Jev dynamically adjusts GPT-6 reasoning effort in Codex
The author automatically switches reasoning effort per step in Codex CLI, lowering it on routine steps to save tokens, and says the overall task runs faster without triggering cache rebuilds.
If this gets traction, I'll open-source it on my GitHub http://github.com/miuuyy (and post again on X to notify). I've been using it for real work in Codex CLI. It uses Codex CLI's experimental per-step settings to change reasoning effort before the next GPT-6 generation. After tool results, Jev gets the task, published reasoning/progress summaries, and the last six tool calls with bounded outputs. It picks an effort level and how long to keep it: 1, 2, 5, or 10 generations. No extra Jev calls during that window. Tool failures or new user input can trigger an earlier reassessment. This version specifically targets GPT-6 Astra. Effort changes use native Codex configuration updates that preserve the existing prompt prefix and cache. No cache rebuild penalty just for changing effort. Jev is fast enough that I don't notice the routing overhead. Lower effort on routine steps saves enough reasoning time to make the overall task faster, while using fewer tokens.