feat(whisper): add dropdown preset keybinding selector for speech-to-text (#447)

* feat(whisper): add dropdown preset keybinding selector for speech-to-text

Replace the single HotkeyRecorder + 'Set to Fn' button in Whisper hotkey
settings with a dropdown offering preset keybinding options. This solves
the problem where standalone modifier keys (Option, Command, etc.) could
not be captured by the recorder since browser keydown events treat them
as modifiers rather than keys.

Preset options include: Fn (hold-to-talk), Option (hold-to-talk), F5,
F6, Option+Space, Option+., Command+., Control+Space, Shift+Space.
A 'Custom…' option in the dropdown reveals the HotkeyRecorder for
advanced key combos.

Backend changes generalize the native CGEventTap-based Fn speak-toggle
watcher to support any standalone modifier key as a hold-to-talk trigger
(Option/Alt keyCode 58, Command keyCode 55, etc.). The
hotkey-hold-monitor.swift binary already handles flagsChanged events for
modifier keys, so no native code changes were needed.

All 9 locale files updated with new i18n keys (custom, holdToTalkHint)
replacing the removed keys (setToFn, fnHint, fnHintBefore, fnHintAfter).

* fix(whisper): trim dropdown to Fn/Option/Command with L/R variants, fix Custom auto-record

- Replace the 9 preset list (F5, F6, combos) with the 3 hold-to-talk
  modifier families: Fn, Left/Right Option, Left/Right Command
- Add right-side modifier key codes (61=RightOption, 54=RightCommand) to
  STANDALONE_MODIFIER_KEYCODES and parseHoldShortcutConfig key map
- Update normalizeAccelerator to recognize left/right modifier tokens as
  modifiers when used in combos (e.g. LeftOption+Space → Alt+Space)
- Update isStandaloneAlt/isStandaloneCmd detection for left/right variants
- Format display: ⌥←/⌥→/⌘←/⌘→ with directional arrows for side info
- Fix Custom option: blur the <select> when Custom is chosen so it stops
  intercepting keyboard events, and add autoRecord prop to HotkeyRecorder
  so it auto-starts recording and grabs focus on mount

* fix(whisper): move whisperCustomMode useState above early return to fix hooks order

The useState for whisperCustomMode was placed after the early return
(!settings), causing React to throw 'Rendered more hooks than during the
previous render' when settings loaded asynchronously.

* fix(whisper): show HotkeyRecorder when Custom is selected from dropdown

The recorder visibility was gated on whisperPresetValue which only
reflects the stored hotkey — but selecting 'Custom…' doesn't change the
stored value, so the recorder never appeared. Use whisperSelectValue
instead, which accounts for the user's explicit Custom selection.

* fix(whisper): eliminate dropdown flash when recording custom keybinding

Keep whisperCustomMode=true until the stored hotkey actually updates
via IPC instead of clearing it in the recorder's onChange (which fires
before the async settings save completes). A 150ms timeout fallback
handles the edge case where the recorded value equals the current
stored value.

* fix(whisper): move whisperCustomMode useEffect above early return

The useEffect for clearing whisperCustomMode was placed after the
component-level early return guard, causing the hooks order mismatch
again. Derive whisperSpeakToggleHotkey from settings? before the guard
and move the effect up with the other hooks.

* fix(whisper): keep custom mode active until recorder saves, not on timer

The previous 150ms timeout-based useEffect fired immediately when
custom mode was entered, snapping the dropdown back before the user
could record anything. Now custom mode only clears when the
HotkeyRecorder's onChange resolves (i.e. after IPC save completes).

Author: monotykamary

src/main/main.ts

@@ -3043,6 +3043,7 @@ let hyperKeyMonitorRestartTimer: NodeJS.Timeout | null = null;
 let hyperKeyMonitorEnabled = false;
 let fnSpeakToggleLastPressedAt = 0;
 let fnSpeakToggleIsPressed = false;
+let fnSpeakToggleCurrentShortcut = 'Fn';
 type LocalSpeakBackend = 'edge-tts' | 'system-say';
 let edgeTtsConstructorResolved = false;
 let edgeTtsConstructor: any | null = null;
@@ -6299,15 +6300,15 @@ function normalizeAccelerator(shortcut: string): string {
       else normalizedModifiers.control = true;
       continue;
     }
-    if (token === 'cmd' || token === 'command' || token === 'meta' || token === 'super') {
+    if (token === 'cmd' || token === 'command' || token === 'meta' || token === 'super' || token === 'leftcmd' || token === 'leftcommand' || token === 'leftmeta' || token === 'rightcmd' || token === 'rightcommand' || token === 'rightmeta') {
       normalizedModifiers.command = true;
       continue;
     }
     if (token === 'ctrl' || token === 'control') {
       normalizedModifiers.control = true;
       continue;
     }
-    if (token === 'alt' || token === 'option') {
+    if (token === 'alt' || token === 'option' || token === 'leftalt' || token === 'leftoption' || token === 'rightalt' || token === 'rightoption') {
       normalizedModifiers.alt = true;
       continue;
     }
@@ -6405,6 +6406,29 @@ function isFnShortcut(shortcut: string): boolean {
   return Boolean(config?.fn);
 }
 
+// Standalone modifier keys that need a native CGEventTap watcher
+// instead of Electron's globalShortcut (which ignores bare modifiers).
+const STANDALONE_MODIFIER_KEYCODES: Record<string, number> = {
+  alt: 58, option: 58,                     // Left Option
+  leftoption: 58, leftalt: 58,             // Left Option (explicit)
+  rightoption: 61, rightalt: 61,           // Right Option
+  command: 55, cmd: 55, meta: 55,           // Left Command
+  leftcommand: 55, leftcmd: 55, leftmeta: 55, // Left Command (explicit)
+  rightcommand: 54, rightcmd: 54, rightmeta: 54, // Right Command
+  control: 59, ctrl: 59,                   // Left Control
+  shift: 56,                                // Left Shift
+};
+
+function isStandaloneModifierShortcut(shortcut: string): boolean {
+  const normalized = normalizeAccelerator(shortcut).trim().toLowerCase();
+  return normalized in STANDALONE_MODIFIER_KEYCODES;
+}
+
+function needsNativeHoldWatcher(shortcut: string): boolean {
+  if (!shortcut) return false;
+  return isFnOnlyShortcut(shortcut) || isFnShortcut(shortcut) || isStandaloneModifierShortcut(shortcut);
+}
+
 function parseHoldShortcutConfig(shortcut: string): {
   keyCode: number;
   cmd: boolean;
@@ -6433,16 +6457,32 @@ function parseHoldShortcutConfig(shortcut: string): {
     home: 115, end: 119, pageup: 116, pagedown: 121,
     f1: 122, f2: 120, f3: 99, f4: 118, f5: 96, f6: 97, f7: 98, f8: 100,
     f9: 101, f10: 109, f11: 103, f12: 111,
+    // Standalone modifier keys for CGEventTap monitoring
+    alt: 58, option: 58,
+    leftoption: 58, leftalt: 58,
+    rightoption: 61, rightalt: 61,
+    command: 55, cmd: 55, meta: 55,
+    leftcommand: 55, leftcmd: 55, leftmeta: 55,
+    rightcommand: 54, rightcmd: 54, rightmeta: 54,
+    control: 59, ctrl: 59,
+    shift: 56,
   };
   const keyCode = map[keyToken];
   if (!Number.isFinite(keyCode)) return null;
   const fnAsModifier = mods.has('fn') || mods.has('function');
+  // When the key token itself is a standalone modifier, set the corresponding
+  // flag so the Swift monitor checks that the modifier flag is active when
+  // the physical key is pressed (same pattern as the Fn key).
+  const isStandaloneAlt = keyToken === 'alt' || keyToken === 'option' || keyToken === 'leftoption' || keyToken === 'leftalt' || keyToken === 'rightoption' || keyToken === 'rightalt';
+  const isStandaloneCmd = keyToken === 'command' || keyToken === 'cmd' || keyToken === 'meta' || keyToken === 'leftcommand' || keyToken === 'leftcmd' || keyToken === 'leftmeta' || keyToken === 'rightcommand' || keyToken === 'rightcmd' || keyToken === 'rightmeta';
+  const isStandaloneCtrl = keyToken === 'control' || keyToken === 'ctrl';
+  const isStandaloneShift = keyToken === 'shift';
   return {
     keyCode,
-    cmd: mods.has('command') || mods.has('cmd') || mods.has('meta'),
-    ctrl: mods.has('control') || mods.has('ctrl'),
-    alt: mods.has('alt') || mods.has('option'),
-    shift: mods.has('shift'),
+    cmd: mods.has('command') || mods.has('cmd') || mods.has('meta') || isStandaloneCmd,
+    ctrl: mods.has('control') || mods.has('ctrl') || isStandaloneCtrl,
+    alt: mods.has('alt') || mods.has('option') || isStandaloneAlt,
+    shift: mods.has('shift') || isStandaloneShift,
     fn: fnAsModifier || keyToken === 'fn' || keyToken === 'function',
   };
 }
@@ -6842,7 +6882,7 @@ function startFnCommandWatcher(commandId: string, shortcut: string): void {
 
 function startFnSpeakToggleWatcher(): void {
   if (fnSpeakToggleWatcherProcess || !fnSpeakToggleWatcherEnabled) return;
-  const config = parseHoldShortcutConfig('Fn');
+  const config = parseHoldShortcutConfig(fnSpeakToggleCurrentShortcut || 'Fn');
   if (!config) return;
   const binaryPath = ensureWhisperHoldWatcherBinary();
   if (!binaryPath) return;
@@ -6951,11 +6991,11 @@ function startFnSpeakToggleWatcher(): void {
 }
 
 function syncFnSpeakToggleWatcher(hotkeys: Record<string, string>): void {
-  // Do not start the CGEventTap-based Fn watcher during onboarding.
+  // Do not start the CGEventTap-based watcher during onboarding.
   // The tap requires Input Monitoring (and sometimes Accessibility) permission,
   // which would trigger system dialogs before the user reaches the Grant Access step.
   // Exception: fnWatcherOnboardingOverride is set when the user reaches the Dictation
-  // test step (step 4) so they can actually test the Fn key during setup.
+  // test step (step 4) so they can actually test the key during setup.
   if (!loadSettings().hasSeenOnboarding && !fnWatcherOnboardingOverride) {
     stopFnSpeakToggleWatcher();
     return;
@@ -6966,12 +7006,21 @@ function syncFnSpeakToggleWatcher(hotkeys: Record<string, string>): void {
     return;
   }
   const speakToggle = String(hotkeys?.['system-supercmd-whisper-speak-toggle'] || '').trim();
-  const shouldEnable = isFnOnlyShortcut(speakToggle);
+  const shouldEnable = needsNativeHoldWatcher(speakToggle);
   if (!shouldEnable) {
+    fnSpeakToggleCurrentShortcut = '';
     stopFnSpeakToggleWatcher();
     return;
   }
+  // If the shortcut changed, stop the existing watcher so it restarts with the new key.
+  const shortcutChanged = speakToggle !== fnSpeakToggleCurrentShortcut;
+  if (shortcutChanged && fnSpeakToggleWatcherProcess) {
+    try { fnSpeakToggleWatcherProcess.kill('SIGTERM'); } catch {}
+    fnSpeakToggleWatcherProcess = null;
+    fnSpeakToggleWatcherStdoutBuffer = '';
+  }
   fnSpeakToggleWatcherEnabled = true;
+  fnSpeakToggleCurrentShortcut = speakToggle;
   startFnSpeakToggleWatcher();
 }
 
@@ -6981,7 +7030,7 @@ function syncFnCommandWatchers(hotkeys: Record<string, string>): void {
     const shortcut = String(shortcutRaw || '').trim();
     if (!shortcut) continue;
     const normalized = normalizeAccelerator(shortcut);
-    const isFnSpeakToggle = commandId === 'system-supercmd-whisper-speak-toggle' && isFnOnlyShortcut(normalized);
+    const isFnSpeakToggle = commandId === 'system-supercmd-whisper-speak-toggle' && (isFnOnlyShortcut(normalized) || isStandaloneModifierShortcut(normalized));
     if (isFnSpeakToggle) continue;
     if (!isFnShortcut(normalized)) continue;
     desired.set(commandId, normalized);
@@ -13072,6 +13121,9 @@ function registerCommandHotkeys(hotkeys: Record<string, string>): void {
     if (commandId === 'system-supercmd-whisper-speak-toggle' && isFnOnlyShortcut(normalizedShortcut)) {
       continue;
     }
+    if (commandId === 'system-supercmd-whisper-speak-toggle' && isStandaloneModifierShortcut(normalizedShortcut)) {
+      continue;
+    }
     if (isFnShortcut(normalizedShortcut)) {
       continue;
     }
@@ -14410,14 +14462,35 @@ app.whenReady().then(async () => {
 
         const isFnSpeakToggle =
           commandId === 'system-supercmd-whisper-speak-toggle' &&
-          isFnOnlyShortcut(normalizedHotkey);
+          (isFnOnlyShortcut(normalizedHotkey) || isStandaloneModifierShortcut(normalizedHotkey));
         const isFnHotkey = isFnShortcut(normalizedHotkey);
         const isHyperHotkey = isHyperShortcut(normalizedHotkey);
 
+        // Standalone modifier shortcuts (Option, Command, etc.) only work for
+        // the whisper speak-toggle (hold-to-talk) command, since they require
+        // the native CGEventTap watcher. Reject them for other commands.
+        if (isStandaloneModifierShortcut(normalizedHotkey) && !isFnSpeakToggle) {
+          // Attempt to restore old mapping if the new one failed.
+          if (oldHotkey) {
+            const normalizedOldHotkey = normalizeAccelerator(oldHotkey);
+            try {
+              const restored = globalShortcut.register(normalizedOldHotkey, async () => {
+                await runCommandById(commandId, 'hotkey');
+              });
+              if (restored) {
+                registeredHotkeys.set(normalizedOldHotkey, commandId);
+              }
+            } catch {}
+          }
+          return { success: false, error: 'unavailable' as const };
+        }
+
         // Register the new one
         try {
           let success = false;
           if (isFnSpeakToggle) {
+            // Standalone modifier or Fn-only shortcuts are handled by the
+            // native CGEventTap speak-toggle watcher, not Electron globalShortcut.
             success = true;
           } else if (isFnHotkey) {
             const fnConfig = parseHoldShortcutConfig(normalizedHotkey);

src/renderer/src/i18n/locales/de.json

@@ -384,10 +384,8 @@
         "hotkeys": {
           "title": "Whisper-Tastenkombinationen",
           "startStop": "Sprechen starten/stoppen",
-          "setToFn": "Auf Fn setzen",
-          "fnHint": "Verwende Auf Fn setzen, um die standardmaessige Push-to-Talk-Taste wiederherzustellen.",
-          "fnHintBefore": "Use",
-          "fnHintAfter": "to restore the default hold-to-talk key."
+          "custom": "Benutzerdefiniert…",
+          "holdToTalkHint": "Waehlen Sie eine Push-to-Talk-Taste. Halten zum Aufnehmen, loslassen zum Eingeben. Benutzen Sie Benutzerdefiniert fuer jede Tastenkombination."
         },
         "autoClose": {
           "title": "Auto-Close After Dictation",

src/renderer/src/i18n/locales/en.json

@@ -384,10 +384,8 @@
         "hotkeys": {
           "title": "Whisper Hotkeys",
           "startStop": "Start/Stop Speaking",
-          "setToFn": "Set to Fn",
-          "fnHint": "Use Set to Fn to restore the default hold-to-talk key.",
-          "fnHintBefore": "Use",
-          "fnHintAfter": "to restore the default hold-to-talk key."
+          "custom": "Custom…",
+          "holdToTalkHint": "Select a hold-to-talk key. Hold to record, release to type. Use Custom to record any key combo."
         },
         "autoClose": {
           "title": "Auto-Close After Dictation",

src/renderer/src/i18n/locales/es.json

@@ -384,10 +384,8 @@
         "hotkeys": {
           "title": "Atajos de Whisper",
           "startStop": "Iniciar/detener dictado",
-          "setToFn": "Asignar a Fn",
-          "fnHint": "Usa Asignar a Fn para restaurar la tecla predeterminada de pulsar para hablar.",
-          "fnHintBefore": "Use",
-          "fnHintAfter": "to restore the default hold-to-talk key."
+          "custom": "Personalizado…",
+          "holdToTalkHint": "Seleccione una tecla push-to-talk. Mantenga para grabar, suelte para escribir. Use Personalizado para grabar cualquier combinacion."
         },
         "autoClose": {
           "title": "Auto-Close After Dictation",

src/renderer/src/i18n/locales/fr.json

@@ -384,10 +384,8 @@
         "hotkeys": {
           "title": "Raccourcis Whisper",
           "startStop": "Demarrer/arreter la dictee",
-          "setToFn": "Definir sur Fn",
-          "fnHint": "Utilisez Definir sur Fn pour restaurer la touche push-to-talk par defaut.",
-          "fnHintBefore": "Use",
-          "fnHintAfter": "to restore the default hold-to-talk key."
+          "custom": "Personnalise…",
+          "holdToTalkHint": "Selectionnez une touche push-to-talk. Maintenez pour enregistrer, relachez pour saisir. Utilisez Personnalise pour enregistrer toute combinaison."
         },
         "autoClose": {
           "title": "Auto-Close After Dictation",

src/renderer/src/i18n/locales/it.json

@@ -384,10 +384,8 @@
         "hotkeys": {
           "title": "Scorciatoie di Whisper",
           "startStop": "Avvia/Ferma la dettatura",
-          "setToFn": "Imposta su Fn",
-          "fnHint": "Usa Imposta su Fn per ripristinare il tasto predefinito di registrazione.",
-          "fnHintBefore": "Usa",
-          "fnHintAfter": "per ripristinare il tasto predefinito di registrazione."
+          "custom": "Personalizzato…",
+          "holdToTalkHint": "Seleziona un tasto push-to-talk. Tieni premuto per registrare, rilascia per digitare. Usa Personalizzato per registrare qualsiasi combinazione."
         },
         "autoClose": {
           "title": "Chiusura automatica dopo la dettatura",

src/renderer/src/i18n/locales/ja.json

@@ -384,10 +384,8 @@
         "hotkeys": {
           "title": "Whisper ホットキー",
           "startStop": "発話の開始/停止",
-          "setToFn": "Fn に設定",
-          "fnHint": "「Fn に設定」を使用してデフォルトの押しっぱなし発話キーを復元します。",
-          "fnHintBefore": "使用するには",
-          "fnHintAfter": "でデフォルトの押しっぱなし発話キーを復元できます。"
+          "custom": "カスタム…",
+          "holdToTalkHint": "押しっぱなし発話キーを選択してください。押して録音、離して入力。カスタムで任意のキー組み合わせを録音できます。"
         },
         "autoClose": {
           "title": "ディクテーション後に自動で閉じる",

src/renderer/src/i18n/locales/ko.json

@@ -384,10 +384,8 @@
         "hotkeys": {
           "title": "Whisper 단축키",
           "startStop": "말하기 시작/중지",
-          "setToFn": "Fn으로 설정",
-          "fnHint": "기본 길게 눌러 말하기 키로 되돌리려면 Fn으로 설정을 사용하세요.",
-          "fnHintBefore": "사용",
-          "fnHintAfter": "하여 기본 길게 눌러 말하기 키로 복원하세요."
+          "custom": "사용자 지정…",
+          "holdToTalkHint": "길게 눌러 말하기 키를 선택하세요. 눌러서 녹음, 놓아서 입력. 사용자 지정으로 원하는 조합을 녹음할 수 있습니다."
         },
         "autoClose": {
           "title": "받아쓰기 후 자동 닫기",

src/renderer/src/i18n/locales/ru.json

@@ -384,10 +384,8 @@
         "hotkeys": {
           "title": "Whisper Hotkeys",
           "startStop": "Start/Stop Speaking",
-          "setToFn": "Set to Fn",
-          "fnHint": "Use Set to Fn to restore the default hold-to-talk key.",
-          "fnHintBefore": "Use",
-          "fnHintAfter": "to restore the default hold-to-talk key."
+          "custom": "Custom…",
+          "holdToTalkHint": "Select a hold-to-talk key. Hold to record, release to type. Use Custom to record any key combo."
         },
         "autoClose": {
           "title": "Auto-Close After Dictation",

src/renderer/src/i18n/locales/zh-Hans.json

@@ -384,10 +384,8 @@
         "hotkeys": {
           "title": "语音输入快捷键",
           "startStop": "开始/停止说话",
-          "setToFn": "设为 Fn 键",
-          "fnHint": "使用「设为 Fn 键」恢复默认的按住说话快捷键。",
-          "fnHintBefore": "使用",
-          "fnHintAfter": "可恢复默认的按住说话快捷键。"
+          "custom": "自定义…",
+          "holdToTalkHint": "选择按住说话的按键。按住录音，松开输入。使用自定义录制任意组合键。"
         },
         "autoClose": {
           "title": "听写后自动关闭",