feat: 统一手动发送入口为文字转语音

- 移除普通文本、图片和本地语音的手动发送入口
- 保留文字转语音的生成、试听和发送能力

tests/component/chat-menus.test.tsx

@@ -91,7 +91,7 @@ describe('chat menus', () => {
     expect(searchInput).toHaveFocus()
     await user.type(searchInput, '测试')
     expect(onContentFilterChange).toHaveBeenCalledTimes(2)
-    expect(screen.getByRole('button', { name: '发送消息' })).toBeDisabled()
+    expect(screen.getByRole('button', { name: '文字转语音' })).toBeDisabled()
 
     await user.click(screen.getByRole('button', { name: '关闭搜索' }))
     expect(onContentFilterChange).toHaveBeenLastCalledWith('')

tests/component/personal-wechat-send-dialog.test.tsx

@@ -1,4 +1,4 @@
-import { fireEvent, render, screen, waitFor } from '@testing-library/react'
+import { render, screen, waitFor } from '@testing-library/react'
 import userEvent from '@testing-library/user-event'
 import type React from 'react'
 import { beforeEach, describe, expect, it, vi } from 'vitest'
@@ -13,12 +13,9 @@ vi.mock('../../src/renderer/src/utils/runtime-environment', () => ({
 
 const getStatus = vi.fn()
 const getRuntimeStatus = vi.fn()
-const downloadRuntime = vi.fn()
 const onRuntimeProgress = vi.fn(() => vi.fn())
 const rebind = vi.fn()
-const selectImage = vi.fn()
-const selectVoice = vi.fn()
-const sendMessage = vi.fn()
+const sendGeneratedTtsVoice = vi.fn()
 const getTextToSpeechSettings = vi.fn()
 const listTextToSpeechVoices = vi.fn()
 const synthesizeTextToSpeech = vi.fn()
@@ -32,6 +29,7 @@ const contact = {
   md5: 'fixture-md5',
   type: 'group' as const
 }
+
 const readyStatus = {
   state: 'online' as const,
   platform: 'darwin',
@@ -59,6 +57,7 @@ const readyStatus = {
   canSendVoice: true,
   message: '个人微信已绑定'
 }
+
 const readyRuntime = {
   version: 'v0.0.18',
   state: 'ready' as const,
@@ -80,32 +79,19 @@ function renderDialog(
 }
 
 async function startComposer(): Promise<void> {
-  await screen.findByText('绑定个人微信')
-  const bind = screen.queryByRole('button', { name: '绑定微信' })
-  if (bind) {
-    fireEvent.click(bind)
-    await screen.findByText('✓ 微信已绑定')
-  }
-  const detect = await screen.findByRole('button', { name: '重新检测' })
-  fireEvent.click(detect)
-  const start = await screen.findByRole('button', { name: '开始发送' })
-  fireEvent.click(start)
+  await screen.findByRole('textbox', { name: '语音文字' })
 }
 
 describe('PersonalWechatSendDialog', () => {
   beforeEach(() => {
     getStatus.mockReset().mockResolvedValue(readyStatus)
     getRuntimeStatus.mockReset().mockResolvedValue(readyRuntime)
-    downloadRuntime.mockReset().mockResolvedValue({ success: true, status: readyRuntime })
     onRuntimeProgress.mockReset().mockReturnValue(vi.fn())
     rebind.mockReset().mockResolvedValue(readyStatus)
-    selectImage
-      .mockReset()
-      .mockResolvedValue({ canceled: false, path: '/Users/fixture/test.png', name: 'test.png' })
-    selectVoice
-      .mockReset()
-      .mockResolvedValue({ canceled: false, path: '/Users/fixture/test.silk', name: 'test.silk' })
-    sendMessage.mockReset().mockResolvedValue({ success: true, status: readyStatus })
+    sendGeneratedTtsVoice.mockReset().mockResolvedValue({
+      action: { status: 'sent' },
+      status: readyStatus
+    })
     getTextToSpeechSettings.mockReset().mockResolvedValue({
       success: true,
       settings: {
@@ -121,16 +107,7 @@ describe('PersonalWechatSendDialog', () => {
     })
     listTextToSpeechVoices.mockReset().mockResolvedValue({
       success: true,
-      items: [
-        {
-          id: 'fish-warm-female',
-          name: '暖阳女声',
-          description: '自然温和',
-          tags: ['女声'],
-          languages: ['中文'],
-          source: 'fish-audio'
-        }
-      ],
+      items: [{ id: 'fish-warm-female', name: '暖阳女声' }],
       total: 1,
       pageNumber: 1,
       pageSize: 24,
@@ -149,12 +126,9 @@ describe('PersonalWechatSendDialog', () => {
       value: {
         getPersonalWechatSenderStatus: getStatus,
         getPersonalWechatRuntimeStatus: getRuntimeStatus,
-        downloadPersonalWechatRuntime: downloadRuntime,
         onPersonalWechatRuntimeProgress: onRuntimeProgress,
         rebindPersonalWechatSender: rebind,
-        selectPersonalWechatImage: selectImage,
-        selectPersonalWechatVoice: selectVoice,
-        sendPersonalWechatMessage: sendMessage,
+        sendGeneratedTtsVoice,
         getTextToSpeechSettings,
         listTextToSpeechVoices,
         synthesizeTextToSpeech,
@@ -165,257 +139,39 @@ describe('PersonalWechatSendDialog', () => {
     })
   })
 
-  it('shows a user-facing four-step setup and keeps diagnostics collapsed', async () => {
-    getRuntimeStatus
-      .mockResolvedValueOnce({ ...readyRuntime, state: 'missing', progress: 0 })
-      .mockResolvedValue(readyRuntime)
-    getStatus.mockResolvedValue({
-      ...readyStatus,
-      state: 'stopped',
-      runtimeReady: false,
-      canSend: false,
-      canSendText: false,
-      canSendImage: false,
-      canSendVoice: false,
-      message: '尚未绑定当前微信'
-    })
-    renderDialog()
-    expect(await screen.findByText('准备 OneBot 运行时')).toBeInTheDocument()
-    expect(screen.getByRole('button', { name: '下载运行时' })).toBeEnabled()
-    expect(screen.getByText('绑定个人微信')).toBeInTheDocument()
-    expect(screen.getByText('验证消息能力')).toBeInTheDocument()
-    expect(screen.getByText('能力检测')).toBeInTheDocument()
-    expect(screen.getByText('图片和语音消息')).toBeInTheDocument()
-    expect(screen.getByRole('note')).toHaveTextContent(
-      '绑定微信可能导致当前微信异常闪退，这是正常现象。若微信退出，请重新启动微信后，再回到这里重新检测/绑定。'
-    )
-    fireEvent.click(screen.getByRole('button', { name: '查看支持的微信版本' }))
-    const versionsDialog = screen.getByRole('dialog', { name: '支持的微信版本' })
-    expect(versionsDialog).toBeInTheDocument()
-    expect(versionsDialog).toHaveTextContent('4.1.11.53')
-    expect(screen.queryByLabelText('消息列表')).not.toBeInTheDocument()
-    expect(screen.queryByText('TraceMemo 消息发送')).not.toBeInTheDocument()
-    expect(screen.queryByText('PID 4668')).not.toBeVisible()
-    fireEvent.click(screen.getByText('高级诊断'))
-    expect(screen.getByText('PID 4668')).toBeInTheDocument()
-  })
-
-  it('sends text through the existing message API and echoes it in the chat', async () => {
+  it('opens the TTS composer immediately when voice capability is ready', async () => {
     renderDialog()
     await startComposer()
-    await userEvent
-      .setup()
-      .type(screen.getByRole('textbox', { name: '消息内容' }), '你好 TraceMemo')
-    fireEvent.click(screen.getByRole('button', { name: '发送消息' }))
-    await waitFor(() =>
-      expect(sendMessage).toHaveBeenCalledWith({
-        type: 'text',
-        to: 'fixture-room@chatroom',
-        text: '你好 TraceMemo',
-        isGroup: true
-      })
-    )
-    expect(
-      screen.getByLabelText('消息列表').querySelector('.personal-wechat-message-bubble')
-    ).toHaveTextContent('你好 TraceMemo')
+    expect(screen.getByRole('dialog')).toHaveTextContent('文字转语音')
+    expect(screen.queryByText('验证消息能力')).not.toBeInTheDocument()
+    expect(screen.getByRole('button', { name: '生成语音' })).toBeDisabled()
   })
 
-  it('supports local image and voice selection', async () => {
-    renderDialog()
-    await startComposer()
-    fireEvent.click(screen.getByRole('radio', { name: '图片' }))
-    fireEvent.click(screen.getByRole('button', { name: '选择图片' }))
-    expect(await screen.findByText('test.png')).toBeInTheDocument()
-    fireEvent.click(screen.getByRole('button', { name: '发送消息' }))
-    await waitFor(() =>
-      expect(sendMessage).toHaveBeenCalledWith({
-        type: 'image',
-        to: 'fixture-room@chatroom',
-        filePath: '/Users/fixture/test.png',
-        isGroup: true
-      })
-    )
-
-    fireEvent.click(screen.getByRole('radio', { name: '语音' }))
-    fireEvent.click(screen.getByRole('radio', { name: '选择本地文件' }))
-    fireEvent.click(screen.getByRole('button', { name: '选择语音' }))
-    expect(await screen.findByText('test.silk')).toBeInTheDocument()
-    fireEvent.click(screen.getByRole('button', { name: '发送消息' }))
-    await waitFor(() =>
-      expect(sendMessage).toHaveBeenCalledWith({
-        type: 'voice',
-        to: 'fixture-room@chatroom',
-        filePath: '/Users/fixture/test.silk',
-        isGroup: true
-      })
-    )
-  })
-
-  it('sends the same generated voice through the comparison path', async () => {
-    renderDialog()
-    await startComposer()
-    fireEvent.click(screen.getByRole('radio', { name: '语音' }))
-    fireEvent.change(screen.getByRole('textbox', { name: '语音文字' }), {
-      target: { value: '入口2语音测试' }
-    })
-    fireEvent.click(screen.getByRole('button', { name: '生成语音' }))
-    await waitFor(() => expect(screen.getByText('语音已生成')).toBeInTheDocument())
-    fireEvent.click(screen.getByRole('button', { name: '空白语音？重新处理' }))
-    await waitFor(() =>
-      expect(sendMessage).toHaveBeenCalledWith({
-        type: 'voice',
-        to: 'fixture-room@chatroom',
-        filePath: '/tmp/generated.mp3',
-        isGroup: true,
-        voiceSendMode: 'legacy'
-      })
-    )
-  })
-
-  it('uses the existing runtime, binding and detection IPC actions', async () => {
-    getRuntimeStatus
-      .mockResolvedValueOnce({ ...readyRuntime, state: 'missing', progress: 0 })
-      .mockResolvedValue(readyRuntime)
-    getStatus
-      .mockResolvedValueOnce({
-        ...readyStatus,
-        state: 'stopped',
-        runtimeReady: false,
-        canSend: false,
-        canSendText: false,
-        canSendImage: false,
-        canSendVoice: false
-      })
-      .mockResolvedValue({
-        ...readyStatus,
-        state: 'stopped',
-        runtimeReady: true,
-        canSend: false,
-        canSendText: false,
-        canSendImage: false,
-        canSendVoice: false
-      })
-    renderDialog()
-    await screen.findByRole('button', { name: '下载运行时' })
-    fireEvent.click(screen.getByRole('button', { name: '下载运行时' }))
-    await waitFor(() => expect(downloadRuntime).toHaveBeenCalledOnce())
-    fireEvent.click(screen.getByRole('button', { name: '绑定微信' }))
-    await waitFor(() => expect(rebind).toHaveBeenCalledOnce())
-  })
-
-  it('shows a stable bound state after binding', async () => {
-    getRuntimeStatus.mockResolvedValue(readyRuntime)
-    getStatus
-      .mockResolvedValueOnce({
-        ...readyStatus,
-        state: 'stopped',
-        canSend: false,
-        canSendText: false,
-        canSendImage: false,
-        canSendVoice: false
-      })
-      .mockResolvedValue(readyStatus)
-    renderDialog()
-    await screen.findByRole('button', { name: '绑定微信' })
-    fireEvent.click(screen.getByRole('button', { name: '绑定微信' }))
-    expect(await screen.findByText('✓ 微信已绑定')).toBeInTheDocument()
-    expect(screen.queryByRole('button', { name: '绑定微信' })).not.toBeInTheDocument()
-  })
-
-  it('treats image and voice readiness as one media capability', async () => {
-    getStatus.mockResolvedValue({
-      ...readyStatus,
-      canSendImage: false,
-      canSendVoice: true
-    })
-    renderDialog()
-    expect(await screen.findByText('图片和语音消息')).toBeInTheDocument()
-    const bind = screen.queryByRole('button', { name: '绑定微信' })
-    if (bind) {
-      fireEvent.click(bind)
-      await screen.findByText('✓ 微信已绑定')
-    }
-    fireEvent.click(await screen.findByRole('button', { name: '重新检测' }))
-    expect(screen.getByText('微信消息发送已配置完成')).toBeInTheDocument()
-    expect(screen.getByRole('button', { name: '开始发送' })).toBeEnabled()
-    expect(screen.queryByText('图片消息')).not.toBeInTheDocument()
-    expect(screen.queryByText('语音消息')).not.toBeInTheDocument()
-  })
-
-  it('keeps re-detection available and explains when no new messages are found', async () => {
-    getRuntimeStatus.mockResolvedValue(readyRuntime)
-    getStatus.mockResolvedValue({
-      ...readyStatus,
-      canSend: false,
-      canSendText: false,
-      canSendImage: false,
-      canSendVoice: false,
-      message: '等待消息初始化'
-    })
-    renderDialog()
-    await screen.findByText('绑定个人微信')
-    const bind = screen.queryByRole('button', { name: '绑定微信' })
-    if (bind) {
-      fireEvent.click(bind)
-      await screen.findByText('✓ 微信已绑定')
-    }
-    const detect = await screen.findByRole('button', { name: '重新检测' })
-    expect(detect).toBeEnabled()
-    fireEvent.click(detect)
-    expect(
-      await screen.findByText(
-        '暂未检测到新的消息，请确认已在手机微信中发送文字和图片，然后再次检测。'
-      )
-    ).toBeInTheDocument()
-    expect(screen.getAllByText('未检测').length).toBe(2)
-  })
-
-  it('keeps the dialog and controls stable while sending', async () => {
+  it('generates, previews and sends a voice through the semantic TTS IPC', async () => {
     const user = userEvent.setup()
-    sendMessage.mockImplementation(() => new Promise(() => undefined))
     renderDialog()
     await startComposer()
-    await screen.findByRole('textbox', { name: '消息内容' })
-    await user.type(screen.getByRole('textbox', { name: '消息内容' }), '发送中')
-    await user.click(screen.getByRole('button', { name: '发送消息' }))
-    expect(screen.getByRole('button', { name: '正在发送…' })).toBeDisabled()
-    expect(screen.getByRole('radio', { name: '图片' })).toBeDisabled()
+    await user.type(screen.getByRole('textbox', { name: '语音文字' }), '你好 TraceMemo')
+    await user.click(screen.getByRole('button', { name: '生成语音' }))
+    expect(await screen.findByText('语音已生成')).toBeInTheDocument()
+    expect(screen.getByRole('button', { name: '试听' })).toBeEnabled()
+    await user.click(screen.getByRole('button', { name: '发送到微信' }))
+    await waitFor(() =>
+      expect(sendGeneratedTtsVoice).toHaveBeenCalledWith({
+        to: 'fixture-room@chatroom',
+        isGroup: true,
+        filePath: '/tmp/generated.mp3'
+      })
+    )
+    expect(screen.getByLabelText('消息列表')).toHaveTextContent('你好 TraceMemo')
   })
 
-  it('shows and copies the latest redacted voice diagnostic JSON', async () => {
-    getPersonalWechatVoiceDiagnostic.mockResolvedValue({
-      request_id: 'request-1',
-      voice_id: 'request-1',
-      phase: 'completed',
-      encoder_name: 'go-silk',
-      encoder_version: 'wechat_chatter-v0.0.18',
-      input_bytes: 35107,
-      normalized_input_bytes: 69804,
-      pcm_size: 69760,
-      sample_rate: 16000,
-      channels: 1,
-      input_duration_ms: 2180,
-      upload_result: '0',
-      upload_data_len: 4380,
-      silk_duration_ms: 2180,
-      send_result: '1'
-    })
-    renderDialog()
-    await startComposer()
-    fireEvent.click(screen.getByRole('button', { name: '语音发送诊断' }))
-    const diagnosticDialog = await screen.findByRole('dialog', { name: '语音发送诊断' })
-    expect(diagnosticDialog).toHaveTextContent('"encoder_name": "go-silk"')
-    expect(diagnosticDialog).not.toHaveTextContent('aesKey')
-    fireEvent.click(screen.getByRole('button', { name: '复制诊断 JSON' }))
-    await waitFor(() => expect(copyText).toHaveBeenCalledWith(expect.stringContaining('request-1')))
-    expect(screen.getByRole('button', { name: '已复制' })).toBeInTheDocument()
-  })
-
-  it('shows an empty state when no voice diagnostic exists', async () => {
-    renderDialog()
-    await startComposer()
-    fireEvent.click(screen.getByRole('button', { name: '语音发送诊断' }))
-    expect(await screen.findByText('暂无诊断信息')).toBeInTheDocument()
-    expect(screen.getByRole('button', { name: '复制诊断 JSON' })).toBeDisabled()
+  it('keeps the setup guide voice-only when voice capability is unavailable', async () => {
+    getStatus.mockResolvedValue({ ...readyStatus, canSend: false, canSendVoice: false })
+    renderDialog({ onOpenPersonalWechatSettings: vi.fn() })
+    expect(await screen.findByText('验证消息能力')).toBeInTheDocument()
+    expect(screen.getByText('语音消息')).toBeInTheDocument()
+    expect(screen.queryByText('文字消息')).not.toBeInTheDocument()
+    expect(screen.queryByText('图片和语音消息')).not.toBeInTheDocument()
   })
 })

tests/component/text-to-speech-page-windows.test.tsx

@@ -160,11 +160,11 @@ describe('PersonalWechatSendPage on Windows', () => {
     expect(screen.queryByText(/OneBot/i)).not.toBeInTheDocument()
     expect(screen.queryByRole('switch', { name: '保留 OneBot 进程' })).not.toBeInTheDocument()
     expect(screen.queryByRole('button', { name: '语音发送诊断' })).not.toBeInTheDocument()
-    expect(screen.getByRole('heading', { name: '个人微信发送' })).toBeVisible()
-    expect(screen.getByRole('region', { name: '发送消息' })).toBeVisible()
+    expect(screen.getByRole('heading', { name: '文字转语音' })).toBeVisible()
+    expect(screen.getByRole('region', { name: '文字转语音' })).toBeVisible()
   })
 
-  it('opens the Windows send dialog in text mode by default', async () => {
+  it('opens the Windows send dialog in TTS mode by default', async () => {
     getPersonalWechatSenderStatus.mockResolvedValue(windowsStatus)
 
     render(
@@ -180,11 +180,8 @@ describe('PersonalWechatSendPage on Windows', () => {
       />
     )
 
-    expect(await screen.findByRole('radio', { name: '文字' })).toHaveAttribute(
-      'data-state',
-      'checked'
-    )
-    expect(screen.getByRole('textbox', { name: '消息内容' })).toBeVisible()
+    expect(await screen.findByRole('textbox', { name: '语音文字' })).toBeVisible()
+    expect(screen.queryByRole('radio', { name: '文字' })).not.toBeInTheDocument()
   })
 
   it('keeps the Windows voice page focused on speech settings', async () => {