feat(v0.3.1): storyline — canonical Minecraft survival quest

The bot has been stuck in a loop for two days:
  acquire-food (fail: no nearby food) → explore.far → pillar-up (fail) → repeat

Diagnosis: manifesto + LLM advisor both correctly identify "you need
food" but neither expresses *what concretely to do next*. Manifesto is
a priority ladder (need-detection), not a narrative arc.

This commit adds the missing narrative layer — an ordered list of
operational steps that mirror the vanilla Minecraft survival path:

  1. orient_self      — Понять где я
  2. first_wood       — Собрать 8 поленьев
  3. crafting_basics  — Сделать верстак и палки
  4. first_tools      — Деревянные орудия
  5. first_food       — Найти первую еду
  6. shelter_minimal  — Простой шелтер с кроватью
  7. stone_tier       — Каменные орудия
  8. food_security    — Запас еды на 16+
  9. iron_age         — Железо и печь
  10. settle_base     — Постоянная база
  11. village_grow    — Развивать деревню (ongoing)

Each step has:
  - completed(snapshot) → bool — detects achievement from snapshot
  - suggestSkill(snapshot) → { skillId, args? } — concrete next dispatch
  - emergencyPause(snapshot) → bool — defers to manifesto L0 alive
    emergencies (low HP near hostile, lava under foot, food = 0)
  - narration_ru — chat-friendly Russian one-liner spoken on entry

Components:

- runtime/goal/storyline.js — 11-step canonical quest catalogue
- runtime/goal/state.js — pickCurrentStep(snapshot) walks the list,
  returns first non-completed step + its suggestion. 3s cache.
  Validates suggestSkill's skillId against the live registry.
- runtime/reflex.js — curriculumReflex dispatch priority is now:
    1. manifesto (L0 alive emergencies always win)
    2. storyline (concrete operational subgoal)
    3. curriculum plan (legacy fallback)
  Tests pass ctx.disableStoryline=true for isolation.
- runtime/bot.js — snapshot.storyStep populated each tick so
  chatter/advisor/reflect observers see the same view.
- runtime/coach/fast-advisor.js — buildUserPrompt now embeds the
  current step + its suggested skill, so LLM advice is anchored
  ("step 5 first_food, storyline wants survive.acquire-food, but
  recent dispatches show it's failing — try explore.far + scout").
- runtime/coach/advisor-trigger.js — forwards ctx.storyStep into
  advise() and logs step id at trigger time.
- runtime/coach/reflect.js — reflection prompt includes storyline
  progress so 30-min self-assessment is anchored.
- runtime/persona/chatter.js — narrates step.narration_ru on
  transition. Rate-limited via existing maybeNarrateRaw().

New operator CLI:

- scripts/show-story.js — fetches the live snapshot via IPC sock and
  prints step progress with ✓/→/ markers, current skill, inventory.
  Falls back to --plain catalogue view when bot offline.

Token cost impact: ~+30 input tokens per advise() call (one extra
line in user prompt). Trivial vs the value of grounding LLM advice
in a concrete narrative.

Operator usage:

  node scripts/show-story.js          # live progress + which step + why
  node scripts/show-story.js --plain  # static catalogue of all 11 steps

Tests: 376 green (was 360, +16 storyline tests).

Also in this branch (already committed): dev/v0.3.1/PRD.md —
LLM prompt cost optimization design doc.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

runtime/persona/chatter.js

@@ -94,6 +94,7 @@ let _last = {
 	threatHostile: null,
 	dayPart: null,
 	noProgressReason: null,
+	storyStepId: null,
 };
 let _lastNarrationAt = 0;
 let _narrationTimes = [];
@@ -164,6 +165,15 @@ function tick() {
 		_last.noProgressReason = snap.noProgressReason;
 	}
 
+	// 4b. Storyline step transition — narrate the *narration_ru* line
+	// straight from runtime/goal/storyline.js when the step changes.
+	// This is the bot speaking about its current quest concretely.
+	const story = snap.storyStep ?? null;
+	if (story?.step?.id && story.step.id !== _last.storyStepId && story.step.narration_ru) {
+		maybeNarrateRaw(story.step.narration_ru);
+		_last.storyStepId = story.step.id;
+	}
+
 	// 5. Milestone done — fires when activeSkill flips to noop and lastResult.ok
 	const last = snap.lastResult;
 	if (last?.ok && last?.code === "done") {
@@ -200,13 +210,19 @@ function inferDayPart(snap) {
 }
 
 function maybeNarrate(key) {
+	const line = pickLine(key);
+	if (!line) return;
+	maybeNarrateRaw(line);
+}
+
+function maybeNarrateRaw(line) {
+	if (!line) return;
 	const now = Date.now();
 	const hourAgo = now - 3600_000;
 	_narrationTimes = _narrationTimes.filter((t) => t > hourAgo);
 	if (now - _lastNarrationAt < MIN_GAP_MS) return;
 	if (_narrationTimes.length >= MAX_PER_HOUR) return;
-	const line = pickLine(key);
-	if (!line) return;
+	if (line === _lastTemplate) return;
 	const ok = sendChat(line);
 	if (ok) {
 		_lastNarrationAt = now;