openai / openai/codex

"Ran 5 commands" - Can we not do this? Or make it optional?

Open
#41,238 3 comments 4 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug CLI enhancement TUI
Dominant language
Rust
Stars
125k
Forks
19.4k
PR merge metrics
PR metrics pending

Description

What version of Codex CLI is running?

Latest

What subscription do you have?

Pro

Which model were you using?

No response

What platform is your computer?

No response

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

No response

Codex doctor report

What issue are you seeing?

Codex now ambiguously says "Ran number commands", without giving any information on what those commands are, or why. Firstly, this is annoying, Anthropic did this before they moved to basically showing you absolutely nothing between a prompt and its output, and it's one of the main reasons I hate using their product. They rightfully received a lot of backlash over that.

Can we not move in the same direction as Anthropic where all of the useful feedback from the model is hidden away? Yeah, ctrl+t lets you see the transcript, but its slow to load and spammy. I'd much rather just see the commands scrolling than have them grouped and have no idea what is happening. Or give us a way to toggle it... But I don't like the move toward hiding things from the user. We shouldn't have to sit there toggling back and forth to know what the model is doing.

What steps can reproduce the bug?

See above.

What is the expected behavior?

No response

Additional information

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing the Codex CLI terminal output that renders the "Ran number commands" summary, then compare it with the transcript opened by Ctrl+T. Determine how command output is grouped and identify the smallest user-visible behavior that would show commands directly or provide a toggle; done means the change is observable during command execution and does not require switching to the transcript.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
cli
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
52/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.