Hi @rancid turret. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
#codex stuck?
late oxideBOT
It sounds like Codex may be hanging rather than just “thinking”.
From the knowledge sources, there are a few relevant patterns and checks:
-
Check OpenAI Status page
Codex has had temporary outages / elevated error rates before, which made it unusable until the incident was resolved. [Codex error rate; Codex unusable]- Go to https://status.openai.com and look for any current incidents affecting Codex or the Responses API.
-
Wait vs. “stuck”
In some cases, users have reported Codex or GPT‑5 taking a very long time or effectively never returning when the task/context is large or complex. [Infinite wait GPT5]- If you’ve already waited 10+ minutes with no progress, it’s likely stuck rather than just slow.
-
Try a smaller / simpler task
Since complex, multi‑file coding tasks can trigger long “thinking” or apparent hangs, try: [Infinite wait GPT5]- Asking Codex to do something very small (e.g., fix one file or one function).
- If small tasks work but big ones hang, you may need to break your request into smaller steps.
-
Check for environment / configuration issues in VS Code
There was a case where Codex appeared “broken” in VS Code Dev Containers because of a VS Code setting (.vscode/settings.json → remote.extensionKind) that forced the AI agent to run on the host instead of inside the container. Fixing that setting restored normal behavior. [Dev container setting]- If you’re using Dev Containers, check that setting and ensure Codex can see the workspace correctly.
- See if it’s a transient service issue
There have been short‑lived issues where Codex couldn’t create tasks or couldn’t be used at all, which were later resolved on OpenAI’s side. [Codex tasks failing; Codex unusable]- If status shows a recent incident, it may just require waiting and trying again later.