feat: meal tracking, dish recognition UX improvements, English AI prompts

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>
2026-03-17 14:29:36 +02:00
parent 2a95bcd53c
commit 87ef2097fc
16 changed files with 1269 additions and 350 deletions
--- a/backend/internal/adapters/ai/types.go
+++ b/backend/internal/adapters/ai/types.go
@@ -94,16 +94,20 @@ type ReceiptResult struct {
 	Unrecognized []UnrecognizedItem `json:"unrecognized"`
 }

-// DishResult is the result of dish recognition.
+// DishCandidate is a single dish recognition candidate with estimated nutrition.
+type DishCandidate struct {
+	DishName    string  `json:"dish_name"`
+	WeightGrams int     `json:"weight_grams"`
+	Calories    float64 `json:"calories"`
+	ProteinG    float64 `json:"protein_g"`
+	FatG        float64 `json:"fat_g"`
+	CarbsG      float64 `json:"carbs_g"`
+	Confidence  float64 `json:"confidence"`
+}
+
+// DishResult is the result of dish recognition with multiple ranked candidates.
 type DishResult struct {
-	DishName      string   `json:"dish_name"`
-	WeightGrams   int      `json:"weight_grams"`
-	Calories      float64  `json:"calories"`
-	ProteinG      float64  `json:"protein_g"`
-	FatG          float64  `json:"fat_g"`
-	CarbsG        float64  `json:"carbs_g"`
-	Confidence    float64  `json:"confidence"`
-	SimilarDishes []string `json:"similar_dishes"`
+	Candidates []DishCandidate `json:"candidates"`
 }

 // IngredientTranslation holds the localized name and aliases for one language.
--- a/backend/internal/adapters/openai/recognition.go
+++ b/backend/internal/adapters/openai/recognition.go
@@ -9,30 +9,43 @@ import (
 	"github.com/food-ai/backend/internal/adapters/ai"
 )

-// RecognizeReceipt uses the vision model to extract food items from a receipt photo.
-func (c *Client) RecognizeReceipt(ctx context.Context, imageBase64, mimeType string) (*ai.ReceiptResult, error) {
-	prompt := `Ты — OCR-система для чеков из продуктовых магазинов.
+// langNames maps ISO 639-1 codes to English language names used in AI prompts.
+var langNames = map[string]string{
+	"en": "English", "ru": "Russian", "es": "Spanish",
+	"de": "German", "fr": "French", "it": "Italian",
+	"pt": "Portuguese", "zh": "Chinese", "ja": "Japanese",
+	"ko": "Korean", "ar": "Arabic", "hi": "Hindi",
+}

-Проанализируй фото чека и извлеки список продуктов питания.
-Для каждого продукта определи:
- name: название на русском языке (убери артикулы, коды, лишние символы)
- quantity: количество (число)
- unit: единица (г, кг, мл, л, шт, уп)
+// RecognizeReceipt uses the vision model to extract food items from a receipt photo.
+func (c *Client) RecognizeReceipt(ctx context.Context, imageBase64, mimeType, lang string) (*ai.ReceiptResult, error) {
+	langName := langNames[lang]
+	if langName == "" {
+		langName = "English"
+	}
+	prompt := fmt.Sprintf(`You are an OCR system for grocery receipts.
+
+Analyse the receipt photo and extract a list of food products.
+For each product determine:
+- name: product name (remove article codes, extra symbols)
+- quantity: amount (number)
+- unit: unit (g, kg, ml, l, pcs, pack)
 - category: dairy | meat | produce | bakery | frozen | beverages | other
 - confidence: 0.0–1.0

-Позиции, которые не являются едой (бытовая химия, табак, алкоголь) — пропусти.
-Позиции с нечитаемым текстом — добавь в unrecognized.
+Skip items that are not food (household chemicals, tobacco, alcohol).
+Items with unreadable text — add to unrecognized.

-Верни ТОЛЬКО валидный JSON без markdown:
+Return all text fields (name) in %s.
+Return ONLY valid JSON without markdown:
 {
  "items": [
-    {"name": "Молоко 2.5%", "quantity": 1, "unit": "л", "category": "dairy", "confidence": 0.95}
+    {"name": "...", "quantity": 1, "unit": "l", "category": "dairy", "confidence": 0.95}
  ],
  "unrecognized": [
-    {"raw_text": "ТОВ АРТИК 1ШТ", "price": 89.0}
+    {"raw_text": "...", "price": 89.0}
  ]
-}`
+}`, langName)

 	text, err := c.generateVisionContent(ctx, prompt, imageBase64, mimeType)
 	if err != nil {
@@ -53,25 +66,30 @@ func (c *Client) RecognizeReceipt(ctx context.Context, imageBase64, mimeType str
 }

 // RecognizeProducts uses the vision model to identify food items in a photo (fridge, shelf, etc.).
-func (c *Client) RecognizeProducts(ctx context.Context, imageBase64, mimeType string) ([]ai.RecognizedItem, error) {
-	prompt := `Ты — система распознавания продуктов питания.
+func (c *Client) RecognizeProducts(ctx context.Context, imageBase64, mimeType, lang string) ([]ai.RecognizedItem, error) {
+	langName := langNames[lang]
+	if langName == "" {
+		langName = "English"
+	}
+	prompt := fmt.Sprintf(`You are a food product recognition system.

-Посмотри на фото и определи все видимые продукты питания.
-Для каждого продукта оцени:
- name: название на русском языке
- quantity: приблизительное количество (число)
- unit: единица (г, кг, мл, л, шт)
+Look at the photo and identify all visible food products.
+For each product estimate:
+- name: product name
+- quantity: approximate amount (number)
+- unit: unit (g, kg, ml, l, pcs)
 - category: dairy | meat | produce | bakery | frozen | beverages | other
 - confidence: 0.0–1.0

-Только продукты питания. Пустые упаковки и несъедобные предметы — пропусти.
+Food products only. Skip empty packaging and inedible objects.

-Верни ТОЛЬКО валидный JSON без markdown:
+Return all text fields (name) in %s.
+Return ONLY valid JSON without markdown:
 {
  "items": [
-    {"name": "Яйца", "quantity": 10, "unit": "шт", "category": "dairy", "confidence": 0.9}
+    {"name": "...", "quantity": 10, "unit": "pcs", "category": "dairy", "confidence": 0.9}
  ]
-}`
+}`, langName)

 	text, err := c.generateVisionContent(ctx, prompt, imageBase64, mimeType)
 	if err != nil {
@@ -91,28 +109,49 @@ func (c *Client) RecognizeProducts(ctx context.Context, imageBase64, mimeType st
 }

 // RecognizeDish uses the vision model to identify a dish and estimate its nutritional content.
-func (c *Client) RecognizeDish(ctx context.Context, imageBase64, mimeType string) (*ai.DishResult, error) {
-	prompt := `Ты — диетолог и кулинарный эксперт.
+// Returns 3–5 ranked candidates so the user can correct mis-identifications.
+func (c *Client) RecognizeDish(ctx context.Context, imageBase64, mimeType, lang string) (*ai.DishResult, error) {
+	langName := langNames[lang]
+	if langName == "" {
+		langName = "English"
+	}
+	prompt := fmt.Sprintf(`You are a dietitian and culinary expert.

-Посмотри на фото блюда и определи:
- dish_name: название блюда на русском языке
- weight_grams: приблизительный вес порции в граммах
- calories: калорийность порции (приблизительно)
- protein_g, fat_g, carbs_g: БЖУ на порцию
- confidence: 0.0–1.0
- similar_dishes: до 3 похожих блюд (для поиска рецептов)
+Look at the dish photo and suggest 3 to 5 possible dishes it could be.
+Even if the first option is obvious, add 2–4 alternative dishes with lower confidence.
+For each candidate specify:
+- dish_name: dish name
+- weight_grams: approximate portion weight in grams (estimate from photo)
+- calories: calories for this portion (kcal)
+- protein_g, fat_g, carbs_g: macros for this portion (grams)
+- confidence: certainty 0.0–1.0

-Верни ТОЛЬКО валидный JSON без markdown:
+Sort candidates by descending confidence. First — most likely.
+
+Return dish_name values in %s.
+Return ONLY valid JSON without markdown:
 {
-  "dish_name": "Паста Карбонара",
-  "weight_grams": 350,
-  "calories": 520,
-  "protein_g": 22,
-  "fat_g": 26,
-  "carbs_g": 48,
-  "confidence": 0.85,
-  "similar_dishes": ["Паста с беконом", "Спагетти"]
-}`
+  "candidates": [
+    {
+      "dish_name": "...",
+      "weight_grams": 350,
+      "calories": 520,
+      "protein_g": 22,
+      "fat_g": 26,
+      "carbs_g": 48,
+      "confidence": 0.88
+    },
+    {
+      "dish_name": "...",
+      "weight_grams": 350,
+      "calories": 540,
+      "protein_g": 20,
+      "fat_g": 28,
+      "carbs_g": 49,
+      "confidence": 0.65
+    }
+  ]
+}`, langName)

 	text, err := c.generateVisionContent(ctx, prompt, imageBase64, mimeType)
 	if err != nil {
@@ -120,11 +159,11 @@ func (c *Client) RecognizeDish(ctx context.Context, imageBase64, mimeType string
 	}

 	var result ai.DishResult
-	if err := parseJSON(text, &result); err != nil {
-		return nil, fmt.Errorf("parse dish result: %w", err)
+	if parseError := parseJSON(text, &result); parseError != nil {
+		return nil, fmt.Errorf("parse dish result: %w", parseError)
 	}
-	if result.SimilarDishes == nil {
-		result.SimilarDishes = []string{}
+	if result.Candidates == nil {
+		result.Candidates = []ai.DishCandidate{}
 	}
 	return &result, nil
 }