feat(esopull): runtime body sync for EsoPull streaming mode

- New esopull_sync.cu: DecodeCellsToPhysical + EncodePhysicalToCells
  (compact-list mode, ddf_shifting-aware, encode applies collision).
- sync_bodies() now branches for double_buffer vs esopull: decode
  backing layout to physical DDF on GPU -> host patch -> collide +
  encode back to backing layout. No temp_gpu, no full-grid copy.
- 4 new integration tests covering esopull add/remove/cycle/roundtrip.
- ddf_shifting + esopull + sync_bodies jointly verified (1300 steps
  stable after add/remove).
- Bump version to 0.5.0.

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

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

@@ -0,0 +1,81 @@
+// CelerisLab -- step/esopull_sync.cu
+// Compact-list EsoPull decode/encode for runtime body topology sync.
+//
+// Decodes a subset of cells from EsoPull backing layout to physical DDF,
+// or encodes physical DDF back to EsoPull backing layout.
+// Each thread handles one cell from a compact index list.
+//
+// Included by kernel_v2.cu.  No standalone compilation.
+// ============================================================================
+
+#ifndef CELERIS_STEP_ESOPULL_SYNC_CU
+#define CELERIS_STEP_ESOPULL_SYNC_CU
+
+// ---------------------------------------------------------------------------
+// DecodeCellsToPhysical:  backing layout -> physical DDF (compact list)
+//
+// Uses ``t`` as the step count for EsoPull semantic parity decoding.
+// ---------------------------------------------------------------------------
+__global__ void DecodeCellsToPhysical(
+    const fpxx* fi,
+    float* fi_phys,
+    const unsigned int* cell_idx,
+    unsigned int n_cells,
+    unsigned long t)
+{
+    unsigned int tid = threadIdx.x + blockIdx.x * blockDim.x;
+    if (tid >= n_cells) return;
+
+    unsigned long k = (unsigned long)cell_idx[tid];
+    unsigned int x, y; coordinates(k, x, y);
+    unsigned long j[NQ]; compute_neighbors(x, y, j);
+
+    float f[NQ];
+    load_physical_node_esopull(k, fi, j, t, f);
+
+    // DDF-shifting: backing layout stores f-w, unshift to physical for host patch
+#if USE_DDF_SHIFTING
+    #pragma unroll
+    for (int i = 0; i < NQ; i++)
+        f[i] += (float)d_w[i];
+#endif
+
+    for (int i = 0; i < NQ; i++)
+        fi_phys[tid * NQ + i] = f[i];
+}
+
+// ---------------------------------------------------------------------------
+// EncodePhysicalToCells:  physical DDF -> backing layout (compact list)
+//
+// Reads physical (pre-collision) DDF from *fi_phys*, applies collision
+// to produce post-collision DDF, then encodes into the EsoPull backing
+// layout on *fi*.  The backing layout stores post-collision values,
+// matching what store_f_esopull would produce at step *t*.
+// ---------------------------------------------------------------------------
+__global__ void EncodePhysicalToCells(
+    fpxx* fi,
+    const float* fi_phys,
+    const unsigned int* cell_idx,
+    unsigned int n_cells,
+    unsigned long t)
+{
+    unsigned int tid = threadIdx.x + blockIdx.x * blockDim.x;
+    if (tid >= n_cells) return;
+
+    unsigned long k = (unsigned long)cell_idx[tid];
+    unsigned int x, y; coordinates(k, x, y);
+    unsigned long j[NQ]; compute_neighbors(x, y, j);
+
+    float f[NQ];
+    for (int i = 0; i < NQ; i++)
+        f[i] = fi_phys[tid * NQ + i];
+
+    // Collide: physical (pre-collision) -> post-collision
+    float rho_n, ux, uy;
+    compute_rho_u(f, rho_n, ux, uy);
+    collide_dispatch(f, rho_n, ux, uy);
+
+    store_physical_node_esopull(k, f, fi, j, t);
+}
+
+#endif // CELERIS_STEP_ESOPULL_SYNC_CU