Add recipe suggestions, chat tab, and major workflow improvements

- Replace 7-day grid menu with browsable recipe suggestion cards (swap, remove, make this)
- Add Chat tab: conversational AI with full pantry/menu/grocery context
- Grocery list works without a menu (pantry-only mode)
- Individual grocery checkboxes auto-add items to pantry
- Swap modal with optional preference input
- User notes textarea on menu and grocery generation
- Clear button for menu and grocery list
- LLM notes/summary displayed after generation, persisted to DB
- Favicon linked in HTML
- Category dropdown styled for dark theme
- System prompt configurable via SYSTEM_PROMPT in .env
- Fix startup error (ollama_timeout default), DB migration for menu_plans.notes
- Simplify: batch N+1 queries, extract _current_monday(), merge chat sync fns,
  asyncio.get_running_loop(), fix currentGroceryId bug, cap chat history

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

1 files changed, 18 insertions, 4 deletions

diff --git a/CLAUDE.md b/CLAUDE.md
index 5da8209..b2f68b7 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -18,7 +18,7 @@ uvicorn main:app --reload --port 8080
 open http://localhost:8000/docs
 ```
 
-There are no tests. The SQLite database (`chef.db`) is auto-created on first startup via `Base.metadata.create_all()` in the lifespan handler — no migrations needed.
+There are no tests. The SQLite database (`chef.db`) is auto-created on first startup via `Base.metadata.create_all()` in the lifespan handler — no migrations needed for new installs. The lifespan handler also runs a one-time `ALTER TABLE menu_plans ADD COLUMN notes TEXT` migration for existing databases that predate that column.
 
 ## Architecture
 
@@ -27,17 +27,31 @@ Single-process FastAPI app. All state lives in SQLite. Ollama runs as a separate
 **Request flow for AI endpoints:**
 1. Router calls `pantry_service.build_pantry_context(db)` to snapshot the current pantry + recent meal history into a plain dict
 2. That dict is passed to an `ai_service` function which builds a prompt and calls Ollama synchronously via `run_in_executor` (keeps the async event loop unblocked during the 15–120s generation)
-3. Ollama always returns JSON (`format="json"` is set on every call); the response is `json.loads()`'d and returned directly — no intermediate parsing layer
+3. Structured AI endpoints (menu, grocery, swap) use `format="json"` and return parsed dicts. The chat endpoint uses plain text — no JSON parsing.
 4. The router saves AI output into the DB and returns both the DB record and the raw AI response to the frontend
 
 **Route registration order matters:** `app.include_router(...)` calls happen before `app.mount("/", StaticFiles(...))`. Reversing this breaks all API routes — the static catch-all intercepts them first.
 
 **JSON columns:** `recipes.ingredients`, `menu_plans.plan`, and `grocery_lists.items` are stored as JSON strings in `Text` columns. Always `json.dumps()` before saving and `json.loads()` before using.
 
-**`menu_plans.plan` structure:** `{"monday": {"breakfast": <recipe_id>, "lunch": <recipe_id>, "dinner": <recipe_id>}, ...}`. The `POST /api/menus/generate` response also includes `week_plan` with full recipe details (name, ingredients, instructions) — the frontend uses this for display without a second fetch. On page reload only the plan with IDs is available, so `GET /api/recipes` is needed to look up names.
+**`menu_plans.plan` structure:** A flat JSON array of recipe IDs — `[1, 4, 7, ...]`. The `POST /api/menus/generate` response also includes `recipes` with full recipe details (name, ingredients, instructions) — the frontend uses this for immediate display. On page reload only the plan IDs are available, so `GET /api/recipes` is needed to hydrate names and details.
 
 **`meal_ingredients.ingredient_name` is denormalized** — it stores a copy of the name string rather than a FK to `ingredients`. This preserves meal history when pantry items are deleted.
 
 **`grocery.py` exports two routers:** `router` (prefix `/api/grocery`) and `ai_router` (prefix `/api/ai`). Both are included in `main.py`.
 
-**Config** is loaded from `.env` via `pydantic-settings`. Key vars: `OLLAMA_HOST`, `MODEL_NAME`, `DATABASE_URL`. Change `MODEL_NAME` to switch Ollama models (e.g. `mistral`, `llama3.1`).
+**`_current_monday()` helper** is defined in both `routers/menus.py` and `routers/grocery.py`. It returns the ISO date of the current week's Monday and is used by every endpoint that scopes data to the current week.
+
+**`ai_service._chat_sync(messages, json_format=True)`** is the single sync Ollama call. Pass `json_format=False` for the chat endpoint which returns plain text. All async public functions call `run_in_executor` wrapping this to avoid blocking the event loop.
+
+**Config** is loaded from `.env` via `pydantic-settings`. Key vars:
+
+| Var | Default | Purpose |
+|-----|---------|---------|
+| `OLLAMA_HOST` | `http://localhost:11434` | Ollama server URL |
+| `MODEL_NAME` | — | Which Ollama model to use (e.g. `llama3.1`, `mistral`) |
+| `DATABASE_URL` | `sqlite:///./chef.db` | SQLAlchemy DB URL |
+| `OLLAMA_TIMEOUT` | `120` | Seconds before Ollama call times out |
+| `SYSTEM_PROMPT` | *(see config.py)* | System prompt prepended to all structured AI calls |
+
+Change `MODEL_NAME` to switch models. Edit `SYSTEM_PROMPT` to change the AI's persona and priorities for menu/grocery/swap generation (does not affect the chat tab's system prompt, which is built dynamically with kitchen context).