feat(knowledge): knowledge-refresh — living register, deterministic stale core + web poll (v5.7 Chunk 3)

The 'living' half of the v5.7 living knowledge base. Same hybrid split as the
optimization lens (Chunk 2b): a deterministic, byte-stable, unit-tested core +
a web/judgment command shell.

- scanners/lib/knowledge-refresh.mjs: pure assessFreshness(register,
  {referenceDate, staleAfterDays=90}) — age-based fresh/stale classification of
  source.verified; referenceDate injected (never reads the clock) → fully
  deterministic. 15 tests.
- scanners/knowledge-refresh-cli.mjs: -cli (NOT an orchestrated scanner →
  scanner count stays 15, suite byte-stable). Read-only — never writes the
  register, never hits the network. --reference-date/--stale-after/--dry-run,
  exit 0/1/3. 8 tests.
- commands/knowledge-refresh.md (opus): CLI stale-report → re-verify each stale
  entry by re-reading its source.url → poll CC changelog + Anthropic blog →
  apply ONLY human-approved writes, then re-validate the register. No unverified
  claim is ever auto-written (Verifiseringsplikt). Web-driven → not byte-stable.

No new agent, no new orchestrated scanner. Docs/badges: commands 19→20,
tests 1068→1091 (20 lib + 32 scanner test files). self-audit A/A, readmeCheck passed.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-06-21 19:22:57 +02:00
commit 0f9c091a14
7 changed files with 601 additions and 3 deletions

View file

@ -0,0 +1,103 @@
#!/usr/bin/env node
/**
* knowledge-refresh CLI feeds the v5.7 `/config-audit knowledge-refresh` command
* (Chunk 3: the "living" half of the living knowledge base).
*
* This is the DETERMINISTIC half of the hybrid motor: it loads the best-practices
* register and classifies every entry as `fresh` or `stale` by the age of its
* `source.verified` stamp (via the pure `assessFreshness` core). It is READ-ONLY
* it NEVER writes the register and NEVER touches the network. Candidate discovery
* (polling the CC changelog + Anthropic blog) and the human-approved writes live in
* the command layer (Verifiseringsplikt). `--dry-run` is implicit and the only mode;
* the flag is accepted for explicitness and echoed back.
*
* Naming: `-cli` suffix NOT an orchestrated scanner (the scan-orchestrator only
* loads scanner modules), so the scanner count is unchanged and the snapshot suite
* stays byte-stable.
*
* Usage:
* node knowledge-refresh-cli.mjs [--output-file <path>] [--stale-after <N>]
* [--reference-date <YYYY-MM-DD>] [--dry-run]
*
* Exit codes: 0 = every entry fresh, 1 = one or more stale (advisory), 3 = error.
*/
import { resolve } from 'node:path';
import { writeFile } from 'node:fs/promises';
import { loadRegister, REGISTER_PATH } from './lib/best-practices-register.mjs';
import { assessFreshness, STALE_AFTER_DAYS_DEFAULT } from './lib/knowledge-refresh.mjs';
const DATE_RE = /^\d{4}-\d{2}-\d{2}$/;
function fail(message) {
process.stderr.write(`Error: ${message}\n`);
process.exit(3);
}
async function main() {
const args = process.argv.slice(2);
let outputFile = null;
let staleAfterDays = STALE_AFTER_DAYS_DEFAULT;
let referenceDate = null; // null → today
let dryRun = false;
for (let i = 0; i < args.length; i++) {
const a = args[i];
if (a === '--dry-run') dryRun = true;
else if (a === '--output-file' && args[i + 1]) outputFile = args[++i];
else if (a === '--stale-after' && args[i + 1] !== undefined) {
const n = Number.parseInt(args[++i], 10);
if (!Number.isInteger(n) || n < 0) fail('--stale-after must be a non-negative integer (days)');
staleAfterDays = n;
} else if (a === '--reference-date' && args[i + 1]) {
referenceDate = args[++i];
if (!DATE_RE.test(referenceDate)) fail('--reference-date must be YYYY-MM-DD');
}
}
// The clock is read here ONLY — the core takes an injected date and stays pure.
const ref = referenceDate || new Date();
let register;
try {
register = loadRegister();
} catch (err) {
fail(`could not load register at ${REGISTER_PATH}: ${err.message}`);
}
let assessment;
try {
assessment = assessFreshness(register, { referenceDate: ref, staleAfterDays });
} catch (err) {
fail(err.message);
}
const payload = {
status: 'ok',
registerPath: REGISTER_PATH,
version: register.version,
dryRun: true, // this CLI never writes; the flag is informational
requestedDryRun: dryRun,
referenceDate: assessment.referenceDate,
staleAfterDays: assessment.staleAfterDays,
counts: assessment.counts,
stale: assessment.stale,
fresh: assessment.fresh,
};
const json = JSON.stringify(payload, null, 2);
if (outputFile) await writeFile(outputFile, json, 'utf-8');
else process.stdout.write(json + '\n');
process.exit(assessment.counts.stale > 0 ? 1 : 0);
}
const isDirectRun =
process.argv[1] && resolve(process.argv[1]) === resolve(new URL(import.meta.url).pathname);
if (isDirectRun) {
main().catch((err) => {
process.stderr.write(`Fatal: ${err.message}\n`);
process.exit(3);
});
}

View file

@ -0,0 +1,94 @@
/**
* knowledge-refresh deterministic freshness core for the best-practices register.
*
* The "living" half of the v5.7 living knowledge base (Chunk 3). This module is the
* PURE, deterministic part of the hybrid `/config-audit knowledge-refresh` motor: given a
* register and an injected reference date, it classifies each entry as `fresh` or `stale`
* by the age of its `source.verified` stamp. It NEVER touches the network and NEVER writes
* candidate discovery (polling CC changelog + Anthropic blog) and the human-approved
* writes live in the command layer (Verifiseringsplikt: no unverified claim is auto-written).
*
* `referenceDate` is injected (not read from the clock here) so the function is fully
* deterministic and unit-testable; the CLI passes today's date. See
* docs/v5.7-optimization-lens-plan.md.
*/
/** Default re-verify cadence: a confirmed best-practice older than this needs a re-check. */
export const STALE_AFTER_DAYS_DEFAULT = 90;
const DATE_RE = /^\d{4}-\d{2}-\d{2}$/;
const DAY_MS = 86_400_000;
/**
* Normalize a reference date (Date or YYYY-MM-DD string) to a UTC-midnight {iso, ms}.
* Throws TypeError on anything else the reference date is required and must be valid.
*/
function normalizeReferenceDate(value) {
let iso;
if (value instanceof Date) {
if (Number.isNaN(value.getTime())) throw new TypeError('referenceDate is an invalid Date');
iso = value.toISOString().slice(0, 10);
} else if (typeof value === 'string' && DATE_RE.test(value)) {
iso = value;
} else {
throw new TypeError('referenceDate must be a Date or a YYYY-MM-DD string');
}
const ms = Date.parse(`${iso}T00:00:00Z`);
if (Number.isNaN(ms)) throw new TypeError(`referenceDate is not a real calendar date: ${iso}`);
return { iso, ms };
}
/** Parse an entry's `source.verified` to UTC-midnight ms, or null if missing/unparseable. */
function verifiedMs(entry) {
const v = entry && entry.source && entry.source.verified;
if (typeof v !== 'string' || !DATE_RE.test(v)) return null;
const ms = Date.parse(`${v}T00:00:00Z`);
return Number.isNaN(ms) ? null : ms;
}
/**
* Classify every register entry as fresh or stale by the age of its source.verified stamp.
*
* @param {{entries:object[]}} register
* @param {{ referenceDate: string|Date, staleAfterDays?: number }} opts
* @returns {{
* referenceDate: string,
* staleAfterDays: number,
* stale: Array<{id:string, verified:string|undefined, ageDays:number|null, url:string|undefined, claim:string|undefined}>,
* fresh: Array<{id:string, verified:string|undefined, ageDays:number}>,
* counts: { total:number, stale:number, fresh:number }
* }}
*/
export function assessFreshness(register, opts = {}) {
const ref = normalizeReferenceDate(opts.referenceDate);
const staleAfterDays =
typeof opts.staleAfterDays === 'number' ? opts.staleAfterDays : STALE_AFTER_DAYS_DEFAULT;
const entries = (register && Array.isArray(register.entries)) ? register.entries : [];
const stale = [];
const fresh = [];
for (const e of entries) {
const verified = e && e.source ? e.source.verified : undefined;
const vms = verifiedMs(e);
if (vms === null) {
// No re-checkable date → needs attention. Stale with ageDays null.
stale.push({ id: e && e.id, verified, ageDays: null, url: e && e.source && e.source.url, claim: e && e.claim });
continue;
}
const ageDays = Math.floor((ref.ms - vms) / DAY_MS);
if (ageDays > staleAfterDays) {
stale.push({ id: e.id, verified, ageDays, url: e.source && e.source.url, claim: e.claim });
} else {
fresh.push({ id: e.id, verified, ageDays });
}
}
return {
referenceDate: ref.iso,
staleAfterDays,
stale,
fresh,
counts: { total: entries.length, stale: stale.length, fresh: fresh.length },
};
}