Perf: Optimize macOS screen capture with CGDisplayStream

Core optimization:
- Use CGDisplayStream instead of per-frame CGDisplayCreateImage
- Push model: CPU sleeps when screen is static (condition_variable wait)
- IOSurface capture avoids expensive image creation per frame
- ~47% CPU reduction during active remote desktop (45% → 24%)

Additional optimizations:
- vImageVerticalReflect (SIMD) replaces manual row-by-row flip
- Cache CGColorSpaceRef to avoid per-frame creation/release
- Cache tempBuffer to avoid per-frame memory allocation
- Throttle getCursorTypeIndex to 250ms (Accessibility API is expensive)

Bug fixes:
- Fix unreliable screen capture permission check (use actual capture test)
- Improve permission logging

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

macos/ScreenHandler.h

@@ -3,6 +3,7 @@
 #import <CoreGraphics/CoreGraphics.h>
 #import <dispatch/dispatch.h>
 #import <IOKit/pwr_mgt/IOPMLib.h>
+#import <IOSurface/IOSurface.h>
 #import "../client/IOCPClient.h"
 #import "../common/commands.h"  // QualityLevel, QualityProfile, ALGORITHM_*
 #include <vector>
@@ -11,6 +12,7 @@
 #include <thread>
 #include <cstdint>
 #include <memory>
+#include <condition_variable>
 
 // Forward declarations
 class IOCPClient;
@@ -118,6 +120,7 @@ private:
     std::vector<uint8_t> m_prevFrame;
     std::vector<uint8_t> m_currFrame;
     std::vector<uint8_t> m_diffBuffer;
+    std::vector<uint8_t> m_tempBuffer;  // 临时缓冲区，避免每帧分配
 
     // Quality settings
     std::atomic<uint8_t> m_algorithm;
@@ -133,4 +136,25 @@ private:
 
     // Power management: prevent display sleep during remote desktop
     IOPMAssertionID m_displayAssertionID;
+
+    // Cached color space (avoid per-frame creation)
+    CGColorSpaceRef m_colorSpace;
+
+    // CGDisplayStream (efficient continuous capture)
+    CGDisplayStreamRef m_displayStream;
+    dispatch_queue_t m_streamQueue;
+    IOSurfaceRef m_latestSurface;
+    std::mutex m_surfaceMutex;
+    std::condition_variable m_surfaceCond;
+    std::atomic<bool> m_hasNewFrame;
+
+    // Initialize/cleanup display stream
+    bool initDisplayStream();
+    void cleanupDisplayStream();
+
+    // Process frame from IOSurface (called by stream callback)
+    void processIOSurface(IOSurfaceRef surface);
+
+    // Capture from IOSurface to buffer (with vertical flip)
+    bool captureFromIOSurface(IOSurfaceRef surface, std::vector<uint8_t>& buffer);
 };