feat(ms-ai-architect): Sesjon 6 - lag 3 verifisering-INN (authority-binding)
Lag 3 etablerer per-fil autoritetsbinding som mater verify-out regel 3 (autoritets-mismatch — regresjonens rotårsak, inert til nå pga 0% dekning). Designvalg (operatør 2026-06-19): HEADER-AS-TRUTH — en fils **Source:**-header ER den utpekte autoriteten. Gjetter ALDRI fra siterte URLer (251/303 filer siterer 4-10 → gjetning ville fått regel 3 til å bomme + 303 operatør-beslutninger = primær-fallgruven). - lib/authority.mjs (ren lib, SKRIVER ALDRI; kun read-only kb-headers+url-normalize): resolveAuthority (validert http(s); fri tekst avvist; ikke-MS-autoritet som EU-forordning tillatt), collectDeclaredSources (normalisert Set), markUrlAuthority, authorityCoverage. - build-registry: recomputer authority_source per URL-entry fra headere (ikke carry-over) + dekningslogg. - commands/kb-update.md §4 c1: authority_source=resolveAuthority(fil) → lag-5 c2. TDD: 11 tester FØR kode inkl. import-invariant + ende-til-ende regel 3 (source_url ≠ header-autoritet → flagged). Tester: validate 239 · kb-update 122 (+11) · kb-eval 15 · kb-integrity 115/115. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
This commit is contained in:
parent
3ed32c343c
commit
e42a84fb7b
4 changed files with 243 additions and 10 deletions
|
|
@ -9,7 +9,7 @@ import { join, relative, dirname } from 'node:path';
|
|||
import { fileURLToPath } from 'node:url';
|
||||
import { normalizeUrl, extractUrls } from './lib/url-normalize.mjs';
|
||||
import { loadRegistry, saveRegistry } from './lib/registry-io.mjs';
|
||||
import { parseSourceHeader } from './lib/kb-headers.mjs';
|
||||
import { resolveAuthority, markUrlAuthority } from './lib/authority.mjs';
|
||||
|
||||
const __dirname = dirname(fileURLToPath(import.meta.url));
|
||||
const PLUGIN_ROOT = join(__dirname, '..', '..');
|
||||
|
|
@ -36,6 +36,7 @@ const existing = merge ? loadRegistry() : null;
|
|||
const urlToFiles = new Map(); // normalizedUrl → Set<relativePath>
|
||||
let totalFiles = 0;
|
||||
let filesWithSourceHeader = 0; // coverage of the optional **Source:** authority header
|
||||
const declaredSources = new Set(); // normalized authority URLs declared by files (lag 3)
|
||||
|
||||
const skillDirs = readdirSync(SKILLS_DIR, { withFileTypes: true })
|
||||
.filter(d => d.isDirectory())
|
||||
|
|
@ -51,10 +52,15 @@ for (const skill of skillDirs) {
|
|||
const urls = extractUrls(content);
|
||||
const relPath = relative(PLUGIN_ROOT, file);
|
||||
|
||||
// Read the optional **Source:**/**Primary source:** authority header.
|
||||
// 0% coverage today; tracked here so we can populate authority_source as
|
||||
// files adopt it (population semantics designed in the verification layer).
|
||||
if (parseSourceHeader(content)) filesWithSourceHeader++;
|
||||
// Lag 3 (header-as-truth): the **Source:** header is the file's declared
|
||||
// authority. Collect declared sources (normalized) so each URL entry can be
|
||||
// marked as a designated authority below.
|
||||
const authority = resolveAuthority(content);
|
||||
if (authority) {
|
||||
filesWithSourceHeader++;
|
||||
const n = normalizeUrl(authority);
|
||||
if (n) declaredSources.add(n);
|
||||
}
|
||||
|
||||
for (const url of urls) {
|
||||
if (!urlToFiles.has(url)) urlToFiles.set(url, new Set());
|
||||
|
|
@ -79,9 +85,10 @@ for (const [url, files] of urlToFiles) {
|
|||
sitemap_lastmod: prev?.sitemap_lastmod || null,
|
||||
reference_files: [...files].sort(),
|
||||
status: prev?.status || 'unpolled',
|
||||
// Reserved schema (lag 0): authority_source = declared verification source
|
||||
// (**Source:** header, 0% coverage today); course = Learn course-track ref.
|
||||
authority_source: prev?.authority_source ?? null,
|
||||
// Lag 3: authority_source = this URL iff a file declares it as its **Source:**
|
||||
// (a designated authority), else null. Recomputed from headers (truth), not
|
||||
// carried over. course = Learn course-track ref (reserved).
|
||||
authority_source: markUrlAuthority(url, declaredSources),
|
||||
course: prev?.course ?? null,
|
||||
};
|
||||
}
|
||||
|
|
@ -93,6 +100,8 @@ const multiRef = [...urlToFiles.values()].filter(s => s.size > 1).length;
|
|||
console.log(`Registry built: ${urlToFiles.size} unique URLs from ${totalFiles} files`);
|
||||
console.log(` URLs referenced by multiple files: ${multiRef}`);
|
||||
console.log(` Files declaring **Source:** header: ${filesWithSourceHeader}/${totalFiles}`);
|
||||
const authMarked = Object.values(registry.urls).filter(e => e.authority_source).length;
|
||||
console.log(` URL entries marked as authority_source: ${authMarked}/${urlToFiles.size}`);
|
||||
if (merge && existing?.urls) {
|
||||
const newUrls = [...urlToFiles.keys()].filter(u => !existing.urls[u]).length;
|
||||
console.log(` New URLs added (merge): ${newUrls}`);
|
||||
|
|
|
|||
80
scripts/kb-update/lib/authority.mjs
Normal file
80
scripts/kb-update/lib/authority.mjs
Normal file
|
|
@ -0,0 +1,80 @@
|
|||
// authority.mjs — Lag 3: VERIFISERING-INN. Establishes the per-file authority
|
||||
// binding that feeds verify-out rule 3 (authority mismatch — the regression's
|
||||
// root cause) and build-registry's per-URL authority_source field.
|
||||
//
|
||||
// Design (operatør-valg 2026-06-19): HEADER-AS-TRUTH. A file's **Source:** header
|
||||
// IS the designated authority for that file's claims — full stop. We never GUESS
|
||||
// an authority from a file's many cited URLs (251/303 files cite 4–10 URLs, so a
|
||||
// derivation would be a guess, and a wrong authority makes rule 3 misfire). Coverage
|
||||
// grows as files adopt the header (lag 4 writes it for every regenerated file).
|
||||
//
|
||||
// Pure lib (mirrors decisions-io / verify-out / transform): the only imports are
|
||||
// read-only sibling parsers (kb-headers, url-normalize). It NEVER writes.
|
||||
|
||||
import { parseSourceHeader } from './kb-headers.mjs';
|
||||
import { normalizeUrl } from './url-normalize.mjs';
|
||||
|
||||
const RE_HTTP_URL = /^https?:\/\/\S+$/i;
|
||||
|
||||
/**
|
||||
* The designated authority for a file's claims = its declared **Source:** header,
|
||||
* IF that value is a real http(s) URL. A free-text "source" is not an authority
|
||||
* binding (verifiseringsplikt: no guessed authority). The URL is returned as
|
||||
* declared (not normalized) — it may legitimately be a non-Microsoft authority
|
||||
* (e.g. an EU regulation for a governance file); verify-out normalizes when it
|
||||
* compares. Returns null when absent or not a URL.
|
||||
* @param {string} content — full reference-file content (header scanned)
|
||||
* @returns {string|null}
|
||||
*/
|
||||
export function resolveAuthority(content) {
|
||||
const src = parseSourceHeader(content);
|
||||
if (!src) return null;
|
||||
return RE_HTTP_URL.test(src.trim()) ? src.trim() : null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Collect the set of declared authority sources across many files, normalized to
|
||||
* match registry keys. Only learn.microsoft.com authorities survive normalization
|
||||
* (normalizeUrl returns null otherwise) — which is correct, since the registry
|
||||
* only tracks Microsoft Learn URLs. A non-MS authority is a valid per-file binding
|
||||
* but is simply not a tracked registry entry to mark.
|
||||
* @param {string[]} contents — reference-file contents
|
||||
* @returns {Set<string>} normalized declared-source URLs
|
||||
*/
|
||||
export function collectDeclaredSources(contents) {
|
||||
const set = new Set();
|
||||
for (const c of contents || []) {
|
||||
const a = resolveAuthority(c);
|
||||
if (!a) continue;
|
||||
const n = normalizeUrl(a);
|
||||
if (n) set.add(n);
|
||||
}
|
||||
return set;
|
||||
}
|
||||
|
||||
/**
|
||||
* The authority_source value for a registry URL entry: the URL itself when some
|
||||
* file declares it as its **Source:** (i.e. this URL is a designated authority),
|
||||
* else null. The registry is URL-keyed, so storing the URL is type-consistent with
|
||||
* the change.authority_source field rule 3 consumes; null keeps the field honest
|
||||
* where no file vouches for the URL.
|
||||
* @param {string} normUrl — a normalized registry URL key
|
||||
* @param {Set<string>} declaredSet — output of collectDeclaredSources
|
||||
* @returns {string|null}
|
||||
*/
|
||||
export function markUrlAuthority(normUrl, declaredSet) {
|
||||
return declaredSet && declaredSet.has(normUrl) ? normUrl : null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Coverage metric for the criterion ("authority_source-dekning > 0%").
|
||||
* @param {{urls: object}} registry
|
||||
* @returns {{withAuthority: number, total: number, ratio: number}}
|
||||
*/
|
||||
export function authorityCoverage(registry) {
|
||||
const urls = (registry && registry.urls) || {};
|
||||
const entries = Object.values(urls);
|
||||
const withAuthority = entries.filter((e) => e && e.authority_source).length;
|
||||
const total = entries.length;
|
||||
return { withAuthority, total, ratio: total ? withAuthority / total : 0 };
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue