mirror of
https://github.com/hanzoai/dev.git
synced 2026-10-25 03:32:32 +00:00
Add best-effort remote /models parity with on-disk cache + TUI preset merge. Harden exec handling by spooling output to disk, avoiding unbounded in-memory buffering, and using best-effort Linux cgroup limits + explicit OOM surfacing so child failures don’t kill the parent.