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

..

browse.ts

feat: worktree isolation for E2E tests + infrastructure elegance (v0.11.12.0) (#425)

2026-03-23 23:05:22 -07:00

codex-helpers.ts

feat: worktree isolation for E2E tests + infrastructure elegance (v0.11.12.0) (#425)

2026-03-23 23:05:22 -07:00

constants.ts

feat: worktree isolation for E2E tests + infrastructure elegance (v0.11.12.0) (#425)

2026-03-23 23:05:22 -07:00

design.ts

fix: Codex description limit + wrong-repo bug (v0.11.19.0) (#471)

2026-03-25 23:07:07 -07:00

index.ts

feat: test coverage gate + plan completion audit + auto-verification (v0.11.13.0) (#428)

2026-03-24 20:01:37 -07:00

preamble.ts

feat: GitLab support for /retro, /ship, and /document-release (v0.11.20.0) (#508)

2026-03-26 07:21:15 -06:00

review.ts

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

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

testing.ts

feat: test coverage gate + plan completion audit + auto-verification (v0.11.13.0) (#428)

2026-03-24 20:01:37 -07:00

types.ts

feat: worktree isolation for E2E tests + infrastructure elegance (v0.11.12.0) (#425)

2026-03-23 23:05:22 -07:00

utility.ts

feat: GitLab support for /retro, /ship, and /document-release (v0.11.20.0) (#508)

2026-03-26 07:21:15 -06:00