feat: 集成豆包 ASR 语音识别后端，支持 /voice doubao 切换 (#357)

* feat: 集成豆包 ASR 语音识别后端，支持 /voice doubao 切换

- 新增 src/services/doubaoSTT.ts 适配模块，将 doubaoime-asr 的
  AsyncGenerator 协议适配为现有 VoiceStreamConnection 接口
- /voice doubao 启用豆包后端，/voice 使用默认 Anthropic 后端
- 后端选择持久化到 settings.json 的 voiceProvider 字段
- 豆包后端跳过 Anthropic OAuth 认证、语言限制和 Focus Mode
- 豆包后端松手即出结果，跳过 processing 状态
- 凭证文件存放在 ~/.claude/tts/doubao/credentials.json
- doubaoime-asr 作为 optionalDependencies 安装
- 移除 /voice 命令的 claude-ai 可用性限制，所有用户可用

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* docs: 更新 Voice Mode 文档，添加豆包 ASR 后端说明和致谢

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

src/hooks/useVoice.ts

@@ -20,6 +20,10 @@ import {
   isVoiceStreamAvailable,
   type VoiceStreamConnection,
 } from '../services/voiceStreamSTT.js'
+import {
+  connectDoubaoStream,
+  isDoubaoAvailableSync,
+} from '../services/doubaoSTT.js'
 import { logForDebugging } from '../utils/debug.js'
 import { toError } from '../utils/errors.js'
 import { getSystemLocaleLanguage } from '../utils/intl.js'
@@ -27,6 +31,10 @@ import { logError } from '../utils/log.js'
 import { getInitialSettings } from '../utils/settings/settings.js'
 import { sleep } from '../utils/sleep.js'
 
+function isDoubaoProvider(): boolean {
+  return getInitialSettings().voiceProvider === 'doubao'
+}
+
 // ─── Language normalization ─────────────────────────────────────────────
 
 const DEFAULT_STT_LANGUAGE = 'en'
@@ -574,7 +582,7 @@ export function useVoice({
   // stop when it loses focus. This enables a "multi-clauding army"
   // workflow where voice input follows window focus.
   useEffect(() => {
-    if (!enabled || !focusMode) {
+    if (!enabled || !focusMode || isDoubaoProvider()) {
       // Focus mode was disabled while a focus-driven recording was active —
       // stop the recording so it doesn't linger until the silence timer fires.
       if (focusTriggeredRef.current && stateRef.current === 'recording') {
@@ -778,7 +786,11 @@ export function useVoice({
 
     const attemptConnect = (keyterms: string[]): void => {
       const myAttemptGen = attemptGenRef.current
-      void connectVoiceStream(
+      // Select STT backend based on settings.voiceProvider
+      const connectFn = isDoubaoProvider()
+        ? (cbs: Parameters<typeof connectDoubaoStream>[0], opts: Parameters<typeof connectDoubaoStream>[1]) => connectDoubaoStream(cbs, opts)
+        : (cbs: Parameters<typeof connectVoiceStream>[0], opts: Parameters<typeof connectVoiceStream>[1]) => connectVoiceStream(cbs, opts)
+      void connectFn(
         {
           onTranscript: (text: string, isFinal: boolean) => {
             if (isStale()) return
@@ -1007,7 +1019,12 @@ export function useVoice({
       })
     }
 
-    void getVoiceKeyterms().then(attemptConnect)
+    // Doubao backend doesn't use keyterms — skip the async fetch
+    if (isDoubaoProvider()) {
+      attemptConnect([])
+    } else {
+      void getVoiceKeyterms().then(attemptConnect)
+    }
   }
 
   // ── Hold-to-talk handler ────────────────────────────────────────────
@@ -1021,7 +1038,8 @@ export function useVoice({
   // delay of ~500ms on macOS).
   const handleKeyEvent = useCallback(
     (fallbackMs = REPEAT_FALLBACK_MS): void => {
-      if (!enabled || !isVoiceStreamAvailable()) {
+      const sttAvailable = isDoubaoProvider() ? isDoubaoAvailableSync() : isVoiceStreamAvailable()
+      if (!enabled || !sttAvailable) {
         return
       }
 

src/hooks/useVoiceEnabled.ts

@@ -7,19 +7,22 @@ import {
 
 /**
  * Combines user intent (settings.voiceEnabled) with auth + GB kill-switch.
+ * When using Doubao backend, auth check is skipped (Doubao has its own credentials).
  * Only the auth half is memoized on authVersion — it's the expensive one
  * (cold getClaudeAIOAuthTokens memoize → sync `security` spawn, ~60ms/call,
  * ~180ms total in profile v5 when token refresh cleared the cache mid-session).
  * GB is a cheap cached-map lookup and stays outside the memo so a mid-session
  * kill-switch flip still takes effect on the next render.
- *
- * authVersion bumps on /login only. Background token refresh leaves it alone
- * (user is still authed), so the auth memo stays correct without re-eval.
  */
 export function useVoiceEnabled(): boolean {
   const userIntent = useAppState(s => s.settings.voiceEnabled === true)
+  const provider = useAppState(s => s.settings.voiceProvider)
+  // All hooks must be called unconditionally (Rules of Hooks)
   const authVersion = useAppState(s => s.authVersion)
   // eslint-disable-next-line react-hooks/exhaustive-deps
   const authed = useMemo(hasVoiceAuth, [authVersion])
+  if (provider === 'doubao') {
+    return userIntent && isVoiceGrowthBookEnabled()
+  }
   return userIntent && authed && isVoiceGrowthBookEnabled()
 }