mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-28 06:23:01 +00:00
Initial run showed OC parallel `--local` at 10-wide hits 40% failure rate (17/30 across 3 runs). That's the finding, not a test bug — process startup stampede + LLM rate limits. Bench now prints error samples and reports the numbers instead of gating. Minions side still gates at 90% (30/30 observed in practice).