"Reached max token limit" keeps appearing even though I'm using BYOK via Azure Foundry

Foundry Toolkit for VS Code keeps popping up with a message saying "You have reached max token limit. Increase the limit or start a new chat" whilst processing a rqeuest. Whilst it's popping up, it does look as though its able to retry and proceed but this pop-up seems to be slowing it down/disrupting the flow. I can see in the Azure output terminal that its reconnecting to the Azure subscription each time it bumps into this error.

Unclear what this is referring to or how I change the limit if I'm using Azure Foundry and Foundry Toolkit extension. There shouldn't be a max token limit if you're BYOK? I don't believe I'm maxxing out on the Azure Foundry limits as they're set to 10,000 per minute and 10,000,000 tokens per minute.

I have set the BYOK utility model to an Azure Foundry model as well.

VS Code:
Version: 1.129.1 (user setup)
Commit: 8a7abeba6e03ea3af87bfbce9a1b7e48fed567b8
Date: 2026-07-17T15:35:09Z
Electron: 42.6.0
ElectronBuildId: 14623276
Chromium: 148.0.7778.280
Node.js: 24.18.0
V8: 14.8.178.38-electron.0
OS: Windows_NT x64 10.0.26200

Foundry Toolkit version:
Identifier: ms-windows-ai-studio.windows-ai-studio
Version: 1.6.5