Flagged as potentially violating usage policy by mistake.

What version of Codex CLI is running?

codex-cli 0.146.0

What subscription do you have?

20x pro

Which model were you using?

gpt5.6sol ultrafast

What platform is your computer?

Linux 5.10.134-013.8.2.kangaroo.al8.x86_64 x86_64 x86_64

What terminal emulator and version are you using (if applicable)?

_No response_

Codex doctor report

What issue are you seeing?

All my prompts are rejected somehow. The message says:
■ Invalid prompt: your prompt was flagged as potentially violating our usage policy. Please try again with a different
prompt: https://platform.openai.com/docs/guides/reasoning#advice-on-prompting
But actually I didn't send any illegal messages or try to steal cot through prompt injection. Just pure engineering dialogues.

What steps can reproduce the bug?

Uploaded thread: 019fc66d-e163-7a70-9b5a-fa4cd279e50e

What is the expected behavior?

Allow my thread to proceed.

Additional information

_No response_