Files
pepa-pi-bot/runtime/skills/contract.test.js
T
mayatnikovandClaude Opus 4.7 0834bb6b73 feat(runtime): skill substrate + dynamic groups + reference skills (Phase 2)
Phase 2 of plans/autonomous-survival-bot-prd.md. Establishes the
composable skill contract from PRD §5.2 and ports three reference
skills so future phases can layer survival behaviour on top instead of
adding more ad-hoc branches to reflex.js.

New: runtime/skills/
- index.js: skill registry + runSkill(id, ctx, args) wrapper. Enforces
  preconditions, hard timeout, normalises {ok, code, detail, worldDelta}
  on every result, runs validate() and calls recover() on failure.
  Stable failure codes live in RUNNER_CODES (unknown_skill,
  precondition_failed, timeout, threw, validation_failed, done).
- groups.js: registry-derived item/block sets — logs/planks/sticks/beds
  derived by suffix; foods intersects a curated allowlist with the live
  bot.registry; axes/pickaxes/swords scoped to whatever the connected
  server's item table actually ships. Empty set instead of throwing on
  missing registry, so skills can emit code:"unsupported_version".
- chop-logs.js: gather.logs reference skill (wraps chopNearestTree).
- eat.js: survive.eat (wraps eatBestFood, preconditions check carrying
  edible food from the registry-derived set).
- wander.js: explore.wander (wraps wander).
- contract.test.js + groups.test.js: 14 tests covering precondition
  gating, timeout firing recover(), execute exceptions, validate
  flipping ok→false, dynamic group filtering across mock registries.

package.json: `npm test` runs the new contract + groups suites.
docs/runtime.md: documents the skill contract, runner, dynamic groups
and the reference skills.

Reflex.js still calls actions.js directly — wiring the scheduler to
runSkill() lands in later phases when the survival curriculum kicks in.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 22:15:24 +03:00

158 lines
4.4 KiB
JavaScript

// Contract tests for runtime/skills/index.js. Run with: node --test runtime/skills
//
// We avoid spinning up a real mineflayer bot — synthetic skills are
// registered via _registerForTest and exercise every branch of runSkill:
// preconditions, timeout, exception, validate, recover.
import { test } from "node:test";
import assert from "node:assert/strict";
import { runSkill, RUNNER_CODES, _registerForTest } from "./index.js";
const ctx = {}; // skills under test ignore ctx fully
test("unknown skill returns unknown_skill code", async () => {
const res = await runSkill("does.not.exist", ctx);
assert.equal(res.ok, false);
assert.equal(res.code, RUNNER_CODES.UNKNOWN_SKILL);
});
test("preconditions gate execution", async () => {
const teardown = _registerForTest({
id: "test.precondition-block",
title: "blocked",
timeoutMs: 1000,
preconditions: () => ({ ok: false, code: "missing_x", detail: "no x" }),
execute: async () => {
throw new Error("should not run");
},
});
try {
const res = await runSkill("test.precondition-block", ctx);
assert.equal(res.ok, false);
assert.equal(res.code, "missing_x");
assert.equal(res.detail, "no x");
} finally {
teardown();
}
});
test("preconditions that throw produce precondition_failed", async () => {
const teardown = _registerForTest({
id: "test.precondition-throw",
preconditions: () => {
throw new Error("kaboom");
},
execute: async () => ({ ok: true }),
});
try {
const res = await runSkill("test.precondition-throw", ctx);
assert.equal(res.ok, false);
assert.equal(res.code, RUNNER_CODES.PRECONDITION_FAILED);
assert.match(res.detail, /kaboom/);
} finally {
teardown();
}
});
test("timeout fires and recover is called", async () => {
let recovered = false;
const teardown = _registerForTest({
id: "test.timeout",
timeoutMs: 50,
preconditions: () => ({ ok: true }),
execute: () =>
new Promise((resolve) => {
// never resolves within the timeout
setTimeout(() => resolve({ ok: true }), 500);
}),
recover: () => {
recovered = true;
return { hint: "retry-later" };
},
});
try {
const res = await runSkill("test.timeout", ctx);
assert.equal(res.ok, false);
assert.equal(res.code, RUNNER_CODES.TIMEOUT);
assert.equal(recovered, true);
assert.deepEqual(res.recovery, { hint: "retry-later" });
} finally {
teardown();
}
});
test("execute throw -> threw code with recovery hint", async () => {
const teardown = _registerForTest({
id: "test.throws",
preconditions: () => ({ ok: true }),
execute: async () => {
throw new Error("oops");
},
recover: (ctx, result) => ({ saw: result.code }),
});
try {
const res = await runSkill("test.throws", ctx);
assert.equal(res.ok, false);
assert.equal(res.code, RUNNER_CODES.THREW);
assert.match(res.detail, /oops/);
assert.deepEqual(res.recovery, { saw: RUNNER_CODES.THREW });
} finally {
teardown();
}
});
test("happy path returns done with worldDelta", async () => {
const teardown = _registerForTest({
id: "test.happy",
preconditions: () => ({ ok: true }),
execute: async () => ({ ok: true, code: "done", detail: { count: 4 }, worldDelta: { gathered: 4 } }),
});
try {
const res = await runSkill("test.happy", ctx);
assert.equal(res.ok, true);
assert.equal(res.code, "done");
assert.deepEqual(res.worldDelta, { gathered: 4 });
} finally {
teardown();
}
});
test("validate failure flips ok to false with validation_failed", async () => {
let recoverArgs = null;
const teardown = _registerForTest({
id: "test.validate-fail",
preconditions: () => ({ ok: true }),
execute: async () => ({ ok: true, code: "done", worldDelta: { x: 1 } }),
validate: () => false,
recover: (ctx, result) => {
recoverArgs = result;
return null;
},
});
try {
const res = await runSkill("test.validate-fail", ctx);
assert.equal(res.ok, false);
assert.equal(res.code, RUNNER_CODES.VALIDATION_FAILED);
assert.ok(recoverArgs);
assert.equal(recoverArgs.code, RUNNER_CODES.VALIDATION_FAILED);
} finally {
teardown();
}
});
test("result missing code defaults to runner DONE on success", async () => {
const teardown = _registerForTest({
id: "test.no-code",
preconditions: () => ({ ok: true }),
execute: async () => ({ ok: true }),
});
try {
const res = await runSkill("test.no-code", ctx);
assert.equal(res.ok, true);
assert.equal(res.code, RUNNER_CODES.DONE);
} finally {
teardown();
}
});