CLAUDE.md

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Overview

A Hugging Face Spaces app that translates English text to 22 production-ready languages (BLEU 35+ both directions, Section A.10) from Google's [MADLAD-400](https://arxiv.org/pdf/2309.04662) 3B Seq2Seq model. Built with Gradio and deployed on HF Spaces. Falls back to CPU with a warning when no CUDA GPU is available.

## Commands

```bash
# Setup
uv venv --python 3.12
source .venv/bin/activate
uv pip install -r requirements.txt

# Run (launches on http://localhost:7860)
python app.py

# Lint and format
ruff check .
ruff format .

# Type check
ty check

# Test
pytest                     # all tests (slow tests require CUDA + model download)
pytest -m "not slow"       # fast tests only
pytest -m slow             # model tests only (CUDA only)
```

## Architecture

**`app.py`** — Single-file application with a Google Translate-style layout: a centered language bar ("English → [Target]") above side-by-side input/output text areas and a translate button. Uses `@lru_cache` for lazy loading of the `google/madlad400-3b-mt` tokenizer and model (no download on import). Uses `float16` on CUDA, `float32` on CPU. MPS is not supported (produces garbage output with T5 models). Translation prepends a language token with a space to the input text (e.g., `<2fr> Hello`) before tokenization and generation. The `@spaces.GPU` decorator allocates GPU on HF Spaces infrastructure.

**`langmap/`** — Package with `langid_mapping.py`, a hand-maintained dictionary mapping 22 Tier 1 production-ready language tokens (BLEU 35+ both directions, Section A.10) to human-readable language names. Available languages at runtime are the intersection of this mapping and the model's vocabulary.

**`tests/`** — 31 tests (21 fast, 10 slow). `test_langmap.py` has 8 fast tests for language mapping validation. `test_app.py` has 13 fast tests (signatures, device fallback, UI layout) and 10 slow tests (translation with various parameters, language mapping). Slow tests require CUDA and model download; auto-skipped without CUDA.

## Tooling

- **uv** — Python package manager. Used for venv creation and dependency installation from `requirements.txt`. No `pyproject.toml`; `requirements.txt` remains the single source of truth (required by HF Spaces).
- **Ruff** — linter and formatter (`ruff.toml`). Rules: `E`, `F`, `I`, `W`. Line length: 120.
- **ty** — type checker (`ty.toml`). Python 3.12 target.
- **pytest** — test runner (`pytest.ini`). Custom `slow` marker for CUDA-dependent tests.