
-from dataclasses import replace
 from pathlib import Path
 import resource
 import sys
@@ -22,7 +21,7 @@ import CelerisLab
 from CelerisLab.config import LBMConfig
 from CelerisLab.cuda import compiler_v2 as compiler
 from CelerisLab.cuda.context import CudaContext
-from CelerisLab.lbm.refinement_stepper import FixedPatchStepper, PeriodicPatchStepper
+from CelerisLab.lbm.refinement_stepper import PeriodicPatchStepper
 
 ROOT = Path(__file__).resolve().parents[3]
 POP_ATOL = 3e-6
@@ -61,69 +60,6 @@ def global_array(module, name, shape):
 
 
 class CoupledGPU(unittest.TestCase):
-    def test_actual_tg_rates_one_interval(self):
-        """Algebraic rate/phase check, not a new physical Taylor--Green benchmark.
-
-        The N64/Re100 TG rates are exercised on the existing small patch with
-        a nonequilibrium state. One interval checks g=C(f), including the
-        shifted blocked path; no accuracy gate or production source changes.
-        """
-        self.assertEqual(Path(CelerisLab.__file__).resolve(), ROOT / "src/CelerisLab/__init__.py")
-        self.assertEqual(Path(compiler._KERNEL_DIR).resolve(), ROOT / "src/CelerisLab/lbm/kernels")
-        spec = replace(ref.make_spec(collision="srt"),
-                       tau_coarse=.5576, tau_fine=.6152)
-        maps = ref.build_maps(spec)
-        state = ref.make_state(spec, velocity=(.03, -.02))
-        rng = np.random.default_rng(1)
-        state = ref.State(*(a * (1 + 1e-3 * rng.standard_normal(a.shape))
-                            for a in (state.coarse_f, state.fine_f)))
-        initial = postcollision(state, spec, maps)
-        next_state, _ = ref.advance_coarse_once(spec, maps, state)
-        expected = postcollision(next_state, spec, maps)
-        arrivals = (next_state.coarse_f, next_state.fine_f)
-
-        cases = (("dense_unshifted", False, {}),
-                 ("blocked_shifted", True,
-                  dict(level_blocks=[(4, 4), (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)],
-                                           **storage) as backend:
-                        self.assertAlmostEqual(backend.patch.tau_coarse, spec.tau_coarse)
-                        self.assertAlmostEqual(backend.patch.tau_fine, spec.tau_fine)
-                        self.assertEqual(tuple(level.shape for level in backend._levels),
-                                         ((9, 16, 16), (9, 24, 24)))
-                        # Physical FP64 g is encoded by initialize before FP32 rounding.
-                        backend.initialize(*initial)
-                        before = totals(backend.download(), maps)
-                        backend.step(1)
-                        actual = backend.download()
-                        self.assertEqual(backend.step_count, 1)
-                        backend.patch.check_synchronization(
-                            1, next_state.tick, phase="postcollision_g")
-                        for got, want, arrival in zip(actual, expected, arrivals):
-                            np.testing.assert_array_equal(np.isnan(got), np.isnan(want))
-                            np.testing.assert_allclose(got, want, rtol=0, atol=POP_ATOL,
-                                                       equal_nan=True)
-                            # A raw arrival-f comparison must fail on BOTH levels.
-                            # Equilibrium-only data would make this control vacuous.
-                            with self.assertRaises(AssertionError):
-                                np.testing.assert_allclose(got, arrival, rtol=0,
-                                                           atol=POP_ATOL, equal_nan=True)
-                        np.testing.assert_allclose(totals(actual, maps), before,
-                                                   rtol=0, atol=MOMENT_ATOL)
-                        np.testing.assert_allclose(totals(actual, maps),
-                                                   totals(expected, maps),
-                                                   rtol=0, atol=MOMENT_ATOL)
-                        error = max(float(np.nanmax(np.abs(a - e)))
-                                    for a, e in zip(actual, expected))
-                        print(f"actual-TG-rate algebraic check: {label} steps=1 "
-                              f"tau=.5576/.6152 max_population={error:.9g}; "
-                              "wrong-phase controls PASS", flush=True)
-
     def test_cleanup_attempts_every_allocation(self):
         backend = PeriodicPatchStepper.__new__(PeriodicPatchStepper)
         backend.ctx = Mock(activate=nullcontext)
@@ -148,7 +84,7 @@ 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 +123,7 @@ 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 +206,7 @@ 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()

tests/validation/multigrid/test_refinement_jets.py

@@ -41,9 +41,8 @@ def mocked(objects, jets, fine_block):
             patch.object(compiler, "load_module", return_value=module), \
             patch.object(cuda, "mem_alloc", side_effect=lambda size: Mock()), \
             patch.object(cuda, "memcpy_htod", htod):
-        backend = FixedPatchStepper(config("periodic"), context=context, refinements=[BOUNDS],
-                                    level_blocks=[None, fine_block], level_objects=[(), tuple(objects)],
-                                    level_jets=[(), tuple(jets)])
+        backend = FixedPatchStepper(config("periodic"), BOUNDS, context=context,
+                                    fine_objects=objects, fine_block=fine_block, jets=jets)
     return backend, htod
 
 
@@ -150,9 +149,8 @@ class JetStepperCPU(unittest.TestCase):
     def test_jet_overlapping_legacy_aperture_rejected_before_cuda(self):
         with patch.object(cuda, "Stream", side_effect=AssertionError("CUDA touched")):
             with self.assertRaisesRegex(ValueError, "SurfaceActuation"):
-                FixedPatchStepper(config("periodic"), context=Mock(), refinements=[BOUNDS],
-                                  level_objects=[(), (circle(actuation(SPEED)),)],
-                                  level_jets=[(), (jet(),)])
+                FixedPatchStepper(config("periodic"), BOUNDS, context=Mock(),
+                                  fine_objects=[circle(actuation(SPEED))], jets=[jet()])
 
 
 def run(mode, fine_block, *, objects, jets, switch=None):
@@ -160,9 +158,8 @@ def run(mode, fine_block, *, objects, jets, switch=None):
     cfg = config(mode)
     patch_ = FixedPatch2D.from_config(cfg, BOUNDS)
     with CudaContext(0) as context, FixedPatchStepper(
-            cfg, context=context, coarse_boundary=mode, refinements=[BOUNDS],
-            level_blocks=[None, fine_block], level_objects=[(), tuple(objects)],
-            level_jets=[(), tuple(jets)]) as backend:
+            cfg, BOUNDS, context=context, coarse_boundary=mode, fine_objects=objects,
+            fine_block=fine_block, jets=jets) as backend:
         backend.initialize(state(NY, NX, 1), state(*patch_.fine_shape, 2))
         if switch is None:
             backend.step(STEPS)

tests/validation/multigrid/test_refinement_mrt_gpu.py

@@ -1,96 +0,0 @@
-"""MRT reuse GPU gates. Caller owns GPU admission (CUDA_VISIBLE_DEVICES).
-
-Run: python -m unittest discover -s tests/validation/multigrid -p test_refinement_mrt_gpu.py
-Parity compares the blocked MRT channel root with uniform MRT OneStep: the existing
-pressure-NEQ outlet branch differs by collision model, so SRT is never the reference.
-AMR checks are finite-evolution/split-invariance smoke tests, not benchmark validation.
-"""
-from dataclasses import replace
-import unittest
-import numpy as np
-
-from CelerisLab.config import LBMConfig
-from CelerisLab.cuda.context import CudaContext
-from CelerisLab.lbm.population_storage import _encode_physical
-from CelerisLab.lbm.refinement_stepper import FixedPatchStepper
-from test_channel_root_gpu import run_root, state
-from test_refinement_blocked_base import raw, exact
-
-
-class RefinementMRTGPU(unittest.TestCase):
-    def test_uniform_matched_mrt_root(self):
-        with CudaContext(0) as context:
-            for shifted in (False, True):
-                for profile in ("uniform", "parabolic"):
-                    cfg = LBMConfig(nx=24, ny=20, viscosity=.1, velocity=.025, collision="MRT",
-                                    ddf_shifting=shifted, inlet_profile=profile)
-                    initial = _encode_physical(state(cfg.ny, cfg.nx), shifted)
-                    expected = run_root(cfg, context, initial)
-                    self.assertTrue(np.isfinite(expected).all())
-                    for block in ((20, 24), (5, 6), (4, 1)):
-                        np.testing.assert_array_equal(run_root(cfg, context, initial, block), expected)
-
-    def test_amr_mrt_smoke(self):
-        from CelerisLab.body.geometry.circle import CircleGeometry
-        from CelerisLab.body.objects import SimObject
-        center = (24., 16.)
-        body = SimObject(0, geometry=CircleGeometry(*center, 2.15), center=center, radius=2.15)
-        with CudaContext(0) as context:
-            for boundary in ("periodic", "channel"):
-                for shifted in (False, True):
-                    cfg = LBMConfig(nx=48, ny=32, viscosity=.1, velocity=.015 if boundary == "channel" else 0.,
-                                    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:
-                            backend.initialize(*[state(*level.shape[1:]) for level in backend._levels])
-                            backend.step(8)
-                            raw = backend._download_raw()
-                            for a, mask in zip(raw.values, backend._state):
-                                self.assertTrue(np.isfinite(a[:, mask]).all())
-                            if reference is None: reference = raw.values
-                            else:
-                                for a, b in zip(reference, raw.values): np.testing.assert_array_equal(a, b)
-
-    def test_dense_versus_blocked_mrt_two_level(self):
-        """Unshifted MRT: all-dense PatchCoarseStep/PatchFineStep vs mixed/all-blocked storage."""
-        from test_refinement_blocked_base import BASE_BLOCKS, FINE_BLOCK
-        from test_refinement_blocked_fine import NX, NY, BOUNDS
-        import test_refinement_blocked_fine as fixture
-        cfg = LBMConfig(nx=NX, ny=NY, viscosity=.1, collision="MRT")
-        with CudaContext(0) as context:
-            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:
-                    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)
-            for layout in layouts[1:]:
-                for level, (a, b) in enumerate(zip(results[layout], results[None, None])):
-                    exact(self, a, b, f"layout={layout} level={level}")
-
-    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)
-        with CudaContext(0) as context:
-            with FixedPatchStepper(cfg, 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)
-                    checked.validate()  # omega is derived only by validate()
-                    self.assertEqual(checked.collision, "MRT")
-                    self.assertTrue(checked.ddf_shifting)
-                    self.assertTrue(np.isclose(checked.omega, 1 / (3 * 2**level * .1 + .5), rtol=1e-14))
-                backend.initialize(*[state(*level.shape[1:]) for level in backend._levels])
-                backend.step(4)
-                values = backend._download_raw().values
-                for a, mask in zip(values, backend._state):
-                    self.assertTrue(np.isfinite(a[:, mask]).all())
-
-
-if __name__ == "__main__": unittest.main()

tests/validation/multigrid/test_refinement_multipatch.py

@@ -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}"

tests/validation/multigrid/test_refinement_three_level.py

@@ -27,16 +27,7 @@ from test_refinement_blocked_base import raw
 
 CFG = LBMConfig(nx=16, ny=16, viscosity=.1)
 L1, L2 = (4, 4, 12, 12), (8, 8, 16, 16)
-B = (4, 4)
-
-
-def levels(l1=L1, l2=L2, blocks=(B, B, B), objects=((), (), ()), jets=((), (), ())):
-    """Level-list keywords for the scalar L1 patch with one scalar L2 child."""
-    return dict(refinements=[l1, l2], level_blocks=list(blocks),
-                level_objects=list(objects), level_jets=list(jets))
-
-
-KW = levels()
+KW = dict(fine_block=(4, 4), base_block=(4, 4), child=L2, child_block=(4, 4))
 
 
 def child_body(spec=None):
@@ -61,29 +52,26 @@ def mocked_child():
             patch.object(compiler, "load_module", return_value=module), \
             patch.object(cuda, "mem_alloc", side_effect=lambda size: Mock()), \
             patch.object(cuda, "memcpy_htod"):
-        return FixedPatchStepper(CFG, context=context,
-                                 **levels(objects=((), (), (child_body(),)), jets=((), (), (child_jet(),))))
+        return FixedPatchStepper(CFG, L1, context=context, child_objects=[child_body()],
+                                 child_jets=[child_jet()], **KW)
 
 
 class ThreeLevelCPU(unittest.TestCase):
     def test_rejections_before_cuda(self):
         context = object()  # never activated: every case must fail first
-        bad = (levels(blocks=(B, B, None)), levels(blocks=(B, None, B)),
-               levels(objects=((), (circle(),), ())), levels(l2=(4, 8, 16, 16)),
-               levels(blocks=(B, B, (5, 4))))
+        bad = (dict(KW, child_block=None), dict(KW, fine_block=None),
+               dict(KW, fine_objects=[circle()]), dict(KW, child=(4, 8, 16, 16)),
+               dict(KW, child_block=(5, 4)))
         for kw in bad:
             with self.subTest(kw=kw), self.assertRaises(ValueError):
-                FixedPatchStepper(CFG, context=context, **kw)
-        # L2 bodies/Jets without an L2 level (one entry too many), and an L2 Jet without a body.
-        two_level = dict(refinements=[L1], level_blocks=[None, None])
-        for kw in (dict(two_level, level_objects=[(), (), (child_body(),)]),
-                   dict(two_level, level_jets=[(), (), (child_jet(),)]),
-                   levels(jets=((), (), (child_jet(),)))):
+                FixedPatchStepper(CFG, L1, context=context, **kw)
+        for kw in (dict(child_objects=[child_body()]), dict(child_jets=[child_jet()]),
+                   dict(KW, child_jets=[child_jet()])):
             with self.assertRaises(ValueError):
-                FixedPatchStepper(CFG, context=context, **kw)
-        with self.assertRaises(ValueError):  # several L1 patches + scalar child: not yet
-            FixedPatchStepper(LBMConfig(nx=32, ny=16, viscosity=.1), context=context,
-                              **levels(l1=((4, 4, 12, 12), (20, 4, 28, 12))))
+                FixedPatchStepper(CFG, L1, context=context, **kw)
+        with self.assertRaises(ValueError):  # several L1 patches + child: not yet
+            FixedPatchStepper(LBMConfig(nx=32, ny=16, viscosity=.1), ((4, 4, 12, 12), (20, 4, 28, 12)),
+                              context=context, **KW)
 
 
     def test_four_halo_bfl_steps_and_fresh_middle_feeds(self):
@@ -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):

tests/validation/multigrid/test_refinement_three_level_multipatch_gpu.py

@@ -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)))

tests/validation/multigrid/test_runtime_child_remap_gpu.py

@@ -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):

tests/validation/multigrid/test_shifted_jets_gpu.py

@@ -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

tests/validation/multigrid/test_shifted_remap_gpu.py

@@ -22,8 +22,9 @@ B=((20,16,36,40),)
 
 
 def make(ctx):
-    return FixedPatchStepper(CFG,context=ctx,refinements=[PARENTS,A],
-                             level_blocks=[(4,4)]*3)
+    return FixedPatchStepper(CFG,PARENTS,context=ctx,base_block=(4,4),
+                             fine_block=(4,4),child_block=(4,4),
+                             child_rectangles_in_parent=A)
 
 
 def initial(run):

tests/validation/run_dfg_re20.py

@@ -1,222 +0,0 @@
-"""Steady DFG 2D-1 (Re 20): refined and uniform runs against the official reference intervals.
-
-Not a full benchmark certification. Declared deviations from the official setup:
-pressure-NEQ outlet (``neq_extrap``) instead of do-nothing, local Zou-He inlet.
-Geometry, inflow profile, initial state, refined layout and observation reuse the
-pinned Re100 runner (``run_refined_dfg``) and ``re100_helpers`` unchanged; only the
-lattice viscosity is set for Re 20 (nu = U_lattice * D / 20 at the root level).
-
-Units. The helpers use scaled DFG units with mean inflow speed 1, so
-Cd = 2 Fx / (rho U^2 D) and Cl = 2 Fy / (rho U^2 D) are scale-free, and
-``pressure_probes`` returns dp / (rho U^2). The official p_diff = p(0.15, 0.2) -
-p(0.25, 0.2) uses U = 0.2 m/s, rho = 1, so p_diff = dp * 0.04. Both are reported;
-only p_diff is compared with the official interval. Forces use the existing sign
-convention: F is the force of the fluid on the cylinder, i.e. the refined raw
-exchange impulse (window ledger, ``total.impulse``) or the uniform ``read_force``,
-with x along the inflow and y up from the bottom wall. Cd must be positive, and the
-official Cl is positive (centre 0.20 below the centreline 0.205), so a flipped sign
-shows up as Cl outside its interval.
-
-Sampling. One sample every SAMPLE_TSTAR (t* = U t / D; 0.25 s), taken at the end of
-a completed root step with all levels synchronized; the step index is recorded. Cd
-and Cl are means over the sample interval (window exchange ledger refined, per-batch
-forces uniform), which filters acoustic and step-parity oscillation; p_diff is the
-end-of-interval value at the exact surface points.
-
-Steady rule (our engineering choice, frozen before any run; not official). Over the
-trailing WINDOW_TSTAR (t* 50..60 inclusive, 21 samples), for each of Cd, Cl and
-p_diff: range (max - min) <= 10 % and |least-squares slope * window| <= 2 % of the
-width of its official interval. Absolute limits, so the small Cl is never a divisor;
-the slope term bounds slow monotone drift that the range alone would pass. If the
-rule fails at TSTAR_MAX the run reports "not steady" and gives no interval verdict;
-limits are never relaxed after a run. The verdict uses the window mean, and the
-distance of each mean to its nearest interval edge is reported (negative outside).
-"""
-
-import argparse
-import json
-import math
-import os
-from pathlib import Path
-import sys
-import time
-from tempfile import TemporaryDirectory
-
-import numpy as np
-
-HERE = Path(__file__).resolve().parent
-sys.path.insert(0, str(HERE))
-import run_refined_dfg as rr  # noqa: E402
-
-RE = 20.0
-U_PHYS = 0.2                   # m/s mean inflow; rho = 1
-TSTAR_MAX = 60.0               # 30 s physical
-SAMPLE_TSTAR = 0.5             # 0.25 s
-WINDOW_TSTAR = 10.0            # trailing 5 s, 21 samples
-# Schaefer & Turek (1996), 2D-1 lower/upper bounds.
-BANDS = dict(cd=(5.57, 5.59), cl=(0.0104, 0.0110), p_diff=(0.1172, 0.1176))
-STEADY_RANGE = {k: (hi - lo) / 10 for k, (lo, hi) in BANDS.items()}
-STEADY_SLOPE = {k: (hi - lo) / 50 for k, (lo, hi) in BANDS.items()}
-DEVIATIONS = ("pressure-NEQ outlet (neq_extrap), not do-nothing", "local Zou-He inlet")
-
-_re100_config = rr.config
-
-
-def config(h, diameter, collision="SRT", jet_scenario="none"):
-    """The pinned Re100 configuration with the lattice viscosity set for Re 20."""
-    if jet_scenario != "none":
-        raise ValueError("DFG 2D-1 runs have no Jets")
-    cfg, body, p = _re100_config(h, diameter, collision, jet_scenario)
-    nu = p["mean_speed"] * p["diameter"] / RE
-    cfg["physics"]["viscosity"] = nu
-    return cfg, body, dict(p, viscosity=nu, re=RE)
-
-
-def lattice_parameters(diameter, speed=rr.SPEED):
-    nu = speed * diameter / RE
-    return dict(viscosity=nu, tau=0.5 + 3 * nu, steps=math.ceil(TSTAR_MAX * diameter / speed),
-                interval=round(SAMPLE_TSTAR * diameter / speed))
-
-
-def sample(impulse, n, diameter, dp):
-    den = rr.SPEED**2 * diameter / 2
-    return dict(cd=float(impulse[0] / n / den), cl=float(impulse[1] / n / den),
-                dp_scaled=float(dp), p_diff=float(dp) * U_PHYS**2)
-
-
-def summarize(rows):
-    """Steady rule over the trailing window, then the interval verdict (or none)."""
-    if not rows or rows[-1]["tstar"] < TSTAR_MAX - 1e-9:
-        return dict(status="INCOMPLETE", steady=False, verdict=None)
-    window = [r for r in rows if r["tstar"] >= TSTAR_MAX - WINDOW_TSTAR - 1e-9]
-    t = np.array([r["tstar"] for r in window])
-    ranges = {k: max(r[k] for r in window) - min(r[k] for r in window) for k in BANDS}
-    drifts = {k: abs(np.polyfit(t, [r[k] for r in window], 1)[0]) * WINDOW_TSTAR for k in BANDS}
-    steady = all(ranges[k] <= STEADY_RANGE[k] and drifts[k] <= STEADY_SLOPE[k] for k in BANDS)
-    final = {k: float(np.mean([r[k] for r in window])) for k in BANDS}
-    edge = {k: min(final[k] - BANDS[k][0], BANDS[k][1] - final[k]) for k in BANDS}
-    result = dict(window_samples=len(window), ranges=ranges, drifts=drifts,
-                  range_limits=STEADY_RANGE, slope_limits=STEADY_SLOPE, steady=steady,
-                  window_mean=final, edge_distance=edge, bands=BANDS,
-                  deviations=DEVIATIONS, cd_positive=final["cd"] > 0)
-    if not steady:
-        return dict(result, status="NOT_STEADY", verdict=None)
-    inside = {k: BANDS[k][0] <= final[k] <= BANDS[k][1] for k in BANDS}
-    return dict(result, status="WITHIN_INTERVALS" if all(inside.values()) else "OUTSIDE_INTERVALS",
-                verdict=inside)
-
-
-def healthy(row):
-    return row["max_mach"] <= 0.2 and row["rho_min"] >= 0.5 and row["rho_max"] <= 1.5
-
-
-def run_case(a, h, case):
-    from contextlib import ExitStack
-    from CelerisLab.cuda.context import CudaContext
-    from CelerisLab.lbm.descriptors import FLUID
-    from CelerisLab.lbm.refinement_stepper import FixedPatchStepper
-    from CelerisLab.simulation import Simulation
-
-    refined = case == "refined"
-    cfgdict, bodydict, p = config(h, 40 if refined else 80, a.collision)
-    lp = lattice_parameters(p["diameter"])
-    rows = []
-    with ExitStack() as stack:
-        if refined:
-            cfg, pair, body, host = rr.host_geometry(a.source, h, a.collision)
-            context = stack.enter_context(CudaContext(0))
-            backend = stack.enter_context(FixedPatchStepper(
-                cfg, context=context, coarse_boundary="channel", refinements=[rr.PLACEMENTS["wide"]],
-                level_blocks=[rr.BASE_BLOCK, rr.FINE_BLOCK], level_objects=[(), (body,)],
-                observe_raw_exchange=True, observe_window_exchange=True))
-            from CelerisLab.lbm.channel import channel_masks
-            from CelerisLab.lbm.refinement import ACTIVE
-            from CelerisLab.lbm.descriptors import SOLID
-            masks = [channel_masks(pair.coarse_shape)[0] & ~pair.covered,
-                     (pair.fine_kind == ACTIVE)
-                     & ((host.flags.reshape(pair.fine_shape) & SOLID) == 0)]
-            backend.initialize(rr.initial_state(pair.coarse_shape, (0.0, 0.0), 1.0, root=True),
-                               rr.initial_state(pair.fine_shape, pair.fine_origin, 0.5))
-            probe_p = dict(p, center=[(80.5 - pair.fine_origin[0]) / 0.5 - 0.5,
-                                      (81.0 - pair.fine_origin[1]) / 0.5 - 0.5], radius=40.0)
-        else:
-            tmp = Path(stack.enter_context(TemporaryDirectory()))
-            (tmp / "lbm.json").write_text(json.dumps(cfgdict))
-            (tmp / "body.json").write_text(json.dumps(bodydict))
-            sim = stack.enter_context(Simulation(str(tmp / "lbm.json"), str(tmp / "body.json"),
-                                                 device_id=0))
-            sim.initialize()
-            probe_p = p
-            fluid = (sim.field.flag.reshape(p["ny"], p["nx"]) & FLUID) != 0
-        begin = 0
-        while begin < lp["steps"]:
-            rr.check_deadline(a.deadline)
-            n = min(lp["interval"], lp["steps"] - begin)
-            if refined:
-                impulse = rr.advance_refined_interval(backend, n, a.deadline, "window")
-                fields = [rr.macros(g) for g in backend.download()]
-                rho, ux, uy = fields[1]
-                fluid = masks[1]
-                vals = [tuple(v[m] for v in f) for m, f in zip(masks, fields)]
-            else:
-                impulse, done = np.zeros(2), 0
-                while done < n:
-                    batch = min(100, n - done)
-                    sim.run(batch)
-                    impulse += sim.read_force(0).astype(np.float64) * batch
-                    done += batch
-                m = sim.get_macroscopic()
-                rho, ux, uy = [np.asarray(m[k], np.float64).reshape(p["ny"], p["nx"])
-                               for k in ("rho", "ux", "uy")]
-                vals = [(rho[fluid], ux[fluid], uy[fluid])]
-            begin += n
-            row = dict(step=begin, tstar=begin * rr.SPEED / p["diameter"],
-                       **sample(impulse, n, p["diameter"],
-                                h.pressure_probes(rho, fluid, probe_p)["dp"]),
-                       rho_min=float(min(v[0].min() for v in vals)),
-                       rho_max=float(max(v[0].max() for v in vals)),
-                       max_mach=float(max(np.sqrt(3 * (v[1]**2 + v[2]**2)).max() for v in vals)))
-            rr.ensure_finite(row)
-            rows.append(row)
-            if not healthy(row):
-                break
-    summary = summarize(rows) if healthy(rows[-1]) else dict(status="UNHEALTHY", steady=False,
-                                                             verdict=None)
-    return dict(case=case, collision=a.collision, lattice=lp, rows=rows, **summary)
-
-
-def plan(collision="SRT"):
-    return dict(re=RE, collision=collision, tstar_max=TSTAR_MAX, sample_tstar=SAMPLE_TSTAR,
-                window_tstar=WINDOW_TSTAR, bands=BANDS, range_limits=STEADY_RANGE, slope_limits=STEADY_SLOPE,
-                deviations=DEVIATIONS, pressure_scale=U_PHYS**2,
-                refined_root=lattice_parameters(40), refined_fine_tau=0.5 + 3 * 2 * rr.SPEED * 40 / RE,
-                uniform=lattice_parameters(80),
-                label="compared against the official reference bands (non-canonical neq_extrap outlet, zou_he_local inlet); not a full benchmark certification")
-
-
-def main():
-    parser = argparse.ArgumentParser(description=__doc__.splitlines()[0])
-    parser.add_argument("--case", choices=["refined", "uniform", "both"], default="refined")
-    parser.add_argument("--collision", choices=["SRT", "MRT"], default="SRT")
-    parser.add_argument("--source", type=Path, default=rr.DEFAULT_SOURCE)
-    parser.add_argument("--output", type=Path, required=True)
-    parser.add_argument("--plan", action="store_true", help="Write the frozen plan; no CUDA")
-    parser.add_argument("--max-wall-seconds", type=float)
-    a = parser.parse_args()
-    a.source = a.source.resolve()
-    a.output.mkdir(parents=True, exist_ok=False)
-    (a.output / "plan.json").write_text(json.dumps(plan(a.collision), indent=2, allow_nan=False))
-    if a.plan:
-        return
-    if not a.max_wall_seconds or a.max_wall_seconds <= 0 or not os.environ.get("CUDA_VISIBLE_DEVICES"):
-        raise SystemExit("GPU run needs --max-wall-seconds > 0 and explicit CUDA_VISIBLE_DEVICES")
-    h, _ = rr.helpers(a.source)
-    rr.config = config  # host_geometry builds its root configuration through this name
-    a.deadline = time.monotonic() + a.max_wall_seconds
-    cases = ["refined", "uniform"] if a.case == "both" else [a.case]
-    results = [run_case(a, h, case) for case in cases]
-    (a.output / "result.json").write_text(json.dumps(results, indent=2, allow_nan=False))
-
-
-if __name__ == "__main__":
-    main()

tests/validation/run_jet_circle_cv.py

@@ -74,25 +74,7 @@ def cv(g, fluid, origin, rectangle, nu, h=0.5):
     Cauchy stress from centred velocity gradients, NOT postcollision non-equilibrium.
     Rectangle faces lie on cell edges; fluid mask excludes the staircase cylinder.
     """
-    return _cv_quantities(*moments(g), fluid, origin, rectangle, nu, h)
-
-
-def cv_from_macros(rho, ux, uy, fluid, origin, rectangle, nu, h=0.5):
-    """Same CV calculation from public macros, in one common length/time frame.
-
-    ``origin`` is the lower cell edge, ``h`` the cell width, and ``nu`` uses
-    that frame. Returns [mass, Px, Py] inventory and outward total flux.
-    Crop fields/mask together and translate origin before calling if desired.
-    No boundary-exchange observation enters this independent estimator.
-    """
-    rho = np.asarray(rho, np.float64)
-    if rho.ndim != 2 or any(np.shape(v) != rho.shape for v in (ux, uy, fluid)):
-        raise ValueError("CV macros and fluid mask must have matching 2D shapes")
-    vel = np.asarray([ux, uy], np.float64)
-    return _cv_quantities(rho, rho[None] * vel, vel, fluid, origin, rectangle, nu, h)
-
-
-def _cv_quantities(rho, mom, vel, fluid, origin, rectangle, nu, h):
+    rho, mom, vel = moments(g)
     x0, y0, x1, y1 = np.rint((np.array(rectangle) - np.tile(origin, 2)) / h).astype(int)
     np.testing.assert_allclose(
         np.array([x0, y0, x1, y1]) * h + np.tile(origin, 2), rectangle, atol=1e-12
@@ -279,11 +261,12 @@ def run_case(c, ctx, output, provenance, continuation=False):
         PeriodicBlockStepper(fine_cfg, layout, context=ctx, objects=[fobj]) as uniform,
         FixedPatchStepper(
             cfg,
+            c["bounds"],
             context=ctx,
-            refinements=[c["bounds"]],
-            level_blocks=[(8, 8), (8, 8)],
-            level_objects=[(), (obj,)],
-            level_jets=[(), tuple(jets)],
+            base_block=(8, 8),
+            fine_block=(8, 8),
+            fine_objects=[obj],
+            jets=jets,
             observe_raw_exchange=True,
         ) as amr,
     ):