GPT-6 Astra rejects harmless prompts and falls back to GPT-5.6 Sol

What version of the Codex App are you using (From “About Codex” dialog)?

26.903.8094.0

What subscription do you have?

Plus

What platform is your computer?

Microsoft Windows 11 Pro 10.0.26200 x64

What issue are you seeing?

GPT-6 Astra rejects harmless prompts such as “你好” or “Hello” with the following error:

Invalid prompt: your prompt was flagged as potentially violating our usage policy. Please try again with a different prompt.

Codex then automatically changes the model from GPT-6 Astra to GPT-5.6 Sol. GPT-5.6 Sol works normally.

The issue also occurs in a completely new task with no previous conversation context.

Local logs around the reproduction contain:

• DeviceCheck attestation unavailable (errorCode=1)
• Received turn/started for unknown conversation

What steps can reproduce the bug?

1. Open the Windows Codex desktop app.
2. Create a new empty task.
3. Select GPT-6 Astra.
4. Send “你好” or “Hello”.
5. The prompt is rejected as a usage-policy violation.
6. Codex automatically falls back to GPT-5.6 Sol.

Reproduction rate: 100%.

Expected behavior:
GPT-6 Astra should respond normally to harmless greetings.[

](url)

What is the expected behavior?

No response

Additional information

No response

Start by reproducing the failure in the Windows Codex desktop app with a new task, selecting GPT-6 Astra and sending “你好” or “Hello”. Inspect the local logs around the reproduction, including the DeviceCheck attestation and unknown-conversation messages. Done means harmless prompts are accepted by GPT-6 Astra without an automatic fallback to GPT-5.6 Sol.