v0.3.1: survival behaviour overhaul — storyline, biome-aware scout, wedge-relocate, food/perf fixes, monitor TUI (#28)

* docs(v0.3.1): PRD — LLM prompt cost optimization

Design-only commit; no runtime changes. Spec for the next patch iteration.

Goal: cut per-advise() input tokens from ~800 to ≤300, preserving the
LLM's ability to produce valid registered skill ids and useful rationale.

Five proposed changes ranked by impact:

  P1  Compact registry format (saves ~350t/call) — group by namespace,
      comma-list ids, drop human titles. Default mode for advisor;
      verbose mode kept for postmortem/reflect.
  P2  Need-scoped registry (~50t additional) — show LLM only skills
      relevant to the active Maslow need + always-available safety
      skills (survive.flee, pillar-up, recovery.tunnel-out, explore.*).
  P3  Snapshot pruning (~50t) — drop weather/experience/dimension/biome/
      players from the user prompt; the LLM doesn't consult them.
  P4  Prompt caching probe — check if TimeWeb passes through
      prompt_tokens_details.cached_tokens. If yes, restructure prefix
      to maximize cache hits (cached input is ~10x cheaper at OpenAI).
  P5  Per-trigger cost telemetry in scripts/list-improvements.js --stats:
      avg_in / avg_out / cost_₽ / share% per trigger_reason, using
      TIMEWEB_PRICE_IN_RUB_PER_M and TIMEWEB_PRICE_OUT_RUB_PER_M env.

Trigger: TimeWeb admin panel after first day of v0.3.0 live showed
34K tokens / day at low activity. At cap budget that projects to
~480₽/month (101₽/M in, 608₽/M out for gpt-5.4-mini). Manageable
but the savings are mostly free — repeated infra tokens, not signal.

All changes are additive; runtime behaviour stays the same. If the
LLM produces worse advice with the compact registry, flip back via a
single constant in fast-advisor.js.

Acceptance: re-run scripts/check-timeweb.js probe 3 — expect
tokens_in ≤ 300 (was ~800). Live for 1h, check --stats: avg_in ≤ 300
per trigger group. Existing 360 tests still green.

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

* 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>

* fix(v0.3.1): storyline beats manifesto L1+ (only L0 alive emergencies override)

Found in live logs after the previous commit deployed:
  storyline: step 1/11: orient_self → explore.wander
  advisor-trigger: firing because wedged (planned=survive.acquire-food, ...)

Manifesto was still picking survive.acquire-food (L1 food) over the
storyline's orient_self → explore.wander. That's the wrong precedence —
storyline expresses a *concrete operational subgoal* and L1+ manifesto
needs are just "you'd benefit from food" priorities, not emergencies.

New dispatch precedence in curriculumReflex:
  1. manifesto L0 (alive emergencies: lava, low-HP+hostile, food=0)
  2. storyline (concrete narrative subgoal — beats L1+ manifesto)
  3. manifesto L1+ (fallback when storyline has no concrete suggestion)
  4. curriculum plan (legacy fallback)

This way the bot starts following the narrative arc even while
manifesto's L1 food is technically unsatisfied — orient_self runs to
completion before pursuing food explicitly. Storyline already handles
food as step 5 (first_food), so we're not skipping it.

Tests: 378 green (+2 priority-ordering tests):
- L0 manifesto emergency: upstream reflex (defend/modes) catches before
  curriculum dispatch
- storyline beats manifesto when both have suggestions: well-fed bot
  with logs → craft.planks (storyline crafting_basics), not gather.logs
  (manifesto L2)
- updated "manifesto fallback" test to require disableStoryline=true

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

* feat(tui): fullscreen monitor-only TUI (opencode-style)

Replaces the old tui/tui.tsx hotkey-heavy dashboard with a read-only
observability screen. Operator actions live in scripts/* now —
TUI is for watching, not driving.

Layout (top to bottom, all auto-resizing to terminal):
  1. Header     — MC/IPC status, pos, HP, food, day/night, hostiles
  2. Storyline  — current step + 11-step quest map (✓/→/○)
  3. Activity   — last N skill dispatches (colour by outcome)
  4. MC Chat    — last N chat lines (cyan for bot, yellow for players)
  5. Advisor    — last N LLM recommendations (trigger + outcome + tokens)
  6. Improvements — open requests from knowledge.improvement_requests
  7. Footer     — 24h token usage + cost in ₽ + q-to-quit

Data sources:
  - IPC sock: snapshot frames, log frames, chat frames (push)
  - SQLite knowledge.db: advisor_recommendations + improvement_requests
    polled every 5s (pull)

Token cost displayed live using TIMEWEB_PRICE_IN_RUB_PER_M /
TIMEWEB_PRICE_OUT_RUB_PER_M env vars (defaults: 101 / 608 for
gpt-5.4-mini).

Switches:
  - npm run tui          → new monitor (this file)
  - npm run tui:legacy   → old action-driven tui/tui.tsx (kept for now)

Implementation notes:
  - Uses ink + alternate-screen-buffer ANSI for proper "opencode-feel"
    fullscreen behaviour; restores prior terminal contents on quit.
  - Skips alt-screen and useInput when stdin/stdout isn't a TTY
    (smoke tests, piped output) — both gracefully degrade.
  - Stable React keys via per-event uid counter, avoids reconciler
    duplicate-key warnings as logs/chat/dispatches stream in.
  - Resize handled via 1s stdout-dimension poll, NOT direct
    'resize' listener (which conflicts with ink's own listener and
    triggers MaxListenersExceededWarning).

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

* ui(tui): compact 4-section monitor (was 6) — fits 1080p without zoom

Operator reported the TUI overflowed the screen unless terminal was
zoomed way out. The 11-step storyline list alone was eating ~13
rows, and each advisor/improvement entry took 2-3 rows. Now:

- Header + storyline collapsed into one panel (2 lines):
    line 1: pepa · ●MC ●IPC · 1m50s · pepa_bot · (697,61,702) · HP 20 · food 5 · ☀ · ⚔60(creeper@58b)
    line 2: story ▓▒░░░░░░░░░ 1/11 orient_self · Понять где я → explore.wander
  The 11-step ladder is now a unicode progress bar (▓ done, ▒ current,
  ░ pending) — same info, fits in one row.

- Advisor entries: one line each instead of two.
    ✓ wedged_60s → survive.flee  802t 1900ms
    (outcome mark / trigger / target skill / tokens / latency)

- Improvements entries: one line each instead of two.
    #1 P2 ×3  Add craft.iron-pickaxe skill
  Description dropped from the row — use `node scripts/list-improvements.js`
  for full text.

- Sections: 4 (was 6).
    [header+story] · [activity | chat] · [advisor | improvements] · [footer]

Tested on a typical 1080p terminal — fits comfortably without zoom.

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

* feat(v0.3.1): real survival patterns — biome-aware scout, wedge-relocate, escape-pit-safe

Operator reported the bot wandered the same 50×50 patch for 2 hours
without making any progress toward food. Diagnosis showed three root
causes; this commit addresses all five open improvement_requests
the LLM (postmortem + tuner) flagged automatically.

Research basis (`Voyager`, `Plan4MC`, `GITM`, `Mindcraft`):
  - Coverage / commit-to-cardinal exploration when local scan fails
  - Biome-aware strategy switching using a static affordance table
  - Wedge detector above the skill layer that triggers RELOCATE not
    RETRY (per-skill stuck checks reset on re-entry — useless)
  - Time-in-region bbox heuristic + need-duration AND skill-cycle gate

Concrete changes:

1. `runtime/goal/storyline.js`
   - orient_self.completed: added timeout fallback (HP=full + session
     >120s → done) so barren biomes don't block the bot on step 1.
     Closes improvement #2 'Нет навыка оценки когда сменить район'.
   - first_food.suggestSkill: now picks survive.scout-food (new) when
     no passive mob is nearby; falls back to survive.acquire-food only
     when something is in immediate range.

2. `runtime/biome-affordances.js` (new)
   - Static table: 40+ biomes → {has_passive_mobs, has_trees,
     has_water, has_crops, livable}.
   - Unknown biomes return optimistic defaults to avoid regressions.
   - Closes improvement #1 'Нет навыка целевого поиска еды по биому'.

3. `runtime/skills/scout-food.js` (new — survive.scout-food)
   - Tiered strategy: biome check → scan 32 → scan 64 → commit a
     cardinal for 200 blocks rescanning every 16. On cardinal
     exhaustion, returns code:"exhausted" so the curriculum can
     escalate to village.relocate.
   - In barren biomes (desert/ocean/snowy_plains) the scan is
     SKIPPED — bot walks straight toward the nearest neighbour
     biome that affords passive mobs (8-direction biome probe at
     radius 64).

4. `runtime/awareness/wedge-detector.js` (new)
   - Rolling 10-min position bbox tracker. observe() called every
     tick; isWedged() returns true when bbox<50 AND active need
     unmet >5min AND skill cycles ≥3.
   - markRelocationStarted() suppresses further wedge firings
     until the bot has displaced ≥200b — prevents stack overflow
     of relocate calls.
   - Lives ABOVE the skill layer (in runtime/reflex.js), because
     any per-skill stuck check resets on re-entry.

5. `runtime/skills/relocate.js` (new — village.relocate)
   - 300-block walk in least-recently-used cardinal (per-incident
     memory in ctx.recentRelocations).
   - Re-paths every 32 blocks, soft-tolerates pathfinder failures
     (3 consecutive throws → exit with code:"stuck_in_place").
   - Closes improvement #2 + #4 ('low success rate trigger').

6. `runtime/skills/escape-pit-safe.js` (new — recovery.escape-pit-safe)
   - Surveys 4 cardinals AND ceiling height before committing.
     Picks the direction with most open blocks (≥3, no lava).
     Falls through to pillar-up only if ceiling clear ≥4b. Returns
     code:"no_strategy" if both blocked so curriculum can escalate
     to relocate.
   - Closes improvement #3 'Нет навыка для безопасного выхода'.

7. `runtime/reflex.js`
   - Wedge detector wired before manifesto/storyline. If wedge.wedged
     is true, dispatches village.relocate directly and returns —
     bypasses every other branch.
   - ctx.disableWedge flag for tests.

8. `runtime/coach/advisor-trigger.js`
   - LLM provider outage backoff: 3 consecutive http_400 / timeout /
     network_error → suppress advisor for 10 min. Today's TimeWeb
     gpt-5.4-mini was 400'ing for an hour straight; we were spending
     trigger budget on dead calls. Closes improvement implicit gap
     in #5.

9. `runtime/bot.js`
   - Tracks botSpawnedAt; snapshot._sessionMs exposed for storyline
     orient_self timeout fallback.

Tests: 396 green (was 378, +18):
  - runtime/biome-affordances.test.js — 8 tests
  - runtime/awareness/wedge-detector.test.js — 9 tests
  - runtime/goal/storyline.test.js — 1 new test (orient_self timeout)

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

* fix(coach/trigger-tuner): crash after ~1h — runOnce is sync, not a Promise

The live bot died overnight with:
  TypeError: runOnce(...).catch is not a function
  at trigger-tuner.js:42  →  [supervisor] child exited code=1

attach() wrapped the timer body as `runOnce().catch(...)` but
runOnce() returns a plain {ok, flagged, ...} object (pure SQL, no
await). The first tuner tick (60min after spawn) threw → killed the
whole bot process. Never surfaced before because the bot rarely ran
uninterrupted for a full hour during development.

Fix: guard the synchronous call with try/catch, matching how
persona/chatter.js already does its sync tick. (postmortem.drainOnce
and reflect.runOnce ARE async, so their .catch is correct — audited.)

Regression test added: captures the setInterval callback and invokes
it synchronously, asserting it does not throw.

Tests: 397 green.

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

* fix(v0.3.1): mechanical food/stuck fixes — bot reaches the chicken now

The wedge wasn't only in the manifesto layer; several mechanical bugs
kept the bot in a dead random-walk:

- storyline / manifesto / curriculum: "local food" now means an edible
  passive mob within <=32 blocks. A distant chicken or a cod no longer
  fools the bot into dispatching acquire-food (which then fails on
  no_path). Long-range food goes through scout-food instead.

- scout-food: partial approach to a target now counts as progress
  (approached_target, e.g. moved:14); a blocked heading is NOT counted
  as movement; added blind/tunnel fallback so it doesn't die when the
  pathfinder can't route cleanly.

- acquire-food: on no_path it now also tries a blind/tunnel approach to
  the animal; no_drop routes back into food scouting instead of giving
  up.

- explore.far / relocate / flee: fewer false "done" results (micro-steps
  no longer counted as success), more genuine escapes from stuck.

- scripts/show-story.js: live IPC now actually renders the current
  storyline step.

Verification: scripts/lint-patch.js clean; npm test 404/404 green; bot
relaunched in tmux `pepa`. Live logs show real progress — bot switched
to survive.scout-food, approached the chicken (approached_target
moved:14), then reached survive.acquire-food: hunting chicken. Food
isn't fully closed yet but the remaining issue is concrete pickup/drop,
not dead random-walk.

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

* 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>

---------

Co-authored-by: Yuriy Mayatnikov <mayatnikov@me.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
This commit was merged in pull request #28.
This commit is contained in:
Yuriy Mayatnikov
2026-05-28 09:43:57 +03:00
committed by GitHub
co-authored by Claude Opus 4.7 mayatnikov
parent 7d96e44804
commit 15b6c11002
37 changed files with 3259 additions and 71 deletions
+408
View File
@@ -0,0 +1,408 @@
// survive.scout-food — longer-range, biome-aware food search.
//
// Why this exists alongside survive.acquire-food:
//
// acquire-food is the "I see a cow, hunt it" skill. Its precondition
// requires a passive food mob within ~32 blocks; if there isn't one,
// the skill bails immediately. In v0.3.0 that produced two failure
// modes that kept the bot looping for hours:
//
// 1. Biome with NO passive mobs (desert, ocean, snowy peaks, deep
// caves). acquire-food can never succeed there — the bot just
// kept scanning the same 32-block sphere.
//
// 2. Biome WITH passive mobs but the immediate area is empty. The
// bot wandered 1-8 blocks at a time around the same 50×50 patch
// and never committed to a direction long enough to leave it.
//
// scout-food applies the "commit-to-cardinal" pattern (per the v0.3.1
// design research): scan(32) → patrol(64, time-budget) → if still
// nothing, walk a chosen cardinal for ~200 blocks, rescanning every
// 16 blocks. On exhaustion of all 4 cardinals it surrenders to the
// curriculum so the operator-driven `village.relocate` or LLM advisor
// can pick up.
//
// Biome-awareness:
// - If current biome's affordance table has has_passive_mobs=false
// AND has_water=false, skip the local scan entirely and pick the
// most plausible "leave biome" heading: sample neighbour biomes at
// radius 64 in 8 directions, pick the first one whose affordances
// say has_passive_mobs=true.
// - In water-bearing barren biomes (ocean shores, frozen rivers)
// fishing isn't implemented yet — operator-facing improvement.
import pathfinderPkg from "mineflayer-pathfinder";
const { pathfinder, goals, Movements } = pathfinderPkg;
import { info, warn } from "../log.js";
import { foods } from "./groups.js";
import { affordancesFor, hasPassiveMobs, isBarren } from "../biome-affordances.js";
import { blindWalkOrTunnelOut } from "./explore-far.js";
const PASSIVE_FOOD_MOBS = new Set(["cow", "pig", "chicken", "sheep", "rabbit", "mooshroom"]);
const CARDINALS = [
{ name: "N", dx: 0, dz: -1, yaw: Math.PI },
{ name: "E", dx: 1, dz: 0, yaw: -Math.PI / 2 },
{ name: "S", dx: 0, dz: 1, yaw: 0 },
{ name: "W", dx: -1, dz: 0, yaw: Math.PI / 2 },
];
const PATROL_TICK_DISTANCE = 16;
const PATROL_STEP_TIMEOUT_MS = 12_000;
const DEFAULT_COMMIT_DISTANCE = 200;
let pluginLoaded = new WeakSet();
function ensurePathfinder(bot) {
if (pluginLoaded.has(bot)) return;
bot.loadPlugin(pathfinder);
pluginLoaded.add(bot);
}
function setMovementsForTravel(bot) {
const m = new Movements(bot);
m.canDig = true;
m.allow1by1towers = false;
bot.pathfinder.setMovements(m);
}
function foodCount(bot) {
const allowed = foods(bot);
return bot.inventory.items().reduce((sum, item) => allowed.has(item.name) ? sum + item.count : sum, 0);
}
function nearestPassiveFoodMob(bot, maxDistance) {
const here = bot?.entity?.position;
if (!here) return null;
let best = null;
for (const e of Object.values(bot.entities ?? {})) {
if (!e?.position || !PASSIVE_FOOD_MOBS.has(e.name)) continue;
const d = e.position.distanceTo(here);
if (d > maxDistance) continue;
if (!best || d < best.distance) best = { entity: e, distance: d };
}
return best;
}
function currentBiomeName(bot) {
try {
const block = bot.blockAt?.(bot.entity?.position);
const b = block?.biome;
if (typeof b === "string") return b;
if (b?.name) return b.name;
return null;
} catch { return null; }
}
function biomeNameAt(bot, x, y, z) {
try {
const block = bot.blockAt?.({ x: Math.floor(x), y: Math.floor(y), z: Math.floor(z) });
const b = block?.biome;
if (typeof b === "string") return b;
if (b?.name) return b.name;
return null;
} catch { return null; }
}
// Sample biomes in 8 compass directions at the given radius; return
// the heading whose biome has passive mobs.
function scanForFoodCapableNeighbourBiome(bot, radius = 64) {
const here = bot?.entity?.position;
if (!here) return null;
const dirs = [
{ name: "N", dx: 0, dz: -1 },
{ name: "NE", dx: 0.71, dz: -0.71 },
{ name: "E", dx: 1, dz: 0 },
{ name: "SE", dx: 0.71, dz: 0.71 },
{ name: "S", dx: 0, dz: 1 },
{ name: "SW", dx: -0.71, dz: 0.71 },
{ name: "W", dx: -1, dz: 0 },
{ name: "NW", dx: -0.71, dz: -0.71 },
];
for (const d of dirs) {
const b = biomeNameAt(bot, here.x + d.dx * radius, here.y, here.z + d.dz * radius);
if (b && hasPassiveMobs(b)) return { heading: d, biome: b };
}
return null;
}
function scoutState(ctx, bot) {
const here = bot?.entity?.position;
const now = Date.now();
const prev = ctx.scoutFoodState;
const expired = !prev || now - (prev.ts ?? 0) > 10 * 60_000;
const displaced = prev?.origin && here
? Math.hypot(here.x - prev.origin.x, here.z - prev.origin.z) > 128
: false;
if (expired || displaced) {
ctx.scoutFoodState = {
ts: now,
origin: here ? { x: here.x, z: here.z } : null,
tried: new Set(),
};
return ctx.scoutFoodState;
}
prev.ts = now;
if (!(prev.tried instanceof Set)) prev.tried = new Set(prev.tried ?? []);
return prev;
}
async function patrolCardinal(bot, cardinal, distance, ctx) {
ensurePathfinder(bot);
setMovementsForTravel(bot);
const start = bot.entity.position.clone?.() ?? { ...bot.entity.position };
let travelled = 0;
while (travelled < distance) {
if (ctx?.abortSignal?.aborted) return { aborted: true, travelled };
const tx = start.x + cardinal.dx * (travelled + PATROL_TICK_DISTANCE);
const tz = start.z + cardinal.dz * (travelled + PATROL_TICK_DISTANCE);
const goal = new goals.GoalNear(Math.floor(tx), Math.floor(bot.entity.position.y), Math.floor(tz), 2);
try {
await Promise.race([
bot.pathfinder.goto(goal),
new Promise((_, rej) => setTimeout(() => rej(new Error("patrol step timeout")), PATROL_STEP_TIMEOUT_MS)),
]);
} catch (e) {
info("action", `scout-food: path step failed (${e?.message ?? e}); blind fallback ${cardinal.name}`);
try { bot.pathfinder?.stop?.(); } catch {}
const blind = await blindWalkOrTunnelOut(bot, {
yaw: cardinal.yaw ?? -Math.atan2(cardinal.dx, cardinal.dz),
dirName: cardinal.name,
blindMs: 12_000,
minMove: 6,
reason: `scout-food ${cardinal.name}`,
});
const progress = cardinalProgress(start, bot.entity.position, cardinal);
travelled = progress.along;
const target = nearestPassiveFoodMob(bot, 32);
if (target) return { aborted: false, travelled, target };
if (progress.total >= 4 && progress.along < 4) {
info("action", `scout-food: ${cardinal.name} blocked; drifted ${progress.driftName ?? "sideways"} ${progress.total.toFixed(1)}b`);
return {
aborted: false,
travelled,
blocked: true,
drifted: progress.driftName,
error: `blocked_${cardinal.name}`,
};
}
if (!blind.ok && progress.total < 4) {
return { aborted: false, travelled, error: e?.message ?? String(e) };
}
continue;
}
const progress = cardinalProgress(start, bot.entity.position, cardinal);
travelled = Math.max(travelled + PATROL_TICK_DISTANCE, progress.along);
// Rescan after every step.
const target = nearestPassiveFoodMob(bot, 32);
if (target) return { aborted: false, travelled, target };
}
return { aborted: false, travelled };
}
function cardinalProgress(start, pos, cardinal) {
const dx = (pos?.x ?? 0) - (start?.x ?? 0);
const dz = (pos?.z ?? 0) - (start?.z ?? 0);
const along = Math.max(0, dx * cardinal.dx + dz * cardinal.dz);
const total = Math.hypot(dx, dz);
return { along, total, driftName: dominantCardinal(dx, dz, cardinal.name) };
}
function dominantCardinal(dx, dz, fallback = null) {
if (Math.abs(dx) < 0.5 && Math.abs(dz) < 0.5) return fallback;
if (Math.abs(dx) >= Math.abs(dz)) return dx >= 0 ? "E" : "W";
return dz >= 0 ? "S" : "N";
}
export const skill = Object.freeze({
id: "survive.scout-food",
title: "Scout for food at long range (biome-aware)",
timeoutMs: 240_000,
preconditions(ctx) {
if (!ctx?.bot) return { ok: false, code: "no_bot", detail: "bot missing" };
if (foodCount(ctx.bot) > 0) {
return { ok: false, code: "already_have", detail: "already carrying edible food" };
}
return { ok: true };
},
async execute(ctx, args = {}) {
const bot = ctx.bot;
const before = foodCount(bot);
const state = scoutState(ctx, bot);
const triedCardinals = new Set([...(args?._triedCardinals ?? []), ...(state.tried ?? [])]);
// Step 0: biome check. If barren, head toward a food-capable neighbour.
const biome = currentBiomeName(bot);
const aff = affordancesFor(biome);
info("action", `scout-food: biome=${biome ?? "?"} mobs=${aff.has_passive_mobs} barren=${isBarren(biome)}`);
if (!aff.has_passive_mobs) {
const next = scanForFoodCapableNeighbourBiome(bot, 64);
if (next) {
info("action", `scout-food: leaving barren biome ${biome}${next.biome} via ${next.heading.name}`);
const result = await patrolCardinal(bot, next.heading, DEFAULT_COMMIT_DISTANCE, ctx);
if (result.aborted) return { ok: false, code: "preempted", worldDelta: null };
if (result.target) {
return await tryHunt(bot, result.target, before);
}
if (result.blocked) {
state.tried.add(next.heading.name);
return {
ok: false,
code: "blocked_heading",
detail: `blocked ${next.heading.name}, drifted ${result.drifted ?? "sideways"}`,
worldDelta: { moved: Math.round(result.travelled), heading: next.heading.name, drifted: result.drifted ?? null },
};
}
return {
ok: false,
code: "no_target",
detail: `walked ${Math.round(result.travelled)}b ${next.heading.name} toward ${next.biome}, still no food`,
worldDelta: { moved: Math.round(result.travelled), heading: next.heading.name, from_biome: biome, to_biome: next.biome },
};
}
// Ringed by barren biomes; pick the first cardinal not yet tried.
}
// Step 1: scan radius 32 (cheap).
let target = nearestPassiveFoodMob(bot, 32);
if (target) return await tryHunt(bot, target, before);
// Step 2: scan radius 64 — entities frequently spawn just outside
// our local horizon.
target = nearestPassiveFoodMob(bot, 64);
if (target) return await tryHunt(bot, target, before);
// Step 3: commit to a cardinal we haven't tried in this incident.
const untried = CARDINALS.filter((c) => !triedCardinals.has(c.name));
if (untried.length === 0) {
return {
ok: false,
code: "exhausted",
detail: "tried all 4 cardinals without finding a food mob — switch to village.relocate",
worldDelta: null,
};
}
const cardinal = untried[0];
state.tried.add(cardinal.name);
info("action", `scout-food: commit cardinal ${cardinal.name} for ${DEFAULT_COMMIT_DISTANCE}b`);
const result = await patrolCardinal(bot, cardinal, DEFAULT_COMMIT_DISTANCE, ctx);
if (result.aborted) return { ok: false, code: "preempted", worldDelta: null };
if (result.target) return await tryHunt(bot, result.target, before);
if (result.blocked) {
return {
ok: false,
code: "blocked_heading",
detail: { tried: cardinal.name, travelled: Math.round(result.travelled), drifted: result.drifted ?? null, error: result.error ?? null },
worldDelta: { moved: Math.round(result.travelled), heading: cardinal.name, drifted: result.drifted ?? null, from_biome: biome },
};
}
return {
ok: false,
code: "no_target",
detail: { tried: cardinal.name, travelled: Math.round(result.travelled), error: result.error ?? null },
worldDelta: { moved: Math.round(result.travelled), heading: cardinal.name, from_biome: biome },
};
},
recover(ctx, result) {
if (result.code === "exhausted") {
return { hint: "relocate", reason: "scout-food exhausted all 4 cardinals; needs a long jump" };
}
if (result.code === "blocked_heading") {
return { hint: "scout-food", reason: "chosen scout heading is blocked; retry another cardinal" };
}
if (result.code === "approached_target" || result.code === "no_path") {
return { hint: "scout-food", reason: "made or attempted progress toward food target; rescan from current position" };
}
if (result.code === "no_target") {
return { hint: "wander", reason: "scout completed leg without finding mob; try another cardinal" };
}
return null;
},
});
async function tryHunt(bot, target, before) {
ensurePathfinder(bot);
setMovementsForTravel(bot);
const start = bot.entity.position.clone?.() ?? { ...bot.entity.position };
try {
await Promise.race([
bot.pathfinder.goto(new goals.GoalFollow(target.entity, 2)),
new Promise((_, rej) => setTimeout(() => rej(new Error("path-to-mob timeout")), 30_000)),
]);
} catch (e) {
try { bot.pathfinder?.stop?.(); } catch {}
const moved = horizontalDistance(start, bot.entity.position);
if (moved >= 6) {
return {
ok: false,
code: "approached_target",
detail: { target: target.entity.name, moved: Math.round(moved), mode: "pathfinder_partial", error: e?.message ?? "path failed" },
worldDelta: { moved: Math.round(moved), target: target.entity.name, mode: "pathfinder_partial" },
};
}
const yaw = yawToward(bot.entity.position, target.entity.position);
if (yaw !== null) {
const blind = await blindWalkOrTunnelOut(bot, {
yaw,
dirName: `toward-${target.entity.name}`,
blindMs: 8_000,
minMove: 4,
reason: `scout-food target ${target.entity.name}`,
});
const afterBlind = horizontalDistance(start, bot.entity.position);
if (blind.ok || afterBlind >= 4) {
return {
ok: false,
code: "approached_target",
detail: { target: target.entity.name, moved: Math.round(afterBlind), mode: "blind_target", error: e?.message ?? "path failed" },
worldDelta: { moved: Math.round(afterBlind), target: target.entity.name, mode: "blind_target" },
};
}
}
return { ok: false, code: "no_path", detail: e?.message ?? "path failed", worldDelta: null };
}
info("action", `scout-food: engaging ${target.entity.name}@${target.distance.toFixed(1)}b`);
for (let i = 0; i < 8; i++) {
const current = Object.values(bot.entities ?? {}).find((e) => e.id === target.entity.id);
if (!current) break;
if (current.position.distanceTo(bot.entity.position) > 4) {
try {
await Promise.race([
bot.pathfinder.goto(new goals.GoalFollow(current, 2)),
new Promise((_, rej) => setTimeout(() => rej(new Error("repath timeout")), 8_000)),
]);
} catch {}
}
bot.attack(current);
await new Promise((r) => setTimeout(r, 700));
}
await new Promise((r) => setTimeout(r, 1_000));
const after = foodCount(bot);
if (after <= before) {
return { ok: false, code: "no_drop", detail: `hunted ${target.entity.name} but no edible drop`, worldDelta: null };
}
return {
ok: true,
code: "done",
detail: { source: "hunt", mob: target.entity.name, gained: after - before },
worldDelta: { acquiredFood: after - before, source: "hunt", mob: target.entity.name },
};
}
function horizontalDistance(a, b) {
return Math.hypot((b?.x ?? 0) - (a?.x ?? 0), (b?.z ?? 0) - (a?.z ?? 0));
}
function yawToward(from, to) {
if (!from || !to) return null;
const dx = to.x - from.x;
const dz = to.z - from.z;
if (Math.hypot(dx, dz) < 0.5) return null;
return -Math.atan2(dx, dz);
}
// Test exports
export const __testing = {
CARDINALS, PATROL_TICK_DISTANCE, DEFAULT_COMMIT_DISTANCE, PATROL_STEP_TIMEOUT_MS,
nearestPassiveFoodMob, currentBiomeName, scanForFoodCapableNeighbourBiome,
cardinalProgress, dominantCardinal, horizontalDistance, yawToward,
};