codex - 💡(How to fix) Fix Switch model mid-prompt [2 comments, 3 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openai/codex#20842Fetched 2026-05-04 05:09:34
View on GitHub
Comments
2
Participants
3
Timeline
7
Reactions
0
Timeline (top)
labeled ×3commented ×2closed ×1renamed ×1
RAW_BUFFERClick to expand / collapse

What variant of Codex are you using?

CLI

What feature would you like to see?

Add the ability to switch models through /model while a prompt is running such that the next prompt uses a different model especially while queuing prompts one after each other

it would be very useful to be able to switch to a different reasoning effort. For example, if the next prompt should use higher effort.

Additional information

No response

extent analysis

TL;DR

Implementing a model switching feature through the /model command while a prompt is running could be achieved by modifying the CLI to handle concurrent model changes.

Guidance

  • Investigate the current implementation of the /model command to understand how model switching is handled.
  • Consider adding a queueing system to manage prompts and apply model changes between each prompt.
  • Evaluate the feasibility of implementing a dynamic model switching feature without interrupting ongoing prompts.
  • Review the documentation and existing codebase for any existing model management or queueing mechanisms that could be leveraged.

Notes

The exact implementation details are uncertain due to the lack of information about the current Codex CLI architecture and codebase.

Recommendation

Apply workaround: Implement a custom queueing system to manage prompts and model changes, as the current functionality is not available.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING