feat: Add CoVe commands, template sync, and Python SOLID checklist#24
Merged
feat: Add CoVe commands, template sync, and Python SOLID checklist#24
Conversation
Inspired by serpro69/claude-starter-kit: adds Chain-of-Verification commands (/cove, /cove-isolated) for high-stakes accuracy, a template sync workflow for downstream projects, and Python-specific SOLID checklist items in the refactoring-specialist agent. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Organization UI Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (3)
📝 WalkthroughWalkthroughThis PR introduces Chain-of-Verification (CoVe) commands for multi-step answer verification, adds a GitHub Actions workflow for automated upstream template synchronization, enhances the refactoring-specialist agent with Python-specific SOLID checks, and provides corresponding documentation and test coverage. Changes
Sequence Diagram(s)sequenceDiagram
participant User as User/Requester
participant System as Claude System
participant Agent as Verification Agent
participant Tools as Tools (Read/Grep/Bash)
User->>System: Request with CoVe command
System->>System: Step 1: Generate Baseline Response
System->>System: Step 2: Plan Verification Questions (3-8 fact-checks)
System->>Agent: Step 3: Send verification questions<br/>(Isolated: no baseline access)
Agent->>Tools: Query source code/docs
Tools-->>Agent: Return evidence
Agent-->>System: Return verification results<br/>(CONFIRMED/INCORRECT)
System->>System: Step 4: Generate Final Response<br/>Incorporate corrections if needed
System-->>User: Return verified response
sequenceDiagram
participant Scheduler as GitHub Scheduler
participant Workflow as Workflow (template-sync.yml)
participant Git as Git Operations
participant Upstream as Upstream Repository
participant PR as PR Creation
Scheduler->>Workflow: Trigger (scheduled weekly or manual)
Workflow->>Workflow: Determine template repo & branch
Workflow->>Git: Add upstream remote
Git->>Upstream: Fetch upstream branch
Upstream-->>Git: Return upstream code
Workflow->>Workflow: Compare template-managed paths<br/>(diff against upstream)
alt has_changes
Workflow->>Git: Create sync branch<br/>(template-sync/YYYYMMDD)
Git->>Workflow: Checkout upstream files
Workflow->>Git: Stage & commit changes
Git->>Workflow: Push branch
Workflow->>PR: Create/update pull request<br/>with change summary
PR-->>Workflow: PR created or already exists
else No Changes
Workflow->>Workflow: Mark as up-to-date
end
Workflow-->>Scheduler: Workflow complete
Estimated code review effort🎯 4 (Complex) | ⏱️ ~50 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ 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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.github/workflows/template-sync.yml:
- Around line 113-116: The Apply step can exit early without setting sync_branch
in GITHUB_ENV which leaves env.sync_branch empty when the "Create pull request"
step runs; add an id to the Apply step (e.g., id: apply) and set an output flag
(e.g., outputs.changed=true/false or write a flag to GITHUB_ENV) to indicate
whether a branch was created, then update the "Create pull request" step
condition to check that output (e.g., if: steps.apply.outputs.changed == 'true')
before running commands that use sync_branch or calling gh pr list --head;
ensure any path that sets sync_branch writes it to GITHUB_ENV so the PR step
only runs when sync_branch is defined.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: b2e1b0a8-e865-49d7-85fd-8a047c60dc11
📒 Files selected for processing (8)
.claude/agents/refactoring-specialist.md.claude/commands/cove-isolated.md.claude/commands/cove.md.github/workflows/template-sync.ymlREADME.mddocs/CHANGELOG.mddocs/DEVELOPMENT_PROCESS.mdtests/test_commands.py
Address CodeRabbit review: if the apply step exits early (no changes after checkout), sync_branch was never set, causing gh pr list to run with an empty --head argument. Now uses step output flag to gate the PR creation step. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Replace stat.S_IXUSR filesystem check with git ls-files -s mode check in test_hook_is_executable (NTFS has no Unix permission bits) - Remove stale test_sync_does_not_classify assertion that no longer matches the rewritten sync skill content Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The integration tests copy the template to a non-git directory, so git ls-files returns nothing. Fall back to stat.S_IXUSR when not in a git repo (works on Linux CI), use git mode check otherwise (works on Windows). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
Adopts three features inspired by serpro69/claude-starter-kit:
/cove,/cove-isolated) -- 4-step self-verification process based on Meta's CoVe paper for reducing hallucinations. The isolated variant runs step 3 in a separate agent to prevent confirmation bias..github/workflows/template-sync.yml) -- weekly or manual workflow that syncs template-managed files from upstream into downstream projects via PR, preserving project-specific code.refactoring-specialistagent -- adds checks for mutable default arguments, ABC/Protocol misuse, missing dependency injection, god classes,@propertyoveruse, and circular imports.Attribution added to README Credits section.
Test plan
python -m pytest tests/test_commands.py -v-- all 35 tests pass (5 new CoVe tests)python -m pytest tests/test_agents.py -v-- all 114 tests passpython -m pytest tests/ -v-- 400 passed, 7 pre-existing Windows-only failurespython -m ruff check tests/test_commands.py-- cleanpython -m ruff format --check tests/test_commands.py-- clean🤖 Generated with Claude Code
Summary by CodeRabbit
Release Notes
New Features
Documentation