- Rewrite receipt OCR prompt: completes truncated names, preserves fat%
and flavour attributes, extracts weight/volume from line, infers
typical package sizes for solid goods with quantity_confidence field
- Add quantity_confidence to RecognizedItem, EnrichedItem, and
ProductJobResultItem; propagate through item enricher and worker
- Replace per-item create loop with single POST /user-products/batch call
from RecognitionConfirmScreen
- Rebuild RecognitionConfirmScreen: amber qty border for low
quantity_confidence, tappable product name → catalog picker,
sort items by confidence, full L10n (no hardcoded strings)
- Add timestamps (HH:mm / d MMM HH:mm) to recent scan chips
- Show close-app hint on ProductJobWatchScreen (queued + processing)
- Refresh recentProductJobsProvider on watch screen init so new job
appears without a manual pull-to-refresh
- App-level WidgetsBindingObserver refreshes product and dish job lists
on resume, fixing stale lists after background/foreground transitions
- Add 9 new L10n keys across all 12 locales
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Generate recipes in English (reverted prompt to English-only)
- Add TranslateRecipes to OpenAI client (translate.go) — sends compact
JSON payload of translatable fields, merges back into original recipes
- recommendation/handler.go: translate recipes in-memory before response
when lang != "en"; falls back to English on error
- dish/repository.go: Create() now returns (dishID, recipeID, err) so
callers can upsert dish_translations after saving
- menu/handler.go: saveRecipes returns savedRecipeEntry slice with dishID;
saveDishTranslations calls TranslateRecipes then UpsertTranslation for
each dish when the request locale is not English
- savedrecipe/repository.go: updated to ignore dishID from Create()
- init.go: wire openaiClient as RecipeTranslator and dishRepository as
DishTranslator for menu.NewHandler
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
buildRecipePrompt ignored req.Lang entirely and hardcoded two
English instructions in the prompt. Added targetLang resolution
using the existing langNames map (from recognition.go) and
threaded it into both "Generate N recipes in …" and "All text
fields … MUST be in …" instructions. The image_query field
remains English since it is passed to the Pexels photo API.
Fixes recommendations and menu recipes being returned in English
regardless of the Accept-Language header.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
RecognizeDish() and buildRecipePrompt() were generating text in the
user's language and storing it in base tables, violating the project
rule that base tables always hold English canonical text.
- RecognizeDish(): hardcode English for dish_name; enrichDishInBackground()
now correctly translates FROM English into all other languages
- buildRecipePrompt(): remove langName lookup, hardcode English for all
text fields; drop unused locale import
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Remove denormalized columns (name, calories, protein_g, fat_g, carbs_g)
from meal_diary. Name is now resolved via JOIN with dishes/dish_translations;
macros are computed as recipe.*_per_serving * portions at query time.
- Add dish.Repository.FindOrCreateRecipe: finds or creates a minimal recipe
stub seeded with AI-estimated macros
- recognition/handler: resolve recipe_id synchronously per candidate;
simplify enrichDishInBackground to translations-only
- diary/handler: accept dish_id OR name; always resolve recipe_id via
FindOrCreateRecipe before INSERT
- diary/entity: DishID is now non-nullable string; CreateRequest drops macros
- diary/repository: ListByDate and Create use JOIN to return computed macros
- ai/types: add RecipeID field to DishCandidate
- Update tests and wire_gen accordingly
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Backend:
- Translate all recognition prompts (receipt, products, dish) from Russian to English
- Add lang parameter to Recognizer interface and pass locale.FromContext in handlers
- DishResult type uses candidates array for multi-candidate responses
Client:
- Add meal tracking: diary provider, date selector, meal type model
- DishResult parser: backward-compatible with legacy flat format and new candidates format
- DishResultScreen: sticky bottom button, full-width portion/meal-type inputs,
КБЖУ disclaimer moved under nutrition card, add date field to diary POST body
- Recognition prompts now return dish/product names in user's preferred language
- Onboarding, profile, home screen visual updates
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add internal/adapters/ai/types.go with neutral shared types
(Recipe, DayPlan, RecognizedItem, IngredientClassification, etc.)
- Remove types from internal/adapters/openai/ — adapter now uses ai.*
- Define Recognizer interface in recognition package
- Define MenuGenerator interface in menu package
- Define RecipeGenerator interface in recommendation package
- Handler structs now hold interfaces, not *openai.Client
- Add wire.Bind entries for the three new interface bindings
To swap OpenAI for another provider: implement the three interfaces
using ai.* types and change the wire.Bind lines in cmd/server/wire.go.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
