Jev in production › Evaluation and testing
CLI sends a git diff to Jev once as shared state with one question per test, then prints filter arguments for vitest, jest, Playwright, cargo test or go test so only affected tests run; one 110-test run cost $0.00098 (author).
jev-test-filter reads a git diff, asks a model how much that change can alter the outcome of every single test in the repository, and prints the filter arguments your test runner already understands. It hands those arguments to the runner you already use — vitest, jest, node --test, bun test, Playwright, cargo test, go test or rspec — so the run covers the tests the change could plausibly break instead of all of them.
It uses Jev, TypeSafe's System One model: one shared state (the diff), one question per test, one round trip. There is no agent loop and no file reading by the model.
For the project's own README, linking back here: