Captures brainstorm decisions for the meal-planner algorithm and the
minimum recipe-engine surface needed to feed it:
- 6 hard constraints (blocklist, never_suggest, recency N=4, calories
+/-20%, time <=45min, cost <=$30)
- Top-K=20 set enumeration with diversity penalty for protein/cuisine
- Ingredient<->grocery_item matching as a cacheable layer (rapidfuzz +
manual override) rather than per-run fuzzy work
- Thin phase 4: recipe CRUD, ingredient CRUD, resolve-ingredient
assist, manual match override, match job, 30-recipe seed
- Recipe ingestion source pros/cons (TheMealDB + Spoonacular + manual)
documented; decision deferred until phase 4 + phase 9 work end-to-end
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Updates ORIENTATION.md and HANDOFF.md to reflect actual state as of
commit 8e89f79: phases 1/2/3/7 complete (verified, not just claimed),
phases 4/5/6/8/9/10/11 not started. Documents the auth model, the
bootstrap login hatch, the SWIFTLY_BEARER_TOKEN expiration handling,
the Swiftly JSON API ingestion path that replaced Playwright, the
canonicalized API paths, and the verification commands to reproduce
the 31/31 pytest gate locally and in CI.
HANDOFF.md is intended for fresh agents and points at .agent/
phase-summaries for the per-phase write-ups. Surfaces 10 caveats and
traps the next agent will hit if they skim, and recommends Phase 9
(meal-planner generation algorithm) as the next move.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
adminandClaude Opus 4.7