- Make AI routing rules DB-driven (read from system_configs, removed from config.py)
- Add translation quota tracking to LLM translation (OpenAIProvider)
- Add Alibaba MT ECS RAM role support (STS token, no AccessKey needed)
- Fix admin sidebar link for AI模型配置 page
- Fix Quota.vue API path (quotas → translation-quotas)
- Fix login auto-redirect to dashboard
- Add provider dropdown selects to AI routing config UI
- Clean up stale ai_provider_* system_configs records
- Remove OpencodeGo, Spark providers (code + DB)
- Update deploy config: nginx port 8000, systemd cwd
- Fix usage/stats 500: use Date() not datetime.date() for SQL cast
- Fix customers 422: raise size limit to 1000
- Replace unreliable MCP client with direct Bing batch search for discovery
- Batch all search queries in one browser session (faster)
- Show real company names/URLs from Bing, not generic templates
- Smart filter for non-business results (news, blogs, forums)
- Fallback suggestions when search results are insufficient
- Frontend: clickable contact URLs, provider indicator, better layout
- WeChat Pay APIv3 integration (JSAPI + Native) with cert-based auth
- TranslationQuota model + admin management UI (配额 tab)
- Alibaba MT provider now checks quota before translation
- Fix: admin tabs scrollable on mobile, remove header-card
- Fix: profile/login navigation - logout stays on profile, login returns to profile
- Fix: login form now visible by default (no extra click to show)
- Fix: home page translate link uses navigateTo (was switchTab to non-tabBar page)
- Add .coverage and apiclient_key.pem to gitignore
- 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
TradeMate Dev