Garry Tan 11977d46ae fix: per-mode reasoning effort defaults, add --xhigh override ...

xhigh reasoning uses ~23x more tokens and causes 50+ minute hangs
on large context tasks (OpenAI issues #8545, #8402, #6931).

Per-mode defaults for /codex skill:
- Review: high (bounded diff, needs thoroughness)
- Challenge: high (adversarial but bounded by diff)
- Consult: medium (large context, interactive, needs speed)

Also changes all Outside Voice / adversarial codex invocations
across gstack (resolvers, gen-skill-docs) from xhigh to high.
Users can override with --xhigh flag when they want max reasoning.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-26 12:18:25 -06:00

..

SKILL.md

fix: per-mode reasoning effort defaults, add --xhigh override

2026-03-26 12:18:25 -06:00

SKILL.md.tmpl

fix: per-mode reasoning effort defaults, add --xhigh override

2026-03-26 12:18:25 -06:00