<#
.SYNOPSIS
    Make the Gitea Actions runner on this machine survive restarts, and give it
    a toolchain the SYSTEM service account can actually see.

.DESCRIPTION
    Why this file exists (2026-10-11 CI audit, the "many jobs never ran" bug):

    Six consecutive runs (16..21, i.e. 12 jobs) produced ZERO log lines. The
    runner `win-stm32-ci` was simply offline, and two independent causes made
    that permanent:

      1. NO SUPERVISION. gitea-runner v4.0.1 `daemon` has no service support
         (v4 removed `daemon install`), and it EXITS when the first Declare
         call fails. The runner log shows exactly that after a Gitea restart:

             level=error msg="fail to invoke Declare" error="unavailable:
               dial tcp 127.0.0.1:3001: connectex: ... actively refused it."
             Error: unavailable: dial tcp 127.0.0.1:3001 ...

         ...and the process is gone. So one Gitea restart (or one reboot)
         silently kills CI until a human notices days later. Queued runs then
         get cancelled by the NEXT push, because ci.yml sets
         `concurrency.cancel-in-progress: true` -- which is why the symptom
         looks like "tasks vanish" rather than "tasks fail".

      2. NO MACHINE-LEVEL TOOLCHAIN. The runner service runs as SYSTEM.
         pre-commit / cppcheck were only reachable through the interactive
         user's PATH, and no machine-level DTU_* variable was ever set, so
         even a live runner died in the L0 environment check.

    This script installs the missing supervision (a watchdog launcher + a
    scheduled task) and, with -SetEnv, writes the machine-level DTU_* variables
    by discovering the tools the same way CI does.

    Run elevated, from the repo:

        powershell -ExecutionPolicy Bypass -File scripts\ci_runner_bootstrap.ps1 -SetEnv -StartNow

.PARAMETER RunnerDir
    Directory holding gitea-runner.exe / config.yaml / .runner.

.PARAMETER GiteaUrl
    Instance address the runner registered against (must match .runner's
    "address"; the runner talks to it directly, not through the public URL).

.PARAMETER TaskName
    Scheduled-task name for the watchdog.

.PARAMETER SetEnv
    Discover and write MACHINE-level DTU_PRECOMMIT_PYTHON / DTU_CPPCHECK /
    DTU_MSVC_CL. Existing values are preserved unless -Force.

.PARAMETER StartNow
    Start the task after registering it.

.PARAMETER Status
    Only report: task state, daemon process, Gitea reachability.

.PARAMETER Force
    With -SetEnv, overwrite existing machine-level values.

.OUTPUTS
    Progress lines. Exit codes: 0 = ok, 1 = precondition failed, 2 = not elevated.

.NOTES
    Keep this file pure ASCII (PowerShell 5.1 decodes BOM-less files as CP936).
#>
[CmdletBinding()]
param(
    [string]$RunnerDir = 'D:\Docker\act_runner',
    [string]$GiteaUrl  = 'http://127.0.0.1:3001',
    [string]$TaskName  = 'GiteaActionsRunner',
    [switch]$SetEnv,
    [switch]$StartNow,
    [switch]$Status,
    [switch]$Force
)

$ErrorActionPreference = 'Stop'

function Info($m) { Write-Host "[INFO] $m" -ForegroundColor Cyan }
function Ok($m)   { Write-Host "[ OK ] $m" -ForegroundColor Green }
function Warn($m) { Write-Host "[WARN] $m" -ForegroundColor Yellow }
function Fail($m) { Write-Host "[FAIL] $m" -ForegroundColor Red }

function Test-Admin {
    $id = [Security.Principal.WindowsIdentity]::GetCurrent()
    (New-Object Security.Principal.WindowsPrincipal($id)
        ).IsInRole([Security.Principal.WindowsBuiltInRole]::Administrator)
}

function Test-Gitea([string]$url) {
    try {
        Invoke-WebRequest -Uri "$url/api/v1/version" -UseBasicParsing -TimeoutSec 10 | Out-Null
        return $true
    }
    catch { return $false }
}

function Get-MachineEnv([string]$name) {
    $v = [Environment]::GetEnvironmentVariable($name, 'Machine')
    if ([string]::IsNullOrWhiteSpace($v)) { return $null }
    return $v
}

function Set-MachineEnv([string]$name, [string]$value, [string]$label) {
    $cur = Get-MachineEnv $name
    if ($cur) {
        if ($cur -ieq $value) { Ok "$label already set: $cur"; return }
        if (-not $Force) {
            Warn "$label already set to a different value: $cur (use -Force to overwrite)"
            return
        }
        Warn "$label overwriting $cur -> $value"
    }
    [Environment]::SetEnvironmentVariable($name, $value, 'Machine')
    Ok "$label set (MACHINE scope): $value"
}

function Find-Cppcheck {
    $pf   = $env:ProgramFiles
    $pf86 = ${env:ProgramFiles(x86)}
    if ([string]::IsNullOrWhiteSpace($pf))   { $pf   = 'C:\Program Files' }
    if ([string]::IsNullOrWhiteSpace($pf86)) { $pf86 = 'C:\Program Files (x86)' }
    foreach ($c in @((Join-Path $pf 'Cppcheck\cppcheck.exe'),
                     (Join-Path $pf86 'Cppcheck\cppcheck.exe'))) {
        if (Test-Path -LiteralPath $c) { return $c }
    }
    $cmd = Get-Command cppcheck -ErrorAction SilentlyContinue
    if ($cmd) { return $cmd.Source }
    return $null
}

function Find-MsvcCl {
    $pf   = $env:ProgramFiles
    $pf86 = ${env:ProgramFiles(x86)}
    if ([string]::IsNullOrWhiteSpace($pf))   { $pf   = 'C:\Program Files' }
    if ([string]::IsNullOrWhiteSpace($pf86)) { $pf86 = 'C:\Program Files (x86)' }
    $roots = @()
    foreach ($year in @('2019', '2022', '2026', '18')) {
        foreach ($edition in @('BuildTools', 'Community', 'Professional', 'Enterprise')) {
            $roots += (Join-Path $pf86 "Microsoft Visual Studio\$year\$edition")
            $roots += (Join-Path $pf   "Microsoft Visual Studio\$year\$edition")
        }
    }
    foreach ($r in $roots) {
        if (-not (Test-Path -LiteralPath $r)) { continue }
        $cl = Get-ChildItem -LiteralPath $r -Recurse -Filter 'cl.exe' -ErrorAction SilentlyContinue |
              Where-Object { $_.FullName -like '*Hostx64\x64*' } |
              Select-Object -First 1
        if ($cl) { return $cl.FullName }
    }
    return $null
}

# ---------------------------------------------------------------------------
# -Status: read-only report
# ---------------------------------------------------------------------------
if ($Status) {
    Info "task $TaskName"
    $t = Get-ScheduledTask -TaskName $TaskName -ErrorAction SilentlyContinue
    if ($t) { Ok ("task state: {0}" -f $t.State) } else { Warn 'task not registered' }

    $proc = Get-Process | Where-Object { $_.ProcessName -match 'gitea-runner|act_runner' }
    if ($proc) { Ok ("daemon running: pid(s) " + ($proc.Id -join ',')) } else { Warn 'daemon not running' }

    if (Test-Gitea $GiteaUrl) { Ok "Gitea reachable at $GiteaUrl" }
    else { Fail "Gitea NOT reachable at $GiteaUrl" }

    foreach ($n in @('DTU_PRECOMMIT_PYTHON', 'DTU_CPPCHECK', 'DTU_MSVC_CL')) {
        $v = Get-MachineEnv $n
        if ($v) { Ok ("MACHINE {0} = {1}" -f $n, $v) }
        else { Warn "MACHINE $n not set (CI auto-discovery still applies; see scripts/ci_find_python.ps1)" }
    }
    exit 0
}

# ---------------------------------------------------------------------------
# Preconditions
# ---------------------------------------------------------------------------
if (-not (Test-Admin)) {
    Fail 'not elevated -- rerun from an elevated PowerShell (this writes a scheduled task and machine env vars)'
    exit 2
}

$exe     = Join-Path $RunnerDir 'gitea-runner.exe'
$cfg     = Join-Path $RunnerDir 'config.yaml'
$regFile = Join-Path $RunnerDir '.runner'
$launcher = Join-Path $RunnerDir 'run_runner_watchdog.ps1'

foreach ($f in @($exe, $cfg)) {
    if (-not (Test-Path -LiteralPath $f)) { Fail "missing file: $f"; exit 1 }
}
if (-not (Test-Path -LiteralPath $regFile)) {
    Fail "not registered: $regFile is missing"
    Info 'register first, e.g.:'
    Write-Host "  & '$exe' register --no-interactive --instance '$GiteaUrl' --token <RegistrationToken> --name win-stm32-ci --labels 'windows:host'"
    exit 1
}

# The daemon must talk to the address baked into .runner, not the public URL.
$registeredAddress = $null
try {
    $registeredAddress = (Get-Content -LiteralPath $regFile -Raw | ConvertFrom-Json).address
}
catch { Warn "cannot parse $regFile : $_" }
if ($registeredAddress -and $registeredAddress.TrimEnd('/') -ne $GiteaUrl.TrimEnd('/')) {
    Warn ".runner address is $registeredAddress but -GiteaUrl is $GiteaUrl -- using the .runner value for the readiness probe"
    $GiteaUrl = $registeredAddress
}

# ---------------------------------------------------------------------------
# 1. machine-level toolchain (SYSTEM cannot see the interactive user's PATH)
# ---------------------------------------------------------------------------
if ($SetEnv) {
    Info 'discovering toolchain for MACHINE scope ...'

    $findPy = Join-Path $PSScriptRoot 'ci_find_python.ps1'
    if (Test-Path -LiteralPath $findPy) {
        $py = & $findPy -NeedPreCommit
        if ($LASTEXITCODE -eq 0 -and $py) {
            Set-MachineEnv 'DTU_PRECOMMIT_PYTHON' ("$py".Trim()) 'DTU_PRECOMMIT_PYTHON'
        }
        else {
            Warn 'no interpreter with pre-commit found -- install pre-commit into a machine-wide interpreter first'
        }
    }
    else { Warn "not found: $findPy (skipping DTU_PRECOMMIT_PYTHON)" }

    $cpp = Find-Cppcheck
    if ($cpp) { Set-MachineEnv 'DTU_CPPCHECK' $cpp 'DTU_CPPCHECK' }
    else { Warn 'cppcheck not found (install Cppcheck.Cppcheck, or set DTU_CPPCHECK manually)' }

    $cl = Find-MsvcCl
    if ($cl) { Set-MachineEnv 'DTU_MSVC_CL' $cl 'DTU_MSVC_CL' }
    else { Warn 'MSVC cl.exe (Hostx64\x64) not found -- L0.5 will degrade to "skipped" without it' }

    Info 'machine env vars are read when a PROCESS STARTS: the daemon must be restarted below'
}

# ---------------------------------------------------------------------------
# 2. watchdog launcher (the actual fix for "daemon exits and nobody notices")
# ---------------------------------------------------------------------------
Info "writing watchdog launcher: $launcher"

$template = @'
# AUTO-GENERATED by scripts/ci_runner_bootstrap.ps1 -- do not edit by hand.
#
# gitea-runner `daemon` exits when its first Declare call fails (no retry, no
# service support in v4), so a plain scheduled task is NOT enough: a Gitea
# restart would take CI down until a human noticed. This loop
#   1) waits until Gitea answers, then
#   2) runs the daemon, and
#   3) restarts it after a short pause whenever it exits.
# Keep this file pure ASCII (PowerShell 5.1 decodes BOM-less files as CP936).
$ErrorActionPreference = 'Continue'

$runnerDir   = '__RUNNER_DIR__'
$runnerExe   = Join-Path $runnerDir 'gitea-runner.exe'
$runnerCfg   = Join-Path $runnerDir 'config.yaml'
$logDir      = Join-Path $runnerDir 'log'
$log         = Join-Path $logDir 'runner-stdout.log'
$probeUrl    = '__GITEA_URL__/api/v1/version'
$maxWaitSec  = 1800

if (-not (Test-Path -LiteralPath $logDir)) {
    New-Item -ItemType Directory -Force -Path $logDir | Out-Null
}

function Log($m) {
    $line = '{0} [watchdog] {1}' -f (Get-Date -Format 'o'), $m
    Add-Content -LiteralPath $log -Value $line -Encoding ascii
}

while ($true) {
    $waited = 0
    while ($true) {
        $ok = $false
        try {
            Invoke-WebRequest -Uri $probeUrl -UseBasicParsing -TimeoutSec 10 | Out-Null
            $ok = $true
        }
        catch { $ok = $false }
        if ($ok) { break }
        if ($waited -eq 0) { Log "waiting for Gitea at $probeUrl" }
        Start-Sleep -Seconds 15
        $waited += 15
        if ($waited -ge $maxWaitSec) {
            Log 'Gitea still not answering after 30m -- starting anyway so the real error lands in the log'
            break
        }
    }

    Log 'starting daemon'
    & $runnerExe daemon --config $runnerCfg *>> $log
    Log ("daemon exited, exit code {0}; restarting in 10s" -f $LASTEXITCODE)
    Start-Sleep -Seconds 10
}
'@

$content = $template.Replace('__RUNNER_DIR__', $RunnerDir).Replace('__GITEA_URL__', $GiteaUrl.TrimEnd('/'))
$utf8NoBom = New-Object System.Text.UTF8Encoding($false)
[System.IO.File]::WriteAllText($launcher, $content, $utf8NoBom)
Ok 'launcher written'

# ---------------------------------------------------------------------------
# 3. scheduled task: start at boot, run as SYSTEM, restart if it dies
# ---------------------------------------------------------------------------
$existing = Get-ScheduledTask -TaskName $TaskName -ErrorAction SilentlyContinue
if ($existing) {
    Info "task $TaskName exists -- unregistering to re-register with the current settings"
    Unregister-ScheduledTask -TaskName $TaskName -Confirm:$false
}

$action = New-ScheduledTaskAction `
    -Execute 'powershell.exe' `
    -Argument "-NoProfile -ExecutionPolicy Bypass -WindowStyle Hidden -File `"$launcher`"" `
    -WorkingDirectory $RunnerDir

# -AtStartup needs the "System" account; a boot trigger plus StartWhenAvailable
# also covers "machine was off when the task was created".
$trigger = New-ScheduledTaskTrigger -AtStartup
$trigger.Delay = 'PT1M'
$trigger.StartWhenAvailable = $true

$settings = New-ScheduledTaskSettingsSet `
    -AllowStartIfOnBatteries -DontStopIfGoingOnBatteries `
    -ExecutionTimeLimit ([TimeSpan]::Zero) `
    -RestartCount 999 -RestartInterval (New-TimeSpan -Minutes 1) `
    -MultipleInstances IgnoreNew

Register-ScheduledTask -TaskName $TaskName -Action $action -Trigger $trigger `
    -Settings $settings -User 'SYSTEM' -RunLevel Highest `
    -Description 'Gitea Actions runner watchdog (STM32F4-Base CI). Supervises gitea-runner daemon: waits for Gitea, restarts the daemon when it exits. Generated by scripts/ci_runner_bootstrap.ps1.' |
    Out-Null
Ok "scheduled task registered: $TaskName (at boot +1m, as SYSTEM, unlimited runtime, restart x999/1m)"

# ---------------------------------------------------------------------------
# 4. start it
# ---------------------------------------------------------------------------
if ($StartNow) {
    if (-not (Test-Gitea $GiteaUrl)) {
        Warn "Gitea is not answering at $GiteaUrl right now -- the watchdog will keep waiting"
    }
    Start-ScheduledTask -TaskName $TaskName
    Ok "task started; watch: Get-Content '$(Join-Path $RunnerDir 'log\runner-stdout.log')' -Tail 20"
    Info 'verify on the web UI: repo -> Settings -> Actions -> Runners -> win-stm32-ci should turn Idle'
}

Ok 'done'
exit 0