chore(skills): batch review findings before push - #8533
Merged
Conversation
Signed-off-by: Carlos Villela <cvillela@nvidia.com>
Contributor
📝 WalkthroughWalkthroughThe PR strengthens PR review closure procedures. It adds complete, head-stable evidence collection, grouped finding resolution, sensitive-workflow checks, final-commit documentation review, push gating, and policy tests. ChangesReview closure workflow
Estimated code review effort: 3 (Moderate) | ~20 minutes Sequence Diagram(s)sequenceDiagram
participant Contributor
participant PRFollowUpWorkflow
participant GitHubReviewEvidence
participant Repository
Contributor->>PRFollowUpWorkflow: Start review collection
PRFollowUpWorkflow->>GitHubReviewEvidence: Collect paginated PR evidence
GitHubReviewEvidence-->>PRFollowUpWorkflow: Return head-stable findings and checks
PRFollowUpWorkflow->>Repository: Apply grouped fixes and validation
PRFollowUpWorkflow->>GitHubReviewEvidence: Recollect evidence for final head
GitHubReviewEvidence-->>PRFollowUpWorkflow: Return final review receipt
PRFollowUpWorkflow->>Repository: Push when no actionable findings remain
Possibly related PRs
Suggested labels: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Warning Tools execution failed with the following error: Failed to run tools: 14 UNAVAILABLE: Connection dropped Comment |
Contributor
Code Coverage OverviewLanguages: TypeScript TypeScript / code-coverage/pluginThe overall coverage in commit 2babbe4 in the TypeScript / code-coverage/cliThe overall coverage in commit 2babbe4 in the Show a code coverage summary of the most impacted files.
Updated |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.agents/skills/_shared/pr-follow-up.md:
- Around line 88-90: Update Step 1 of the latest completed head-stable
collection to gather the complete result set for every required check, including
passing, pending, cancelled, skipped, and failed states, rather than only
failures. Preserve recording each check’s source commit when available, or the
collected head SHA otherwise, and ensure the complete required-check set is
available for the final collection and push decision.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: a0004a1c-5f80-4c6f-a9b6-68a072ae755b
📒 Files selected for processing (4)
.agents/skills/_shared/documentation-writing-review.md.agents/skills/_shared/pr-follow-up.md.agents/skills/nemoclaw-contributor-create-pr/SKILL.mdtest/maintainer-skills-policy.test.ts
Comment on lines
+88
to
+90
| Before editing, collect and classify all review signals in the latest completed head-stable collection: | ||
|
|
||
| 1. Re-read `headRefOid`. Collect current required-check failures, issue comments, submitted reviews, inline threads with resolution state, advisor findings, and required independent-review findings. Record each source commit when GitHub provides it; otherwise record the collected head SHA. |
Contributor
There was a problem hiding this comment.
🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick win
Collect every required-check result in the complete review cycle.
Line 70 requires the collection to record every required check, including pending, cancelled, and skipped results. Step 1 narrows this to required-check failures. A pending, cancelled, or skipped required check can therefore be absent from the final collection and push decision. Use the complete result set in Step 1.
Proposed wording
-1. Re-read `headRefOid`. Collect current required-check failures, issue comments, submitted reviews, inline threads with resolution state, advisor findings, and required independent-review findings.
+1. Re-read `headRefOid`. Collect the status, conclusion, and evaluated commit of every required check, including pending, cancelled, and skipped results; issue comments, submitted reviews, inline threads with resolution state, advisor findings, and required independent-review findings.📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| Before editing, collect and classify all review signals in the latest completed head-stable collection: | |
| 1. Re-read `headRefOid`. Collect current required-check failures, issue comments, submitted reviews, inline threads with resolution state, advisor findings, and required independent-review findings. Record each source commit when GitHub provides it; otherwise record the collected head SHA. | |
| Before editing, collect and classify all review signals in the latest completed head-stable collection: | |
| 1. Re-read `headRefOid`. Collect the status, conclusion, and evaluated commit of every required check, including pending, cancelled, and skipped results; issue comments, submitted reviews, inline threads with resolution state, advisor findings, and required independent-review findings. Record each source commit when GitHub provides it; otherwise record the collected head SHA. |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In @.agents/skills/_shared/pr-follow-up.md around lines 88 - 90, Update Step 1
of the latest completed head-stable collection to gather the complete result set
for every required check, including passing, pending, cancelled, skipped, and
failed states, rather than only failures. Preserve recording each check’s source
commit when available, or the collected head SHA otherwise, and ensure the
complete required-check set is available for the final collection and push
decision.
Contributor
PR Review Advisor — No blocking findings reportedAdvisor assessment: No blocking advisor findings reported Model lanes
8 terminology differences from the second opinionAdvisory only. These are normalized differences from the primary terminology receipt.
Second-opinion terminology and E2E selections are advisory. Live E2E does not run automatically for pull requests. 4 semantic terminology decisionsTerminology decisions are advisory. They affect the assessment only when a separate finding identifies concrete semantic impact.
E2E guidanceAdvisory only. A maintainer can dispatch the default E2E suite against this exact revision. Recommended E2E: None This automated review informs maintainers. Warnings and suggestions do not require a response. A maintainer decides whether to merge. |
22 tasks
6 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Changes PR repair guidance from a per-finding edit loop to one complete review cycle. Agents now collect and classify review evidence, group findings by root cause, model sensitive failure states, review every corrected commit, and push once after the final review and recollection pass.
Changes
HEADto pass independent review before one final push.Type of Change
Quality Gates
Documentation Writer Review
docs-updated.agents/skills/_shared/documentation-writing-review.md.agents/skills/_shared/pr-follow-up.md.agents/skills/nemoclaw-contributor-create-pr/SKILL.md2babbe47e.DGX Station Hardware Evidence
Verification
Signed-off-by:line and every commit appears asVerifiedin GitHubpre-commit,commit-msg, andpre-pushhooks passed, ornpm run validate:prpassed after refreshingorigin/mainwhen hooks were skipped or unavailablenpx vitest run --project integration test/maintainer-skills-policy.test.ts test/skills-frontmatter.test.ts(2 files, 57 tests passed)npm run checks:repositorypassed.npm run docsbuilds without warnings (doc changes only)Additional focused checks:
npm run checks:repositorynpx --yes markdownlint-cli2@0.22.0 '.agents/skills/_shared/*.md' '.agents/skills/nemoclaw-contributor-create-pr/**/*.md'git diff --check2babbe47eSigned-off-by: Carlos Villela cvillela@nvidia.com
Summary by CodeRabbit
Documentation
Tests