feat(ci): add contributor attribution check on PRs (#9376)

Adds a CI workflow that blocks PRs introducing commits with
unmapped author emails. Checks each new commit's author email
against AUTHOR_MAP in scripts/release.py — GitHub noreply emails
auto-pass, but personal/work emails must be mapped.

Also adds --strict and --diff-base flags to contributor_audit.py
for programmatic use. --strict exits 1 when new unmapped emails
are found; --diff-base scopes the check to only flag emails from
commits after a given ref (grandfathers existing unknowns).

Prevention for the 97-unmapped-email gap found in the April 2026
contributor audit.
This commit is contained in:
Teknium 2026-04-13 21:13:08 -07:00 committed by GitHub
parent 5719c1f391
commit dd86deef13
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 119 additions and 0 deletions

70
.github/workflows/contributor-check.yml vendored Normal file
View file

@ -0,0 +1,70 @@
name: Contributor Attribution Check
on:
pull_request:
branches: [main]
paths:
# Only run when code files change (not docs-only PRs)
- '*.py'
- '**/*.py'
- '.github/workflows/contributor-check.yml'
jobs:
check-attribution:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0 # Full history needed for git log
- name: Check for unmapped contributor emails
run: |
# Get the merge base between this PR and main
MERGE_BASE=$(git merge-base origin/main HEAD)
# Find any new author emails in this PR's commits
NEW_EMAILS=$(git log ${MERGE_BASE}..HEAD --format='%ae' --no-merges | sort -u)
if [ -z "$NEW_EMAILS" ]; then
echo "No new commits to check."
exit 0
fi
# Check each email against AUTHOR_MAP in release.py
MISSING=""
while IFS= read -r email; do
# Skip teknium and bot emails
case "$email" in
*teknium*|*noreply@github.com*|*dependabot*|*github-actions*|*anthropic.com*|*cursor.com*)
continue ;;
esac
# Check if email is in AUTHOR_MAP (either as a key or matches noreply pattern)
if echo "$email" | grep -qP '\+.*@users\.noreply\.github\.com'; then
continue # GitHub noreply emails auto-resolve
fi
if ! grep -qF "\"${email}\"" scripts/release.py 2>/dev/null; then
AUTHOR=$(git log --author="$email" --format='%an' -1)
MISSING="${MISSING}\n ${email} (${AUTHOR})"
fi
done <<< "$NEW_EMAILS"
if [ -n "$MISSING" ]; then
echo ""
echo "⚠️ New contributor email(s) not in AUTHOR_MAP:"
echo -e "$MISSING"
echo ""
echo "Please add mappings to scripts/release.py AUTHOR_MAP:"
echo -e "$MISSING" | while read -r line; do
email=$(echo "$line" | sed 's/^ *//' | cut -d' ' -f1)
[ -z "$email" ] && continue
echo " \"${email}\": \"<github-username>\","
done
echo ""
echo "To find the GitHub username for an email:"
echo " gh api 'search/users?q=EMAIL+in:email' --jq '.items[0].login'"
exit 1
else
echo "✅ All contributor emails are mapped in AUTHOR_MAP."
fi