I still assume that Copilot uses my private repositories as training data, with them taking some care to not make it obvious. The software house i'm working at actually took the whole thing seriously and is currently migrating to an internally hosted GitLab. Not sure what potential leak exactly scares the responsible team, but interestingly it looks like it makes GitHub lose some worried customers.
Well written article! Also very glad to hear your approach to support the native implementation. For all of our projects when we're integrating external services we usually keep the relevant original JSON responses as a jsonb as kind of a backup. Next to that we extract the data we'll be using to queryable data. To be able to use those "dumps" directly would be a nice thing to have.
Well, loving "tldr"[1] and smashing the tab key for my autocompletes that Copilot CLI thing kind of sounds like another level of laziness and less Googling.