Hey, thanks for the report. This looks like a known issue. We had a similar report 5 days ago with Codex Extra High: GPT 5.2 Codex Extra High does not use the native TODOs when planning
It was fixed back then by updating to 2.4, but you’re already on 2.4.21, so it’s either a regression or something model-specific.
We need a bit more info:
- Does this happen every time with Codex, or only sometimes?
- Can you try another model in Plan mode (Claude 4.5 Sonnet or GPT-5 High without Codex)? Do the to-dos get created correctly there?
- If you can, can you share the Request ID? (Top right menu in the chat > Copy Request ID)
This will help us figure out what exactly is going wrong with Codex.