mayatnikovandClaude Opus 4.8
cd63edfeaf
Patches each link of the closed-loop chain (world-truth -> invariant -> dispatch -> worldDelta -> milestone) so the contract can no longer advance on a lie or stall on an unreachable milestone, and surfaces the result on the monitor. - Unblock M6_lighting: add gather.coal producer (mirrors gather.stone, strict expectGain), register it, add the skill-graph node, and make curriculum.shelter.torch two-step (gather coal -> craft torch). craft.torch needed coal but no skill produced it, so the contract pinned on M6 forever and starved M7/M8/M9. One curriculum edit fixes both rails. - M8 no longer falsely satisfied: build-shelter records locations.shelter only on real progress (setLocation moved below the no_progress guard). - M2_bed made monotonic: sleepInBed writes locations.bed when the bot places its own bed, so M2 stays met after the carried bed item is consumed. - Observability: new ink-free tui/format.js helper renders per-tick state / firing rail / active skill / blocked prerequisite / stall reason in the monitor header (fields bot.js already computes but never showed). - Harden the valid-skill-id guardrail: skillRegistryPrompt preserves the "NEVER invent" footer when truncating (a growing registry was dropping it), and fix the stale "tech-tree > autonomous" reflex chain in the escalation prompt. Tests: 494/494 passing; new build-shelter / invariants / format suites plus skill-graph, curriculum, skill-registry cases. lint-patch clean. Deferred audit findings recorded in plans/v0.4.0-vnext.md (local). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
76 lines
2.7 KiB
JavaScript
76 lines
2.7 KiB
JavaScript
import { test } from "node:test";
|
|
import assert from "node:assert/strict";
|
|
|
|
import {
|
|
listSkillIds,
|
|
isRegistered,
|
|
describeSkill,
|
|
skillRegistryPrompt,
|
|
} from "./skill-registry.js";
|
|
|
|
test("registry: lists at least the known v0.2 skill set", () => {
|
|
const ids = listSkillIds();
|
|
assert.ok(ids.length >= 20, `expected 20+ skills, got ${ids.length}`);
|
|
for (const must of [
|
|
"gather.logs",
|
|
"survive.eat",
|
|
"survive.sleep",
|
|
"survive.flee",
|
|
"survive.pillar-up",
|
|
"explore.far",
|
|
"explore.wander",
|
|
"recovery.tunnel-out",
|
|
"village.choose-base",
|
|
"village.build-shelter",
|
|
]) {
|
|
assert.ok(ids.includes(must), `registry missing ${must}`);
|
|
}
|
|
});
|
|
|
|
test("isRegistered: true for real, false for hallucinated", () => {
|
|
assert.equal(isRegistered("survive.flee"), true);
|
|
assert.equal(isRegistered("relocate.surface"), false);
|
|
assert.equal(isRegistered("choose.safe.surface"), false);
|
|
assert.equal(isRegistered("gather.visible_log"), false);
|
|
assert.equal(isRegistered("survive.shelter"), false);
|
|
assert.equal(isRegistered("tunnel-out"), false, "missing recovery. prefix");
|
|
assert.equal(isRegistered(null), false);
|
|
assert.equal(isRegistered(""), false);
|
|
assert.equal(isRegistered(42), false);
|
|
});
|
|
|
|
test("describeSkill: returns shape for known id", () => {
|
|
const s = describeSkill("survive.pillar-up");
|
|
assert.ok(s, "expected description");
|
|
assert.equal(s.id, "survive.pillar-up");
|
|
assert.ok(typeof s.timeoutMs === "number" && s.timeoutMs > 0);
|
|
});
|
|
|
|
test("registryPrompt: contains the real ids grouped by namespace", () => {
|
|
const txt = skillRegistryPrompt();
|
|
assert.match(txt, /Valid skill ids/);
|
|
assert.match(txt, /survive:/);
|
|
assert.match(txt, /- survive\.flee/);
|
|
assert.match(txt, /- recovery\.tunnel-out/);
|
|
assert.match(txt, /NEVER invent/);
|
|
// must NOT contain hallucinated ids
|
|
assert.doesNotMatch(txt, /relocate\.surface/);
|
|
assert.doesNotMatch(txt, /survive\.shelter[^-]/);
|
|
});
|
|
|
|
test("registryPrompt: respects limit and preserves the NEVER-invent guardrail when truncating", () => {
|
|
const short = skillRegistryPrompt({ limit: 200 });
|
|
assert.ok(short.length <= 200, `expected <=200, got ${short.length}`);
|
|
// The skill LIST is truncated (…), but the guardrail footer must always
|
|
// survive — otherwise a growing registry silently stops telling the LLM
|
|
// not to hallucinate skill ids.
|
|
assert.match(short, /\.\.\./, "list should be truncated");
|
|
assert.match(short, /NEVER invent/, "guardrail footer must survive truncation");
|
|
});
|
|
|
|
test("registryPrompt: default limit fits the full registry incl. the guardrail footer", () => {
|
|
const full = skillRegistryPrompt();
|
|
assert.match(full, /NEVER invent/);
|
|
assert.doesNotMatch(full, /\n\.\.\.\n/, "default prompt should not be truncated");
|
|
});
|