feat(phase-e-4-a): alpha_window_push circular-buffer kernel + GPU test

Phase E.4.A Task 6: tiny CUDA kernel that pushes a state[state_dim]
vector into slot `head_idx` of a circular window buffer
[K, state_dim]. Host tracks head_idx and zeros buffer on episode
reset. This is the GPU-side append primitive that the smoke
binary's per-step inference will call (T7) before Mamba2 over the
buffer (T8).

GPU smoke (alpha_window_push_circular_writes_to_indexed_slot):
writes state_a at slot 0, state_b at slot 2, verifies non-targeted
slots stay zero. PASS.

docs/isv-slots.md: documents kernel as slot-agnostic per
kernel-audit-doc hook requirement.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

crates/ml/build.rs

@@ -1621,6 +1621,10 @@ fn main() {
         // atom support, single network, no per-branch / Adam machinery —
         // testing the calibration hypothesis from `pearl_action_pruning_falsified`.
         "alpha_c51.cu",
+        // Phase E.4.A.6 (2026-05-15): circular-buffer push kernel for the
+        // sliding-window state input to the Mamba2 temporal encoder
+        // (Mamba2Block from ml-alpha).
+        "alpha_window_push.cu",
     ];
 
     // ALL kernels get common header (BF16 types + wrappers)