fix: improve /model --fast description clarity and prevent accidental activation (#3077)

Replace vague "background tasks" with specific "prompt suggestions and speculative
execution" in the --fast flag description across all i18n locales, docs, and VS Code
schema. Update example model name from qwen3.5-flash to qwen3-coder-flash. Also fix
completion logic to require a non-empty partial arg before suggesting --fast, preventing
Tab+Enter from accidentally entering fast model mode.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

packages/cli/src/config/settingsSchema.ts

@@ -672,7 +672,7 @@ const SETTINGS_SCHEMA = {
     requiresRestart: false,
     default: '',
     description:
-      'Model for background tasks (suggestion generation, speculation). Leave empty to use the main model. A smaller/faster model (e.g., qwen3.5-flash) reduces latency and cost.',
+      'Model used for generating prompt suggestions and speculative execution. Leave empty to use the main model. A smaller/faster model (e.g., qwen3-coder-flash) reduces latency and cost.',
     showInDialog: true,
   },
 

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

@@ -990,8 +990,8 @@ export default {
   // Commands - Model
   // ============================================================================
   'Switch the model for this session': 'Modell für diese Sitzung wechseln',
-  'Set fast model for background tasks':
-    'Schnelles Modell für Hintergrundaufgaben festlegen',
+  'Set a lighter model for prompt suggestions and speculative execution':
+    'Leichteres Modell für Eingabevorschläge und spekulative Ausführung festlegen',
   'Content generator configuration not available.':
     'Inhaltsgenerator-Konfiguration nicht verfügbar.',
   'Authentication type not available.':

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

@@ -1152,7 +1152,8 @@ export default {
   // Commands - Model
   // ============================================================================
   'Switch the model for this session': 'Switch the model for this session',
-  'Set fast model for background tasks': 'Set fast model for background tasks',
+  'Set a lighter model for prompt suggestions and speculative execution':
+    'Set a lighter model for prompt suggestions and speculative execution',
   'Content generator configuration not available.':
     'Content generator configuration not available.',
   'Authentication type not available.': 'Authentication type not available.',

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

@@ -744,8 +744,8 @@ export default {
     'サマリーの生成に失敗 - LLMレスポンスからテキストコンテンツを受信できませんでした',
   // Model
   'Switch the model for this session': 'このセッションのモデルを切り替え',
-  'Set fast model for background tasks':
-    'バックグラウンドタスク用の高速モデルを設定',
+  'Set a lighter model for prompt suggestions and speculative execution':
+    'プロンプト提案と投機的実行用の軽量モデルを設定',
   'Content generator configuration not available.':
     'コンテンツジェネレーター設定が利用できません',
   'Authentication type not available.': '認証タイプが利用できません',

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

@@ -997,8 +997,8 @@ export default {
   // Commands - Model
   // ============================================================================
   'Switch the model for this session': 'Trocar o modelo para esta sessão',
-  'Set fast model for background tasks':
-    'Definir modelo rápido para tarefas em segundo plano',
+  'Set a lighter model for prompt suggestions and speculative execution':
+    'Definir modelo mais leve para sugestões de prompt e execução especulativa',
   'Content generator configuration not available.':
     'Configuração do gerador de conteúdo não disponível.',
   'Authentication type not available.': 'Tipo de autenticação não disponível.',

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

@@ -998,8 +998,8 @@ export default {
   // Команды - Модель
   // ============================================================================
   'Switch the model for this session': 'Переключение модели для этой сессии',
-  'Set fast model for background tasks':
-    'Установить быструю модель для фоновых задач',
+  'Set a lighter model for prompt suggestions and speculative execution':
+    'Установить облегчённую модель для подсказок и спекулятивного выполнения',
   'Content generator configuration not available.':
     'Конфигурация генератора содержимого недоступна.',
   'Authentication type not available.': 'Тип авторизации недоступен.',

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

@@ -1093,7 +1093,8 @@ export default {
   // Commands - Model
   // ============================================================================
   'Switch the model for this session': '切换此会话的模型',
-  'Set fast model for background tasks': '设置后台任务的快速模型',
+  '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',
   'Content generator configuration not available.': '内容生成器配置不可用',
   'Authentication type not available.': '认证类型不可用',
   'No models available for the current authentication type ({{authType}}).':

packages/cli/src/ui/commands/modelCommand.ts

@@ -21,11 +21,13 @@ export const modelCommand: SlashCommand = {
   },
   kind: CommandKind.BUILT_IN,
   completion: async (_context, partialArg) => {
-    if ('--fast'.startsWith(partialArg)) {
+    if (partialArg && '--fast'.startsWith(partialArg)) {
       return [
         {
           value: '--fast',
-          description: t('Set fast model for background tasks'),
+          description: t(
+            'Set a lighter model for prompt suggestions and speculative execution',
+          ),
         },
       ];
     }