feat: enforce held-out benchmark workflow

feat: add model quality workflow gate

fix: align test_ab_ui_pipeline.py with single return value of process_image

fix: resolve Windows cp1252 terminal encoding in test_all.py with 100% pass rate

feat: add master system verification test suite test_all.py with 100% pass rate and exit code 0

feat: complete Phase 6 Stage II Transformer fine-tuning setup and verification with exit code 0

feat: verify Phase 7 A/B Model & Preset Pipeline with exit code 0

feat: verify Phase 4 Dataset Expansion & Game Character Mixing with exit code 0

docs: update handover.md and add dynamic fallback verification to quantize_onnx_static.py

fix: remove static quantization from Dockerfile build and add fail-safe ONNX loader

fix(hf): integrate Static INT8 ONNX build into Dockerfile and fix thread state guard in app.py

feat: implement static INT8 ONNX quantization tool & UI model engine selector

fix: resolve B11 (offline setuptools wheel build via base64 encoding and Dockerfile update) and finalize Task 11 bug fixes

fix: update download_weights.py to use stable github release urls

fix: resolve Hugging Face deployment crashes and dependency conflicts

feat: complete custom training pipeline bugfixes, dataset crawling, and validation

CPU optimizations and UI defaults

Optimize CPU performance: add INT8 quantization, set default lightweight detector, disable heavy upscaling by default

fix: make CPU training run (disable mkldnn, cv2 filter2D, num_block=6, gt=256, LMDB) + handover

perf: maximize CPU/RAM/disk for CPU training (LMDB, avx512, larger batch/queue)

feat: optimize CPU performance and add agents rules

feat: add Google Colab GPU notebook, ONNX export script, and pipeline ONNX optimization

style: move utility and test scripts into tools/ folder to clean up root directory