Files
c910457817 v0.4.0 vNext — closed-loop world model + settlement contract (#29)
* feat(v0.4.0): vNext — closed-loop world model + settlement contract

Implements the vNext architecture from the research doc: demote the noisy
multi-rail planner in favour of a closed loop (world truth → invariant check)
plus a single utility-driven goal authority.

L1 services (fix no_drop / silent pathfinder hang first):
- InventoryLedger: diff-based "did I actually get it" verifier; acquire-food
  now confirms via ledger.gainedSince instead of the unreliable count/event.
- MotionService.gotoSafe: wall-clock timeout + progress watchdog +
  path_update(noPath/timeout) → structured {reached|stuck|timeout|nopath}.

L3 plan — unify the three competing rails (curriculum/manifesto/storyline):
- Settlement Contract: ordered M0–M9 milestones, each invariant-checked
  against an authoritative world view (early steps delegate to the proven
  curriculum; late game adds farming).
- InvariantChecker + predicate library; GoalManager selects the lowest unmet
  milestone via utility argmax (food-urgency preempts, DEPS-style).
- Wired into the scheduler: bot.js precomputes snapshot.contract; reflex.js
  consumes it in place of the storyline rail. Manifesto L0 still preempts.

Eval + robustness:
- Village Score (single 0..1 metric) on the snapshot + TUI "build" line.
- survive.dig-in skill + dusk_dig_in mode (exposed at night, no bed → cover).
- approach_block helper (GoalNear + lookAt, avoids GoalLookAtBlock #341).

+28 new tests (450 total green). LLM remains entirely off the tick path.

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

* feat(v0.4.0): finish vNext plan — anti-loop, skill-graph, worldDelta diff, flee→motion

Completes the remaining v0.4.0 plan items and one fix motivated by a live
in-game observation (flee hanging 30s against a persistent zombie).

- flee → MotionService.gotoSafe: structured {stuck|timeout|nopath} in ~4s with
  a blind-retreat fallback, instead of the observed 30s pathfinder hang + 3
  watchdog replans. Movements setup guarded so it is unit-testable.
- QW5 anti-loop (runtime/anti-loop.js): same skill failing >=3x in 5min →
  30min blacklist (reflex shouldSkip) + one-shot improvement_request
  (bot.js drainFired -> writeProposal).
- 4.1 closed-loop worldDelta: runSkill snapshots inventory before execute and
  attaches the real delta (_invObserved) to every successful result; opt-in
  skill.expectGain asserts the claimed gain or returns world_unchanged.
- 3.6 skill-graph (Plan4MC): declarative requires/produces for ~20 skills;
  prerequisitesMet/canRun/runnableFrontier; GoalManager annotates suggestions
  with blockedBy when prereqs are unmet.

+22 tests (472 total green). Live smoke confirmed dig-in works and no new
errors; flee loop is what this commit's flee migration addresses.

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>
2026-05-28 11:29:39 +03:00

614 lines
18 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
disableContract = true, // contract path tested below + goal-manager.test.js
} = {}) {
const dispatches = [];
const ctx = {
bot,
snapshot,
busy,
currentActionLabel: null,
lastEatAt,
lastSleepAttemptAt,
lastCurriculumAt,
skillBackoff,
metrics,
disableManifesto,
disableAdvisor,
disableStoryline,
disableWedge,
disableContract,
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 visible food drives survive.scout-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.scout-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());
});
// ---- v0.4.0 Settlement Contract integration --------------------------------
test("contract suggestion drives dispatch (beats curriculum plan)", () => {
const { ctx, dispatches } = makeCtx({
disableContract: false,
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
// curriculum (legacy) would say gather.logs; the contract says farm.
curriculum: { plan: { skillId: "gather.logs" } },
contract: {
done: false,
milestone: { id: "M9_farm", title: "Start a wheat farm" },
suggestedSkill: { skillId: "farm.wheat" },
},
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(dispatches[0].label, "farm.wheat");
assert.equal(out.source, "contract:M9_farm");
});
test("contract dispatches even when curriculum plan is exhausted (no wander)", () => {
const { ctx, dispatches } = makeCtx({
disableContract: false,
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: null, // curriculum exhausted
contract: {
done: false,
milestone: { id: "M9_farm", title: "Start a wheat farm" },
suggestedSkill: { skillId: "farm.wheat" },
},
},
});
const out = runTick(ctx);
assert.equal(dispatches[0].label, "farm.wheat");
});
test("contract done → falls through to wander when nothing else suggests", () => {
const { ctx, dispatches } = makeCtx({
disableContract: false,
snapshot: {
connected: true,
health: 20,
food: 20,
isDay: true,
curriculum: null,
contract: { done: true, milestone: null, suggestedSkill: null },
},
});
const out = runTick(ctx);
assert.equal(out.reflex, "curriculum");
assert.equal(dispatches[0].label, "wander");
});