Added disable_reasoning toggle that works via: 1. API parameter: reasoning_effort: 'none' (DeepSeek, Qwen) 2. System prompt instruction: 'Respond directly with ONLY the JSON. Do NOT include any reasoning, thinking, or chain-of-thought' (works for ALL models universally) Backend: model column, schema, preview+executor payload Frontend: checkbox in LLM settings, i18n en+ru
Superset Tools Frontend (SvelteKit)
This is the frontend for the Superset Tools application, built with SvelteKit in SPA mode.
Development
-
Install dependencies:
npm install -
Run development server:
npm run devThe frontend will be available at
http://localhost:5173. It is configured to proxy API requests tohttp://localhost:8000.
Production Build
-
Build the static SPA:
npm run buildThis generates a static SPA in the
build/directory. -
Serve with Backend: The Python backend is configured to serve the files from
frontend/build/. Ensure the backend is running:cd ../backend python src/app.py
Architecture
- Routing: File-based routing in
src/routes/. - Layouts: Shared UI in
src/routes/+layout.svelte. - Data Loading:
loadfunctions in+page.tsfor efficient data fetching. - API Client: Centralized API logic in
src/lib/api.js. - Styling: Tailwind CSS.