v0.3.0-rc.1: live skill registry + fast advisor scaffold
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>
This commit is contained in:
+14
-6
@@ -10,7 +10,8 @@
|
||||
// recall → behavioural change. Without this, the DB is just a log.
|
||||
|
||||
import { isAvailable as knowledgeAvailable, topAdvice, markApplied } from "../knowledge/index.js";
|
||||
import { info } from "../log.js";
|
||||
import { isRegistered } from "../skill-registry.js";
|
||||
import { info, warn } from "../log.js";
|
||||
|
||||
// Skills we will not blindly swap into — they require their own
|
||||
// preconditions (e.g. survive.flee needs a known threat direction).
|
||||
@@ -47,15 +48,19 @@ const MODE_TO_SKILL = Object.freeze({
|
||||
});
|
||||
|
||||
function normalisePreferSkill(raw) {
|
||||
if (!raw || typeof raw !== "string") return raw;
|
||||
if (SAFE_OVERRIDES.has(raw)) return raw;
|
||||
if (!raw || typeof raw !== "string") return null;
|
||||
if (SAFE_OVERRIDES.has(raw) && isRegistered(raw)) return raw;
|
||||
const lower = raw.toLowerCase().trim();
|
||||
if (MODE_TO_SKILL[lower]) return MODE_TO_SKILL[lower];
|
||||
// Pi sometimes writes "survive_flee" or "survive flee"; normalise.
|
||||
const dot = lower.replace(/[_\s]+/g, ".");
|
||||
if (SAFE_OVERRIDES.has(dot)) return dot;
|
||||
if (SAFE_OVERRIDES.has(dot) && isRegistered(dot)) return dot;
|
||||
if (MODE_TO_SKILL[dot]) return MODE_TO_SKILL[dot];
|
||||
return raw;
|
||||
// Anything else (Pi hallucinated names like "relocate.surface",
|
||||
// "choose.safe.surface", "survive.shelter", "gather.visible_log") —
|
||||
// hard reject. We'd rather fall through to 'avoid' / 'proceed' than
|
||||
// dispatch a nonexistent skill.
|
||||
return null;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -81,7 +86,7 @@ export function consult({ plannedSkillId, snapshot } = {}) {
|
||||
// avoid_skill matches?
|
||||
if (advice.avoid && advice.avoid === plannedSkillId) {
|
||||
const normalisedPrefer = normalisePreferSkill(advice.prefer);
|
||||
if (normalisedPrefer && SAFE_OVERRIDES.has(normalisedPrefer)) {
|
||||
if (normalisedPrefer && SAFE_OVERRIDES.has(normalisedPrefer) && isRegistered(normalisedPrefer)) {
|
||||
if (normalisedPrefer !== advice.prefer) {
|
||||
info("coach", `advice: normalised prefer "${advice.prefer}" → "${normalisedPrefer}"`);
|
||||
}
|
||||
@@ -93,6 +98,9 @@ export function consult({ plannedSkillId, snapshot } = {}) {
|
||||
lesson: advice.lesson,
|
||||
};
|
||||
}
|
||||
if (advice.prefer && !normalisedPrefer) {
|
||||
warn("coach", `advice: rejected hallucinated prefer_skill "${advice.prefer}" (lesson #${advice.lessonId})`);
|
||||
}
|
||||
info("coach", `advice: avoid ${plannedSkillId} (lesson #${advice.lessonId})`);
|
||||
return { action: "avoid", lessonId: advice.lessonId, lesson: advice.lesson };
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user