Files
pepa-pi-bot/runtime/goal/village-score.test.js
T
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

53 lines
1.8 KiB
JavaScript

import { test } from "node:test";
import assert from "node:assert/strict";
import { computeVillageScore, _internal } from "./village-score.js";
function snap(extra = {}) {
return { connected: true, health: 20, food: 20, hasFood: false, locations: {}, ...extra };
}
test("empty/fresh world scores low", () => {
const r = computeVillageScore(snap({ health: 20, food: 5 }), {
contract: { completed: 0, total: 10 },
uptimeMs: 0,
metrics: {},
});
assert.ok(r.score < 0.2, `expected low score, got ${r.score}`);
});
test("a fully established settlement scores high", () => {
const metrics = {};
for (let i = 0; i < 12; i++) metrics[`skill.${i}`] = { ok: 3, fail: 0 };
const r = computeVillageScore(
snap({ health: 20, food: 20, hasFood: true, locations: { base: {}, shelter: {}, chest: {} } }),
{ contract: { completed: 10, total: 10 }, uptimeMs: 3 * 60 * 60 * 1000, metrics },
);
assert.ok(r.score > 0.9, `expected high score, got ${r.score}`);
assert.equal(r.components.milestones, 1);
assert.equal(r.components.base, 1);
});
test("score is monotonic in milestone completion", () => {
const base = { uptimeMs: 0, metrics: {} };
const low = computeVillageScore(snap(), { ...base, contract: { completed: 1, total: 10 } });
const high = computeVillageScore(snap(), { ...base, contract: { completed: 8, total: 10 } });
assert.ok(high.score > low.score);
});
test("score stays within 0..1", () => {
const r = computeVillageScore(snap({ health: 999, food: 999 }), {
contract: { completed: 100, total: 10 },
uptimeMs: 1e12,
metrics: { a: { ok: 999 } },
});
assert.ok(r.score >= 0 && r.score <= 1);
});
test("clamp01 helper", () => {
assert.equal(_internal.clamp01(-1), 0);
assert.equal(_internal.clamp01(2), 1);
assert.equal(_internal.clamp01(0.5), 0.5);
assert.equal(_internal.clamp01(NaN), 0);
});