orca/.github/workflows/cloud-deploy-relay-production.yml

name: Deploy Relay Production Candidate

on:
  workflow_dispatch:
    inputs:
      source-cell-id:
        description: Existing Terraform cell ID to evacuate
        required: true
        type: string
      target-cell-id:
        description: Distinct Terraform candidate cell ID
        required: true
        type: string
      mode:
        description: Audit/preflight are read-only; recover/continue resume committed work; disable/enable/reset/execute mutate admission
        required: true
        default: preflight
        type: choice
        options:
          - audit
          - preflight
          - recover-forward
          - continue-evacuation
          - disable-cell
          - enable-empty-cell
          - reset-empty-candidate
          - execute
      confirmation:
        description: Enter RECOVER_FORWARD, CONTINUE_EVACUATION, DISABLE_CELL, ENABLE_CELL, RESET_CANDIDATE, or EVACUATE for the matching mutation
        required: false
        type: string
      monitor-run-id:
        description: Successful fresh dry-run monitor workflow run ID
        required: false
        type: string
      monitor-run-attempt:
        description: Exact dry-run monitor workflow attempt
        required: false
        type: string

permissions:
  actions: read
  contents: read
  id-token: write

concurrency:
  group: production-cloud-sql-rollout
  cancel-in-progress: false

defaults:
  run:
    working-directory: cloud

jobs:
  candidate:
    if: ${{ vars.ORCA_CLOUD_OPERATIONS_ENABLED == 'true' && (github.ref == 'refs/heads/main') }}
    runs-on: blacksmith-2vcpu-ubuntu-2204
    environment: production
    env:
      GCP_PROJECT_ID: onorca-cloud
      DIRECTOR_ORIGIN: https://relay.onorca.dev
      ADMIN_AUDIENCE: https://relay.onorca.dev/v1/admin/drain
      SOURCE_CELL_ID: ${{ inputs.source-cell-id }}
      TARGET_CELL_ID: ${{ inputs.target-cell-id }}
      DEPLOY_MODE: ${{ inputs.mode }}
      MONITOR_RUN_ID: ${{ inputs.monitor-run-id }}
      MONITOR_RUN_ATTEMPT: ${{ inputs.monitor-run-attempt }}
    steps:
      - uses: actions/checkout@v4

      - name: Require fresh dry-run evidence reference
        if: ${{ inputs.mode != 'audit' && inputs.mode != 'preflight' }}
        run: |
          [[ "${MONITOR_RUN_ID}" =~ ^[0-9]+$ ]]
          [[ "${MONITOR_RUN_ATTEMPT}" =~ ^[1-9][0-9]*$ ]]

      - name: Download private dry-run evidence
        if: ${{ inputs.mode != 'audit' && inputs.mode != 'preflight' }}
        uses: actions/download-artifact@v4
        with:
          name: relay-monitor-dry-run-${{ inputs.monitor-run-id }}-${{ inputs.monitor-run-attempt }}
          path: ${{ runner.temp }}/relay-monitor-evidence
          github-token: ${{ github.token }}
          run-id: ${{ inputs.monitor-run-id }}

      - uses: pnpm/action-setup@v4
        with:
          package_json_file: cloud/package.json

      - uses: actions/setup-node@v4
        with:
          node-version: 24
          cache: pnpm
          cache-dependency-path: cloud/pnpm-lock.yaml

      - run: pnpm install --frozen-lockfile

      - uses: hashicorp/setup-terraform@v3
        with:
          terraform_wrapper: false

      - name: Verify dry-run artifact before cloud authentication
        if: ${{ inputs.mode != 'audit' && inputs.mode != 'preflight' }}
        run: |
          node dev/scripts/relay-monitor-evidence.mjs verify-restore \
            --directory "${RUNNER_TEMP}/relay-monitor-evidence" \
            --incident-id "relay-${MONITOR_RUN_ID}-dry-run" \
            --run-id "${MONITOR_RUN_ID}" \
            --run-attempt "${MONITOR_RUN_ATTEMPT}" \
            --commit-sha "${GITHUB_SHA}" \
            --mode dry-run

      - name: Reject previously consumed dry-run evidence
        if: ${{ inputs.mode != 'audit' && inputs.mode != 'preflight' }}
        env:
          GH_TOKEN: ${{ github.token }}
        run: |
          MARKER_NAME="relay-monitor-consumed-${MONITOR_RUN_ID}-${MONITOR_RUN_ATTEMPT}"
          COUNT="$(gh api \
            "/repos/${GITHUB_REPOSITORY}/actions/artifacts?name=${MARKER_NAME}&per_page=1" \
            --jq '.total_count')"
          test "${COUNT}" = "0"

      - id: google-auth
        uses: google-github-actions/auth@v2
        with:
          workload_identity_provider: ${{ vars.PRODUCTION_GCP_RELAY_DEPLOY_WORKLOAD_IDENTITY_PROVIDER }}
          service_account: ${{ vars.PRODUCTION_GCP_RELAY_DEPLOY_SERVICE_ACCOUNT }}
          token_format: id_token
          id_token_audience: https://relay.onorca.dev/v1/admin/drain
          id_token_include_email: true

      - uses: google-github-actions/setup-gcloud@v2

      - uses: ./.github/actions/cloud-sql-rollout-lease
        with:
          bucket: onorca-cloud-terraform-state
          object: terraform/state/cloud-sql-rollout/production.lock

      - name: Require explicit mutation confirmation
        if: ${{ inputs.mode != 'audit' && inputs.mode != 'preflight' }}
        env:
          CONFIRMATION: ${{ inputs.confirmation }}
        run: |
          if [[ "${DEPLOY_MODE}" = "execute" ]]; then
            test "${CONFIRMATION}" = "EVACUATE"
          elif [[ "${DEPLOY_MODE}" = "recover-forward" ]]; then
            test "${CONFIRMATION}" = "RECOVER_FORWARD"
          elif [[ "${DEPLOY_MODE}" = "continue-evacuation" ]]; then
            test "${CONFIRMATION}" = "CONTINUE_EVACUATION"
          elif [[ "${DEPLOY_MODE}" = "disable-cell" ]]; then
            test "${CONFIRMATION}" = "DISABLE_CELL"
          elif [[ "${DEPLOY_MODE}" = "enable-empty-cell" ]]; then
            test "${CONFIRMATION}" = "ENABLE_CELL"
          else
            test "${CONFIRMATION}" = "RESET_CANDIDATE"
          fi

      - name: Read reviewed Terraform topology
        run: |
          node dev/scripts/infra.mjs init --env production
          terraform -chdir=infra/terraform output -json relay_gce_cell_deployments > "${RUNNER_TEMP}/relay-gce-topology.json"
          RUNTIME_SERVICE_ACCOUNT="$(terraform -chdir=infra/terraform output -raw relay_runtime_service_account)"
          echo "RUNTIME_SERVICE_ACCOUNT=${RUNTIME_SERVICE_ACCOUNT}" >> "${GITHUB_ENV}"

      - name: Verify fresh dry-run evidence against live selector
        if: ${{ inputs.mode != 'audit' && inputs.mode != 'preflight' }}
        env:
          ORCA_RELAY_ADMIN_ID_TOKEN: ${{ steps.google-auth.outputs.id_token }}
        run: |
          node dev/scripts/relay-monitor-evidence.mjs verify-mutation \
            --directory "${RUNNER_TEMP}/relay-monitor-evidence" \
            --incident-id "relay-${MONITOR_RUN_ID}-dry-run" \
            --run-id "${MONITOR_RUN_ID}" \
            --run-attempt "${MONITOR_RUN_ATTEMPT}" \
            --commit-sha "${GITHUB_SHA}" \
            --mode dry-run \
            --mutation-mode "${DEPLOY_MODE}" \
            --source-cell-id "${SOURCE_CELL_ID}" \
            --director-origin "${DIRECTOR_ORIGIN}"

      - name: Recheck all live safety signals
        if: ${{ inputs.mode != 'audit' && inputs.mode != 'preflight' }}
        env:
          ORCA_RELAY_ADMIN_ID_TOKEN: ${{ steps.google-auth.outputs.id_token }}
        run: |
          pnpm incident:relay-preflight -- \
            --state-file "${RUNNER_TEMP}/relay-monitor-evidence/relay-${MONITOR_RUN_ID}-dry-run.state.json"

      - name: Create single-use dry-run marker
        if: ${{ inputs.mode != 'audit' && inputs.mode != 'preflight' }}
        run: |
          MARKER_NAME="relay-monitor-consumed-${MONITOR_RUN_ID}-${MONITOR_RUN_ATTEMPT}"
          mkdir -p "${RUNNER_TEMP}/relay-monitor-consumption"
          printf '%s\n' "${GITHUB_RUN_ID}" \
            > "${RUNNER_TEMP}/relay-monitor-consumption/${MARKER_NAME}"

      - name: Consume dry-run evidence
        if: ${{ inputs.mode != 'audit' && inputs.mode != 'preflight' }}
        uses: actions/upload-artifact@v4
        with:
          name: relay-monitor-consumed-${{ inputs.monitor-run-id }}-${{ inputs.monitor-run-attempt }}
          path: ${{ runner.temp }}/relay-monitor-consumption/relay-monitor-consumed-${{ inputs.monitor-run-id }}-${{ inputs.monitor-run-attempt }}
          retention-days: 90
          if-no-files-found: error

      - name: Preflight or evacuate exact GCE candidate
        env:
          ORCA_RELAY_ADMIN_ID_TOKEN: ${{ steps.google-auth.outputs.id_token }}
        run: |
          node dev/scripts/deploy-relay-gce-candidate.mjs \
            --project "${GCP_PROJECT_ID}" \
            --director-origin "${DIRECTOR_ORIGIN}" \
            --admin-audience "${ADMIN_AUDIENCE}" \
            --topology-file "${RUNNER_TEMP}/relay-gce-topology.json" \
            --source-cell-id "${SOURCE_CELL_ID}" \
            --target-cell-id "${TARGET_CELL_ID}" \
            --runtime-service-account "${RUNTIME_SERVICE_ACCOUNT}" \
            --mode "${DEPLOY_MODE}"