fix(esopull): correct init layout and pre-streaming semantics (v0.5.1)

EsoPull curved boundaries and wall BCs now use consistent backing-layout
reads; InitEsoPull writes equilibrium in t=0 EsoPull layout. Cache N_OBJS
after compile and atomic config header writes to avoid parallel races.
Adds config screening tools, flume configs, and FP16S/EsoPull diagnosis doc.

Co-authored-by: Cursor <cursoragent@cursor.com>

tests/postproc/run_exp_ctrl_matrix_vorticity.py

@@ -48,8 +48,12 @@ OMEGA_SIGN_FROM_ACTION = -1.0
 VORT_VMIN = -0.003
 VORT_VMAX = 0.003
 
+STEALTH_REF_OMEGA_M_S = 0.01806
+STEALTH_STEADY_FRAC = 1.25  # s125 from steady sweep
+STEALTH_STEADY_OMEGA_M_S = STEALTH_REF_OMEGA_M_S * STEALTH_STEADY_FRAC
+
 CONFIG_PATH = _REPO / "src/CelerisLab/configs/config_lbm_three_cylinder_triangle.json"
-DEFAULT_OUT = _REPO / "tests" / "output" / "exp_ctrl_matrix_vort_ny300"
+DEFAULT_OUT = _REPO / "tests" / "output" / "exp_ctrl_matrix_vort_nx1500"
 FIXED_STEPS = 100000  # keep constant while grid changes
 # Body order: 0=apex, 1=rear-lower(y_lower), 2=rear-upper(y_upper); swap action2/action3 targets.
 SWAP_ACTION23_BODIES = True
@@ -70,8 +74,8 @@ CONTROL_CASES: List[Tuple[str, str, Dict[str, Any]]] = [
         "stealth",
         {
             "action1": {"mean": 0.0, "components": [(0.1354, 0.0, 1.600)]},
-            "action2": {"mean": -0.01806, "components": [(0.1354, 0.0, 2.099)]},
-            "action3": {"mean": 0.01806, "components": [(0.1354, 0.0, 1.639)]},
+            "action2": {"mean": -STEALTH_STEADY_OMEGA_M_S, "components": [(0.1354, 0.0, 2.099)]},
+            "action3": {"mean": STEALTH_STEADY_OMEGA_M_S, "components": [(0.1354, 0.0, 1.639)]},
         },
     ),
     (
@@ -308,43 +312,31 @@ def run_case(
     dt_phys = dx_phys * (u_lb / INLET_U_PHYS_M_S)
     cylinders = cylinders_from_triangle_layout(layout)
 
-    print(f"--- {case_id} {slug} steps={steps} u_lb={u_lb} dt_phys={dt_phys} batch={batch} ---")
-    stream = sim.stream
-    batch_size = max(1, int(batch))
+    print(f"--- {case_id} {slug} steps={steps} u_lb={u_lb} dt_phys={dt_phys} ---")
 
-    # Main loop: precompute actions, batch-step, read forces/sensors at intervals
-    for batch_start in range(0, steps, batch_size):
-        batch_end = min(batch_start + batch_size, steps)
-        for j in range(batch_start, batch_end):
-            t_phys = j * dt_phys
-            a1, a2, a3 = _actions_at_time(t_phys, features)
-            w1 = _action_to_omega_lb(a1, u_lb)
-            w2 = _action_to_omega_lb(a2, u_lb)
-            w3 = _action_to_omega_lb(a3, u_lb)
-            if SWAP_ACTION23_BODIES:
-                _set_body_omegas(sim, w1, w3, w2)
-            else:
-                _set_body_omegas(sim, w1, w2, w3)
+    for step in range(steps):
+        t_phys = step * dt_phys
+        a1, a2, a3 = _actions_at_time(t_phys, features)
+        w1 = _action_to_omega_lb(a1, u_lb)
+        w2 = _action_to_omega_lb(a2, u_lb)
+        w3 = _action_to_omega_lb(a3, u_lb)
+        if SWAP_ACTION23_BODIES:
+            _set_body_omegas(sim, w1, w3, w2)
+        else:
+            _set_body_omegas(sim, w1, w2, w3)
+        sim.run(1, sync_obs=False)
 
-        n = batch_end - batch_start
-        sim.stepper.step(
-            n,
-            action_gpu=sim.bodies.action_gpu,
-            obs_gpu=sim.bodies.obs_gpu,
-            stream=stream,
-        )
-
-        if report_every > 0 and (batch_end % report_every == 0 or batch_end == steps):
-            stream.synchronize()
+        if report_every > 0 and ((step + 1) % report_every == 0 or step + 1 == steps):
+            sim.stream.synchronize()
             for bid in range(sim.bodies.count):
                 fx = sim.bodies.read_force(bid)
                 print(
-                    f"  step={batch_end} body={bid}"
+                    f"  step={step + 1} body={bid}"
                     f" fx={float(fx[0]):+.6f} fy={float(fx[1]):+.6f}",
                     flush=True,
                 )
 
-    stream.synchronize()
+    sim.stream.synchronize()
     macro = sim.get_macroscopic()
     vort = compute_vorticity(macro["ux"], macro["uy"])
     png = out_dir / f"vorticity_{case_id}_{slug}.png"
@@ -461,6 +453,8 @@ def main() -> int:
         "device_id": int(args.device_id),
         "vort_vmin": VORT_VMIN,
         "vort_vmax": VORT_VMAX,
+        "stealth_steady_omega_m_s": STEALTH_STEADY_OMEGA_M_S,
+        "stealth_steady_frac": STEALTH_STEADY_FRAC,
         "swap_action23_bodies": bool(SWAP_ACTION23_BODIES),
         "cases": summaries,
     }