Define AI Code review configurations and instructions#445
Conversation
Co-authored-by: Cassidy James <cassidyjames@roost.tools>
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughAdds CodeRabbit review configuration, a Copilot instructions file with AI review checklists and tone guidance, and Dependabot label additions across multiple update blocks. ChangesAI Review Configuration and Guidance
Dependabot Configuration
🎯 2 (Simple) | ⏱️ ~12 minutes 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Tip 💬 Introducing Slack Agent: The best way for teams to turn conversations into code.Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.
Built for teams:
One agent for your entire SDLC. Right inside Slack. Comment |
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 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 @.coderabbit.yaml:
- Around line 51-52: Remove the invalid tool key "prettier" from the
reviews.tools section and delete the unsupported "ast-grep.enabled" property
under the ast-grep tool; instead, replace them with the correct configuration
fields per the CodeRabbit schema (consult the CodeRabbit schema docs for the
proper ast-grep keys such as "rules", "config", or "version" as applicable) so
that reviews.tools only contains valid tool identifiers and each tool uses
supported properties.
In @.github/copilot-instructions.md:
- Line 8: Update the package count in the sentence that begins "Four independent
packages, not an npm workspace:" to match the listed entries by changing "Four"
to "Five" (or remove one of the listed paths if the intent is four); ensure the
heading and the enumerated paths (/ (root), /server, /client, /db, /migrator)
remain consistent with the corrected numeric count.
🪄 Autofix (Beta)
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: Pro Plus
Run ID: 10f7796b-4283-40f1-b411-49438be7c63a
📒 Files selected for processing (2)
.coderabbit.yaml.github/copilot-instructions.md
julietshen
left a comment
There was a problem hiding this comment.
looks mostly fine; i don't feel strongly about the path-scoped review but I think we should definitely add a what-not-to-flag section in instructions
- Switch Dependabot filter to ignore_usernames (race-proof — the pull_request.opened webhook fires before pull_request.labeled). Keep labels: ['!dependabot'] as a manual opt-out path. - Re-enable hadolint and shellcheck — they aren't covered by CI workflows. - Move path-specific guidance from copilot-instructions.md into .coderabbit.yaml path_instructions (resolvers, server/api.ts, ClickHouse adapters, Scylla, iocContainer, migrations, client, dependency manifests). Shorter per-diff prompts for CodeRabbit; cross-cutting concerns stay in the markdown for Copilot and other readers. - Add "What not to flag" section to copilot-instructions.md with examples of low-signal comments to suppress. Co-Authored-By: Cursor Agent <noreply@cursor.com>
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 @.coderabbit.yaml:
- Around line 25-31: The path_filters block currently excludes package-lock
files via the pattern '!**/package-lock.json', which conflicts with the
dependency-review rules that must surface lockfile-only transitive bumps; update
the path_filters to stop excluding lockfiles (remove the '!**/package-lock.json'
entry or narrow it to a more specific path that doesn't hide repo-level
lockfiles), ensuring package-lock.json (and other lockfiles you need surfaced)
are no longer filtered out so the rules referenced around lines 91-94 can detect
transitive dependency updates.
🪄 Autofix (Beta)
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: Pro Plus
Run ID: 9dfeae30-0af3-4595-9f0d-ad3f2e673694
📒 Files selected for processing (2)
.coderabbit.yaml.github/copilot-instructions.md
✅ Files skipped from review due to trivial changes (1)
- .github/copilot-instructions.md
Context & Requests for Reviewers
Initial Scaffolding for AI code review instructions. Defines expectations on what to look for and ignore linting errors.
Summary by CodeRabbit