docs: Sprint 15 round 2 — +18 recipes, library at 67 total, LLM 21/21

Sprint 15 round 2 (commit 97b84a7) added seed_recipes_round2.py
which seeded 18 more Spoonacular recipes today. Library went
49 -> 67 total. LLM test (Sprint 13 endpoint, week 2026-07-20):
  {picked_count: 0, filled_count: 21, failed_count: 0}
The library now covers all 21 slots of a week (was 19/21 + 2
failed in round 1).

This commit updates the 6 running docs:

- .agent/plan.md — Sprint 15 Round 2 section (S15R2.1-S15R2.4
  + Done when + Out of scope) added after the round 1 sections.
  50-query list documented by category.
- .agent/context.md — Round 2 decisions (D7-D10) added: list
  focuses on cuisines round 1 didn't cover, round 2 is a
  separate script, library at 67 with 21/21 LLM coverage.
- Review/sprint15-verification.md — Round 2 section appended
  with: 50-query list, 18-imported result, 12 no-hits, 1 402,
  updated DB state (37 Spoonacular + 30 manual = 67), LLM
  test result, round 3 follow-up ticket.
- Review/ui-nielsen-audit.md — Round 2 paragraph added to the
  Sprint 15 status block.
- fix-ui-audit.md — T8.6 added to the Sprint 15 section.
- Review/handoff-ui-audit.md — TL;DR and Sprint 15 section
  updated with round 2.
- docs/HANDOFF.md — Round 2 paragraph added to the Sprint 15
  section, Last-updated footer updated.

All 6 docs now reflect Sprint 15 round 2. Library has 67 unique
recipes — 1.25x rotation across 4 weeks of planning. Round 3
can add 30+ more by re-running scripts/seed_recipes.py on the
next day (its query list has round 1 cap-blocked American +
Mediterranean cuisines still to import).

Review/ui-nielsen-audit.md

@@ -153,6 +153,8 @@ The app looks polished on the surface (Tailwind palette, clean cards, working to
 > - **Verification log:** `Review/sprint15-verification.md` (full breakdown of 18 imported, free-tier math, LLM test, risk table).
 > - **No new runtime dependencies. No schema changes. No UI changes. Deploy is `git pull` + `docker compose up -d --build backend frontend` (backend picks up the main.py fix; the 18 new recipes are already in the DB).**
 >
+> **Sprint 15 Round 2 (2026-06-07):** +18 recipes, library at 67 total. `scripts/seed_recipes_round2.py` (NEW, ~120 lines) — 50-query list focused on cuisines the round 1 list didn't cover: Indian (8) + Thai (6) + Chinese regional (6) + Soups & stews (6) + Salads (6) + Sandwiches/wraps (5) + Breakfast (5) + German/European (4) + French (4). Same idempotent behavior (409 on duplicate). 18 imported; 12 queries returned no hits from Spoonacular's free-tier index; 30th query hit 402. LLM test (Sprint 13, week 2026-07-20, prompt "variety, mix of cuisines, family-friendly, no repeats"): `picked_count=0 / filled_count=21 / failed_count=0`. **Library now covers all 21 slots of a week.** Tracking: appended to `Review/sprint15-verification.md`.
+>
 >
 > **Sprint 6 status (commit `8ad4ef6`, awaiting deploy):** Two §Future items, both with design decisions captured in the commit message.
 > - **F3** Bulk 'add checked to pantry' on ShoppingList. Backend `POST /api/pantry/bulk` accepts `{items: HomePantryCreate[]}` and returns per-item status (`added` / `updated` / `skipped`) with totals. Per-item failure model: unknown ingredient → `skipped` with reason, not a 4xx. Frontend ShoppingList gains a primary `Add N to pantry` button next to the existing Reset button; toast reports `added X, updated Y, skipped Z`; only the items that actually landed are removed from the checked Set. **Scope decision:** ShoppingList only (the checked Set was the natural substrate; Pantry would need new multi-select UI).