- rewrite docker.sh with gpu default and --no-gpu override
- inject host uid/gid via ASTRAI_UID/GID in train.sh compose()
- filter readonly UID/GID lines when sourcing .env.train
- build image user via USER_UID/USER_GID args matching host uid/gid
- pass all GPUs (count: all) and filter by CUDA_VISIBLE_DEVICES inside the container
- forward NCCL vars through compose environment