fix(v0.3.1): sated bot stops chasing food + perf-leak + fuzzy improvement dedup

Third day of "bot just walks back and forth burning tokens". Root
causes were mechanical, not the manifesto:

1. SATED BOT CHASING FOOD (the big one)
   Bot had food=17 (nearly full) but storyline first_food + manifesto
   L1 required 2+ food ITEMS in inventory, so it looped scout-food /
   acquire-food for hours instead of working. Now both treat a hunger
   bar >= 14 (SATED_FOOD) as satisfied even with empty food inventory —
   a full bot chops wood / makes tools and grabs food opportunistically,
   only hard-pursuing food when actually hungry (< 14).
   manifesto/needs.js foodDetect + goal/storyline.js first_food.completed.

2. perf_hooks MEMORY LEAK (overnight OOM suspect)
   "MaxPerformanceEntryBufferExceededWarning: 1,000,001 measure entries".
   mineflayer/pathfinder emit perf marks we never consume. Added a
   60s reaper in bot.js (performance.clearMeasures/clearMarks). unref'd.

3. IMPROVEMENT QUEUE SELF-DUPLICATING
   The LLM re-filed closed gaps with reworded titles (#5/#8/#9 were
   dupes of implemented #1/#2/#3). Exact-title dedup missed them.
   Replaced with token-set fuzzy match (isDuplicateTitle): jaccard>=0.75
   OR >=3 shared meaningful tokens with jaccard>=0.5. Also: a re-filed
   gap that's already implemented/rejected is NOT resurrected as a new
   open row. Cleared all 5 open requests (now genuinely implemented).

Also confirmed (no change needed):
- canDig=true is a DELIBERATE codebase-wide choice ("without it the bot
  gets permanently stuck", actions.js). The stale memory recommending
  canDig=false is updated. ViaBackwards dig works partially (dug:1
  moved:1.8 observed); false would trap the bot in every pit.
- scout-food already has blind/tunnel fallback + 12s step timeout
  (operator's earlier edits) so trapped-pathfinder degrades instead of
  hanging 30s.

Tests: 407 green (was 404). Updated needs/state/storyline tests for the
SATED_FOOD threshold; added fuzzy-dedup + tokenize/jaccard tests.

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

runtime/knowledge/index.js

@@ -334,16 +334,28 @@ export function createImprovementRequest({
 } = {}) {
 	if (!_isAvailable() || !title) return null;
 	try {
-		// Dedup: if an open request with same title (case-insensitive) exists,
-		// bump its votes instead of inserting a new row.
-		const dup = _getStore().prepare(`
-			SELECT id, votes FROM improvement_requests
-			WHERE LOWER(title) = LOWER(?) AND status = 'open'
-			ORDER BY ts DESC LIMIT 1
-		`).get(title);
-		if (dup) {
-			_getStore().prepare(`UPDATE improvement_requests SET votes = votes + 1 WHERE id = ?`).run(dup.id);
-			return dup.id;
+		// Fuzzy dedup: the LLM re-files the same gap with reworded titles
+		// ("целевого поиска еды" vs "целевого дальнего поиска еды по биому").
+		// Exact-title match misses these, so we compare normalized token
+		// sets against ALL recent requests (any status — a closed/
+		// implemented one shouldn't reappear as a fresh open row). On a
+		// strong overlap we bump votes (if still open) and return, instead
+		// of inserting a near-duplicate.
+		const incoming = tokenize(title);
+		const candidates = _getStore().prepare(`
+			SELECT id, title, status, votes FROM improvement_requests
+			ORDER BY ts DESC LIMIT 60
+		`).all();
+		for (const c of candidates) {
+			if (isDuplicateTitle(incoming, tokenize(c.title))) {
+				// Re-flagged gap. If it's still open, count the vote. If it
+				// was implemented/rejected, do NOT resurrect it — just
+				// return its id so the caller treats it as "already known".
+				if (c.status === "open") {
+					_getStore().prepare(`UPDATE improvement_requests SET votes = votes + 1 WHERE id = ?`).run(c.id);
+				}
+				return c.id;
+			}
 		}
 		const res = _getStore().prepare(`
 			INSERT INTO improvement_requests
@@ -412,7 +424,48 @@ export function markImprovementStatus(id, { status, notes } = {}) {
 
 function clamp(n, lo, hi) { return Math.max(lo, Math.min(hi, Number(n) || lo)); }
 
+// Normalize a title into a set of meaningful tokens for fuzzy dedup.
+// Lowercase, strip punctuation, drop short / stop words (RU + EN) that
+// carry no signal ("нет", "навыка", "для", "the", "a", …).
+const _STOP = new Set([
+	"нет", "навык", "навыка", "для", "из", "по", "в", "на", "и", "с", "к",
+	"когда", "нужно", "это", "что", "the", "a", "an", "to", "of", "for",
+	"no", "skill", "has", "is", "low", "rate",
+]);
+function tokenize(s) {
+	if (!s || typeof s !== "string") return new Set();
+	const words = s.toLowerCase()
+		.replace(/["'`(),.:;!?\/\\-]+/g, " ")
+		.split(/\s+/)
+		.filter((w) => w.length >= 3 && !_STOP.has(w));
+	return new Set(words);
+}
+function jaccard(a, b) {
+	if (a.size === 0 || b.size === 0) return 0;
+	let inter = 0;
+	for (const w of a) if (b.has(w)) inter++;
+	return inter / (a.size + b.size - inter);
+}
+function intersectionSize(a, b) {
+	let n = 0;
+	for (const w of a) if (b.has(w)) n++;
+	return n;
+}
+// Two titles are "the same gap" when they either overlap very strongly
+// (jaccard ≥ 0.75) OR share at least 3 meaningful tokens with moderate
+// overlap (≥ 0.5). The 3-token floor stops short titles with one or two
+// generic words in common ("low-prio thing" vs "high-prio thing") from
+// false-matching, while still catching reworded long titles.
+function isDuplicateTitle(a, b) {
+	const j = jaccard(a, b);
+	if (j >= 0.75) return true;
+	return intersectionSize(a, b) >= 3 && j >= 0.5;
+}
+
 function safeParse(s) {
 	if (!s) return null;
 	try { return JSON.parse(s); } catch { return null; }
 }
+
+// Test exports
+export const __testing = { tokenize, jaccard, isDuplicateTitle };

runtime/knowledge/knowledge.test.js

@@ -320,6 +320,42 @@ test("improvement requests: create, dedup-by-title bumps votes, list filters", a
 	assert.ok(!stillOpen.some((r) => r.id === id1));
 });
 
+test("improvement requests: fuzzy dedup catches reworded titles + won't resurrect closed ones", async () => {
+	await bootstrap();
+	if (!isAvailable()) return;
+	const a = createImprovementRequest({
+		source: "postmortem", category: "skill",
+		title: "Нет навыка целевого поиска еды по биому", priority: 1,
+	});
+	assert.ok(a);
+	// Reworded near-duplicate — should map to the SAME row, bump votes.
+	const b = createImprovementRequest({
+		source: "reflect", category: "skill",
+		title: "Нет навыка целевого дальнего поиска еды по биому", priority: 1,
+	});
+	assert.equal(b, a, "reworded title deduped to original");
+
+	// Mark it implemented, then the LLM re-files the same gap reworded
+	// again — must NOT create a fresh open row (no resurrection).
+	markImprovementStatus(a, { status: "implemented", notes: "scout-food" });
+	const c = createImprovementRequest({
+		source: "reflect", category: "skill",
+		title: "Нужен навык дальнего поиска еды по биому", priority: 1,
+	});
+	assert.equal(c, a, "re-filed closed gap returns existing id, no new row");
+	const open = listImprovements({ status: "open" });
+	assert.ok(!open.some((r) => r.id === a), "closed gap stays closed");
+});
+
+test("tokenize / jaccard: similarity helpers", async () => {
+	const { tokenize, jaccard } = (await import("./index.js")).__testing;
+	const t1 = tokenize("Нет навыка целевого поиска еды по биому");
+	const t2 = tokenize("Нет навыка целевого дальнего поиска еды по биому");
+	assert.ok(jaccard(t1, t2) >= 0.6, `expected ≥0.6, got ${jaccard(t1, t2)}`);
+	const t3 = tokenize("Trigger wedged_96s has low success rate");
+	assert.ok(jaccard(t1, t3) < 0.3, "unrelated titles score low");
+});
+
 test("improvement requests: priority and status ordering", async () => {
 	await bootstrap();
 	if (!isAvailable()) return;