Performance unacceptable
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 25/100
- Issue type
- Bug
- Clarity
- Needs clarification
- Activity status
- Quiet
- Tech stack
- rust
- Domain
- ai, cli, performance
Research direction
Start with the uploaded thread 019fe5fc-ad16-75e0-9613-ec5621ce0401 and the Codex doctor report, then reproduce the behavior on Windows using Visual Studio. Compare the work performed and token usage with the requested simple task; done would require a reproducible improvement in task focus, project-context retention, and performance.
Written by the indexing model from the issue text.
Description
What version of Codex CLI is running?
Latest always
What subscription do you have?
Pro 5x
Which model were you using?
GPT 5.6
What platform is your computer?
Windows
What terminal emulator and version are you using (if applicable)?
Visual Studio
Codex doctor report
the complete report was uploaded through the terminal, the issue is still the same as before, it has become a bit better but still codex is doing just too much overengineering even though it is told not to do that, and even with over-engineering the code still does not work, codex looses track of the bigger picture and than does things and implements code that is absolutely stupid, you guys have to solve this, Codex just burned through 40% of weekly usage for one simple task and this is something that is super annoying, what do i pay you guys for?
What issue are you seeing?
Performance issues, doing work simply to burn through tokens and not delivering a good result.
What steps can reproduce the bug?
Uploaded thread: 019fe5fc-ad16-75e0-9613-ec5621ce0401
What is the expected behavior?
A smart system that understands this the bigger picture of a project? I have build an extra brain so Codex is getting smarter over time but this should not be my work it should be your work to make the system smarter and know things in a bigger sense. it simply bad that codex does not know what it did 5min ago
Additional information
No response
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.5k
- Avg merge
- 1m
- Merged PRs (30d)
- 1k
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from openai/codex
-
enhancement remote
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
bug CLI windows-os
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
-
macOS sandbox blocks hw.optional.arm64 sysctl, causing Flutter to misdetect Apple Silicon as x64 Openbug CLI sandbox
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
-
bug CLI TUI
Difficulty 2/5 1-3 hours Newbie friendliness 90/100
-
CLI config enhancement skills
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 86/100
kwakseongjae/auto-hwp#319 ·
-
area:cli bug filter-quality good first issue priority:medium
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
-
Difficulty 1/5 Under an hour Newbie friendliness 72/100
bevyengine/bevy#25861 ·
-
comp-datalake
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
ClickHouse/ClickHouse#121222 ·
-
A-linter
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
oxc-project/oxc#26863 ·