simulation: keep the owner context active through moving diagnostics readback

moving_diagnostics is context_bound, so stream synchronization and the
DTOH copy run inside one owner activation. Tests: owner stays active
through sync and download; launch order moving -> static curved -> OneStep
with a real static link count and the buffer swap between steps.

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

tests/unit/test_moving_bodies.py

@@ -261,21 +261,61 @@ def test_moving_tables_layout_and_attachment(monkeypatch):
     assert sim.stepper.moving is None and sim.stepper.blocked is not None
 
 
+class CountingOwner(Owner):
+    """Owner double that counts nested activations like CudaContext."""
+    def __init__(self):
+        super().__init__()
+        self.active = 0
+
+    def activate(self):
+        from contextlib import contextmanager
+
+        @contextmanager
+        def scope():
+            self.active += 1
+            try:
+                yield self
+            finally:
+                self.active -= 1
+        return scope()
+
+
+def test_public_diagnostics_keep_owner_active_through_sync_and_download(monkeypatch):
+    sim = make_simulation(monkeypatch)
+    sim.ctx, sim._failed = CountingOwner(), None
+    seen = []
+    sim._stream = SimpleNamespace(synchronize=lambda: seen.append(("sync", sim.ctx.active)))
+    expected = np.arange(6, dtype=np.float32).reshape(1, 6)
+
+    def download():
+        seen.append(("download", sim.ctx.active))
+        return expected
+    sim.stepper = SimpleNamespace(moving=SimpleNamespace(download_diagnostics=download))
+    assert sim.moving_diagnostics() is expected
+    assert [name for name, _ in seen] == ["sync", "download"]
+    assert all(active > 0 for _, active in seen) and sim.ctx.active == 0
+
+
 def test_stepper_launches_moving_links_before_static_curved():
     from CelerisLab.lbm.stepper import LBMStepper
     launches = []
     module = SimpleNamespace(get_function=lambda name: lambda *a, **k: launches.append((name, a, k)))
     cfg = SimpleNamespace(streaming="double_buffer", threads_per_block=128, is_d2q9=True,
                           nx=64, ny=32, nz=1)
-    field = SimpleNamespace(ddf_gpu="ddf", temp_gpu="temp", flag_gpu="flag", n_curved=0,
-                            invalidate_host_ddf_cache=lambda: None)
+    curved = SimpleNamespace(**{f"{name}_gpu": name for name in (
+        "fluid_idx", "dir", "q", "rx", "ry", "rz", "fallback_class", "body_id")},
+        surface_velocity=None, surface_velocity_gpu=None, link_exchange_gpu=None)
+    field = SimpleNamespace(ddf_gpu="ddf", temp_gpu="temp", flag_gpu="flag", n_curved=5,
+                            curved=curved, invalidate_host_ddf_cache=lambda: None)
     stepper = LBMStepper(field, module, cfg)
     stepper._launch_force_region = stepper._launch_sensor = lambda *a, **k: None
     stepper.moving = SimpleNamespace(band_gpu="band", geom_gpu="geom", diag_gpu="diag",
                                      slot_debug_gpu=None, n_bodies=1, n_slots=300)
     stepper.step(2, action_gpu="act", obs_gpu="obs")
     names = [name for name, _, _ in launches]
-    assert names == ["MovingCircleLinks", "OneStep"] * 2 and stepper.step_count == 2
+    assert names == ["MovingCircleLinks", "CurvedBoundaryKernel", "OneStep"] * 2
+    assert stepper.step_count == 2
+    assert launches[1][1][0] == "ddf" and launches[3][1][0] == "temp"  # swap between steps
     args, kw = launches[0][1], launches[0][2]
     assert args[:4] == ("ddf", "flag", "band", "geom") and int(args[5]) == 300
     assert kw["grid"] == (3, 1, 1) and kw["block"] == (128, 1, 1)