Files
pepa-pi-bot/runtime/reflex.test.js
T
mayatnikovandClaude Opus 4.7 08ac2e1bc1 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>
2026-05-27 23:01:39 +03:00

550 lines
16 KiB
JavaScript

// Tests for the new curriculum-driven scheduler in runtime/reflex.js.
// We exercise runTick with synthetic snapshots + a recording ctx so we can
// assert which reflex fires and what gets dispatched.
import { test } from "node:test";
import assert from "node:assert/strict";
import { runTick } from "./reflex.js";
function vec(x, y, z) {
return {
x,
y,
z,
distanceTo(other) {
return Math.hypot(this.x - other.x, this.y - other.y, this.z - other.z);
},
offset(dx, dy, dz) {
return vec(this.x + dx, this.y + dy, this.z + dz);
},
};
}
function makeCombatBot({ removeOnAttack = false } = {}) {
return {
attacks: 0,
entity: { position: vec(0, 64, 0) },
entities: {
zombie1: { name: "zombie", height: 1.8, position: vec(3, 64, 0) },
},
inventory: { items: () => [] },
lookAt: async () => {},
attack() {
this.attacks++;
if (removeOnAttack) delete this.entities.zombie1;
},
};
}
function makeCtx({
snapshot,
busy = false,
bot = { entities: {}, entity: { position: { x: 0, y: 64, z: 0 } } },
skillBackoff,
lastEatAt = 0,
lastSleepAttemptAt = 0,
lastCurriculumAt = 0,
metrics,
disableManifesto = true, // curriculum branch tests don't construct
// full snapshots; manifesto is exercised by
// runtime/manifesto/state.test.js separately.
disableAdvisor = true, // advisor-trigger fires real async LLM calls,
// tested directly in advisor-trigger.test.js.
disableStoryline = true, // storyline tested in goal/storyline.test.js
disableWedge = true, // wedge tested in awareness/wedge-detector.test.js
} = {}) {
const dispatches = [];
const ctx = {
bot,
snapshot,
busy,
currentActionLabel: null,
lastEatAt,
lastSleepAttemptAt,
lastCurriculumAt,
skillBackoff,
metrics,
disableManifesto,
disableAdvisor,
disableStoryline,
disableWedge,
dispatch(fn, label, opts = {}) {
dispatches.push({ fn, label, opts });
},
};
return { ctx, dispatches };
}
test("busy ctx returns skipped without dispatching", () => {
const { ctx, dispatches } = makeCtx({
snapshot: { connected: true, curriculum: { plan: { skillId: "gather.logs" } } },
busy: true,
currentActionLabel: "chopping",
});
const out = runTick(ctx);
assert.equal(out.reflex, "busy");
assert.equal(out.action, "skipped");
assert.equal(dispatches.length, 0);
});
test("disconnected snapshot → no dispatch", () => {
const { ctx, dispatches } = makeCtx({ snapshot: { connected: false } });
const out = runTick(ctx);
assert.equal(out, null);
assert.equal(dispatches.length, 0);
});
test("mode hit dispatches the returned skill immediately", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 4,
food: 10,
hasFood: true,
inventory: { bread: 1 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "mode:self_preservation");
assert.equal(out.action, "dispatched");
assert.equal(dispatches[0].label, "survive.eat");
});
test("defend wins over curriculum when hostile in melee", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
closestHostile: { name: "zombie", distance: 3 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "defend");
assert.match(dispatches[0].label, /attack zombie/);
});
test("defend attack does not report success while hostile remains nearby", async () => {
const bot = makeCombatBot();
const { ctx, dispatches } = makeCtx({
bot,
snapshot: {
connected: true,
health: 20,
closestHostile: { name: "zombie", distance: 3 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
ctx.defendAttackMaxSwings = 2;
ctx.defendAttackSettleMs = 0;
const out = runTick(ctx);
assert.equal(out.reflex, "defend");
const res = await dispatches[0].fn();
assert.equal(res.ok, false);
assert.equal(res.code, "hostile_still_near");
assert.equal(bot.attacks, 2);
});
test("defend flees after a verified attack leaves hostile in reach", () => {
const bot = makeCombatBot();
const { ctx, dispatches } = makeCtx({
bot,
snapshot: {
connected: true,
health: 20,
closestHostile: { name: "zombie", distance: 3 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const first = runTick(ctx);
assert.equal(first.reflex, "defend");
dispatches[0].opts.onComplete({ ok: false, code: "hostile_still_near" });
const second = runTick(ctx);
assert.equal(second.reflex, "defend");
assert.equal(second.kind, "defend-flee");
assert.equal(dispatches[1].label, "flee from zombie");
});
test("defend flees after repeated attack successes still leave hostile in reach", () => {
const bot = makeCombatBot();
const { ctx, dispatches } = makeCtx({
bot,
snapshot: {
connected: true,
health: 20,
closestHostile: { name: "zombie", distance: 3 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const first = runTick(ctx);
assert.equal(first.kind, "defend-attack");
dispatches[0].opts.onComplete({ ok: true, code: "done" });
const second = runTick(ctx);
assert.equal(second.kind, "defend-attack");
dispatches[1].opts.onComplete({ ok: true, code: "done" });
const third = runTick(ctx);
assert.equal(third.reflex, "defend");
assert.equal(third.kind, "defend-flee");
assert.equal(dispatches[2].label, "flee from zombie");
});
test("eat wins over curriculum when food low and bot has food in inventory", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 10,
// 2026-05-26: eat reflex now requires actual food in inventory
// to avoid the eat-spam loop that fired every tick on empty
// inventory.
inventory: { bread: 1 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "eat");
assert.equal(dispatches[0].label, "eat");
});
test("eat reflex does NOT dispatch when no food in inventory (no spam)", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 10,
inventory: { dirt: 1 },
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
// Falls through to curriculum.
assert.equal(out.reflex, "curriculum");
});
test("curriculum dispatches suggested skill by id", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(dispatches[0].label, "gather.logs");
assert.ok(typeof dispatches[0].opts.onComplete === "function");
});
test("manifesto: hungry bot with no food drives survive.acquire-food (manifesto fallback when storyline disabled)", () => {
const { ctx, dispatches } = makeCtx({
disableManifesto: false,
disableStoryline: true,
snapshot: {
connected: true,
health: 20,
food: 12,
hasFood: false,
inventory: {}, // no food, no tools
equipment: {},
nearbyBlocks: {},
hazards: { footBlock: "grass_block", belowBlock: "dirt", headBlock: "air" },
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(dispatches[0].label, "survive.acquire-food", "manifesto L1 food took over");
assert.equal(ctx.activeNeed?.need?.id, "food");
});
test("L0 manifesto emergency: defend/modes layer catches the threat BEFORE curriculum", () => {
// HP=4 + creeper@3m fires `modes` (self_preservation) or defendReflex
// before curriculum even runs — which is the right outcome: alive
// emergencies don't reach the storyline/manifesto branch at all.
const { ctx, dispatches } = makeCtx({
disableManifesto: false,
disableStoryline: false,
bot: { entities: { z1: { name: "creeper", height: 1.7, position: { x: 3, y: 64, z: 0, distanceTo: () => 3 } } }, entity: { position: { x: 0, y: 64, z: 0 } } },
snapshot: {
connected: true,
health: 4,
food: 12,
hasFood: false,
inventory: { oak_log: 10 },
equipment: {},
nearbyBlocks: { logs: 4 },
hazards: { footBlock: "grass_block", belowBlock: "dirt", headBlock: "air" },
closestHostile: { name: "creeper", distance: 3 },
threats: [{ name: "creeper", distance: 3, position: { x: 3, y: 64, z: 0 } }],
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.notEqual(out?.kind, "curriculum-skill", "an upstream reflex caught the emergency before curriculum");
});
test("storyline beats manifesto L1+ when both have suggestions", () => {
// Snapshot: well-fed (food=20 + 8 bread → manifesto L1 satisfied, L2
// tools_wood unmet) AND storyline orient_self complete (HP=20, blocks
// visible). Storyline should drive a wood-tier crafting step, not
// manifesto's gather.logs (which would also be valid but less concrete).
const { ctx, dispatches } = makeCtx({
disableManifesto: false,
disableStoryline: false,
snapshot: {
connected: true,
health: 20,
food: 20,
hasFood: true,
inventory: { bread: 8, oak_log: 10 }, // logs done, no planks
equipment: {},
nearbyBlocks: { logs: 3 },
hazards: { footBlock: "grass_block", belowBlock: "dirt", headBlock: "air" },
isDay: true,
_sessionMs: 60_000,
curriculum: { plan: { skillId: "explore.far" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
// Storyline step crafting_basics suggests craft.planks (10 logs, no planks yet).
assert.equal(dispatches[0].label, "craft.planks");
assert.equal(ctx.storyStep?.step?.id, "crafting_basics");
});
test("manifesto: well-fed bot with all wood tools defers to curriculum plan", () => {
const { ctx, dispatches } = makeCtx({
disableManifesto: false,
snapshot: {
connected: true,
health: 20,
food: 20,
hasFood: true,
inventory: {
bread: 8,
wooden_pickaxe: 1, wooden_axe: 1, wooden_sword: 1,
white_bed: 1,
},
equipment: {},
nearbyBlocks: { beds: 1 },
hazards: { footBlock: "grass_block", belowBlock: "dirt", headBlock: "air" },
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
// L4 tools_stone unmet → gather.stone takes precedence even if curriculum says logs
assert.equal(dispatches[0].label, "gather.stone");
assert.equal(ctx.activeNeed?.need?.id, "tools_stone");
});
test("curriculum falls back to wander when no plan", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: null,
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(dispatches[0].label, "wander");
});
test("curriculum falls back to wander when skill id is unknown", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "shelter.assemble" } }, // not registered yet
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.match(dispatches[0].label, /^wander/);
});
test("curriculum honours per-skill backoff", () => {
const future = Date.now() + 30_000;
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.stone" } },
},
skillBackoff: { "gather.stone": future },
});
const out = runTick(ctx);
// Backoff blocks the curriculum reflex; idle still won't fire on this
// tick (idleCounter not at the 20-tick mark) so runTick yields.
assert.equal(out, null);
assert.equal(dispatches.length, 0);
});
test("wander-hint backoff swaps skill for wander on the next tick", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
skillBackoff: { __wander_hint__: Date.now() + 30_000 },
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(dispatches[0].label, "wander");
});
test("recent repeated skill timeouts trigger metric recovery", () => {
const now = Date.now();
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
metrics: {
snapshot: () => ({
"gather.logs": { ok: 0, fail: 3, lastTs: now, lastCode: "timeout" },
}),
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(out.kind, "curriculum-metric-recovery");
assert.equal(dispatches[0].label, "explore.far");
assert.ok((ctx.skillBackoff?.["gather.logs"] ?? 0) > Date.now());
});
test("recent movement timeouts trigger tunnel recovery", () => {
const now = Date.now();
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
metrics: {
snapshot: () => ({
"explore.far": { ok: 0, fail: 1, lastTs: now, lastCode: "timeout" },
}),
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(out.kind, "curriculum-metric-recovery");
assert.equal(dispatches[0].label, "recovery.tunnel-out");
});
test("successful tunnel recovery clears movement-timeout trigger", () => {
const now = Date.now();
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
metrics: {
snapshot: () => ({
"explore.far": { ok: 0, fail: 1, lastTs: now - 5_000, lastCode: "timeout" },
"recovery.tunnel-out": { ok: 1, fail: 0, lastTs: now, lastCode: "done" },
}),
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(out.kind, "curriculum-skill");
assert.equal(dispatches[0].label, "gather.logs");
});
test("onComplete sets wander hint when skill recovery says so", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
});
runTick(ctx);
const cb = dispatches[0].opts.onComplete;
cb({ ok: false, code: "no_target", recovery: { hint: "wander" } });
assert.ok((ctx.skillBackoff?.__wander_hint__ ?? 0) > Date.now());
});
test("onComplete clears wander hint on success", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
skillBackoff: { __wander_hint__: Date.now() + 30_000 },
});
// With wander hint active, first tick will choose wander, not gather.logs.
runTick(ctx);
// Simulate the wander completing and clearing the hint manually since
// wander is dispatched via actions.js directly (no recover hint).
ctx.skillBackoff.__wander_hint__ = 0;
// Next tick — past the curriculum cooldown.
ctx.lastCurriculumAt = 0;
const { ctx: ctx2, dispatches: dispatches2 } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.logs" } },
},
});
runTick(ctx2);
dispatches2[0].opts.onComplete({ ok: true, code: "done" });
assert.equal(ctx2.skillBackoff.__wander_hint__, 0);
});
test("onComplete sets per-skill backoff on cooldown-class failures", () => {
const { ctx, dispatches } = makeCtx({
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: { plan: { skillId: "gather.stone" } },
},
});
runTick(ctx);
const cb = dispatches[0].opts.onComplete;
cb({ ok: false, code: "missing_tool", detail: "no pickaxe" });
assert.ok((ctx.skillBackoff?.["gather.stone"] ?? 0) > Date.now());
});