Merge pull request #2002 from Molecule-AI/ci/merge-group-trigger-linter

ci: linter to catch missing merge_group triggers on required workflows

.github/workflows/check-merge-group-trigger.yml

@@ -0,0 +1,123 @@
+name: Check merge_group trigger on required workflows
+
+# Pre-merge guard against the deadlock pattern where a workflow whose
+# check is in `required_status_checks` lacks a `merge_group:` trigger.
+# Without it, GitHub merge queue stalls forever in AWAITING_CHECKS
+# because the required check can't fire on `gh-readonly-queue/...` refs.
+#
+# This workflow:
+#   1. Lists required status checks on the branch protection rule for `staging`
+#   2. For each required check, finds the workflow that produces it (by job
+#      name match)
+#   3. Fails if any such workflow lacks `merge_group:` in its triggers
+#
+# Reasoning for staging-only: main has its own CI gating model (PR review),
+# but staging is what the merge queue runs on, so it's the trigger that
+# matters.
+
+on:
+  pull_request:
+    paths:
+      - '.github/workflows/**.yml'
+      - '.github/workflows/**.yaml'
+  push:
+    branches: [staging, main]
+    paths:
+      - '.github/workflows/**.yml'
+      - '.github/workflows/**.yaml'
+  # Self-listen on merge_group so the linter passes its own queue run.
+  merge_group:
+    types: [checks_requested]
+
+jobs:
+  check:
+    name: Required workflows have merge_group trigger
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@v4
+      - name: Verify merge_group trigger on required-check workflows
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          REPO: ${{ github.repository }}
+        shell: bash
+        run: |
+          set -euo pipefail
+
+          # Branch we care about — the one merge queue runs on.
+          BRANCH=staging
+
+          # Pull the list of required status check contexts. If the branch
+          # has no protection or no required checks, exit clean — nothing
+          # to lint.
+          REQUIRED=$(gh api "repos/${REPO}/branches/${BRANCH}/protection/required_status_checks" \
+            --jq '.contexts[]' 2>/dev/null || true)
+          if [ -z "$REQUIRED" ]; then
+            echo "No required status checks on ${BRANCH} — nothing to verify."
+            exit 0
+          fi
+
+          echo "Required checks on ${BRANCH}:"
+          echo "${REQUIRED}" | sed 's/^/  - /'
+          echo
+
+          # Build a map: workflow file -> set of job names declared in it.
+          # We use yq if available, otherwise grep the `name:` lines under
+          # `jobs:`. Stick with grep for portability — runner image always
+          # has it; yq isn't in the default image as of 2026-04.
+          declare -A workflow_jobs
+          shopt -s nullglob
+          for wf in .github/workflows/*.yml .github/workflows/*.yaml; do
+            [ -f "$wf" ] || continue
+            # Extract the workflow name (the `name:` at file root).
+            wf_name=$(awk '/^name:[[:space:]]/ {sub(/^name:[[:space:]]+/,""); gsub(/^"|"$/,""); print; exit}' "$wf")
+            # Extract job step names from the `jobs:` block. A job step is:
+            #   - id under `jobs:` (key with 2-space indent followed by colon)
+            #   - the `name:` field inside that job (4-space indent)
+            # We collect both because required_status_checks contexts can
+            # match either, depending on how the workflow was authored.
+            jobs_block=$(awk '/^jobs:/{flag=1; next} flag' "$wf")
+            job_names=$(echo "$jobs_block" | awk '/^[[:space:]]{4}name:[[:space:]]/ {sub(/^[[:space:]]+name:[[:space:]]+/,""); gsub(/^["'"'"']|["'"'"']$/,""); print}')
+            workflow_jobs["$wf"]="${wf_name}"$'\n'"${job_names}"
+          done
+
+          # For each required check, find the workflow that produces it.
+          # Then verify that workflow lists merge_group as a trigger.
+          FAILED=0
+          while IFS= read -r check; do
+            [ -z "$check" ] && continue
+            owning_wf=""
+            for wf in "${!workflow_jobs[@]}"; do
+              if echo "${workflow_jobs[$wf]}" | grep -Fxq "$check"; then
+                owning_wf="$wf"
+                break
+              fi
+            done
+
+            if [ -z "$owning_wf" ]; then
+              echo "::warning::Required check '${check}' has no matching workflow in this repo. Skipping (may be from an external app)."
+              continue
+            fi
+
+            # Does the workflow's trigger list include merge_group?
+            # Match either bare `merge_group:` line or merge_group with
+            # subsequent indented config (types: [checks_requested]).
+            if grep -qE '^[[:space:]]*merge_group:' "$owning_wf"; then
+              echo "OK: '${check}' (in $owning_wf) — has merge_group trigger"
+            else
+              echo "::error file=${owning_wf}::Required check '${check}' is produced by ${owning_wf}, but the workflow does not declare a 'merge_group:' trigger. With merge queue enabled on ${BRANCH}, this will deadlock the queue (every PR sits AWAITING_CHECKS forever). Add this to the workflow's 'on:' block:"
+              echo "::error file=${owning_wf}::  merge_group:"
+              echo "::error file=${owning_wf}::    types: [checks_requested]"
+              FAILED=1
+            fi
+          done <<< "$REQUIRED"
+
+          if [ "$FAILED" -ne 0 ]; then
+            echo
+            echo "::error::Block. See errors above. Reference: $(grep -l 'reference_merge_queue' /dev/null 2>/dev/null || echo 'memory: reference_merge_queue_enablement.md')."
+            exit 1
+          fi
+
+          echo
+          echo "All required workflows on ${BRANCH} declare merge_group triggers."