Codex CLI cannot use Luna Reserve after standard usage limit is exhausted

Open 💬 2 comments Opened Aug 26, 2026 by kubrick06010
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

Summary

Codex CLI appears unable to use the Luna Reserve entitlement after the standard usage limit is exhausted, even though the same ChatGPT account has Luna Reserve available in Codex App.

Reproduction

  1. Use the same ChatGPT Plus account in Codex App and Codex CLI.
  2. In Codex CLI 0.149.1, select model gpt-5.6-luna.
  3. Exhaust the standard 5-hour limit.
  4. Run /status.
  5. Send a minimal prompt such as: Reply only with: OK.

Observed behavior

Codex CLI reports:

5h limit: 0% left
Weekly limit: 73% left

The minimal prompt fails with:

You've hit your usage limit.

At the same time, Codex App, using the same account, shows:

Luna Reserve: 100% remaining

Expected behavior

If Luna Reserve is intended to be available across Codex clients, the CLI should automatically use the reserve after the standard allowance is exhausted, or clearly explain that the entitlement is App-only.

Environment

  • Codex CLI: 0.149.1
  • Plan: ChatGPT Plus
  • Model: gpt-5.6-luna
  • Authentication: ChatGPT account

The CLI already appears to support multiple rate-limit snapshots generically, so this may be an entitlement/request-context parity issue rather than only a /status display issue.

Could you clarify whether Luna Reserve is intentionally limited to Codex App, or whether ChatGPT-authenticated Codex CLI sessions should be able to use the same reserve entitlement?

View original on GitHub ↗

2 Comments

github-actions[bot] contributor · 1 day ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #40744

Powered by Codex Action

kubrick06010 · 1 day ago

Thanks. I reviewed #40744, and I don't believe this is a duplicate.

#40744 is about Codex App Goals: after pausing/resuming a Goal, model/effort switching does not work, which prevents the Goal from continuing in Luna Reserve mode.

This issue is specifically about Codex CLI. There are no Goals involved. With the same ChatGPT Plus account, Codex App shows Luna Reserve: 100% remaining, while Codex CLI 0.149.1 running gpt-5.6-luna has the standard 5h bucket exhausted and rejects even Reply only with: OK with You've hit your usage limit.

So the execution paths are different:

  • #40744: Codex App → Goals → resume/model-switch behavior → Luna Reserve
  • #40939: Codex CLI → standard allowance exhausted → gpt-5.6-luna → no access to Luna Reserve

They may share an underlying Luna Reserve entitlement/routing problem, but #40744 does not cover CLI behavior or CLI/App entitlement parity. I'll keep this open unless maintainers confirm that Luna Reserve is intentionally App-only or that both issues have the same underlying fix.