openai / openai/codex

Corrupted output in final response

Open
#43,546 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug CLI model-behavior
Dominant language
Rust
Stars
125k
Forks
19.4k
PR merge metrics
PR metrics pending

Description

What version of Codex CLI is running?

codex-cli 0.153.4

What subscription do you have?

Pro

Which model were you using?

gpt-5.6-sol

What platform is your computer?

Microsoft Windows NT 10.0.26200.0 x64

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

WSL 2.0

What issue are you seeing?

I see corrupted output in the final response after a coding session with delegates that seems to have succeeded successfully. The model seems unsure whether it is in the reasoning or final channel.

What steps can reproduce the bug?

Uploaded thread: 01a07a69-1d05-77d2-a334-5f3aa243e0e8

What is the expected behavior?

Correct ouput.

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 reviewing the uploaded thread 01a07a69-1d05-77d2-a334-5f3aa243e0e8 and reproducing the final-response corruption with codex-cli 0.153.4 on Windows through WSL 2. The issue is done when a coding session with delegates produces correct final output without mixing reasoning and final channels.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
cli
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.