Codex Cloud — 터미널 살아남는 작업

~12 min · codex, cloud, long-running

Level 0🌱 입문자

0 XP0/70 lessons0/11 achievements

0/120 XP to next level120 XP to go0% complete

OpenAI 인프라에 작업 hand

Codex Cloud (실험적) 가 OpenAI 의 managed 인프라에 작업 제출 — 노트북 닫아도 job 안 죽음. 위해: 긴 test suite, multi-repo 리팩토링, 큰 마이그레이션 job, 그 외에 Spot instance 에서 run 할 만한 거.

features.codex_cloud = true 로 enable. codex cloud submit 으로 제출; codex cloud list / codex cloud status 로 체크; codex cloud pull 로 결과 로컬에 pull. Sandbox + approval 정책이 작업과 같이 이동.

Code

Submit, monitor, pull back·bash

# Enable in config
# [features]
# codex_cloud = true

# Submit a task
codex cloud submit --name nightly-bench \
  --sandbox workspace-write \
  --ask-for-approval never \
  "Run the full bench suite, write report to ./bench-$(date +%F).md"

# Monitor
codex cloud list
codex cloud status nightly-bench

# Pull results when done
codex cloud pull nightly-bench
# Files are merged into your local working copy; conflicts are flagged.

When Cloud is the right answer·text

Use Codex Cloud when:
- The task takes >30 min and you don't want to pin your laptop
- You want consistent execution environment (cloud > your laptop)
- Multiple parallel jobs (10 PRs to refactor — fan out to cloud)

Don't use it when:
- Task is short (<5 min)
- Task needs your local files outside the repo
- Task requires real-time iteration with you in the loop

External links

Codex Cloud (experimental)

Exercise

access 있으면 진짜 long-running 작업을 Codex Cloud 에 제출 (느린 test suite, 멀티파일 리팩토링). 떠나. 결과 pull back. 경험이 로컬 + Spot+SSH 대안보다 좋았던 / 나빴던 데 적어.

Progress

Progress is local-only — sign in to sync across devices.

← PreviousCodex 의 Sub-agent Next →퀴즈 · 3 questions

이 페이지에서 버그를 발견하셨거나 피드백이 있으세요?문제 신고

🔔 답글 알림 (로그인 필요)

로그인 — 댓글을 남기려면 로그인해 주세요.

아직 댓글이 없어요. 첫 댓글을 남겨보세요.