innercontext/frontend/src
Piotr Oleszczyk 31e030eaac feat: AI pre-fill for product form via Gemini API
Add POST /products/parse-text endpoint that accepts raw product text,
calls Gemini (google-genai) with a structured extraction prompt, and
returns a partial ProductParseResponse. Frontend gains a collapsible
"AI pre-fill" card at the top of ProductForm that merges the LLM
response into all form fields reactively.

- Backend: ProductParseRequest/Response schemas, system prompt with
  enum constraints, temperature=0.0 for deterministic extraction,
  effect_profile always returned in full
- Frontend: parseProductText() in api.ts; controlled $state bindings
  for all text/number/checkbox inputs; applyAiResult() merges response

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-27 23:04:24 +01:00
..
lib feat: AI pre-fill for product form via Gemini API 2026-02-27 23:04:24 +01:00
routes feat: add full/empty weight fields to Product and last_weighed_at to ProductInventory 2026-02-27 16:35:08 +01:00
app.css feat: add API client, types, layout, and all page routes 2026-02-26 20:45:54 +01:00
app.d.ts feat: add SvelteKit frontend scaffold with Tailwind CSS 2026-02-26 20:34:34 +01:00
app.html feat: add SvelteKit frontend scaffold with Tailwind CSS 2026-02-26 20:34:34 +01:00