Relax protein to 1.7 g/kg; add rational-portion guard + weekly protein floor

- diet.protein_per_kg 2 -> 1.7 g/kg (evidence ceiling for trained/resistance-adapted adults)
  daily target 190-200 -> 165-175 g/day, ~80-90 g/meal
- weekly non-whey protein floor 1330 -> 1190 g (170 g/day x 7), still excl whey
- SKILL.md: RATIONAL PORTIONS hard rule (per-item max_per_meal caps, no single-ingredient
  overload, honest shortfall reporting); WEEKLY PROTEIN FLOOR (>=3 sources, none >50%)
- inventory.json: per-item max_per_meal caps + rational_portions defaults table
- scripts/verify_portions.py: regression probe for overload/cap violations
- README + references synced to 1.7 g/kg; .idea/.agentbridge gitignored

.gitignore

@@ -9,3 +9,7 @@ last-shop.json
 # Python caches
 __pycache__/
 scripts/__pycache__/
+
+# IDE artifacts
+.idea/
+.agentbridge/

README.md

@@ -1,7 +1,7 @@
 # Meal Suggestion — Kitchen Inventory + High-Protein Meals
 
 An automated, research-grounded meal system for a single user (jp): a recovering
-burns victim on a **high-protein diet (~190–200 g/day)** who is also losing fat,
+burns victim on a **high-protein diet (~165–175 g/day)** who is also losing fat,
 and who wants to **avoid buying red meat**. It does two things on a schedule:
 
 1. **Daily meal suggestions** — two meals (lunch + dinner) built only from what
@@ -66,7 +66,7 @@ meal-suggestion/
 │   ├── email-template.md          # HTML email scaffold (inline CSS, mobile-friendly)
 │   ├── food-health.md             # Healing + 46yo health + easy/tasty meal research
 │   ├── protein-sources.md         # Allowed proteins + example pairings
-│   ├── protein-targets.md         # Protein math (2 g/kg)
+│   ├── protein-targets.md         # Protein math (1.7 g/kg)
 │   ├── meal-history.md            # 7-day logger spec + reconcile-from-inventory logic
 │   └── eastbourne-shops.md        # Shop price table (Lidl preferred)
 ├── scripts/
@@ -86,7 +86,7 @@ is a synced mirror under `~/IdeaProjects/meal-suggestion/`. The two stay in step
 
 ## Core rules
 
-- **High-protein target:** ~190–200 g/day (≈2 g/kg at ~95–100 kg, for burns
+- **High-protein target:** ~165–175 g/day (≈1.7 g/kg at ~95–100 kg, for burns
   recovery + lean-mass preservation during ~15 kg fat loss). Aim ~90–100 g per
   meal and **state the per-meal and daily protein totals** in the email.
 - **Weight-loss framing:** mild calorie deficit via bulking with veg and going
@@ -202,7 +202,7 @@ creds from `~/.hermes/.env`). Both HTML (inline CSS, mobile-friendly, dark-on-li
 and a plain-text alternative are produced so the plan survives HTML-stripping
 clients.
 
-- **Daily:** header (date + `high-protein · ~190–200g/day · no red meat bought`),
+- **Daily:** header (date + `high-protein · ~165–175g/day · no red meat bought`),
   two meal cards (name, ingredients, 2–3 step method, protein total, short
   "health boost" note), footer (`Reply to tell me what you used and I'll update
   the inventory`).

SKILL.md

@@ -46,6 +46,35 @@ Schema:
 - Suggest **two meals** per day (e.g. lunch + dinner) using only items currently in the inventory.
 - **Maximize protein** per meal; lead with a protein source.
 - **EGG LIMIT (hard rule):** Eggs are capped at **4 per meal** and **only ONE of the two daily meals may contain eggs** — the other meal MUST be egg-free. Never suggest more than 4 eggs in a single meal, and never put eggs in both meals. If a meal needs more protein than 4 eggs supply, close the gap with other proteins (lentils, beans, halloumi, cheese, tinned fish, whey) or a whey shake — do NOT add a 5th+ egg. This overrides the "lead with eggs" preference below.
+- **MEAL VARIETY (rule):** the two daily meals (lunch + dinner) should use **disjoint
+  ingredient sets** — avoid repeating the same items across both meals. Build each meal
+  from a different subset of the inventory so the day isn't the same plate twice. Only
+  reuse an ingredient if stock genuinely forces it, and keep any reuse to the minimum.
+  This often means leading one meal with a non-red-meat protein (lentils/beans/eggs/whey/
+  cheese) and the other with a different protein (e.g. in-stock red meat being used up,
+  or eggs if the first meal was egg-free). Honour this alongside the EGG LIMIT and the
+  STRICT inventory rule.
+  Do NOT inflate a single ingredient's quantity to an unrealistic amount just to avoid
+  overlap (e.g. 2 cans of baked beans in one meal). If a fully-disjoint meal can't reach
+  the protein target, close the gap with a whey shake / extra eggs (third hit) rather than
+  unrealistic quantities.
+
+- **RATIONAL PORTIONS (hard rule):** every meal must be a *realistic, balanced, interesting*
+  plate — NOT overloaded with one ingredient. Each protein item has a `max_per_meal` cap in
+  `inventory.json` (expressed in that item's own unit, e.g. Eggs 4, Cumberland sausages 6,
+  Cheese 0.5 "small block" ≈ 60 g, Lamb mince 200 g, Lentils 150 g, Whey 50 g, Baked beans 1 can).
+  The daily job MUST NOT exceed a cap in any single meal. If an item has no `max_per_meal`,
+  fall back to `diet.rational_portions.default_caps` (keyword match) or `unit_fallback`
+  (count→6, g→200, can→1). `scripts/verify_portions.py` converts caps and logged amounts to
+  grams so a cap stored as "small block" is compared correctly against e.g. cheese logged in grams.
+  OVERLOAD test (what makes a meal "silly"): ONE protein at >=70% of its cap AND supplying
+  >=85% of that meal's protein — e.g. a bowl of 10 sausages. A balanced plate where the lead
+  protein is capped but other proteins + veg contribute is NOT overload (a normal 4-egg meal
+  passes). So spread across 3+ different proteins (plus veg, grain, dairy) so the plate is varied.
+  **If capped + balanced meals still can't reach ~165 g/day with current stock, DO NOT fake it**
+  — produce the best balanced meal you can, state the realistic total, and list the top 2–3
+  things to buy (eggs, whey, chicken, tuna) to close the gap. Never suggest "10 sausages" or any
+  single-ingredient overload. This rule overrides "maximize protein" — balance and realism beat a number.
 - **Avoid red meat for PURCHASES** (beef, lamb, pork, venison, bacon, gammon) — the
   weekly shopping list must NEVER suggest red meat to buy.
 - **If red meat is already in the inventory, it stays usable** in daily meal
@@ -55,10 +84,11 @@ Schema:
   tempeh, lentils, beans, chickpeas, Greek yogurt, cottage cheese, quark, skim milk,
   whey, tinned tuna/salmon, edamame, halloumi.
   (Eggs are subject to the EGG LIMIT hard rule above: max 4 per meal, only one meal/day may include them.)
-- **Protein target:** ~**190–200 g/day** (user ~95–100 kg × 2 g/kg — burns recovery +
+- **Protein target:** ~**165–175 g/day** (user ~95–100 kg × 1.7 g/kg — evidence ceiling for
-  preserving lean mass while losing ~15 kg fat). Aim each meal at **~90–100 g protein**
+  trained/resistance-adapted adults; burns recovery + preserving lean mass while losing ~15 kg
+  fat). Aim each meal at **~80–90 g protein**
   and **STATE the per-meal and daily protein totals** in the email. If 2 meals can't
-  reach ~190 g with current stock, say so and suggest a third hit (whey shake, extra
+  reach ~165 g with current stock, say so and suggest a third hit (whey shake, extra
   eggs, Greek yogurt) to close the gap.
 - **Weight-loss framing:** keep meals calorie-moderate — bulk with veg, go easy on oven
   chips, white bread, and oil; lead with lean protein. Fat loss comes from a mild calorie
@@ -110,6 +140,15 @@ To keep shops and meals varied over time, each week's list is themed around a
 **randomly chosen world cuisine**. This is driven by
 `scripts/pick_cuisine.py` (same skill dir).
 
+**Theme start rule (IMPORTANT):** the cuisine is picked by the **Monday weekly job**
+and it themes that week's **shop basket**, but it applies to **MEALS from TUESDAY
+onward**. Monday's daily meal suggestion is cooked **UNTHEMED** from whatever is
+currently in stock (the shop items aren't in inventory yet). From Tuesday the daily
+meal job cooks **on-theme**. If `cuisine-rotation.json` has no `current` cuisine set
+(e.g. cleared between weeks, or the rest of a week with no active theme), meals are
+unthemed. This keeps a fresh shop's new ingredients aligned with themed meals without
+forcing a theme onto the day the shop is only proposed.
+
 - Run `python3 scripts/pick_cuisine.py` at the **start of the weekly job**. It
   picks a cuisine seeded by the week's Monday, so it is **stable within a week**
   (re-runs/retries never flip the cuisine mid-week) but **varies week to week**
@@ -125,12 +164,23 @@ To keep shops and meals varied over time, each week's list is themed around a
   items that are just flavour (spices, sauces, lime, herbs) are the optional
   "interest" buys — keep them low-price and behind protein + veg + staples.
 - Persist the active cuisine so the **daily meal job can read `cuisine-rotation.json`
-  and on-theme meals from the same week's buys** (e.g. build a Korean bowl, a
+  and cook on-theme meals from the same week's buys (TUESDAY–SUNDAY only; Monday is
-  Mexican bowl, etc., from stock). The daily job should still respect the STRICT
+  unthemed)** (e.g. build a Korean bowl, a Mexican bowl, etc., from stock). The daily
-  inventory rule — only cook with what's actually in inventory.json.
+  job should still respect the STRICT inventory rule — only cook with what's actually
+  in inventory.json.
 - The rotation file keeps a short history; no manual tracking needed.
 
 ## Weekly shopping list (Mondays)
+- **WEEKLY PROTEIN FLOOR (hard rule):** the non-whey protein bought in the Monday shop MUST be
+  enough to cover the week. Required = 170 g/day × 7 = **1190 g** of **non-whey** protein
+  (whey is excluded — it is a third-hit top-up, not a meal base). Estimate the non-whey protein
+  ALREADY in `inventory.json` (sum each protein/cheese/dairy item's qty × its per-g from
+  `references/protein-sources.md`). The shop's bought non-whey protein must total at least
+  `MAX(0, 1190 − in_stock)` g. **SPREAD it across ≥3 distinct protein sources** — no single
+  source may exceed ~50% of the bought total (never "20 eggs only", never one tub). If £30 can't
+  reach the floor, get as close as budget allows and STATE the shortfall + what to buy next.
+  Record `bought_protein_g_excl_whey` and `stock_protein_g_excl_whey` on `last-shop.json` and
+  show both in the email so weekly coverage is visible.
 - Budget **£30** total. Use realistic UK supermarket prices (Tesco/Asda/Sainsbury's).
 - **Pick this week's cuisine first** (see "Weekly cuisine rotation" above) and
   theme the basket around it — varied ingredients keep meals interesting.
@@ -300,6 +350,20 @@ Note: this is entirely on-demand — the weekly job itself never writes inventor
   EGG LIMIT prose rule above, (b) `diet.egg_rules` in inventory.json, and (c) running
   `scripts/verify_eggs.py` after any history/inventory change or before a resend.
   Always run that probe before sending a regenerated day.
+- **Don't auto-resend after a stock update.** When the user reports actual consumption or you
+  correct `inventory.json` mid-day, update the inventory and STOP — do NOT volunteer a fresh
+  meal email. The next scheduled 09:00 cron picks up the new stock automatically. Only
+  regenerate + resend when the user explicitly asks (usually because they flagged a
+  meal-QUALITY issue, e.g. unrealistic portions — "2 cans of baked beans is silly, be
+  realistic"). They said plainly "I will wait for the cron job to run." Distinguish: a
+  consumption report = update stock, no email; a meal-quality complaint = regenerate fresh.
+- **Portion probe scope + threshold (avoid false positives).** `verify_portions.py` defaults to
+  TODAY only — run it that way before a send. Its OVERLOAD flag requires BOTH >=70% of one
+  protein's cap AND >=85% of that meal's protein; a capped lead protein with real supporting
+  proteins (e.g. a normal 4-egg meal) must NOT trip it. If you widen the threshold later you'll
+  start flagging legitimate balanced plates — keep the >=85% dominance condition. `--all` is an
+  audit of history, not a send gate; historical over-cap rows (old halloumi quantities) are
+  already-sent and only fixed on explicit request.
 
 ## Automation
 Two cron jobs (created via the `cronjob` tool), both loading this skill:
@@ -316,6 +380,16 @@ Delivery is `local` because the email itself is the deliverable; check
 - `scripts/verify_eggs.py` — regression probe for the EGG LIMIT. Run after any change to
   `meal-history.json`, `inventory.json`, or the daily job, and before sending a
   regenerated day's email. Exits non-zero on violation. See "Pitfalls".
+- `scripts/verify_portions.py` — regression probe for RATIONAL PORTIONS. By DEFAULT checks
+  only TODAY's entries in `meal-history.json` (the meals the daily job just wrote, before
+  sending). It flags (a) any protein used above its `max_per_meal` (or fallback) cap, and
+  (b) single-ingredient OVERLOAD — one protein at >=70% of its cap that ALSO supplies >=85%
+  of the meal's protein (a "pile of one thing", e.g. 10 sausages). Caps are stored in each
+  item's own unit (e.g. Cheese 0.5 "small block"); the probe converts to grams so it can
+  compare against logged grams (e.g. 40 g cheese). Run it alongside `verify_eggs.py` BEFORE
+  sending a regenerated day. Pass `--all` to audit the full 7-day window (this WILL flag
+  ALREADY-SENT historical rows like old 100–200 g halloumi — audit only, NOT a send gate;
+  only fix history on explicit user request). Exits non-zero on violation.
 
 ## References
 - `references/protein-sources.md` — allowed proteins + example pairings.

references/food-health.md

@@ -6,7 +6,7 @@ AARP / BodyLogic (men 40+); BBC Good Food & Berry Street (budget meals).
 General guidance, NOT medical advice — defer to the user's clinical/dietitian team.
 
 ## Healing & high-protein (burns recovery)
-- Protein at EVERY meal + snack. Target ~2 g/kg (user 95–100 kg → ~190–200 g/day).
+- Protein at EVERY meal + snack. Target ~1.7 g/kg (user 95–100 kg → ~165–175 g/day).
 - Best proteins (no red meat): eggs, poultry (chicken/turkey, skin off), fish &
   shellfish, dairy (milk/yogurt/cottage cheese/quark), tofu, tempeh, edamame,
   lentils, beans, peas, nuts, peanut butter, whey.

references/protein-targets.md

@@ -4,12 +4,13 @@ User profile this skill was tuned for: recovering burns victim, healing well,
 ~95–100 kg, wants to lose ~15 kg fat while **preserving lean mass**.
 
 ## Target math
-- Burns recovery + lean-mass preservation during a deficit: **2 g protein per kg
+- Burns recovery + lean-mass preservation during a deficit: **1.7 g protein per kg
-  bodyweight per day**.
+  bodyweight per day** (evidence ceiling for trained/resistance-adapted adults;
-- At 95–100 kg → **~190–200 g/day**.
+  relaxed from 2 g/kg per user preference).
-- Split across 2 main meals: aim **~90–100 g per meal**; any remainder comes from a
+- At 95–100 kg → **~165–175 g/day**.
+- Split across 2 main meals: aim **~80–90 g per meal**; any remainder comes from a
   third hit.
-- **Recompute whenever the user reports a new weight:** target = weight_kg × 2.
+- **Recompute whenever the user reports a new weight:** target = weight_kg × 1.7.
   Keep `diet.bodyweight_kg`, `diet.protein_per_kg`, and
   `diet.protein_target_g_per_day` in inventory.json in sync with that.
 

scripts/verify_portions.py

@@ -0,0 +1,134 @@
+#!/usr/bin/env python3
+"""
+Regression guard for RATIONAL PORTIONS.
+
+Checks TODAY's meals in meal-history.json (override with --all for the 7-day window)
+for:
+  1. CAP EXCEEDED — a protein item used in a single meal above its inventory
+     `max_per_meal`, or above the fallback cap when no explicit cap exists.
+  2. OVERLOAD — a single protein at >=70% of its cap that ALSO supplies >=85% of the
+     meal's protein (a "pile of one ingredient", e.g. 10 sausages). A balanced plate
+     where the lead protein is capped but other proteins/veg contribute is NOT flagged.
+
+Units are normalised to grams so items logged in different units (cheese in g vs
+inventory's "small block") compare correctly.
+
+Exits non-zero (prints violations) if any rule is broken.
+"""
+import json, sys, os, argparse
+from datetime import datetime, timedelta
+
+SKILL_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+HISTORY = os.path.join(SKILL_DIR, "meal-history.json")
+INV = os.path.join(SKILL_DIR, "inventory.json")
+
+# protein (g) per unit, for the dominance estimate
+PROTEIN_G = {
+    "egg": 6, "sausage": 11, "mince": 0.18, "lentil": 0.24, "tofu": 0.12,
+    "tempeh": 0.19, "bean": 9, "whey": 0.8, "cheese": 0.25, "halloumi": 0.21,
+    "tuna": 25, "salmon": 25, "mackerel": 20, "chicken": 0.31, "turkey": 0.29,
+    "prawn": 0.24, "yogurt": 0.10, "yoghurt": 0.10, "fish": 25,
+}
+
+# grams per inventory unit, for converting a stored cap to grams
+GRAMS_PER_UNIT = {
+    "g": 1, "ml": 1, "kg": 1000, "count": 1, "can": 1,
+    "small block": 120, "block": 120, "serving": 1, "portion": 1,
+    "pack": 1, "jar": 1, "tub": 1, "bulb": 1, "bottle": 1, "loaf": 1,
+}
+
+PROTEIN_CATS = {"protein", "dairy"}
+
+
+def cap_grams(name, unit, inv):
+    it = next((i for i in inv["items"] if i["name"].lower() == name.lower()), None)
+    if it and "max_per_meal" in it:
+        gpu = GRAMS_PER_UNIT.get(it.get("unit", unit), 1)
+        return it["max_per_meal"] * gpu
+    rp = inv.get("diet", {}).get("rational_portions", {})
+    defaults = rp.get("default_caps", {})
+    for kw, cap in defaults.items():
+        if kw in name.lower():
+            gpu = GRAMS_PER_UNIT.get(rp.get("unit_fallback_unit", unit), 1)
+            return cap * gpu
+    fb = rp.get("unit_fallback", {}).get(unit, 6)
+    return fb * GRAMS_PER_UNIT.get(unit, 1)
+
+
+def est_protein_g(name, qty, unit):
+    per = PROTEIN_G.get(name.lower())
+    if per is None:
+        for kw, v in PROTEIN_G.items():
+            if kw in name.lower():
+                per = v
+                break
+    if per is None:
+        return 0.0
+    gpu = GRAMS_PER_UNIT.get(unit, 1)
+    base = qty * gpu  # grams of food
+    # per is g protein per g of food for g/ml units; per-unit for count/can
+    if unit in ("g", "ml", "kg"):
+        return per * base
+    return per * qty
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--all", action="store_true", help="check full 7-day window")
+    args = ap.parse_args()
+    inv = json.load(open(INV))
+    hist = json.load(open(HISTORY))
+    entries = hist if isinstance(hist, list) else hist.get("entries", [])
+    today = datetime.now().strftime("%Y-%m-%d")
+    cutoff = datetime.now() - timedelta(days=7)
+    violations = []
+    for e in entries:
+        try:
+            d = datetime.strptime(e["date"], "%Y-%m-%d")
+        except Exception:
+            continue
+        if args.all:
+            if d < cutoff:
+                continue
+        else:
+            if e["date"] != today:
+                continue
+        meal_items = e.get("items", [])
+        # 1) cap check
+        for it in meal_items:
+            cap = cap_grams(it["name"], it.get("unit", "count"), inv)
+            used = est_protein_g(it["name"], it["qty"], it.get("unit", "count"))
+            # compare the RAW quantity against the cap's raw quantity (both in same unit)
+            cap_raw = cap / GRAMS_PER_UNIT.get(it.get("unit", "count"), 1) if it.get("unit") in ("g", "ml", "kg") else cap
+            # simpler: compare grams of food used vs grams of cap
+            food_g = it["qty"] * GRAMS_PER_UNIT.get(it.get("unit", "count"), 1)
+            cap_food_g = cap
+            if food_g > cap_food_g + 1e-6:
+                violations.append(
+                    f"CAP EXCEEDED {e['date']} {e['meal']} '{e['name']}': "
+                    f"{it['name']} {it['qty']} {it.get('unit','')} exceeds cap "
+                    f"~{cap_food_g:.0f} g ({it.get('unit','')})")
+        # 2) overload check (single protein >=70% cap AND >=85% of meal protein)
+        prot = [(it, cap_grams(it["name"], it.get("unit", "count"), inv),
+                 est_protein_g(it["name"], it["qty"], it.get("unit", "count")))
+                for it in meal_items]
+        total = sum(p for _, _, p in prot) or 1
+        for it, cap, pg in prot:
+            food_g = it["qty"] * GRAMS_PER_UNIT.get(it.get("unit", "count"), 1)
+            if cap and food_g > 0.7 * cap and pg > 0.85 * total:
+                violations.append(
+                    f"OVERLOAD {e['date']} {e['meal']} '{e['name']}': "
+                    f"{it['name']} {it['qty']} is >=70% of its cap and supplies "
+                    f"{pg:.0f}/{total:.0f} g ({pg/total*100:.0f}%) of meal protein "
+                    f"— not a balanced plate")
+    if violations:
+        print("FAIL: rational-portion violations:")
+        for v in violations:
+            print("  -", v)
+        sys.exit(1)
+    scope = "all logged meals (7d)" if args.all else f"today ({today})"
+    print(f"PASS: portions rational — no overload ({scope}).")
+
+
+if __name__ == "__main__":
+    main()