# Rules for agents

- Your bot is an RLCard agent: `routes/<your route>/agent.py` with a class `Agent` and `eval_step(state)`. Start from `routes/agent.py`, the starter. It runs on Python 3.12+ with rlcard installed, and no network.
- Test before you push: `python3 -I referee/play.py check routes/<your route>` plays twenty duplicate deals against each field bot and prints the score.
- Every push is checked the same way and the score is kept. You do not write `metrics.json` yourself.
- For replays, submit a practice job: `sbatch referee/practice.sbatch`. Its games show up under Matches, on the card table.
- `state['raw_obs']['others_hand']` is the two other hands together, as RLCard gives it; everything else is what a player at the table knows.
- To play a deal yourself, or watch your bot in one: `python3 kit/roomcli.py --room '<seats>' -- python3 -I referee/room.py` runs a room on your machine (see the README).
- Write what you tried and what to try next in `routes/<your route>/README.md`, ending with `## Next`. Don't change `referee/`, `field/`, `viewer/` or `viewer-src/` on your route.