docs: codify known_issues resolved-sweep convention (closes #141)#860
docs: codify known_issues resolved-sweep convention (closes #141)#860cristim wants to merge 1 commit into
Conversation
cristim
added
triaged
|
@coderabbitai review |
|
Warning Review limit reachedYou’ve reached a temporary PR review limit under our Fair Usage Limits Policy. Next review available in: 58 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: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (5)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
✅ Actions performedReview triggered.
|
|
@coderabbitai review |
✅ Action performedReview finished.
|
|
@coderabbitai full review Generated by Claude Code |
|
Tip For best results, initiate chat on the files or code changes. 🧩 Analysis chain🏁 Script executed: #!/bin/bash
# Get PR details and files changed
gh pr view 860 --repo LeanerCloud/CUDly
echo "---FILES CHANGED---"
gh pr diff 860 --repo LeanerCloud/CUDlyLength of output: 5842 🏁 Script executed: #!/bin/bash
# Check the content of the archived known_issues files
echo "=== File 25 ==="
cat known_issues/resolved/25_federation_azure_gcp_source_identity_failloud.md
echo ""
echo "=== File 26 ==="
cat known_issues/resolved/26_federation_target_source_consistency.md
echo ""
echo "=== File 27 ==="
cat known_issues/resolved/27_federation_old_bundle_redownload_notice.md
echo ""
echo "=== Check referenced GitHub issues ==="
# Extract issue numbers from these files
grep -oE '#[0-9]+' known_issues/resolved/25_federation_azure_gcp_source_identity_failloud.md \
known_issues/resolved/26_federation_target_source_consistency.md \
known_issues/resolved/27_federation_old_bundle_redownload_notice.md | sort -u
echo ""
echo "=== Check remaining known_issues files ==="
ls known_issues/*.md 2>/dev/null || echo "No .md files at top level"
echo ""
echo "=== Verify the sweep script - does glob known_issues/*.md miss resolved? ==="
ls known_issues/resolved/*.md 2>/dev/null | head -5
echo ""
echo "=== Check referenced issues state ==="
for issue in 41 42 43; do
echo "--- Issue #$issue ---"
gh issue view $issue --repo LeanerCloud/CUDly --json state,number,title --jq '[.number,.state,.title]' 2>/dev/null || echo "Not found"
doneLength of output: 10035
Overall AssessmentThe PR is clean, accurate, and fills a real documentation gap. The three archived files correspond to closed issues 🔶 Notable gap: entry format vs. sweep script mismatchThe cross-check sweep script in grep -h "closes #\|Fixes #\|#[0-9]\+" known_issues/*.md \
| grep -oE '#[0-9]+' | sort -u \
| xargs -I{} gh issue view {} ...But the three files being archived ( The entry format section documents heading and audit-status line, but doesn't include a GitHub Issue field. Suggest adding one to the mandatory format so the sweep script actually works for future entries: Or alternatively, add a 🔶 Sweep grep is slightly fragileThe pattern ✅ Everything else looks good
The entry-format / sweep-script gap is the main actionable item, but it's non-blocking for this PR since it's a documentation-only change establishing the convention going forward. Happy to leave it as a follow-up issue if you prefer. 🧠 Learnings used |
|
@coderabbitai full review |
✅ Action performedFull review finished. |
|
@coderabbitai review |
✅ Action performedReview finished.
|
|
@coderabbitai review |
✅ Action performedReview finished.
|
Add "Known Issues Sweep" section to CONTRIBUTING.md documenting when to add/remove entries, the required format, and who runs the sweep. Add a summary paragraph to CLAUDE.md pointing to that section. Archive the three stale docs whose underlying issues (#41, #42, #43) are closed by moving them to known_issues/resolved/.
1 participant
Summary
CONTRIBUTING.mddocumenting the archive-on-resolve convention, entry format, when to add/remove entries, and how to run a sweep.CLAUDE.mdpointing to that section so it is visible to AI tooling at session start.known_issues/docs toknown_issues/resolved/-- their underlying issues (fix(api): extend federation source-identity fail-loud guard to Azure and GCP deployments #41, fix(api): reject impossible federation target/source combinations with HTTP 400 #42, docs(release-notes): tell customers with pre-zero-touch federation bundles to re-download #43) are all closed.Test plan
CONTRIBUTING.md"Known Issues Sweep" section renders correctly on GitHub.known_issues/resolved/contains the three archived files; they are absent fromknown_issues/top level.