Move product and skin AI helpers into modal flows, simplify product edit/inventory navigation, and improve responsive actions so core forms are faster to use. Localize remaining frontend labels/placeholders and strip deprecated Rollup output options to remove deploy-time build warnings.
Keep /products/suggest lean by exposing product UUIDs and fetching INCI, safety rules, actives, and usage notes on demand through Gemini function tools. Add conservative fallback behavior for tool roundtrip limits and expand helper tests to cover tool wiring and payload handlers.
Keep the /routines/suggest base context lean by sending only active names and fetching detailed safety, actives, usage notes, and INCI on demand. Add a conservative fallback when tool roundtrip limits are hit to preserve safe outputs instead of failing the request.
Enable on-demand INCI retrieval in /routines/suggest through Gemini function calling so detailed ingredient data is fetched only when needed. Persist and normalize tool_trace data in AI logs to make function-call behavior directly inspectable via /ai-logs endpoints.
Expose leave-on behavior, contraindications, safety alerts, and compact usage notes in AVAILABLE PRODUCTS so Gemini can make safer routine decisions with real-world product constraints.
Introduces `get_extraction_config` and `get_creative_config` to standardize Gemini API calls.
* Defines explicit config profiles with appropriate `temperature` and `thinking_level` for Gemini 3 Flash.
* Extraction tasks use minimal thinking and temp=0.0 to reduce latency and token usage.
* Creative tasks use low thinking, temp=0.4, and top_p=0.8 to balance naturalness and safety.
* Applies these helpers across products, routines, and skincare endpoints.
* Also updates default model to `gemini-3-flash-preview`.
- Install eslint, prettier and related plugins
- Add lint and format npm scripts
- Configure eslint.config.js with Svelte + TypeScript rules
- Configure .prettierrc with Svelte plugin
- Fix code to comply with lint rules:
- Use resolve() for navigation links
- Use SvelteMap for reactive maps
- Use writable instead of +
- Remove unused imports and variables
Note: ignoreGoto is set to true due to eslint-plugin-svelte#1327
- Add POST /api/products/suggest endpoint that analyzes skin condition
and inventory to suggest product types (e.g., 'Salicylic Acid 2% Masque')
- Add MCP tool get_shopping_suggestions() for MCP clients
- Add 'Suggest' button to Products page in frontend
- Add /products/suggest page with suggestion cards
- Include product type, key ingredients, target concerns, why_needed,
recommended_time, and frequency in suggestions
- Fix stock logic: sealed products now count as available inventory
- Add legend to clarify ✓ (in stock) vs ✗ (not in stock) markers
- Layout: mobile hamburger + drawer nav (backdrop button + sibling nav),
desktop sidebar hidden on small screens, p-4 md:p-8 main padding
- Products: card list view on mobile, flex-wrap filters
- Lab results: card list view on mobile
- ProductForm: responsive grids (grid-cols-1 sm:grid-cols-2), skin
profile checkboxes 2→3 cols, active ingredient row restructured
(name+✕ in flex row, percent/strength/irritation in 3-col grid),
section headers stack on mobile
- Skin snapshots: date+icons on one row, badges on separate row below
- Product [id] header: back link stacked above title, redundant badge removed
- Routines header: flex-col on mobile, sm:flex-row
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Remove _build_inventory_context; fold pao_months into DOSTĘPNE PRODUKTY entries
- Remove "Otwarte równolegle" duplicate section from prompt
- Rename OSTATNIE RUTYNY (7 dni) → OSTATNIE RUTYNY
- Add _build_day_context and SuggestRoutineRequest.leaving_home (optional bool)
- System prompt: replace unconditional PAO rule with conditional; add SPF factor
selection logic based on KONTEKST DNIA leaving_home value
- Frontend: leaving_home checkbox (AM only) + i18n keys pl/en
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Gemini API rejects int-valued enums (StrengthLevel) in response_schema,
raising a validation error before any request is sent. Fix by introducing
AIActiveIngredient (inherits ActiveIngredient, overrides strength_level and
irritation_potential as Optional[int]) and ProductParseLLMResponse used only
as the Gemini schema. The two-step validation converts ints back to StrengthLevel
via Pydantic coercion. Adds a test covering the numeric strength level path.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
gemini-flash-latest resolves to gemini-3-flash-preview which uses
thinking_level instead of the legacy thinking_budget (mixing both
returns HTTP 400). Use LOW to reduce thinking overhead while keeping
basic reasoning, replacing the now-incompatible thinking_budget=0.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
When Gemini stops generation early (e.g. due to safety filters or
thinking-model quirks), finish_reason != STOP but no exception is raised,
causing the caller to receive truncated JSON and a confusing 502 "invalid
JSON" error. Now:
- finish_reason is extracted from candidates[0] and stored in ai_call_logs
- any non-STOP finish_reason raises HTTP 502 with a clear message
- Alembic migration adds the finish_reason column to ai_call_logs
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
analyzeSkinPhotos was hardcoding PUBLIC_API_BASE, causing browser-side
requests to hit localhost:8000 directly instead of going through nginx.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
priorities was present in the model, API, and LLM prompt but never
surfaced in the frontend — add it to create/edit forms, read view,
AI photo pre-fill, and page.server.ts actions.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
