# Development

## Code map
- `facts.py`: pure game-state parsing and arithmetic.
- `brain.py`: policy entry point; dispatch, navigation, shops, and minigames.
- `policy/combat.py` and `policy/selection.py`: combat and selection proposals.
- `policy/context.py`: shared `Decision`, pending actions, and session-owned `PolicyContext`.
- `run.py`: observe–decide–act loop, captures, and session attribution.
- `run_state.py`: reported run identity and combat-pile provenance; see `docs/RUN_STATE.md`.
- `sts2.py`: local game HTTP client. `jev.py`: TypeSafe model client and gates.
- `migrate.py`: dataset migration and integrity checks.
- `CONTEXT.md`: domain terms. `docs/POLICY.md`: policy boundaries. `docs/DATASET.md`: dataset schema and limits.
- `docs/research/11-prototype-hardening.md`: audited findings and the proposed development order.
- Treat historical claims in `docs/DESIGN.md` as context; verify against current code.

## Checks
Use Python 3.10+ from the repository root. Core Python code uses the standard library.

```sh
python3 test_facts.py && python3 test_brain.py && python3 test_run.py
python3 migrate.py --check-only
bash -n eval_batch.sh ab_card_skip.sh
```

Tests are executable scripts, not unittest/pytest suites. They need no model or game connection.
Some checks read local captures and game history when available.
Prefer integration/end-to-end checks; keep only essential regression tests and use temporary isolated probes for unit-level edge cases.

## Invariants
- Execute one game action, then read a fresh observation. Card indices can change after each action.
- Keep policy memory session-owned. Proposals do not record execution; reconcile accepted requests with fresh observations.
- Compute arithmetic and legality in code, not in Jev. Confidence does not prove correctness.
- Keep deterministic fallbacks usable with `client=None`. Test model paths with stubs.
- Preserve session/step attribution. Run outcomes are not per-decision correctness labels.
- Split evaluation data by run, not by decision row.

## Safety and scope
- Default to offline tests. Ask before live game actions, model calls, or evaluation batches.
- `run.py --dry-run` sends no action POSTs; state/identity reads, model calls, and logs still run.
- The runner ignores legacy `deck.json`. Combat-pile evidence is session-local and is not the persistent deck.
- Never print or commit credentials. Do not read secret files for development checks.
- Do not rebuild `dataset/`, change captures, or edit `vendor/` unless the task requires it.
- `migrate.py --verify` rebuilds data; use `--check-only` for routine verification.
- Keep code simple and lean. Use `docs/` as the detailed reference for humans and agents.
- Keep changes focused. Prefer `jj status` and `jj diff`; do not create commits unless asked.

## Pi
Project prompts live in `.pi/prompts/`: `/sts2-check` and `/sts2-review`.
They provide instructions, not a sandbox or permission enforcement.