codex - 💡(How to fix) Fix Duplicated output [4 comments, 4 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#18121Fetched 2026-04-17 08:32:31
View on GitHub
Comments
4
Participants
4
Timeline
12
Reactions
1
Timeline (top)
commented ×4labeled ×4unlabeled ×2closed ×1
RAW_BUFFERClick to expand / collapse

What version of Codex CLI is running?

0.121.0

What subscription do you have?

Pro

Which model were you using?

gpt-5.4-xhigh

What platform is your computer?

Ubuntu

What terminal emulator and version are you using (if applicable)?

No response

What issue are you seeing?

<img width="2560" height="356" alt="Image" src="https://github.com/user-attachments/assets/78683818-7732-42e4-93c7-4583fcc5a1bc" />

It often duplicates output

What steps can reproduce the bug?

just work.

What is the expected behavior?

No response

Additional information

No response

extent analysis

TL;DR

The issue of duplicated output in Codex CLI 0.121.0 with the gpt-5.4-xhigh model on Ubuntu may require adjusting the model or CLI settings to prevent duplication.

Guidance

  • Verify Model Settings: Check if the gpt-5.4-xhigh model has any specific settings or configurations that could be causing the output duplication.
  • Check CLI Options: Look into the Codex CLI documentation for any options or flags that might control or affect output behavior, potentially preventing duplication.
  • Test with Different Model: Try using a different model with the Codex CLI to see if the issue persists, which could help determine if the problem is model-specific.

Notes

The provided information lacks specific details about the expected behavior and additional context, making it challenging to provide a precise solution. The issue might be related to how the model processes input or an undocumented feature of the CLI.

Recommendation

Apply workaround: Given the lack of detailed information and the specificity of the issue to the gpt-5.4-xhigh model, attempting to adjust model settings or using a different model as a workaround seems like the most viable next step.

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