From 557131b8d88826cbdd6cfe411826cbf94e4a6619 Mon Sep 17 00:00:00 2001 From: Filip Skokan Date: Wed, 8 Jul 2026 10:52:18 +0200 Subject: [PATCH 1/2] tools: prefilter commit queue metadata Run `git node metadata --readme` in the lightweight commit queue selector before starting the checkout-heavy landing job. The selector keeps `commit-queue` on PRs that are only waiting for approvals, TSC approval count, or wait time. Other metadata failures continue to the existing commit queue script so failure labels and comments are still produced by the current landing path. Fetch age-based, fast-track, and broader queue buckets before deduplicating the list so not-yet-ready PRs do not crowd out PRs that would otherwise have been selected. Signed-off-by: Filip Skokan --- .github/workflows/commit-queue.yml | 150 ++++++++++++++++++++++++++--- doc/contributing/commit-queue.md | 141 ++++++++++++++++++--------- 2 files changed, 229 insertions(+), 62 deletions(-) diff --git a/.github/workflows/commit-queue.yml b/.github/workflows/commit-queue.yml index 7af71226871159..7a4fb9f93a22cf 100644 --- a/.github/workflows/commit-queue.yml +++ b/.github/workflows/commit-queue.yml @@ -30,30 +30,150 @@ jobs: outputs: numbers: ${{ steps.get_mergeable_prs.outputs.numbers }} steps: - - name: Get Pull Requests - id: get_mergeable_prs + - name: Get Pull Request Candidates + id: get_candidate_prs run: | - prs=$(gh pr list \ + list_prs() { + gh pr list \ --repo "$GITHUB_REPOSITORY" \ --base "$GITHUB_REF_NAME" \ --label 'commit-queue' \ + "$@" \ --json 'number' \ - --search "created:<=$(date --date="2 days ago" +"%Y-%m-%dT%H:%M:%S%z") -label:blocked" \ -t '{{ range . }}{{ .number }} {{ end }}' \ - --limit 100) - fast_track_prs=$(gh pr list \ - --repo "$GITHUB_REPOSITORY" \ - --base "$GITHUB_REF_NAME" \ - --label 'commit-queue' \ + --limit 100 + } + ready_prs=$(list_prs \ + --search "created:<=$(date --date="2 days ago" +"%Y-%m-%dT%H:%M:%S%z") -label:blocked") + fast_track_prs=$(list_prs \ --label 'fast-track' \ - --search "-label:blocked" \ - --json 'number' \ - -t '{{ range . }}{{ .number }} {{ end }}' \ - --limit 100) - numbers=$(echo $prs' '$fast_track_prs | jq -r -s 'unique | join(" ")') - echo "numbers=$numbers" >> "$GITHUB_OUTPUT" + --search "-label:blocked") + queued_prs=$(list_prs \ + --search "-label:blocked") + candidates=$(printf '%s %s %s\n' "$ready_prs" "$fast_track_prs" "$queued_prs" | + jq -r -s 'reduce .[] as $pr ([]; if index($pr) then . else . + [$pr] end) | join(" ")') + echo "candidates=$candidates" >> "$GITHUB_OUTPUT" env: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + + - name: Install Node.js + if: steps.get_candidate_prs.outputs.candidates != '' + uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0 + with: + node-version: ${{ env.NODE_VERSION }} + - name: Install @node-core/utils + if: steps.get_candidate_prs.outputs.candidates != '' + run: npm install -g @node-core/utils + + - name: Filter Pull Requests + if: steps.get_candidate_prs.outputs.candidates != '' + id: get_mergeable_prs + run: | + fail_selector() { + echo "$1" + exit 1 + } + + metadata_has_non_deferred_output() { + METADATA_NON_DEFERRED=0 + + if grep -Eq \ + -e 'This PR has conflicts that must be resolved' \ + -e 'This PR was merged on ' \ + -e 'This PR was closed on ' \ + -e 'PR author is a new contributor:' \ + -e 'No commits detected' \ + -e 'Requested Changes: [0-9]+' \ + -e 'Commits were pushed since the last approving review:' \ + -e '[0-9]+ failure\(s\) on the last Jenkins CI run' \ + -e '[0-9]+ GitHub CI job\(s\) failed:' \ + -e '[0-9]+ GitHub CI job\(s\) cancelled:' \ + -e 'GitHub CI failed with status:' \ + -e 'No Jenkins CI runs detected' \ + -e 'No full Jenkins CI runs detected' \ + -e 'Commits were pushed after the last .* CI run:' \ + -e 'Last Jenkins CI still running' \ + -e 'No GitHub CI runs detected' \ + -e 'GitHub CI is still running' \ + -e 'Mismatched commits:' \ + -e 'Failed to apply patches' \ + -e 'Patch still contains lint errors' \ + output; then + METADATA_NON_DEFERRED=1 + fi + } + + classify_metadata_output() { + METADATA_DEFERRED=0 + + metadata_has_non_deferred_output + if [ "$METADATA_NON_DEFERRED" -eq 1 ]; then + return + fi + + if grep -Eq \ + -e 'Approvals: 0' \ + -e 'No approving reviews found' \ + -e 'This PR needs to wait .* to land' \ + -e 'semver-major requires at least 2 TSC approvals' \ + output; then + METADATA_DEFERRED=1 + fi + } + + repository="${GITHUB_REPOSITORY#*/}" + readme="${RUNNER_TEMP}/README.md" + readme_base64="${RUNNER_TEMP}/README.md.base64" + + ncu-config set branch "${GITHUB_REF_NAME}" + ncu-config set username "$USERNAME" + ncu-config set token "$GITHUB_TOKEN" + ncu-config set jenkins_token "$JENKINS_TOKEN" + ncu-config set repo "$repository" + ncu-config set owner "${GITHUB_REPOSITORY_OWNER}" + + if ! gh api "repos/${GITHUB_REPOSITORY}/contents/README.md?ref=${GITHUB_REF_NAME}" \ + --jq '.content' > "$readme_base64"; then + fail_selector "failed to download README.md" + fi + + if ! base64 -d < "$readme_base64" > "$readme"; then + fail_selector "failed to decode README.md" + fi + + numbers= + # shellcheck disable=SC2086 + for pr in $CANDIDATES; do + if git node metadata "$pr" \ + --owner "$GITHUB_REPOSITORY_OWNER" \ + --repo "$repository" \ + --readme "$readme" > output 2>&1; then + numbers="$numbers $pr" + rm output + continue + fi + + classify_metadata_output + if [ "$METADATA_DEFERRED" -eq 1 ]; then + echo "pr ${pr} skipped, not ready to land" + cat output + rm output + continue + fi + + echo "pr ${pr} will be handled by the commit queue" + cat output + numbers="$numbers $pr" + rm output + done + + numbers=$(echo "$numbers" | xargs) + echo "numbers=$numbers" >> "$GITHUB_OUTPUT" + env: + CANDIDATES: ${{ steps.get_candidate_prs.outputs.candidates }} + USERNAME: ${{ secrets.JENKINS_USER }} + GITHUB_TOKEN: ${{ secrets.GH_USER_TOKEN }} + JENKINS_TOKEN: ${{ secrets.JENKINS_TOKEN }} commitQueue: needs: get_mergeable_prs if: needs.get_mergeable_prs.outputs.numbers != '' diff --git a/doc/contributing/commit-queue.md b/doc/contributing/commit-queue.md index 6cedc833029e12..5509b9c98d31fd 100644 --- a/doc/contributing/commit-queue.md +++ b/doc/contributing/commit-queue.md @@ -1,12 +1,15 @@ # Commit queue -_tl;dr: You can land pull requests by adding the `commit-queue` label to it._ +_tl;dr: You can ask the queue to land pull requests by adding the +`commit-queue` label to them._ Commit Queue is a feature for the project which simplifies the landing process by automating it via GitHub Actions. With it, collaborators can -land pull requests by adding the `commit-queue` label to a PR. All -checks will run via `@node-core/utils`, and if the pull request is ready to -land, the Action will rebase it and push to `main`. +queue pull requests for landing by adding the `commit-queue` label to a PR. The +selector checks readiness with `@node-core/utils`. If the selector determines +that the pull request is not ready to land yet, the queue will leave the label +in place and retry later. If it is ready, the Action will rebase it and land it +on `main`. This document gives an overview of how the Commit Queue works, as well as implementation details, reasoning for design choices, and current limitations. @@ -15,22 +18,31 @@ implementation details, reasoning for design choices, and current limitations. From a high-level, the Commit Queue works as follow: -1. Collaborators will add `commit-queue` label to pull requests ready to land -2. Every five minutes the queue will do the following for each mergeable pull request - with the label: - 1. Check if the PR also has a `request-ci` label (if it has, skip this PR +1. Collaborators will add `commit-queue` label to pull requests they want the + queue to land. The label can be added before the pull request has completed + its wait time or approvals, or before requested CI has finished. The commit + queue does not request CI on its own. +2. On each scheduled run, the queue builds a candidate list from open pull + requests with the label. The workflow uses a five-minute cron, but GitHub + Actions scheduled workflows are not guaranteed to run exactly every five + minutes. For each candidate, the queue will: + 1. Run a metadata-only readiness check that uses `@node-core/utils` without + checking out the repository + 2. If the metadata check says the PR is not ready yet only because it is + waiting for approvals, TSC approval count, or wait time, keep the + `commit-queue` label and skip this PR until a later queue run + 3. Check if the PR also has a `request-ci` label (if it has, skip this PR since it's pending a CI run) - 2. Check if the last Jenkins CI is finished running (if it is not, skip this - PR) - 3. Remove the `commit-queue` label - 4. Run `git node land --oneCommitMax` - 5. If it fails: + 4. Check whether GitHub checks are still running (if they are, skip this PR) + 5. Remove the `commit-queue` label and run + `git node land --oneCommitMax` + 6. If it fails: 1. Abort `git node land` session 2. Add `commit-queue-failed` label to the PR 3. Leave a comment on the PR with the output from `git node land` 4. Skip next steps, go to next PR in the queue - 6. If it succeeds: - 1. Push the changes to nodejs/node + 7. If it succeeds: + 1. Push or merge the changes into nodejs/node 2. Leave a comment on the PR with `Landed in ...` 3. Close the PR 4. Go to next PR in the queue @@ -51,7 +63,7 @@ of the commit queue: guidelines or be a valid [`fixup!`](https://git-scm.com/docs/git-commit#Documentation/git-commit.txt---fixupamendrewordltcommitgt) commit that will be correctly handled by the [`--autosquash`](https://git-scm.com/docs/git-rebase#Documentation/git-rebase.txt---autosquash) option -2. A CI must've ran and succeeded since the last change on the PR +2. A CI must have run and succeeded since the last change on the PR 3. A collaborator must have approved the PR since the last change 4. Only Jenkins CI and GitHub Actions are checked (V8 CI and CITGM are ignored) 5. The PR must target the `main` branch (PRs opened against other branches, such @@ -59,10 +71,15 @@ of the commit queue: ## Implementation -The [action](../../.github/workflows/commit-queue.yml) will run on scheduler -events every five minutes. Five minutes is the smallest number accepted by -the scheduler. The scheduler is not guaranteed to run every five minutes, it -might take longer between runs. +The [action](../../.github/workflows/commit-queue.yml) runs on scheduled events. +It uses a five-minute cron because that is the smallest interval accepted by +GitHub Actions. Scheduled workflows are not guaranteed to run exactly at that +cadence and might take longer between runs. + +The workflow also uses a concurrency group so only one commit queue run can be +active at a time. If a scheduled run starts while a previous run is still +running, GitHub Actions keeps at most one pending run for the same concurrency +group. A newer pending run replaces an older pending run. Using the scheduler is preferable over using pull\_request\_target for two reasons: @@ -76,41 +93,71 @@ reasons: commit, meaning we wouldn't be able to use it for already opened PRs without rebasing them first. -`@node-core/utils` is configured with a personal token and -a Jenkins token from -[@nodejs-github-bot](https://github.com/nodejs/github-bot). -`octokit/graphql-action` is used to fetch all pull requests with the -`commit-queue` label. The output is a JSON payload, so `jq` is used to turn -that into a list of PR ids we can pass as arguments to -[`commit-queue.sh`](../../tools/actions/commit-queue.sh). - -> The personal token only needs permission for public repositories and to read -> profiles, we can use the GITHUB\_TOKEN for write operations. Jenkins token is +`@node-core/utils` is configured with a personal token and a Jenkins token from +[@nodejs-github-bot](https://github.com/nodejs/github-bot). The workflow starts +with a small selector step that uses GitHub CLI to fetch pull requests with the +`commit-queue` label. It first fetches the same age-based and fast-track buckets +the queue used before accepting early queue requests, then fetches the broader +queue and de-duplicates the result. This keeps not-yet-ready PRs from crowding +out PRs that the previous query would have selected if GitHub paginates or caps +a query result. + +If there are candidate PRs, the selector installs `@node-core/utils`, downloads +the target branch's README without checking out the repository, and runs +`git node metadata --readme` for each candidate. This uses the same +`@node-core/utils` PR readiness checks as `git node land`, but does not clone, +fetch, or merge the PR. PRs that fail only because they are waiting for +approvals, TSC approval count, or wait time keep the `commit-queue` label and +are retried later. PRs whose metadata succeeds, plus PRs with other metadata +failures, are turned into the list of PR ids passed as arguments to +[`commit-queue.sh`](../../tools/actions/commit-queue.sh). Those failures +continue through `commit-queue.sh` so the queue removes the label, adds +`commit-queue-failed`, and leaves the failure comment in the same place as +before. + +If the selector cannot run the metadata check, the workflow fails before +starting the landing job. That keeps PR labels unchanged so the queue can retry +on a later scheduled run. + +> The personal token needs permission for public repositories and to read +> profiles. It is used by `@node-core/utils` and by the landing job for +> checkout, label and comment updates, merging, and pushing. Jenkins token is > required to check CI status. `commit-queue.sh` receives the following positional arguments: 1. The repository owner 2. The repository name -3. The Action GITHUB\_TOKEN -4. Every positional argument starting at this one will be a pull request ID of +3. Every positional argument starting at this one will be a pull request ID of a pull request with commit-queue set. -The script will iterate over the pull requests. `ncu-ci` is used to check if -the last CI is still pending, and calls to the GitHub API are used to check if -the PR is waiting for CI to start (`request-ci` label). The PR is skipped if CI -is pending. No other CI validation is done here since `git node land` will fail -if the last CI failed. - -The script removes the `commit-queue` label. It then runs `git node land`, -forwarding stdout and stderr to a file. If any errors happen, -`git node land --abort` is run, and then a `commit-queue-failed` label is added -to the PR, as well as a comment with the output of `git node land`. - -If no errors happen during `git node land`, the script will use the -`GITHUB_TOKEN` to push the changes to `main`, and then will leave a -`Landed in ...` comment in the PR, and then will close it. Iteration continues -until all PRs have done the steps above. +The script will iterate over the pull requests. GitHub CLI is used to check if +the PR is waiting for CI to start (`request-ci` label) or still has pending +GitHub checks. The PR is skipped if CI is pending. No other CI validation is +done here since `git node land` will fail if the last CI failed. + +The script removes the `commit-queue` label, then runs `git node land`, +forwarding stdout and stderr to a file. PRs that are only waiting for approval, +wait time, or CI should have already been filtered by the metadata check. If the +PR state changes between the selector job and the landing job, the landing job +uses the same failure path as other `git node land` errors: it runs +`git node land --abort`, adds a `commit-queue-failed` label to the PR, and +leaves a comment with the output of `git node land`. + +Fast-tracked PRs use the metadata check before the landing job. If the +fast-track request has not yet received enough collaborator thumbs-up, the queue +keeps the `commit-queue` label and retries until either the fast-track request +is approved or the PR becomes landable through the regular wait-time rules. The +commit queue does not create the fast-track request comment; that is handled +when the `fast-track` label is added. If that comment is missing, the queue +reports the failure instead of keeping the PR queued. + +If no errors happen during `git node land`, the script either pushes the direct +rebase landing to `main` or uses GitHub's squash merge API for single-commit and +fixup landings. It then leaves a `Landed in ...` comment in the PR. GitHub +closes PRs merged through the merge API automatically; for direct pushes, the +script closes the PR. Iteration continues until all PRs have done the steps +above. ## Reverting broken commits From da1c1a285472a722703373b3c48acae3f697bc2c Mon Sep 17 00:00:00 2001 From: Filip Skokan Date: Wed, 8 Jul 2026 14:52:52 +0200 Subject: [PATCH 2/2] fixup! tools: prefilter commit queue metadata --- .github/workflows/commit-queue.yml | 88 +++++++++++------------------- doc/contributing/commit-queue.md | 32 +++++++---- 2 files changed, 53 insertions(+), 67 deletions(-) diff --git a/.github/workflows/commit-queue.yml b/.github/workflows/commit-queue.yml index 7a4fb9f93a22cf..a695a0c67b477f 100644 --- a/.github/workflows/commit-queue.yml +++ b/.github/workflows/commit-queue.yml @@ -74,53 +74,6 @@ jobs: exit 1 } - metadata_has_non_deferred_output() { - METADATA_NON_DEFERRED=0 - - if grep -Eq \ - -e 'This PR has conflicts that must be resolved' \ - -e 'This PR was merged on ' \ - -e 'This PR was closed on ' \ - -e 'PR author is a new contributor:' \ - -e 'No commits detected' \ - -e 'Requested Changes: [0-9]+' \ - -e 'Commits were pushed since the last approving review:' \ - -e '[0-9]+ failure\(s\) on the last Jenkins CI run' \ - -e '[0-9]+ GitHub CI job\(s\) failed:' \ - -e '[0-9]+ GitHub CI job\(s\) cancelled:' \ - -e 'GitHub CI failed with status:' \ - -e 'No Jenkins CI runs detected' \ - -e 'No full Jenkins CI runs detected' \ - -e 'Commits were pushed after the last .* CI run:' \ - -e 'Last Jenkins CI still running' \ - -e 'No GitHub CI runs detected' \ - -e 'GitHub CI is still running' \ - -e 'Mismatched commits:' \ - -e 'Failed to apply patches' \ - -e 'Patch still contains lint errors' \ - output; then - METADATA_NON_DEFERRED=1 - fi - } - - classify_metadata_output() { - METADATA_DEFERRED=0 - - metadata_has_non_deferred_output - if [ "$METADATA_NON_DEFERRED" -eq 1 ]; then - return - fi - - if grep -Eq \ - -e 'Approvals: 0' \ - -e 'No approving reviews found' \ - -e 'This PR needs to wait .* to land' \ - -e 'semver-major requires at least 2 TSC approvals' \ - output; then - METADATA_DEFERRED=1 - fi - } - repository="${GITHUB_REPOSITORY#*/}" readme="${RUNNER_TEMP}/README.md" readme_base64="${RUNNER_TEMP}/README.md.base64" @@ -144,27 +97,52 @@ jobs: numbers= # shellcheck disable=SC2086 for pr in $CANDIDATES; do + metadata="${RUNNER_TEMP}/metadata-${pr}.json" + output="${RUNNER_TEMP}/metadata-${pr}.txt" if git node metadata "$pr" \ --owner "$GITHUB_REPOSITORY_OWNER" \ --repo "$repository" \ - --readme "$readme" > output 2>&1; then + --readme "$readme" \ + --json > "$metadata" 2> "$output"; then + metadata_status=0 + else + metadata_status=$? + fi + + if [ -s "$output" ]; then + cat "$output" + fi + + case "$metadata_status" in + 0|2[0-9]|4[0-9]) ;; + *) + fail_selector "git node metadata failed for pr ${pr} with exit code ${metadata_status}" + ;; + esac + + metadata_exit_code=$(jq -r '.exitCode' "$metadata") || + fail_selector "failed to parse metadata JSON for pr ${pr}" + if [ "$metadata_exit_code" != "$metadata_status" ]; then + fail_selector "metadata JSON exitCode mismatch for pr ${pr}" + fi + metadata_reason_codes=$(jq -r '.reasonCodes | join(", ")' "$metadata") || + fail_selector "failed to parse metadata reason codes for pr ${pr}" + + if [ "$metadata_status" -eq 0 ]; then + echo "pr ${pr} is ready for the commit queue" numbers="$numbers $pr" - rm output continue fi - classify_metadata_output - if [ "$METADATA_DEFERRED" -eq 1 ]; then + if [ "$metadata_status" -ge 20 ] && [ "$metadata_status" -le 29 ]; then echo "pr ${pr} skipped, not ready to land" - cat output - rm output + echo "reason codes: ${metadata_reason_codes}" continue fi echo "pr ${pr} will be handled by the commit queue" - cat output + echo "reason codes: ${metadata_reason_codes}" numbers="$numbers $pr" - rm output done numbers=$(echo "$numbers" | xargs) diff --git a/doc/contributing/commit-queue.md b/doc/contributing/commit-queue.md index 5509b9c98d31fd..c2ee8f201bde5f 100644 --- a/doc/contributing/commit-queue.md +++ b/doc/contributing/commit-queue.md @@ -28,9 +28,9 @@ From a high-level, the Commit Queue works as follow: minutes. For each candidate, the queue will: 1. Run a metadata-only readiness check that uses `@node-core/utils` without checking out the repository - 2. If the metadata check says the PR is not ready yet only because it is - waiting for approvals, TSC approval count, or wait time, keep the - `commit-queue` label and skip this PR until a later queue run + 2. If the metadata check exits with a deferrable readiness code, meaning + the PR is only waiting for approvals, TSC approval count, or wait time, + keep the `commit-queue` label and skip this PR until a later queue run 3. Check if the PR also has a `request-ci` label (if it has, skip this PR since it's pending a CI run) 4. Check whether GitHub checks are still running (if they are, skip this PR) @@ -104,16 +104,24 @@ a query result. If there are candidate PRs, the selector installs `@node-core/utils`, downloads the target branch's README without checking out the repository, and runs -`git node metadata --readme` for each candidate. This uses the same +`git node metadata --readme --json` for each candidate. This uses the same `@node-core/utils` PR readiness checks as `git node land`, but does not clone, -fetch, or merge the PR. PRs that fail only because they are waiting for -approvals, TSC approval count, or wait time keep the `commit-queue` label and -are retried later. PRs whose metadata succeeds, plus PRs with other metadata -failures, are turned into the list of PR ids passed as arguments to -[`commit-queue.sh`](../../tools/actions/commit-queue.sh). Those failures -continue through `commit-queue.sh` so the queue removes the label, adds -`commit-queue-failed`, and leaves the failure comment in the same place as -before. +fetch, or merge the PR. The selector consumes the structured metadata result +and its exit code instead of matching human-readable output: + +* exit code `0`: the PR is ready and is passed to + [`commit-queue.sh`](../../tools/actions/commit-queue.sh) +* exit codes `20`-`29`: the PR is not ready for a deferrable metadata reason, + so it keeps the `commit-queue` label and is retried later +* exit codes `40`-`49`: the PR has a hard or mixed metadata readiness failure + and is passed to [`commit-queue.sh`](../../tools/actions/commit-queue.sh) + +The `20`-`29` exit code range is reserved by `@node-core/utils` for deferrable +metadata readiness states, and `40`-`49` is reserved for hard metadata failure +states. Unknown selector failures fail the workflow before starting the landing +job. PRs passed through with exit code `40`-`49` continue through +`commit-queue.sh` so the queue removes the label, adds `commit-queue-failed`, +and leaves the failure comment in the same place as before. If the selector cannot run the metadata check, the workflow fails before starting the landing job. That keeps PR labels unchanged so the queue can retry