jev-codex-router
Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.
How it uses Jev
Per-call model routing for Codex, driven by Jev (TypeSafe System One).
Getting started
The native model ladder is the policy unless the ChatGPT usage window is exhausted (manual sentinel file, or an automatic flip on a 429 / usage-limit response, which also retries the failed call). OpenAI remains strictly first while the native allowance answers: provider discovery is not even run on healthy turns.
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.