Issue Station
Sign In
Tools hereToolbox

codex - 💡(How to fix) Fix CLI/TUI: support editing an already-sent user message and regenerating downstream turns [2 comments, 1 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#17243•Fetched 2026-04-10 03:43:28
View on GitHub
Comments
2
Participants
1
Timeline
6
Reactions
0
Author
astomodynamicsastomodynamics
Participants
astomodynamicsastomodynamics
Timeline (top)
labeled ×3commented ×2closed ×1
RAW_BUFFERClick to expand / collapse

What variant of Codex are you using? CLI

What feature would you like to see? Support editing an already-sent user message in Codex CLI/TUI, with the same semantics as VS Code Codex and ChatGPT web: edit a previous user turn, submit the edited text, and regenerate downstream turns from that point. This is not history recall, rollback/backtrack, or fork/branch. It is true post-send message editing.

Additional information This would make CLI prompt iteration consistent with other Codex/OpenAI surfaces. The closest existing issue I found is about branching from a previous message, but that is a different workflow from editing an existing sent message in place and regenerating from there. If full support is too large initially, even a first version limited to editing the most recent user message would help.

extent analysis

TL;DR

Implementing support for editing already-sent user messages in Codex CLI/TUI would require modifying the existing message handling and regeneration logic.

Guidance

  • Identify the specific requirements for editing sent messages, including how to store and manage message history, and how to regenerate downstream turns.
  • Determine the technical feasibility of implementing this feature, considering the existing architecture and limitations of the Codex CLI/TUI.
  • Consider starting with a limited version of the feature, such as editing only the most recent user message, to test and refine the implementation.
  • Evaluate how the edited message will be handled in terms of conversation state and context, to ensure consistency with other Codex/OpenAI surfaces.

Notes

The implementation details of this feature are not provided, and the technical requirements may vary depending on the specific Codex CLI/TUI architecture and dependencies.

Recommendation

Apply workaround: Implement a basic version of the feature, limited to editing the most recent user message, to test and refine the implementation, and then expand to support editing of earlier messages.

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…
#retriever error#indexing error#inference speed#output truncation#response parsing

Still need to ship something?

×6

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

Back to top recommendations

TRENDING