2 commits

Author	SHA1	Message	Date
pyr0ball	76516abd62	feat: metric/imperial unit preference (#81) ... - Settings: add unit_system key (metric | imperial, default metric) - Recipe LLM prompts: inject unit instruction into L3 and L4 prompts so generated recipes use the user's preferred units throughout - Frontend: new utils/units.ts converter (mirrors Python units.py) - Inventory list: display quantities converted to preferred units - Settings view: metric/imperial toggle with save button - Settings store: load/save unit_system alongside cooking_equipment Closes #81	2026-04-15 23:04:29 -07:00
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