Add SSIM structural comparison (perceptual score + changed regions)

[JE-Chen]

Perceptual screen comparison that reports what changed. Pixel diff (diff_screenshots) fires on a one-pixel shift; a colour histogram (detect_drift) is blind to layout. SSIM is the standard visual-regression metric — tolerant of small illumination changes, sensitive to structural change (edited text, moved/missing elements).

• ssim_compare (AC_ssim_compare): mean SSIM 0..1 (1.0 = identical) between a reference and the live screen (or a given image). ignore=[[x,y,w,h]] masks live clocks / cursors. Raises ValueError on size mismatch.
• ssim_changed_regions (AC_ssim_changed_regions): boxes of the regions where local 1 - SSIM exceeds threshold, connected blobs >= min_area, largest first.
• Pure NumPy + OpenCV (no scikit-image dependency); 11x11 Gaussian-windowed SSIM, NaN-free. Injectable image pair → headless-testable on synthetic arrays.
• DRY: extracted a shared cv2_utils.blobs.connected_boxes helper, now used by both the colour-region locator and SSIM change detection.
• Wired through all 5 layers (core/facade/executor/MCP/Script Builder) + headless test + EN/Zh docs + WHATS_NEW. Qt-free.

[codacy-production]

Not up to standards ⛔

_{NEW Get contextual insights on your PRs based on Codacy's metrics, along with PR and Jira context, without leaving GitHub. Enable AI reviewer
TIP This summary will be updated as you push new changes.}

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube Cloud