db-backup.yml

name: Database Dump

on:
  schedule:
    - cron: '0 0 * * 1' # Every Monday at midnight UTC
  workflow_dispatch:

jobs:
  backup:
    timeout-minutes: 120
    runs-on: blacksmith-32vcpu-ubuntu-2404
    permissions:
      contents: write
    steps:
      - uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
      - uses: pnpm/action-setup@0e279bb959325dab635dd2c09392533439d90093 # v6.0.8
      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
        with:
          node-version: '24'
          cache: pnpm
      - name: Install dependencies
        run: pnpm install --filter @semianalysisai/inferencex-db...
        env:
          CYPRESS_INSTALL_BINARY: '0'

      - name: Dump database
        env:
          DATABASE_READONLY_URL: ${{ secrets.DATABASE_READONLY_URL }}
        run: |
          set -euo pipefail
          DUMP_DIR="inferencex-dump-$(date -u +%Y-%m-%d)"
          pnpm admin:db:dump "$DUMP_DIR"
          echo "DUMP_DIR=${DUMP_DIR}" >> "$GITHUB_ENV"
          echo "TAG=db-dump/$(date -u +%Y-%m-%d)" >> "$GITHUB_ENV"

      - name: Compress and split dump
        run: |
          set -euo pipefail
          ( cd packages/db
            tar -cf - "$DUMP_DIR" \
              | xz -v -T0 --memlimit-compress=99% --lzma2=preset=9e,dict=192MiB \
              | split -b 1900m -d -a 2 - "${GITHUB_WORKSPACE}/${DUMP_DIR}.tar.xz.part" )
          echo "DUMP_GLOB=${DUMP_DIR}.tar.xz.part*" >> "$GITHUB_ENV"

      - name: Create release
        env:
          GH_TOKEN: ${{ github.token }}
        run: |
          # $DUMP_GLOB is intentionally unquoted so the shell expands it to every part file.
          gh release create "$TAG" $DUMP_GLOB \
            --title "DB Dump $(date -u +%Y-%m-%d)" \
            --notes 'Weekly full database dump (xz-compressed, split into parts under 2 GiB). Reassemble: `cat *.tar.xz.part* | xz -d | tar -x`' \
            --latest=false