I don't know how anyone can actually use Luna max on ANY real workload. I've had Sol orchestrate a bunch of Luna agents, these agents were explicitly given small chunks of larger objectives and they still filled their entire context windows with just reasoning tokens, until compaction hit, and then reasoning again.
I've probably wasted a good 40% of my weekly usage on Luna Max agents just thinking and not writing a single line of code.
Are you sure you actually spun up Luna sub agents? Sol up until recently could only spin up Sol and Terra agents and would even name them "Luna" despite not being so, you can check in your usage whether it was Luna or not. I believe now it's fixed though.
The one time I tried asking Sol to use subagents for a small project, it took a surprisingly long time, used up the entire usage limit in one go, and basically failed the project.
I’m pretty sure that plain Sol, serially, could have finished the task faster, cheaper, and far more accurately. I’m also pretty sure that any competent subagent orchestration could have gotten it done with even very simple subagents quickly and cheaply.
(Is it really that hard to set up a handful of subagents that all use the same initial context and to load that context with what actually matters? The APIs certainly support it.)
I've probably wasted a good 40% of my weekly usage on Luna Max agents just thinking and not writing a single line of code.