Add scheduled lychee cronjob with automatic GitHub issue creation

[Copilot]

Fixes #2736

Implements a scheduled lychee link checker that runs on a cron schedule at 09 UTC every Monday and automatically opens GitHub issues for broken links, replacing the previous PR-based link checking.

[Copilot]

Pull Request Overview

This PR replaces PR-based link checking with a scheduled approach that automatically creates GitHub issues for broken links, reducing CI noise while maintaining proactive link health monitoring.

• Introduces scheduled lychee link checker that runs weekly on Mondays at 9:00 AM UTC
• Removes lychee job from Rust CI workflow to prevent PR blocking
• Implements automatic GitHub issue creation and management for broken links

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
.github/workflows/rust_ci.yaml	Removes lychee link checking job from CI pipeline
.github/workflows/lychee.yaml	Adds new scheduled workflow with automatic issue creation for broken links

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[claude]

Claude finished @Copilot's task —— View job

---

Pull Request Review

This PR successfully implements a scheduled lychee link checker with automatic GitHub issue creation. Here's my comprehensive review:

Todo List

• Read and analyze the new lychee.yaml workflow
• Review the rust_ci.yaml modifications
• Evaluate code quality and best practices
• Check for potential bugs or issues
• Assess security considerations
• Review performance implications
• Provide comprehensive feedback

✅ Strengths

Architecture & Design:

• Smart approach: Moving from PR-blocking to scheduled issue creation reduces CI noise while maintaining proactive monitoring
• Proper scheduling: Monday 9AM UTC is reasonable for weekly link health checks
• Issue management: close-previous-issues: true prevents duplicate issue spam

Security & Permissions:

• Minimal permissions: Correctly requests only issues: write and contents: read
• Standard token usage: Uses GITHUB_TOKEN appropriately for rate limiting avoidance
• No credential exposure: No hardcoded secrets or unsafe practices

Configuration:

• Reuses existing config: Leverages lychee.toml maintaining consistency
• Appropriate timeout: 30-minute timeout prevents hanging jobs
• Manual trigger: workflow_dispatch enables testing and on-demand runs

⚠️ Issues Found

Critical Bug (.github/workflows/lychee.yaml:30):

# Current (incorrect)
args: ... './docs/**/*.com'
# Should be
args: ... './docs/**/*.json'

The .com extension appears to be a typo and should likely be .json for documentation files. This was correctly identified by the previous reviewer.

Minor Improvements:

1. Workflow name consistency: Consider Link Health Check to match the purpose better than just Link Checker

2. Issue template enhancement: The issue body could include more context:

issue-body: |
  The automated link checker found broken links in the repository.
  
  **Schedule**: This check runs every Monday at 9:00 AM UTC
  **Last successful run**: Check the [Actions tab](https://github.com/${{ github.repository }}/actions/workflows/lychee.yaml)
  
  Please review and fix the broken links listed below:
  
  $LYCHEE_REPORT

✅ Code Quality Assessment

Best Practices:

• ✅ Uses pinned action versions (@v5, @v2)
• ✅ Proper YAML formatting and indentation
• ✅ Clear job and step naming
• ✅ Appropriate use of environment variables

Performance Considerations:

• ✅ 30-minute timeout prevents runaway jobs
• ✅ fail: false ensures workflow doesn't fail on broken links (appropriate for issue creation flow)
• ✅ Cache exclusion for 429 status codes handles rate limiting gracefully

Maintainability:

• ✅ Clean removal of lychee job from rust_ci.yaml (lines 172-196 cleanly removed)
• ✅ Configuration centralized in lychee.toml
• ✅ Clear documentation in PR description

🔍 Test Coverage

Missing but Acceptable:

• No direct tests for GitHub Actions workflows (this is standard practice)
• Manual testing possible via workflow_dispatch trigger
• The existing lychee.toml config has been validated in previous PR-based runs

📊 Impact Assessment

Positive Changes:

• ✅ Reduces CI noise and PR blocking
• ✅ Maintains proactive link monitoring
• ✅ Provides better issue tracking for broken links
• ✅ Separates concerns (CI vs. maintenance tasks)

Risk Assessment:

• 🟡 Low risk: File pattern typo needs fixing but won't break workflow
• 🟢 No security concerns: Proper permission model
• 🟢 No performance regression: Removes load from PR pipeline

Recommendation

APPROVE with the file extension typo fix. This is a well-implemented solution that achieves the goal of reducing PR noise while maintaining link health monitoring.

Required Fix:

• Fix .com → .json in lychee.yaml:30

Optional Enhancements (can be done in follow-up):

• Enhanced issue template with more context
• Consider workflow name improvement

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 86.0%. Comparing base (b68d533) to head (dd228fe).
⚠️ Report is 2 commits behind head on main.
✅ All tests successful. No failed tests found.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[refcell]

One thing that concerns me here is if the issues aren't fixed relatively quickly, this will wind up creating a ton of issues over time. Is it possible to have a workflow that checks if issues exist already? One open issue should be sufficient to track all relevant lychee issues.

[emhane]

One thing that concerns me here is if the issues aren't fixed relatively quickly, this will wind up creating a ton of issues over time. Is it possible to have a workflow that checks if issues exist already? One open issue should be sufficient to track all relevant lychee issues.

@copliot pls fix