point 1: merge smaller features more often. Multi-thousand line PRs suck no matter if they're squashed or not.
point 2: As people mentioned, this is for PRs done by individual people, usually squashing their local history. If multiple people were working on the branch, they should have been PR-ing against that branch (squashing the commits), then you merge that branch to master (you may rebase it, but not do significantly destructive stuff).
Even then, these are features to use with critical thinking. If your PR is really large, massage the history to be relevant and meaningful for git bisect purpose. Use full squashing when it was a local work full of "My hands are typing words" commits of no relevance.
I swear, we're in an industry full of people making 6 figure salaries, who treat their job as if it was a call center script to follow. If you're an engineer, use your head and engineer solutions around the tools you have.
point 2: As people mentioned, this is for PRs done by individual people, usually squashing their local history. If multiple people were working on the branch, they should have been PR-ing against that branch (squashing the commits), then you merge that branch to master (you may rebase it, but not do significantly destructive stuff).
Even then, these are features to use with critical thinking. If your PR is really large, massage the history to be relevant and meaningful for git bisect purpose. Use full squashing when it was a local work full of "My hands are typing words" commits of no relevance.
I swear, we're in an industry full of people making 6 figure salaries, who treat their job as if it was a call center script to follow. If you're an engineer, use your head and engineer solutions around the tools you have.