Files
orca/skill-guides
Jinjing be8f5ace6c docs(orchestration): tell workers to report effort from --effort, not reasoning_effort (#41356)
The numeric reasoning_effort a model sees is not on a 0-100 scale
(claude-opus-5-5: low=5, medium=10, high=15, xhigh=40). Workers launched
with --effort high read 15 as low and misreported their effort.
2026-11-11 19:52:08 -08:00
..