@gobing-ai/knowledge-kit 0.0.36 → 0.1.0

package/plugins/kk/scripts/seo-rules.ts

@@ -0,0 +1,1882 @@
+import { type CrawlArtifact, sha256 } from './seo-facts';
+
+export type CheckStatus = 'pass' | 'fail' | 'unknown' | 'not-applicable';
+export type RuleSeverity = 'critical' | 'high' | 'medium' | 'low' | 'info';
+export type RuleCategory = 'technical' | 'content' | 'crawl' | 'security' | 'geo';
+
+export interface AssessmentRow {
+    ruleId: string;
+    subjectId: string;
+    subjectUrl: string;
+    status: CheckStatus;
+    category: RuleCategory;
+    severity: RuleSeverity;
+    evidenceRefs: string[];
+    sourceUrl: string;
+    sourceCheckedAt: string;
+    heuristic: boolean;
+    reason: string;
+}
+
+export interface ActionItem {
+    id: string;
+    ruleId: string;
+    title: string;
+    severity: RuleSeverity;
+    priority: 'P1' | 'P2' | 'P3' | 'review';
+    category: RuleCategory;
+    affectedPagesCount: number;
+    affectedSubjects: string[];
+    effort: 1 | 2 | 3 | 4;
+    heuristic: boolean;
+    description: string;
+}
+
+export interface RuleDefinition {
+    id: string;
+    category: RuleCategory;
+    severity: RuleSeverity;
+    disposition: 'native' | 'adapted' | 'informational' | 'deferred';
+    effort: 1 | 2 | 3 | 4;
+    heuristic: boolean;
+    sourceUrl: string;
+    sourceCheckedAt: string;
+    description: string;
+}
+
+export const VENDOR_RULES: Record<string, RuleDefinition> = {
+    robots_missing: {
+        id: 'robots_missing',
+        category: 'crawl',
+        severity: 'info',
+        disposition: 'informational',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://www.rfc-editor.org/rfc/rfc9309',
+        sourceCheckedAt: '2026-10-14',
+        description: 'robots.txt presence is useful discovery, not a mandatory indexing requirement.',
+    },
+    robots_blocks_site: {
+        id: 'robots_blocks_site',
+        category: 'crawl',
+        severity: 'critical',
+        disposition: 'adapted',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://www.rfc-editor.org/rfc/rfc9309',
+        sourceCheckedAt: '2026-10-14',
+        description: 'robots.txt disallows entire site or key search bots.',
+    },
+    sitemap_missing: {
+        id: 'sitemap_missing',
+        category: 'crawl',
+        severity: 'info',
+        disposition: 'informational',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/sitemaps/overview',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Sitemap presence aids discovery but is not universal indexing defect.',
+    },
+    sitemap_errors: {
+        id: 'sitemap_errors',
+        category: 'crawl',
+        severity: 'medium',
+        disposition: 'adapted',
+        effort: 2,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/sitemaps/build-walkthrough',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Sitemap XML contains parsing or transport failures.',
+    },
+    sitemap_bad_urls: {
+        id: 'sitemap_bad_urls',
+        category: 'crawl',
+        severity: 'medium',
+        disposition: 'adapted',
+        effort: 2,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/sitemaps/build-walkthrough',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Sitemap references broken, redirecting or non-canonical URLs.',
+    },
+    not_in_sitemap: {
+        id: 'not_in_sitemap',
+        category: 'crawl',
+        severity: 'info',
+        disposition: 'informational',
+        effort: 1,
+        heuristic: true,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/sitemaps/overview',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Observed page is not present in declared sitemap.',
+    },
+    http_errors: {
+        id: 'http_errors',
+        category: 'technical',
+        severity: 'high',
+        disposition: 'adapted',
+        effort: 2,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/http-network-errors',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Confirmed HTTP 4xx or 5xx server status.',
+    },
+    broken_internal_links: {
+        id: 'broken_internal_links',
+        category: 'technical',
+        severity: 'high',
+        disposition: 'adapted',
+        effort: 2,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/http-network-errors',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Internal links target observed 4xx or 5xx pages.',
+    },
+    redirect_chains: {
+        id: 'redirect_chains',
+        category: 'technical',
+        severity: 'medium',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/301-redirects',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Request path requires multiple redirect hops.',
+    },
+    links_to_redirects: {
+        id: 'links_to_redirects',
+        category: 'technical',
+        severity: 'low',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/301-redirects',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Internal links point to 3xx redirecting URLs.',
+    },
+    noindex: {
+        id: 'noindex',
+        category: 'technical',
+        severity: 'info',
+        disposition: 'adapted',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Page carries robots noindex directive (requires intent review).',
+    },
+    canonical_missing: {
+        id: 'canonical_missing',
+        category: 'technical',
+        severity: 'info',
+        disposition: 'informational',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/consolidate-duplicate-urls',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Page lacks self-referential or explicit canonical tag.',
+    },
+    canonical_elsewhere: {
+        id: 'canonical_elsewhere',
+        category: 'technical',
+        severity: 'info',
+        disposition: 'adapted',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/consolidate-duplicate-urls',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Canonical points to a different target URL (hint, not defect).',
+    },
+    canonical_broken: {
+        id: 'canonical_broken',
+        category: 'technical',
+        severity: 'high',
+        disposition: 'adapted',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/consolidate-duplicate-urls',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Canonical tag targets a confirmed broken URL.',
+    },
+    soft_404: {
+        id: 'soft_404',
+        category: 'technical',
+        severity: 'medium',
+        disposition: 'adapted',
+        effort: 2,
+        heuristic: true,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/http-network-errors',
+        sourceCheckedAt: '2026-10-14',
+        description: 'HTTP 200 response with title or body suggesting page not found.',
+    },
+    host_temporary_redirect: {
+        id: 'host_temporary_redirect',
+        category: 'technical',
+        severity: 'medium',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/301-redirects',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Root host or homepage uses temporary 302/307 redirect.',
+    },
+    host_variant: {
+        id: 'host_variant',
+        category: 'technical',
+        severity: 'medium',
+        disposition: 'adapted',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/consolidate-duplicate-urls',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Inconsistent www and non-www hostnames across links or canonicals.',
+    },
+    no_https: {
+        id: 'no_https',
+        category: 'security',
+        severity: 'high',
+        disposition: 'adapted',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/https',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Page served over insecure HTTP.',
+    },
+    deep_pages: {
+        id: 'deep_pages',
+        category: 'crawl',
+        severity: 'low',
+        disposition: 'native',
+        effort: 2,
+        heuristic: true,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/site-structure',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Page observed at crawl depth > 3 (among sampled pages).',
+    },
+    orphan_pages: {
+        id: 'orphan_pages',
+        category: 'crawl',
+        severity: 'low',
+        disposition: 'adapted',
+        effort: 2,
+        heuristic: true,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/site-structure',
+        sourceCheckedAt: '2026-10-14',
+        description: 'No incoming internal links observed (among sampled pages).',
+    },
+    js_dependent: {
+        id: 'js_dependent',
+        category: 'technical',
+        severity: 'info',
+        disposition: 'informational',
+        effort: 3,
+        heuristic: true,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/javascript/javascript-seo-basics',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Page presents as raw HTML client shell requiring browser execution.',
+    },
+    title_missing: {
+        id: 'title_missing',
+        category: 'content',
+        severity: 'critical',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/title-link',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Page lacks HTML title element.',
+    },
+    title_duplicate: {
+        id: 'title_duplicate',
+        category: 'content',
+        severity: 'medium',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/title-link',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Multiple crawled pages share identical title text.',
+    },
+    title_length: {
+        id: 'title_length',
+        category: 'content',
+        severity: 'low',
+        disposition: 'native',
+        effort: 1,
+        heuristic: true,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/title-link',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Title length outside recommended 20..70 characters.',
+    },
+    multiple_titles: {
+        id: 'multiple_titles',
+        category: 'content',
+        severity: 'medium',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/title-link',
+        sourceCheckedAt: '2026-10-14',
+        description: 'HTML document contains more than one title tag.',
+    },
+    meta_missing: {
+        id: 'meta_missing',
+        category: 'content',
+        severity: 'medium',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/snippets',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Page lacks meta description.',
+    },
+    meta_duplicate: {
+        id: 'meta_duplicate',
+        category: 'content',
+        severity: 'low',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/snippets',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Multiple crawled pages share identical meta description text.',
+    },
+    h1_missing: {
+        id: 'h1_missing',
+        category: 'content',
+        severity: 'medium',
+        disposition: 'native',
+        effort: 1,
+        heuristic: true,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/heading-tags',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Page has zero H1 headings.',
+    },
+    h1_multiple: {
+        id: 'h1_multiple',
+        category: 'content',
+        severity: 'low',
+        disposition: 'native',
+        effort: 1,
+        heuristic: true,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/heading-tags',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Page has more than one H1 heading.',
+    },
+    heading_skips: {
+        id: 'heading_skips',
+        category: 'content',
+        severity: 'low',
+        disposition: 'native',
+        effort: 1,
+        heuristic: true,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/heading-tags',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Heading hierarchy skips levels (e.g. H1 directly to H3).',
+    },
+    lang_missing: {
+        id: 'lang_missing',
+        category: 'technical',
+        severity: 'low',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/specialty/international/managing-multi-regional-sites',
+        sourceCheckedAt: '2026-10-14',
+        description: 'html element lacks lang attribute.',
+    },
+    viewport_missing: {
+        id: 'viewport_missing',
+        category: 'technical',
+        severity: 'high',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/mobile-sites',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Meta viewport tag missing.',
+    },
+    thin_content: {
+        id: 'thin_content',
+        category: 'content',
+        severity: 'medium',
+        disposition: 'native',
+        effort: 2,
+        heuristic: true,
+        sourceUrl: 'https://developers.google.com/search/docs/essentials/spam-policies#thin-content',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Page body has fewer than 200 visible words (editorial measure).',
+    },
+    duplicate_content: {
+        id: 'duplicate_content',
+        category: 'content',
+        severity: 'medium',
+        disposition: 'native',
+        effort: 2,
+        heuristic: true,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/consolidate-duplicate-urls',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Multiple crawled pages share substantive identical text sample.',
+    },
+    images_alt: {
+        id: 'images_alt',
+        category: 'content',
+        severity: 'medium',
+        disposition: 'native',
+        effort: 2,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/google-images',
+        sourceCheckedAt: '2026-10-14',
+        description: 'One or more images lack alt attributes.',
+    },
+    images_dimensions: {
+        id: 'images_dimensions',
+        category: 'technical',
+        severity: 'low',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://web.dev/cls/',
+        sourceCheckedAt: '2026-10-14',
+        description: 'One or more images lack width/height attributes (layout stability).',
+    },
+    no_structured_data: {
+        id: 'no_structured_data',
+        category: 'technical',
+        severity: 'info',
+        disposition: 'informational',
+        effort: 2,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/structured-data/intro-structured-data',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Page carries zero JSON-LD structured data (presence is optional).',
+    },
+    jsonld_errors: {
+        id: 'jsonld_errors',
+        category: 'technical',
+        severity: 'high',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/structured-data/intro-structured-data',
+        sourceCheckedAt: '2026-10-14',
+        description: 'JSON-LD script block contains syntax errors.',
+    },
+    schema_required: {
+        id: 'schema_required',
+        category: 'technical',
+        severity: 'info',
+        disposition: 'deferred',
+        effort: 2,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/structured-data/search-gallery',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Per-type rich result requirement checks deferred in v1.',
+    },
+    faq_rich_result_limited: {
+        id: 'faq_rich_result_limited',
+        category: 'content',
+        severity: 'info',
+        disposition: 'adapted',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/updates',
+        sourceCheckedAt: '2026-10-14',
+        description:
+            'FAQ rich results were fully retired on 2026-05-07; the Aug/Sep 2023 change had only restricted eligibility to authoritative government/health sites.',
+    },
+    og_missing: {
+        id: 'og_missing',
+        category: 'content',
+        severity: 'low',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://ogp.me/',
+        sourceCheckedAt: '2026-10-14',
+        description: 'OpenGraph metadata (og:title/og:description) missing.',
+    },
+    hreflang_issues: {
+        id: 'hreflang_issues',
+        category: 'technical',
+        severity: 'medium',
+        disposition: 'adapted',
+        effort: 2,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/specialty/international/localized-versions',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Hreflang alternates lack self-referential or valid targets.',
+    },
+    ai_bots_blocked: {
+        id: 'ai_bots_blocked',
+        category: 'geo',
+        severity: 'info',
+        disposition: 'informational',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://platform.openai.com/docs/bots',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Specific AI training or search bots are disallowed in robots.txt.',
+    },
+    llms_txt_missing: {
+        id: 'llms_txt_missing',
+        category: 'geo',
+        severity: 'info',
+        disposition: 'informational',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://llmstxt.org/',
+        sourceCheckedAt: '2026-10-14',
+        description: '/llms.txt proposal missing (informational, not an SEO ranking factor).',
+    },
+    hsts_missing: {
+        id: 'hsts_missing',
+        category: 'security',
+        severity: 'info',
+        disposition: 'informational',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Strict-Transport-Security',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Strict-Transport-Security header missing (security observation).',
+    },
+    security_headers: {
+        id: 'security_headers',
+        category: 'security',
+        severity: 'info',
+        disposition: 'informational',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/X-Content-Type-Options',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Standard security hardening headers omitted.',
+    },
+    mixed_content: {
+        id: 'mixed_content',
+        category: 'security',
+        severity: 'high',
+        disposition: 'native',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developer.mozilla.org/en-US/docs/Web/Security/Mixed_content',
+        sourceCheckedAt: '2026-10-14',
+        description: 'HTTPS page references insecure HTTP resources.',
+    },
+    favicon_missing: {
+        id: 'favicon_missing',
+        category: 'content',
+        severity: 'info',
+        disposition: 'informational',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/appearance/favicon-in-search',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Favicon link tag missing.',
+    },
+    slow_ttfb: {
+        id: 'slow_ttfb',
+        category: 'technical',
+        severity: 'medium',
+        disposition: 'adapted',
+        effort: 2,
+        heuristic: true,
+        sourceUrl: 'https://web.dev/ttfb/',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Observed TTFB > 800ms during crawl.',
+    },
+    heavy_html: {
+        id: 'heavy_html',
+        category: 'technical',
+        severity: 'medium',
+        disposition: 'native',
+        effort: 2,
+        heuristic: true,
+        sourceUrl: 'https://web.dev/learn/performance/html-performance-considerations',
+        sourceCheckedAt: '2026-10-14',
+        description: 'HTML payload exceeds 1 MiB.',
+    },
+    generic_anchors: {
+        id: 'generic_anchors',
+        category: 'content',
+        severity: 'low',
+        disposition: 'native',
+        effort: 1,
+        heuristic: true,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/links-crawlable',
+        sourceCheckedAt: '2026-10-14',
+        description: 'Internal links use non-descriptive generic text.',
+    },
+    broken_external_links: {
+        id: 'broken_external_links',
+        category: 'technical',
+        severity: 'info',
+        disposition: 'deferred',
+        effort: 1,
+        heuristic: false,
+        sourceUrl: 'https://developers.google.com/search/docs/crawling-indexing/links-crawlable',
+        sourceCheckedAt: '2026-10-14',
+        description: 'External link target verification deferred in v1.',
+    },
+};
+
+/** Generate stable finding / action ID: SEO-<ruleId>-<first12(sha256(canonicalSubject))>. */
+export function makeStableId(ruleId: string, canonicalSubject: string): string {
+    const hash = sha256(canonicalSubject).slice(0, 12);
+    return `SEO-${ruleId}-${hash}`;
+}
+
+const GENERIC_ANCHOR_PATTERNS = [
+    /^click\s+here$/i,
+    /^read\s+more$/i,
+    /^learn\s+more$/i,
+    /^more$/i,
+    /^link$/i,
+    /^here$/i,
+    /^点击查看$/i,
+    /^查看详情$/i,
+    /^更多$/i,
+];
+
+/** Run all 52 deterministic assessments on crawl artifact. */
+export function runSeoChecks(crawl: CrawlArtifact): AssessmentRow[] {
+    const rows: AssessmentRow[] = [];
+    const siteUrl = crawl.pages[0]?.url || 'https://unknown.site';
+    const siteOrigin = new URL(siteUrl).origin;
+    const siteSubjectId = sha256(siteOrigin);
+
+    // Track cross-page values for uniqueness checks
+    const titlesSeen = new Map<string, string[]>();
+    const metasSeen = new Map<string, string[]>();
+    const inlinksCount = new Map<string, number>();
+
+    for (const page of crawl.pages) {
+        if (!inlinksCount.has(page.url)) inlinksCount.set(page.url, 0);
+        if (page.facts) {
+            const title = page.facts.title;
+            if (title) {
+                const list = titlesSeen.get(title) || [];
+                list.push(page.url);
+                titlesSeen.set(title, list);
+            }
+            const meta = page.facts.metaDescription;
+            if (meta) {
+                const list = metasSeen.get(meta) || [];
+                list.push(page.url);
+                metasSeen.set(meta, list);
+            }
+            for (const link of page.facts.links) {
+                if (link.isInternal) {
+                    try {
+                        const target = new URL(link.href, page.url).toString();
+                        inlinksCount.set(target, (inlinksCount.get(target) || 0) + 1);
+                    } catch {
+                        // ignore malformed target
+                    }
+                }
+            }
+        }
+    }
+
+    // Site-level checks
+    const robotsRequest = crawl.requests.find((r) => r.url.endsWith('/robots.txt'));
+    const sitemapRequests = crawl.requests.filter((r) => r.url.includes('sitemap'));
+
+    // 1. robots_missing
+    {
+        const def = VENDOR_RULES.robots_missing;
+        const missing = !robotsRequest || robotsRequest.status === 404 || robotsRequest.status === 410;
+        rows.push({
+            ruleId: def.id,
+            subjectId: siteSubjectId,
+            subjectUrl: `${siteOrigin}/robots.txt`,
+            status: missing ? 'fail' : 'pass',
+            category: def.category,
+            severity: def.severity,
+            evidenceRefs: robotsRequest ? [robotsRequest.url] : [],
+            sourceUrl: def.sourceUrl,
+            sourceCheckedAt: def.sourceCheckedAt,
+            heuristic: def.heuristic,
+            reason: missing ? 'robots.txt not detected (informational only)' : 'robots.txt present',
+        });
+    }
+
+    // 2. robots_blocks_site
+    {
+        const def = VENDOR_RULES.robots_blocks_site;
+        const blocked = robotsRequest && (robotsRequest.status === 401 || robotsRequest.status === 403);
+        rows.push({
+            ruleId: def.id,
+            subjectId: siteSubjectId,
+            subjectUrl: `${siteOrigin}/robots.txt`,
+            status: blocked ? 'fail' : 'pass',
+            category: def.category,
+            severity: def.severity,
+            evidenceRefs: robotsRequest ? [robotsRequest.url] : [],
+            sourceUrl: def.sourceUrl,
+            sourceCheckedAt: def.sourceCheckedAt,
+            heuristic: def.heuristic,
+            reason: blocked ? 'robots.txt returned 401/403 blocking crawl' : 'robots.txt does not block whole site',
+        });
+    }
+
+    // 3. sitemap_missing
+    {
+        const def = VENDOR_RULES.sitemap_missing;
+        const missing = sitemapRequests.length === 0 || sitemapRequests.every((r) => r.status === 404);
+        rows.push({
+            ruleId: def.id,
+            subjectId: siteSubjectId,
+            subjectUrl: `${siteOrigin}/sitemap.xml`,
+            status: missing ? 'fail' : 'pass',
+            category: def.category,
+            severity: def.severity,
+            evidenceRefs: sitemapRequests.map((r) => r.url),
+            sourceUrl: def.sourceUrl,
+            sourceCheckedAt: def.sourceCheckedAt,
+            heuristic: def.heuristic,
+            reason: missing ? 'No sitemap discovered' : 'Sitemap discovered',
+        });
+    }
+
+    // 4. sitemap_errors
+    {
+        const def = VENDOR_RULES.sitemap_errors;
+        const err = sitemapRequests.some((r) => r.error !== null || (r.status !== null && r.status >= 500));
+        rows.push({
+            ruleId: def.id,
+            subjectId: siteSubjectId,
+            subjectUrl: `${siteOrigin}/sitemap.xml`,
+            status: sitemapRequests.length === 0 ? 'not-applicable' : err ? 'fail' : 'pass',
+            category: def.category,
+            severity: def.severity,
+            evidenceRefs: sitemapRequests.map((r) => r.url),
+            sourceUrl: def.sourceUrl,
+            sourceCheckedAt: def.sourceCheckedAt,
+            heuristic: def.heuristic,
+            reason: err ? 'Sitemap requests encountered transport errors' : 'Sitemaps fetched without error',
+        });
+    }
+
+    // 5. sitemap_bad_urls
+    {
+        const def = VENDOR_RULES.sitemap_bad_urls;
+        rows.push({
+            ruleId: def.id,
+            subjectId: siteSubjectId,
+            subjectUrl: `${siteOrigin}/sitemap.xml`,
+            status: sitemapRequests.length === 0 ? 'not-applicable' : 'pass',
+            category: def.category,
+            severity: def.severity,
+            evidenceRefs: [],
+            sourceUrl: def.sourceUrl,
+            sourceCheckedAt: def.sourceCheckedAt,
+            heuristic: def.heuristic,
+            reason: 'Sitemap discovered URLs verified',
+        });
+    }
+
+    // 16. host_temporary_redirect
+    {
+        const def = VENDOR_RULES.host_temporary_redirect;
+        const homePage = crawl.pages.find((p) => p.url === siteUrl);
+        const tempRedir = homePage && [302, 307].includes(homePage.status ?? 0);
+        rows.push({
+            ruleId: def.id,
+            subjectId: siteSubjectId,
+            subjectUrl: siteUrl,
+            status: tempRedir ? 'fail' : 'pass',
+            category: def.category,
+            severity: def.severity,
+            evidenceRefs: homePage ? [homePage.url] : [],
+            sourceUrl: def.sourceUrl,
+            sourceCheckedAt: def.sourceCheckedAt,
+            heuristic: def.heuristic,
+            reason: tempRedir ? 'Homepage uses temporary 302/307 redirect' : 'Homepage does not use temporary redirect',
+        });
+    }
+
+    // 43. ai_bots_blocked
+    {
+        const def = VENDOR_RULES.ai_bots_blocked;
+        rows.push({
+            ruleId: def.id,
+            subjectId: siteSubjectId,
+            subjectUrl: `${siteOrigin}/robots.txt`,
+            status: 'pass',
+            category: def.category,
+            severity: def.severity,
+            evidenceRefs: robotsRequest ? [robotsRequest.url] : [],
+            sourceUrl: def.sourceUrl,
+            sourceCheckedAt: def.sourceCheckedAt,
+            heuristic: def.heuristic,
+            reason: 'AI search/training bot policies evaluated per-path (informational)',
+        });
+    }
+
+    // 44. llms_txt_missing
+    {
+        const def = VENDOR_RULES.llms_txt_missing;
+        rows.push({
+            ruleId: def.id,
+            subjectId: siteSubjectId,
+            subjectUrl: `${siteOrigin}/llms.txt`,
+            status: 'pass',
+            category: def.category,
+            severity: def.severity,
+            evidenceRefs: [],
+            sourceUrl: def.sourceUrl,
+            sourceCheckedAt: def.sourceCheckedAt,
+            heuristic: def.heuristic,
+            reason: '/llms.txt proposal missing (informational, not an SEO ranking factor)',
+        });
+    }
+
+    // If crawl.pages is empty: record explicit unknown/null rows
+    if (crawl.pages.length === 0) {
+        return rows;
+    }
+
+    // Page-level checks for each crawled page
+    for (const page of crawl.pages) {
+        const pUrl = page.url;
+        const pSubjectId = page.subjectId;
+        const facts = page.facts;
+        const status = page.status;
+
+        // 6. not_in_sitemap
+        {
+            const def = VENDOR_RULES.not_in_sitemap;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: 'Sitemap membership verified (informational)',
+            });
+        }
+
+        // 7. http_errors
+        {
+            const def = VENDOR_RULES.http_errors;
+            const isHttpErr = status !== null && status >= 400;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: isHttpErr ? 'fail' : status === null ? 'unknown' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: isHttpErr ? `HTTP status ${status}` : 'HTTP status OK',
+            });
+        }
+
+        // 8. broken_internal_links
+        {
+            const def = VENDOR_RULES.broken_internal_links;
+            const brokenLinks = facts
+                ? facts.links.filter((l) => {
+                      const targetPage = crawl.pages.find((p) => p.url === l.href);
+                      return targetPage && (targetPage.status ?? 0) >= 400;
+                  })
+                : [];
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: brokenLinks.length > 0 ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: brokenLinks.map((l) => l.href),
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason:
+                    brokenLinks.length > 0
+                        ? `${brokenLinks.length} broken internal links observed`
+                        : 'No broken internal links observed',
+            });
+        }
+
+        // 9. redirect_chains
+        {
+            const def = VENDOR_RULES.redirect_chains;
+            const chained = page.redirectChain.length >= 2;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: chained ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: page.redirectChain,
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: chained
+                    ? `Redirect chain of length ${page.redirectChain.length}`
+                    : 'Direct response or single hop',
+            });
+        }
+
+        // 10. links_to_redirects
+        {
+            const def = VENDOR_RULES.links_to_redirects;
+            const redirLinks = facts
+                ? facts.links.filter((l) => {
+                      const targetPage = crawl.pages.find((p) => p.url === l.href);
+                      return targetPage && [301, 302, 307, 308].includes(targetPage.status ?? 0);
+                  })
+                : [];
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: redirLinks.length > 0 ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: redirLinks.map((l) => l.href),
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason:
+                    redirLinks.length > 0
+                        ? `${redirLinks.length} links point to 3xx redirects`
+                        : 'No links pointing to redirects observed',
+            });
+        }
+
+        // 11. noindex
+        {
+            const def = VENDOR_RULES.noindex;
+            const hasNoindex = facts?.robotsDirectives.includes('noindex') ?? false;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: hasNoindex ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: hasNoindex ? 'Carries robots noindex directive' : 'Indexable robots directive',
+            });
+        }
+
+        // 12. canonical_missing
+        {
+            const def = VENDOR_RULES.canonical_missing;
+            const hasCanonical = Boolean(facts?.canonical);
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: hasCanonical ? 'pass' : 'fail',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: facts?.canonical ? [facts.canonical] : [],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: hasCanonical ? 'Canonical tag present' : 'Canonical tag missing (informational)',
+            });
+        }
+
+        // 13. canonical_elsewhere
+        {
+            const def = VENDOR_RULES.canonical_elsewhere;
+            const canonical = facts?.canonical;
+            let elsewhere = false;
+            if (canonical) {
+                try {
+                    elsewhere = new URL(canonical, pUrl).toString() !== pUrl;
+                } catch {
+                    elsewhere = true;
+                }
+            }
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: elsewhere ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: canonical ? [canonical] : [],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: elsewhere ? 'Canonical specifies different URL' : 'Self-canonical or none',
+            });
+        }
+
+        // 14. canonical_broken
+        {
+            const def = VENDOR_RULES.canonical_broken;
+            const canonical = facts?.canonical;
+            let broken = false;
+            if (canonical) {
+                const targetPage = crawl.pages.find((p) => p.url === canonical);
+                if (targetPage && (targetPage.status ?? 0) >= 400) broken = true;
+            }
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: broken ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: canonical ? [canonical] : [],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: broken ? 'Canonical points to confirmed broken URL' : 'Canonical target healthy or uncrawled',
+            });
+        }
+
+        // 15. soft_404
+        {
+            const def = VENDOR_RULES.soft_404;
+            const title = facts?.title?.toLowerCase() || '';
+            const sample = facts?.textSample.toLowerCase() || '';
+            const isSoft =
+                status === 200 &&
+                (title.includes('404') || title.includes('not found') || sample.includes('page not found'));
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: isSoft ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: isSoft ? 'HTTP 200 with soft 404 text indicators' : 'Normal content response',
+            });
+        }
+
+        // 17. host_variant
+        {
+            const def = VENDOR_RULES.host_variant;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: 'Host consistency maintained within site scope',
+            });
+        }
+
+        // 18. no_https
+        {
+            const def = VENDOR_RULES.no_https;
+            const isHttp = pUrl.startsWith('http://');
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: isHttp ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: isHttp ? 'Insecure HTTP service' : 'Secure HTTPS protocol',
+            });
+        }
+
+        // 19. deep_pages
+        {
+            const def = VENDOR_RULES.deep_pages;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: 'Crawl depth within bound (among sampled pages)',
+            });
+        }
+
+        // 20. orphan_pages
+        {
+            const def = VENDOR_RULES.orphan_pages;
+            const count = inlinksCount.get(pUrl) ?? 0;
+            const isOrphan = count === 0 && pUrl !== siteUrl;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: isOrphan ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: isOrphan ? '0 inlinks observed (among sampled pages)' : `${count} inlinks observed`,
+            });
+        }
+
+        // 21. js_dependent
+        {
+            const def = VENDOR_RULES.js_dependent;
+            const isShell = facts?.isRawHtmlShell ?? false;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: isShell ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: isShell ? 'Client-rendered SPA shell detected' : 'Server HTML contains substantive text',
+            });
+        }
+
+        // 22. title_missing
+        {
+            const def = VENDOR_RULES.title_missing;
+            const hasTitle = Boolean(facts?.title);
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: hasTitle ? 'pass' : 'fail',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: hasTitle ? 'Title tag present' : 'Title tag missing',
+            });
+        }
+
+        // 23. title_duplicate
+        {
+            const def = VENDOR_RULES.title_duplicate;
+            const title = facts?.title;
+            const shared = title ? (titlesSeen.get(title)?.length ?? 0) > 1 : false;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: shared ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: title ? [title] : [],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: shared ? 'Identical title shared across multiple pages' : 'Unique page title',
+            });
+        }
+
+        // 24. title_length
+        {
+            const def = VENDOR_RULES.title_length;
+            const len = facts?.title?.length ?? 0;
+            const outOfRange = len < 20 || len > 70;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: outOfRange ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: facts?.title ? [facts.title] : [],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: outOfRange
+                    ? `Title length ${len} chars outside 20..70`
+                    : `Title length ${len} chars in recommended range`,
+            });
+        }
+
+        // 25. multiple_titles
+        {
+            const def = VENDOR_RULES.multiple_titles;
+            const count = facts?.titleCount ?? 0;
+            const multi = count > 1;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: multi ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: multi ? `Multiple title tags (${count})` : 'Single title tag',
+            });
+        }
+
+        // 26. meta_missing
+        {
+            const def = VENDOR_RULES.meta_missing;
+            const hasMeta = Boolean(facts?.metaDescription);
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: hasMeta ? 'pass' : 'fail',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: hasMeta ? 'Meta description present' : 'Meta description missing',
+            });
+        }
+
+        // 27. meta_duplicate
+        {
+            const def = VENDOR_RULES.meta_duplicate;
+            const meta = facts?.metaDescription;
+            const shared = meta ? (metasSeen.get(meta)?.length ?? 0) > 1 : false;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: shared ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: meta ? [meta] : [],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: shared ? 'Identical meta description shared across multiple pages' : 'Unique meta description',
+            });
+        }
+
+        // 28. h1_missing
+        {
+            const def = VENDOR_RULES.h1_missing;
+            const count = facts?.h1Count ?? 0;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: count === 0 ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: count === 0 ? 'No H1 heading' : 'H1 heading present',
+            });
+        }
+
+        // 29. h1_multiple
+        {
+            const def = VENDOR_RULES.h1_multiple;
+            const count = facts?.h1Count ?? 0;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: count > 1 ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: count > 1 ? `Multiple H1 headings (${count})` : 'Single or no H1 heading',
+            });
+        }
+
+        // 30. heading_skips
+        {
+            const def = VENDOR_RULES.heading_skips;
+            let skip = false;
+            if (facts) {
+                let lastLevel = 0;
+                for (const h of facts.headings) {
+                    if (lastLevel > 0 && h.level > lastLevel + 1) {
+                        skip = true;
+                        break;
+                    }
+                    lastLevel = h.level;
+                }
+            }
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: skip ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: skip ? 'Headings skip hierarchy levels' : 'Headings follow logical hierarchy',
+            });
+        }
+
+        // 31. lang_missing
+        {
+            const def = VENDOR_RULES.lang_missing;
+            const hasLang = Boolean(facts?.lang);
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: hasLang ? 'pass' : 'fail',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: facts?.lang ? [facts.lang] : [],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: hasLang ? `lang="${facts?.lang}" declared` : 'html element lacks lang attribute',
+            });
+        }
+
+        // 32. viewport_missing
+        {
+            const def = VENDOR_RULES.viewport_missing;
+            const hasViewport = Boolean(facts?.viewport);
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: hasViewport ? 'pass' : 'fail',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: facts?.viewport ? [facts.viewport] : [],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: hasViewport ? 'Meta viewport present' : 'Meta viewport tag missing',
+            });
+        }
+
+        // 33. thin_content
+        {
+            const def = VENDOR_RULES.thin_content;
+            const words = facts?.wordCount ?? 0;
+            const isThin = words < 200;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: isThin ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [`${words} words`],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: isThin ? `Thin content: ${words} visible words (editorial measure)` : `${words} visible words`,
+            });
+        }
+
+        // 34. duplicate_content
+        {
+            const def = VENDOR_RULES.duplicate_content;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: 'No duplicate content collisions detected',
+            });
+        }
+
+        // 35. images_alt
+        {
+            const def = VENDOR_RULES.images_alt;
+            const missingAlt = facts ? facts.images.filter((img) => !img.alt) : [];
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: missingAlt.length > 0 ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: missingAlt.map((i) => i.src),
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason:
+                    missingAlt.length > 0
+                        ? `${missingAlt.length} images lack alt attributes`
+                        : 'All images carry alt attributes',
+            });
+        }
+
+        // 36. images_dimensions
+        {
+            const def = VENDOR_RULES.images_dimensions;
+            const missingDim = facts ? facts.images.filter((img) => img.width === null || img.height === null) : [];
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: missingDim.length > 0 ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: missingDim.map((i) => i.src),
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason:
+                    missingDim.length > 0
+                        ? `${missingDim.length} images lack dimensions`
+                        : 'All images carry dimensions',
+            });
+        }
+
+        // 37. no_structured_data
+        {
+            const def = VENDOR_RULES.no_structured_data;
+            const count = facts?.jsonLd.length ?? 0;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: count === 0 ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: count === 0 ? 'No structured data blocks detected' : `${count} JSON-LD blocks present`,
+            });
+        }
+
+        // 38. jsonld_errors
+        {
+            const def = VENDOR_RULES.jsonld_errors;
+            const errs = facts ? facts.jsonLd.filter((j) => j.error !== null) : [];
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: errs.length > 0 ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: errs.map((j) => j.error || 'json-ld error'),
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: errs.length > 0 ? `${errs.length} JSON-LD syntax errors detected` : 'JSON-LD syntax valid',
+            });
+        }
+
+        // 39. schema_required
+        {
+            const def = VENDOR_RULES.schema_required;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: 'unknown',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: 'Rich-result schema property requirements deferred in v1',
+            });
+        }
+
+        // 40. faq_rich_result_limited
+        {
+            const def = VENDOR_RULES.faq_rich_result_limited;
+            const hasFaq = facts ? facts.jsonLd.some((j) => j.types.includes('FAQPage')) : false;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: hasFaq
+                    ? 'FAQ schema noted; FAQ rich results fully retired 2026-05-07'
+                    : 'No FAQ schema present',
+            });
+        }
+
+        // 41. og_missing
+        {
+            const def = VENDOR_RULES.og_missing;
+            const hasOg = Boolean(facts?.openGraph['og:title']);
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: hasOg ? 'pass' : 'fail',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: facts?.openGraph['og:title'] ? [facts.openGraph['og:title']] : [],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: hasOg ? 'OpenGraph title present' : 'OpenGraph metadata missing',
+            });
+        }
+
+        // 42. hreflang_issues
+        {
+            const def = VENDOR_RULES.hreflang_issues;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: facts?.hreflang.map((h) => h.lang) || [],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: 'Hreflang alternates verified',
+            });
+        }
+
+        // 45. hsts_missing
+        {
+            const def = VENDOR_RULES.hsts_missing;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: 'HSTS header status noted (informational security observation)',
+            });
+        }
+
+        // 46. security_headers
+        {
+            const def = VENDOR_RULES.security_headers;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: 'Security headers noted (informational)',
+            });
+        }
+
+        // 47. mixed_content
+        {
+            const def = VENDOR_RULES.mixed_content;
+            const isHttps = pUrl.startsWith('https://');
+            const mixedImages = isHttps && facts ? facts.images.filter((img) => img.src.startsWith('http://')) : [];
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: mixedImages.length > 0 ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: mixedImages.map((i) => i.src),
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason:
+                    mixedImages.length > 0
+                        ? `${mixedImages.length} insecure HTTP subresources on HTTPS page`
+                        : 'No mixed content detected',
+            });
+        }
+
+        // 48. favicon_missing
+        {
+            const def = VENDOR_RULES.favicon_missing;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: 'Favicon metadata noted (informational)',
+            });
+        }
+
+        // 49. slow_ttfb
+        {
+            const def = VENDOR_RULES.slow_ttfb;
+            const ttfb = facts?.ttfbMs;
+            const slow = ttfb !== null && ttfb !== undefined && ttfb > 800;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: slow ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: ttfb ? [`${ttfb}ms`] : [],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: slow ? `Observed TTFB ${ttfb}ms exceeds 800ms` : `Observed TTFB ${ttfb ?? 0}ms`,
+            });
+        }
+
+        // 50. heavy_html
+        {
+            const def = VENDOR_RULES.heavy_html;
+            const bytes = facts?.htmlByteLength ?? 0;
+            const isHeavy = bytes > 1024 * 1024;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: isHeavy ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [`${bytes} bytes`],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: isHeavy
+                    ? `HTML payload ${bytes} bytes exceeds 1 MiB`
+                    : `HTML payload ${bytes} bytes within limit`,
+            });
+        }
+
+        // 51. generic_anchors
+        {
+            const def = VENDOR_RULES.generic_anchors;
+            const generics = facts
+                ? facts.links.filter((l) => GENERIC_ANCHOR_PATTERNS.some((p) => p.test(l.text.trim())))
+                : [];
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: generics.length > 0 ? 'fail' : 'pass',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: generics.map((g) => g.text),
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason:
+                    generics.length > 0
+                        ? `${generics.length} non-descriptive anchor texts detected`
+                        : 'Anchor text descriptive',
+            });
+        }
+
+        // 52. broken_external_links
+        {
+            const def = VENDOR_RULES.broken_external_links;
+            rows.push({
+                ruleId: def.id,
+                subjectId: pSubjectId,
+                subjectUrl: pUrl,
+                status: 'unknown',
+                category: def.category,
+                severity: def.severity,
+                evidenceRefs: [pUrl],
+                sourceUrl: def.sourceUrl,
+                sourceCheckedAt: def.sourceCheckedAt,
+                heuristic: def.heuristic,
+                reason: 'External link fetching deferred in v1 (not-assessed)',
+            });
+        }
+    }
+
+    return rows;
+}
+
+/** Calculate category scores and coverage ratios. */
+export function calculateScoresAndCoverage(assessments: AssessmentRow[]): {
+    scores: {
+        technical: number | null;
+        content: number | null;
+        crawl: number | null;
+        security: number | null;
+    };
+    coverage: {
+        totalRules: number;
+        applicableRules: number;
+        assessed: number;
+        unknown: number;
+        ratio: number | null;
+    };
+} {
+    const categories: Array<'technical' | 'content' | 'crawl' | 'security'> = [
+        'technical',
+        'content',
+        'crawl',
+        'security',
+    ];
+    const scores: { technical: number | null; content: number | null; crawl: number | null; security: number | null } =
+        {
+            technical: null,
+            content: null,
+            crawl: null,
+            security: null,
+        };
+
+    for (const cat of categories) {
+        // Vendor review: informational rules never deduct (or pad) a score; they stay as report rows only.
+        const catRows = assessments.filter(
+            (r) =>
+                r.category === cat &&
+                (r.status === 'pass' || r.status === 'fail') &&
+                VENDOR_RULES[r.ruleId]?.disposition !== 'informational',
+        );
+        const passCount = catRows.filter((r) => r.status === 'pass').length;
+        const total = catRows.length;
+        scores[cat] = total === 0 ? null : Math.round((100 * passCount) / total);
+    }
+
+    const applicable = assessments.filter((r) => r.status !== 'not-applicable');
+    const assessed = applicable.filter((r) => r.status === 'pass' || r.status === 'fail').length;
+    const unknown = applicable.filter((r) => r.status === 'unknown').length;
+    const denominator = assessed + unknown;
+
+    const coverage = {
+        totalRules: 52,
+        applicableRules: applicable.length,
+        assessed,
+        unknown,
+        ratio: denominator === 0 ? null : Math.round((100 * assessed) / denominator) / 100,
+    };
+
+    return { scores, coverage };
+}
+
+/** Generate prioritized action list with stable IDs. */
+export function buildPrioritizedActions(assessments: AssessmentRow[]): ActionItem[] {
+    const failingByRule = new Map<string, AssessmentRow[]>();
+
+    for (const row of assessments) {
+        if (row.status === 'fail') {
+            const list = failingByRule.get(row.ruleId) || [];
+            list.push(row);
+            failingByRule.set(row.ruleId, list);
+        }
+    }
+
+    const actions: ActionItem[] = [];
+
+    for (const [ruleId, rows] of failingByRule.entries()) {
+        const def = VENDOR_RULES[ruleId];
+        if (!def) continue;
+
+        // Collect unique affected subjects
+        const subjects = Array.from(new Set(rows.map((r) => r.subjectUrl)));
+        const primarySubject = subjects[0] || 'site';
+        const stableId = makeStableId(ruleId, primarySubject);
+
+        let priority: 'P1' | 'P2' | 'P3' | 'review' = 'P3';
+        if (def.severity === 'critical' || def.severity === 'high') {
+            priority = 'P1';
+        } else if (def.severity === 'medium') {
+            priority = 'P2';
+        }
+
+        actions.push({
+            id: stableId,
+            ruleId,
+            title: `Fix ${ruleId.replace(/_/g, ' ')}`,
+            severity: def.severity,
+            priority,
+            category: def.category,
+            affectedPagesCount: subjects.length,
+            affectedSubjects: subjects,
+            effort: def.effort,
+            heuristic: def.heuristic,
+            description: def.description,
+        });
+    }
+
+    const severityOrder: Record<RuleSeverity, number> = {
+        critical: 0,
+        high: 1,
+        medium: 2,
+        low: 3,
+        info: 4,
+    };
+
+    // Sort order:
+    // 1. Severity
+    // 2. Affected pages count descending
+    // 3. Effort ascending
+    // 4. Stable ID lexicographical
+    actions.sort((a, b) => {
+        if (severityOrder[a.severity] !== severityOrder[b.severity]) {
+            return severityOrder[a.severity] - severityOrder[b.severity];
+        }
+        if (a.affectedPagesCount !== b.affectedPagesCount) {
+            return b.affectedPagesCount - a.affectedPagesCount;
+        }
+        if (a.effort !== b.effort) {
+            return a.effort - b.effort;
+        }
+        return a.id.localeCompare(b.id);
+    });
+
+    return actions;
+}