I'm sorry you ran into problems repeatedly, and couldn't agree more. As much as we've aimed to innovate on customization, it does not have to be an either/or. We recognized this, heard a lot from the community, and the goal of our 1.0 was to focus ourselves very seriously on stability. Going forward we are going to continue to treat Continue as the foundational tool that we hope it can be. This has meant investment in testing, clearer contributing guidelines, and a general mindset shift to understand that AI code assistants have become fundamental to developer workflows and have to be rock solid (when something is doing work on every keystroke, it better not break!)

If you get the chance to try the 1.0, I'd love to hear whether you find it better, or if you think we can do even better—we think it's in a solid place and it'll always be improving from here.