Doing its own thing again - Same bug from a few weeks ago not fixed!
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 25/100
Research direction
Start by reproducing the behavior in Codex App version 26.727.51351 on macOS using a plan and the rules in Agents.md. Compare the requested narrow change with the agent's invented tests and extra work; done means the agent follows the plan and stops adding unrelated tests or scenarios.
Written by the indexing model from the issue text.
Description
What version of the Codex App are you using (From “About Codex” dialog)?
Version 26.727.51351
What subscription do you have?
Plus
What platform is your computer?
MacOS - Darwin 25.5.0 arm64 arm
What issue are you seeing?
Sol5.6 - High ignores anything regarding focused effort. I even had it audit the issues by scouring the chat and Agents.md, where it agreed it had gone off on its own tangent, ignoring my requests and the rules in Agents.md.
The lovely chat agents on support say thanks for letting us know, but nothing else. Wasted 4 days, 3 resets (built up from before) and regret from Codex!
Gone back to using Claude Code for now; I cannot trust Sol5.6 to actually do what I ask it in a straightforward manner with reliable and believable results.
What steps can reproduce the bug?
Ask it to implement a plan and it will go off making up minute tests, running full tests wasting 1000s of tokens. When asked to stop and cut out behaviour, it just goes again. Strict rules in Agents.md do not stop the behaviour. Unusable because simple code changes seem to be tested to the nth degree, it makes up tests that are not asked for.
What is the expected behavior?
Narrow-focused changes (what it used to do a few weeks ago, not inventing tests and scenarios. Do what the plan asks, not what it thinks. I wouldn't mind, but it wrote the plan!
Additional information
This makes Codex unusable to get simple work done, it needs an urgent fix!
- 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 ·