Constrain v7 to prevalidated grounded wording choices

Add deterministic untrusted-choice guard and fresh v6 gate

Replace brittle multi-field output with SAMS v5 wording selector

Rebuild SAMS v4 bounded selector and strict 40-case gate

Resume v3 from preserved adapter and apply 90 percent adapter diagnostic gate

Deploy SAMS v3 targeted quantization-robust retraining

Remove obsolete v1 action policy

Replace rejected v1 with bounded SAMS v2 training pipeline

Preserve adapter checkpoint and fix GGUF export dependency

Remove duplicate runtime data

Stage validated dataset and base model during free build

Fix model download configuration

Handle blocked optional reference downloads

Upload final artifacts before completing

Add Dockerfile

Add app.py

Add tests/test_dataset.py

Add trainer/run_pipeline.py

Add trainer/merge_and_export.py

Add trainer/evaluate.py

Add trainer/train.py

Add trainer/validate_dataset.py

Add trainer/build_dataset.py

Add trainer/download_sources.py

Add trainer/common.py

Add trainer/__init__.py

Add knowledge/altitude_policy.json

Add .gitignore

Add README.md

Add training dependencies

initial commit