Merge remote-tracking branch 'origin/master' into claude/issue-73

# Conflicts:
#	interfaces/Crafter.Graphics-Mesh.cppm

interfaces/Crafter.Graphics-ImageVulkan.cppm

@@ -75,9 +75,12 @@ export namespace Crafter {
         VkImage image;
         VkDeviceMemory imageMemory;
         VulkanBuffer<PixelType, true> buffer;
-        // Lives until the compressed Update path's cmd buffer completes.
-        // Same lifetime contract as Mesh::compressedStaging — caller must
-        // not destroy / re-Update before the submit fence is signaled.
+        // Transient host-visible staging for the compressed Update path. Same
+        // lifetime contract as Mesh::compressedStaging: the compressed Update
+        // releases it via DeferredClear() right after recording the decompress,
+        // so the fence-keyed deletion queue (#101/#102) frees it once that
+        // submit's frame has cleared instead of pinning it for the image's life.
+        // Between Updates the handle is null; the next Update's Resize re-creates it.
         VulkanBuffer<std::byte, true> compressedStaging;
         VkImageView imageView;
         VkDescriptorImageInfo descriptor;
@@ -299,6 +302,16 @@ export namespace Crafter {
                 VK_PIPELINE_STAGE_2_COPY_BIT,
                 VK_ACCESS_2_TRANSFER_READ_BIT);
 
+            // Compressed staging is read only by the decompress recorded above;
+            // the buffer→image copy below reads `buffer` (the decompress dst),
+            // never this. Release it to the fence-keyed deletion queue
+            // (#101/#102) now instead of pinning host-visible memory for the
+            // image's whole life. The recorded vkCmdDecompressMemoryEXT still
+            // references compressedStaging.address, so it must outlive this
+            // submit — which the queue guarantees by retiring the allocation
+            // only after framesInFlight frames (i.e. after the submit's fence).
+            compressedStaging.DeferredClear();
+
             // Continue with the existing buffer→image upload + layout transitions.
             // We've already inserted the decompress→transfer-read barrier,
             // so we skip the FlushDevice host-write barrier the regular Update

interfaces/Crafter.Graphics-Mesh.cppm

@@ -83,12 +83,13 @@ export namespace Crafter {
         // Lifetime contract matches vertexBuffer/indexBuffer: must stay
         // alive until the build submitted on `cmd` completes.
         VulkanBuffer<RTAabb, false> aabbBuffer;
-        // Lives until the cmd buffer issued by the compressed Build path
-        // completes execution. Kept as a member so the recorded
-        // vkCmdDecompressMemoryEXT references valid memory until the queue
-        // submit signals — caller must not re-Build or destroy the Mesh
-        // before that submit's fence is signaled (same contract as the
-        // existing uncompressed path).
+        // Transient host-visible staging for the compressed Build path. Kept as
+        // a member only so the recorded vkCmdDecompressMemoryEXT has a stable
+        // address to reference; the compressed Build releases it via
+        // DeferredClear() right after recording the decompress, so it is freed
+        // by the fence-keyed deletion queue (#101/#102) once that submit's frame
+        // has cleared — no longer pinned for the mesh's life. Between Builds the
+        // handle is null; the next Build's Resize re-creates it.
         VulkanBuffer<std::byte, true> compressedStaging;
         VkAccelerationStructureGeometryTrianglesDataKHR blasData;
         VkAccelerationStructureGeometryKHR blas;

interfaces/Crafter.Graphics-PipelineRTVulkan.cppm

@@ -103,7 +103,30 @@ export namespace Crafter {
             hitRegion.size = hitGroups.size() * sbtStride;
 
             std::size_t bufferSize =  hitRegion.deviceAddress + hitRegion.size;
-            sbtBuffer.Create(VK_BUFFER_USAGE_2_SHADER_BINDING_TABLE_BIT_KHR | VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT, VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT, bufferSize);
+            // The SBT is written once here (the memcpys below) and read by the
+            // GPU on every vkCmdTraceRaysKHR for the pipeline's lifetime — the
+            // textbook write-once/read-many buffer (issue #72). Get it into
+            // device-local memory so trace dispatches read raygen/miss/hit
+            // records out of VRAM instead of over PCIe from system RAM.
+            //
+            // Route the placement through #89: when a DEVICE_LOCAL|HOST_VISIBLE
+            // type exists (ReBAR/UMA, or a BAR window — the SBT is tiny so the
+            // window budget is never the constraint), prefer DEVICE_LOCAL on top
+            // of the required HOST_VISIBLE so the allocation lands in device
+            // memory we can still map. The one-time memcpy goes write-combined
+            // over PCIe (write-only, sequential — ideal); GPU reads then hit
+            // local VRAM. When no combined type exists at all (no spec
+            // guarantee), PreferDirectDeviceWrite returns false and the preferred
+            // hint is dropped, so GetMemoryType falls back to plain HOST_VISIBLE
+            // (current behaviour, the per-trace PCIe read) — the cheaper fallback
+            // the issue blesses while staging isn't wired here.
+            //
+            // Either way the buffer stays mapped, and the FlushDevice below gates
+            // its flush on the *chosen* memory type's flags (issue #60), so a
+            // direct-write type lacking HOST_COHERENT is still flushed correctly.
+            VkMemoryPropertyFlags sbtPreferred = Device::PreferDirectDeviceWrite(bufferSize)
+                ? VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT : 0;
+            sbtBuffer.Create(VK_BUFFER_USAGE_2_SHADER_BINDING_TABLE_BIT_KHR | VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT, VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT, bufferSize, sbtPreferred);
 
             std::uint8_t* offset = sbtBuffer.value;
             std::uint8_t* handleOffset = shaderHandles.data();