vgpu in-guest producer in-tree, release CI, flexible vmie discovery

- src/si/vgpu-stream: in-guest vgpu producer built as a Windows cross-compiled target (if(WIN32))
- .gitea: release workflow — cross-build the agent and build/publish the deb against system vmie
- cmake/makefile: resolve vmie from a source tree (LIBVMIE_PATH) or installed libvmie-dev

src/si/vgpu-stream/win32/cursor.h

@@ -0,0 +1,26 @@
+#ifndef VGPU_CURSOR_H
+#define VGPU_CURSOR_H
+
+/* cursor.h — win32 GDI cursor sample/compose onto a tight BGRA frame. */
+
+#include <stdint.h>
+#include "ctx.h"           /* win32 vgpu_ctx (cursor state) */
+
+/* Sample the current cursor (position/shape) into ctx->cursor.
+ * Returns 1 if anything changed since last sample, else 0. */
+int  cursor_sample(vgpu_ctx* ctx);
+
+/* Resolve a HCURSOR to a VGPU_CURSOR_ID_* by comparing against the system cursor table
+ * (LoadCursor(NULL, IDC_*) loaded once on first use). Returns VGPU_CURSOR_ID_UNKNOWN for
+ * custom cursors. Not hot-path: called only under the shape-change gate. */
+int  cursor_resolve_id(HCURSOR hc);
+
+/* Extract glyph/hotspot/dims for hc into ctx->cursor, resolve its cursor_id, and record it as
+ * the current handle. For backends that source position elsewhere (DDA from frame info) and
+ * only need the shape on a shape-change gate. Caller serializes ctx->cursor writes. */
+void cursor_apply_shape(vgpu_ctx* ctx, HCURSOR hc);
+
+/* Alpha/AND-XOR compose the sampled cursor onto a tight BGRA frame. */
+void cursor_draw(vgpu_ctx* ctx, uint8_t* bgra, uint32_t width, uint32_t height);
+
+#endif /* VGPU_CURSOR_H */