feat: major engine overhaul - scene demo with lighting, sphere, ground

- Scene Demo: cube + sphere + ground plane with proper lighting
- Audio: XAudio2 dynamic loading + WAV playback
- Physics: expanded collision system
- Renderer: improved pipeline with materials
- UI: extended widget system
- VisualScript: enhanced serializer + block interactions
- ASM: optimized math/memory/profiling routines
- Window: mouse input + scroll support

Engine/ASM/memory.asm

@@ -114,7 +114,7 @@ mem_aligned_realloc PROC
     push    rdi
     push    rsi
     push    r12
-    sub     rsp, 40
+    sub     rsp, 56                         ; shadow + 3 saved qwords
 
     mov     rbx, rdx                        ; rbx = new size
     mov     rdi, r8                         ; rdi = alignment
@@ -124,8 +124,11 @@ mem_aligned_realloc PROC
     jz      realloc_alloc
 
     ; 保存旧信息
-    mov     rsi, [rcx - 8]                  ; 原始指针
-    mov     r12, [rcx - 16]                 ; 旧 size
+    mov     [rsp + 32], rcx                 ; 旧对齐指针（即用户数据起始）
+    mov     rax, [rcx - 8]
+    mov     [rsp + 24], rax                 ; 旧原始 malloc 指针
+    mov     rax, [rcx - 16]
+    mov     [rsp + 16], rax                 ; 旧 size
 
     ; 分配新内存
     mov     rcx, rbx
@@ -134,26 +137,26 @@ mem_aligned_realloc PROC
     test    rax, rax
     jz      realloc_failed
 
+    mov     rsi, rax                        ; rsi = 新对齐指针
+
     ; 复制旧数据 (取较小值)
-    mov     rdx, r12
+    mov     rdx, [rsp + 16]                 ; 旧 size
     cmp     rdx, rbx
     jbe     realloc_copy_ok
     mov     rdx, rbx
 
 realloc_copy_ok:
-    mov     rdi, rax                        ; 保存新指针
-    mov     rcx, rax                        ; dst
-    ; rsi = 旧数据起始
-    mov     rsi, [rcx - 8]                  ; 旧原始指针
-    ; 需要获取旧的对齐偏移
-    ; 简化: 直接复制
+    ; fast_memcpy(dst, src, count): rcx=dst, rdx=src, r8=count
+    mov     rcx, rsi
+    mov     r8, rdx
+    mov     rdx, [rsp + 32]                 ; 旧对齐指针
     call    fast_memcpy
 
-    ; 释放旧内存
-    mov     rcx, rsi
+    ; 释放旧内存（使用原始 malloc 指针）
+    mov     rcx, [rsp + 24]
     call    mem_aligned_free
 
-    mov     rax, rdi                        ; 返回新指针
+    mov     rax, rsi                        ; 返回新指针
     jmp     realloc_done
 
 realloc_alloc:
@@ -166,7 +169,7 @@ realloc_failed:
     xor     rax, rax
 
 realloc_done:
-    add     rsp, 40
+    add     rsp, 56
     pop     r12
     pop     rsi
     pop     rdi