[flagged]
My setup is that I run `/merge`[1] , which will first have the agent rebase changes on base, and on conflicts, it's instructed to understand both sides before resolving, which helps it merge them cleanly. I haven't resolved conflicts manually in months and also haven't had any issues with agents resolving them incorrectly. A solved problem as far as I'm concerned.
One thing we found works really well is having the agent read the other agent’s plan document when it hits a merge conflict, not just the diff. A lot of conflicts are hard to resolve correctly without the intent behind the change.