feat: add nightlight.sh, chained discover -> plan -> overnight wrapper - #23
Conversation
A single command running the full pipeline instead of three manual invocations: pnpm nightlight [repo] chains discover.sh -> plan.sh -> overnight.sh, using the exact same scripts under the hood (no new approval logic -- discover/plan's existing interactive gates apply unchanged). - --scan is forwarded to discover.sh only. - overnight.sh's five flags (--stop-after, --limit, --stack, --extra-instructions, --override-prompt) are captured generically and forwarded verbatim to the overnight.sh call, unvalidated by nightlight.sh itself -- overnight.sh remains the source of truth for what each flag means and requires. - A y/N confirmation gate sits between plan and overnight specifically (not between discover and plan, which are already fully interactive and approval-gated): overnight is the one unattended, potentially hours-long, real-cost phase, so this is the one place a chained command should make you deliberately opt in. Declining exits 0 with a pointer to run overnight.sh manually later. - package.json gains a "nightlight" script entry; README documents the new command (## nightlight.sh, Scripts, Usage, Setup).
|
Warning Review limit reached
Next review available in: 38 minutes You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (3)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Summary
nightlight.shchainsdiscover.sh->plan.sh->overnight.shinto one command (pnpm nightlight [repo]), reusing each script unchanged -- no new approval logic of its own.--scanroutes todiscover.shonly;overnight.sh's five flags (--stop-after,--limit,--stack,--extra-instructions,--override-prompt) are captured generically and forwarded verbatim to theovernight.shcall, unvalidated bynightlight.sh--overnight.shstays the single source of truth for its own flag semantics.y/Nconfirmation gate sits only betweenplanandovernight(not betweendiscover/plan, which are already fully interactive/approval-gated) --overnight.shis the one unattended, potentially hours-long, real-cost phase, so this is the one point a chained command should make you deliberately opt in rather than sliding straight into it.package.jsongains anightlightscript entry; README documents the new command.Test plan
bash -n nightlight.sh-- syntax valid--scan, overnight flags, no-repo--limit, unknown flag) -- all routed to the correct downstream script, unknown flag rejected before anything launchespackage.jsonvalidated as well-formed JSONpnpm nightlightagainst a realPROJECT_REPOS_DIR(needs a real target-repo setup to exercise, same caveat as feat: add no-arg multi-repo mode to discover/plan, self-merging Finalize #20)🤖 Generated with Claude Code