openclaw/.github/workflows/windows-testbox-probe.yml

name: Windows Testbox Probe

on:
  workflow_dispatch:
    inputs:
      target_ref:
        description: "Git ref or SHA to check out"
        required: false
        default: "main"
        type: string
      runner_label:
        description: "Windows runner label"
        required: false
        default: "blacksmith-16vcpu-windows-2025"
        type: choice
        options:
          - blacksmith-16vcpu-windows-2025
          - blacksmith-32vcpu-windows-2025
          - windows-2025
      keepalive_minutes:
        description: "Minutes to keep the Windows runner alive for SSH inspection"
        required: false
        default: "20"
        type: string
      require_wsl2:
        description: "Fail the run when WSL2 is unavailable"
        required: false
        default: false
        type: boolean
      import_ubuntu_wsl2:
        description: "Import a throwaway Ubuntu WSL2 distro when none is installed"
        required: false
        default: false
        type: boolean
      enable_wsl2_features:
        description: "Try enabling Windows WSL2/VM optional features before probing"
        required: false
        default: false
        type: boolean
      run_windows_ci:
        description: "Run the focused Windows CI shard and native Scheduled Task proof"
        required: false
        default: false
        type: boolean

permissions:
  contents: read

env:
  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"

jobs:
  probe:
    name: Windows probe
    runs-on: ${{ inputs.runner_label }}
    timeout-minutes: 75
    defaults:
      run:
        shell: pwsh
    steps:
      - name: Checkout
        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
        with:
          ref: ${{ inputs.target_ref || github.ref }}
          persist-credentials: false
          submodules: false

      - name: Probe native Windows
        env:
          TARGET_REF: ${{ inputs.target_ref || github.ref }}
        run: |
          $ErrorActionPreference = "Stop"
          Write-Host "runner=$env:RUNNER_NAME"
          Write-Host "machine=$env:COMPUTERNAME"
          Write-Host "workspace=$env:GITHUB_WORKSPACE"
          Write-Host "target_ref=$env:TARGET_REF"
          Write-Host ("os=" + [System.Environment]::OSVersion.VersionString)
          Write-Host ("arch=" + [System.Runtime.InteropServices.RuntimeInformation]::OSArchitecture)
          Write-Host ("powershell=" + $PSVersionTable.PSVersion.ToString())
          cmd.exe /c ver
          git --version

      - name: Probe WSL2
        id: wsl2
        env:
          ENABLE_WSL2_FEATURES: ${{ inputs.enable_wsl2_features }}
          IMPORT_UBUNTU_WSL2: ${{ inputs.import_ubuntu_wsl2 }}
        run: |
          $ErrorActionPreference = "Continue"
          $ok = $false
          $restartRequired = $false

          function Resolve-UbuntuWslRootfsUrl {
            $osArch = ([System.Runtime.InteropServices.RuntimeInformation]::OSArchitecture).ToString().ToLowerInvariant()
            switch ($osArch) {
              "x64" { $wslArch = "amd64" }
              "arm64" { $wslArch = "arm64" }
              default { throw "Unsupported Windows architecture for Ubuntu WSL rootfs: $osArch" }
            }
            Write-Host "ubuntu_wsl_rootfs_arch=$wslArch"
            "https://cloud-images.ubuntu.com/wsl/releases/24.04/current/ubuntu-noble-wsl-$wslArch-wsl.rootfs.tar.gz"
          }

          function Invoke-WslText {
            param([string[]] $Arguments)
            $output = & wsl.exe @Arguments 2>&1
            $code = $LASTEXITCODE
            $text = (($output | ForEach-Object { "$_" }) -join "`n") -replace "`0", ""
            [pscustomobject]@{ Code = $code; Text = $text }
          }

          function Get-WslDistros {
            $result = Invoke-WslText -Arguments @("--list", "--quiet")
            $result.Text -split "\r?\n" |
              ForEach-Object { $_.Trim() } |
              Where-Object {
                $_ -and
                $_ -notmatch "Windows Subsystem for Linux has no installed distributions" -and
                $_ -notmatch "^Use 'wsl\.exe" -and
                $_ -notmatch "^and 'wsl\.exe"
              }
          }

          $wsl = Get-Command wsl.exe -ErrorAction SilentlyContinue
          if (-not $wsl) {
            Write-Warning "wsl.exe is not available on this runner."
          } else {
            Write-Host "wsl.exe=$($wsl.Source)"
            if ($env:ENABLE_WSL2_FEATURES -eq "true") {
              Write-Host "enable_wsl2_features=true"
              foreach ($feature in @("Microsoft-Windows-Subsystem-Linux", "VirtualMachinePlatform", "HypervisorPlatform")) {
                dism.exe /online /enable-feature /featurename:$feature /all /norestart
                Write-Host "enable_feature_${feature}_exit=$LASTEXITCODE"
                if ($LASTEXITCODE -eq 3010) {
                  $restartRequired = $true
                }
              }
              if ($restartRequired) {
                Write-Warning "wsl2_restart_required=true; Windows optional feature changes require a runner reboot before WSL2 can be imported."
              }
            }

            $status = Invoke-WslText -Arguments @("--status")
            Write-Host $status.Text
            Write-Host "wsl_status_exit=$($status.Code)"

            $list = Invoke-WslText -Arguments @("--list", "--verbose")
            Write-Host $list.Text
            Write-Host "wsl_list_exit=$($list.Code)"

            $distros = @(Get-WslDistros)
            if ($distros.Count -eq 0 -and $env:IMPORT_UBUNTU_WSL2 -eq "true" -and -not $restartRequired) {
              Write-Host "import_ubuntu_wsl2=true"
              $wslRoot = "C:\wsl\UbuntuProbe"
              $rootfs = "C:\wsl\ubuntu-noble-wsl.rootfs.tar.gz"
              $rootfsUrl = Resolve-UbuntuWslRootfsUrl
              New-Item -ItemType Directory -Force -Path @((Split-Path -Parent $rootfs), $wslRoot) | Out-Null
              Invoke-WebRequest `
                -Uri $rootfsUrl `
                -OutFile $rootfs `
                -UseBasicParsing `
                -ConnectionTimeoutSeconds 15 `
                -OperationTimeoutSeconds 120
              $import = Invoke-WslText -Arguments @("--import", "UbuntuProbe", $wslRoot, $rootfs, "--version", "2")
              Write-Host $import.Text
              Write-Host "wsl_import_exit=$($import.Code)"
              $list = Invoke-WslText -Arguments @("--list", "--verbose")
              Write-Host $list.Text
              Write-Host "wsl_list_after_import_exit=$($list.Code)"
              $distros = @(Get-WslDistros)
            } elseif ($distros.Count -eq 0 -and $env:IMPORT_UBUNTU_WSL2 -eq "true" -and $restartRequired) {
              Write-Warning "import_ubuntu_wsl2=skipped_restart_required"
            }

            if ($distros.Count -gt 0) {
              $distro = $distros[0]
              Write-Host "wsl_probe_distro=$distro"
              $exec = Invoke-WslText -Arguments @("-d", $distro, "--exec", "bash", "-lc", 'set -euo pipefail; uname -a; if [ -f /etc/os-release ]; then sed -n "1,8p" /etc/os-release; fi')
            } elseif ($restartRequired) {
              $exec = [pscustomobject]@{ Code = 1; Text = "wsl_exec_skipped=restart_required" }
            } else {
              $exec = Invoke-WslText -Arguments @("--exec", "bash", "-lc", 'set -euo pipefail; uname -a; if [ -f /etc/os-release ]; then sed -n "1,8p" /etc/os-release; fi')
            }
            Write-Host $exec.Text
            if ($exec.Code -eq 0) {
              $ok = $true
            }
            Write-Host "wsl_exec_exit=$($exec.Code)"
          }

          if ($ok) {
            "wsl2_ok=true" >> $env:GITHUB_OUTPUT
            "wsl2_restart_required=false" >> $env:GITHUB_OUTPUT
            "OPENCLAW_WSL2_PROBE_OK=true" >> $env:GITHUB_ENV
            "OPENCLAW_WSL2_RESTART_REQUIRED=false" >> $env:GITHUB_ENV
            Write-Host "wsl2_ok=true"
          } else {
            "wsl2_ok=false" >> $env:GITHUB_OUTPUT
            "wsl2_restart_required=$($restartRequired.ToString().ToLowerInvariant())" >> $env:GITHUB_OUTPUT
            "OPENCLAW_WSL2_PROBE_OK=false" >> $env:GITHUB_ENV
            "OPENCLAW_WSL2_RESTART_REQUIRED=$($restartRequired.ToString().ToLowerInvariant())" >> $env:GITHUB_ENV
            Write-Warning "wsl2_ok=false"
          }

          exit 0

      - name: Try to exclude workspace from Windows Defender (best-effort)
        if: ${{ inputs.run_windows_ci }}
        shell: pwsh
        run: |
          $cmd = Get-Command Add-MpPreference -ErrorAction SilentlyContinue
          if (-not $cmd) {
            Write-Host "Add-MpPreference not available, skipping Defender exclusions."
            exit 0
          }

          try {
            Add-MpPreference -ExclusionPath "$env:GITHUB_WORKSPACE" -ErrorAction Stop
            Add-MpPreference -ExclusionProcess "node.exe" -ErrorAction Stop
            Write-Host "Defender exclusions applied."
          } catch {
            Write-Warning "Failed to apply Defender exclusions, continuing. $($_.Exception.Message)"
          }

      - name: Setup Node.js
        if: ${{ inputs.run_windows_ci }}
        shell: bash
        env:
          REQUESTED_NODE_VERSION: "22.x"
        run: |
          set -euo pipefail
          source .github/actions/setup-pnpm-store-cache/ensure-node.sh
          openclaw_ensure_node "$REQUESTED_NODE_VERSION"

      - name: Setup pnpm
        if: ${{ inputs.run_windows_ci }}
        uses: ./.github/actions/setup-pnpm-store-cache
        with:
          node-version: 22.x

      - name: Runtime versions
        if: ${{ inputs.run_windows_ci }}
        shell: bash
        run: |
          node -v
          npm -v
          pnpm -v

      - name: Capture node path
        if: ${{ inputs.run_windows_ci }}
        shell: bash
        run: |
          node_bin="$(dirname "$(node -p 'process.execPath')")"
          if command -v cygpath >/dev/null 2>&1; then
            node_bin="$(cygpath -u "$node_bin")"
          fi
          echo "NODE_BIN=$node_bin" >> "$GITHUB_ENV"

      - name: Install dependencies
        if: ${{ inputs.run_windows_ci }}
        shell: bash
        env:
          CI: true
        run: |
          export PATH="$NODE_BIN:$PATH"
          which node
          node -v
          pnpm -v
          pnpm install --frozen-lockfile --prefer-offline --ignore-scripts=false --config.engine-strict=false --config.enable-pre-post-scripts=true --config.side-effects-cache=true || pnpm install --frozen-lockfile --prefer-offline --ignore-scripts=false --config.engine-strict=false --config.enable-pre-post-scripts=true --config.side-effects-cache=true

      - name: Run Windows CI tests
        if: ${{ inputs.run_windows_ci }}
        shell: bash
        env:
          CI: true
          NODE_OPTIONS: --max-old-space-size=8192
          OPENCLAW_TEST_SKIP_FULL_EXTENSIONS_SHARD: 1
          OPENCLAW_VITEST_MAX_WORKERS: 1
        run: |
          set -euo pipefail
          export PATH="$NODE_BIN:$PATH"
          pnpm test:windows:ci

      - name: Preflight native Scheduled Task session
        if: ${{ inputs.run_windows_ci }}
        shell: pwsh
        run: |
          $ErrorActionPreference = "Stop"
          $identity = [Security.Principal.WindowsIdentity]::GetCurrent()
          $principal = [Security.Principal.WindowsPrincipal]::new($identity)
          $isAdmin = $principal.IsInRole([Security.Principal.WindowsBuiltInRole]::Administrator)
          $sessionId = (Get-Process -Id $PID).SessionId
          Write-Host "identity=$($identity.Name)"
          Write-Host "session_id=$sessionId"
          Write-Host "user_interactive=$([Environment]::UserInteractive)"
          Write-Host "administrator=$isAdmin"
          query user 2>&1 | Write-Host
          if (-not [Environment]::UserInteractive) {
            throw "Native Scheduled Task proof requires an interactive Windows runner session."
          }

      - name: Run native Scheduled Task lifecycle proof
        id: native_schtasks
        if: ${{ inputs.run_windows_ci }}
        timeout-minutes: 5
        shell: bash
        env:
          CI_WINDOWS_SCHTASKS_PROOF_PATH: ${{ github.workspace }}\.artifacts\windows-schtasks\proof.json
          CI_WINDOWS_SCHTASKS_ROOT: ${{ runner.temp }}\openclaw-schtasks-${{ github.run_id }}-${{ github.run_attempt }}
          CI_WINDOWS_SCHTASKS_TEST_ID: ${{ github.run_id }}-${{ github.run_attempt }}
          EXPECTED_HEAD: ${{ inputs.target_ref }}
        run: |
          set -euo pipefail
          export PATH="$NODE_BIN:$PATH"
          if [[ ! "$EXPECTED_HEAD" =~ ^[0-9a-f]{40}$ ]]; then
            echo "Native Scheduled Task proof requires target_ref to be an exact 40-character commit SHA." >&2
            exit 1
          fi
          CI_WINDOWS_SCHTASKS_HEAD="$(git rev-parse HEAD)"
          if [[ "$CI_WINDOWS_SCHTASKS_HEAD" != "$EXPECTED_HEAD" ]]; then
            echo "Checked out $CI_WINDOWS_SCHTASKS_HEAD, expected frozen target $EXPECTED_HEAD." >&2
            exit 1
          fi
          export CI_WINDOWS_SCHTASKS_HEAD
          mkdir -p .artifacts/windows-schtasks
          pnpm test:windows:schtasks:integration

      - name: Clean native Scheduled Task residue
        id: native_cleanup
        if: ${{ always() && inputs.run_windows_ci }}
        shell: pwsh
        env:
          TEST_ID: ${{ github.run_id }}-${{ github.run_attempt }}
          TEST_ROOT: ${{ runner.temp }}\openclaw-schtasks-${{ github.run_id }}-${{ github.run_attempt }}
        run: |
          $ErrorActionPreference = "Continue"
          $cleanupErrors = @()
          $profile = "schtasks-int-$env:TEST_ID"
          $taskName = "OpenClaw Gateway ($profile)"
          $stateDir = Join-Path $env:USERPROFILE ".openclaw-$profile"
          New-Item -ItemType Directory -Force -Path $env:TEST_ROOT | Out-Null
          schtasks.exe /End /TN $taskName 2>$null
          Start-Sleep -Milliseconds 200
          $activePidPath = Join-Path $env:TEST_ROOT "active-pid.txt"
          if (Test-Path -LiteralPath $activePidPath) {
            try {
              $probePid = 0
              $activePid = (Get-Content -LiteralPath $activePidPath -Raw).Trim()
              if (-not [int]::TryParse($activePid, [ref]$probePid) -or $probePid -le 1) {
                throw "Invalid Scheduled Task active process id: $activePid"
              }
              $processQueryError = @()
              $process = Get-CimInstance Win32_Process -Filter "ProcessId = $probePid" -ErrorAction SilentlyContinue -ErrorVariable processQueryError
              if ($processQueryError.Count -gt 0) {
                throw "Could not inspect Scheduled Task probe process $probePid."
              }
              if ($process) {
                $probePath = Join-Path $env:TEST_ROOT "probe.cjs"
                $eventsPath = Join-Path $env:TEST_ROOT "runs.txt"
                if (
                  $process.CommandLine -like "*$probePath*" -and
                  $process.CommandLine -like "*$eventsPath*"
                ) {
                  taskkill.exe /F /T /PID $probePid 2>$null
                  $deadline = [DateTime]::UtcNow.AddSeconds(30)
                  do {
                    Start-Sleep -Milliseconds 200
                    $processQueryError = @()
                    $process = Get-CimInstance Win32_Process -Filter "ProcessId = $probePid" -ErrorAction SilentlyContinue -ErrorVariable processQueryError
                    if ($processQueryError.Count -gt 0) {
                      throw "Could not verify Scheduled Task probe process $probePid exited."
                    }
                  } while ($process -and [DateTime]::UtcNow -lt $deadline)
                  if ($process) {
                    throw "Scheduled Task probe process $probePid survived cleanup."
                  }
                } else {
                  throw "Refusing to kill reused or unverifiable process id $probePid."
                }
              }
            } catch {
              $cleanupErrors += $_.Exception.Message
            }
          }
          schtasks.exe /Delete /F /TN $taskName 2>$null
          $deleteExit = $LASTEXITCODE
          try {
            $service = New-Object -ComObject "Schedule.Service"
            $service.Connect()
            $null = $service.GetFolder("\").GetTask($taskName)
            $taskExists = $true
          } catch {
            $exception = $_.Exception
            while ($null -ne $exception.InnerException) {
              $exception = $exception.InnerException
            }
            if ($exception.HResult -eq -2147024894 -or $exception.HResult -eq -2147024893) {
              $taskExists = $false
            } else {
              $cleanupErrors += "Could not verify Scheduled Task cleanup for $taskName (HRESULT $($exception.HResult))."
              $taskExists = $null
            }
          }
          if ($taskExists -eq $true) {
            $cleanupErrors += "Scheduled Task cleanup left $taskName registered (delete exit $deleteExit)."
          }
          @(
            "task_name=$taskName"
            "delete_exit=$deleteExit"
            "task_exists=$taskExists"
            "proof_outcome=${{ steps.native_schtasks.outcome }}"
            "cleanup_errors=$($cleanupErrors -join ' ')"
          ) | Set-Content -LiteralPath (Join-Path $env:TEST_ROOT "cleanup-summary.txt")
          if ($cleanupErrors.Count -gt 0) {
            throw ($cleanupErrors -join " ")
          }
          exit 0

      - name: Upload native Scheduled Task proof
        id: native_proof_upload
        if: ${{ always() && inputs.run_windows_ci }}
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
        with:
          name: windows-schtasks-proof-${{ github.run_id }}-${{ github.run_attempt }}
          path: |
            .artifacts/windows-schtasks/proof.json
            ${{ runner.temp }}\openclaw-schtasks-${{ github.run_id }}-${{ github.run_attempt }}\failure-diagnostics.json
            ${{ runner.temp }}\openclaw-schtasks-${{ github.run_id }}-${{ github.run_attempt }}\cleanup-summary.txt
          if-no-files-found: warn
          retention-days: 7

      - name: Remove retained native Scheduled Task evidence
        if: ${{ always() && inputs.run_windows_ci && steps.native_cleanup.outcome == 'success' && steps.native_proof_upload.outcome == 'success' }}
        shell: pwsh
        env:
          TEST_ID: ${{ github.run_id }}-${{ github.run_attempt }}
          TEST_ROOT: ${{ runner.temp }}\openclaw-schtasks-${{ github.run_id }}-${{ github.run_attempt }}
        run: |
          $profile = "schtasks-int-$env:TEST_ID"
          Remove-Item -LiteralPath (Join-Path $env:USERPROFILE ".openclaw-$profile") -Recurse -Force -ErrorAction SilentlyContinue
          Remove-Item -LiteralPath $env:TEST_ROOT -Recurse -Force -ErrorAction SilentlyContinue

      - name: Keep runner alive for SSH inspection
        if: ${{ always() && !cancelled() }}
        env:
          KEEPALIVE_MINUTES: ${{ inputs.keepalive_minutes }}
        run: |
          $ErrorActionPreference = "Stop"
          $minutes = 20
          if ($env:KEEPALIVE_MINUTES -match '^\d+$') {
            $minutes = [int]$env:KEEPALIVE_MINUTES
          }
          $minutes = [Math]::Max(0, [Math]::Min($minutes, 60))
          Write-Host "keepalive_minutes=$minutes"
          for ($i = 1; $i -le $minutes; $i++) {
            Write-Host "keepalive minute $i/$minutes"
            Start-Sleep -Seconds 60
          }

      - name: Enforce WSL2 requirement
        if: ${{ always() && !cancelled() && inputs.require_wsl2 }}
        run: |
          if ($env:OPENCLAW_WSL2_PROBE_OK -ne "true") {
            if ($env:OPENCLAW_WSL2_RESTART_REQUIRED -eq "true") {
              Write-Error "WSL2 probe enabled required Windows features, but the runner needs a reboot before WSL2 can start."
              exit 1
            }
            Write-Error "WSL2 probe failed or WSL2 is unavailable on this Windows runner."
            exit 1
          }