feat(cli): add /model --vision for a fallback vision model

.github/workflows/qwen-code-pr-review.yml

@@ -144,9 +144,9 @@ jobs:
       github.event.pull_request.state == 'open' &&
       !github.event.pull_request.draft &&
       needs.authorize.outputs.should_review == 'true'
-    # Stays on hosted: the 30-minute environment wait timer would otherwise idle a self-hosted ECS slot for the whole wait (GitHub allocates the runner before evaluating the environment timer).
+    # Stays on hosted: the environment wait timer would otherwise idle a self-hosted ECS slot for the whole wait (GitHub allocates the runner before evaluating the environment timer).
     runs-on: 'ubuntu-latest'
-    # Configured in repo settings with a 30-minute wait timer.
+    # Wait timer is configured in repo settings (Settings → Environments → qwen-pr-review-delay), currently 10 minutes.
     environment:
       name: 'qwen-pr-review-delay'
       deployment: false

packages/cli/src/config/config.ts

@@ -2006,6 +2006,7 @@ export async function loadCliConfig(
       ? false
       : (settings.memory?.autoSkillConfirm ?? true),
     fastModel: settings.fastModel || undefined,
+    visionModel: settings.visionModel || undefined,
     // Use separated hooks if provided, otherwise fall back to merged hooks
     userHooks: bareMode
       ? undefined

packages/cli/src/config/settingsSchema.ts

@@ -1247,6 +1247,17 @@ const SETTINGS_SCHEMA = {
     showInDialog: true,
   },
 
+  visionModel: {
+    type: 'string',
+    label: 'Vision Model',
+    category: 'Model',
+    requiresRestart: false,
+    default: '',
+    description:
+      'Image-capable model used as the vision bridge: when a text-only main model receives an image, it is transcribed by this model first. Set with /model --vision. Leave empty to auto-pick a same-provider vision model.',
+    showInDialog: true,
+  },
+
   voiceModel: {
     type: 'string',
     label: 'Voice Model',

packages/cli/src/i18n/locales/en.js

@@ -1433,13 +1433,21 @@ export default {
     'Switch the model for this session (--fast for suggestion model, [model-id] to switch immediately).',
   'Switch the model for this session (--fast for suggestion model, --voice for voice transcription model, [model-id] to switch immediately).':
     'Switch the model for this session (--fast for suggestion model, --voice for voice transcription model, [model-id] to switch immediately).',
+  'Switch the model for this session (--fast for suggestion model, --voice for voice transcription model, --vision for the vision bridge model, [model-id] to switch immediately).':
+    'Switch the model for this session (--fast for suggestion model, --voice for voice transcription model, --vision for the vision bridge model, [model-id] to switch immediately).',
+  "⚠ '{{model}}' is not a known image-capable model; the vision bridge may fail on images.":
+    "⚠ '{{model}}' is not a known image-capable model; the vision bridge may fail on images.",
   'Set a lighter model for prompt suggestions and speculative execution':
     'Set a lighter model for prompt suggestions and speculative execution',
   'Toggle voice dictation input': 'Toggle voice dictation input',
   'Set the model for voice transcription':
     'Set the model for voice transcription',
+  'Set the image-capable model used to transcribe images for a text-only main model':
+    'Set the image-capable model used to transcribe images for a text-only main model',
   'Select Fast Model': 'Select Fast Model',
+  'Select Vision Model': 'Select Vision Model',
   'Select Voice Model': 'Select Voice Model',
+  'Vision Model': 'Vision Model',
   'Voice Model': 'Voice Model',
   'Selected voice model is unavailable.':
     'Selected voice model is unavailable.',
@@ -1686,6 +1694,8 @@ export default {
   'not set': 'not set',
   'Current voice model: {{voiceModel}}\nUse "/model --voice <model-id>" to set voice model.':
     'Current voice model: {{voiceModel}}\nUse "/model --voice <model-id>" to set voice model.',
+  'Current vision model: {{visionModel}}\nUse "/model --vision <model-id>" to set the vision bridge model.':
+    'Current vision model: {{visionModel}}\nUse "/model --vision <model-id>" to set the vision bridge model.',
   "Voice model '{{modelName}}' is ambiguous. Configure a unique model id before using /model --voice.":
     "Voice model '{{modelName}}' is ambiguous. Configure a unique model id before using /model --voice.",
   none: 'none',

packages/cli/src/i18n/locales/zh-TW.js

@@ -1230,12 +1230,20 @@ export default {
     '切換此會話的模型（--fast 可設置建議模型）',
   'Switch the model for this session (--fast for suggestion model, --voice for voice transcription model, [model-id] to switch immediately).':
     '切換此會話的模型（--fast 可設置建議模型，--voice 可設置語音轉寫模型，[model-id] 可立即切換）',
+  'Switch the model for this session (--fast for suggestion model, --voice for voice transcription model, --vision for the vision bridge model, [model-id] to switch immediately).':
+    '切換此會話的模型（--fast 可設置建議模型，--voice 可設置語音轉寫模型，--vision 可設置視覺橋接模型，[model-id] 可立即切換）',
+  "⚠ '{{model}}' is not a known image-capable model; the vision bridge may fail on images.":
+    "⚠ '{{model}}' 不是已知的圖像能力模型；視覺橋接處理圖片時可能會失敗。",
   'Set a lighter model for prompt suggestions and speculative execution':
     '設置用於輸入建議和推測執行的輕量模型',
   'Toggle voice dictation input': '切換語音聽寫輸入',
   'Set the model for voice transcription': '設定語音轉寫模型',
+  'Set the image-capable model used to transcribe images for a text-only main model':
+    '設定用於為純文字主模型轉寫圖像的圖像能力模型',
   'Select Fast Model': '選擇快速模型',
+  'Select Vision Model': '選擇視覺模型',
   'Select Voice Model': '選擇語音模型',
+  'Vision Model': '視覺模型',
   'Voice Model': '語音模型',
   'Selected voice model is unavailable.': '所選語音模型不可用。',
   "Voice model '{{model}}' is configured more than once. Remove duplicate model ids before selecting it for voice transcription.":
@@ -1439,6 +1447,8 @@ export default {
   'not set': '未設置',
   'Current voice model: {{voiceModel}}\nUse "/model --voice <model-id>" to set voice model.':
     '當前語音模型：{{voiceModel}}\n使用 "/model --voice <model-id>" 設置語音模型。',
+  'Current vision model: {{visionModel}}\nUse "/model --vision <model-id>" to set the vision bridge model.':
+    '當前視覺模型：{{visionModel}}\n使用 "/model --vision <model-id>" 設置視覺橋接模型。',
   "Voice model '{{modelName}}' is ambiguous. Configure a unique model id before using /model --voice.":
     "語音模型 '{{modelName}}' 不唯一。請先配置唯一的模型 ID，再使用 /model --voice。",
   none: '無',

packages/cli/src/i18n/locales/zh.js

@@ -1344,12 +1344,20 @@ export default {
     '切换此会话的模型（--fast 可设置建议模型）',
   'Switch the model for this session (--fast for suggestion model, --voice for voice transcription model, [model-id] to switch immediately).':
     '切换此会话的模型（--fast 可设置建议模型，--voice 可设置语音转写模型，[model-id] 可立即切换）',
+  'Switch the model for this session (--fast for suggestion model, --voice for voice transcription model, --vision for the vision bridge model, [model-id] to switch immediately).':
+    '切换此会话的模型（--fast 可设置建议模型，--voice 可设置语音转写模型，--vision 可设置视觉桥接模型，[model-id] 可立即切换）',
+  "⚠ '{{model}}' is not a known image-capable model; the vision bridge may fail on images.":
+    "⚠ '{{model}}' 不是已知的图像能力模型；视觉桥接处理图片时可能会失败。",
   'Set a lighter model for prompt suggestions and speculative execution':
     '设置用于输入建议和推测执行的轻量模型',
   'Toggle voice dictation input': '切换语音听写输入',
   'Set the model for voice transcription': '设置语音转写模型',
+  'Set the image-capable model used to transcribe images for a text-only main model':
+    '设置用于为纯文本主模型转写图像的图像能力模型',
   'Select Fast Model': '选择快速模型',
+  'Select Vision Model': '选择视觉模型',
   'Select Voice Model': '选择语音模型',
+  'Vision Model': '视觉模型',
   'Voice Model': '语音模型',
   'Selected voice model is unavailable.': '所选语音模型不可用。',
   "Voice model '{{model}}' is configured more than once. Remove duplicate model ids before selecting it for voice transcription.":
@@ -1581,6 +1589,8 @@ export default {
   'not set': '未设置',
   'Current voice model: {{voiceModel}}\nUse "/model --voice <model-id>" to set voice model.':
     '当前语音模型：{{voiceModel}}\n使用 "/model --voice <model-id>" 设置语音模型。',
+  'Current vision model: {{visionModel}}\nUse "/model --vision <model-id>" to set the vision bridge model.':
+    '当前视觉模型：{{visionModel}}\n使用 "/model --vision <model-id>" 设置视觉桥接模型。',
   "Voice model '{{modelName}}' is ambiguous. Configure a unique model id before using /model --voice.":
     "语音模型 '{{modelName}}' 不唯一。请先配置唯一的模型 ID，再使用 /model --voice。",
   none: '无',

packages/cli/src/ui/AppContainer.tsx

@@ -1096,6 +1096,7 @@ export const AppContainer = (props: AppContainerProps) => {
     isModelDialogOpen,
     isFastModelMode,
     isVoiceModelMode,
+    isVisionModelMode,
     openModelDialog,
     closeModelDialog,
   } = useModelCommand();
@@ -3627,6 +3628,7 @@ export const AppContainer = (props: AppContainerProps) => {
       isModelDialogOpen,
       isFastModelMode,
       isVoiceModelMode,
+      isVisionModelMode,
       isTrustDialogOpen,
       activeArenaDialog,
       isPermissionsDialogOpen,
@@ -3765,6 +3767,7 @@ export const AppContainer = (props: AppContainerProps) => {
       isModelDialogOpen,
       isFastModelMode,
       isVoiceModelMode,
+      isVisionModelMode,
       isTrustDialogOpen,
       activeArenaDialog,
       isPermissionsDialogOpen,