vignette/scripts/watch-public-runtime.ps1

232 lines
6.6 KiB
PowerShell

param(
[string]$Workspace = "D:\workspace\vignette",
[int]$ApiPort = 8001,
[int]$WebPort = 5174,
[int]$EnginePort = 9099,
[string]$Python = "$env:LOCALAPPDATA\Programs\Python\Python311\python.exe",
[string]$Cloudflared = "$env:LOCALAPPDATA\Microsoft\WinGet\Links\cloudflared.exe",
[string]$CloudflaredConfig = "$env:USERPROFILE\.cloudflared\vignette-config.yml",
[string]$PublicHealthUrl = "https://api-vignette.chanpaca.net/health",
[string[]]$AdditionalPublicHealthUrls = @(),
[string]$LogPath = "",
[int]$FailuresBeforeRestart = 3,
[switch]$CheckOnly,
[switch]$SkipPublicHealth,
[switch]$SkipCloudflaredRestart
)
$ErrorActionPreference = "Stop"
if (!$LogPath) {
$LogPath = Join-Path $Workspace "public-runtime-watchdog.log"
}
# 연속 실패 카운터(재시작 debounce용). 워치독은 매 실행마다 새 프로세스라 파일로 유지한다.
$FailCountPath = Join-Path $Workspace "public-runtime-watchdog.failcount"
function Get-FailCount {
if (Test-Path $FailCountPath) {
$raw = (Get-Content -Raw -Path $FailCountPath -ErrorAction SilentlyContinue)
$n = 0
if ([int]::TryParse(($raw -replace '\s', ''), [ref]$n)) { return $n }
}
return 0
}
function Set-FailCount {
param([int]$Value)
Set-Content -Path $FailCountPath -Value $Value -Encoding ascii
}
function Write-WatchdogLog {
param([string]$Message)
$line = "{0} {1}" -f (Get-Date -Format "yyyy-MM-ddTHH:mm:ssK"), $Message
Write-Output $line
Add-Content -Path $LogPath -Value $line -Encoding UTF8
}
function Test-JsonHealth {
param(
[string]$Name,
[string]$Uri,
[scriptblock]$IsHealthy,
[int]$TimeoutSec = 30
)
try {
$response = Invoke-RestMethod -Uri $Uri -TimeoutSec $TimeoutSec
$ok = [bool](& $IsHealthy $response)
$detail = $response | ConvertTo-Json -Compress -Depth 5
[pscustomobject]@{
Name = $Name
Ok = $ok
Detail = $detail
}
} catch {
[pscustomobject]@{
Name = $Name
Ok = $false
Detail = $_.Exception.Message
}
}
}
function Test-CloudflaredProcess {
if ($SkipCloudflaredRestart) {
return [pscustomobject]@{
Name = "cloudflared"
Ok = $true
Detail = "skipped"
}
}
$configLeaf = Split-Path -Leaf $CloudflaredConfig
$process = Get-CimInstance Win32_Process |
Where-Object {
$_.Name -eq "cloudflared.exe" -and
$_.CommandLine -and
$_.CommandLine -like "*$configLeaf*"
} |
Select-Object -First 1
[pscustomobject]@{
Name = "cloudflared"
Ok = $null -ne $process
Detail = if ($process) { "pid=$($process.ProcessId)" } else { "not running" }
}
}
$startScript = Join-Path $PSScriptRoot "start-public-runtime.ps1"
if (!(Test-Path $startScript)) {
throw "Start script not found at $startScript"
}
$checks = @(
(Test-JsonHealth `
-Name "engine" `
-Uri "http://127.0.0.1:$EnginePort/health" `
-IsHealthy { param($health) $health.ok -eq $true }),
(Test-JsonHealth `
-Name "api" `
-Uri "http://127.0.0.1:$ApiPort/health" `
-IsHealthy { param($health) $health.environment -eq "prod" -and $health.db }),
(Test-JsonHealth `
-Name "web-preview" `
-Uri "http://127.0.0.1:$WebPort/" `
-IsHealthy { param($body) $true }),
(Test-CloudflaredProcess)
)
if (!$SkipPublicHealth) {
$checks += Test-JsonHealth `
-Name "public-api" `
-Uri $PublicHealthUrl `
-IsHealthy { param($health) $health.environment -eq "prod" -and $health.db } `
-TimeoutSec 30
foreach ($url in $AdditionalPublicHealthUrls) {
$checks += Test-JsonHealth `
-Name "public-api:$url" `
-Uri $url `
-IsHealthy { param($health) $health.environment -eq "prod" -and $health.db } `
-TimeoutSec 30
}
}
$failed = @($checks | Where-Object { -not $_.Ok })
if ($failed.Count -eq 0) {
Set-FailCount 0
Write-WatchdogLog "healthy: $($checks.Name -join ', ')"
exit 0
}
$failCount = (Get-FailCount) + 1
Set-FailCount $failCount
Write-WatchdogLog "unhealthy ($failCount/$FailuresBeforeRestart): $((($failed | ForEach-Object { "$($_.Name)=$($_.Detail)" }) -join '; '))"
if ($CheckOnly) {
exit 1
}
# 연속 실패 debounce: claude -p readiness probe 는 콜드 스폰 시 10~20초가 정상이라
# 단발 timeout 을 장애로 오판해 전체 재시작하던 것이 재시작 폭풍의 원인이었다.
# 연속 $FailuresBeforeRestart 회 실패해야 실제 재시작한다.
if ($failCount -lt $FailuresBeforeRestart) {
Write-WatchdogLog "defer restart: $FailuresBeforeRestart 연속 실패 전까지 대기 (현재 $failCount)"
exit 1
}
$startArgs = @{
Workspace = $Workspace
ApiPort = $ApiPort
WebPort = $WebPort
EnginePort = $EnginePort
Python = $Python
Cloudflared = $Cloudflared
CloudflaredConfig = $CloudflaredConfig
}
if (($checks | Where-Object { $_.Name -eq "web-preview" }).Ok) {
$startArgs["SkipWebRestart"] = $true
}
if ($SkipCloudflaredRestart) {
$startArgs["SkipCloudflaredRestart"] = $true
}
try {
& $startScript @startArgs 2>&1 | ForEach-Object {
Write-WatchdogLog "$_"
}
} catch {
Write-WatchdogLog "restart failed: $($_.Exception.Message)"
throw
}
$apiAfter = Test-JsonHealth `
-Name "api" `
-Uri "http://127.0.0.1:$ApiPort/health" `
-IsHealthy { param($health) $health.environment -eq "prod" -and $health.db } `
-TimeoutSec 20
if (!$apiAfter.Ok) {
throw "Public API still unhealthy after restart: $($apiAfter.Detail)"
}
$webAfter = Test-JsonHealth `
-Name "web-preview" `
-Uri "http://127.0.0.1:$WebPort/" `
-IsHealthy { param($body) $true } `
-TimeoutSec 20
if (!$webAfter.Ok) {
throw "Public web preview still unhealthy after restart: $($webAfter.Detail)"
}
$engineAfter = Test-JsonHealth `
-Name "engine" `
-Uri "http://127.0.0.1:$EnginePort/health" `
-IsHealthy { param($health) $health.ok -eq $true } `
-TimeoutSec 20
if (!$engineAfter.Ok) {
throw "Engine gateway still unhealthy after isolated restart: $($engineAfter.Detail)"
}
if (!$SkipPublicHealth) {
$publicAfter = Test-JsonHealth `
-Name "public-api" `
-Uri $PublicHealthUrl `
-IsHealthy { param($health) $health.environment -eq "prod" -and $health.db } `
-TimeoutSec 30
if (!$publicAfter.Ok) {
throw "Public API tunnel still unhealthy after restart: $($publicAfter.Detail)"
}
foreach ($url in $AdditionalPublicHealthUrls) {
$publicExtraAfter = Test-JsonHealth `
-Name "public-api:$url" `
-Uri $url `
-IsHealthy { param($health) $health.environment -eq "prod" -and $health.db } `
-TimeoutSec 30
if (!$publicExtraAfter.Ok) {
throw "Public API tunnel still unhealthy after restart: $($publicExtraAfter.Detail)"
}
}
}
Set-FailCount 0
Write-WatchdogLog "restart verified"