# AGENTS.md

## Environment

This project uses a conda environment named `longitudinal-313` (Python 3.13).

Activate with:

```bash
source /opt/conda/etc/profile.d/conda.sh && conda activate longitudinal-313
```

Key packages: torch 2.14 (+cu126), torchvision, monai 1.6 (pip, Pipeline C), numpy, scipy, pandas, scikit-learn, scikit-image, matplotlib, nibabel, SimpleITK. Registration toolkits (benchmark, see REGISTRATION_BENCHMARK.md): `itk` + `itk-elastix`, `antspyx`, niftyreg 1.5.69 (`conda install -c conda-forge niftyreg`, provides `reg_aladin`), plus Docker images `freesurfer/synthmorph` and `vboussot/elastix_impact`.

## Project

Longitudinal (repeated-measures) analysis of medical imaging data. Repo is at an early stage — see README.md for any project notes.

**All path config lives in `config/paths.json`** — the external data roots the code reads or writes (`data`, `lee`, `m6`, `ntuh_register_inv`). Code resolves them through `src.common` (`PATHS` dict, `path(name)` lookup, `DATA`/`d()` for `data/...` paths). To move any dataset, only edit `config/paths.json`; the repo root is derived from the code location (override with `LONGITUDINAL_ROOT` if needed).

## Conventions

- All Python commands must run inside the `longitudinal-313` conda environment.
- GPU is available (CUDA 12.6); use `torch.device('cuda')` when appropriate. Multi-GPU stages of Pipelines A and C run via `torchrun --standalone --nproc_per_node N` (rank = GPU).
- No lint/test tooling is configured yet; run scripts directly with `python <script>` from the repo root.