Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →How to run tests using remote executor.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -81% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -70% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -69% | 0% |
Some Codex integration tests select local, docker, or wine-exec through CODEX_TEST_ENVIRONMENT. The legacy CODEX_TEST_REMOTE_ENV=<container> still selects Docker; otherwise execution is local.
Docker container is built and initialized via ./scripts/test-remote-env.sh
On x86-64 Linux, run Wine exec with bazel test //codex-rs/core:core-all-wine-exec-test --test_output=errors. Temporary blockers belong beside the test in skip_if_wine_exec! calls.
You can list devboxes via applied_devbox ls, pick the one with codex in the name. Connect to devbox via ssh <devbox_name>. Reuse the same checkout of codex in ~/code/codex. Reset files if needed. Multiple checkouts take longer to build and take up more space. Check whether the SHA and modified files are in sync between remote and local.
Other measured skills in the registry, with their headline benchmark lift.