omrimaya

The capability-based permission propagation is the part I'd want to stress-test first, in practice we found that the interesting failure mode isn't the agent escaping its sandbox, it's …

The one-line summary + lazy-load pattern is exactly where we landed too after trying to stuff schemas into context. What I'd add: the harder problem is invalidation, those skill files accumulate …

The "infrastructure instead of a library" pattern is everywhere in the LLM tooling space right now. We went through the same decision point, stood up LiteLLM, ran it for a week, then ripped …

The design decision I find most interesting here is ephemeral-by-default with opt-in checkpointing, that inversion of the usual "persist everything, clean up manually" model fits agent code …