Garry Tan 1d7e79f7c3 feat: parallelize CI evals — 12 runners (1 per suite) for ~3min wall clock ...

Matrix strategy spins up 12 ubicloud-standard-2 runners simultaneously,
one per test file. Separate report job aggregates all artifacts into a
single PR comment. Bun dependency cache cuts install from ~30s to ~3s.

Runner cost: ~$0.048 (from $0.024) — negligible vs $3-4 API costs.
Wall clock: ~3-4min (from ~8min).

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

2026-03-23 05:25:13 -07:00

..

evals.yml

feat: parallelize CI evals — 12 runners (1 per suite) for ~3min wall clock

2026-03-23 05:25:13 -07:00

skill-docs.yml

fix: Codex compatibility — 1024-char cap, duplicate skills, repo-local installs, kiro support (v0.11.2.0) (#346)

2026-03-22 19:27:10 -07:00