Skip to content

Make /review configurable to specify number of issues #5547

Open

Description

@guidedways

What feature would you like to see?

Not a feature request (unless there's room to improve)

/review is just amazing. The way it's been implemented to work in a separate isolated context (with its own window) is praiseworthy; and the way it performs an isolated review is just how it should be. Thank you!

The way it walks through the code, scrutinizing every line, every character modified, every input combination of every function is amazing. Sure, it rarely flags non-issues but only rarely.

Excellent work on this guys, please don't take this feature away. I'd say this one feature alone justifies the cost for going Pro.

If I could change one thing? That is that /review seems to currently only return a single issue (most of the times a P0 and it'll abruptly stop) - I wish there was at least an option to allow /review to continue hunting for a few more issues and list them all in one go. A single review can take 5 - 15minutes at times, depending upon the complexity of code, but one has to run these back to back when a fix in between was just tweaking one or two lines of code, only to discover from a second review that there's one more place to fix.

Additional information

No response

Activity

  1. github-actions commented on Oct 23, 2025

    @github-actions
    Contributor

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

    Powered by Codex Action

  2. Thanaen commented on Oct 23, 2025

    @Thanaen

    I agree with everything that has been said here!

    In addition to being able to submit multiple suggestions, it would be great to be able to launch a review in non-interactive mode, such as codex review --branch my-feature --base develop, or something like that.

  3. changed the title [-]Praise: /review is excellent[/-] [+]Make `/review` configurable to specify number of issues[/+] on Oct 23, 2025
  4. etraut-openai commented on Oct 23, 2025

    @etraut-openai
    Contributor

    Thanks for the positive feedback! We're glad you like the feature.

    And thanks also for the suggestions. I'm going to change the title of the issue to reflect the enhancement request.

  5. Daanvdplas commented on Feb 9, 2026

    @Daanvdplas

    When does this land? It will greatly improve using codex as reviewer in github integration

  6. deleted a comment from Daanvdplas on Feb 9, 2026
  7. Daanvdplas commented on Feb 11, 2026

    @Daanvdplas

    When can we expect this landing? This really makes us think to getting another agent x github integration if there is no timeline

  8. Watcher3056 commented on Feb 18, 2026

    @Watcher3056

    +1, useless without this.

  9. Daanvdplas commented on Feb 19, 2026

    @Daanvdplas

    @etraut-openai can you put attention to this please?

  10. ehendrix23 commented on Feb 21, 2026

    @ehendrix23

    +1, I keep fixing 1 or 2 and then have it run another review.

  11. deshazer commented on Feb 23, 2026

    @deshazer

    This might help some people. What I do is I paste this prompt into my locally running codex agent. Note: it's important that it have GitHub CLI access to your repo. If you're ok with this level of trust, then ship it. It has worked well for me at least. I go work on other things, and eventually it's done and I can review what it did. YMMV 🤷‍♂️

    TL;DR - it runs a loop where it polls for additional review comments and then fixes them until there are no more comments.

    Run a closed-loop GitHub Codex review remediation cycle for the current branch PR targeting `dev`.
    
    Context:
    
    - You have terminal access and `gh` CLI.
    
    - Do not ask clarifying questions.
    
    - Execute immediately and keep looping until completion criteria are met.
    
    Completion criteria (all required):
    
    1) PR description has Codex 👍 reaction.
    
    2) PR description no longer has Codex 👀 reaction.
    
    3) No unresolved Codex review threads/comments remain.
    
    Rules:
    
    - Poll every 60 seconds.
    
    - Triage only substantive review items (bugs, regressions, security, correctness, tests, perf).
    
    - For each Codex comment:
    
    - If valid: fix it, run relevant tests/lint, commit (Conventional Commit), push.
    
    - If not valid: reply with concise technical rationale and evidence.
    
    - Resolve addressed threads.
    
    - Do not use partial staging.
    
    - Do not amend commits.
    
    - Do not commit secrets.
    
    - Do not stop after one pass.
    
    Required workflow:
    
    1) Discover PR for current branch against `dev`.
    
    2) Enter a 60s polling loop:
    
    - Refresh PR state (including description reactions).
    
    - Fetch unresolved review threads/comments.
    
    - Filter Codex-authored items (e.g. `chatgpt-codex-connector`).
    
    - Process newly found items immediately (fix or reply).
    
    - Push after each fix batch.
    
    3) Continue loop until completion criteria are met.
    
    Reporting format each loop:
    
    - Timestamp
    
    - 👀 present? (yes/no)
    
    - 👍 present? (yes/no)
    
    - New Codex comments found
    
    - Actions taken (fixes, replies, resolved threads)
    
    - Commits pushed (hashes)
    
    Final output:
    
    - “Codex review loop complete”
    
    - PR URL
    
    - Final unresolved Codex thread count (must be 0)
    
    - Last commits pushed
    
    - `git status --porcelain=v1` output 
    
  12. eddiedozier commented on Mar 1, 2026

    @eddiedozier

    @etraut-openai any update on when we can expect this to land? It would be nice to have this configurable code review option.

  13. serhii-chernenko commented on Apr 6, 2026

    @serhii-chernenko

    Yes, running every time to find new P1s is insane. Especially when the first attempt displays P1 and P2 (2 findings), but the second attempt does it again. Why not use P1 + P1 the first time?

  14. Watcher3056 commented on Apr 6, 2026

    @Watcher3056

    Why we can't just get it to find ALL issues in the single run?

  15. clhereistian commented on Apr 27, 2026

    @clhereistian

    1 - 2 findings at a time will never be useful to any of my processes. in the real world, who does a Pr review, finds several P1 findings, and only reports 1-2 of them, saving the rest for after the author fixes one issue? It's problematic for many reasons. I've been forced to remove codex from my pipeline and rely on other tools.

  16. wcmultishipping commented on May 2, 2026

    @wcmultishipping

    +1

    I’ve been stuck in a push/review loop for hours. So frustrating 😭

  17. lostincomputer commented on May 6, 2026

    @lostincomputer

    Does anybody how under what conditions Codex limits the findings it returns? I'm worried about this issue, but I can't reproduce it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    code-reviewIssues relating to code reviews performed by codexenhancementNew feature or request

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions