busya
814f2da139
Root cause: batch sizing underestimated CJK token density (1.5→1.0 chars/token) and ignored output budget as primary constraint, causing cascading finish_reason=length. Changes: - _token_budget.py: CJK_RATIO 1.5→1.0, OTHER_RATIO 2.2→1.8, safety factors 0.75/0.70 - _token_budget.py: new _compute_max_rows_by_output() — output budget is PRIMARY constraint - _batch_sizer.py: resolve_provider_config() with DB-level context_window/max_output_tokens - _batch_sizer.py: INPUT_SAFETY_FACTOR applied, max_rows_by_output used as row cap - _llm_http.py: log actual usage.prompt_tokens/.completion_tokens from provider - _llm_call.py: retry only missing rows after finish_reason=length (save partial result) - models/llm.py + schema: provider-level context_window / max_output_tokens (nullable) - services/llm_provider.py: get_provider_token_config() helper - Alembic migration: add columns to llm_providers - Svelte ProviderConfig: collapsible Advanced: Token Limits section - 12 new tests (token budget, batch sizer, provider config) - All 492 tests pass
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.