codex - 💡(How to fix) Fix /goal does not actually complete the goal when doing review loops [4 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#21176Fetched 2026-05-06 06:25:22
View on GitHub
Comments
4
Participants
3
Timeline
10
Reactions
0
Author
Timeline (top)
commented ×4labeled ×3renamed ×2unlabeled ×1
RAW_BUFFERClick to expand / collapse

What version of Codex CLI is running?

0.128

What subscription do you have?

Pro

Which model were you using?

gpt-5.5

What platform is your computer?

No response

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

No response

What issue are you seeing?

I asked it to review an implementation plan and fix any gaps or issues

I wrote the following

/goal review the plan ImplementationPlan.md and fix and gaps and issues that you find, do this in a loop until you find no more gaps and issues that needs fixing

It then claimed the goal was done. After it claimed the goal was done I wrote "Do another review" it found a lot of new issues with the plan.

What steps can reproduce the bug?

Write an implementation plan as an md file

Then write:

/goal review the plan ImplementationPlan.md and fix and gaps and issues that you find, do this in a loop until you find no more gaps and issues that needs fixing

Then:

"Do another review"

It will return found a number of issues that it finds (at least it has done every time I tried)

What is the expected behavior?

It should have finished the goal and done reviews and fixes in a loop until it could not find any more issues.

Additional information

No response

extent analysis

TL;DR

The issue may be resolved by rephrasing the goal command to ensure continuous review and fixing of gaps and issues until no more are found.

Guidance

  • The problem seems to stem from the model's interpretation of the goal command, which may not be looping as intended.
  • Try rephrasing the goal command to explicitly instruct the model to continue reviewing and fixing until no issues are found, such as "/goal review the plan ImplementationPlan.md and fix any gaps and issues that you find, then repeat the review until no more gaps or issues are identified".
  • Verify the issue by testing the rephrased command and checking if the model continues to review and fix gaps and issues in a loop until none are found.
  • Consider providing more specific instructions or constraints within the goal command to help the model understand the desired behavior.

Example

No code snippet is provided as the issue is related to natural language input and model interpretation.

Notes

The effectiveness of the suggested fix may depend on the model's ability to understand and execute the rephrased command correctly. Further testing and refinement of the command may be necessary.

Recommendation

Apply workaround: Rephrase the goal command to explicitly instruct the model to continue reviewing and fixing until no issues are found, as this may help resolve the issue without requiring a version upgrade or other changes.

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

codex - 💡(How to fix) Fix /goal does not actually complete the goal when doing review loops [4 comments, 3 participants]