Phase 6 — Recipe / Bill / Workbench / CraftingProvider / Quality / Skills

Three gdscript-refactor agents in parallel; Opus did integration + caught
the wall-trap bug via MCP runtime test.

Data layer (Agent A):
- scenes/ai/recipe.gd: class Recipe (RefCounted) — id, ingredient_type,
  output_type, work_ticks, required_skill (Crafting/Cooking), skill_threshold
- scenes/ai/bill.gd: class Bill — Mode enum (FOREVER/COUNT/UNTIL_N),
  recipe ref, target_count, completed_count, paused, is_active() per-mode
  logic. UNTIL_N walks World.items each call (acceptable at MVP scale; cache
  if items grow large in Phase 16+)
- scenes/ai/recipe_catalog.gd: RecipeCatalog.plank() / .stone_block() — 2
  starter recipes; Phase 7+ expands toward the design.md ~22 catalog
- Item: added Quality enum (SHODDY/NORMAL/EXCELLENT/MASTERWORK/LEGENDARY),
  @export quality field, quality-coloured border in _draw (dull-grey / no /
  blue / gold / magenta), TYPE_PLANK + TYPE_STONE_BLOCK constants
- Pawn: added skills dict (5 skills × levels 0–10), get_skill/set_skill,
  skills round-trip in to_dict/from_dict
- strings.gd: item.plank, item.stone_block, quality.* (5 keys)

Workbench entity (Agent B, scenes/entities/workbench.{gd,tscn}, ~310 lines):
- class Workbench extends Node2D, bottom-anchored 3/4 perspective like Wall
- BuildJob interface (is_buildable / on_build_tick / _complete) — same
  pattern as Wall / Crate
- Bills queue (add_bill, find_active_bill matches by accepted_skill)
- Craft cycle hooks: begin_craft / tick_craft / on_craft_complete /
  on_craft_interrupted — JobRunner._tick_craft delegates to these
- Procedural _draw differentiates Carpenter (brown bench + vise) vs
  Smelter (dark stone + orange ember glow) via the @export label_text
  field — no subclass needed for Phase 6
- World autoload: workbenches registry + register_workbench/unregister_workbench

Crafting AI (Agent C):
- Toil.KIND_CRAFT + Toil.craft_at(workbench_path, bill_index) factory
- JobRunner._tick_craft: validates pawn-at-workbench, ingredient match;
  delegates progress to wb.tick_craft; on complete spawns output Item
  with QualityCalc.roll() applied; records bill completion
- crafting_provider.gd: priority=4 WorkProvider, 4-toil job
  (walk_to(ingredient) → pickup → walk_to(wb) → craft_at)
- quality.gd: QualityCalc.roll(skill) — additive formula
  skill × 0.04 + RNG(0, 0.6) with bucket thresholds matching
  architecture.md spec. Skill 0 caps at Excellent; Skill 10 reaches
  Legendary ~8% of the time

Opus integration:
- world.tscn: CraftingProvider node added
- world.gd: registered crafting_provider with World (priority order:
  construction=6 > chop=5 > mine=4 > crafting=4 > haul=3 > rest=0)
- Pawn spawn data extended with crafting skill (Bram=8, Cora=4, Edda=0)
  for visible quality variation in the demo
- _seed_phase5_demo_buildings extended: pre-built Carpenter at (46, 25)
  with plank bill (FOREVER) + Smelter at (48, 25) with stone_block bill
  (UNTIL_N=5)

The wall-trap bug (caught via MCP runtime — initial Phase 6 run hung):
- Pawns building walls stood ON the wall tile. When wall._complete fired
  set_cell_walkable(false), the pawn was stuck on a solid cell.
  AStarGrid2D returns no path when start cell is solid → all subsequent
  jobs failed pathfinding from the trapped position.
- Fix: ConstructionProvider checks site.blocks_pathing_when_complete()
  (new method on Wall, returns true; not implemented on Floor/Door/Crate/
  Workbench since they remain walkable). Walls route the pawn to an
  adjacent walkable cell via _find_adjacent_walkable. Floors/doors/etc.
  build on-tile as before.
- This bug existed since Phase 5 but only surfaced in Phase 6 because
  Phase 5 demos ended at construction-complete; Phase 6 needed pawns to
  walk away from finished walls toward the workbench.

Acceptance — MCP-verified end-to-end:
- 3 pawns boot with varied Crafting skills
- Construction priority wins first; all 48 build sites (23 walls + 1 door
  + 24 floors) complete. Pawns escape wall tiles safely (fix verified).
- Pawns transition to chop/mine, then crafting at the Carpenter workbench
- At tick 9215, 12 planks crafted with quality distribution matching
  expected spread per skill: 1 SHODDY + 6 NORMAL + 4 EXCELLENT + 1
  MASTERWORK. Quality-coloured borders visible on items.
- Smelter UNTIL_N=5 bill correctly idle (no stone consumed yet) because
  CraftingProvider prefers closer workbench-ingredient pairs and the
  carpenter+wood is closer to where pawns end up than smelter+stone

Phase 6 followups for later phases:
- on_craft_interrupted has no JobRunner hook — Phase 9 status interrupts
  will need a 'cancel callback' on toils or wb.on_craft_interrupted will
  leak current_bill/current_work_progress on canceled crafts
- Bill.from_dict reconstructs Recipe inline via Recipe.from_dict — Phase
  16 may need a recipe registry for save-format stability across catalog
  changes
- UNTIL_N's per-call World.items walk is O(items) — acceptable at MVP
  scale; profile if it becomes hot

Delegation report this phase:
- Agent A: Recipe + Bill + RecipeCatalog + Item.quality + Pawn.skills + i18n
- Agent B: Workbench (one class, label_text-driven differentiation, no
  Carpenter/Smelter subclass) + World registry
- Agent C: Toil.KIND_CRAFT + JobRunner._tick_craft + CraftingProvider +
  QualityCalc
- Opus: scene wiring + pawn-skill init + workbench demo seed + wall-trap
  fix (caught via MCP) + runtime verification

~75% of Phase 6 GDScript was subagent-authored.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

scenes/ai/crafting_provider.gd

@@ -0,0 +1,105 @@
+class_name CraftingProvider extends WorkProvider
+## WorkProvider for the Crafting work category. Slots into the 5-layer pawn AI
+## (Decision → WorkProvider → Job + JobRunner) as layer 2.
+##
+## Each call to find_best_for(pawn) scans World.workbenches for the best
+## (Workbench, Bill) pair the pawn qualifies for, then builds a 4-toil job:
+##   walk_to(ingredient.tile) → pickup → walk_to(wb.tile) → craft_at(wb, bill_index)
+##
+## Scoring: Manhattan distance pawn→ingredient + ingredient→workbench (lower wins).
+##
+## Phase 6 simplification: pawn must be empty-handed (one task at a time); ingredient
+## search is global (no per-bench radius restriction — Phase 17 polish item per
+## docs/architecture.md "Ingredient acquisition radius").
+##
+## Workbench and Pawn are intentionally duck-typed (no class_name reference) to match
+## WorkProvider convention and avoid init-order issues. Only Item.Quality and
+## QualityCalc are referenced by class_name (in job_runner.gd, not here).
+##
+## See docs/architecture.md "CraftingProvider" and docs/design.md "Bills".
+
+
+func _init() -> void:
+	category = &"crafting"
+	# Priority 4 — above haul (3), below chop (5).
+	# Phase 6 demo ordering; final 9-category matrix is authored in Phase 17.
+	priority = 4
+
+
+# ── WorkProvider override ─────────────────────────────────────────────────────
+
+## Returns a craft Job for `pawn`, or null if no valid work exists.
+## Pawn must expose: .carried_item, .tile (Vector2i), .get_skill(StringName) -> int.
+func find_best_for(pawn) -> Job:
+	# Skip if pawn is already carrying something — deposit first.
+	if pawn.get("carried_item") != null:
+		return null
+
+	var best_wb = null
+	var best_bill = null
+	var best_bill_index: int = -1
+	var best_src = null
+	var best_dist: int = 999999
+
+	for wb in World.workbenches:
+		# Duck-type guard: skip workbenches that aren't fully set up yet.
+		if not wb.get("_completed"):
+			continue
+
+		for i in wb.bills.size():
+			var b = wb.bills[i]
+			if not b.is_active():
+				continue
+
+			# Skill threshold check — pawn must meet the bill's minimum.
+			if pawn.get_skill(b.recipe.required_skill) < b.recipe.skill_threshold:
+				continue
+
+			# Confirm a qualifying ingredient exists on the floor.
+			var src = _find_ingredient_item(b.recipe.ingredient_type)
+			if src == null:
+				continue
+
+			# Score: total Manhattan travel distance pawn → ingredient → workbench.
+			var d: int = _manhattan(pawn.tile, src.tile) + _manhattan(src.tile, wb.tile)
+			if d < best_dist:
+				best_dist = d
+				best_wb = wb
+				best_bill = b
+				best_bill_index = i
+				best_src = src
+
+	if best_wb == null:
+		return null
+
+	# Re-resolve the source item in case multiple bills tied on the same item.
+	var src_item = _find_ingredient_item(best_bill.recipe.ingredient_type)
+	if src_item == null:
+		return null
+
+	var j := Job.new()
+	j.label = "Craft %s at %s" % [best_bill.recipe.label, best_wb.get("label_text") if best_wb.get("label_text") != null else "workbench"]
+	j.toils.append(Toil.walk_to(src_item.tile))
+	j.toils.append(Toil.pickup())
+	j.toils.append(Toil.walk_to(best_wb.tile))
+	j.toils.append(Toil.craft_at(best_wb.get_path(), best_bill_index))
+	return j
+
+
+# ── private helpers ───────────────────────────────────────────────────────────
+
+## Returns the first on-floor Item of matching type that is not being carried.
+## Phase 6 simplification: global search, first match wins (no nearest-first
+## at this layer — distance is factored into the outer loop scoring instead).
+func _find_ingredient_item(item_type: StringName):
+	for it in World.items:
+		if it.being_carried:
+			continue
+		if it.item_type == item_type:
+			return it
+	return null
+
+
+## Manhattan distance between two Vector2i tile coordinates.
+func _manhattan(a: Vector2i, b: Vector2i) -> int:
+	return abs(a.x - b.x) + abs(a.y - b.y)