# Repository Guidelines

## Project Structure & Module Organization

- `src/leld.py` is the primary entrypoint (X11 STT daemon).
- `src/recorder.py` handles audio capture using PortAudio via `sounddevice`.
- `src/leld.py` owns Whisper setup and transcription.
- `src/aiprocess.py` runs the in-process Llama-3.2-3B cleanup.

## Build, Test, and Development Commands

- Install deps: `uv sync`.
- Run daemon: `uv run python3 src/leld.py --config ~/.config/lel/config.json`.

System packages (example names): `portaudio`/`libportaudio2`, `libayatana-appindicator3`.

## Coding Style & Naming Conventions

- Shell scripts use Bash with `set -euo pipefail`.
- Indentation is two spaces; prefer lowercase variable names for locals and uppercase for environment-configured values.
- Keep functions small and focused; add comments only where the intent is not obvious.

## Testing Guidelines

- No automated tests are present.
- If you add tests, include a brief note in `AGENTS.md` with the runner command and test location.

## Commit & Pull Request Guidelines

- Commit history is minimal and does not establish a convention; use short, imperative messages (e.g., "Add device override").
- PRs should include a concise description, repro steps, and any environment variables or dependencies added.

## Configuration Tips

- Audio input is configured via the `recording.input` field in `config.json`.
- STT model and device are configured via the `stt` section in `config.json`.
- LLM model settings are locked; model downloads to `~/.cache/lel/models/`.
- `-v/--verbose` enables verbose logs (including llama.cpp) with `llama::` prefix.