release: silence runtime logs and stabilize benches

- Fix HAKMEM_LOG gating to use  (numeric) so release builds compile out logs.
- Switch remaining prints to HAKMEM_LOG or guard with :
  - core/box/hak_core_init.inc.h (EVO sample warning, shutdown banner)
  - core/hakmem_config.c (config/feature prints)
  - core/hakmem.c (BigCache eviction prints)
  - core/hakmem_tiny_superslab.c (OOM, head init/expand, C7 init diagnostics)
  - core/hakmem_elo.c (init/evolution)
  - core/hakmem_batch.c (init/flush/stats)
  - core/hakmem_ace.c (33KB route diagnostics)
  - core/hakmem_ace_controller.c (ACE logs macro → no-op in release)
  - core/hakmem_site_rules.c (init banner)
  - core/box/hak_free_api.inc.h (unknown method error → release-gated)
- Rebuilt benches and verified quiet output for release:
  - bench_fixed_size_hakmem/system
  - bench_random_mixed_hakmem/system
  - bench_mid_large_mt_hakmem/system
  - bench_comprehensive_hakmem/system

Note: Kept debug logs available in debug builds and when explicitly toggled via env.

core/hakmem.c

@@ -263,7 +263,7 @@ static void bigcache_free_callback(void* ptr, size_t size) {
 
     // Verify magic before accessing method field
     if (hdr->magic != HAKMEM_MAGIC) {
-        fprintf(stderr, "[hakmem] BigCache eviction: invalid magic, fallback to free()\n");
+        HAKMEM_LOG("BigCache eviction: invalid magic, fallback to free()\n");
         // CRITICAL FIX: When magic is invalid, allocation came from LIBC (NO header)
         // Therefore ptr IS the allocated address, not raw (ptr - HEADER_SIZE)
         // MUST use __libc_free to avoid infinite recursion through free() wrapper
@@ -302,7 +302,7 @@ static void bigcache_free_callback(void* ptr, size_t size) {
             break;
 
         default:
-            fprintf(stderr, "[hakmem] BigCache eviction: unknown method %d\n", hdr->method);
+            HAKMEM_LOG("BigCache eviction: unknown method %d\n", hdr->method);
             free(raw);  // Fallback
             break;
     }