feat(android): 键盘事件双通道 + 手机到 Windows 全链路 proof

真机暴露出 IME/按键通道的缺口,一并补上并证明:
1. RemoteInputConnection.sendKeyEvent 与 Activity.onKeyDown 都先处理**可打印**
   unicodeChar(走 v3 Text 通道),再退到扫描码查表。原先只查表:软键盘发的是
   keyCode=UNKNOWN + unicodeChar,查不到表就被当未映射键吞掉,字整个丢了。
   门槛排除控制值(Enter/Tab)——远端应用要的是按键事件而非 WM_CHAR。
2. onKeyDown/onKeyUp 补齐硬键与物理键盘路径(阶段 2 验收里的软键盘按键),
   repeatCount>0 只发一次 down,避免长按把远端消息队列刷爆。
   isAutorepeat() 是 @hide,改用公开的 getRepeatCount()(javap 核实)。
3. getUnicodeChar() 返回的是单个 UTF-16 code unit 而非码点,注释按此改正:
   BMP 外字符由 IME commitText 成对送达,不经这条路。

tools/phone_chain_proof.ps1:手机按键 -> v3 Text -> agent SendInput -> 自有
Windows 靶窗自报内容,全链路一次跑通(真机 vivo S6 实测 abc 到位、ENTER 走
scan 28、BACK 断开回表单、表单 UI 重连成功)。要点:
- 靶窗必须自报窗口句柄(pid+hwnd 两行),Get-Process 取 MainWindowHandle 有竞态;
- 不能用 keybd_event(VK_MENU) 破前台锁:ALT 之后的首个字符被当菜单助记键吞掉,
  实测三个字符只剩 b;改用 AttachThreadInput + SetForegroundWindow,不合成按键;
- 退役遗留靶窗只能 touch 已存在的 stop.flag:新建会命中即将启动那次的停止路径,
  靶窗刚起就自杀(实测 pid 报了又消失);
- adb 进度信息走 stderr,PS 5.1 + ErrorActionPreference=Stop 会当终止错误,
  按 build-android.ps1 同款办法临时放宽并只看退出码。
- 表单填字用 keyevent 而非 adb input text:设备只有第三方中文 IME,text 注入会被
  组词(ASCII 句点变 U+3002)。跑前记录并禁用原 IME,finally 精确还原。
This commit is contained in:
郑博文 2026-10-30 12:58:36 +08:00
parent a93430dd3f
commit 9f0b0742a8
5 changed files with 380 additions and 8 deletions

View File

@ -276,8 +276,22 @@ class MainActivity : Activity(), RemoteSurfaceView.Listener {
override fun isReadyForInput(): Boolean = handle != 0L
/**
* 返回键:软键盘开着时先收键盘(否则一次返回同时关键盘和会话);
* 远控态已连接 = 断开回连接界面;连接态 = 交还系统(退出 App)。
* 按键转发(物理键盘 / adb 注入 / 无 IME 时的软键盘):
* - 返回键:先收 IME,否则断开回表单(阶段 2a 语义延续);
* - **可打印**的 `unicodeChar`(0x20 起、排除 0x7F)→ v3 **Text** 通道:
* 字符注入与远端键盘布局无关。注意 `getUnicodeChar()` 给的是单个
* UTF-16 code unit 而非码点,所以这条路只覆盖 BMP;增补平面字符由
* IME `commitText` 成对送达,不经这里;
* - 控制值(Enter/Tab/方向键…)与其余控制键 → Set-1 扫描码通道(down/up 配对):
* 远端应用期待的是按键事件,不是 WM_CHAR;
* - 自动重复(`repeatCount > 0`,长按)只发一次 down:重复由远端键盘驱动,
* 本地重发会打爆消息队列。
*
* 与 IME 路径互斥:IME 显示时按键先被输入法消费(走 commitText),不会到这里;
* IME 隐藏时才走本方法。两条路同时生效会重复注入。
*
* 诊断:vivo logcat 被限流(lessons R-6),路由结果写状态栏,只报 keyCode
* 与去向,不报字符内容。
*/
override fun onKeyDown(keyCode: Int, event: KeyEvent?): Boolean {
if (keyCode == KeyEvent.KEYCODE_BACK) {
@ -291,8 +305,44 @@ class MainActivity : Activity(), RemoteSurfaceView.Listener {
disconnect()
return true
}
return super.onKeyDown(keyCode, event)
}
return super.onKeyDown(keyCode, event)
val h = handle
if (h == 0L || event == null) return super.onKeyDown(keyCode, event)
// 只报 keyCode 与路由结果,不报字符内容(诊断通道会显示在屏幕上)
val cp = event.unicodeChar
if (cp >= 0x20 && cp != 0x7F) {
if (event.repeatCount == 0) RustBridge.nativeSendText(h, charArrayOf(cp.toChar()))
lastTouchDbg = "key code=$keyCode -> text 1u"
runOnUiThread { refreshStatus() }
return true
}
val key = WinScancode.of(keyCode) ?: run {
lastTouchDbg = "key code=$keyCode 未映射"
runOnUiThread { refreshStatus() }
return super.onKeyDown(keyCode, event)
}
if (event.repeatCount == 0) {
RustBridge.nativeSendKey(h, key.scancode, if (key.extended) 1 else 0, 1)
}
lastTouchDbg = "key code=$keyCode -> scan ${key.scancode} ext=${key.extended}"
runOnUiThread { refreshStatus() }
return true
}
override fun onKeyUp(keyCode: Int, event: KeyEvent?): Boolean {
val h = handle
if (keyCode == KeyEvent.KEYCODE_BACK || h == 0L || event == null) {
return super.onKeyUp(keyCode, event)
}
// 字符事件没有「抬起」语义(Text 通道是整段提交),只回扫控制键。
// 门槛与 onKeyDown 一致:不可打印的 unicodeChar(Enter/Tab)仍需发 key up,
// 否则 onKeyDown 发了 down、这里不发 up,远端会留下按住未释放的键。
val cp = event.unicodeChar
if (cp >= 0x20 && cp != 0x7F) return true
val key = WinScancode.of(keyCode) ?: return super.onKeyUp(keyCode, event)
RustBridge.nativeSendKey(h, key.scancode, if (key.extended) 1 else 0, 0)
return true
}
// ---- 连接 / 解码 ----

View File

@ -43,6 +43,19 @@ class RemoteInputConnection(
}
return true
}
// 字符事件优先于扫描码:多数软键盘发的是 keyCode=KEYCODE_UNKNOWN +
// unicodeChar(adb `input text` 同款形态)。这一分支必须排在 WinScancode
// 查表**之前**——否则 UNKNOWN(0) 查不到表会被当「未映射」吞掉,字就丢了。
// 注意 `getUnicodeChar()` 返回的是单个 UTF-16 code unit(不是码点),
// 所以这条路只覆盖 BMP;增补平面字符由 `commitText` 成对送达。
// 只收**可打印**字符(空格起、排除 0x7F):控制值(Enter/Tab)必须走扫描码,
// 远端应用期待的是按键事件而非 WM_CHAR。见 MainActivity.onKeyDown 同款门槛。
val cp = event.unicodeChar
if (event.action == KeyEvent.ACTION_DOWN && cp >= 0x20 && cp != 0x7F) {
sendText(charArrayOf(cp.toChar()))
debug("keychar 1u")
return true
}
val key = WinScancode.of(event.keyCode)
if (key == null) {
debug("IME 未映射键 code=${event.keyCode}")

259
tools/phone_chain_proof.ps1 Normal file
View File

@ -0,0 +1,259 @@
# 2b full-chain proof (phone side): Android key -> v3 Text channel -> agent
# SendInput -> dedicated Windows target window, read back from that window.
# ASCII-only source (PS 5.1 + BOM-less = GBK corruption; see personal lessons).
# State checks use ASCII markers ("RTT=" / EditText presence) rather than
# matching the app's Chinese labels, for the same reason.
#
# Why ONE atomic script: SendInput lands on the FOREGROUND window, and Windows'
# foreground lock means a background process cannot simply reclaim it. This
# box's interactive GUI steals foreground between separate tool calls, so
# launch -> assert foreground -> drive phone -> read back must run without
# yielding. Every injection is preceded by a foreground assertion: if the target
# lost foreground we ABORT rather than inject into some other application.
#
# Prereqs: vivo device online via adb, app installed, v3 agent build present.
# Usage:
# powershell -ExecutionPolicy Bypass -File tools\phone_chain_proof.ps1
param(
[string]$PhoneIp = "192.168.1.180",
[int]$Port = 47800,
[string]$Code = "t"
)
$ErrorActionPreference = "Stop"
$repo = (Resolve-Path "$PSScriptRoot\..").Path
$adb = "D:\working\android\sdk\platform-tools\adb.exe"
$tmp = "$env:TEMP\remote-phone-proof"
New-Item -ItemType Directory -Force -Path $tmp | Out-Null
$pidFile = "$tmp\target.pid"
$stopFile = "$tmp\stop.flag"
$resultFile = "$tmp\received.txt"
Remove-Item $pidFile,$stopFile,$resultFile -ErrorAction SilentlyContinue
Add-Type -TypeDefinition @"
using System;
using System.Runtime.InteropServices;
public static class FgApi {
[DllImport("user32.dll")] public static extern IntPtr GetForegroundWindow();
}
"@
function Adb {
param([Parameter(Mandatory)][string[]]$AdbArgs)
# adb writes progress ("1 file pulled...") to stderr; PS 5.1 with
# $ErrorActionPreference=Stop turns every stderr line into a terminating
# error. Same workaround build-android.ps1 documents: relax for native
# calls, judge by exit code and captured stdout.
$old = $ErrorActionPreference
$ErrorActionPreference = "Continue"
try {
$out = & $adb @AdbArgs 2>$null
return @{ out = ($out -join "`n"); code = $LASTEXITCODE }
}
finally { $ErrorActionPreference = $old }
}
function Adb-Shell {
param([Parameter(Mandatory)][string[]]$Cmd)
return Adb -AdbArgs (@("shell") + $Cmd)
}
function Wait-File {
param([string]$Path, [int]$TimeoutMs = 20000)
$t = 0
while (-not (Test-Path $Path) -and $t -lt ($TimeoutMs / 150)) { Start-Sleep -Milliseconds 150; $t++ }
if (-not (Test-Path $Path)) { throw "timeout waiting for $Path" }
}
function Assert-Foreground([IntPtr]$hwnd, [string]$where) {
# Bounded wait, not a single instant check: the target re-asserts itself
# every 60ms in proof mode, so a momentary steal by the interactive desktop
# is recoverable. Still refuse to inject if it never comes back - a stray
# injection lands in whatever window DOES hold foreground.
$deadline = (Get-Date).AddMilliseconds(1500)
while ((Get-Date) -lt $deadline) {
if ([FgApi]::GetForegroundWindow() -eq $hwnd) { return }
Start-Sleep -Milliseconds 30
}
throw "$where : foreground=$([FgApi]::GetForegroundWindow()) want=$hwnd after 1.5s - refusing to inject"
}
function Read-Received {
Wait-File $resultFile 8000
$b = [System.IO.File]::ReadAllBytes($resultFile)
$s = [System.Text.Encoding]::UTF8.GetString($b)
if ($s.Length -gt 0 -and $s[0] -eq [char]0xFEFF) { $s = $s.Substring(1) }
return $s
}
function Get-PhoneUiText {
[void](Adb-Shell @("uiautomator", "dump", "/sdcard/ui.xml"))
$r = Adb -AdbArgs @("pull", "/sdcard/ui.xml", "$tmp\ui.xml")
if ($r.code -ne 0 -or -not (Test-Path "$tmp\ui.xml")) { return "" }
return [System.IO.File]::ReadAllText("$tmp\ui.xml", [System.Text.Encoding]::UTF8)
}
function Wait-For-LiveSession([int]$Seconds, [ref]$outXml) {
$deadline = (Get-Date).AddSeconds($Seconds)
while ((Get-Date) -lt $deadline) {
Start-Sleep -Milliseconds 900
$x = Get-PhoneUiText
if ($x -match "RTT=") { $outXml.Value = $x; return $true }
}
$outXml.Value = (Get-PhoneUiText)
return $false
}
Write-Host "=== 0. stale-agent guard (same rule as the desktop proof) ==="
$agentExe = "$repo\target\release\agent.exe"
$ag = Get-Process agent -ErrorAction SilentlyContinue
if ($ag -and (Get-Item $agentExe).LastWriteTime -gt $ag.StartTime) {
Write-Host " running agent predates current build; restarting it"
Stop-Process -Name agent -Force -ErrorAction SilentlyContinue
Start-Sleep -Milliseconds 800
$ag = $null
}
if (-not $ag) {
Start-Process $agentExe -ArgumentList "--port",$Port,"--code",$Code -WindowStyle Hidden
Start-Sleep -Seconds 1
Write-Host " agent started (v3)"
}
Write-Host "=== 1. launch target window (own process, empty field) ==="
# Retire leftovers from earlier runs WITHOUT killing them. Killing a foreground
# window hands foreground to the next app (this box's interactive GUI), and the
# foreground lock then refuses a brand-new background process any claim - the
# new target could never take foreground back.
# Signal only stop files that ALREADY EXIST: creating a fresh one here would
# hit the stop path of the run we are about to start, and that target would
# close itself the moment it launched (seen 2026-10-30: pid reported then gone).
$existingFlags = @(Get-ChildItem -Path $env:TEMP -Recurse -Filter "stop.flag" -ErrorAction SilentlyContinue |
Where-Object { $_.FullName -like "*remote*proof*" })
if ($existingFlags.Count -gt 0) {
Write-Host " retiring $($existingFlags.Count) earlier target(s) via their own stop file"
foreach ($f in $existingFlags) { (Get-Item $f.FullName).LastWriteTime = Get-Date }
Start-Sleep -Seconds 3
}
Start-Process powershell.exe -ArgumentList "-NoProfile","-ExecutionPolicy","Bypass",`
"-File","$repo\tools\text_target.ps1","-PidFile",$pidFile,`
"-ResultFile",$resultFile,"-StopFile",$stopFile,"-GrabForeground"
Wait-File $pidFile
# pid file carries "pid<n><hwnd>": the target writes its own handle once the
# form is realized, which removes the Get-Process MainWindowHandle race.
$parts = @((Get-Content $pidFile -Raw) -split "`n")
$tid = [int]$parts[0].Trim()
$hwnd = [IntPtr][long]$parts[1].Trim()
if ($hwnd -eq 0) { throw "target reported a null window handle" }
Assert-Foreground $hwnd "after launch"
Write-Host " target pid=$tid hwnd=$($hwnd.ToInt64()) foreground=yes"
Write-Host "=== 2. start app, connect via intent extras ==="
[void](Adb-Shell @("am", "force-stop", "com.verify.remote"))
[void](Adb-Shell @("am", "start", "-n", "com.verify.remote/.MainActivity",
"--es", "host", $PhoneIp, "--ei", "port", "$Port", "--es", "code", $Code))
$xmlRef = ""
if (-not (Wait-For-LiveSession 25 ([ref]$xmlRef))) { throw "phone never reported a live session (no RTT marker)" }
$script:xml = $xmlRef
Write-Host " phone: $([regex]::Match($script:xml,'text="([^"]*RTT=[^"]*)"').Groups[1].Value)"
Assert-Foreground $hwnd "after connect"
Write-Host "=== 3. phone keys A B C -> Activity.onKeyDown -> v3 Text channel ==="
# 29/30/31 = KEYCODE_A/B/C. adb-injected keys arrive with a printable
# unicodeChar, so the app routes them to nativeSendText (IME hidden). That is
# the product path introduced in 2b, not a stand-in for it.
foreach ($k in 29,30,31) {
Assert-Foreground $hwnd "before keyevent $k"
[void](Adb-Shell @("input", "keyevent", "$k"))
Start-Sleep -Milliseconds 250
}
$deadline = (Get-Date).AddSeconds(10)
$got = ""
while ((Get-Date) -lt $deadline) {
$got = Read-Received
if ($got -eq "abc") { break }
Start-Sleep -Milliseconds 300
}
Write-Host " target received: [$got]"
if ($got -ne "abc") {
Write-Host " foreground now: $([FgApi]::GetForegroundWindow()) target: $hwnd"
throw "FULL-CHAIN FAIL: expected [abc] got [$got]"
}
Write-Host " PASS: Android key -> v3 Text -> agent KEYEVENTF_UNICODE -> Windows window"
Write-Host "=== 4. phone ENTER (66): control key uses the scancode channel ==="
# Enter carries no printable unicodeChar, so it must go down the WinScancode
# path. Observable acceptance: session survives and keeps streaming (a
# single-line TextBox swallows Enter, so glyph-level proof is not possible).
Assert-Foreground $hwnd "before ENTER"
[void](Adb-Shell @("input", "keyevent", "66"))
Start-Sleep -Milliseconds 900
$xmlRef = ""
if (-not (Wait-For-LiveSession 6 ([ref]$xmlRef))) { throw "session died after ENTER" }
Write-Host " session alive: $([regex]::Match($xmlRef,'text="([^"]*RTT=[^"]*)"').Groups[1].Value)"
Write-Host "=== 5. phone BACK (4): disconnect and return to form ==="
[void](Adb-Shell @("input", "keyevent", "4"))
Start-Sleep -Seconds 2
$xml2 = Get-PhoneUiText
if ($xml2 -match "RTT=") { throw "BACK did not disconnect (still live session)" }
if ($xml2 -notmatch "android\.widget\.EditText") { throw "BACK did not return to the form" }
Write-Host " PASS: disconnected, form visible again"
Write-Host "=== 6. connect again FROM THE FORM (V4 through real UI, not intent) ==="
# Form typing uses keyevent, not 'adb input text': with the Chinese IME active,
# text injection gets composed (ASCII '.' becomes U+3002). We disable the IME,
# restore it in finally, and never assume a Chinese IME is absent.
$origIme = (Adb-Shell @("settings", "get", "secure", "default_input_method")).out.Trim()
Write-Host " original IME: [$origIme]"
if ($origIme -and $origIme -ne "null") { [void](Adb-Shell @("ime", "disable", $origIme)) }
try {
$xml3 = Get-PhoneUiText
$fields = [regex]::Matches($xml3, '<node[^>]*class="android\.widget\.EditText"[^>]*bounds="\[(\d+),(\d+)\]\[(\d+),(\d+)\]"')
if ($fields.Count -lt 3) { throw "expected 3 form fields, found $($fields.Count)" }
function Center($m) {
$a = [int]$m.Groups[1].Value; $b = [int]$m.Groups[2].Value
$c = [int]$m.Groups[3].Value; $d = [int]$m.Groups[4].Value
return @(([int](($a + $c) / 2)), ([int](($b + $d) / 2)))
}
$ipC = Center $fields[0]; $codeC = Center $fields[2]
# KEYCODE_0=7..KEYCODE_9=16, PERIOD=56, DEL=67, T=48 (A=29 -> T=29+19;
# all from javap against android-34, not memory)
[void](Adb-Shell @("input", "tap", "$($ipC[0])", "$($ipC[1])"))
Start-Sleep -Milliseconds 400
for ($i = 0; $i -lt 24; $i++) { [void](Adb-Shell @("input", "keyevent", "67")) }
foreach ($k in @(8,16,9,56,8,13,15,56,8,56,8,15,7)) { # 192.168.1.180
[void](Adb-Shell @("input", "keyevent", "$k"))
}
[void](Adb-Shell @("input", "tap", "$($codeC[0])", "$($codeC[1])"))
Start-Sleep -Milliseconds 400
for ($i = 0; $i -lt 6; $i++) { [void](Adb-Shell @("input", "keyevent", "67")) }
[void](Adb-Shell @("input", "keyevent", "48"))
$xml3 = Get-PhoneUiText
$vals = [regex]::Matches($xml3, '<node[^>]*class="android\.widget\.EditText"[^>]*text="([^"]*)"') |
ForEach-Object { $_.Groups[1].Value }
Write-Host " form now: $($vals -join ' | ')"
$btn = [regex]::Match($xml3, '<node[^>]*class="android\.widget\.Button"[^>]*bounds="\[(\d+),(\d+)\]\[(\d+),(\d+)\]"')
if (-not $btn.Success) { throw "connect button not found" }
$bc = Center $btn
Assert-Foreground $hwnd "before form connect"
[void](Adb-Shell @("input", "tap", "$($bc[0])", "$($bc[1])"))
$xmlRef = ""
if (-not (Wait-For-LiveSession 25 ([ref]$xmlRef))) {
$shown = [regex]::Matches($xmlRef, 'text="([^"]+)"') | ForEach-Object { $_.Groups[1].Value }
throw "V4 FAIL: form connect did not reach a live session. screen=[$($shown -join ' | ')]"
}
Write-Host " V4 PASS via form UI: $([regex]::Match($xmlRef,'text="([^"]*RTT=[^"]*)"').Groups[1].Value)"
}
finally {
if ($origIme -and $origIme -ne "null") {
[void](Adb-Shell @("ime", "enable", $origIme))
[void](Adb-Shell @("ime", "set", $origIme))
Write-Host " IME restored: $((Adb-Shell @("settings", "get", "secure", "default_input_method")).out.Trim())"
}
}
Write-Host "=== 7. stop target ==="
New-Item -ItemType File -Force -Path $stopFile | Out-Null
Start-Sleep -Milliseconds 600
Write-Host "=== PHONE CHAIN PROOF COMPLETE ==="

View File

@ -114,11 +114,13 @@ Start-Process powershell.exe -ArgumentList "-NoProfile","-ExecutionPolicy","Bypa
"-File","$repo\tools\text_target.ps1","-PidFile",$pidFile,`
"-ResultFile",$resultFile,"-StopFile",$stopFile
Wait-File $pidFile
$tid = [int](Get-Content $pidFile -Raw).Trim()
# target.pid holds "pid<n><hwnd>" (see text_target.ps1 Shown handler); take line 1.
$parts = @((Get-Content $pidFile -Raw) -split "`n")
$tid = [int]$parts[0].Trim()
$tp = Get-Process -Id $tid
Start-Sleep -Milliseconds 1200
$hwnd = $tp.MainWindowHandle
if ($hwnd -eq 0) { throw "target has no window handle" }
$hwnd = [IntPtr][long]$parts[1].Trim()
if ($hwnd -eq 0) { throw "target reported a null window handle" }
Write-Host " target pid=$tid hwnd=$hwnd title=[$($tp.MainWindowTitle)]"
Assert-TargetForeground $hwnd
Write-Host " target is foreground: yes"

View File

@ -10,7 +10,13 @@
param(
[Parameter(Mandatory = $true)][string]$PidFile,
[Parameter(Mandatory = $true)][string]$ResultFile,
[Parameter(Mandatory = $true)][string]$StopFile
[Parameter(Mandatory = $true)][string]$StopFile,
# SendInput lands on whatever is FOREGROUND. When the injector is driven
# from another machine (phone -> agent -> this desktop), nothing in this
# process keeps our window on top, so an unrelated window could eat the
# injection. With this switch the form re-asserts foreground every tick and
# the caller still asserts foreground before injecting.
[switch]$GrabForeground
)
$ErrorActionPreference = "Stop"
Add-Type -AssemblyName System.Windows.Forms
@ -36,6 +42,37 @@ $tb.Font = New-Object System.Drawing.Font("Segoe UI", 16.0)
$tb.Dock = "Fill"
$form.Controls.Add($tb)
$script:GrabForeground = $GrabForeground
if ($script:GrabForeground) {
Add-Type -TypeDefinition @"
using System;
using System.Runtime.InteropServices;
public static class OwnForeground {
[DllImport("user32.dll")] public static extern IntPtr GetForegroundWindow();
[DllImport("user32.dll")] public static extern bool SetForegroundWindow(IntPtr h);
[DllImport("user32.dll")] public static extern uint GetWindowThreadProcessId(IntPtr h, IntPtr pid);
[DllImport("kernel32.dll")] public static extern uint GetCurrentThreadId();
[DllImport("user32.dll")] public static extern bool AttachThreadInput(uint a, uint b, bool f);
// Deliberately NO keybd_event(VK_MENU). The usual 'tap ALT to beat the
// foreground lock' trick corrupts exactly what we measure: after ALT, Windows
// treats the next character as a menu MNEMONIC, so the first injected
// character is eaten. Measured 2026-10-30: ALT re-asserting every 60ms turned
// three injected characters into only 'b' in the target.
// Attaching input queues is a lock workaround that synthesises no key input.
public static bool Claim(IntPtr h) {
uint fgThread = GetWindowThreadProcessId(GetForegroundWindow(), IntPtr.Zero);
uint myThread = GetCurrentThreadId();
AttachThreadInput(myThread, fgThread, true);
bool ok = SetForegroundWindow(h);
AttachThreadInput(myThread, fgThread, false);
return ok && GetForegroundWindow() == h;
}
public static IntPtr Now() { return GetForegroundWindow(); }
}
"@
}
$timer = New-Object System.Windows.Forms.Timer
$timer.Interval = 150
$timer.Add_Tick({
@ -43,6 +80,14 @@ $timer.Add_Tick({
$form.Close()
return
}
if ($script:GrabForeground) {
# Re-assert only when actually lost (unconditional claiming every tick
# would fight the user for the desktop outside a proof run).
if ([OwnForeground]::Now() -ne $form.Handle) {
[void]$form.Activate()
[void][OwnForeground]::Claim($form.Handle)
}
}
if ($tb.Text -ne $script:lastWritten) {
$script:lastWritten = $tb.Text
$enc = New-Object System.Text.UTF8Encoding($true)
@ -54,7 +99,10 @@ $timer.Add_Tick({
$form.Add_Shown({
$form.Activate()
[void]$tb.Focus()
[System.IO.File]::WriteAllText($script:PidFile, "$PID")
# Report BOTH pid and window handle: a proof caller resolving the handle via
# Get-Process races with window creation and can read 0. Handle is stable
# here because the form is realized by the time Shown fires.
[System.IO.File]::WriteAllText($script:PidFile, "$PID`n" + $form.Handle.ToInt64())
})
$timer.Start()