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>

.gitignore

@@ -44,3 +44,4 @@ data
 !.codex/prompts/
 !.codex/prompts/**
 teach-me
+credentials.json

README.md

@@ -27,7 +27,7 @@
 | **Poor Mode**               | 穷鬼模式，关闭记忆提取和键入建议,大幅度减少并发请求                                                                          | /poor 可以开关                                                                                                                            |
 | **Channels 频道通知**       | MCP 服务器推送外部消息到会话（飞书/Slack/Discord/微信等），`--channels plugin:name@marketplace` 启用                         | [文档](https://ccb.agent-aura.top/docs/features/channels)                                                                                 |
 | **自定义模型供应商**        | OpenAI/Anthropic/Gemini/Grok 兼容                                                                                            | [文档](https://ccb.agent-aura.top/docs/features/custom-platform-login)                                                                    |
-| Voice Mode                  | Push-to-Talk 语音输入                                                                                                        | [文档](https://ccb.agent-aura.top/docs/features/voice-mode)                                                                               |
+| Voice Mode                  | 语音输入，支持豆包语言输入（`/voice doubao`）                                                                   | [文档](https://ccb.agent-aura.top/docs/features/voice-mode)                                                                               |
 | Computer Use                | 屏幕截图、键鼠控制                                                                                                           | [文档](https://ccb.agent-aura.top/docs/features/computer-use)                                                                             |
 | Chrome Use                  | 浏览器自动化、表单填写、数据抓取                                                                                             | [自托管](https://ccb.agent-aura.top/docs/features/chrome-use-mcp) [原生版](https://ccb.agent-aura.top/docs/features/claude-in-chrome-mcp) |
 | Sentry                      | 企业级错误追踪                                                                                                               | [文档](https://ccb.agent-aura.top/docs/internals/sentry-setup)                                                                            |
@@ -233,6 +233,10 @@ TUI (REPL) 模式需要真实终端，无法直接通过 VS Code launch 启动
  </picture>
 </a>
 
+## 致谢
+
+- [doubaoime-asr](https://github.com/starccy/doubaoime-asr) — 豆包 ASR 语音识别 SDK，为 Voice Mode 提供无需 Anthropic OAuth 的语音输入方案
+
 ## 许可证
 
 本项目仅供学习研究用途。Claude Code 的所有权利归 [Anthropic](https://www.anthropic.com/) 所有。

bun.lock

@@ -145,6 +145,9 @@
         "yaml": "^2.8.3",
         "zod": "^4.3.6",
       },
+      "optionalDependencies": {
+        "doubaoime-asr": "^0.1.0",
+      },
     },
     "packages/@ant/claude-for-chrome-mcp": {
       "name": "@ant/claude-for-chrome-mcp",
@@ -1791,6 +1794,8 @@
 
     "dompurify": ["dompurify@3.4.0", "https://registry.npmmirror.com/dompurify/-/dompurify-3.4.0.tgz", { "optionalDependencies": { "@types/trusted-types": "^2.0.7" } }, "sha512-nolgK9JcaUXMSmW+j1yaSvaEaoXYHwWyGJlkoCTghc97KgGDDSnpoU/PlEnw63Ah+TGKFOyY+X5LnxaWbCSfXg=="],
 
+    "doubaoime-asr": ["doubaoime-asr@0.1.0", "", { "dependencies": { "opus-encdec": "^0.1.1", "protobufjs": "^8.0.0", "ws": "^8.18.0" }, "bin": { "doubaoime-asr": "bin/doubaoime-asr.mjs" } }, "sha512-HYUfHkTxNdOoztXwS18e6GBRLY9dSDWX43K4WvPvEmO6+RevO6WbawMMoUfHKPb4ySQn461un7XyN5l4UGejwg=="],
+
     "dunder-proto": ["dunder-proto@1.0.1", "https://registry.npmmirror.com/dunder-proto/-/dunder-proto-1.0.1.tgz", { "dependencies": { "call-bind-apply-helpers": "^1.0.1", "es-errors": "^1.3.0", "gopd": "^1.2.0" } }, "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A=="],
 
     "ecdsa-sig-formatter": ["ecdsa-sig-formatter@1.0.11", "https://registry.npmmirror.com/ecdsa-sig-formatter/-/ecdsa-sig-formatter-1.0.11.tgz", { "dependencies": { "safe-buffer": "^5.0.1" } }, "sha512-nagl3RYrbNv6kQkeJIpt6NJZy8twLB/2vtz6yN9Z4vRKHN4/QZJIEbqohALSgwKdnksuY3k5Addp5lg8sVoVcQ=="],
@@ -2343,6 +2348,8 @@
 
     "openai": ["openai@6.34.0", "https://registry.npmmirror.com/openai/-/openai-6.34.0.tgz", { "peerDependencies": { "ws": "^8.18.0", "zod": "^3.25 || ^4.0" }, "optionalPeers": ["ws", "zod"], "bin": { "openai": "bin/cli" } }, "sha512-yEr2jdGf4tVFYG6ohmr3pF6VJuveP0EA/sS8TBx+4Eq5NT10alu5zg2dmxMXMgqpihRDQlFGpRt2XwsGj+Fyxw=="],
 
+    "opus-encdec": ["opus-encdec@0.1.1", "", {}, "sha512-TDzyGqYqrwn5UEUNaLsfLGu8Ma+HRNrgLYj7Vx5wfTnafAA21G6Bnm/qTIa3orQi/yZPZYmkdpO/gez4nfA1Rw=="],
+
     "os-tmpdir": ["os-tmpdir@1.0.2", "https://registry.npmmirror.com/os-tmpdir/-/os-tmpdir-1.0.2.tgz", {}, "sha512-D2FR03Vir7FIu45XBY20mTb+/ZSWB00sjU9jdQXt83gDrI4Ztz5Fs7/yy74g2N5SVQY4xY1qDr4rNddwYRVX0g=="],
 
     "oxc-parser": ["oxc-parser@0.121.0", "https://registry.npmmirror.com/oxc-parser/-/oxc-parser-0.121.0.tgz", { "dependencies": { "@oxc-project/types": "^0.121.0" }, "optionalDependencies": { "@oxc-parser/binding-android-arm-eabi": "0.121.0", "@oxc-parser/binding-android-arm64": "0.121.0", "@oxc-parser/binding-darwin-arm64": "0.121.0", "@oxc-parser/binding-darwin-x64": "0.121.0", "@oxc-parser/binding-freebsd-x64": "0.121.0", "@oxc-parser/binding-linux-arm-gnueabihf": "0.121.0", "@oxc-parser/binding-linux-arm-musleabihf": "0.121.0", "@oxc-parser/binding-linux-arm64-gnu": "0.121.0", "@oxc-parser/binding-linux-arm64-musl": "0.121.0", "@oxc-parser/binding-linux-ppc64-gnu": "0.121.0", "@oxc-parser/binding-linux-riscv64-gnu": "0.121.0", "@oxc-parser/binding-linux-riscv64-musl": "0.121.0", "@oxc-parser/binding-linux-s390x-gnu": "0.121.0", "@oxc-parser/binding-linux-x64-gnu": "0.121.0", "@oxc-parser/binding-linux-x64-musl": "0.121.0", "@oxc-parser/binding-openharmony-arm64": "0.121.0", "@oxc-parser/binding-wasm32-wasi": "0.121.0", "@oxc-parser/binding-win32-arm64-msvc": "0.121.0", "@oxc-parser/binding-win32-ia32-msvc": "0.121.0", "@oxc-parser/binding-win32-x64-msvc": "0.121.0" } }, "sha512-ek9o58+SCv6AV7nchiAcUJy1DNE2CC5WRdBcO0mF+W4oRjNQfPO7b3pLjTHSFECpHkKGOZSQxx3hk8viIL5YCg=="],
@@ -2435,7 +2442,7 @@
 
     "property-information": ["property-information@7.1.0", "https://registry.npmmirror.com/property-information/-/property-information-7.1.0.tgz", {}, "sha512-TwEZ+X+yCJmYfL7TPUOcvBZ4QfoT5YenQiJuX//0th53DE6w0xxLEtfK3iyryQFddXuvkIk51EEgrJQ0WJkOmQ=="],
 
-    "protobufjs": ["protobufjs@7.5.4", "https://registry.npmmirror.com/protobufjs/-/protobufjs-7.5.4.tgz", { "dependencies": { "@protobufjs/aspromise": "^1.1.2", "@protobufjs/base64": "^1.1.2", "@protobufjs/codegen": "^2.0.4", "@protobufjs/eventemitter": "^1.1.0", "@protobufjs/fetch": "^1.1.0", "@protobufjs/float": "^1.0.2", "@protobufjs/inquire": "^1.1.0", "@protobufjs/path": "^1.1.2", "@protobufjs/pool": "^1.1.0", "@protobufjs/utf8": "^1.1.0", "@types/node": ">=13.7.0", "long": "^5.0.0" } }, "sha512-CvexbZtbov6jW2eXAvLukXjXUW1TzFaivC46BpWc/3BpcCysb5Vffu+B3XHMm8lVEuy2Mm4XGex8hBSg1yapPg=="],
+    "protobufjs": ["protobufjs@8.0.1", "", { "dependencies": { "@protobufjs/aspromise": "^1.1.2", "@protobufjs/base64": "^1.1.2", "@protobufjs/codegen": "^2.0.4", "@protobufjs/eventemitter": "^1.1.0", "@protobufjs/fetch": "^1.1.0", "@protobufjs/float": "^1.0.2", "@protobufjs/inquire": "^1.1.0", "@protobufjs/path": "^1.1.2", "@protobufjs/pool": "^1.1.0", "@protobufjs/utf8": "^1.1.0", "@types/node": ">=13.7.0", "long": "^5.0.0" } }, "sha512-NWWCCscLjs+cOKF/s/XVNFRW7Yih0fdH+9brffR5NZCy8k42yRdl5KlWKMVXuI1vfCoy4o1z80XR/W/QUb3V3w=="],
 
     "proxy-addr": ["proxy-addr@2.0.7", "https://registry.npmmirror.com/proxy-addr/-/proxy-addr-2.0.7.tgz", { "dependencies": { "forwarded": "0.2.0", "ipaddr.js": "1.9.1" } }, "sha512-llQsMLSUDUPT44jdrU/O37qlnifitDP+ZwrmmZcoSKyLKvtZxpyV0n2/bD/N4tBAAZ/gJEdZU7KMraoK1+XYAg=="],
 
@@ -3029,6 +3036,8 @@
 
     "@fastify/otel/@opentelemetry/instrumentation": ["@opentelemetry/instrumentation@0.212.0", "https://registry.npmmirror.com/@opentelemetry/instrumentation/-/instrumentation-0.212.0.tgz", { "dependencies": { "@opentelemetry/api-logs": "0.212.0", "import-in-the-middle": "^2.0.6", "require-in-the-middle": "^8.0.0" }, "peerDependencies": { "@opentelemetry/api": "^1.3.0" } }, "sha512-IyXmpNnifNouMOe0I/gX7ENfv2ZCNdYTF0FpCsoBcpbIHzk81Ww9rQTYTnvghszCg7qGrIhNvWC8dhEifgX9Jg=="],
 
+    "@grpc/proto-loader/protobufjs": ["protobufjs@7.5.4", "https://registry.npmmirror.com/protobufjs/-/protobufjs-7.5.4.tgz", { "dependencies": { "@protobufjs/aspromise": "^1.1.2", "@protobufjs/base64": "^1.1.2", "@protobufjs/codegen": "^2.0.4", "@protobufjs/eventemitter": "^1.1.0", "@protobufjs/fetch": "^1.1.0", "@protobufjs/float": "^1.0.2", "@protobufjs/inquire": "^1.1.0", "@protobufjs/path": "^1.1.2", "@protobufjs/pool": "^1.1.0", "@protobufjs/utf8": "^1.1.0", "@types/node": ">=13.7.0", "long": "^5.0.0" } }, "sha512-CvexbZtbov6jW2eXAvLukXjXUW1TzFaivC46BpWc/3BpcCysb5Vffu+B3XHMm8lVEuy2Mm4XGex8hBSg1yapPg=="],
+
     "@grpc/proto-loader/yargs": ["yargs@17.7.2", "https://registry.npmmirror.com/yargs/-/yargs-17.7.2.tgz", { "dependencies": { "cliui": "^8.0.1", "escalade": "^3.1.1", "get-caller-file": "^2.0.5", "require-directory": "^2.1.1", "string-width": "^4.2.3", "y18n": "^5.0.5", "yargs-parser": "^21.1.1" } }, "sha512-7dSzzRQ++CKnNI/krKnYRV7JKKPUXMEh61soaHKg9mrWEhzFWhFnxPxGl+69cD1Ou63C13NUPCnmIcrvqCuM6w=="],
 
     "@hono/node-ws/@hono/node-server": ["@hono/node-server@1.19.13", "https://registry.npmmirror.com/@hono/node-server/-/node-server-1.19.13.tgz", { "peerDependencies": { "hono": "^4" } }, "sha512-TsQLe4i2gvoTtrHje625ngThGBySOgSK3Xo2XRYOdqGN1teR8+I7vchQC46uLJi8OF62YTYA3AhSpumtkhsaKQ=="],
@@ -3123,6 +3132,8 @@
 
     "@opentelemetry/otlp-transformer/@opentelemetry/sdk-trace-base": ["@opentelemetry/sdk-trace-base@2.6.1", "https://registry.npmmirror.com/@opentelemetry/sdk-trace-base/-/sdk-trace-base-2.6.1.tgz", { "dependencies": { "@opentelemetry/core": "2.6.1", "@opentelemetry/resources": "2.6.1", "@opentelemetry/semantic-conventions": "^1.29.0" }, "peerDependencies": { "@opentelemetry/api": ">=1.3.0 <1.10.0" } }, "sha512-r86ut4T1e8vNwB35CqCcKd45yzqH6/6Wzvpk2/cZB8PsPLlZFTvrh8yfOS3CYZYcUmAx4hHTZJ8AO8Dj8nrdhw=="],
 
+    "@opentelemetry/otlp-transformer/protobufjs": ["protobufjs@7.5.4", "https://registry.npmmirror.com/protobufjs/-/protobufjs-7.5.4.tgz", { "dependencies": { "@protobufjs/aspromise": "^1.1.2", "@protobufjs/base64": "^1.1.2", "@protobufjs/codegen": "^2.0.4", "@protobufjs/eventemitter": "^1.1.0", "@protobufjs/fetch": "^1.1.0", "@protobufjs/float": "^1.0.2", "@protobufjs/inquire": "^1.1.0", "@protobufjs/path": "^1.1.2", "@protobufjs/pool": "^1.1.0", "@protobufjs/utf8": "^1.1.0", "@types/node": ">=13.7.0", "long": "^5.0.0" } }, "sha512-CvexbZtbov6jW2eXAvLukXjXUW1TzFaivC46BpWc/3BpcCysb5Vffu+B3XHMm8lVEuy2Mm4XGex8hBSg1yapPg=="],
+
     "@opentelemetry/sdk-logs/@opentelemetry/core": ["@opentelemetry/core@2.6.1", "https://registry.npmmirror.com/@opentelemetry/core/-/core-2.6.1.tgz", { "dependencies": { "@opentelemetry/semantic-conventions": "^1.29.0" }, "peerDependencies": { "@opentelemetry/api": ">=1.0.0 <1.10.0" } }, "sha512-8xHSGWpJP9wBxgBpnqGL0R3PbdWQndL1Qp50qrg71+B28zK5OQmUgcDKLJgzyAAV38t4tOyLMGDD60LneR5W8g=="],
 
     "@opentelemetry/sdk-logs/@opentelemetry/resources": ["@opentelemetry/resources@2.6.1", "https://registry.npmmirror.com/@opentelemetry/resources/-/resources-2.6.1.tgz", { "dependencies": { "@opentelemetry/core": "2.6.1", "@opentelemetry/semantic-conventions": "^1.29.0" }, "peerDependencies": { "@opentelemetry/api": ">=1.3.0 <1.10.0" } }, "sha512-lID/vxSuKWXM55XhAKNoYXu9Cutoq5hFdkbTdI/zDKQktXzcWBVhNsOkiZFTMU9UtEWuGRNe0HUgmsFldIdxVA=="],

docs/features/voice-mode.md

@@ -1,27 +1,32 @@
 # VOICE_MODE — 语音输入
 
 > Feature Flag: `FEATURE_VOICE_MODE=1`
-> 实现状态：完整可用（需要 Anthropic OAuth）
+> 实现状态：完整可用（双后端：Anthropic OAuth / 豆包 ASR）
 > 引用数：46
 
 ## 一、功能概述
 
-VOICE_MODE 实现"按键说话"（Push-to-Talk）语音输入。用户按住空格键录音，音频通过 WebSocket 流式传输到 Anthropic STT 端点（Nova 3），实时转录显示在终端中。
+VOICE_MODE 实现"按键说话"（Push-to-Talk）语音输入。用户按住空格键录音，音频流式传输到 STT 后端，实时转录显示在终端中。支持两个后端：
+
+- **Anthropic STT（默认）**：通过 WebSocket 流式传输到 Nova 3 端点，需要 Anthropic OAuth
+- **豆包 ASR（Doubao）**：通过 `doubaoime-asr` 包的 AsyncGenerator 协议流式识别，使用独立凭证文件，无需 Anthropic OAuth
 
 ### 核心特性
 
 - **Push-to-Talk**：长按空格键录音，释放后自动发送
 - **流式转录**：录音过程中实时显示中间转录结果
 - **无缝集成**：转录文本直接作为用户消息提交到对话
+- **双后端切换**：通过 `/voice` 命令参数选择 STT 后端，持久化到 settings.json
 
 ## 二、用户交互
 
 | 操作 | 行为 |
 |------|------|
 | 长按空格 | 开始录音，显示录音状态 |
-| 释放空格 | 停止录音，等待最终转录 |
+| 释放空格 | 停止录音，转录结果自动提交 |
-| 转录完成 | 自动插入到输入框并提交 |
+| `/voice` | 切换语音模式开关（默认使用 Anthropic 后端） |
-| `/voice` 命令 | 切换语音模式开关 |
+| `/voice doubao` | 启用语音模式并使用豆包 ASR 后端 |
+| `/voice anthropic` | 切换回 Anthropic STT 后端 |
 
 ### UI 反馈
 
@@ -35,26 +40,37 @@ VOICE_MODE 实现"按键说话"（Push-to-Talk）语音输入。用户按住空
 
 文件：`src/voice/voiceModeEnabled.ts`
 
-三层检查：
+两层检查函数：
 
 ```ts
+// Anthropic 后端（需要 OAuth）
 isVoiceModeEnabled() = hasVoiceAuth() && isVoiceGrowthBookEnabled()
+
+// 豆包后端 / 通用可用性检查（不需要 OAuth）
+isVoiceAvailable() = isVoiceGrowthBookEnabled()
 ```
 
 1. **Feature Flag**：`feature('VOICE_MODE')` — 编译时/运行时开关
 2. **GrowthBook Kill-Switch**：`!getFeatureValue_CACHED_MAY_BE_STALE('tengu_amber_quartz_disabled', false)` — 紧急关闭开关（默认 false = 未禁用）
-3. **Auth 检查**：`hasVoiceAuth()` — 需要 Anthropic OAuth token（非 API key）
+3. **Auth 检查（仅 Anthropic）**：`hasVoiceAuth()` — 需要 Anthropic OAuth token（非 API key）
+4. **Provider 检查**：`voiceProvider` 设置决定使用哪个后端，豆包后端跳过 OAuth 检查
 
 ### 3.2 核心模块
 
 | 模块 | 职责 |
 |------|------|
 | `src/voice/voiceModeEnabled.ts` | Feature flag + GrowthBook + Auth 三层门控 |
-| `src/hooks/useVoice.ts` | React hook 管理录音状态和 WebSocket 连接 |
+| `src/hooks/useVoice.ts` | React hook 管理录音状态和后端连接 |
-| `src/services/voiceStreamSTT.ts` | WebSocket 流式传输到 Anthropic STT |
+| `src/services/voiceStreamSTT.ts` | Anthropic WebSocket 流式 STT |
+| `src/services/doubaoSTT.ts` | 豆包 ASR 适配器（AsyncGenerator → VoiceStreamConnection） |
+| `src/commands/voice/voice.ts` | `/voice` 命令实现，处理后端选择和持久化 |
+| `src/hooks/useVoiceEnabled.ts` | 语音启用状态 hook，根据 provider 决定是否跳过 OAuth |
+| `src/utils/settings/types.ts` | `voiceProvider: 'anthropic' | 'doubao'` 设置类型定义 |
 
 ### 3.3 数据流
 
+#### Anthropic 后端
+
 ```
 用户按下空格键
       │
@@ -79,20 +95,108 @@ WebSocket 连接到 Anthropic STT 端点
 转录文本 → 插入输入框 → 自动提交
 ```
 
+#### 豆包 ASR 后端
+
+```
+用户按下空格键
+      │
+      ▼
+useVoice hook 激活（检测到 voiceProvider === 'doubao'）
+      │
+      ▼
+macOS 原生音频 / SoX 开始录音
+      │
+      ▼
+connectDoubaoStream() 创建 AudioChunkQueue + VoiceStreamConnection
+      │
+      ├──→ onReady 立即触发（无需等待握手）
+      │
+      ▼
+音频数据通过 AudioChunkQueue 传入 transcribeRealtime()
+      │
+      ├──→ INTERIM_RESULT → 实时显示中间转录
+      ├──→ FINAL_RESULT   → 显示最终转录
+      │
+      ▼
+用户释放空格键
+      │
+      ▼
+finalize() 立即返回（豆包在录音过程中已返回结果，无需等待）
+      │
+      ▼
+转录文本 → 插入输入框 → 自动提交
+```
+
 ### 3.4 音频录制
 
-支持两种音频后端：
+支持两种音频后端（两个 STT 后端共享）：
 - **macOS 原生音频**：优先使用，低延迟
 - **SoX（Sound eXchange）**：回退方案，跨平台
 
-音频流通过 WebSocket 发送到 Anthropic 的 Nova 3 STT 模型。
+### 3.5 豆包 ASR 适配器设计
+
+文件：`src/services/doubaoSTT.ts`
+
+豆包后端使用适配器模式，将 `doubaoime-asr` 的 AsyncGenerator 协议桥接到 `VoiceStreamConnection` 接口：
+
+**AudioChunkQueue** — push 式异步队列：
+- 实现 `AsyncIterable<Uint8Array>` 接口
+- `push(chunk)` 将音频数据入队，`push(null)` 发送结束信号
+- 内部维护等待者（waiting）和缓冲队列（chunks）两个状态
+
+**connectDoubaoStream()** — 连接入口：
+- 动态导入 `doubaoime-asr`（optionalDependencies）
+- 从 `~/.claude/tts/doubao/credentials.json` 加载凭证
+- 创建 AudioChunkQueue 和 VoiceStreamConnection
+- 立即触发 `onReady`（避免与 useVoice 的音频缓冲死锁）
+- `finalize()` 立即返回（豆包在录音过程中已返回结果）
+- 后台 async IIFE 消费 `transcribeRealtime` generator，映射响应类型到回调
+
+**响应类型映射**：
+
+| doubaoime-asr ResponseType | 回调映射 |
+|----------------------------|----------|
+| SESSION_STARTED | 日志记录 |
+| VAD_START | 日志记录 |
+| INTERIM_RESULT | `onTranscript(text, false)` |
+| FINAL_RESULT | `onTranscript(text, true)` |
+| ERROR | `onError(errorMsg)` |
+| SESSION_FINISHED | 日志记录 |
+
+### 3.6 后端选择逻辑
+
+文件：`src/hooks/useVoice.ts`
+
+```ts
+// 判断当前 provider
+isDoubaoProvider() → 读取 settings.voiceProvider
+
+// handleKeyEvent 中的可用性检查
+const sttAvailable = isDoubaoProvider()
+  ? isDoubaoAvailableSync()    // 乐观检查（首次返回 true）
+  : isVoiceStreamAvailable()   // Anthropic WebSocket 检查
+
+// attemptConnect 中的连接函数选择
+const connectFn = isDoubaoProvider()
+  ? connectDoubaoStream
+  : connectVoiceStream
+```
+
+豆包后端的特殊处理：
+- 跳过 `getVoiceKeyterms()` 调用（豆包无需关键词提示）
+- 跳过 Focus Mode（`if (!enabled || !focusMode || isDoubaoProvider())`）
 
 ## 四、关键设计决策
 
-1. **OAuth 独占**：语音模式使用 `voice_stream` 端点（claude.ai），仅 Anthropic OAuth 用户可用。API key、Bedrock、Vertex 用户无法使用
+1. **双后端共存**：豆包后端作为独立适配器与 Anthropic 后端并存，不替换原有流程，通过 `voiceProvider` 设置切换
-2. **GrowthBook 负向门控**：`tengu_amber_quartz_disabled` 默认 `false`，新安装自动可用（无需等 GrowthBook 初始化）
+2. **设置持久化**：`voiceProvider` 存储在 `settings.json`，通过 `/voice` 命令修改，跨会话生效
-3. **Keychain 缓存**：`getClaudeAIOAuthTokens()` 首次调用访问 macOS keychain（~20-50ms），后续缓存命中
+3. **OAuth 独占（Anthropic）**：Anthropic 后端使用 `voice_stream` 端点（claude.ai），仅 OAuth 用户可用
-4. **独立于主 feature flag**：`isVoiceGrowthBookEnabled()` 在 feature flag 关闭时短路返回 `false`，不触发任何模块加载
+4. **豆包无需 OAuth**：豆包后端使用独立凭证文件，不依赖 Anthropic 认证，通过 `isVoiceAvailable()` 放宽门控
+5. **GrowthBook 负向门控**：`tengu_amber_quartz_disabled` 默认 `false`，新安装自动可用
+6. **onReady 立即触发**：豆包后端在连接建立后立即触发 `onReady`，避免与 useVoice 音频缓冲的时序死锁（Anthropic 需要等待 WebSocket 握手）
+7. **finalize() 立即返回**：豆包在录音过程中已返回所有结果，用户抬手时无需等待处理
+8. **乐观可用性检查**：`isDoubaoAvailableSync()` 在首次调用时返回 `true`，实际导入错误在 `connectDoubaoStream` 中处理
+9. **optionalDependencies**：`doubaoime-asr` 作为可选依赖，安装失败不影响 Anthropic 后端
 
 ## 五、使用方式
 
@@ -100,26 +204,60 @@ WebSocket 连接到 Anthropic STT 端点
 # 启用 feature
 FEATURE_VOICE_MODE=1 bun run dev
 
-# 在 REPL 中使用
+# 在 REPL 中使用 Anthropic 后端
 # 1. 确保已通过 OAuth 登录（claude.ai 订阅）
-# 2. 按住空格键说话
+# 2. 输入 /voice 启用
-# 3. 释放空格键等待转录
+# 3. 按住空格键说话
-# 4. 或使用 /voice 命令切换开关
+# 4. 释放空格键等待转录
+
+# 在 REPL 中使用豆包 ASR 后端
+# 1. 确保 doubaoime-asr 已安装（bun add doubaoime-asr）
+# 2. 配置凭证文件：~/.claude/tts/doubao/credentials.json
+# 3. 输入 /voice doubao 启用
+# 4. 按住空格键说话
+# 5. 释放空格键，转录结果即刻显示
+
+# 切换后端
+/voice doubao      # 切换到豆包 ASR
+/voice anthropic   # 切换回 Anthropic STT
+/voice             # 关闭语音模式
+```
+
+### 豆包凭证配置
+
+凭证文件路径：`~/.claude/tts/doubao/credentials.json`
+
+```json
+{
+  "deviceId": "...",
+  "installId": "...",
+  "cdid": "...",
+  "openudid": "...",
+  "clientudid": "...",
+  "token": "..."
+}
 ```
 
 ## 六、外部依赖
 
-| 依赖 | 说明 |
+| 依赖 | 说明 | 适用后端 |
-|------|------|
+|------|------|----------|
-| Anthropic OAuth | claude.ai 订阅登录，非 API key |
+| Anthropic OAuth | claude.ai 订阅登录，非 API key | Anthropic |
-| GrowthBook | `tengu_amber_quartz_disabled` 紧急关闭 |
+| GrowthBook | `tengu_amber_quartz_disabled` 紧急关闭 | 通用 |
-| macOS 原生音频 或 SoX | 音频录制 |
+| macOS 原生音频 或 SoX | 音频录制 | 通用 |
-| Nova 3 STT | 语音转文本模型 |
+| Nova 3 STT | Anthropic 语音转文本模型 | Anthropic |
+| doubaoime-asr | 豆包 ASR SDK（optionalDependencies） | 豆包 |
+| 凭证文件 | `~/.claude/tts/doubao/credentials.json` | 豆包 |
 
 ## 七、文件索引
 
-| 文件 | 行数 | 职责 |
+| 文件 | 职责 |
-|------|------|------|
+|------|------|
-| `src/voice/voiceModeEnabled.ts` | 54 | 三层门控逻辑 |
+| `src/voice/voiceModeEnabled.ts` | 三层门控逻辑 + `isVoiceAvailable()` |
-| `src/hooks/useVoice.ts` | — | React hook（录音状态 + WebSocket） |
+| `src/hooks/useVoice.ts` | React hook（录音状态 + 后端选择 + 连接管理） |
-| `src/services/voiceStreamSTT.ts` | — | STT WebSocket 流式传输 |
+| `src/hooks/useVoiceEnabled.ts` | 语音启用状态 hook（按 provider 决定 OAuth 检查） |
+| `src/services/voiceStreamSTT.ts` | Anthropic STT WebSocket 流式传输 |
+| `src/services/doubaoSTT.ts` | 豆包 ASR 适配器（AudioChunkQueue + connectDoubaoStream） |
+| `src/commands/voice/voice.ts` | `/voice` 命令（开关 + 后端选择） |
+| `src/commands/voice/index.ts` | 命令注册（去除 availability 限制） |
+| `src/utils/settings/types.ts` | `voiceProvider` 类型定义 |

package.json

@@ -205,5 +205,8 @@
     "xss": "^1.0.15",
     "yaml": "^2.8.3",
     "zod": "^4.3.6"
+  },
+  "optionalDependencies": {
+    "doubaoime-asr": "^0.1.0"
   }
 }

src/commands/voice/index.ts

@@ -1,17 +1,15 @@
 import type { Command } from '../../commands.js'
 import {
-  isVoiceGrowthBookEnabled,
+  isVoiceAvailable,
-  isVoiceModeEnabled,
 } from '../../voice/voiceModeEnabled.js'
 
 const voice = {
   type: 'local',
   name: 'voice',
-  description: 'Toggle voice mode',
+  description: 'Toggle voice mode. Use /voice doubao for Doubao ASR backend',
-  availability: ['claude-ai'],
+  isEnabled: () => isVoiceAvailable(),
-  isEnabled: () => isVoiceGrowthBookEnabled(),
   get isHidden() {
-    return !isVoiceModeEnabled()
+    return !isVoiceAvailable()
   },
   supportsNonInteractive: false,
   load: () => import('./voice.js'),

src/commands/voice/voice.ts

@@ -2,29 +2,19 @@ import { normalizeLanguageForSTT } from '../../hooks/useVoice.js'
 import { getShortcutDisplay } from '../../keybindings/shortcutFormat.js'
 import { logEvent } from '../../services/analytics/index.js'
 import type { LocalCommandCall } from '../../types/command.js'
-import { isAnthropicAuthEnabled } from '../../utils/auth.js'
 import { getGlobalConfig, saveGlobalConfig } from '../../utils/config.js'
 import { settingsChangeDetector } from '../../utils/settings/changeDetector.js'
 import {
   getInitialSettings,
   updateSettingsForSource,
 } from '../../utils/settings/settings.js'
-import { isVoiceModeEnabled } from '../../voice/voiceModeEnabled.js'
+import { isVoiceAvailable } from '../../voice/voiceModeEnabled.js'
 
 const LANG_HINT_MAX_SHOWS = 2
 
-export const call: LocalCommandCall = async () => {
+export const call: LocalCommandCall = async (args) => {
-  // Check auth and kill-switch before allowing voice mode
+  // Check kill-switch before allowing voice mode
-  if (!isVoiceModeEnabled()) {
+  if (!isVoiceAvailable()) {
-    // Differentiate: OAuth-less users get an auth hint, everyone else
-    // gets nothing (command shouldn't be reachable when the kill-switch is on).
-    if (!isAnthropicAuthEnabled()) {
-      return {
-        type: 'text' as const,
-        value:
-          'Voice mode requires a Claude.ai account. Please run /login to sign in.',
-      }
-    }
     return {
       type: 'text' as const,
       value: 'Voice mode is not available.',
@@ -33,6 +23,47 @@ export const call: LocalCommandCall = async () => {
 
   const currentSettings = getInitialSettings()
   const isCurrentlyEnabled = currentSettings.voiceEnabled === true
+  const providerArg = args?.trim().toLowerCase()
+
+  // Handle provider argument when already enabled — switch backend only
+  if (isCurrentlyEnabled && providerArg === 'doubao') {
+    const result = updateSettingsForSource('userSettings', {
+      voiceProvider: 'doubao',
+    })
+    if (result.error) {
+      return {
+        type: 'text' as const,
+        value:
+          'Failed to update settings. Check your settings file for syntax errors.',
+      }
+    }
+    settingsChangeDetector.notifyChange('userSettings')
+    const key = getShortcutDisplay('voice:pushToTalk', 'Chat', 'Space')
+    return {
+      type: 'text' as const,
+      value: `Voice mode switched to Doubao ASR. Hold ${key} to record.`,
+    }
+  }
+
+  // Handle provider argument when already enabled — switch to anthropic
+  if (isCurrentlyEnabled && providerArg === 'anthropic') {
+    const result = updateSettingsForSource('userSettings', {
+      voiceProvider: 'anthropic',
+    })
+    if (result.error) {
+      return {
+        type: 'text' as const,
+        value:
+          'Failed to update settings. Check your settings file for syntax errors.',
+      }
+    }
+    settingsChangeDetector.notifyChange('userSettings')
+    const key = getShortcutDisplay('voice:pushToTalk', 'Chat', 'Space')
+    return {
+      type: 'text' as const,
+      value: `Voice mode switched to Anthropic STT. Hold ${key} to record.`,
+    }
+  }
 
   // Toggle OFF — no checks needed
   if (isCurrentlyEnabled) {
@@ -54,7 +85,10 @@ export const call: LocalCommandCall = async () => {
     }
   }
 
-  // Toggle ON — run pre-flight checks first
+  // Toggle ON — determine provider from argument or default
+  const provider = providerArg === 'doubao' ? 'doubao' : 'anthropic'
+
+  // Run pre-flight checks
   const { isVoiceStreamAvailable } = await import(
     '../../services/voiceStreamSTT.js'
   )
@@ -70,8 +104,8 @@ export const call: LocalCommandCall = async () => {
     }
   }
 
-  // Check for API key
+  // Check for API key (only for Anthropic backend — Doubao uses its own credentials)
-  if (!isVoiceStreamAvailable()) {
+  if (provider !== 'doubao' && !isVoiceStreamAvailable()) {
     return {
       type: 'text' as const,
       value:
@@ -111,8 +145,11 @@ export const call: LocalCommandCall = async () => {
     }
   }
 
-  // All checks passed — enable voice
+  // All checks passed — enable voice with provider
-  const result = updateSettingsForSource('userSettings', { voiceEnabled: true })
+  const result = updateSettingsForSource('userSettings', {
+    voiceEnabled: true,
+    ...(provider === 'doubao' ? { voiceProvider: 'doubao' } : {}),
+  })
   if (result.error) {
     return {
       type: 'text' as const,
@@ -123,28 +160,30 @@ export const call: LocalCommandCall = async () => {
   settingsChangeDetector.notifyChange('userSettings')
   logEvent('tengu_voice_toggled', { enabled: true })
   const key = getShortcutDisplay('voice:pushToTalk', 'Chat', 'Space')
-  const stt = normalizeLanguageForSTT(currentSettings.language)
-  const cfg = getGlobalConfig()
-  // Reset the hint counter whenever the resolved STT language changes
-  // (including first-ever enable, where lastLanguage is undefined).
-  const langChanged = cfg.voiceLangHintLastLanguage !== stt.code
-  const priorCount = langChanged ? 0 : (cfg.voiceLangHintShownCount ?? 0)
-  const showHint = !stt.fellBackFrom && priorCount < LANG_HINT_MAX_SHOWS
   let langNote = ''
-  if (stt.fellBackFrom) {
+  const providerLabel = provider === 'doubao' ? 'Doubao ASR' : 'Anthropic'
-    langNote = ` Note: "${stt.fellBackFrom}" is not a supported dictation language; using English. Change it via /config.`
+  // Doubao backend handles all languages natively — skip language hints
-  } else if (showHint) {
+  if (provider !== 'doubao') {
-    langNote = ` Dictation language: ${stt.code} (/config to change).`
+    const stt = normalizeLanguageForSTT(currentSettings.language)
-  }
+    const cfg = getGlobalConfig()
-  if (langChanged || showHint) {
+    const langChanged = cfg.voiceLangHintLastLanguage !== stt.code
-    saveGlobalConfig(prev => ({
+    const priorCount = langChanged ? 0 : (cfg.voiceLangHintShownCount ?? 0)
-      ...prev,
+    const showHint = !stt.fellBackFrom && priorCount < LANG_HINT_MAX_SHOWS
-      voiceLangHintShownCount: priorCount + (showHint ? 1 : 0),
+    if (stt.fellBackFrom) {
-      voiceLangHintLastLanguage: stt.code,
+      langNote = ` Note: "${stt.fellBackFrom}" is not a supported dictation language; using English. Change it via /config.`
-    }))
+    } else if (showHint) {
+      langNote = ` Dictation language: ${stt.code} (/config to change).`
+    }
+    if (langChanged || showHint) {
+      saveGlobalConfig(prev => ({
+        ...prev,
+        voiceLangHintShownCount: priorCount + (showHint ? 1 : 0),
+        voiceLangHintLastLanguage: stt.code,
+      }))
+    }
   }
   return {
     type: 'text' as const,
-    value: `Voice mode enabled. Hold ${key} to record.${langNote}`,
+    value: `Voice mode enabled (${providerLabel}). Hold ${key} to record.${langNote}`,
   }
 }

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()
 }

src/services/doubaoSTT.ts

@@ -0,0 +1,230 @@
+// Doubao (豆包) ASR speech-to-text adapter for voice mode.
+//
+// Wraps the doubaoime-asr npm package to expose the same interface as
+// voiceStreamSTT.ts. The doubao backend uses an AsyncGenerator-based
+// streaming protocol internally; this adapter bridges it to the
+// send/finalize/close pattern used by useVoice.ts.
+
+import { homedir } from 'node:os'
+import type { ASRResponse } from 'doubaoime-asr'
+import type { FinalizeSource, VoiceStreamCallbacks, VoiceStreamConnection } from './voiceStreamSTT.js'
+import { logForDebugging } from '../utils/debug.js'
+import { logError } from '../utils/log.js'
+
+// Re-export FinalizeSource so useVoice can import from either module
+export type { FinalizeSource } from './voiceStreamSTT.js'
+
+// Maximum time to wait for the generator to finish after end-of-stream signal.
+const FINALIZE_SAFETY_TIMEOUT_MS = 5_000
+
+// ─── AsyncIterable audio queue ─────────────────────────────────────────
+
+// A push-based queue that implements AsyncIterable<Uint8Array>.
+// send() pushes chunks; push(null) signals end-of-stream.
+class AudioChunkQueue {
+  private chunks: (Uint8Array | null)[] = []
+  private waiting: ((result: IteratorResult<Uint8Array>) => void) | null = null
+  private done = false
+
+  push(chunk: Uint8Array | null): void {
+    if (this.done) return
+    if (chunk === null) {
+      this.done = true
+      if (this.waiting) {
+        const resolve = this.waiting
+        this.waiting = null
+        resolve({ value: undefined, done: true })
+      }
+      return
+    }
+    if (this.waiting) {
+      const resolve = this.waiting
+      this.waiting = null
+      resolve({ value: chunk, done: false })
+    } else {
+      this.chunks.push(chunk)
+    }
+  }
+
+  abort(): void {
+    this.done = true
+    this.chunks.length = 0
+    if (this.waiting) {
+      const resolve = this.waiting
+      this.waiting = null
+      resolve({ value: undefined, done: true })
+    }
+  }
+
+  [Symbol.asyncIterator](): AsyncIterator<Uint8Array> {
+    return {
+      next: async (): Promise<IteratorResult<Uint8Array>> => {
+        if (this.chunks.length > 0) {
+          const chunk = this.chunks.shift()!
+          return { value: chunk, done: false }
+        }
+        if (this.done) {
+          return { value: undefined, done: true }
+        }
+        return new Promise<IteratorResult<Uint8Array>>((resolve) => {
+          this.waiting = resolve
+        })
+      },
+    }
+  }
+}
+
+// ─── Availability ────────────────────────────────────────────────────────
+
+let doubaoAvailable: boolean | null = null
+
+export async function isDoubaoAvailable(): Promise<boolean> {
+  if (doubaoAvailable !== null) return doubaoAvailable
+  try {
+    await import('doubaoime-asr')
+    doubaoAvailable = true
+  } catch {
+    doubaoAvailable = false
+  }
+  return doubaoAvailable
+}
+
+// Synchronous check — returns cached result or optimistic true when
+// VOICE_PROVIDER=doubao is set and no cached result exists yet.
+// The actual import happens in connectDoubaoStream which reports errors.
+export function isDoubaoAvailableSync(): boolean {
+  if (doubaoAvailable !== null) return doubaoAvailable
+  return true
+}
+
+// ─── Connection ──────────────────────────────────────────────────────────
+
+export async function connectDoubaoStream(
+  callbacks: VoiceStreamCallbacks,
+  _options?: { language?: string },
+): Promise<VoiceStreamConnection | null> {
+  let doubaoAsr: typeof import('doubaoime-asr')
+  try {
+    doubaoAsr = await import('doubaoime-asr')
+  } catch {
+    logError(new Error('[doubao-asr] Failed to import doubaoime-asr package'))
+    callbacks.onError('doubaoime-asr package is not installed. Install it with: bun add doubaoime-asr', { fatal: true })
+    return null
+  }
+
+  const { transcribeRealtime, ASRConfig, ResponseType } = doubaoAsr
+
+  const queue = new AudioChunkQueue()
+  let finalized = false
+
+  // Resolve handle for finalize() promise — wrapped in an object to avoid
+  // TypeScript closure-scope type narrowing issues (TS2349 "not callable").
+  const finalizeHandle: { resolve: ((source: FinalizeSource) => void) | null } = { resolve: null }
+
+  const connection: VoiceStreamConnection = {
+    send(audioChunk: Buffer): void {
+      if (finalized) return
+      queue.push(new Uint8Array(audioChunk.buffer, audioChunk.byteOffset, audioChunk.byteLength))
+    },
+    finalize(): Promise<FinalizeSource> {
+      if (finalized) return Promise.resolve<FinalizeSource>('ws_already_closed')
+      finalized = true
+      queue.push(null) // signal end-of-stream to the generator
+      // Doubao returns FINAL_RESULT during recording — by the time the user
+      // releases the key, all transcripts are already in accumulatedRef.
+      // Resolve immediately so the UI skips the 'processing' state and goes
+      // straight to displaying the result.
+      logForDebugging('[doubao-asr] Finalize — resolving immediately')
+      return Promise.resolve<FinalizeSource>('post_closestream_endpoint')
+    },
+    close(): void {
+      finalized = true
+      queue.abort()
+      const r = finalizeHandle.resolve
+      finalizeHandle.resolve = null
+      if (r) r('ws_close')
+      callbacks.onClose()
+    },
+    isConnected(): boolean {
+      return true
+    },
+  }
+
+  // Start the ASR session in the background
+  const config = new ASRConfig({ credentialPath: `${homedir()}/.claude/tts/doubao/credentials.json` })
+
+  // Ensure credentials are initialized (may auto-generate)
+  try {
+    await config.ensureCredentials()
+  } catch (err) {
+    logError(new Error(`[doubao-asr] Credential initialization failed: ${String(err)}`))
+    callbacks.onError(`Doubao ASR 凭证初始化失败: ${String(err)}`, { fatal: true })
+    return null
+  }
+
+  // Fire onReady immediately — unlike the Anthropic WebSocket which needs to
+  // wait for a handshake, the doubao backend accepts audio through the queue
+  // and handles connection internally. The caller (useVoice.ts) needs onReady
+  // to fire before it will route audio chunks via connection.send().
+  logForDebugging('[doubao-asr] Firing onReady immediately')
+  callbacks.onReady(connection)
+
+  // Consume the AsyncGenerator in the background
+  void (async () => {
+    try {
+      const audioSource: AsyncIterable<Uint8Array> = queue
+      const gen: AsyncGenerator<ASRResponse> = transcribeRealtime(audioSource, { config })
+
+      for await (const resp of gen) {
+        if (finalized && resp.type !== ResponseType.FINAL_RESULT && resp.type !== ResponseType.SESSION_FINISHED) {
+          continue
+        }
+
+        switch (resp.type) {
+          case ResponseType.SESSION_STARTED:
+            logForDebugging('[doubao-asr] Session started')
+            break
+          case ResponseType.VAD_START:
+            logForDebugging('[doubao-asr] VAD detected speech start')
+            break
+          case ResponseType.INTERIM_RESULT:
+            if (resp.text) {
+              callbacks.onTranscript(resp.text, false)
+            }
+            break
+          case ResponseType.FINAL_RESULT:
+            if (resp.text) {
+              callbacks.onTranscript(resp.text, true)
+            }
+            break
+          case ResponseType.ERROR:
+            logError(new Error(`[doubao-asr] Error: ${resp.errorMsg}`))
+            if (!finalized) {
+              callbacks.onError(resp.errorMsg || 'Doubao ASR 识别错误')
+            }
+            break
+          case ResponseType.SESSION_FINISHED:
+            logForDebugging('[doubao-asr] Session finished')
+            break
+          default:
+            break
+        }
+      }
+
+      // Generator exhausted naturally
+      const r = finalizeHandle.resolve
+      finalizeHandle.resolve = null
+      if (r) r('post_closestream_endpoint')
+    } catch (err) {
+      logError(new Error(`[doubao-asr] Stream error: ${String(err)}`))
+      if (!finalized) {
+        callbacks.onError(`Doubao ASR 连接错误: ${String(err)}`)
+      }
+      const r2 = finalizeHandle.resolve
+      finalizeHandle.resolve = null
+      if (r2) r2('ws_close')
+    }
+  })()
+
+  return connection
+}

src/utils/settings/types.ts

@@ -880,6 +880,10 @@ export const SettingsSchema = lazySchema(() =>
               .boolean()
               .optional()
               .describe('Enable voice mode (hold-to-talk dictation)'),
+            voiceProvider: z
+              .enum(['anthropic', 'doubao'])
+              .optional()
+              .describe('Voice STT backend: "anthropic" (default) or "doubao" (Doubao ASR)'),
           }
         : {}),
       ...(feature('KAIROS')

src/utils/suggestions/__tests__/commandSuggestions.test.ts

@@ -23,7 +23,7 @@ function makeCommand(name: string, opts?: Partial<Command>): Command {
     type: 'local',
     handler: () => {},
     ...opts,
-  } as Command
+  } as unknown as Command
 }
 
 function makePromptCommand(
@@ -37,7 +37,7 @@ function makePromptCommand(
     handler: () => {},
     source: 'userSettings',
     ...opts,
-  } as Command
+  } as unknown as Command
 }
 
 // ─── isCommandInput ───────────────────────────────────────────────────

src/voice/voiceModeEnabled.ts

@@ -44,11 +44,18 @@ export function hasVoiceAuth(): boolean {
 }
 
 /**
- * Full runtime check: auth + GrowthBook kill-switch. Callers: `/voice`
+ * Full runtime check for Anthropic voice_stream backend.
- * (voice.ts, voice/index.ts), ConfigTool, VoiceModeNotice — command-time
+ * Returns true when both auth + GrowthBook kill-switch pass.
- * paths where a fresh keychain read is acceptable. For React render
- * paths use useVoiceEnabled() instead (memoizes the auth half).
  */
 export function isVoiceModeEnabled(): boolean {
   return hasVoiceAuth() && isVoiceGrowthBookEnabled()
 }
+
+/**
+ * Check if voice mode can be activated with any STT backend.
+ * Always returns true when VOICE_MODE feature flag is on and GrowthBook
+ * kill-switch is off — the Doubao backend does not require Anthropic auth.
+ */
+export function isVoiceAvailable(): boolean {
+  return isVoiceGrowthBookEnabled()
+}