mayatnikovandClaude Opus 4.7
fcfa2277ba
Roots out the v0.2.x failure mode: Pi-extracted lessons routinely named
hallucinated skill ids (relocate.surface, choose.safe.surface,
survive.shelter, gather.visible_log, …). All 47 Pi-lessons in the live DB
had applied_count=0 because normalisePreferSkill couldn't find them.
Fix:
1. runtime/skill-registry.js — single source of truth derived from
skills/index.js. Exports listSkillIds, isRegistered, and a
prompt-ready block (skillRegistryPrompt) grouped by namespace.
2. Pi prompts (coach/postmortem, coach/reflect) embed the live registry
with a "USE ONLY THESE, never invent" instruction. Lessons are
filtered at write-time too — anything not in the registry and not a
known mode name gets dropped.
3. coach/advice.js — normalisePreferSkill now returns null for unknown
ids, hardening consult() against any hallucinations that slip
through. Warn-logged for visibility.
Also lays the LLM substrate for the rest of v0.3.0:
- runtime/llm/provider.js — OpenAI-compatible chat client. Configured
via PEPA_FAST_LLM_{BASE_URL,API_KEY,MODEL,TIMEOUT_MS}. Safe no-op
unless API_KEY is set. Supports JSON-mode.
- runtime/coach/fast-advisor.js — tactical advisor tier (scaffold).
Exposes advise() that asks the fast LLM what to do RIGHT NOW when
the reflex is wedged/stuck. Rejects hallucinated skill ids using the
registry. Rate-limited 6/h, 30s cooldown. Not auto-triggered yet —
wired into reflex in rc.3 (awareness layer).
Tests: 279 green (+24 vs rc.3): 5 registry, 9 provider, 10 advisor.
See dev/v0.3.0/PLAN.md for the full iteration design (manifesto needs
ladder, event-driven awareness, skill pre-emption) and STATUS.md for
shipped/pending tracking.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
66 lines
2.1 KiB
JavaScript
66 lines
2.1 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 parameter", () => {
|
|
const short = skillRegistryPrompt({ limit: 200 });
|
|
assert.ok(short.length <= 200, `expected <=200, got ${short.length}`);
|
|
assert.ok(short.endsWith("..."));
|
|
});
|