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/sprint15-verification.md

@@ -120,3 +120,44 @@ Sprint 15 does not require a migration or new runtime deps. The 18 newly-importe
 ## Open question for follow-up
 
 **Q1 — Re-run `scripts/seed_recipes.py` on a later day to seed the remaining 32 recipes?** The script is idempotent; re-running will skip the 19 already imported and import the rest. The user can do this from the host with one command.
+
+---
+
+## Sprint 15 — Round 2 (2026-06-07): +18 recipes, library at 67 total
+
+**User direction (2026-06-07):** "please add more meals to the potential list" / "Pull in more recipes so we have a larger sample to generate from."
+
+### What changed
+
+- **`scripts/seed_recipes_round2.py` (NEW, ~120 lines)** — second-round seed script. Same idempotent behavior as round 1 (409 on duplicate). Different query list focused on cuisines and meal types 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) = 50 queries.
+- **Result:** 18 recipes imported (queries 1, 2, 3, 5, 6, 7, 8, 10, 17, 19, 21, 22, 23, 24, 25, 27, 28, 29). 12 queries returned no hits (Spoonacular's free-tier index doesn't include all titles, e.g. "chana masala", "thai basil chicken", "dan dan noodles"). Query 30 ("wedge salad") hit 402 mid-import, ending the run.
+
+### Updated DB state
+
+```
+spoonacular | total
+------------+-------
+         37 |    67
+```
+
+- 19 from round 1 + 18 from round 2 = 37 Spoonacular recipes.
+- 30 manual recipes from before.
+- **67 unique recipes total.** 4 weeks × 21 meals = 84 picks needed; 67 unique = 1.25× coverage (some rotation, but no full uniqueness across 4 weeks — some meals will repeat).
+
+### LLM test (Sprint 13 endpoint, week 2026-07-20, prompt: "variety, mix of cuisines, family-friendly, no repeats")
+
+```json
+{"plan_id": "04fe4860-...", "picked_count": 0, "filled_count": 21, "failed_count": 0, "reasoning": null}
+```
+
+- **21/21 slots filled, 0 failed.** Round 1 returned 19/21 + 2 failed; round 2's expanded library now covers all 21 slots. The LLM still returned 0 picks (Sprint 13 tolerance took over).
+- The library fill uses the Sprint 6+ `fillEmptySlots` pattern: prefers un-used recipes, falls back to any. With 67 unique recipes, a 21-slot week has plenty of un-used options.
+
+### Round 2 follow-up
+
+- **Q2 — Run a third round?** Quota resets every 24h. The next day, the user can re-run `scripts/seed_recipes.py` (round 1, will pick up where round 2 left off) or design a round 3 with even more variety. The 67 → 80-100 trajectory is realistic.
+- **Q3 — Lower `_DAILY_LIMIT=140` to 45** to match the real 50-pt free-tier cap. Doesn't block; surface in the next sprint that touches the recipe_search.py file.
+
+### Cost (corrected, both rounds)
+
+Free tier is 50 pts/day. Each query = 1.10 (search) + 1 (information) = 2.10 pts. 50 queries = 105 pts ≈ 2 days. Round 1 imported 18, round 2 imported 18 = 36 new recipes from ~60 queries. Round 3 could add 30 more.