Why did an amber warning appear when I chose the OAuth token option?

Why this happens

Cyberlop warns you early. In Settings → AI Provider, the OAuth option uses a personal subscription token. Those tokens carry rate limits. A long scan makes many model calls. Your AI provider can then throttle the run part-way through, long before the agents finish reading your code. That is the risk.

When that happens, the agents cover less of the codebase, and your report may miss issues that a full run would have found. It adds that a premium model on such a token is unlikely to beat the built-in defaults.

How to fix it

1. Open Settings → AI Provider.
2. Change Provider type to the API key option for your AI provider, so that scan calls use your key and not a subscription token.
3. Paste the key in Replace credential. Cyberlop encrypts it and never shows it again.
4. Click Save credential, then Verify to test it.
5. Under AI Models, leave each tier on its default unless you need a specific model. Then click Save models.

Still not working?

The warning appears only while you have the OAuth option picked. Switch the type and it goes away. Must you stay on an OAuth token? Keep the default models, and expect slower or shallower runs on large apps, because the throttling hits long scans first and hardest.

Your provider bills API-key use. Settings → Plan & usage shows the amount used on your own key. Read API key vs OAuth token and why a premium model may not help. Questions? Use our contact page.

Related questions

• Should I use an API key or a subscription OAuth token for my AI provider?
• I picked a premium model, but the results aren't any better. Why?
• Why did my scan cover less of my codebase than expected?
• How do I use my organization's own AI provider key?
• How do I pick which AI model each tier uses?

Full tutorial

AI provider settings: included allowance, your own credential and models

Step-by-step, with annotated screenshots.

Updated 8 October 2026 · Back to the help centre