Repository navigation
Invalid prompt Response #49120
Description
Activity
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
- BUG：GPT-6 Astra flags every harmless prompt as a policy violation in Codex Desktop and Work #48713
- GPT-6 Sol/Luna/Astra falsely reject benign prompts with Invalid prompt safety error #48817
- Harmless prompts consistently rejected as "Invalid prompt" due to potential usage policy violation #48865
- Codex CLI: invalid_prompt "flagged as potentially violating our usage policy" mid-turn on routine coding work (effort low) #48929
Powered by Codex Action
We also encountered this issue ,sessionid : 01a0f1b6-84eb-79a3-a743-454a06be59ba
What version of the Codex App are you using (From “About Codex” dialog)?
26.924.22138
What subscription do you have?
pro 5x
What platform is your computer?
mac os arm64
What issue are you seeing?
only sent hello
response:
sessionid :
01a0eabb-cdb7-7fb0-8fd0-8d71248f9a5eInvalid 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
What steps can reproduce the bug?
Feedback ID: 01a0eabb-cdb7-7fb0-8fd0-8d71248f9a5e
What is the expected behavior?
No response
Additional information
No response