cleanup-branches.yml

name: Cleanup Branches

# =======================
# Branch Cleanup Workflow
# =======================
# Purpose: Automatically clean up old and merged branches
# Triggers: Weekly on Sundays or manual dispatch
# Jobs:
#   - cleanup-auto-generated: Removes old ga-data-update-* (keeps 1) and staging-aggregate-* branches (keeps 2)
#   - cleanup-merged: Removes branches already merged into master
#   - cleanup-stale: Removes branches with no activity for 1+ month (no open PRs)

on:
  schedule:
    - cron: '0 0 * * 0' # Run every Sunday at midnight UTC
  workflow_dispatch:
    inputs:
      dry_run:
        description: 'Dry run (do not delete)'
        required: false
        type: boolean
        default: false

env:
  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"

permissions:
  contents: write
  pull-requests: read

jobs:
  cleanup-auto-generated:
    name: Cleanup Auto-Generated Branches
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Configure Git
        run: |
          git config --global user.email "github-actions[bot]@users.noreply.github.com"
          git config --global user.name "github-actions[bot]"

      - name: Delete old auto-generated branches
        env:
          DRY_RUN: ${{ inputs.dry_run }}
        run: |
          echo "## 🤖 Auto-Generated Branch Cleanup" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          
          git fetch --all --prune
          
          # Patterns to clean up with their keep counts
          # Format: "pattern:keep_count"
          PATTERN_CONFIGS=("ga-data-update-:1" "staging-aggregate-:2")
          
          for config in "${PATTERN_CONFIGS[@]}"; do
            pattern="${config%%:*}"
            keep_count="${config##*:}"
            
            echo "### Pattern: \`$pattern*\` (keeping $keep_count)" >> $GITHUB_STEP_SUMMARY
            echo "" >> $GITHUB_STEP_SUMMARY
            
            # Get branches matching pattern, sort by name (timestamp), keep only old ones
            BRANCHES_TO_DELETE=$(git branch -r --list "origin/${pattern}*" --sort=-committerdate | tail -n +$((keep_count + 1)) | sed 's/origin\///' | xargs)
            
            if [ -z "$BRANCHES_TO_DELETE" ]; then
              echo "No old \`$pattern*\` branches to delete." >> $GITHUB_STEP_SUMMARY
              echo "" >> $GITHUB_STEP_SUMMARY
              continue
            fi
            
            for branch in $BRANCHES_TO_DELETE; do
              branch=$(echo "$branch" | xargs)
              if [ "$DRY_RUN" = "true" ]; then
                echo "[DRY RUN] Would delete: $branch"
                echo "- 🔍 \`$branch\` (dry run)" >> $GITHUB_STEP_SUMMARY
              else
                echo "Deleting: $branch"
                if git push origin --delete "$branch" 2>/dev/null; then
                  echo "- ✅ \`$branch\` deleted" >> $GITHUB_STEP_SUMMARY
                else
                  echo "- ❌ \`$branch\` failed to delete" >> $GITHUB_STEP_SUMMARY
                fi
              fi
            done
            echo "" >> $GITHUB_STEP_SUMMARY
          done
          exit 0  # Ensure the script exits successfully

  cleanup-merged:
    name: Cleanup Merged Branches
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Configure Git
        run: |
          git config --global user.email "github-actions[bot]@users.noreply.github.com"
          git config --global user.name "github-actions[bot]"

      - name: Delete merged branches
        env:
          DRY_RUN: ${{ inputs.dry_run }}
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          echo "Fetching all branches..."
          git fetch --all --prune --tags

          # Define protected branches
          PROTECTED_BRANCHES="master|gh-pages"

          echo "Finding merged branches..."
          # List remote branches merged into origin/master, exclude protected ones
          MERGED_BRANCHES=$(git branch -r --merged origin/master | grep -vE "HEAD|origin/($PROTECTED_BRANCHES)$" | sed 's/origin\///' | xargs)

          if [ -z "$MERGED_BRANCHES" ]; then
            echo "No merged branches to delete."
            echo "## 🧹 Merged Branch Cleanup" >> $GITHUB_STEP_SUMMARY
            echo "No merged branches found to delete." >> $GITHUB_STEP_SUMMARY
            exit 0
          fi

          echo "## 🧹 Merged Branch Cleanup" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          
          DELETED_COUNT=0
          SKIPPED_COUNT=0

          for branch in $MERGED_BRANCHES; do
            branch=$(echo "$branch" | xargs)
            
            # Skip auto-generated branches (handled by cleanup-auto-generated job)
            if [[ "$branch" =~ ^(staging-aggregate-|ga-data-update-) ]]; then
              echo "Skipping $branch (auto-generated, handled separately)"
              SKIPPED_COUNT=$((SKIPPED_COUNT + 1))
              continue
            fi
            
            if [ "$DRY_RUN" = "true" ]; then
              echo "[DRY RUN] Would delete: $branch"
              echo "- 🔍 \`$branch\` (dry run)" >> $GITHUB_STEP_SUMMARY
            else
              echo "Deleting: $branch"
              if git push origin --delete "$branch" 2>/dev/null; then
                echo "- ✅ \`$branch\` deleted" >> $GITHUB_STEP_SUMMARY
                DELETED_COUNT=$((DELETED_COUNT + 1))
              else
                echo "- ❌ \`$branch\` failed to delete" >> $GITHUB_STEP_SUMMARY
              fi
            fi
          done
          
          echo "" >> $GITHUB_STEP_SUMMARY
          echo "**Summary:** Deleted $DELETED_COUNT branches, skipped $SKIPPED_COUNT" >> $GITHUB_STEP_SUMMARY
          exit 0  # Ensure the script exits successfully

  cleanup-stale:
    name: Cleanup Stale Branches
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Configure Git
        run: |
          git config --global user.email "github-actions[bot]@users.noreply.github.com"
          git config --global user.name "github-actions[bot]"

      - name: Delete stale branches
        env:
          DRY_RUN: ${{ inputs.dry_run }}
          MONTHS_THRESHOLD: 1
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          # Define protected branches
          PROTECTED_BRANCHES="master|gh-pages"

          echo "Fetching all branches..."
          git fetch --all --prune --tags

          # Calculate threshold date
          THRESHOLD_DATE=$(date -d "-$MONTHS_THRESHOLD months" +%s)
          echo "Threshold date: $(date -d "@$THRESHOLD_DATE")"

          echo "## 🕰️ Stale Branch Cleanup" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          echo "Branches with no commits in $MONTHS_THRESHOLD months and no open PRs." >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY

          DELETED_COUNT=0
          SKIPPED_COUNT=0

          # Collect branches into array to avoid subshell issues
          mapfile -t BRANCHES < <(git branch -r | grep -vE "HEAD|origin/($PROTECTED_BRANCHES)$" | xargs -n1)

          for branch in "${BRANCHES[@]}"; do
            branch=$(echo "$branch" | xargs)
            clean_branch_name=${branch#origin/}
            
            # Skip auto-generated branches (handled by cleanup-auto-generated job)
            if [[ "$clean_branch_name" =~ ^(staging-aggregate-|ga-data-update-) ]]; then
              echo "Skipping $clean_branch_name (auto-generated, handled separately)"
              continue
            fi

            # Get last commit date for the branch
            last_commit_date=$(git log -1 --format=%ct "$branch" 2>/dev/null || echo "0")

            # Check if branch has open PR
            open_pr_count=$(gh pr list -H "$clean_branch_name" --state open --json number 2>/dev/null | jq '. | length' || echo "0")

            if [ "$open_pr_count" -gt 0 ]; then
              echo "Skipping $clean_branch_name (Has open PR)"
              SKIPPED_COUNT=$((SKIPPED_COUNT + 1))
              continue
            fi

            if [ "$last_commit_date" -lt "$THRESHOLD_DATE" ]; then
              LAST_DATE=$(date -d "@$last_commit_date" '+%Y-%m-%d')
              echo "Branch '$clean_branch_name' is stale (Last commit: $LAST_DATE)"

              if [ "$DRY_RUN" = "true" ]; then
                echo "[DRY RUN] Would delete: $clean_branch_name"
                echo "- 🔍 \`$clean_branch_name\` (last: $LAST_DATE) - dry run" >> $GITHUB_STEP_SUMMARY
              else
                echo "Deleting: $clean_branch_name"
                if git push origin --delete "$clean_branch_name" 2>/dev/null; then
                  echo "- ✅ \`$clean_branch_name\` deleted (last: $LAST_DATE)" >> $GITHUB_STEP_SUMMARY
                  DELETED_COUNT=$((DELETED_COUNT + 1))
                else
                  echo "- ❌ \`$clean_branch_name\` failed to delete" >> $GITHUB_STEP_SUMMARY
                fi
              fi
            fi
          done
          
          echo "" >> $GITHUB_STEP_SUMMARY
          echo "**Summary:** Deleted $DELETED_COUNT stale branches, skipped $SKIPPED_COUNT (have open PRs)" >> $GITHUB_STEP_SUMMARY
          exit 0  # Ensure the script exits successfully even when branches are skipped