- ModelConfig 新增 max_reference_videos / max_reference_audios (配合既有 max_reference_images);admin 读写接口透传 - custom 模型表单去掉「参考模式」下拉,改为参考图/参考视频/ 参考音频三个数量输入;合计张数走 totalRefLimit 校验 - vivid 上游 /v1/uploads 按文件魔数自动选 kind(image/video/ audio)与 mime;openai 协议上游遇视频/音频参考自动跳过换号 - videoCaps 让 custom 模型的分类上限在画图台/文档徽标生效 - reference_mode 请求级 override 放行 "media" Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
ai-gateway frontend
Vue 3 + Vite admin console for the ai-gateway backend. This replaces the old
single-file static/admin.html.
Develop
npm install
npm run dev # http://localhost:5173
The dev server proxies /admin, /health, /generated, /v1 to the backend.
Start the backend separately:
# from repo root
python app.py # http://0.0.0.0:6060
If the backend runs elsewhere, set VITE_BACKEND before npm run dev:
VITE_BACKEND=http://192.168.1.10:6060 npm run dev
Build
npm run build # outputs static assets to ./dist
npm run preview # serve the production build locally
When hosting dist/ on a different origin than the API, set VITE_API_BASE
(e.g. VITE_API_BASE=http://api-host:6060) at build time, and add that frontend
origin to the backend's CORS_ORIGINS env var.