feat(runtime): early-game survival curriculum + stone/craft skills (Phase 3) (#15)

Phase 3 of plans/autonomous-survival-bot-prd.md. Gives the bot a
deterministic path from empty inventory through stone-tier tools and
basic storage, without an LLM call per tick.

New:
- runtime/curriculum.js: ordered milestone chooser
  (wood.16 → wood.planks-and-sticks → wood.tools → stone.32 →
   stone.tools → food.basic → storage.chest → shelter.torch). Each
  milestone exposes isDone(inventory, snapshot) and suggest() returning
  a { skillId } plan the scheduler can dispatch via runSkill. isDone
  uses "stage reached" escapes so progress is monotonic — crafting
  planks doesn't bounce the chooser back to "gather 16 logs".
- runtime/skills/gather-stone.js: gather.stone with pickaxe-required
  precondition, blacklist on failed paths, registry-aware matching
  (stone / cobblestone / deepslate / cobbled_deepslate / andesite /
  diorite / granite).
- runtime/skills/craft.js: factory + concrete skills for craft.planks,
  craft.sticks, craft.wooden-axe/-pickaxe/-sword, craft.stone-axe/
  -pickaxe/-sword, craft.furnace, craft.chest, craft.torch (torch
  requires coal or charcoal preflight).

Tests:
- runtime/curriculum.test.js: 14 tests covering chooser ordering,
  per-milestone skill suggestion, inventoryFull threshold, monotonic
  advancement across stage transitions.
- npm test now runs the full suite: 28/28 passing.

Wiring:
- runtime/bot.js: lastSnapshot.curriculum carries the next milestone
  + suggested skill on every tick; lastSnapshot.currentMilestone
  prefers the curriculum title over the planner.md line.
- tui/tui.tsx: milestone line shows the curriculum's suggested skill
  and an [inventory full] flag when isInventoryFull fires.

Reflex.js still calls actions.js directly; wiring the scheduler to
runSkill(plan.skillId, …) lands in Phase 4.

Co-authored-by: Yuriy Mayatnikov <mayatnikov@me.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

runtime/bot.js

@@ -38,6 +38,7 @@ import { startPlanner, isPlannerBusy, readNextMilestone, planExists } from "./pl
 import { computeState, STATES } from "./state.js";
 import { createNoProgressDetector } from "./no-progress.js";
 import { maybeStartViewer } from "./viewer.js";
+import { nextMilestone as nextCurriculumMilestone } from "./curriculum.js";
 
 fs.mkdirSync(stateDir, { recursive: true });
 const JOINED_FLAG = path.join(stateDir, "joined-before.flag");
@@ -582,7 +583,14 @@ function tick() {
 		lastSnapshot.activeSkill = reflexCtx.busy
 			? reflexCtx.currentActionLabel
 			: reflexCtx.lastReflex?.label ?? null;
-		lastSnapshot.currentMilestone = cachedMilestone;
+		// Two sources of "next milestone":
+		//   - planner.md (LLM-written, free-form, advisory)
+		//   - curriculum.js (deterministic early-game progression)
+		// The TUI prefers the curriculum's structured milestone (it has a
+		// suggested skill); falls back to the planner line for late-game.
+		const curriculum = nextCurriculumMilestone(lastSnapshot);
+		lastSnapshot.curriculum = curriculum;
+		lastSnapshot.currentMilestone = curriculum?.milestone?.title ?? cachedMilestone;
 		lastSnapshot.lastResult = lastResult;
 		lastSnapshot.noProgressReason = noProgressReason;
 		lastSnapshot.failuresByCode = failuresByCode();