Codex stuck in Loops

[thom-heinrich]

I am an ultra heavy codex user, keeping track on basically every metric you can ablate from the tool.

Currently gpt 5.2 xhigh tends to a) forget where it was b) treat it own responses as user input and c) "solves" the same problems over and over again - this happens also with plan mode.

This leads at the moment to a drastically worse performance and the resolution rate is from ~40% in my repo down to around ~10% or lower. It struggles with basic tasks like browser automation, prompt compiling etc...

I am using Codex CLI as Pro User /w GPT 5.2 xhigh and the latest release.

[github-actions]

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

• Context compaction causes task drift: assistant reverts to stale prior request and executes unrelated command #11315
• Context compacted #11444
• Automatic context compaction causes Codex to lose track of the current turn and start trying to re-perform the previous turn instead #10346
• Context compactization forgets current mission #11054
• When context is auto compacted, agent forgot question already answered in previous turn. #11174

Powered by Codex Action

[wbdb]

GPT-5.3 Codex is better at this. Generally, use /new after each task (especially very different tasks) to ensure clean context management. GPT-5.3 is coming soon, and it will certainly include improvements to avoid unnecessary repetition.

It makes no sense to use xhigh in the standard. Especially not in long chat sequences. The OpenAI models have been very good at understanding context since 5.2, but they are not perfect yet.

[etraut-openai]

Thanks for the bug report. We love to hear from codex power users.

What you're describing here is model behavior, not something that's under the control of the harness. As you noted, gpt-5.3-codex is better at this than gpt-5.2, and we continue to make improvements to newer-generation models.

If you see behaviors like this, it's helpful if you use the /feedback command to upload the session details. This helps the team responsible for training our models understand where improvements are needed. You can skip opening github bug reports for those issues.