docs: Round-6 pause-point skill guidance improvements#1913
Conversation
…idance Round-6 verification feedback showed agents mis-sequencing arm/await, mis-reading clear-time resume, and retrying blindly on missed press edges. Align the skill prose with the behavior shipped in this round: - pause-point: document foreground-enable then background-await as the arm-safe sequence (no fixed sleeps), promote CapturedVariables as the primary value evidence, add entry-point bisection for unhit lines, note that clear resumes Play Mode only for pause-point-owned pauses, extend the physics-callback caveat to the new one-hop indirect-call warning, and require UnityEngine.Debug.Assert for get-logs visibility - control-play-mode: document the ResumedFromPause response field and resume-vs-start semantics of Play while paused - simulate-keyboard: state the hold-key recipe explicitly and document the three PressEdge* diagnostics fields with how to act on each Regenerated .claude/.agents copies via uloop skills install.
|
Warning Review limit reached
Next review available in: 36 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. 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: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (9)
✨ Finishing Touches🧪 Generate unit tests (beta)
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 |
4a89b05
into
feature/round6-pause-point-improvements
Summary
Part of the Round-6 pause-point usability improvements (PR-5 of 5, targeting the integration branch
feature/round6-pause-point-improvements). Documentation-only: aligns three skill files with the behavior shipped in #1910, #1911, and #1912, and folds in guidance gaps observed during the Round-6 verification sessions.uloop-pause-point
--awaitguidance: background only when asimulate-*command must run in parallel; foreground--awaitprints the hit result directly; when arm-before-input must be guaranteed, runenable-pause-pointwithout--awaitin the foreground (response = arm confirmation), then backgroundawait-pause-point— never a fixed sleep.CapturedVariablesas the primary value evidence; post-hit live reads are supplements.Warning), manual pauses are untouched.System.Diagnostics.Debug.Assertfailures are invisible toget-logs; useUnityEngine.Debug.Assert.uloop-control-play-mode
ResumedFromPauseresponse field and thatPlaywhile paused resumes the session withChanged: trueandMessage: "Play mode resumed".uloop-simulate-keyboard
Press --durationorKeyDown→KeyUp; there is no hold action).PressEdge*diagnostics fields added in feat: Add press-edge diagnostics to simulate-keyboard #1912 and how to act on each before retrying..claude/and.agents/copies regenerated viadist/darwin-arm64/uloop skills install --claude --agents.Test plan
git statusshows only the intended 9 files)