The hard part for me is choosing the model and effort, that's why I always resort to Astra xhigh, but then it ends up consuming tokens so fast.

How do you decide what to pick? I mean, I do Platform work on a large monorepo with many different interconnected services, and so I always want the implementation to be "correct".

Simple as it sounds but I ask Sol or Astra to propose optimal model and effort level for a given workload. Works pretty neat for me.