jev-guard

# Jev Guard fix-under-watch Jev Guard runs the test suite in `project/` on every edit and asks Jev (TypeSafe's System One model) to judge each change: how much closer to the goal, how risky, how confident. The pane draws those as meters, a history chart and a run log. The goal is to make the tests pass and the verdict go green with a fix Jev trusts. ## The loop 1. Edit `project/score.js` (that's the work). Jev Guard auto-judges on each edit, or step it with "Judge now" / `node "$JEV_DSH/toolchain/check.mjs"`. 2. Watch the meters: `toward` (progress), `trust` (Jev's confidence in the exact change), `risk` (a red flag on a shaky edit). The run log shows PASS/FAIL per test run with what changed. 3. Iterate until `node project/test.js` prints `ALL TESTS PASS` and the viewer verdict reads as a passing/green judgment. ## Reading Jev Jev's scores are layered on *real test results*: the suite is the ground truth, Jev is the overlay. A focused, honest fix — correct logic, nothing special-cased, nothing extra — is what reads as high `trust` / low `risk`. A hack that greps the test names or returns constants will pass the tests but Jev's `risk` meter will go red. ## Verifying - `node "$JEV_DSH/toolchain/check.mjs"` validates the workspace (goal.json + project/test.js present and runnable). - `node project/test.js` is the real check: exit 0 + `ALL TESTS PASS` is done. - Watch the viewer verdict flip to a green/god-met judgment, not just the tests passing. ## Driving Je...