kiwi/app/styles/italian.yaml
pyr0ball 9371df1c95 feat: recipe engine Phase 3 — StyleAdapter, LLM levels 3-4, user settings
Task 13: StyleAdapter with 5 cuisine templates (Italian, Latin, East Asian,
Eastern European, Mediterranean). Each template includes weighted method_bias
(sums to 1.0), element-filtered aromatics/depth/structure helpers, and
seasoning/finishing-fat vectors. StyleTemplate is a fully immutable frozen
dataclass with tuple fields.

Task 14: LLMRecipeGenerator for Levels 3 and 4. Level 3 builds a structured
element-scaffold prompt; Level 4 generates a minimal wildcard prompt (<1500
chars). Allergy hard-exclusion wired through RecipeRequest.allergies into
both prompt builders and the generate() call path. Parsed LLM response
(title, ingredients, directions, notes) fully propagated to RecipeSuggestion.

Task 15: User settings key-value store. Migration 012 adds user_settings
table. Store.get_setting / set_setting with upsert. GET/PUT /settings/{key}
endpoints with Pydantic SettingBody, key allowlist, get_session dependency.
RecipeEngine reads cooking_equipment from settings when hard_day_mode=True.

55 tests passing.
2026-03-31 14:15:18 -07:00

13 lines
436 B
YAML

style_id: italian
name: Italian
aromatics: [basil, oregano, garlic, onion, fennel, rosemary, thyme, sage, marjoram]
depth_sources: [parmesan, pecorino, anchovies, canned tomato, porcini mushrooms]
brightness_sources: [lemon, white wine, tomato, red wine vinegar]
method_bias:
braise: 0.30
roast: 0.30
saute: 0.25
simmer: 0.15
structure_forms: [pasta, wrapped, layered, risotto]
seasoning_bias: sea salt
finishing_fat: olive oil