adolf/.github/workflows/windows-blacksmith-testbox.yml

name: Windows Blacksmith Testbox

on:
  workflow_dispatch:
    inputs:
      testbox_id:
        type: string
        description: "Testbox session ID"
        required: true
      runner_label:
        type: string
        description: "Windows runner label"
        required: false
        default: "blacksmith-16vcpu-windows-2025"

permissions:
  contents: read

env:
  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"

jobs:
  windows:
    name: windows
    runs-on: ${{ inputs.runner_label }}
    timeout-minutes: 75
    defaults:
      run:
        shell: pwsh
    steps:
      - name: Begin Testbox
        shell: bash
        env:
          TESTBOX_ID: ${{ inputs.testbox_id }}
        run: |
          set -euo pipefail

          metadata_port="${METADATA_PORT:-}"
          if [ -z "$metadata_port" ]; then
            metadata_port="$(cat /proc/cmdline | tr ' ' '\n' | grep '^metadata_port=' | cut -d= -f2)"
          fi
          if [ -z "$metadata_port" ]; then
            echo "metadata_port not found in kernel cmdline" >&2
            exit 1
          fi

          metadata_addr="192.168.127.1:${metadata_port}"
          state=/tmp/.testbox
          mkdir -p "$state"
          chmod 700 "$state"

          installation_model_id="$(curl -s --connect-timeout 2 --max-time 5 "http://${metadata_addr}/installationModelID")"
          api_url="$(curl -s --connect-timeout 2 --max-time 5 "http://${metadata_addr}/backendURL")"
          auth_token="$(curl -s --connect-timeout 2 --max-time 5 "http://${metadata_addr}/stickyDiskToken")"

          if [ -z "$api_url" ] || [ -z "$installation_model_id" ] || [ -z "$auth_token" ]; then
            echo "could not read required Blacksmith metadata" >&2
            exit 1
          fi
          if ! jq -e 'type == "number"' <<<"$installation_model_id" >/dev/null; then
            echo "invalid Blacksmith installation model id: ${installation_model_id}" >&2
            exit 1
          fi

          if [ -n "${BLACKSMITH_HOSTNAME:-}" ]; then
            runner_host="$BLACKSMITH_HOSTNAME"
          else
            runner_host="${BLACKSMITH_HOST_PUBLIC_IP:-}"
          fi
          runner_ssh_port="${BLACKSMITH_SSH_PORT:-22}"

          hydrating_body="$RUNNER_TEMP/testbox-hydrating.json"
          hydrating_response="$RUNNER_TEMP/testbox-hydrating.response"
          jq -n \
            --arg testbox_id "$TESTBOX_ID" \
            --argjson installation_model_id "$installation_model_id" \
            --arg status "hydrating" \
            --arg ip_address "$runner_host" \
            --arg ssh_port "$runner_ssh_port" \
            --arg working_directory "$GITHUB_WORKSPACE" \
            --arg adopted_run_id "$GITHUB_RUN_ID" \
            '{
              testbox_id: $testbox_id,
              installation_model_id: $installation_model_id,
              status: $status,
              ip_address: $ip_address,
              ssh_port: $ssh_port,
              working_directory: $working_directory,
              adopted_run_id: $adopted_run_id,
              metadata: {}
            }' > "$hydrating_body"

          hydrating_http_code="$(curl -sS -L --post302 --post303 -o "$hydrating_response" -w '%{http_code}' \
            -X POST "${api_url}/api/testbox/phone-home" \
            -H "Content-Type: application/json" \
            -H "Authorization: Bearer ${auth_token}" \
            --data-binary @"$hydrating_body" || true)"

          echo "phone_home_hydrating_http=${hydrating_http_code}"
          if [[ ! "$hydrating_http_code" =~ ^2 ]]; then
            echo "Blacksmith phone-home hydrating failed; response body:" >&2
            cat "$hydrating_response" >&2 || true
            exit 1
          fi
          response="$(cat "$hydrating_response")"

          echo "$TESTBOX_ID" > "$state/testbox_id"
          echo "$installation_model_id" > "$state/installation_model_id"
          echo "$auth_token" > "$state/auth_token"
          echo "$api_url" > "$state/api_url"
          echo "$runner_host" > "$state/runner_host"
          echo "$runner_ssh_port" > "$state/runner_ssh_port"
          echo "$GITHUB_WORKSPACE" > "$state/working_directory"
          echo "$GITHUB_RUN_ID" > "$state/adopted_run_id"

          if [ -n "$response" ] && echo "$response" | jq -e . >/dev/null 2>&1; then
            echo "$response" | jq -r '.ssh_public_key // empty' > "$state/ssh_public_key"
            idle_timeout="$(echo "$response" | jq -r '.idle_timeout // empty')"
            echo "${idle_timeout:-10}" > "$state/idle_timeout"
            echo "phone-home response=json"
          else
            printf '%s\n' "$response" > "$state/ssh_public_key"
            echo "10" > "$state/idle_timeout"
            echo "phone-home response=raw"
          fi

          ssh_public_key="$(cat "$state/ssh_public_key" 2>/dev/null || true)"
          if [ -z "$ssh_public_key" ]; then
            echo "Blacksmith phone-home did not return an SSH public key; testbox cannot accept CLI connections." >&2
            exit 1
          fi
          mkdir -p ~/.ssh
          printf '%s\n' "$ssh_public_key" >> ~/.ssh/authorized_keys
          chmod 700 ~/.ssh
          chmod 600 ~/.ssh/authorized_keys

      - name: Checkout
        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6
        with:
          persist-credentials: false
          submodules: false

      - name: Prepare Windows shell
        run: |
          $ErrorActionPreference = "Stop"
          Write-Host "runner=$env:RUNNER_NAME"
          Write-Host "machine=$env:COMPUTERNAME"
          Write-Host ("os=" + [System.Environment]::OSVersion.VersionString)
          Write-Host ("powershell=" + $PSVersionTable.PSVersion.ToString())
          git --version

      - name: Run Testbox
        if: always()
        shell: bash
        run: |
          set -euo pipefail

          state=/tmp/.testbox
          test -d "$state"

          testbox_id="$(cat "$state/testbox_id")"
          installation_model_id="$(cat "$state/installation_model_id")"
          auth_token="$(cat "$state/auth_token")"
          idle_timeout="$(cat "$state/idle_timeout" 2>/dev/null || true)"
          idle_timeout="${idle_timeout:-10}"
          api_url="$(cat "$state/api_url")"
          runner_host="$(cat "$state/runner_host")"
          runner_ssh_port="$(cat "$state/runner_ssh_port")"
          working_directory="$(cat "$state/working_directory")"
          adopted_run_id="$(cat "$state/adopted_run_id")"
          if ! jq -e 'type == "number"' <<<"$installation_model_id" >/dev/null; then
            echo "invalid Blacksmith installation model id: ${installation_model_id}" >&2
            exit 1
          fi

          ready_body="$RUNNER_TEMP/testbox-ready.json"
          jq -n \
            --arg testbox_id "$testbox_id" \
            --argjson installation_model_id "$installation_model_id" \
            --arg status "ready" \
            --arg ip_address "$runner_host" \
            --arg ssh_port "$runner_ssh_port" \
            --arg working_directory "$working_directory" \
            --arg adopted_run_id "$adopted_run_id" \
            '{
              testbox_id: $testbox_id,
              installation_model_id: $installation_model_id,
              status: $status,
              ip_address: $ip_address,
              ssh_port: $ssh_port,
              working_directory: $working_directory,
              adopted_run_id: $adopted_run_id,
              metadata: {}
            }' > "$ready_body"

          http_code="$(curl -sS -L --post302 --post303 -o "$RUNNER_TEMP/testbox-ready.response" -w '%{http_code}' \
            -X POST "${api_url}/api/testbox/phone-home" \
            -H "Content-Type: application/json" \
            -H "Authorization: Bearer ${auth_token}" \
            --data-binary @"$ready_body" || true)"
          echo "phone_home_ready_http=${http_code}"
          if [[ ! "$http_code" =~ ^2 ]]; then
            echo "Blacksmith phone-home ready failed; response body:" >&2
            cat "$RUNNER_TEMP/testbox-ready.response" >&2 || true
            exit 1
          fi

          echo "============================================"
          echo "Testbox ready!"
          echo "  Testbox ID:         ${testbox_id}"
          echo "  Runner host:        ${runner_host}"
          echo "  SSH port:           ${runner_ssh_port}"
          echo "  Working directory:  ${working_directory}"
          echo "  Run ID:             ${adopted_run_id}"
          echo "  SSH:                ssh -p ${runner_ssh_port} runner@${runner_host}"
          echo "============================================"

          last_activity="$(date +%s)"
          idle_timeout_seconds=$(( idle_timeout * 60 ))

          while true; do
            sleep 30
            now="$(date +%s)"

            if netstat -na 2>/dev/null | grep ":${runner_ssh_port}" | grep -q ESTABLISHED; then
              last_activity="$now"
            elif [ -f ~/.testbox-last-activity ]; then
              file_mtime="$(stat -c %Y ~/.testbox-last-activity 2>/dev/null || stat -f %m ~/.testbox-last-activity)"
              if [ "$file_mtime" -gt "$last_activity" ]; then
                last_activity="$file_mtime"
              fi
            fi

            idle_seconds=$(( now - last_activity ))
            if [ "$idle_seconds" -ge "$idle_timeout_seconds" ]; then
              echo "Idle timeout reached (${idle_timeout} minutes). Shutting down."
              exit 0
            fi
          done

      - name: Testbox action marker
        if: ${{ false }}
        uses: useblacksmith/run-testbox@3f60ff9ceb2c10c3feefa87dc0c6490cffae059d