[App] Intermittent false-positive `invalid_prompt` on benign software tasks in fresh gpt-5.6-sol threads

Summary

Codex Desktop intermittently rejects completely benign software-development prompts with:

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

This is happening across multiple brand-new threads and multiple ordinary local repositories. The prompts are routine product/UI/backend development requests, not cybersecurity or other safety-sensitive work.

Environment

• Codex Desktop app on macOS
• Model: gpt-5.6-sol
• ChatGPT subscription auth
• Multiple local Git repositories / workspaces
• Observed on 2026-08-20 / 2026-08-21 (UTC+8)

I do not have the exact Codex Desktop build number handy, but can provide it if needed.

Examples of benign prompts that were blocked

Examples include requests equivalent to:

• "I want the modal to take up 5/6 of the screen width."
• Ordinary travel-admin UI work: adjust a user-tracking table, add an expandable row, reuse an existing nickname/remark field, and add a link to an itinerary-management page.
• Ordinary travel-planning schema/design work involving fields such as scenario, capacity, pax, and vehicle_num.

None of these requests involve credential access, exploitation, bypassing authentication, scanning, malware, or any other cybersecurity activity.

Important behavior / reproduction pattern

The rejection is intermittent rather than tied to a specific user prompt:

1. Open a brand-new Codex Desktop thread in a local repository.
2. Ask Codex to read the workspace rules / AGENTS.md and inspect the repo.
3. Codex can often read files, inspect git status/diffs, and even perform ordinary edits successfully for several minutes.
4. A subsequent benign prompt may suddenly fail with invalid_prompt.
5. Open another fresh thread against the same repository and send essentially the same benign request.
6. The request may succeed normally there.
7. A plain fresh chat with a simple greeting also succeeds, so the account/model is not globally blocked.

In one observed thread, the rejection appeared after the UI showed that the conversation context had been automatically compacted. However, the problem is not limited to old threads: I also reproduced it in newly created threads.

The strongest observed contrast was that the same repository/model could have one thread rejecting a simple modal-width change while another fresh thread was simultaneously inspecting and implementing the same UI task normally.

Expected behavior

Benign local software-development prompts should not be rejected by the safety classifier. If a safeguard does reject a request, the App should ideally expose a request/feedback ID so false positives can be investigated without repeatedly retrying the prompt.

Additional information

This looks similar to #39687 and the older #7250, but this report is specifically about the current Codex Desktop App, gpt-5.6-sol, multiple fresh threads, and ordinary product/UI/travel software development where the same prompt can fail in one thread and succeed in another.

I have multiple screenshots showing the parallel threads and the benign prompts that triggered the error, and can provide them if maintainers need them.

Start in the Codex Desktop app by reproducing the same benign prompt in fresh threads against the same local repository and gpt-5.6-sol model, comparing behavior before and after context compaction. Check whether the app exposes a request or feedback ID. Done means benign software prompts no longer intermittently receive invalid_prompt, or false positives can be investigated using that identifier.