gpt-5.6-sol incorrectly flags harmless prompts as policy violations
Nobody has claimed this yet.
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.4k
- PR merge metrics
- PR metrics pending
Description
What version of Codex CLI is running?
codex-cli 0.154.0
What subscription do you have?
20x
Which model were you using?
gpt-5.6 sol
What platform is your computer?
Linux 6.8.0-138-generic x86_64 x86_64
What terminal emulator and version are you using (if applicable)?
Terminal
Codex doctor report
What issue are you seeing?
gpt-5.6-sol consistently rejects harmless prompts with the following error:
Invalid prompt: your prompt was flagged as potentially violating our usage policy.
Reproduction
- Start Codex CLI using gpt-5.6-sol.
- Enter a harmless prompt, such as: "Reply only with OK."
- The request is immediately rejected.
The same prompt works correctly with:
- gpt-5.6-terra
- gpt-5.6-luna
- gpt-5.5
Only gpt-5.6-sol and gpt-6 is affected.
What steps can reproduce the bug?
Uploaded thread: 01a0ad3d-8a2b-7002-9e52-6869dc617923
What is the expected behavior?
No response
Additional information
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Reproduce the rejection in Codex CLI 0.154.0 on Linux with gpt-5.6-sol using the harmless prompt "Reply only with OK." Compare the result with gpt-5.6-terra, gpt-5.6-luna, and gpt-5.5, and review the uploaded thread 01a0ad3d-8a2b-7002-9e52-6869dc617923. Done means harmless prompts are accepted by the affected model.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- ai, cli
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100