GPT5-codex taking too much initiative
What version of Codex is running?
0.39.0
Which model were you using?
gpt-5-codex high
What platform is your computer?
WSL version: 2.5.10.0 Kernel version: 6.6.87.2-1 WSLg version: 1.0.66 MSRDC version: 1.2.6074 Direct3D version: 1.611.1-81528511 DXCore version: 10.0.26100.1-240331-1435.ge-release Windows version: 10.0.26100.6584
What steps can reproduce the bug?
- Ask agent to perform a task
- Work on another task manually
- Ask agent to commit
What is the expected behavior?
Agent commits its work only or asks if it should stage/commit all unstaged changes
What do you see instead?
Agent discards your manual work in fear of having done it itself unintentionally
<img width="703" height="155" alt="Image" src="https://github.com/user-attachments/assets/f591ce2a-7e80-4d53-a65e-5950754f0d09" />
Additional information
Apologies if this should not be filed as a bug, let me know if I need to post elsewhere.
This sort of behaviour where the agent performs many tasks outside their given command context seems to be a consistent issue with codex, perhaps more specific to the gpt5-codex models.
In multiple occasions I'll ask it to do 1 thing and it will take massive initiative to undo or perform multiple other tasks beyond what was requested. One request before this one I asked "commit" and it instead went around and applied multiple unsolicited fixes before committing.
This goes beyond executing unsolicited commits and can include writing a bunch of unsolicited code changes or discarding other work done while the agent was working on something.
I have mentioned explicit instructions to avoid this behaviour in my AGENTS.md file - but they do not appear to be properly followed. You may include in AGENTS file: "Only commit when the user explicitly requests you to" or something along the lines of - but if you then ask for one commit during an instance, it appears to take initiative to perform commits after every task for the remainder of the instance.
I understand part of the purpose of the codex-specific models is to be more agentic and self-reliant but I assume this much self-assertion is not intentional as it goes beyond user scope.
5 Comments
I had to stop using the codex model completely after it decided to delete several unrelated files. OAI should roll it back
Facing the same issue as well. Really annoying
For me it went about deleting AGENTS.md itself when I was telling it to go and implement a feature instead ->
<img width="3423" height="402" alt="Image" src="https://github.com/user-attachments/assets/f97f4538-678c-4307-9b73-095949a1b680" />
Even though it's reasoning kicked in later, seeing it do this was not something i was expecting, going to support@openai.com also gives you automated responses from gpt itself, incase it ever goes rogue - no clue on how to even reach the proper folks for any of this when things are so much AI controlled.
Deleted unused imports and .venv folder 🤡
Thanks for the bug report. We've shared the feedback with the team members who are responsible for training our codex models. We're tracking this feedback and similar reports so we can make the model more robust in future iterations.
If you see other model behavior that you'd like to report, please use the recently-added /feedback command in the CLI. That will provide us with additional details including logs and conversation text.