plan: cook history + per-serving macros + allergens + picker profiles

Tier-1 data additions for the planner — turning the AI from a title-
matching guesser into a structured-data consumer. ENRICH_VERSION bumped
2→3 so existing meta gets refreshed with the new fields on next walk.

(A) Cook history. db.household_recipe_history aggregates recipe slug
    → {last_planned_date, count_30d, count_long} from cauldron_meal_
    plan_slots over a 180-day window. The plan generator's pool prompt
    now renders each recipe with rotation context: "last:8w-ago 0×/30d
    1×/180d". New planner rule: ROTATION — demote recipes shown 2+
    times in 30d unless they're picks; never repeat the same slug
    within the 7-day plan. New planner rule: VARIETY — don't fill 5
    of 7 slots with the same primary_protein or cuisine.

(B) Per-serving macros in enrichment. forge.enrich_recipe now asks
    Sonnet for calories, protein_g, carbs_g, fat_g per serving (rough
    USDA-grade estimates from ingredient list + yields). Renders into
    the pool prompt as "~480cal protein=32g carbs=45g fat=18g". Lets
    "high protein week" become a quantitative filter instead of a
    title-keyword match.

(C) Allergen booleans. New contains.* block in enrichment:
    {dairy, gluten, nuts, peanuts, eggs, shellfish, fish, soy, sesame,
    pork} — bool per allergen, conservatively defaulting to TRUE when
    uncertain since false negatives can hurt people. Pool prompt
    renders as "has:dairy,gluten,eggs". Foundation for upcoming
    "no dairy this week" exclusion-list UI on /plan.

(D) Picker profiles. db.household_picker_profiles unions current
    cauldron_meal_picks + historical meal_plan_slots.picker_subs over
    365 days, joins with cauldron_recipe_meta, aggregates per-user:
        {display_name, total_picks, cuisines, proteins, comfort_tiers,
         tags} — top-N counters each. Plan generator includes a new
    PICKER PROFILES block in the prompt:
        - cobb (sub=cobb@sulkta.com, 24 picks):
            cuisines=[asian:6, mexican:4, italian:3] ·
            proteins=[chicken:8, beef:5, fish:2] ·
            tags=[weeknight:11, high-protein:9, spicy:7]
    Sonnet uses these to bias AI-chosen slots toward each member's
    actual demonstrated taste — golden signal that's been sitting in
    the database the whole time. Picks still override profile bias.

Cost: cook history is a single SQL aggregate (free, sub-100ms). New
macro+allergen fields fold into the existing ~5s/recipe Sonnet call
with maybe 30 more output tokens. Picker profiles are 2-3 SQL queries
totaling sub-200ms even at scale. No new network round-trips.

Net effect once Cobb runs /enrich-recipes against ENRICH_VERSION 3:
plan generator has structured macros + allergen flags + cook-history
rotation context + per-user preferences to work with. The free-form
preference textarea ("high protein, no dairy") becomes a real query
against actual data, not just a Sonnet vibe-prompt.

cauldron/db.py

@@ -1547,7 +1547,12 @@ class DB:
 
     # --- recipe enrichment ------------------------------------------------
 
-    ENRICH_VERSION = 1
+    # Bump when the meta schema or prompt changes meaningfully so existing
+    # rows get re-enriched on next walk (or on user-clicks "force re-enrich").
+    # v2: added calories, protein_g, carbs_g, fat_g per-serving estimates
+    # v3: added contains.{dairy,gluten,nuts,peanuts,eggs,shellfish,fish,soy,
+    #     sesame,pork} allergen booleans
+    ENRICH_VERSION = 3
 
     def get_recipe_meta(self, household_id: int, recipe_slug: str) -> dict | None:
         with self.conn() as c, c.cursor() as cur:
@@ -1560,6 +1565,185 @@ class DB:
             row = cur.fetchone()
             return dict(row) if row else None
 
+    def household_picker_profiles(
+        self, household_id: int, *, lookback_days: int = 365
+    ) -> dict[str, dict]:
+        """For each member of the household, aggregate the recipes they've
+        explicitly picked (current cauldron_meal_picks + historical
+        meal_plan_slots.picker_subs across the lookback window). Cross
+        with cauldron_recipe_meta to derive their picking pattern:
+
+            {
+              "cobb@sulkta.com": {
+                "display_name": "cobb",
+                "total_picks": 24,
+                "cuisines": {"asian": 6, "mexican": 4, "italian": 3, ...},
+                "proteins": {"chicken": 8, "beef": 5, "fish": 2, ...},
+                "comfort_tiers": {"weeknight-easy": 15, "hearty-comfort": 4, ...},
+                "tags": {"high-protein": 9, "weeknight": 11, "spicy": 7, ...},
+              },
+              ...
+            }
+
+        Used by the plan generator to bias AI-chosen slots toward what
+        each member has historically wanted, even when nobody actively
+        pins for the upcoming week. Picks-attribution is golden signal —
+        the user explicitly said 'I want this.'"""
+        import json as _json
+        # Step 1: gather (sub, recipe_slug) pairs from both sources
+        attributions: list[tuple[str, str]] = []
+        with self.conn() as c, c.cursor() as cur:
+            # Current picks (high-signal, recent activity)
+            cur.execute(
+                """SELECT mp.authentik_sub AS sub, mp.recipe_slug
+                   FROM cauldron_meal_picks mp
+                   JOIN cauldron_household_members m
+                     ON m.authentik_sub = mp.authentik_sub
+                   WHERE m.household_id = %s""",
+                (household_id,),
+            )
+            for r in cur.fetchall():
+                attributions.append((r["sub"], r["recipe_slug"]))
+            # Historical picker_subs in plan slots (what actually got cooked
+            # because someone wanted it)
+            cur.execute(
+                """SELECT s.recipe_slug, s.picker_subs
+                   FROM cauldron_meal_plan_slots s
+                   JOIN cauldron_meal_plans p ON p.id = s.plan_id
+                   WHERE p.household_id = %s
+                     AND p.week_start >= CURDATE() - INTERVAL %s DAY
+                     AND s.picker_subs IS NOT NULL""",
+                (household_id, lookback_days),
+            )
+            for r in cur.fetchall():
+                blob = r["picker_subs"]
+                if isinstance(blob, str):
+                    try:
+                        blob = _json.loads(blob)
+                    except Exception:
+                        continue
+                if not isinstance(blob, list):
+                    continue
+                for sub in blob:
+                    if isinstance(sub, str) and sub:
+                        attributions.append((sub, r["recipe_slug"]))
+
+        if not attributions:
+            return {}
+
+        # Step 2: pull recipe meta for any slug in the attribution set
+        slugs = list({s for _, s in attributions})
+        meta_by_slug: dict[str, dict] = {}
+        if slugs:
+            placeholders = ",".join(["%s"] * len(slugs))
+            with self.conn() as c, c.cursor() as cur:
+                cur.execute(
+                    f"""SELECT recipe_slug, meta_json
+                        FROM cauldron_recipe_meta
+                        WHERE household_id=%s AND recipe_slug IN ({placeholders})""",
+                    (household_id, *slugs),
+                )
+                for r in cur.fetchall():
+                    blob = r["meta_json"]
+                    if isinstance(blob, str):
+                        try:
+                            meta_by_slug[r["recipe_slug"]] = _json.loads(blob)
+                        except Exception:
+                            pass
+                    elif isinstance(blob, dict):
+                        meta_by_slug[r["recipe_slug"]] = blob
+
+        # Step 3: pull display names for the subs we found
+        subs = list({s for s, _ in attributions})
+        display_by_sub: dict[str, str] = {}
+        if subs:
+            placeholders = ",".join(["%s"] * len(subs))
+            with self.conn() as c, c.cursor() as cur:
+                cur.execute(
+                    f"""SELECT authentik_sub, email, display_name
+                        FROM cauldron_users
+                        WHERE authentik_sub IN ({placeholders})""",
+                    tuple(subs),
+                )
+                for r in cur.fetchall():
+                    nm = r["display_name"] or (r["email"] or "").split("@")[0] or r["authentik_sub"]
+                    display_by_sub[r["authentik_sub"]] = nm
+
+        # Step 4: aggregate per user
+        from collections import Counter
+        per_user: dict[str, dict] = {}
+        for sub, slug in attributions:
+            meta = meta_by_slug.get(slug) or {}
+            prof = per_user.setdefault(sub, {
+                "display_name": display_by_sub.get(sub, sub),
+                "total_picks": 0,
+                "cuisines": Counter(),
+                "proteins": Counter(),
+                "comfort_tiers": Counter(),
+                "tags": Counter(),
+            })
+            prof["total_picks"] += 1
+            cuisine = meta.get("cuisine")
+            if cuisine and cuisine not in ("unknown", "other"):
+                prof["cuisines"][cuisine] += 1
+            prot = meta.get("primary_protein")
+            if prot and prot != "none":
+                prof["proteins"][prot] += 1
+            tier = meta.get("comfort_tier")
+            if tier:
+                prof["comfort_tiers"][tier] += 1
+            for t in (meta.get("tags") or [])[:8]:
+                if t:
+                    prof["tags"][t] += 1
+
+        # Step 5: convert Counters to plain top-N dicts for prompt-friendly output
+        out: dict[str, dict] = {}
+        for sub, prof in per_user.items():
+            out[sub] = {
+                "display_name": prof["display_name"],
+                "total_picks": prof["total_picks"],
+                "cuisines": dict(prof["cuisines"].most_common(5)),
+                "proteins": dict(prof["proteins"].most_common(5)),
+                "comfort_tiers": dict(prof["comfort_tiers"].most_common(3)),
+                "tags": dict(prof["tags"].most_common(8)),
+            }
+        return out
+
+    def household_recipe_history(
+        self, household_id: int, *, lookback_days: int = 180
+    ) -> dict[str, dict]:
+        """For each recipe slug that's appeared in this household's meal plans
+        within the lookback window, return:
+          {recipe_slug: {last_planned: date, count_30d: int, count_180d: int}}
+
+        Used by the plan generator to surface rotation context to Sonnet
+        ("don't suggest the same recipe 3 weeks running"). Joins on
+        meal_plan_slots → meal_plans → household."""
+        with self.conn() as c, c.cursor() as cur:
+            cur.execute(
+                """
+                SELECT
+                  s.recipe_slug,
+                  MAX(p.week_start) AS last_planned,
+                  SUM(CASE WHEN p.week_start >= CURDATE() - INTERVAL 30 DAY THEN 1 ELSE 0 END) AS count_30d,
+                  SUM(CASE WHEN p.week_start >= CURDATE() - INTERVAL %s DAY THEN 1 ELSE 0 END) AS count_long
+                FROM cauldron_meal_plan_slots s
+                JOIN cauldron_meal_plans p ON p.id = s.plan_id
+                WHERE p.household_id = %s
+                  AND p.week_start >= CURDATE() - INTERVAL %s DAY
+                GROUP BY s.recipe_slug
+                """,
+                (lookback_days, household_id, lookback_days),
+            )
+            out: dict[str, dict] = {}
+            for r in cur.fetchall():
+                out[r["recipe_slug"]] = {
+                    "last_planned": r["last_planned"],
+                    "count_30d": int(r["count_30d"] or 0),
+                    "count_long": int(r["count_long"] or 0),
+                }
+            return out
+
     def list_recipe_meta_for_household(self, household_id: int) -> list[dict]:
         """Used by the plan generator to splice meta into the recipe pool prompt."""
         with self.conn() as c, c.cursor() as cur:

cauldron/forge.py

@@ -77,6 +77,7 @@ class Forge:
         slots: int = 7,
         week_start: str,
         preference: str | None = None,
+        picker_profiles: dict | None = None,
         model: str | None = None,
     ) -> list[dict]:
         """Ask Sonnet for a {slots}-day plan. Returns a list of slot dicts
@@ -110,7 +111,7 @@ class Forge:
 
         prompt = self._build_plan_prompt(
             picks=picks, recipes=recipes, slots=slots, week_start=week_start,
-            preference=preference,
+            preference=preference, picker_profiles=picker_profiles,
         )
         result = self.run(prompt, model=model or "sonnet")
         parsed = _extract_plan_slots(result)
@@ -163,7 +164,8 @@ class Forge:
         return out
 
     @staticmethod
-    def _build_plan_prompt(*, picks, recipes, slots, week_start, preference=None) -> str:
+    def _build_plan_prompt(*, picks, recipes, slots, week_start, preference=None,
+                            picker_profiles=None) -> str:
         pool_lines = []
         for r in recipes:
             slug = r.get("slug") or ""
@@ -201,11 +203,42 @@ class Forge:
                 meta_tags = meta.get("tags") or []
                 if meta_tags:
                     extras.append("/".join(meta_tags[:5]))
-                if meta.get("summary"):
+                if meta.get("calories"):
-                    # Inline 1-line summary helps Sonnet match preferences
+                    extras.append(f"~{meta['calories']}cal")
-                    summary = str(meta["summary"])[:140]
+                if meta.get("protein_g"):
-                    pool_lines.append(f"- {slug}: {name}  [{' · '.join(extras)}]\n    {summary}")
+                    extras.append(f"protein={meta['protein_g']}g")
-                    continue
+                if meta.get("carbs_g"):
+                    extras.append(f"carbs={meta['carbs_g']}g")
+                if meta.get("fat_g"):
+                    extras.append(f"fat={meta['fat_g']}g")
+                # Allergen flags — short-circuit list of "what's in this"
+                contains = meta.get("contains") or {}
+                if isinstance(contains, dict):
+                    flags = [k for k, v in contains.items() if v]
+                    if flags:
+                        extras.append("has:" + ",".join(flags))
+
+            # Rotation history — let Sonnet avoid 3-weeks-in-a-row repeats
+            history = r.get("history") or {}
+            if history:
+                wa = history.get("weeks_ago")
+                c30 = history.get("count_30d") or 0
+                cl  = history.get("count_long") or 0
+                hist_bits = []
+                if wa is not None:
+                    hist_bits.append(f"last:{wa}w-ago" if wa > 0 else "last:this-week")
+                if c30:
+                    hist_bits.append(f"{c30}×/30d")
+                if cl:
+                    hist_bits.append(f"{cl}×/180d")
+                if hist_bits:
+                    extras.append(" ".join(hist_bits))
+
+            if meta and meta.get("summary"):
+                # Inline 1-line summary helps Sonnet match preferences
+                summary = str(meta["summary"])[:140]
+                pool_lines.append(f"- {slug}: {name}  [{' · '.join(extras)}]\n    {summary}")
+                continue
             extra_str = f"  [{' · '.join(extras)}]" if extras else ""
             pool_lines.append(f"- {slug}: {name}{extra_str}")
 
@@ -222,6 +255,50 @@ class Forge:
         picks_block = "\n".join(pick_lines) if pick_lines else "(none)"
         pool_block = "\n".join(pool_lines)
 
+        # Picker profiles: per-member historical picking patterns. Helps
+        # Sonnet bias AI-chosen slots toward each member's actual taste.
+        profile_block = ""
+        if picker_profiles:
+            lines: list[str] = []
+            for sub, prof in picker_profiles.items():
+                if not isinstance(prof, dict):
+                    continue
+                name = prof.get("display_name") or sub
+                total = prof.get("total_picks") or 0
+                bits = []
+                cuisines = prof.get("cuisines") or {}
+                if cuisines:
+                    bits.append("cuisines=[" + ", ".join(
+                        f"{k}:{v}" for k, v in list(cuisines.items())[:4]
+                    ) + "]")
+                proteins = prof.get("proteins") or {}
+                if proteins:
+                    bits.append("proteins=[" + ", ".join(
+                        f"{k}:{v}" for k, v in list(proteins.items())[:4]
+                    ) + "]")
+                tags = prof.get("tags") or {}
+                if tags:
+                    bits.append("tags=[" + ", ".join(
+                        f"{k}:{v}" for k, v in list(tags.items())[:5]
+                    ) + "]")
+                tier = prof.get("comfort_tiers") or {}
+                if tier:
+                    bits.append("tier=[" + ", ".join(
+                        f"{k}:{v}" for k, v in list(tier.items())[:2]
+                    ) + "]")
+                if bits:
+                    lines.append(f"  - {name} (sub={sub}, {total} picks): " + " · ".join(bits))
+            if lines:
+                profile_block = (
+                    "\nPICKER PROFILES — per-member historical picking patterns:\n"
+                    + "\n".join(lines) + "\n\n"
+                    "Use these to bias AI-chosen slots toward each member's "
+                    "preferences. e.g., if Cobb's profile shows cuisines=[asian:6, "
+                    "mexican:4] and proteins=[chicken:8], lean toward asian-chicken "
+                    "recipes for the AI-filled slots when other constraints permit. "
+                    "Picks still take precedence over profile bias.\n"
+                )
+
         pref_clean = (preference or "").strip()
         pref_block = ""
         if pref_clean:
@@ -244,6 +321,7 @@ class Forge:
             f"PICKS (recipes the family pre-selected — every pick MUST appear "
             f"if pool size >= {slots}; no repeats unless pool < {slots}):\n"
             f"{picks_block}\n"
+            f"{profile_block}"
             f"{pref_block}"
             "Output JSON ONLY, no prose: "
             '{"slots": [{"day": "monday", "recipe_slug": "...", '
@@ -251,9 +329,16 @@ class Forge:
             "Rules:\n"
             f"- Use exactly {slots} recipes\n"
             "- Distribute picks evenly across the week — don't bunch them\n"
+            "- ROTATION: prefer recipes with `last:NNw-ago` further in the past "
+            "or no history shown. If a recipe has been served 2+ times in 30d "
+            "(`2×/30d` or higher), DEMOTE it strongly unless it's a household "
+            "pick. Never repeat the same recipe slug within this 7-day plan.\n"
+            "- VARIETY: don't fill 5 of 7 slots with the same primary_protein or "
+            "the same cuisine. Mix it up across the week.\n"
             "- \"reason\" is a one-line user-facing rationale "
             "(e.g., \"balances heavy and light meals\", \"honors abby's pick\", "
-            "\"high-protein lean — pairs with the gym week\")\n"
+            "\"high-protein lean — pairs with the gym week\", "
+            "\"haven't had this in 8 weeks — fresh on the rotation\")\n"
             "- \"picker_subs\" is the array of authentik_sub strings of family "
             "members who picked this recipe (empty list if AI-chosen)\n"
             "- Day order: monday..sunday\n"
@@ -467,13 +552,42 @@ class Forge:
             '  "veg_forward": "<veg-forward|mixed|meat-forward>",\n'
             '  "comfort_tier": "<weeknight-easy|hearty-comfort|fancy-occasion|kid-friendly|date-night|crowd-pleaser>",\n'
             '  "season_fit": [<one or more of "spring","summer","fall","winter","year-round">],\n'
+            '  "calories":  <int per-serving estimate or null>,\n'
+            '  "protein_g": <int per-serving estimate or null>,\n'
+            '  "carbs_g":   <int per-serving estimate or null>,\n'
+            '  "fat_g":     <int per-serving estimate or null>,\n'
+            '  "contains": {\n'
+            '    "dairy":     <bool>,   // milk/cream/butter/cheese/yogurt/whey\n'
+            '    "gluten":    <bool>,   // wheat/barley/rye/regular pasta/bread/flour (not GF)\n'
+            '    "nuts":      <bool>,   // tree nuts (almonds, cashews, pecans, walnuts, ...)\n'
+            '    "peanuts":   <bool>,   // tracked separately from tree nuts\n'
+            '    "eggs":      <bool>,\n'
+            '    "shellfish": <bool>,   // shrimp, crab, lobster, scallops, ...\n'
+            '    "fish":      <bool>,\n'
+            '    "soy":       <bool>,   // soy sauce, tofu, tempeh, edamame\n'
+            '    "sesame":    <bool>,\n'
+            '    "pork":      <bool>    // for halal/kosher-ish filters\n'
+            '  },\n'
             '  "summary": "<one-line vibe — what KIND of meal is this>",\n'
             '  "best_for": "<short phrase: when is this the right pick>"\n'
             "}\n\n"
             "Rules:\n"
             "- Return ONLY the JSON object, no markdown fences, no prose.\n"
             "- Be concrete: 'high-protein' goes in tags ONLY if the recipe genuinely "
-            "qualifies (significant meat/eggs/dairy/protein source per serving).\n"
+            "qualifies (≥30g protein per serving is a useful threshold).\n"
+            "- Macros (calories, protein_g, carbs_g, fat_g): best-effort PER-SERVING "
+            "estimate from the ingredient list and yields. Use rough USDA averages — "
+            "we want signal not precision. If yields aren't clear, assume 4 servings. "
+            "If the recipe is a sauce/seasoning/drink with no useful per-serving notion, "
+            "set them to null.\n"
+            "- contains.* booleans: TRUE if the ingredient appears anywhere in the "
+            "recipe (even small amounts — these drive allergen filters, not "
+            "macro thresholds). dairy=true for butter, cream, cheese, milk, yogurt, "
+            "ghee, whey, casein. gluten=true for regular flour/bread/pasta/soy "
+            "sauce/beer/seitan; FALSE only when explicitly gluten-free or naturally "
+            "GF. soy=true for soy sauce, tofu, tempeh, edamame, miso. Conservative "
+            "default: when uncertain, set TRUE (false negatives can cause allergic "
+            "reactions; false positives just narrow choices).\n"
             "- estimated_minutes: best guess from prep + cook implied by steps. Dishes "
             "needing rise/marinade time count that time.\n"
             "- complexity: 'easy' = ≤30 min + ≤7 ingredients + simple technique; "
@@ -555,6 +669,24 @@ def _extract_recipe_meta(forge_result: dict) -> dict:
         except (TypeError, ValueError):
             return default
 
+    def _int_or_none(v):
+        if v is None:
+            return None
+        try:
+            n = int(v)
+            return n if n > 0 else None
+        except (TypeError, ValueError):
+            return None
+
+    contains_raw = inner.get("contains") or {}
+    if not isinstance(contains_raw, dict):
+        contains_raw = {}
+    contains = {
+        k: bool(contains_raw.get(k))
+        for k in ("dairy", "gluten", "nuts", "peanuts", "eggs",
+                  "shellfish", "fish", "soy", "sesame", "pork")
+    }
+
     return {
         "tags": _str_list(inner.get("tags")),
         "cuisine": _str(inner.get("cuisine"), "unknown"),
@@ -566,6 +698,11 @@ def _extract_recipe_meta(forge_result: dict) -> dict:
         "veg_forward": _str(inner.get("veg_forward"), "mixed"),
         "comfort_tier": _str(inner.get("comfort_tier"), "weeknight-easy"),
         "season_fit": _str_list(inner.get("season_fit")) or ["year-round"],
+        "calories": _int_or_none(inner.get("calories")),
+        "protein_g": _int_or_none(inner.get("protein_g")),
+        "carbs_g": _int_or_none(inner.get("carbs_g")),
+        "fat_g": _int_or_none(inner.get("fat_g")),
+        "contains": contains,
         "summary": _str_long(inner.get("summary")),
         "best_for": _str_long(inner.get("best_for")),
     }

cauldron/server.py

@@ -669,10 +669,11 @@ def create_app() -> Flask:
             db.set_plan_preference(plan["id"], preference)
             plan["preference_prompt"] = preference[:1000]
 
-        # Pull picks + recipe pool. The pool now splices in cauldron_recipe_meta
+        # Pull picks + recipe pool. The pool splices in:
-        # (Sonnet-generated per-recipe attributes — cuisine, complexity, macros,
+        #   1. cauldron_recipe_meta (Sonnet-generated per-recipe attributes)
-        # meal_type, primary_protein/carb, comfort_tier, summary) so the planner
+        #   2. cook history from cauldron_meal_plan_slots (rotation context)
-        # can match preferences to actual recipe characteristics, not just names.
+        # Both let the planner match preferences to actual characteristics
+        # AND avoid serving the same recipe 3 weeks running.
         picks = db.list_household_picks_with_pickers(hid)
         rows = db.list_indexed_recipes(hid, limit=2000, offset=0)
         meta_rows = db.list_recipe_meta_for_household(hid)
@@ -686,6 +687,7 @@ def create_app() -> Flask:
                     pass
             elif isinstance(blob, dict):
                 meta_by_slug[mr["recipe_slug"]] = blob
+        history_by_slug = db.household_recipe_history(hid, lookback_days=180)
         recipes = []
         for r in rows:
             tags = []
@@ -701,16 +703,42 @@ def create_app() -> Flask:
             m = meta_by_slug.get(r["slug"])
             if m:
                 entry["meta"] = m
+            h = history_by_slug.get(r["slug"])
+            if h:
+                # Compute weeks-ago for the prompt (relative human time
+                # is more useful to Sonnet than ISO dates)
+                last = h.get("last_planned")
+                weeks_ago: int | None = None
+                if last is not None:
+                    today = date.today()
+                    delta_days = (today - last).days if hasattr(last, "days") is False else 0
+                    try:
+                        delta_days = (today - last).days
+                    except Exception:
+                        delta_days = 0
+                    weeks_ago = max(0, delta_days // 7)
+                entry["history"] = {
+                    "weeks_ago": weeks_ago,
+                    "count_30d": h.get("count_30d") or 0,
+                    "count_long": h.get("count_long") or 0,
+                }
             recipes.append(entry)
 
         if not recipes:
             return jsonify({"error": "no_recipes_indexed"}), 409
 
+        # Per-user picking profiles — what each member has historically
+        # pinned, joined with recipe meta. Lets the planner bias AI-chosen
+        # slots toward each member's actual preferences, not just blanket
+        # the household's collective average.
+        picker_profiles = db.household_picker_profiles(hid, lookback_days=365)
+
         try:
             slots = forge.generate_plan(
                 picks=picks, recipes=recipes,
                 slots=7, week_start=this_monday.isoformat(),
                 preference=plan.get("preference_prompt"),
+                picker_profiles=picker_profiles,
             )
         except ForgeError as e:
             return jsonify({"error": "forge_failed", "detail": str(e)}), 502
@@ -781,11 +809,18 @@ def create_app() -> Flask:
         if not recipes:
             return jsonify({"error": "no_recipes_indexed"}), 409
 
+        # Per-user picking profiles — what each member has historically
+        # pinned, joined with recipe meta. Lets the planner bias AI-chosen
+        # slots toward each member's actual preferences, not just blanket
+        # the household's collective average.
+        picker_profiles = db.household_picker_profiles(hid, lookback_days=365)
+
         try:
             slots = forge.generate_plan(
                 picks=picks, recipes=recipes,
                 slots=7, week_start=this_monday.isoformat(),
                 preference=plan.get("preference_prompt"),
+                picker_profiles=picker_profiles,
             )
         except ForgeError as e:
             return jsonify({"error": "forge_failed", "detail": str(e)}), 502