Files
Flamenco-Management/remote_worker_controller.ps1
Nathan e568e02cdf fix opt 6 exit not working
also continue fix attempt on sheepit not starting
2025-12-02 12:08:00 -07:00

285 lines
8.4 KiB
PowerShell

param(
[Parameter(Mandatory = $true)]
[string]$WorkerName,
[Parameter(Mandatory = $true)]
[string]$WorkerType,
[string]$PayloadBase64,
[string]$PayloadBase64Path,
[string]$DataRoot = (Join-Path ([Environment]::GetFolderPath('LocalApplicationData')) 'UnifiedWorkers'),
[int]$MaxRestarts = 5,
[int]$RestartDelaySeconds = 10
)
$ErrorActionPreference = 'Stop'
[System.Management.Automation.Runspaces.Runspace]::DefaultRunspace = $Host.Runspace
# region Path setup
$workerRoot = Join-Path -Path $DataRoot -ChildPath $WorkerType
$instanceRoot = Join-Path -Path $workerRoot -ChildPath $WorkerName
New-Item -ItemType Directory -Path $instanceRoot -Force | Out-Null
$logsRoot = Join-Path -Path $instanceRoot -ChildPath 'logs'
$stateRoot = Join-Path -Path $instanceRoot -ChildPath 'state'
New-Item -ItemType Directory -Path $logsRoot -Force | Out-Null
New-Item -ItemType Directory -Path $stateRoot -Force | Out-Null
$logPath = Join-Path -Path $logsRoot -ChildPath 'worker.log'
$metaPath = Join-Path -Path $stateRoot -ChildPath 'worker-info.json'
$commandPath = Join-Path -Path $stateRoot -ChildPath 'commands.txt'
$payloadPath = Join-Path -Path $stateRoot -ChildPath "payload.ps1"
# endregion
# region Logging
$logStream = [System.IO.FileStream]::new(
$logPath,
[System.IO.FileMode]::Append,
[System.IO.FileAccess]::Write,
[System.IO.FileShare]::ReadWrite
)
$logWriter = [System.IO.StreamWriter]::new($logStream, [System.Text.Encoding]::UTF8)
$logWriter.AutoFlush = $true
if (-not ("UnifiedWorkers.WorkerLogSink" -as [type])) {
Add-Type -Namespace UnifiedWorkers -Name WorkerLogSink -MemberDefinition @"
using System;
using System.Diagnostics;
using System.IO;
public sealed class WorkerLogSink
{
private readonly TextWriter _writer;
private readonly string _prefix;
private readonly object _sync = new object();
public WorkerLogSink(TextWriter writer, string prefix)
{
if (writer == null)
{
throw new ArgumentNullException(\"writer\");
}
if (prefix == null)
{
throw new ArgumentNullException(\"prefix\");
}
_writer = writer;
_prefix = prefix;
}
public void OnData(object sender, DataReceivedEventArgs e)
{
if (e == null || string.IsNullOrEmpty(e.Data))
{
return;
}
lock (_sync)
{
var timestamp = DateTime.UtcNow.ToString("u");
var line = string.Format("[{0} {1}] {2}", _prefix, timestamp, e.Data);
_writer.WriteLine(line);
_writer.Flush();
}
}
}
"@
}
function Write-LogLine {
param(
[string]$Prefix,
[string]$Message
)
if (-not $logWriter) { return }
$timestamp = (Get-Date).ToString('u')
$logWriter.WriteLine("[{0} {1}] {2}" -f $Prefix, $timestamp, $Message)
}
function Write-ControllerLog {
param([string]$Message)
Write-LogLine -Prefix 'CTRL' -Message $Message
}
# endregion
# region Helpers
function Resolve-PayloadBase64 {
if ($PayloadBase64) {
return $PayloadBase64
}
if ($PayloadBase64Path) {
if (-not (Test-Path $PayloadBase64Path)) {
throw "Payload file '$PayloadBase64Path' not found."
}
return (Get-Content -Path $PayloadBase64Path -Raw)
}
throw "No payload data provided to controller."
}
function Write-Metadata {
param(
[string]$Status,
[nullable[int]]$WorkerPid = $null,
[nullable[int]]$ControllerPid = $PID,
[int]$Restarts = 0,
[nullable[int]]$LastExitCode = $null
)
$payload = [pscustomobject]@{
WorkerName = $WorkerName
WorkerType = $WorkerType
Status = $Status
ControllerPid = $ControllerPid
WorkerPid = $WorkerPid
Restarts = $Restarts
LastExitCode = $LastExitCode
LogPath = $logPath
CommandPath = $commandPath
PayloadPath = $payloadPath
UpdatedAtUtc = (Get-Date).ToUniversalTime()
}
$payload | ConvertTo-Json -Depth 5 | Set-Content -Path $metaPath -Encoding UTF8
}
function Get-PendingCommands {
if (-not (Test-Path $commandPath)) {
return @()
}
try {
$lines = Get-Content -Path $commandPath -ErrorAction Stop
Remove-Item -Path $commandPath -Force -ErrorAction SilentlyContinue
return $lines | Where-Object { -not [string]::IsNullOrWhiteSpace($_) }
}
catch {
return @()
}
}
# endregion
# record initial state before launching worker
Write-Metadata -Status 'initializing' -WorkerPid $null -ControllerPid $PID -Restarts 0
$resolvedPayloadBase64 = Resolve-PayloadBase64
$PayloadBase64 = $resolvedPayloadBase64
try {
# Write payload script to disk
$payloadBytes = [Convert]::FromBase64String($resolvedPayloadBase64)
[IO.File]::WriteAllBytes($payloadPath, $payloadBytes)
Write-ControllerLog "Payload written to $payloadPath"
}
catch {
Write-Error "Unable to write payload: $($_.Exception.Message)"
exit 1
}
$restartCount = 0
$controllerPid = $PID
while ($restartCount -le $MaxRestarts) {
try {
# Initialize worker process
$psi = [System.Diagnostics.ProcessStartInfo]::new()
$pwsh = Get-Command pwsh -ErrorAction SilentlyContinue
if ($pwsh) {
$psi.FileName = $pwsh.Source
}
else {
$psi.FileName = (Get-Command powershell -ErrorAction Stop).Source
}
$psi.Arguments = "-NoLogo -NoProfile -ExecutionPolicy Bypass -File `"$payloadPath`""
$psi.UseShellExecute = $false
$psi.RedirectStandardInput = $true
$psi.RedirectStandardOutput = $true
$psi.RedirectStandardError = $true
$psi.CreateNoWindow = $true
$workerProcess = New-Object System.Diagnostics.Process
$workerProcess.StartInfo = $psi
if (-not $workerProcess.Start()) {
throw "Failed to start worker process."
}
Write-ControllerLog "Worker process started with PID $($workerProcess.Id)"
Write-Metadata -Status 'running' -WorkerPid $workerProcess.Id -ControllerPid $controllerPid -Restarts $restartCount
$stdoutSink = [UnifiedWorkers.WorkerLogSink]::new($logWriter, 'OUT')
$stderrSink = [UnifiedWorkers.WorkerLogSink]::new($logWriter, 'ERR')
$outputHandler = [System.Diagnostics.DataReceivedEventHandler]$stdoutSink.OnData
$errorHandler = [System.Diagnostics.DataReceivedEventHandler]$stderrSink.OnData
$workerProcess.add_OutputDataReceived($outputHandler)
$workerProcess.add_ErrorDataReceived($errorHandler)
$workerProcess.BeginOutputReadLine()
$workerProcess.BeginErrorReadLine()
while (-not $workerProcess.HasExited) {
$commands = Get-PendingCommands
foreach ($command in $commands) {
$trimmed = $command.Trim()
if (-not $trimmed) { continue }
Write-ControllerLog "Received command '$trimmed'"
try {
$workerProcess.StandardInput.WriteLine($trimmed)
$workerProcess.StandardInput.Flush()
}
catch {
Write-ControllerLog "Failed to forward command '$trimmed': $($_.Exception.Message)"
}
if ($trimmed -ieq 'quit') {
Write-ControllerLog "Quit command issued. Waiting for worker to exit."
}
}
Start-Sleep -Milliseconds 500
}
$exitCode = $workerProcess.ExitCode
Write-ControllerLog "Worker exited with code $exitCode"
Write-Metadata -Status 'stopped' -WorkerPid $null -ControllerPid $controllerPid -Restarts $restartCount -LastExitCode $exitCode
if ($exitCode -eq 0) {
break
}
}
catch {
Write-ControllerLog "Controller error: $($_.Exception.Message)"
}
$restartCount++
if ($restartCount -gt $MaxRestarts) {
Write-ControllerLog "Maximum restart attempts reached. Controller stopping."
break
}
Write-ControllerLog "Restarting worker in $RestartDelaySeconds seconds (attempt $restartCount of $MaxRestarts)."
Start-Sleep -Seconds $RestartDelaySeconds
}
Write-Metadata -Status 'inactive' -WorkerPid $null -ControllerPid $controllerPid -Restarts $restartCount
Write-ControllerLog "Controller exiting."
if ($logWriter) {
$logWriter.Dispose()
}
if ($logStream) {
$logStream.Dispose()
}