feat: AI assistant phase 2 - configurable prompt, action operations, FAQ matching, NVIDIA provider

- Admin-configurable AI prompt/quick questions from system_configs DB
- GET /api/v1/ai/quick-questions endpoint for fetching quick questions
- Local FAQ matching for instant responses (avoid AI calls for common Qs)
- AI action extraction: "add customer" intent detected, structured data returned
- Frontend action confirmation card with editable fields, calls customer API on confirm
- NVIDIA provider (stepfun-ai/step-3.5-flash) for faster chat vs deepseek-v4-flash
- Fixed httpx client timeout preventing backend hangs
- Added log_usage calls for auth events (register/login/guest/wechat)
- Admin tabs (users/stats/logs/config) fully functional with real backend
- AiAssistant component added to all tabbar pages

uni-app/src/pages/index/index.vue

@@ -253,6 +253,7 @@
       </view>
       <text class="footer-copyright">© 2026 北京宇之然科技中心. 保留所有权利.</text>
     </view>
+    <AiAssistant />
   </view>
 </template>
 
@@ -260,6 +261,7 @@
 import { ref, computed, onUnmounted } from 'vue'
 import { onShow } from '@dcloudio/uni-app'
 import { authApi, customerApi, analyticsApi, onboardingApi, notificationApi, followupApi, translateApi, BASE_URL } from '@/utils/api.js'
+import AiAssistant from '@/components/ai-assistant.vue'
 
 const showAnnouncement = ref(false)
 const currentAnnouncement = ref(0)