seo 0.16.0 → 0.16.1

package/dist/index.js

@@ -1,5 +1,5 @@
 import { createRequire as __seoCreateRequire } from 'node:module'; const require = __seoCreateRequire(import.meta.url);
-import { n as version, t as load } from "./esm-CV5s7esU.js";
+import { n as version, t as load } from "./esm-Cvmg0qhZ.js";
 import { SEO_PROVIDER_API_VERSION } from "./provider-sdk.js";
 import crypto, { createHash, randomUUID, sign } from "node:crypto";
 import { z } from "zod";
@@ -7728,17 +7728,15 @@ function recordHostFetch(input) {
 	const cfg = input.rate.backpressure;
 	health.durations.push(input.durationMs);
 	if (health.durations.length > 20) health.durations.shift();
-	const blocked = [
-		401,
-		403,
-		429
-	].includes(input.status);
-	const errored = input.status >= 500;
+	const rateLimited = input.status === 429 || input.status === 503 && input.retryAfterMs !== void 0;
+	const blocked = [401, 403].includes(input.status);
+	const errored = input.status >= 500 && !rateLimited;
 	const slow = input.durationMs >= cfg.slowMs;
 	health.consecutiveBlocked = blocked ? health.consecutiveBlocked + 1 : 0;
 	health.consecutiveErrors = errored ? health.consecutiveErrors + 1 : 0;
 	health.consecutiveSlow = slow ? health.consecutiveSlow + 1 : 0;
-	if (!blocked && !errored && !slow) health.reason = void 0;
+	if (!blocked && !errored && !slow && !rateLimited) health.reason = void 0;
+	if (rateLimited) health.reason = `origin rate limited the crawler (HTTP ${input.status})`;
 	const retryDelay = input.retryAfterMs === void 0 ? 0 : Math.min(input.retryAfterMs, cfg.retryAfterCapMs);
 	if (retryDelay > 0) {
 		health.reason = `origin sent Retry-After (${Math.round(retryDelay / 1e3)}s)`;
@@ -11288,6 +11286,17 @@ function isAuditableHtmlPage(page) {
 	const contentAuditAllowed = page.contentAuditAllowed ?? (!page.blocked && page.robotsTxt?.allowed !== false);
 	return isSuccessfulResponse(page) && isHtmlPage(page) && !isRedirectedPage(page) && contentAuditAllowed;
 }
+/**
+* Cloudflare serves its own endpoints under `/cdn-cgi/`, such as the email
+* obfuscation link `/cdn-cgi/l/email-protection`. They are not site pages.
+*/
+function isCdnUtilityUrl(value) {
+	try {
+		return new URL(value).pathname.startsWith("/cdn-cgi/");
+	} catch {
+		return false;
+	}
+}
 // packages/core/src/analyze/crawler/audit.ts
 function sameUrl(a, b) {
 	if (!a || !b) return false;
@@ -11557,7 +11566,7 @@ function auditCrawlPages(pages, opts = {}) {
 		if (page.accessBlock) continue;
 		if (page.status >= 500) {
 			issues.push(issue$1("server_error", page, String(page.status), { status: page.status }));
-			if ((page.internalInlinkCount ?? 0) > 0) issues.push(issue$1("broken_internal_link", page, String(page.status), {
+			if ((page.internalInlinkCount ?? 0) > 0 && !isCdnUtilityUrl(page.url)) issues.push(issue$1("broken_internal_link", page, String(page.status), {
 				status: page.status,
 				internalInlinkCount: page.internalInlinkCount
 			}));
@@ -11565,7 +11574,7 @@ function auditCrawlPages(pages, opts = {}) {
 		}
 		if (page.status >= 400) {
 			issues.push(issue$1("client_error", page, String(page.status), { status: page.status }));
-			if (isBrokenLinkStatus(page.status) && (page.internalInlinkCount ?? 0) > 0) issues.push(issue$1("broken_internal_link", page, String(page.status), {
+			if (isBrokenLinkStatus(page.status) && (page.internalInlinkCount ?? 0) > 0 && !isCdnUtilityUrl(page.url)) issues.push(issue$1("broken_internal_link", page, String(page.status), {
 				status: page.status,
 				internalInlinkCount: page.internalInlinkCount
 			}));
@@ -11788,6 +11797,7 @@ function auditCrawlPages(pages, opts = {}) {
 // packages/core/src/analyze/crawler/crawl-skip-reasons.ts
 const CRAWL_SKIP_REASONS = [
 	"asset-url",
+	"cdn-utility-url",
 	"configured-exclusion",
 	"duplicate-normalization",
 	"invalid-url",
@@ -11802,6 +11812,7 @@ const CRAWL_SKIP_REASONS = [
 ];
 const SKIP_IMPACT = {
 	"asset-url": "non-impacting",
+	"cdn-utility-url": "non-impacting",
 	"configured-exclusion": "non-impacting",
 	"duplicate-normalization": "non-impacting",
 	"invalid-url": "non-impacting",
@@ -12428,473 +12439,85 @@ function refreshPrioritiesCsvFiles(report) {
 		...prefixCsvFiles("diagnosis", diagnoseCsvFiles(report.output.diagnosis))
 	]);
 }
-// packages/core/src/analyze/crawler/top-fixes.ts
-const SEVERITY_SCORE = {
-	high: 5e3,
-	medium: 1200,
-	low: 100
-};
-const EFFORT_BY_CATEGORY = {
-	canonical: "medium",
-	content: "high",
-	agents: "low",
-	headings: "low",
-	images: "medium",
-	indexability: "medium",
-	international: "low",
-	metadata: "low",
-	mobile: "low",
-	response: "medium",
-	security: "medium",
-	social: "low",
-	"structured-data": "medium"
-};
-const EFFORT_SCORE = {
-	low: 60,
-	medium: 30,
-	high: 0
-};
-const AFFECTED_URL_WEIGHT = {
-	high: 25,
-	medium: 15,
-	low: 2
-};
-const VALUE_WEIGHT = {
-	high: 1,
-	medium: .75,
-	low: .15
-};
-const CRAWL_REACH_RULES = /* @__PURE__ */ new Set(["crawl_single_page_reach"]);
-function reachRank(ruleId) {
-	return CRAWL_REACH_RULES.has(ruleId) ? 0 : 1;
+// packages/core/src/analyze/crawler/crawl-url-queue.ts
+function before(left, right) {
+	return left.depth < right.depth || left.depth === right.depth && left.url < right.url;
 }
-function matchesPattern(pattern, value) {
-	if (!pattern.includes("*")) return value.includes(pattern);
-	const parts = pattern.split("*");
-	let position = 0;
-	for (const part of parts) {
-		if (!part) continue;
-		const found = value.slice(position).indexOf(part);
-		if (found === -1) return false;
-		position += found + part.length;
+var CrawlUrlQueue = class {
+	#items = [];
+	#positions = /* @__PURE__ */ new Map();
+	get size() {
+		return this.#items.length;
 	}
-	return true;
-}
-function filteredIssues(report, filters) {
-	return report.issues.filter((issue) => {
-		if (filters.category && issue.category !== filters.category) return false;
-		if (filters.severity && issue.severity !== filters.severity) return false;
-		if (filters.url && !matchesPattern(filters.url, issue.url)) return false;
-		if ((filters.recommendation ?? "fix") !== recommendationForRule(issue.ruleId)) return false;
-		return true;
-	});
-}
-function groupIssues(issues) {
-	const groups = /* @__PURE__ */ new Map();
-	for (const issue of issues) {
-		const existing = groups.get(issue.ruleId) ?? {
-			ruleId: issue.ruleId,
-			title: issue.title,
-			category: issue.category,
-			severity: issue.severity,
-			count: 0,
-			sampleUrls: []
-		};
-		existing.count += 1;
-		if (existing.sampleUrls.length < 10) existing.sampleUrls.push(issue.url);
-		groups.set(issue.ruleId, existing);
+	has(url) {
+		return this.#positions.has(url);
 	}
-	return [...groups.values()];
-}
-function searchValueForGroup(report, urls) {
-	const wanted = new Set(urls);
-	const pages = report.pages.filter((page) => wanted.has(page.url) || wanted.has(page.finalUrl));
-	const metrics = pages.map((page) => page.searchMetrics).filter((item) => Boolean(item));
-	const clicks = metrics.reduce((sum, item) => sum + item.clicks, 0);
-	const impressions = metrics.reduce((sum, item) => sum + item.impressions, 0);
-	const sessions = pages.reduce((sum, page) => sum + (page.analytics?.sessions ?? 0), 0);
-	const observedMetrics = new Set(report.dataSources?.analytics.observedMetrics ?? [
-		"sessions",
-		"totalUsers",
-		"conversions"
-	]);
-	const totalUsers = observedMetrics.has("totalUsers") ? pages.reduce((sum, page) => sum + (page.analytics?.totalUsers ?? 0), 0) : void 0;
-	const conversions = observedMetrics.has("conversions") ? pages.reduce((sum, page) => sum + (page.analytics?.conversions ?? 0), 0) : void 0;
-	const avgPosition = metrics.length ? metrics.reduce((sum, item) => sum + item.position, 0) / metrics.length : void 0;
-	return {
-		searchVisibleUrls: metrics.length,
-		clicks,
-		impressions,
-		sessions,
-		totalUsers,
-		conversions,
-		avgPosition
-	};
-}
-function whyThisRanks(input, recommendation, searchStatus, analyticsProvider) {
-	const visibility = input.searchVisibleUrls ? `${input.searchVisibleUrls} affected URLs have GSC visibility (${input.clicks} clicks, ${input.impressions} impressions).` : searchStatus && !["joined", "none"].includes(searchStatus) ? `No joined GSC visibility is available for these affected URLs; Search Console evidence is ${searchStatus}.` : "No affected URL has joined GSC visibility yet.";
-	const analyticsDetails = analyticsProvider ? analyticsProviderDetails(analyticsProvider) : analyticsProviderDetails("google");
-	const analyticsLabel = analyticsDetails.label;
-	const sessionLabel = analyticsDetails.landingMetricLabel;
-	return `${visibility}${input.sessions ? ` ${analyticsLabel} adds ${input.sessions} ${sessionLabel}${input.conversions === void 0 ? "" : ` and ${input.conversions} conversions`} from affected pages.` : ""} ${recommendation === "review" ? "This is a review observation. Confirm it before scheduling implementation work." : `This ranks as a fix. Severity is ${input.severity}; ${input.affectedUrls} URL${input.affectedUrls === 1 ? " is" : "s are"} affected; estimated effort is ${input.effort}.`}`;
-}
-function verificationCommand(report, severity) {
-	return `seo crawl ${report.config.url} --severity ${severity} --max-pages ${Math.min(report.config.maxPages, 100)}`;
-}
-function topFixes(report, filters = {}) {
-	return groupIssues(filteredIssues(report, filters)).map((group) => {
-		const search = searchValueForGroup(report, group.sampleUrls);
-		const effort = EFFORT_BY_CATEGORY[group.category] ?? "medium";
-		const scoreFactors = {
-			severity: SEVERITY_SCORE[group.severity],
-			affectedUrls: group.count,
-			searchVisibleUrls: search.searchVisibleUrls,
-			clicks: search.clicks,
-			impressions: search.impressions,
-			sessions: search.sessions,
-			totalUsers: search.totalUsers,
-			conversions: search.conversions,
-			avgPosition: search.avgPosition,
-			effort,
-			effortScore: EFFORT_SCORE[effort]
-		};
-		const valueWeight = VALUE_WEIGHT[group.severity];
-		const score = scoreFactors.severity + scoreFactors.affectedUrls * AFFECTED_URL_WEIGHT[group.severity] + scoreFactors.searchVisibleUrls * 100 * valueWeight + scoreFactors.clicks * 20 * valueWeight + Math.min(scoreFactors.impressions, 1e4) / 25 * valueWeight + scoreFactors.sessions * 2 * valueWeight + (scoreFactors.conversions ?? 0) * 100 * valueWeight + scoreFactors.effortScore;
-		const rule = explainRule(group.ruleId);
-		const recommendation = recommendationForRule(group.ruleId);
-		return {
-			...group,
-			recommendation,
-			score: Math.round(score),
-			scoreFactors,
-			whyThisRanks: whyThisRanks(scoreFactors, recommendation, report.dataSources?.searchConsole.status, report.dataSources?.analytics.provider),
-			howToFix: rule?.howToFix ?? "",
-			howToVerify: rule?.howToVerify ?? "",
-			verification: {
-				command: verificationCommand(report, group.severity),
-				expected: rule?.howToVerify ?? ""
-			}
-		};
-	}).sort((a, b) => reachRank(a.ruleId) - reachRank(b.ruleId) || b.score - a.score || SEVERITY_SCORE[b.severity] - SEVERITY_SCORE[a.severity] || b.count - a.count || a.ruleId.localeCompare(b.ruleId)).slice(0, filters.limit ?? 10);
-}
-function reviewObservations(report, filters = {}) {
-	return topFixes(report, {
-		...filters,
-		recommendation: "review"
-	});
-}
-// packages/core/src/analyze/crawler/export.ts
-const issueHeaders = [
-	"rule_id",
-	"title",
-	"category",
-	"severity",
-	"url",
-	"detail",
-	"clicks",
-	"impressions",
-	"position"
-];
-const pageHeaders = [
-	"url",
-	"final_url",
-	"status",
-	"indexable",
-	"title",
-	"meta_description",
-	"canonical",
-	"word_count",
-	"content_extractor",
-	"content_extractor_type",
-	"content_extraction_fallback",
-	"word_count_source",
-	"internal_links",
-	"internal_inlinks",
-	"internal_authority_score",
-	"external_links",
-	"images_total",
-	"images_missing_alt",
-	"oversized_image_candidates",
-	"schema_types",
-	"clicks",
-	"impressions",
-	"sessions"
-];
-function renderCrawlCsv(report) {
-	return renderCsv(report.issues.map((issue) => ({
-		rule_id: issue.ruleId,
-		title: issue.title,
-		category: issue.category,
-		severity: issue.severity,
-		url: issue.url,
-		detail: issue.detail,
-		clicks: issue.searchMetrics?.clicks,
-		impressions: issue.searchMetrics?.impressions,
-		position: issue.searchMetrics?.position
-	})), issueHeaders);
-}
-function renderCrawlPagesCsv(report) {
-	return renderCsv(report.pages.map((page) => ({
-		url: page.url,
-		final_url: page.finalUrl,
-		status: page.status,
-		indexable: page.indexable,
-		title: page.title,
-		meta_description: page.metaDescription,
-		canonical: page.canonical,
-		word_count: page.wordCount,
-		content_extractor: page.contentExtraction?.used,
-		content_extractor_type: page.contentExtraction?.extractorType,
-		content_extraction_fallback: page.contentExtraction?.fallback,
-		word_count_source: page.contentExtraction?.wordCountSource,
-		internal_links: page.outgoingInternalCount,
-		internal_inlinks: page.internalInlinkCount,
-		internal_authority_score: page.internalLinkAuthorityScore,
-		external_links: page.outgoingExternalCount,
-		images_total: page.imagesTotal,
-		images_missing_alt: page.imagesMissingAlt,
-		oversized_image_candidates: page.oversizedImageCandidates?.length ?? 0,
-		schema_types: page.schemaTypes?.join("|"),
-		clicks: page.searchMetrics?.clicks,
-		impressions: page.searchMetrics?.impressions,
-		sessions: page.analytics?.sessions
-	})), pageHeaders);
-}
-function renderCrawlPretty(report, fixes = topFixes(report)) {
-	const reviews = reviewObservations(report);
-	const requestSummary = report.requestEvidenceStatus === "available" ? `${report.requests.length} requests` : report.requestEvidenceStatus === "partial" ? `${report.requests.length} observed requests; some started requests were still in flight when the crawl stopped` : "request evidence unavailable for this legacy report";
-	const lines = [
-		`Crawl report for ${report.config.url}`,
-		"",
-		`Status: ${report.status}`,
-		`Strategy: ${report.config.strategy === "health" ? "sitemap health pass" : "full audit"}`,
-		`Crawler: ${report.access.crawler.userAgent}`,
-		`Documents: ${report.summary.totalPages} retained; ${requestSummary}, ${report.summary.discoveredUrls} URLs discovered, ${report.summary.failedUrls} failed, ${report.summary.skippedUrls} skipped`,
-		`Issues: ${report.issues.length} (${report.summary.highIssues} high, ${report.summary.mediumIssues} medium, ${report.summary.lowIssues} low)`
-	];
-	if (report.externalLinkVerification) {
-		const external = report.externalLinkVerification;
-		lines.push(`External links: ${external.fetchedUrls} fetched, ${external.failedUrls} request failure${external.failedUrls === 1 ? "" : "s"}, ${external.deferredUrls} deferred (${external.dataStatus})`);
+	push(item) {
+		if (this.has(item.url)) throw new Error(`URL is already queued: ${item.url}`);
+		const index = this.#items.length;
+		this.#items.push(item);
+		this.#positions.set(item.url, index);
+		this.#bubbleUp(index);
 	}
-	if (report.access.blockedRequests > 0) {
-		lines.push("", `Access blocks: ${report.access.blockedRequests}`);
-		for (const sample of report.access.samples.slice(0, 3)) {
-			const requestId = sample.evidence.requestId ? `, request ID ${sample.evidence.requestId}` : "";
-			lines.push(`- ${sample.url}: ${sample.evidence.guidance.summary} (${sample.evidence.provider}${requestId})`, `  Action: ${sample.evidence.guidance.recommendedAction}`, `  Security: ${sample.evidence.guidance.securityNote}`);
-			if (sample.evidence.guidance.documentationUrl) lines.push(`  Provider docs: ${sample.evidence.guidance.documentationUrl}`);
-		}
+	decreaseDepth(url, depth) {
+		const index = this.#positions.get(url);
+		if (index === void 0) return false;
+		const item = this.#items[index];
+		if (!item || depth >= item.depth) return false;
+		item.depth = depth;
+		this.#bubbleUp(index);
+		return true;
 	}
-	if (fixes.length) {
-		lines.push("", "Prioritised fixes");
-		for (const fix of fixes.slice(0, 5)) {
-			lines.push(`- ${fix.title} (${fix.severity}, ${fix.count} URL${fix.count === 1 ? "" : "s"}): ${fix.howToFix}`);
-			if (fix.sampleUrls[0]) lines.push(`  First URL: ${fix.sampleUrls[0]}`);
+	take() {
+		const first = this.#items[0];
+		if (!first) return void 0;
+		const last = this.#items.pop();
+		this.#positions.delete(first.url);
+		if (last && last !== first) {
+			this.#items[0] = last;
+			this.#positions.set(last.url, 0);
+			this.#bubbleDown(0);
 		}
-	} else lines.push("", "No prioritised fixes found.");
-	if (reviews.length) {
-		lines.push("", "Review observations (check before scheduling work)");
-		for (const observation of reviews.slice(0, 5)) {
-			lines.push(`- ${observation.title} (${observation.severity}, ${observation.count} URL${observation.count === 1 ? "" : "s"}): ${observation.howToFix}`);
-			if (observation.sampleUrls[0]) lines.push(`  First URL: ${observation.sampleUrls[0]}`);
+		return first;
+	}
+	#swap(left, right) {
+		const leftItem = this.#items[left];
+		const rightItem = this.#items[right];
+		if (!leftItem || !rightItem) return;
+		this.#items[left] = rightItem;
+		this.#items[right] = leftItem;
+		this.#positions.set(rightItem.url, left);
+		this.#positions.set(leftItem.url, right);
+	}
+	#bubbleUp(start) {
+		let index = start;
+		while (index > 0) {
+			const parent = Math.floor((index - 1) / 2);
+			const item = this.#items[index];
+			const parentItem = this.#items[parent];
+			if (!item || !parentItem || !before(item, parentItem)) break;
+			this.#swap(index, parent);
+			index = parent;
 		}
 	}
-	lines.push("", "Next commands", report.config.strategy === "health" ? `- seo crawl ${report.config.url} --max-pages ${report.config.maxPages} --json` : `- seo crawl ${report.config.url} --json`);
-	for (const command of [...new Set(fixes.slice(0, 3).map((fix) => fix.verification.command))]) lines.push(`- ${command}`);
-	if (report.warnings.length) lines.push("", "Warnings", ...report.warnings.map((item) => `- ${item}`));
-	if (report.caveats.length) lines.push("", "Caveats", ...report.caveats.map((item) => `- ${item}`));
-	return `${lines.join("\n")}\n`;
-}
-function renderCrawlJunit(report) {
-	const issuesByUrl = /* @__PURE__ */ new Map();
-	for (const issue of report.issues) {
-		const existing = issuesByUrl.get(issue.url) ?? [];
-		existing.push(issue);
-		issuesByUrl.set(issue.url, existing);
+	#bubbleDown(start) {
+		let index = start;
+		while (true) {
+			const left = index * 2 + 1;
+			const right = left + 1;
+			let next = index;
+			const item = this.#items[next];
+			const leftItem = this.#items[left];
+			const rightItem = this.#items[right];
+			if (leftItem && item && before(leftItem, item)) next = left;
+			const nextItem = this.#items[next];
+			if (rightItem && nextItem && before(rightItem, nextItem)) next = right;
+			if (next === index) return;
+			this.#swap(index, next);
+			index = next;
+		}
 	}
-	const sitemapCases = (report.sitemapDiscovery?.roots ?? []).flatMap((root) => {
-		return (root.documents.length ? root.documents : [{
-			url: root.url,
-			dataStatus: root.dataStatus,
-			compression: "none",
-			warning: root.warnings.join(" ") || void 0
-		}]).map((document) => {
-			const failures = [
-				...document.dataStatus !== "complete" ? [document.warning ?? `Sitemap evidence is ${document.dataStatus}.`] : [],
-				...document.redirected ? [`Sitemap redirected to ${document.finalUrl ?? "an unknown URL"}.`] : [],
-				...document.status !== void 0 && (document.status < 200 || document.status >= 300) ? [`Sitemap returned HTTP ${document.status}.`] : []
-			];
-			const output = [
-				`dataStatus=${document.dataStatus}`,
-				...document.status !== void 0 ? [`status=${document.status}`] : [],
-				...document.finalUrl ? [`finalUrl=${document.finalUrl}`] : [],
-				...document.root ? [`root=${document.root}`] : [],
-				...document.warning ? [`warning=${document.warning}`] : []
-			].join("\n");
-			return {
-				xml: [
-					`  <testcase classname="seo.sitemap-document" name="${escapeXml(document.url)}" time="0.000">`,
-					...failures.length ? [`    <failure message="${escapeXml(failures[0] ?? "Sitemap check failed")}">${escapeXml(failures.join("\n"))}</failure>`] : [],
-					`    <system-out>${escapeXml(output)}</system-out>`,
-					"  </testcase>"
-				].join("\n"),
-				failed: failures.length > 0
-			};
-		});
-	});
-	const requestCases = report.requests.map((request) => {
-		const failures = [
-			...(issuesByUrl.get(request.requestedUrl) ?? []).map((issue) => `${issue.severity}: ${issue.title}${issue.detail ? `: ${issue.detail}` : ""}`),
-			...request.outcome === "failure" ? [`${request.failureKind}: ${request.error}`] : [],
-			...request.outcome === "skipped" ? [request.reason === "origin-backpressure" ? request.error : `${request.reason}: ${request.robotsTxt.matchedLine ?? request.robotsTxt.availability}`] : []
-		];
-		const output = request.outcome === "response" ? [
-			`status=${request.status}`,
-			`finalUrl=${request.finalUrl}`,
-			...request.robotsTxt ? [
-				`robotsUrl=${request.robotsTxt.url}`,
-				`robotsAllowed=${request.robotsTxt.allowed ?? "unknown"}`,
-				`robotsAvailability=${request.robotsTxt.availability}`,
-				...request.robotsTxt.status !== void 0 ? [`robotsStatus=${request.robotsTxt.status}`] : [],
-				...request.robotsTxt.matchedLine ? [`robotsMatchedLine=${request.robotsTxt.matchedLine}`] : [],
-				...request.robotsTxt.error ? [`robotsError=${request.robotsTxt.error}`] : []
-			] : [],
-			...request.accessBlock ? [
-				`accessProvider=${request.accessBlock.provider}`,
-				`crawler=${request.accessBlock.crawler.userAgent}`,
-				...request.accessBlock.requestId ? [`requestId=${request.accessBlock.requestId}`] : []
-			] : []
-		].join("\n") : request.outcome === "failure" ? request.error : request.reason === "origin-backpressure" ? `reason=${request.reason}\nerror=${request.error}` : [
-			`reason=${request.reason}`,
-			`robotsUrl=${request.robotsTxt.url}`,
-			`robotsAllowed=${request.robotsTxt.allowed ?? "unknown"}`,
-			`robotsAvailability=${request.robotsTxt.availability}`,
-			...request.robotsTxt.status !== void 0 ? [`robotsStatus=${request.robotsTxt.status}`] : [],
-			...request.robotsTxt.matchedLine ? [`robotsMatchedLine=${request.robotsTxt.matchedLine}`] : [],
-			...request.robotsTxt.error ? [`robotsError=${request.robotsTxt.error}`] : []
-		].join("\n");
-		const duration = ((request.durationMs ?? 0) / 1e3).toFixed(3);
-		return {
-			xml: [
-				`  <testcase classname="seo.sitemap-health" name="${escapeXml(request.requestedUrl)}" time="${duration}">`,
-				...failures.length ? [`    <failure message="${escapeXml(failures[0] ?? "Health check failed")}">${escapeXml(failures.join("\n"))}</failure>`] : [],
-				`    <system-out>${escapeXml(output)}</system-out>`,
-				"  </testcase>"
-			].join("\n"),
-			failed: failures.length > 0
-		};
-	});
-	const cases = [...sitemapCases, ...requestCases];
-	const failures = cases.filter((item) => item.failed).length;
-	const elapsed = report.requests.reduce((sum, request) => sum + (request.durationMs ?? 0), 0);
-	return [
-		"<?xml version=\"1.0\" encoding=\"UTF-8\"?>",
-		`<testsuite name="seo sitemap health" tests="${cases.length}" failures="${failures}" errors="0" skipped="0" time="${(elapsed / 1e3).toFixed(3)}">`,
-		"  <properties>",
-		`    <property name="report.id" value="${escapeXml(report.id)}"/>`,
-		`    <property name="report.status" value="${escapeXml(report.status)}"/>`,
-		`    <property name="crawl.strategy" value="${escapeXml(report.config.strategy)}"/>`,
-		`    <property name="crawler.userAgent" value="${escapeXml(report.access.crawler.userAgent)}"/>`,
-		"  </properties>",
-		...cases.map((item) => item.xml),
-		"</testsuite>",
-		""
-	].join("\n");
-}
-function renderCrawlHtml(report, fixes = topFixes(report)) {
-	const reviews = reviewObservations(report);
-	const issueRows = report.issueGroups.map((group) => {
-		const rule = explainRule(group.ruleId);
-		return `<tr><td>${escapeHtml(group.severity)}</td><td>${escapeHtml(group.title)}</td><td>${group.count}</td><td>${escapeHtml(rule?.howToFix ?? "")}</td><td>${escapeHtml(group.sampleUrls[0] ?? "")}</td></tr>`;
-	}).join("\n");
-	const fixItems = fixes.slice(0, 10).map((fix) => `<li><strong>${escapeHtml(fix.title)}</strong><br>${escapeHtml(fix.howToFix)}<br><span>Verify: ${escapeHtml(fix.howToVerify)}</span><br><code>${escapeHtml(fix.verification.command)}</code></li>`).join("\n");
-	const reviewItems = reviews.slice(0, 10).map((observation) => `<li><strong>${escapeHtml(observation.title)}</strong><br>${escapeHtml(observation.howToFix)}<br><span>Check before scheduling work. ${escapeHtml(observation.howToVerify)}</span></li>`).join("\n");
-	const caveatItems = report.caveats.map((caveat) => `<li>${escapeHtml(caveat)}</li>`).join("\n");
-	const warningItems = report.warnings.map((warning) => `<li>${escapeHtml(warning)}</li>`).join("\n");
-	const accessItems = report.access.samples.map((sample) => `<li><strong>${escapeHtml(sample.url)}</strong><br>${escapeHtml(sample.evidence.guidance.summary)}<br>${escapeHtml(sample.evidence.guidance.recommendedAction)}<br><span>${escapeHtml(sample.evidence.guidance.securityNote)}</span></li>`).join("\n");
-	return `<!doctype html>
-<html lang="en">
-<head>
-  <meta charset="utf-8">
-  <meta name="viewport" content="width=device-width, initial-scale=1">
-  <title>Crawl report for ${escapeHtml(report.config.url)}</title>
-  <style>
-    body { color: #17202a; font: 15px/1.5 system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif; margin: 32px; max-width: 1120px; }
-    h1, h2 { line-height: 1.2; }
-    .summary { display: grid; gap: 12px; grid-template-columns: repeat(auto-fit, minmax(160px, 1fr)); margin: 24px 0; }
-    .metric { border: 1px solid #d8dee4; border-radius: 8px; padding: 12px; }
-    .metric strong { display: block; font-size: 24px; }
-    table { border-collapse: collapse; width: 100%; }
-    th, td { border-bottom: 1px solid #d8dee4; padding: 10px; text-align: left; vertical-align: top; }
-    th { background: #f6f8fa; }
-    li { margin: 0 0 12px; }
-    span { color: #57606a; }
-  </style>
-</head>
-<body>
-  <h1>Crawl report</h1>
-  <p>${escapeHtml(report.config.url)}</p>
-  <p>Strategy: ${escapeHtml(report.config.strategy === "health" ? "sitemap health pass" : "full audit")}<br>Crawler: <code>${escapeHtml(report.access.crawler.userAgent)}</code></p>
-  <section class="summary">
-    <div class="metric"><span>Status</span><strong>${escapeHtml(report.status)}</strong></div>
-    <div class="metric"><span>Documents</span><strong>${report.summary.totalPages}</strong></div>
-    <div class="metric"><span>Requests</span><strong>${report.requestEvidenceStatus === "unavailable" ? "n/a" : report.requests.length}${report.requestEvidenceStatus === "partial" ? " (partial)" : ""}</strong></div>
-    <div class="metric"><span>Discovered</span><strong>${report.summary.discoveredUrls}</strong></div>
-    <div class="metric"><span>Queued</span><strong>${report.summary.queuedUrls}</strong></div>
-    <div class="metric"><span>Skipped</span><strong>${report.summary.skippedUrls}</strong></div>
-    <div class="metric"><span>Failed fetches</span><strong>${report.summary.failedUrls}</strong></div>
-    <div class="metric"><span>Observed internal links</span><strong>${report.summary.observedInternalLinks}</strong></div>
-    <div class="metric"><span>Issues</span><strong>${report.issues.length}</strong></div>
-    <div class="metric"><span>High</span><strong>${report.summary.highIssues}</strong></div>
-  </section>
-  ${accessItems ? `<h2>Access blocks</h2><ul>${accessItems}</ul>` : ""}
-  <h2>Prioritised fixes</h2>
-  ${fixItems ? `<ol>${fixItems}</ol>` : "<p>No prioritised fixes found.</p>"}
-  ${reviewItems ? `<h2>Review observations</h2>
-  <p>Check these before scheduling implementation work.</p>
-  <ul>${reviewItems}</ul>` : ""}
-  ${report.caveats.length ? `<h2>Caveats</h2>
-  <ul>${caveatItems}</ul>` : ""}
-  ${report.warnings.length ? `<h2>Warnings</h2>
-  <ul>${warningItems}</ul>` : ""}
-  <h2>Issue groups</h2>
-  <table>
-    <thead><tr><th>Severity</th><th>Issue</th><th>URLs</th><th>Fix</th><th>Sample URL</th></tr></thead>
-    <tbody>${issueRows}</tbody>
-  </table>
-</body>
-</html>
-`;
-}
-function renderCrawlMarkdownTickets(report, fixes = topFixes(report)) {
-	const reviews = reviewObservations(report);
-	const lines = [
-		`# Crawl Implementation Tickets`,
-		"",
-		`Source: ${report.config.url}`,
-		`Report: ${report.id}`,
-		`Status: ${report.status}`,
-		`Strategy: ${report.config.strategy}`,
-		`Crawler: ${report.access.crawler.userAgent}`,
-		""
-	];
-	if (report.caveats.length) lines.push("## Caveats", "", ...report.caveats.map((item) => `- ${item}`), "");
-	if (report.warnings.length) lines.push("## Warnings", "", ...report.warnings.map((item) => `- ${item}`), "");
-	if (report.access.blockedRequests > 0) lines.push("## Access blocks", "", ...report.access.samples.flatMap((sample) => [
-		`- ${sample.url}: ${sample.evidence.guidance.summary}`,
-		`  - Action: ${sample.evidence.guidance.recommendedAction}`,
-		`  - Security: ${sample.evidence.guidance.securityNote}`
-	]), "");
-	for (const [index, fix] of fixes.entries()) lines.push(`## ${index + 1}. ${fix.title}`, "", `- [ ] Fix ${fix.count} affected URL${fix.count === 1 ? "" : "s"}`, `- Severity: ${fix.severity}`, `- Rule: ${fix.ruleId}`, `- Why this ranks: ${fix.whyThisRanks}`, `- Plain-English fix: ${fix.howToFix}`, `- Verify: ${fix.howToVerify}`, `- Command: ${fix.verification.command}`, "", `Affected URLs:`, ...fix.sampleUrls.slice(0, 10).map((url) => `- ${url}`), "");
-	if (!fixes.length) lines.push("No implementation tickets were generated.");
-	if (reviews.length) lines.push("## Review observations", "", "These are not implementation tickets. Check the evidence before deciding whether to work on them.", "", ...reviews.slice(0, 10).flatMap((observation) => [`- ${observation.title} (${observation.severity}, ${observation.count} URL${observation.count === 1 ? "" : "s"}): ${observation.howToFix}`, `  - First URL: ${observation.sampleUrls[0] ?? "No sample URL recorded"}`]), "");
-	return `${lines.join("\n")}\n`;
-}
-function escapeHtml(value) {
-	return value.replaceAll("&", "&amp;").replaceAll("<", "&lt;").replaceAll(">", "&gt;").replaceAll("\"", "&quot;").replaceAll("'", "&#39;");
-}
-function escapeXml(value) {
-	return escapeHtml(value);
-}
+};
 // packages/core/src/analyze/crawler/report.ts
 const MAX_CRAWL_PAGES = 1e4;
 const MAX_CRAWL_DEPTH = 64;
@@ -13065,6 +12688,10 @@ function sanitizeMessages(values = []) {
 function compareText$17(left, right) {
 	return left < right ? -1 : left > right ? 1 : 0;
 }
+function compareCaveats(left, right) {
+	const rank = (value) => value.startsWith("Coverage incomplete:") ? 0 : 1;
+	return rank(left) - rank(right) || compareText$17(left, right);
+}
 function sortPages(pages) {
 	return [...pages].sort((left, right) => compareText$17(left.url, right.url));
 }
@@ -13216,123 +12843,661 @@ function normalizeLinkUrl(value) {
 		return;
 	}
 }
-function deriveInternalLinkAuthority(pages, linkGraph) {
-	const hasLinkGraph = linkGraph && Object.keys(linkGraph).length > 0;
-	const hasStoredScores = pages.some((page) => page.internalInlinkCount !== void 0 || page.internalLinkAuthorityScore !== void 0);
-	if (!hasLinkGraph && hasStoredScores) {
-		if (pages.every((page) => page.internalInlinkCount !== void 0 && page.internalLinkAuthorityScore !== void 0)) return pages;
-		return pages.map((page) => page.internalInlinkCount !== void 0 && page.internalLinkAuthorityScore !== void 0 ? page : {
-			...page,
-			internalInlinkCount: page.internalInlinkCount ?? 0,
-			internalLinkAuthorityScore: page.internalLinkAuthorityScore ?? 0
-		});
+function deriveInternalLinkAuthority(pages, linkGraph) {
+	const hasLinkGraph = linkGraph && Object.keys(linkGraph).length > 0;
+	const hasStoredScores = pages.some((page) => page.internalInlinkCount !== void 0 || page.internalLinkAuthorityScore !== void 0);
+	if (!hasLinkGraph && hasStoredScores) {
+		if (pages.every((page) => page.internalInlinkCount !== void 0 && page.internalLinkAuthorityScore !== void 0)) return pages;
+		return pages.map((page) => page.internalInlinkCount !== void 0 && page.internalLinkAuthorityScore !== void 0 ? page : {
+			...page,
+			internalInlinkCount: page.internalInlinkCount ?? 0,
+			internalLinkAuthorityScore: page.internalLinkAuthorityScore ?? 0
+		});
+	}
+	const pageByUrl = /* @__PURE__ */ new Map();
+	for (const page of pages) for (const value of [page.url, page.finalUrl]) {
+		const normalized = normalizeLinkUrl(value);
+		if (normalized) pageByUrl.set(normalized, page.url);
+	}
+	const inlinks = /* @__PURE__ */ new Map();
+	for (const page of pages) inlinks.set(page.url, 0);
+	for (const page of pages) {
+		const targets = hasLinkGraph ? linkGraph?.[page.url] ?? linkGraph?.[page.finalUrl] ?? [] : page.sampleInternalLinks ?? [];
+		const linkedPages = /* @__PURE__ */ new Set();
+		for (const target of targets) {
+			const normalized = normalizeLinkUrl(target);
+			const linkedPage = normalized ? pageByUrl.get(normalized) : void 0;
+			if (!linkedPage || linkedPage === page.url) continue;
+			linkedPages.add(linkedPage);
+		}
+		for (const linkedPage of linkedPages) inlinks.set(linkedPage, (inlinks.get(linkedPage) ?? 0) + 1);
+	}
+	let maxInlinks = 0;
+	for (const count of inlinks.values()) maxInlinks = Math.max(maxInlinks, count);
+	return pages.map((page) => {
+		const internalInlinkCount = inlinks.get(page.url) ?? 0;
+		return {
+			...page,
+			internalInlinkCount,
+			internalLinkAuthorityScore: maxInlinks ? Math.round(internalInlinkCount / maxInlinks * 100) : 0
+		};
+	});
+}
+function createCrawlReport(input) {
+	const config = sanitizeCrawlConfig(normalizeCrawlConfig(input.config));
+	const definitionId = crawlDefinitionId({
+		config,
+		site: input.site,
+		googleAnalyticsPropertyId: input.googleAnalyticsPropertyId,
+		analyticsConnection: input.analyticsConnection
+	});
+	const safePagesWithLinks = sortPages(sanitizePages(deriveInternalLinkAuthority(input.pages ?? [], input.linkGraph)));
+	const requests = sortRequests(sanitizeTenantValue(input.requests ?? []));
+	const requestEvidenceStatus = input.requestEvidenceStatus ?? (input.requests ? "available" : "unavailable");
+	if (requestEvidenceStatus === "unavailable" && requests.length > 0) throw new Error("Unavailable request evidence cannot include request observations.");
+	const safeIssues = sanitizeIssues([...input.issues ?? [...auditCrawlRequests(requests), ...auditCrawlPages(safePagesWithLinks, { startUrl: config.url })], ...input.additionalIssues ?? []]);
+	const pages = safePagesWithLinks;
+	return {
+		id: input.id ?? crawlRunId(),
+		definitionId,
+		site: input.site,
+		googleAnalyticsPropertyId: input.googleAnalyticsPropertyId,
+		analyticsConnection: input.analyticsConnection,
+		generatedAt: input.generatedAt ?? (/* @__PURE__ */ new Date()).toISOString(),
+		status: input.status ?? "completed",
+		configHash: crawlConfigHash(config),
+		config,
+		access: crawlAccessSummary(requests),
+		summary: summarizeCrawlReport({
+			pages,
+			requests,
+			requestEvidenceStatus,
+			issues: safeIssues,
+			stats: input.stats
+		}),
+		requestEvidenceStatus,
+		requests,
+		pages,
+		issues: safeIssues,
+		issueGroups: groupCrawlIssues(safeIssues),
+		...input.dataSources ? { dataSources: sanitizeTenantValue(input.dataSources) } : {},
+		...input.ai ? { ai: sanitizeTenantValue(input.ai) } : {},
+		...input.sitemapDiscovery ? { sitemapDiscovery: sanitizeTenantValue(input.sitemapDiscovery) } : {},
+		...input.externalLinkVerification ? { externalLinkVerification: sanitizeTenantValue(input.externalLinkVerification) } : {},
+		...input.siteChecks ? { siteChecks: sanitizeTenantValue(input.siteChecks) } : {},
+		warnings: sanitizeMessages(input.warnings).sort(compareText$17),
+		caveats: sanitizeMessages(input.caveats).sort(compareCaveats)
+	};
+}
+function normalizeLoadedCrawlReport(report) {
+	const config = sanitizeCrawlConfig(normalizeCrawlConfig(report.config));
+	const requestEvidenceStatus = report.requestEvidenceStatus ?? (Object.hasOwn(report, "requests") ? "available" : "unavailable");
+	const issues = sanitizeIssues(report.issues ?? []);
+	const requests = sortRequests(sanitizeTenantValue(report.requests ?? []) ?? []);
+	const pages = sortPages(sanitizePages(deriveInternalLinkAuthority(report.pages ?? [])));
+	return {
+		...sanitizeTenantValue(report),
+		config,
+		access: crawlAccessSummary(requests),
+		requestEvidenceStatus,
+		requests,
+		definitionId: report.definitionId ?? crawlDefinitionId({
+			config,
+			site: report.site,
+			googleAnalyticsPropertyId: report.googleAnalyticsPropertyId,
+			analyticsConnection: report.analyticsConnection
+		}),
+		summary: summarizeCrawlReport({
+			pages,
+			requests,
+			requestEvidenceStatus,
+			issues,
+			stats: report.summary
+		}),
+		pages,
+		issues,
+		issueGroups: groupCrawlIssues(issues),
+		warnings: sanitizeMessages(report.warnings).sort(compareText$17),
+		caveats: sanitizeMessages(report.caveats).sort(compareCaveats)
+	};
+}
+// packages/core/src/analyze/crawler/crawl-caveats.ts
+/** Reports rank a caveat with this prefix first and lead with it. */
+const CRAWL_COVERAGE_CAVEAT_PREFIX = "Coverage incomplete:";
+function rateLimitRerunCommand(config, intervalMs) {
+	const scope = config.strategy === "health" ? " --health" : config.mode === "site" ? "" : ` --mode ${config.mode}`;
+	const sitemap = config.sitemapUrl ? ` --sitemap-url ${config.sitemapUrl}` : "";
+	const slowMs = Math.min(8e3, Math.max(2e3, intervalMs * 2));
+	return `seo crawl ${config.url}${scope}${sitemap} --max-pages ${config.maxPages} --concurrency 1 --fetch-interval-cap 1 --fetch-interval-ms ${slowMs}`;
+}
+/** Set when the sitemaps list more URLs than the page limit let the crawl read. */
+function sitemapLimitCaveatInput(config, discovery, defaulted) {
+	if (!discovery || discovery.urlsReturned < config.maxPages || !discovery.roots.some((root) => root.possiblyTruncated)) return;
+	return {
+		maxPages: config.maxPages,
+		defaulted,
+		ceiling: MAX_CRAWL_PAGES,
+		health: config.strategy === "health",
+		url: config.url
+	};
+}
+function crawlCaveats(input) {
+	const caveats = input.cancelled ? ["Crawl cancelled before all queued URLs finished."] : input.pageLimitReached ? [`Stopped after reaching maxPages (${input.maxPages}).`] : [];
+	if (input.queueSafetySkippedUrls > 0) caveats.push(input.queueSafetyInventoryCapped ? `Left at least ${input.queueSafetySkippedUrls} unique eligible same-origin URLs unqueued to keep this crawl bounded. The excluded-URL inventory reached its reporting cap. Increase --max-pages to inspect more.` : `Left ${input.queueSafetySkippedUrls} unique eligible same-origin URLs unqueued to keep this crawl bounded. Increase --max-pages to inspect more.`);
+	if (input.originBackpressureSkippedUrls > 0) caveats.push(`Stopped ${input.originBackpressureSkippedUrls} queued URL${input.originBackpressureSkippedUrls === 1 ? "" : "s"} because the origin stayed slow. This is incomplete crawl evidence, not a failed URL check.`);
+	if (input.rateLimit) {
+		const { readPages, skippedUrls, rerunCommand } = input.rateLimit;
+		caveats.push(`${CRAWL_COVERAGE_CAVEAT_PREFIX} read ${readPages} of ${readPages + skippedUrls} pages because the origin kept rate limiting the crawl (HTTP 429) after it backed off. Rerun slower: ${rerunCommand}`);
+	}
+	if (input.sitemapLimit) {
+		const { maxPages, defaulted, ceiling, health, url } = input.sitemapLimit;
+		caveats.push(`Checked only the first ${maxPages} sitemap URLs because the page limit is ${maxPages}${defaulted ? " by default" : ""}, and the sitemaps list more. Raise --max-pages, up to ${ceiling.toLocaleString("en-US")}, to check more: seo crawl ${url}${health ? " --health" : ""} --max-pages ${ceiling}`);
+	}
+	if (input.memoryPressureSkippedUrls > 0) caveats.push(`Left ${input.memoryPressureSkippedUrls} eligible URL${input.memoryPressureSkippedUrls === 1 ? "" : "s"} unchecked after the local memory safety limit was reached. Start with --health or lower --max-pages.`);
+	const renderingFallbackUrls = input.renderingFallbackUrls ?? 0;
+	if (renderingFallbackUrls > 0) caveats.push(`JavaScript rendering could not run for ${renderingFallbackUrls} page${renderingFallbackUrls === 1 ? "" : "s"}, so ${renderingFallbackUrls === 1 ? "it was" : "they were"} audited from raw HTML. Client-rendered content, metadata and links may be missing. Install Chromium or set SEO_BROWSER_EXECUTABLE_PATH, then rerun.`);
+	const queryVariantSkippedUrls = input.queryVariantSkippedUrls ?? 0;
+	if (queryVariantSkippedUrls > 0) caveats.push(`Left ${queryVariantSkippedUrls} query-string variant${queryVariantSkippedUrls === 1 ? "" : "s"} unqueued after 5 variants of the same path, so tracking parameters do not fill the crawl.`);
+	for (const issue of input.reachIssues ?? []) if (issue.detail) caveats.push(issue.detail);
+	return caveats;
+}
+/**
+* A site crawl that found no internal links on the start page and no sitemap
+* URLs checked one page, so its other findings cannot stand for the site.
+*/
+function crawlReachIssues(input) {
+	const [page] = input.pages;
+	if (input.crawledPages !== 1 || input.pages.length !== 1 || !page || page.outgoingInternalCount > 0 || input.sitemapUrlsReturned > 0) return [];
+	const rule = explainRule("crawl_single_page_reach");
+	if (!rule) throw new Error("Missing rule guidance for crawl_single_page_reach");
+	return [{
+		ruleId: "crawl_single_page_reach",
+		title: rule.title,
+		category: rule.category,
+		severity: rule.defaultSeverity,
+		url: page.url,
+		detail: page.usedJs ? "The rendered start page had 0 internal links and no sitemap returned URLs, so the crawl checked only this page. List the pages to check with --mode list." : "The start page had 0 internal links in its HTML and no sitemap returned URLs, so the crawl checked only this page. It probably builds its links with JavaScript. Rerun with --rendering on, or list the pages with --mode list.",
+		evidence: {
+			startUrl: input.startUrl,
+			crawledPages: 1,
+			outgoingInternalCount: 0,
+			sitemapUrlsReturned: 0,
+			rendered: Boolean(page.usedJs)
+		}
+	}];
+}
+// packages/core/src/analyze/crawler/top-fixes.ts
+const SEVERITY_SCORE = {
+	high: 5e3,
+	medium: 1200,
+	low: 100
+};
+const EFFORT_BY_CATEGORY = {
+	canonical: "medium",
+	content: "high",
+	agents: "low",
+	headings: "low",
+	images: "medium",
+	indexability: "medium",
+	international: "low",
+	metadata: "low",
+	mobile: "low",
+	response: "medium",
+	security: "medium",
+	social: "low",
+	"structured-data": "medium"
+};
+const EFFORT_SCORE = {
+	low: 60,
+	medium: 30,
+	high: 0
+};
+const AFFECTED_URL_WEIGHT = {
+	high: 25,
+	medium: 15,
+	low: 2
+};
+const VALUE_WEIGHT = {
+	high: 1,
+	medium: .75,
+	low: .15
+};
+const CRAWL_REACH_RULES = /* @__PURE__ */ new Set(["crawl_single_page_reach"]);
+function reachRank(ruleId) {
+	return CRAWL_REACH_RULES.has(ruleId) ? 0 : 1;
+}
+function matchesPattern(pattern, value) {
+	if (!pattern.includes("*")) return value.includes(pattern);
+	const parts = pattern.split("*");
+	let position = 0;
+	for (const part of parts) {
+		if (!part) continue;
+		const found = value.slice(position).indexOf(part);
+		if (found === -1) return false;
+		position += found + part.length;
+	}
+	return true;
+}
+function filteredIssues(report, filters) {
+	return report.issues.filter((issue) => {
+		if (filters.category && issue.category !== filters.category) return false;
+		if (filters.severity && issue.severity !== filters.severity) return false;
+		if (filters.url && !matchesPattern(filters.url, issue.url)) return false;
+		if ((filters.recommendation ?? "fix") !== recommendationForRule(issue.ruleId)) return false;
+		return true;
+	});
+}
+function groupIssues(issues) {
+	const groups = /* @__PURE__ */ new Map();
+	for (const issue of issues) {
+		const existing = groups.get(issue.ruleId) ?? {
+			ruleId: issue.ruleId,
+			title: issue.title,
+			category: issue.category,
+			severity: issue.severity,
+			count: 0,
+			sampleUrls: []
+		};
+		existing.count += 1;
+		if (existing.sampleUrls.length < 10) existing.sampleUrls.push(issue.url);
+		groups.set(issue.ruleId, existing);
+	}
+	return [...groups.values()];
+}
+function searchValueForGroup(report, urls) {
+	const wanted = new Set(urls);
+	const pages = report.pages.filter((page) => wanted.has(page.url) || wanted.has(page.finalUrl));
+	const metrics = pages.map((page) => page.searchMetrics).filter((item) => Boolean(item));
+	const clicks = metrics.reduce((sum, item) => sum + item.clicks, 0);
+	const impressions = metrics.reduce((sum, item) => sum + item.impressions, 0);
+	const sessions = pages.reduce((sum, page) => sum + (page.analytics?.sessions ?? 0), 0);
+	const observedMetrics = new Set(report.dataSources?.analytics.observedMetrics ?? [
+		"sessions",
+		"totalUsers",
+		"conversions"
+	]);
+	const totalUsers = observedMetrics.has("totalUsers") ? pages.reduce((sum, page) => sum + (page.analytics?.totalUsers ?? 0), 0) : void 0;
+	const conversions = observedMetrics.has("conversions") ? pages.reduce((sum, page) => sum + (page.analytics?.conversions ?? 0), 0) : void 0;
+	const avgPosition = metrics.length ? metrics.reduce((sum, item) => sum + item.position, 0) / metrics.length : void 0;
+	return {
+		searchVisibleUrls: metrics.length,
+		clicks,
+		impressions,
+		sessions,
+		totalUsers,
+		conversions,
+		avgPosition
+	};
+}
+function whyThisRanks(input, recommendation, searchStatus, analyticsProvider) {
+	const visibility = input.searchVisibleUrls ? `${input.searchVisibleUrls} affected URLs have GSC visibility (${input.clicks} clicks, ${input.impressions} impressions).` : searchStatus && !["joined", "none"].includes(searchStatus) ? `No joined GSC visibility is available for these affected URLs; Search Console evidence is ${searchStatus}.` : "No affected URL has joined GSC visibility yet.";
+	const analyticsDetails = analyticsProvider ? analyticsProviderDetails(analyticsProvider) : analyticsProviderDetails("google");
+	const analyticsLabel = analyticsDetails.label;
+	const sessionLabel = analyticsDetails.landingMetricLabel;
+	return `${visibility}${input.sessions ? ` ${analyticsLabel} adds ${input.sessions} ${sessionLabel}${input.conversions === void 0 ? "" : ` and ${input.conversions} conversions`} from affected pages.` : ""} ${recommendation === "review" ? "This is a review observation. Confirm it before scheduling implementation work." : `This ranks as a fix. Severity is ${input.severity}; ${input.affectedUrls} URL${input.affectedUrls === 1 ? " is" : "s are"} affected; estimated effort is ${input.effort}.`}`;
+}
+function verificationCommand(report, severity) {
+	return `seo crawl ${report.config.url} --severity ${severity} --max-pages ${Math.min(report.config.maxPages, 100)}`;
+}
+function topFixes(report, filters = {}) {
+	return groupIssues(filteredIssues(report, filters)).map((group) => {
+		const search = searchValueForGroup(report, group.sampleUrls);
+		const effort = EFFORT_BY_CATEGORY[group.category] ?? "medium";
+		const scoreFactors = {
+			severity: SEVERITY_SCORE[group.severity],
+			affectedUrls: group.count,
+			searchVisibleUrls: search.searchVisibleUrls,
+			clicks: search.clicks,
+			impressions: search.impressions,
+			sessions: search.sessions,
+			totalUsers: search.totalUsers,
+			conversions: search.conversions,
+			avgPosition: search.avgPosition,
+			effort,
+			effortScore: EFFORT_SCORE[effort]
+		};
+		const valueWeight = VALUE_WEIGHT[group.severity];
+		const score = scoreFactors.severity + scoreFactors.affectedUrls * AFFECTED_URL_WEIGHT[group.severity] + scoreFactors.searchVisibleUrls * 100 * valueWeight + scoreFactors.clicks * 20 * valueWeight + Math.min(scoreFactors.impressions, 1e4) / 25 * valueWeight + scoreFactors.sessions * 2 * valueWeight + (scoreFactors.conversions ?? 0) * 100 * valueWeight + scoreFactors.effortScore;
+		const rule = explainRule(group.ruleId);
+		const recommendation = recommendationForRule(group.ruleId);
+		return {
+			...group,
+			recommendation,
+			score: Math.round(score),
+			scoreFactors,
+			whyThisRanks: whyThisRanks(scoreFactors, recommendation, report.dataSources?.searchConsole.status, report.dataSources?.analytics.provider),
+			howToFix: rule?.howToFix ?? "",
+			howToVerify: rule?.howToVerify ?? "",
+			verification: {
+				command: verificationCommand(report, group.severity),
+				expected: rule?.howToVerify ?? ""
+			}
+		};
+	}).sort((a, b) => reachRank(a.ruleId) - reachRank(b.ruleId) || b.score - a.score || SEVERITY_SCORE[b.severity] - SEVERITY_SCORE[a.severity] || b.count - a.count || a.ruleId.localeCompare(b.ruleId)).slice(0, filters.limit ?? 10);
+}
+function reviewObservations(report, filters = {}) {
+	return topFixes(report, {
+		...filters,
+		recommendation: "review"
+	});
+}
+// packages/core/src/analyze/crawler/export.ts
+const issueHeaders = [
+	"rule_id",
+	"title",
+	"category",
+	"severity",
+	"url",
+	"detail",
+	"clicks",
+	"impressions",
+	"position"
+];
+const pageHeaders = [
+	"url",
+	"final_url",
+	"status",
+	"indexable",
+	"title",
+	"meta_description",
+	"canonical",
+	"word_count",
+	"content_extractor",
+	"content_extractor_type",
+	"content_extraction_fallback",
+	"word_count_source",
+	"internal_links",
+	"internal_inlinks",
+	"internal_authority_score",
+	"external_links",
+	"images_total",
+	"images_missing_alt",
+	"oversized_image_candidates",
+	"schema_types",
+	"clicks",
+	"impressions",
+	"sessions"
+];
+function renderCrawlCsv(report) {
+	return renderCsv(report.issues.map((issue) => ({
+		rule_id: issue.ruleId,
+		title: issue.title,
+		category: issue.category,
+		severity: issue.severity,
+		url: issue.url,
+		detail: issue.detail,
+		clicks: issue.searchMetrics?.clicks,
+		impressions: issue.searchMetrics?.impressions,
+		position: issue.searchMetrics?.position
+	})), issueHeaders);
+}
+function renderCrawlPagesCsv(report) {
+	return renderCsv(report.pages.map((page) => ({
+		url: page.url,
+		final_url: page.finalUrl,
+		status: page.status,
+		indexable: page.indexable,
+		title: page.title,
+		meta_description: page.metaDescription,
+		canonical: page.canonical,
+		word_count: page.wordCount,
+		content_extractor: page.contentExtraction?.used,
+		content_extractor_type: page.contentExtraction?.extractorType,
+		content_extraction_fallback: page.contentExtraction?.fallback,
+		word_count_source: page.contentExtraction?.wordCountSource,
+		internal_links: page.outgoingInternalCount,
+		internal_inlinks: page.internalInlinkCount,
+		internal_authority_score: page.internalLinkAuthorityScore,
+		external_links: page.outgoingExternalCount,
+		images_total: page.imagesTotal,
+		images_missing_alt: page.imagesMissingAlt,
+		oversized_image_candidates: page.oversizedImageCandidates?.length ?? 0,
+		schema_types: page.schemaTypes?.join("|"),
+		clicks: page.searchMetrics?.clicks,
+		impressions: page.searchMetrics?.impressions,
+		sessions: page.analytics?.sessions
+	})), pageHeaders);
+}
+/** The caveat a report must lead with when the crawl read too little. */
+function crawlCoverageCaveat(report) {
+	return report.caveats.find((caveat) => caveat.startsWith(CRAWL_COVERAGE_CAVEAT_PREFIX));
+}
+function renderCrawlPretty(report, fixes = topFixes(report)) {
+	const reviews = reviewObservations(report);
+	const requestSummary = report.requestEvidenceStatus === "available" ? `${report.requests.length} requests` : report.requestEvidenceStatus === "partial" ? `${report.requests.length} observed requests; some started requests were still in flight when the crawl stopped` : "request evidence unavailable for this legacy report";
+	const coverage = crawlCoverageCaveat(report);
+	const lines = [
+		...coverage ? [coverage, ""] : [],
+		`Crawl report for ${report.config.url}`,
+		"",
+		`Status: ${report.status}`,
+		`Strategy: ${report.config.strategy === "health" ? "sitemap health pass" : "full audit"}`,
+		`Crawler: ${report.access.crawler.userAgent}`,
+		`Documents: ${report.summary.totalPages} retained; ${requestSummary}, ${report.summary.discoveredUrls} URLs discovered, ${report.summary.failedUrls} failed, ${report.summary.skippedUrls} skipped`,
+		`Issues: ${report.issues.length} (${report.summary.highIssues} high, ${report.summary.mediumIssues} medium, ${report.summary.lowIssues} low)`
+	];
+	if (report.externalLinkVerification) {
+		const external = report.externalLinkVerification;
+		lines.push(`External links: ${external.fetchedUrls} fetched, ${external.failedUrls} request failure${external.failedUrls === 1 ? "" : "s"}, ${external.deferredUrls} deferred (${external.dataStatus})`);
 	}
-	const pageByUrl = /* @__PURE__ */ new Map();
-	for (const page of pages) for (const value of [page.url, page.finalUrl]) {
-		const normalized = normalizeLinkUrl(value);
-		if (normalized) pageByUrl.set(normalized, page.url);
+	if (report.access.blockedRequests > 0) {
+		lines.push("", `Access blocks: ${report.access.blockedRequests}`);
+		for (const sample of report.access.samples.slice(0, 3)) {
+			const requestId = sample.evidence.requestId ? `, request ID ${sample.evidence.requestId}` : "";
+			lines.push(`- ${sample.url}: ${sample.evidence.guidance.summary} (${sample.evidence.provider}${requestId})`, `  Action: ${sample.evidence.guidance.recommendedAction}`, `  Security: ${sample.evidence.guidance.securityNote}`);
+			if (sample.evidence.guidance.documentationUrl) lines.push(`  Provider docs: ${sample.evidence.guidance.documentationUrl}`);
+		}
 	}
-	const inlinks = /* @__PURE__ */ new Map();
-	for (const page of pages) inlinks.set(page.url, 0);
-	for (const page of pages) {
-		const targets = hasLinkGraph ? linkGraph?.[page.url] ?? linkGraph?.[page.finalUrl] ?? [] : page.sampleInternalLinks ?? [];
-		const linkedPages = /* @__PURE__ */ new Set();
-		for (const target of targets) {
-			const normalized = normalizeLinkUrl(target);
-			const linkedPage = normalized ? pageByUrl.get(normalized) : void 0;
-			if (!linkedPage || linkedPage === page.url) continue;
-			linkedPages.add(linkedPage);
+	if (fixes.length) {
+		lines.push("", "Prioritised fixes");
+		for (const fix of fixes.slice(0, 5)) {
+			lines.push(`- ${fix.title} (${fix.severity}, ${fix.count} URL${fix.count === 1 ? "" : "s"}): ${fix.howToFix}`);
+			if (fix.sampleUrls[0]) lines.push(`  First URL: ${fix.sampleUrls[0]}`);
+		}
+	} else lines.push("", "No prioritised fixes found.");
+	if (reviews.length) {
+		lines.push("", "Review observations (check before scheduling work)");
+		for (const observation of reviews.slice(0, 5)) {
+			lines.push(`- ${observation.title} (${observation.severity}, ${observation.count} URL${observation.count === 1 ? "" : "s"}): ${observation.howToFix}`);
+			if (observation.sampleUrls[0]) lines.push(`  First URL: ${observation.sampleUrls[0]}`);
 		}
-		for (const linkedPage of linkedPages) inlinks.set(linkedPage, (inlinks.get(linkedPage) ?? 0) + 1);
 	}
-	let maxInlinks = 0;
-	for (const count of inlinks.values()) maxInlinks = Math.max(maxInlinks, count);
-	return pages.map((page) => {
-		const internalInlinkCount = inlinks.get(page.url) ?? 0;
+	lines.push("", "Next commands", report.config.strategy === "health" ? `- seo crawl ${report.config.url} --max-pages ${report.config.maxPages} --json` : `- seo crawl ${report.config.url} --json`);
+	for (const command of [...new Set(fixes.slice(0, 3).map((fix) => fix.verification.command))]) lines.push(`- ${command}`);
+	if (report.warnings.length) lines.push("", "Warnings", ...report.warnings.map((item) => `- ${item}`));
+	if (report.caveats.length) lines.push("", "Caveats", ...report.caveats.map((item) => `- ${item}`));
+	return `${lines.join("\n")}\n`;
+}
+function renderCrawlJunit(report) {
+	const issuesByUrl = /* @__PURE__ */ new Map();
+	for (const issue of report.issues) {
+		const existing = issuesByUrl.get(issue.url) ?? [];
+		existing.push(issue);
+		issuesByUrl.set(issue.url, existing);
+	}
+	const sitemapCases = (report.sitemapDiscovery?.roots ?? []).flatMap((root) => {
+		return (root.documents.length ? root.documents : [{
+			url: root.url,
+			dataStatus: root.dataStatus,
+			compression: "none",
+			warning: root.warnings.join(" ") || void 0
+		}]).map((document) => {
+			const failures = [
+				...document.dataStatus !== "complete" ? [document.warning ?? `Sitemap evidence is ${document.dataStatus}.`] : [],
+				...document.redirected ? [`Sitemap redirected to ${document.finalUrl ?? "an unknown URL"}.`] : [],
+				...document.status !== void 0 && (document.status < 200 || document.status >= 300) ? [`Sitemap returned HTTP ${document.status}.`] : []
+			];
+			const output = [
+				`dataStatus=${document.dataStatus}`,
+				...document.status !== void 0 ? [`status=${document.status}`] : [],
+				...document.finalUrl ? [`finalUrl=${document.finalUrl}`] : [],
+				...document.root ? [`root=${document.root}`] : [],
+				...document.warning ? [`warning=${document.warning}`] : []
+			].join("\n");
+			return {
+				xml: [
+					`  <testcase classname="seo.sitemap-document" name="${escapeXml(document.url)}" time="0.000">`,
+					...failures.length ? [`    <failure message="${escapeXml(failures[0] ?? "Sitemap check failed")}">${escapeXml(failures.join("\n"))}</failure>`] : [],
+					`    <system-out>${escapeXml(output)}</system-out>`,
+					"  </testcase>"
+				].join("\n"),
+				failed: failures.length > 0
+			};
+		});
+	});
+	const requestCases = report.requests.map((request) => {
+		const failures = [
+			...(issuesByUrl.get(request.requestedUrl) ?? []).map((issue) => `${issue.severity}: ${issue.title}${issue.detail ? `: ${issue.detail}` : ""}`),
+			...request.outcome === "failure" ? [`${request.failureKind}: ${request.error}`] : [],
+			...request.outcome === "skipped" ? [request.reason === "origin-backpressure" ? request.error : `${request.reason}: ${request.robotsTxt.matchedLine ?? request.robotsTxt.availability}`] : []
+		];
+		const output = request.outcome === "response" ? [
+			`status=${request.status}`,
+			`finalUrl=${request.finalUrl}`,
+			...request.robotsTxt ? [
+				`robotsUrl=${request.robotsTxt.url}`,
+				`robotsAllowed=${request.robotsTxt.allowed ?? "unknown"}`,
+				`robotsAvailability=${request.robotsTxt.availability}`,
+				...request.robotsTxt.status !== void 0 ? [`robotsStatus=${request.robotsTxt.status}`] : [],
+				...request.robotsTxt.matchedLine ? [`robotsMatchedLine=${request.robotsTxt.matchedLine}`] : [],
+				...request.robotsTxt.error ? [`robotsError=${request.robotsTxt.error}`] : []
+			] : [],
+			...request.accessBlock ? [
+				`accessProvider=${request.accessBlock.provider}`,
+				`crawler=${request.accessBlock.crawler.userAgent}`,
+				...request.accessBlock.requestId ? [`requestId=${request.accessBlock.requestId}`] : []
+			] : []
+		].join("\n") : request.outcome === "failure" ? request.error : request.reason === "origin-backpressure" ? `reason=${request.reason}\nerror=${request.error}` : [
+			`reason=${request.reason}`,
+			`robotsUrl=${request.robotsTxt.url}`,
+			`robotsAllowed=${request.robotsTxt.allowed ?? "unknown"}`,
+			`robotsAvailability=${request.robotsTxt.availability}`,
+			...request.robotsTxt.status !== void 0 ? [`robotsStatus=${request.robotsTxt.status}`] : [],
+			...request.robotsTxt.matchedLine ? [`robotsMatchedLine=${request.robotsTxt.matchedLine}`] : [],
+			...request.robotsTxt.error ? [`robotsError=${request.robotsTxt.error}`] : []
+		].join("\n");
+		const duration = ((request.durationMs ?? 0) / 1e3).toFixed(3);
 		return {
-			...page,
-			internalInlinkCount,
-			internalLinkAuthorityScore: maxInlinks ? Math.round(internalInlinkCount / maxInlinks * 100) : 0
+			xml: [
+				`  <testcase classname="seo.sitemap-health" name="${escapeXml(request.requestedUrl)}" time="${duration}">`,
+				...failures.length ? [`    <failure message="${escapeXml(failures[0] ?? "Health check failed")}">${escapeXml(failures.join("\n"))}</failure>`] : [],
+				`    <system-out>${escapeXml(output)}</system-out>`,
+				"  </testcase>"
+			].join("\n"),
+			failed: failures.length > 0
 		};
 	});
+	const cases = [...sitemapCases, ...requestCases];
+	const failures = cases.filter((item) => item.failed).length;
+	const elapsed = report.requests.reduce((sum, request) => sum + (request.durationMs ?? 0), 0);
+	return [
+		"<?xml version=\"1.0\" encoding=\"UTF-8\"?>",
+		`<testsuite name="seo sitemap health" tests="${cases.length}" failures="${failures}" errors="0" skipped="0" time="${(elapsed / 1e3).toFixed(3)}">`,
+		"  <properties>",
+		`    <property name="report.id" value="${escapeXml(report.id)}"/>`,
+		`    <property name="report.status" value="${escapeXml(report.status)}"/>`,
+		`    <property name="crawl.strategy" value="${escapeXml(report.config.strategy)}"/>`,
+		`    <property name="crawler.userAgent" value="${escapeXml(report.access.crawler.userAgent)}"/>`,
+		"  </properties>",
+		...cases.map((item) => item.xml),
+		"</testsuite>",
+		""
+	].join("\n");
 }
-function createCrawlReport(input) {
-	const config = sanitizeCrawlConfig(normalizeCrawlConfig(input.config));
-	const definitionId = crawlDefinitionId({
-		config,
-		site: input.site,
-		googleAnalyticsPropertyId: input.googleAnalyticsPropertyId,
-		analyticsConnection: input.analyticsConnection
-	});
-	const safePagesWithLinks = sortPages(sanitizePages(deriveInternalLinkAuthority(input.pages ?? [], input.linkGraph)));
-	const requests = sortRequests(sanitizeTenantValue(input.requests ?? []));
-	const requestEvidenceStatus = input.requestEvidenceStatus ?? (input.requests ? "available" : "unavailable");
-	if (requestEvidenceStatus === "unavailable" && requests.length > 0) throw new Error("Unavailable request evidence cannot include request observations.");
-	const safeIssues = sanitizeIssues([...input.issues ?? [...auditCrawlRequests(requests), ...auditCrawlPages(safePagesWithLinks, { startUrl: config.url })], ...input.additionalIssues ?? []]);
-	const pages = safePagesWithLinks;
-	return {
-		id: input.id ?? crawlRunId(),
-		definitionId,
-		site: input.site,
-		googleAnalyticsPropertyId: input.googleAnalyticsPropertyId,
-		analyticsConnection: input.analyticsConnection,
-		generatedAt: input.generatedAt ?? (/* @__PURE__ */ new Date()).toISOString(),
-		status: input.status ?? "completed",
-		configHash: crawlConfigHash(config),
-		config,
-		access: crawlAccessSummary(requests),
-		summary: summarizeCrawlReport({
-			pages,
-			requests,
-			requestEvidenceStatus,
-			issues: safeIssues,
-			stats: input.stats
-		}),
-		requestEvidenceStatus,
-		requests,
-		pages,
-		issues: safeIssues,
-		issueGroups: groupCrawlIssues(safeIssues),
-		...input.dataSources ? { dataSources: sanitizeTenantValue(input.dataSources) } : {},
-		...input.ai ? { ai: sanitizeTenantValue(input.ai) } : {},
-		...input.sitemapDiscovery ? { sitemapDiscovery: sanitizeTenantValue(input.sitemapDiscovery) } : {},
-		...input.externalLinkVerification ? { externalLinkVerification: sanitizeTenantValue(input.externalLinkVerification) } : {},
-		...input.siteChecks ? { siteChecks: sanitizeTenantValue(input.siteChecks) } : {},
-		warnings: sanitizeMessages(input.warnings).sort(compareText$17),
-		caveats: sanitizeMessages(input.caveats).sort(compareText$17)
-	};
+function renderCrawlHtml(report, fixes = topFixes(report)) {
+	const reviews = reviewObservations(report);
+	const issueRows = report.issueGroups.map((group) => {
+		const rule = explainRule(group.ruleId);
+		return `<tr><td>${escapeHtml(group.severity)}</td><td>${escapeHtml(group.title)}</td><td>${group.count}</td><td>${escapeHtml(rule?.howToFix ?? "")}</td><td>${escapeHtml(group.sampleUrls[0] ?? "")}</td></tr>`;
+	}).join("\n");
+	const fixItems = fixes.slice(0, 10).map((fix) => `<li><strong>${escapeHtml(fix.title)}</strong><br>${escapeHtml(fix.howToFix)}<br><span>Verify: ${escapeHtml(fix.howToVerify)}</span><br><code>${escapeHtml(fix.verification.command)}</code></li>`).join("\n");
+	const reviewItems = reviews.slice(0, 10).map((observation) => `<li><strong>${escapeHtml(observation.title)}</strong><br>${escapeHtml(observation.howToFix)}<br><span>Check before scheduling work. ${escapeHtml(observation.howToVerify)}</span></li>`).join("\n");
+	const caveatItems = report.caveats.map((caveat) => `<li>${escapeHtml(caveat)}</li>`).join("\n");
+	const warningItems = report.warnings.map((warning) => `<li>${escapeHtml(warning)}</li>`).join("\n");
+	const accessItems = report.access.samples.map((sample) => `<li><strong>${escapeHtml(sample.url)}</strong><br>${escapeHtml(sample.evidence.guidance.summary)}<br>${escapeHtml(sample.evidence.guidance.recommendedAction)}<br><span>${escapeHtml(sample.evidence.guidance.securityNote)}</span></li>`).join("\n");
+	return `<!doctype html>
+<html lang="en">
+<head>
+  <meta charset="utf-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1">
+  <title>Crawl report for ${escapeHtml(report.config.url)}</title>
+  <style>
+    body { color: #17202a; font: 15px/1.5 system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif; margin: 32px; max-width: 1120px; }
+    h1, h2 { line-height: 1.2; }
+    .summary { display: grid; gap: 12px; grid-template-columns: repeat(auto-fit, minmax(160px, 1fr)); margin: 24px 0; }
+    .metric { border: 1px solid #d8dee4; border-radius: 8px; padding: 12px; }
+    .metric strong { display: block; font-size: 24px; }
+    table { border-collapse: collapse; width: 100%; }
+    th, td { border-bottom: 1px solid #d8dee4; padding: 10px; text-align: left; vertical-align: top; }
+    th { background: #f6f8fa; }
+    li { margin: 0 0 12px; }
+    span { color: #57606a; }
+  </style>
+</head>
+<body>
+  <h1>Crawl report</h1>
+  <p>${escapeHtml(report.config.url)}</p>
+  <p>Strategy: ${escapeHtml(report.config.strategy === "health" ? "sitemap health pass" : "full audit")}<br>Crawler: <code>${escapeHtml(report.access.crawler.userAgent)}</code></p>
+  <section class="summary">
+    <div class="metric"><span>Status</span><strong>${escapeHtml(report.status)}</strong></div>
+    <div class="metric"><span>Documents</span><strong>${report.summary.totalPages}</strong></div>
+    <div class="metric"><span>Requests</span><strong>${report.requestEvidenceStatus === "unavailable" ? "n/a" : report.requests.length}${report.requestEvidenceStatus === "partial" ? " (partial)" : ""}</strong></div>
+    <div class="metric"><span>Discovered</span><strong>${report.summary.discoveredUrls}</strong></div>
+    <div class="metric"><span>Queued</span><strong>${report.summary.queuedUrls}</strong></div>
+    <div class="metric"><span>Skipped</span><strong>${report.summary.skippedUrls}</strong></div>
+    <div class="metric"><span>Failed fetches</span><strong>${report.summary.failedUrls}</strong></div>
+    <div class="metric"><span>Observed internal links</span><strong>${report.summary.observedInternalLinks}</strong></div>
+    <div class="metric"><span>Issues</span><strong>${report.issues.length}</strong></div>
+    <div class="metric"><span>High</span><strong>${report.summary.highIssues}</strong></div>
+  </section>
+  ${accessItems ? `<h2>Access blocks</h2><ul>${accessItems}</ul>` : ""}
+  <h2>Prioritised fixes</h2>
+  ${fixItems ? `<ol>${fixItems}</ol>` : "<p>No prioritised fixes found.</p>"}
+  ${reviewItems ? `<h2>Review observations</h2>
+  <p>Check these before scheduling implementation work.</p>
+  <ul>${reviewItems}</ul>` : ""}
+  ${report.caveats.length ? `<h2>Caveats</h2>
+  <ul>${caveatItems}</ul>` : ""}
+  ${report.warnings.length ? `<h2>Warnings</h2>
+  <ul>${warningItems}</ul>` : ""}
+  <h2>Issue groups</h2>
+  <table>
+    <thead><tr><th>Severity</th><th>Issue</th><th>URLs</th><th>Fix</th><th>Sample URL</th></tr></thead>
+    <tbody>${issueRows}</tbody>
+  </table>
+</body>
+</html>
+`;
 }
-function normalizeLoadedCrawlReport(report) {
-	const config = sanitizeCrawlConfig(normalizeCrawlConfig(report.config));
-	const requestEvidenceStatus = report.requestEvidenceStatus ?? (Object.hasOwn(report, "requests") ? "available" : "unavailable");
-	const issues = sanitizeIssues(report.issues ?? []);
-	const requests = sortRequests(sanitizeTenantValue(report.requests ?? []) ?? []);
-	const pages = sortPages(sanitizePages(deriveInternalLinkAuthority(report.pages ?? [])));
-	return {
-		...sanitizeTenantValue(report),
-		config,
-		access: crawlAccessSummary(requests),
-		requestEvidenceStatus,
-		requests,
-		definitionId: report.definitionId ?? crawlDefinitionId({
-			config,
-			site: report.site,
-			googleAnalyticsPropertyId: report.googleAnalyticsPropertyId,
-			analyticsConnection: report.analyticsConnection
-		}),
-		summary: summarizeCrawlReport({
-			pages,
-			requests,
-			requestEvidenceStatus,
-			issues,
-			stats: report.summary
-		}),
-		pages,
-		issues,
-		issueGroups: groupCrawlIssues(issues),
-		warnings: sanitizeMessages(report.warnings).sort(compareText$17),
-		caveats: sanitizeMessages(report.caveats).sort(compareText$17)
-	};
+function renderCrawlMarkdownTickets(report, fixes = topFixes(report)) {
+	const reviews = reviewObservations(report);
+	const lines = [
+		`# Crawl Implementation Tickets`,
+		"",
+		`Source: ${report.config.url}`,
+		`Report: ${report.id}`,
+		`Status: ${report.status}`,
+		`Strategy: ${report.config.strategy}`,
+		`Crawler: ${report.access.crawler.userAgent}`,
+		""
+	];
+	if (report.caveats.length) lines.push("## Caveats", "", ...report.caveats.map((item) => `- ${item}`), "");
+	if (report.warnings.length) lines.push("## Warnings", "", ...report.warnings.map((item) => `- ${item}`), "");
+	if (report.access.blockedRequests > 0) lines.push("## Access blocks", "", ...report.access.samples.flatMap((sample) => [
+		`- ${sample.url}: ${sample.evidence.guidance.summary}`,
+		`  - Action: ${sample.evidence.guidance.recommendedAction}`,
+		`  - Security: ${sample.evidence.guidance.securityNote}`
+	]), "");
+	for (const [index, fix] of fixes.entries()) lines.push(`## ${index + 1}. ${fix.title}`, "", `- [ ] Fix ${fix.count} affected URL${fix.count === 1 ? "" : "s"}`, `- Severity: ${fix.severity}`, `- Rule: ${fix.ruleId}`, `- Why this ranks: ${fix.whyThisRanks}`, `- Plain-English fix: ${fix.howToFix}`, `- Verify: ${fix.howToVerify}`, `- Command: ${fix.verification.command}`, "", `Affected URLs:`, ...fix.sampleUrls.slice(0, 10).map((url) => `- ${url}`), "");
+	if (!fixes.length) lines.push("No implementation tickets were generated.");
+	if (reviews.length) lines.push("## Review observations", "", "These are not implementation tickets. Check the evidence before deciding whether to work on them.", "", ...reviews.slice(0, 10).flatMap((observation) => [`- ${observation.title} (${observation.severity}, ${observation.count} URL${observation.count === 1 ? "" : "s"}): ${observation.howToFix}`, `  - First URL: ${observation.sampleUrls[0] ?? "No sample URL recorded"}`]), "");
+	return `${lines.join("\n")}\n`;
+}
+function escapeHtml(value) {
+	return value.replaceAll("&", "&amp;").replaceAll("<", "&lt;").replaceAll(">", "&gt;").replaceAll("\"", "&quot;").replaceAll("'", "&#39;");
+}
+function escapeXml(value) {
+	return escapeHtml(value);
 }
 // packages/core/src/analyze/crawler/site-checks-schema.ts
 const crawlSiteChecksSchema = z.object({ soft404: z.object({
@@ -14464,123 +14629,6 @@ function agentReadyIssues(input) {
 	}
 	return issues;
 }
-// packages/core/src/analyze/crawler/crawl-url-queue.ts
-function before(left, right) {
-	return left.depth < right.depth || left.depth === right.depth && left.url < right.url;
-}
-var CrawlUrlQueue = class {
-	#items = [];
-	#positions = /* @__PURE__ */ new Map();
-	get size() {
-		return this.#items.length;
-	}
-	has(url) {
-		return this.#positions.has(url);
-	}
-	push(item) {
-		if (this.has(item.url)) throw new Error(`URL is already queued: ${item.url}`);
-		const index = this.#items.length;
-		this.#items.push(item);
-		this.#positions.set(item.url, index);
-		this.#bubbleUp(index);
-	}
-	decreaseDepth(url, depth) {
-		const index = this.#positions.get(url);
-		if (index === void 0) return false;
-		const item = this.#items[index];
-		if (!item || depth >= item.depth) return false;
-		item.depth = depth;
-		this.#bubbleUp(index);
-		return true;
-	}
-	take() {
-		const first = this.#items[0];
-		if (!first) return void 0;
-		const last = this.#items.pop();
-		this.#positions.delete(first.url);
-		if (last && last !== first) {
-			this.#items[0] = last;
-			this.#positions.set(last.url, 0);
-			this.#bubbleDown(0);
-		}
-		return first;
-	}
-	#swap(left, right) {
-		const leftItem = this.#items[left];
-		const rightItem = this.#items[right];
-		if (!leftItem || !rightItem) return;
-		this.#items[left] = rightItem;
-		this.#items[right] = leftItem;
-		this.#positions.set(rightItem.url, left);
-		this.#positions.set(leftItem.url, right);
-	}
-	#bubbleUp(start) {
-		let index = start;
-		while (index > 0) {
-			const parent = Math.floor((index - 1) / 2);
-			const item = this.#items[index];
-			const parentItem = this.#items[parent];
-			if (!item || !parentItem || !before(item, parentItem)) break;
-			this.#swap(index, parent);
-			index = parent;
-		}
-	}
-	#bubbleDown(start) {
-		let index = start;
-		while (true) {
-			const left = index * 2 + 1;
-			const right = left + 1;
-			let next = index;
-			const item = this.#items[next];
-			const leftItem = this.#items[left];
-			const rightItem = this.#items[right];
-			if (leftItem && item && before(leftItem, item)) next = left;
-			const nextItem = this.#items[next];
-			if (rightItem && nextItem && before(rightItem, nextItem)) next = right;
-			if (next === index) return;
-			this.#swap(index, next);
-			index = next;
-		}
-	}
-};
-// packages/core/src/analyze/crawler/crawl-caveats.ts
-function crawlCaveats(input) {
-	const caveats = input.cancelled ? ["Crawl cancelled before all queued URLs finished."] : input.pageLimitReached ? [`Stopped after reaching maxPages (${input.maxPages}).`] : [];
-	if (input.queueSafetySkippedUrls > 0) caveats.push(input.queueSafetyInventoryCapped ? `Left at least ${input.queueSafetySkippedUrls} unique eligible same-origin URLs unqueued to keep this crawl bounded. The excluded-URL inventory reached its reporting cap. Increase --max-pages to inspect more.` : `Left ${input.queueSafetySkippedUrls} unique eligible same-origin URLs unqueued to keep this crawl bounded. Increase --max-pages to inspect more.`);
-	if (input.originBackpressureSkippedUrls > 0) caveats.push(`Stopped ${input.originBackpressureSkippedUrls} queued URL${input.originBackpressureSkippedUrls === 1 ? "" : "s"} because the origin stayed slow. This is incomplete crawl evidence, not a failed URL check.`);
-	if (input.memoryPressureSkippedUrls > 0) caveats.push(`Left ${input.memoryPressureSkippedUrls} eligible URL${input.memoryPressureSkippedUrls === 1 ? "" : "s"} unchecked after the local memory safety limit was reached. Start with --health or lower --max-pages.`);
-	const renderingFallbackUrls = input.renderingFallbackUrls ?? 0;
-	if (renderingFallbackUrls > 0) caveats.push(`JavaScript rendering could not run for ${renderingFallbackUrls} page${renderingFallbackUrls === 1 ? "" : "s"}, so ${renderingFallbackUrls === 1 ? "it was" : "they were"} audited from raw HTML. Client-rendered content, metadata and links may be missing. Install Chromium or set SEO_BROWSER_EXECUTABLE_PATH, then rerun.`);
-	const queryVariantSkippedUrls = input.queryVariantSkippedUrls ?? 0;
-	if (queryVariantSkippedUrls > 0) caveats.push(`Left ${queryVariantSkippedUrls} query-string variant${queryVariantSkippedUrls === 1 ? "" : "s"} unqueued after 5 variants of the same path, so tracking parameters do not fill the crawl.`);
-	for (const issue of input.reachIssues ?? []) if (issue.detail) caveats.push(issue.detail);
-	return caveats;
-}
-/**
-* A site crawl that found no internal links on the start page and no sitemap
-* URLs checked one page, so its other findings cannot stand for the site.
-*/
-function crawlReachIssues(input) {
-	const [page] = input.pages;
-	if (input.crawledPages !== 1 || input.pages.length !== 1 || !page || page.outgoingInternalCount > 0 || input.sitemapUrlsReturned > 0) return [];
-	const rule = explainRule("crawl_single_page_reach");
-	if (!rule) throw new Error("Missing rule guidance for crawl_single_page_reach");
-	return [{
-		ruleId: "crawl_single_page_reach",
-		title: rule.title,
-		category: rule.category,
-		severity: rule.defaultSeverity,
-		url: page.url,
-		detail: page.usedJs ? "The rendered start page had 0 internal links and no sitemap returned URLs, so the crawl checked only this page. List the pages to check with --mode list." : "The start page had 0 internal links in its HTML and no sitemap returned URLs, so the crawl checked only this page. It probably builds its links with JavaScript. Rerun with --rendering on, or list the pages with --mode list.",
-		evidence: {
-			startUrl: input.startUrl,
-			crawledPages: 1,
-			outgoingInternalCount: 0,
-			sitemapUrlsReturned: 0,
-			rendered: Boolean(page.usedJs)
-		}
-	}];
-}
 // packages/core/src/analyze/crawler/crawl-control.ts
 const CRAWL_CANCELLED = Symbol("crawl-cancelled");
 function abortController(input) {
@@ -14622,6 +14670,96 @@ function crawlRssLimitBytes(totalMemoryBytes) {
 function crawlMemoryPressure(input) {
 	return input.memoryUsage.heapUsed + input.memoryUsage.external >= crawlMemoryLimitBytes(input.totalMemoryBytes) || input.memoryUsage.rss >= crawlRssLimitBytes(input.totalMemoryBytes);
 }
+// packages/core/src/analyze/crawler/crawl-rate-limit.ts
+const RETRIES_PER_URL = 3;
+const BASE_BACKOFF_MS = 2e3;
+const MAX_BACKOFF_MS = 3e4;
+const COOLDOWN_BUDGET_MS = 18e4;
+const LIMITED_INTERVAL_MS = 1e3;
+const LIMITED_MAX_INTERVAL_MS = 4e3;
+function rateLimitEvidence(result, status, nowMs) {
+	if (status !== 429 && status !== 503) return void 0;
+	const header = retryAfterMs(result.page?.responseHeaders?.["retry-after"]);
+	const cooldownUntil = Date.parse(result.page?.fetchDiagnostics?.backpressure?.cooldownUntil ?? "");
+	const fromCooldown = Number.isFinite(cooldownUntil) ? Math.max(0, cooldownUntil - nowMs) : void 0;
+	const wait = header ?? fromCooldown;
+	if (status === 503 && wait === void 0) return void 0;
+	return wait === void 0 ? {} : { retryAfterMs: Math.min(wait, MAX_BACKOFF_MS) };
+}
+/**
+* Rate-limit state for one crawl. After the first 429 the crawl drops to one
+* request at a time with a per-host interval and never speeds back up.
+*/
+var CrawlRateLimit = class {
+	rate;
+	responses = 0;
+	skippedUrls = 0;
+	pendingMs = 0;
+	spentMs = 0;
+	#level = 0;
+	#budgetSpent = false;
+	#retries = /* @__PURE__ */ new Map();
+	constructor(rate) {
+		this.rate = rate;
+	}
+	get limited() {
+		return this.responses > 0;
+	}
+	get intervalMs() {
+		return this.rate.intervalMs ?? LIMITED_INTERVAL_MS;
+	}
+	/** The cool-down before probes that run after the crawl. */
+	get settleMs() {
+		return Math.min(MAX_BACKOFF_MS, BASE_BACKOFF_MS * 2 ** this.#level);
+	}
+	/**
+	* `retry` requeues the URL after `pendingMs`. `skip` gives it up, and
+	* `stop` gives up the rest of the queue too once the budget is spent.
+	*/
+	observe(url, result, status, nowMs) {
+		const evidence = rateLimitEvidence(result, status, nowMs);
+		if (!evidence) return void 0;
+		this.responses += 1;
+		if (this.pendingMs === 0) this.#level += 1;
+		const step = 2 ** Math.max(0, this.#level - 1);
+		const waitMs = evidence.retryAfterMs ?? Math.min(MAX_BACKOFF_MS, BASE_BACKOFF_MS * step);
+		this.rate = {
+			...this.rate,
+			concurrency: 1,
+			intervalCap: 1,
+			intervalMs: Math.min(LIMITED_MAX_INTERVAL_MS, Math.max(this.rate.intervalMs ?? 0, LIMITED_INTERVAL_MS * step))
+		};
+		const nextMs = Math.max(this.pendingMs, waitMs);
+		if (this.spentMs + nextMs > COOLDOWN_BUDGET_MS) this.#budgetSpent = true;
+		const retries = this.#retries.get(url) ?? 0;
+		if (!this.#budgetSpent && retries < RETRIES_PER_URL) {
+			this.#retries.set(url, retries + 1);
+			this.pendingMs = nextMs;
+			return "retry";
+		}
+		this.skippedUrls += 1;
+		return this.#budgetSpent ? "stop" : "skip";
+	}
+	async settle(sleep, signal) {
+		if (this.pendingMs <= 0) return;
+		await sleep(this.pendingMs, signal);
+		this.spentMs += this.pendingMs;
+		this.pendingMs = 0;
+	}
+	caveatInput(config, readPages) {
+		if (this.skippedUrls === 0) return void 0;
+		return {
+			readPages,
+			skippedUrls: this.skippedUrls,
+			rerunCommand: rateLimitRerunCommand(config, this.intervalMs)
+		};
+	}
+	warning() {
+		if (!this.limited) return void 0;
+		const plural = (count, noun) => `${count} ${noun}${count === 1 ? "" : "s"}`;
+		return `The origin rate limited ${plural(this.responses, "request")}. The crawl slowed to one request at a time, at least ${Math.round(this.intervalMs / 1e3)}s apart, and waited ${Math.round(this.spentMs / 1e3)}s in cool-downs${this.skippedUrls > 0 ? `, then left ${plural(this.skippedUrls, "URL")} unread` : " before reading every queued URL"}.`;
+	}
+};
 // packages/core/src/analyze/crawler/external-link-checks.ts
 const EXTERNAL_LINK_SELECTION_LIMIT = 200;
 const EXTERNAL_LINK_STATES = [
@@ -14882,21 +15020,32 @@ function probeObservation(url, result) {
 		error: request.outcome === "failure" ? request.error : `Probe skipped: ${request.reason}`
 	};
 }
+function isConclusive(probe) {
+	return probe.status !== void 0 && !probe.accessBlocked && probe.status !== 429 && probe.status !== 503;
+}
 async function collectCrawlSiteChecks(input) {
+	const probe = async (url) => probeObservation(url, await input.fetchStatusPage(url, {
+		js: "off",
+		refresh: true,
+		timeoutMs: input.timeoutMs,
+		signal: input.signal,
+		writeCache: false,
+		respectRobots: input.respectRobots,
+		...input.rate ? { rate: input.rate } : {}
+	}));
 	const probes = [];
 	for (const url of probeUrls(input.startUrl)) {
 		if (input.signal?.aborted) break;
-		const result = await input.fetchStatusPage(url, {
-			js: "off",
-			refresh: true,
-			timeoutMs: input.timeoutMs,
-			signal: input.signal,
-			writeCache: false,
-			respectRobots: input.respectRobots
-		});
-		probes.push(probeObservation(url, result));
+		probes.push(await probe(url));
+	}
+	if (input.sleep && !input.signal?.aborted && probes.some((item) => !isConclusive(item))) {
+		await input.sleep(input.retryDelayMs ?? 2e3, input.signal);
+		for (const [index, item] of probes.entries()) {
+			if (input.signal?.aborted) break;
+			if (!isConclusive(item)) probes[index] = await probe(item.url);
+		}
 	}
-	const conclusive = probes.filter((probe) => probe.status !== void 0 && !probe.accessBlocked);
+	const conclusive = probes.filter(isConclusive);
 	const successful = conclusive.filter((probe) => (probe.status ?? 0) >= 200 && (probe.status ?? 0) < 400);
 	const correctMissing = conclusive.filter((probe) => probe.status === 404 || probe.status === 410);
 	const status = successful.length > 0 ? "warning" : correctMissing.length === PROBE_COUNT ? "pass" : "unknown";
@@ -14904,7 +15053,7 @@ async function collectCrawlSiteChecks(input) {
 		status,
 		probes,
 		probeLimit: PROBE_COUNT,
-		complete: probes.length === PROBE_COUNT
+		complete: conclusive.length === PROBE_COUNT
 	} };
 	if (status !== "warning") return {
 		checks,
@@ -17460,6 +17609,18 @@ async function fetchLandingPageValues(input, dependencies = defaultDependencies$
 	}[connection.provider](connection);
 }
 // packages/core/src/analyze/crawler/site-crawl-dependencies.ts
+function sleep$2(ms, signal) {
+	return new Promise((resolve) => {
+		if (signal?.aborted) return resolve();
+		const done = () => {
+			clearTimeout(timer);
+			signal?.removeEventListener("abort", done);
+			resolve();
+		};
+		const timer = setTimeout(done, ms);
+		signal?.addEventListener("abort", done, { once: true });
+	});
+}
 function resolveCrawlSiteDependencies(dependencies = {}) {
 	const hasInjectedPerPageSearchProvider = Boolean(dependencies.queryPageMetrics || dependencies.queryPageTopQuery);
 	const hasInjectedLegacyBulkSearchProvider = Boolean(dependencies.queryPagesMetrics || dependencies.queryPagesTopQueries);
@@ -17480,6 +17641,7 @@ function resolveCrawlSiteDependencies(dependencies = {}) {
 		fetchLandingPageValues: dependencies.fetchLandingPageValues ?? fetchLandingPageValues,
 		landingValueForUrl: dependencies.landingValueForUrl ?? landingValueForUrl,
 		now: dependencies.now ?? (() => /* @__PURE__ */ new Date()),
+		sleep: dependencies.sleep ?? sleep$2,
 		memoryUsage: dependencies.memoryUsage ?? (() => process.memoryUsage()),
 		totalMemory: dependencies.totalMemory ?? totalmem
 	};
@@ -17698,6 +17860,7 @@ async function crawlSite(input, dependencies) {
 	const queryVariantsByPath = /* @__PURE__ */ new Map();
 	const queryVariantSkipped = /* @__PURE__ */ new Set();
 	let renderingFallbackUrls = 0;
+	const rateLimit = new CrawlRateLimit(config.fetchRate);
 	let failedUrls = 0;
 	let observedInternalLinks = 0;
 	let memoryLimited = false;
@@ -17782,6 +17945,15 @@ async function crawlSite(input, dependencies) {
 				});
 				return;
 			}
+			if (isCdnUtilityUrl(normalized)) {
+				recordSkip("cdn-utility-url");
+				emitStatus("url_skipped", {
+					url: normalized,
+					depth,
+					reason: "cdn_utility_url"
+				});
+				return;
+			}
 			if (isLikelyAsset(normalized)) {
 				recordSkip("asset-url");
 				emitStatus("url_skipped", {
@@ -17886,7 +18058,7 @@ async function crawlSite(input, dependencies) {
 					js: config.js,
 					refresh: config.refresh,
 					timeoutMs: config.timeoutMs,
-					rate: config.fetchRate,
+					rate: rateLimit.rate,
 					signal,
 					writeCache: false,
 					respectRobots: config.respectRobots,
@@ -17917,7 +18089,11 @@ async function crawlSite(input, dependencies) {
 			});
 		};
 		while (!isCancelled() && (queue.size || inFlight.size) && (!memoryLimited || inFlight.size > 0) && pages.length < config.maxPages) {
-			while (!isCancelled() && !memoryLimited && inFlight.size < activeConcurrency && pages.length + inFlight.size < config.maxPages) {
+			if (rateLimit.pendingMs > 0 && inFlight.size === 0) {
+				await rateLimit.settle(deps.sleep, signal);
+				if (isCancelled()) break;
+			}
+			while (!isCancelled() && !memoryLimited && rateLimit.pendingMs === 0 && inFlight.size < activeConcurrency && pages.length + inFlight.size < config.maxPages) {
 				const item = nextQueueItem();
 				if (!item) break;
 				startTask(item);
@@ -17937,11 +18113,46 @@ async function crawlSite(input, dependencies) {
 				error: result.warning ?? "Crawler returned no page snapshot.",
 				extraction: "not-applicable"
 			});
+			const limited = rateLimit.observe(task.url, result, request.outcome === "response" ? request.status : void 0, deps.now().getTime());
+			if (limited) {
+				activeConcurrency = 1;
+				healthyProbeStreak = 0;
+			}
+			if (limited === "retry") {
+				visited.delete(task.url);
+				if (!queue.has(task.url)) queue.push({
+					url: task.url,
+					depth: task.depth
+				});
+				emitStatus("url_queued", {
+					url: task.url,
+					depth: task.depth,
+					reason: "rate_limited_retry",
+					message: `The origin rate limited ${task.url}. Waiting ${Math.ceil(rateLimit.pendingMs / 1e3)}s, then retrying one request at a time.`
+				});
+				continue;
+			}
+			if (limited) {
+				requests.push(request);
+				recordSkip("origin-backpressure");
+				emitStatus("page_skipped", {
+					url: task.url,
+					depth: task.depth,
+					reason: "origin-backpressure"
+				});
+				if (limited === "stop") {
+					let left = 0;
+					while (queue.take()) left += 1;
+					recordSkips("origin-backpressure", left);
+					rateLimit.skippedUrls += left;
+				}
+				continue;
+			}
 			requests.push(request);
 			if (healthStrategy) {
 				if (request.outcome === "response" && request.status < 400 && !request.accessBlock) {
 					healthyProbeStreak += 1;
-					activeConcurrency = Math.min(config.concurrency, 1 + Math.floor(healthyProbeStreak / 20));
+					activeConcurrency = Math.min(rateLimit.limited ? 1 : config.concurrency, 1 + Math.floor(healthyProbeStreak / 20));
 				} else {
 					healthyProbeStreak = 0;
 					activeConcurrency = 1;
@@ -18014,7 +18225,7 @@ async function crawlSite(input, dependencies) {
 			const storeDocument = (urls) => {
 				const sourceRequest = normalizeUrl$1(task.url, config.url) ?? task.url;
 				const directlyRequested = sourceRequest === finalUrl;
-				const normalizedLinks = urls.map((url) => normalizeUrl$1(url, finalUrl)).filter((url) => Boolean(url));
+				const normalizedLinks = urls.map((url) => normalizeUrl$1(url, finalUrl)).filter((url) => Boolean(url) && !isCdnUtilityUrl(url ?? ""));
 				const syncLinkEvidence = (target, links) => {
 					const sortedLinks = [...links].sort((left, right) => left < right ? -1 : left > right ? 1 : 0);
 					target.outgoingInternalCount = sortedLinks.length;
@@ -18093,7 +18304,7 @@ async function crawlSite(input, dependencies) {
 			if (followLinks && task.depth < config.maxDepth) {
 				if (memoryLimited) for (const value of result.urls) {
 					const normalized = normalizeUrl$1(value, finalUrl);
-					if (normalized && sameOrigin(normalized, origin) && !isLikelyAsset(normalized) && passesFilters(normalized, config.include, config.exclude) && !visited.has(normalized) && !queue.has(normalized)) {
+					if (normalized && sameOrigin(normalized, origin) && !isCdnUtilityUrl(normalized) && !isLikelyAsset(normalized) && passesFilters(normalized, config.include, config.exclude) && !visited.has(normalized) && !queue.has(normalized)) {
 						discovered.add(normalized);
 						memoryDeferredUrls.add(normalized);
 					}
@@ -18118,6 +18329,8 @@ async function crawlSite(input, dependencies) {
 		cancelled = isCancelled();
 		const robotsDisallowed = skipReasonCounts["robots-disallowed"] ?? 0;
 		if (robotsDisallowed > 0) warnings.push(`${robotsDisallowed} URL${robotsDisallowed === 1 ? "" : "s"} disallowed ${SEO_CRAWLER_USER_AGENT} in robots.txt. If the audit should reach them, allow the SEO-Skill token on only those public paths.`);
+		const rateLimitWarning = rateLimit.warning();
+		if (rateLimitWarning) warnings.push(rateLimitWarning);
 		if (cancelled) {
 			warnings.push("Crawl cancelled; returning a partial report.");
 			emitStatus("cancelled", {
@@ -18129,7 +18342,7 @@ async function crawlSite(input, dependencies) {
 		const sitemapEvidencePartial = sitemapDiscovery?.dataStatus === "partial";
 		const accessEvidencePartial = requests.some((request) => request.outcome === "response" && request.accessBlock);
 		const requiredSitemapUnavailable = config.mode === "sitemap" && sitemapDiscovery?.dataStatus === "unavailable";
-		const partial = cancelled || failedUrls > 0 || pageLimitReached || robotsDeferredUrls > 0 || originBackpressureSkippedUrls > 0 || queueSafetySkippedUrls > 0 || queue.size > 0 || inFlight.size > 0 || stoppedForMemory || sitemapEvidencePartial || accessEvidencePartial || requiredSitemapUnavailable;
+		const partial = cancelled || failedUrls > 0 || pageLimitReached || robotsDeferredUrls > 0 || originBackpressureSkippedUrls > 0 || rateLimit.skippedUrls > 0 || queueSafetySkippedUrls > 0 || queue.size > 0 || inFlight.size > 0 || stoppedForMemory || sitemapEvidencePartial || accessEvidencePartial || requiredSitemapUnavailable;
 		const failed = !cancelled && pages.length === 0 && (requiredSitemapUnavailable || requests.length > 0 && requests.every((request) => request.outcome === "failure"));
 		const requestEvidenceStatus = cancelled && inFlight.size > 0 ? "partial" : "available";
 		const dataSources = await crawlDataSources({
@@ -18176,7 +18389,10 @@ async function crawlSite(input, dependencies) {
 			timeoutMs: config.timeoutMs,
 			fetchStatusPage: deps.fetchStatusPage,
 			respectRobots: config.respectRobots,
-			signal
+			signal,
+			rate: rateLimit.rate,
+			sleep: deps.sleep,
+			retryDelayMs: rateLimit.settleMs
 		}) : void 0;
 		for (const page of pages) {
 			if (!page.geo || !llmsTxt) continue;
@@ -18245,6 +18461,8 @@ async function crawlSite(input, dependencies) {
 				queueSafetySkippedUrls,
 				queueSafetyInventoryCapped,
 				originBackpressureSkippedUrls,
+				rateLimit: rateLimit.caveatInput(config, pages.length),
+				sitemapLimit: sitemapLimitCaveatInput(config, sitemapDiscovery, input.maxPages === void 0),
 				memoryPressureSkippedUrls,
 				queryVariantSkippedUrls: queryVariantSkipped.size,
 				renderingFallbackUrls,
@@ -32200,6 +32418,31 @@ async function dataForSeoRows(keys, input, spent) {
 }
 const GAP_DOMAINS = 1e3;
 const GAP_COMPETITORS = 5;
+const SHORTENERS = [
+	"bit.ly",
+	"tinyurl.com",
+	"t.co",
+	"ow.ly",
+	"buff.ly",
+	"is.gd",
+	"cutt.ly",
+	"rebrand.ly",
+	"shorturl.at",
+	"rb.gy",
+	"lnkd.in"
+];
+const FREE_APP_HOSTS = [
+	"web.app",
+	"firebaseapp.com",
+	"pages.dev"
+];
+const LINK_LIST_NAME = /(subdomain|whois|login|signin|coupon|promo|voucher|discount|sitelike|similarsite|sitesimilar|siteprice|sitevalue|siteworth|websiteworth|hypestat|statshow|websiteoutlook|siteinfo|domaininfo|domainstat|domaintools|ipaddress|dnslookup|linkdirectory|webdirectory|alternativeto-)/;
+function isLinkList(domain) {
+	const within = (name) => domain === name || domain.endsWith(`.${name}`);
+	if (SHORTENERS.some(within)) return true;
+	if (FREE_APP_HOSTS.some((name) => domain.endsWith(`.${name}`))) return true;
+	return LINK_LIST_NAME.test(domain.replace(/[-.]/g, ""));
+}
 async function linkGap(provider, headers, input) {
 	const target = bareTarget(input.target).replace(/^www\./, "");
 	const competitors = [...new Set((input.competitors ?? []).map((site) => bareTarget(site).replace(/^www\./, "")))].filter((site) => site && site !== target);
@@ -32240,8 +32483,10 @@ async function linkGap(provider, headers, input) {
 			found.set(domain, entry);
 		}
 	});
+	const gap = [...found.entries()].filter(([, entry]) => entry.sites.length >= 2 && (floor === null || entry.value >= floor));
+	const linkLists = gap.map(([domain]) => domain).filter(isLinkList).sort((a, b) => a.localeCompare(b));
 	return {
-		rows: [...found.entries()].filter(([, entry]) => entry.sites.length >= 2 && (floor === null || entry.value >= floor)).sort(([a, left], [b, right]) => right.value - left.value || right.sites.length - left.sites.length || a.localeCompare(b)).map(([domain, entry]) => ({
+		rows: gap.filter(([domain]) => !isLinkList(domain)).sort(([a, left], [b, right]) => right.value - left.value || right.sites.length - left.sites.length || a.localeCompare(b)).map(([domain, entry]) => ({
 			domain,
 			[score]: entry.value,
 			competitors_linking: entry.sites.length,
@@ -32254,7 +32499,8 @@ async function linkGap(provider, headers, input) {
 		...floor !== null ? { floor: {
 			field: score,
 			value: floor
-		} } : {}
+		} } : {},
+		...linkLists.length ? { leftOut: linkLists } : {}
 	};
 }
 function isPage(target) {
@@ -32621,6 +32867,7 @@ async function runAiAnswers(input, headers, deps, more) {
 		question,
 		impressions,
 		task: null,
+		ref: null,
 		cost_usd: 0,
 		...empty
 	});
@@ -32632,7 +32879,8 @@ async function runAiAnswers(input, headers, deps, more) {
 			...blank("", null),
 			engine: engine.name,
 			result: "pending",
-			task: value
+			task: value,
+			ref: value
 		};
 		rows.push(row);
 		waiting.push({
@@ -32685,6 +32933,7 @@ async function runAiAnswers(input, headers, deps, more) {
 				}
 				row.result = "pending";
 				row.task = `${engine.name}:${task.id}`;
+				row.ref = row.task;
 				waiting.push({
 					row,
 					engine,
@@ -32725,6 +32974,7 @@ async function runAiAnswers(input, headers, deps, more) {
 	const cost = usd(rows.reduce((sum, row) => sum + row.cost_usd, 0));
 	const count = (result) => rows.filter((row) => row.result === result).length;
 	const left = rows.filter((row) => row.task).map((row) => row.task);
+	const refs = rows.flatMap((row) => row.ref ? [row.ref] : []);
 	const cites = /* @__PURE__ */ new Map();
 	for (const row of rows) for (const host of row.sources) cites.set(host, (cites.get(host) ?? 0) + 1);
 	const topCited = [...cites].sort((a, b) => b[1] - a[1] || a[0].localeCompare(b[0])).slice(0, 10);
@@ -32758,7 +33008,7 @@ async function runAiAnswers(input, headers, deps, more) {
 			limit: 50,
 			detail: input.detail,
 			notes,
-			more
+			more: (offset) => more(offset, refs)
 		}),
 		data: {
 			provider: "dataforseo",
@@ -32772,6 +33022,7 @@ async function runAiAnswers(input, headers, deps, more) {
 			questions: [...new Set(rows.map((row) => row.question))],
 			costUsd: cost,
 			pendingTasks: left,
+			tasks: refs,
 			citedSites: topCited.map(([host, answers]) => ({
 				host,
 				answers
@@ -32891,7 +33142,7 @@ function ga4MatchReason(match, site) {
 }
 // packages/core/src/commands/analytics-site.ts
 const STREAM_CHECKS = 30;
-const AT_ONCE = 5;
+const AT_ONCE$1 = 5;
 const TIED = 3;
 const hostOf$1 = (site) => {
 	const value = site.replace(/^sc-domain:/, "");
@@ -32956,8 +33207,8 @@ async function lookProperty(access, site) {
 	}
 	const order = ranked(site, candidates).slice(0, STREAM_CHECKS);
 	let failures = 0;
-	for (let start = 0; start < order.length; start += AT_ONCE) {
-		const batch = order.slice(start, start + AT_ONCE);
+	for (let start = 0; start < order.length; start += AT_ONCE$1) {
+		const batch = order.slice(start, start + AT_ONCE$1);
 		const streams = await Promise.all(batch.map((candidate) => listAnalyticsDataStreams(candidate.google, candidate.property, { signIn: access.signIn }).catch(() => {
 			failures += 1;
 			return [];
@@ -34090,7 +34341,8 @@ async function runClickyRows(input, keys, options) {
 // packages/core/src/commands/domain-rating.ts
 const DR_ATTRIBUTION = "domain_rating: Domain Rating by Ahrefs (https://ahrefs.com/).";
 const ENDPOINT = "https://api.ahrefs.com/v3/public/domain-rating-free";
-const MAX_DOMAINS = 25;
+const MAX_DOMAINS = 50;
+const AT_ONCE = 25;
 const TTL_SECONDS = 86400;
 const DOMAIN_FIELDS = [
 	"domain",
@@ -34121,23 +34373,26 @@ async function lookup(domain, key) {
 	}
 	return body.domain_rating?.domain_rating ?? null;
 }
-async function domainRatings(domains, key) {
+async function domainRatings(domains, key, max = MAX_DOMAINS) {
 	const found = /* @__PURE__ */ new Map();
 	if (!key) return found;
-	const unique = [...new Set(domains.map(bareDomain).filter(Boolean))].slice(0, MAX_DOMAINS);
-	const values = await Promise.all(unique.map((domain) => lookup(domain, key).catch(() => null)));
-	unique.forEach((domain, index) => {
-		found.set(domain, values[index] ?? null);
-	});
+	const unique = [...new Set(domains.map(bareDomain).filter(Boolean))].slice(0, max);
+	for (let start = 0; start < unique.length; start += AT_ONCE) {
+		const batch = unique.slice(start, start + AT_ONCE);
+		const values = await Promise.all(batch.map((domain) => lookup(domain, key).catch(() => null)));
+		batch.forEach((domain, index) => {
+			found.set(domain, values[index] ?? null);
+		});
+	}
 	return found;
 }
-async function withDomainRating(rows, key) {
+async function withDomainRating(rows, key, start = 0) {
 	const field = DOMAIN_FIELDS.find((name) => rows.some((row) => typeof row[name] === "string"));
 	if (!key || !field || rows.some((row) => "domain_rating" in row)) return {
 		rows,
 		added: false
 	};
-	const ratings = await domainRatings(rows.map((row) => String(row[field] ?? "")), key);
+	const ratings = await domainRatings(rows.slice(start).map((row) => String(row[field] ?? "")), key);
 	return {
 		rows: rows.map((row) => {
 			const next = {};
@@ -36173,7 +36428,7 @@ async function runResearch(input, keys, options) {
 	const offset = input.offset ?? 0;
 	const language = input.provider === "dataforseo" ? dataForSeoLanguage(country) : null;
 	if (input.action === "ai_answers") throw new CommandError("INVALID_INPUT", "ai_answers runs on its own.");
-	const { rows: found, costUsd, partial, missed, noData, floor } = await research(input.provider, keys, {
+	const { rows: found, costUsd, partial, missed, noData, floor, leftOut } = await research(input.provider, keys, {
 		action: input.action,
 		keywords: input.keywords ?? [],
 		target,
@@ -36187,7 +36442,8 @@ async function runResearch(input, keys, options) {
 	};
 	const unresolved = rows.filter((row) => row.url === null && row.url_hint !== void 0).length;
 	const drKey = keys.get("x-ahrefs-key") ?? options.drKey;
-	const rated = await withDomainRating(rows, drKey);
+	const byDr = input.action === "link_gap" && input.provider === "dataforseo" && drKey;
+	const rated = byDr ? await sortedByDomainRating(rows, drKey) : await withDomainRating(rows, drKey, offset);
 	const targetDr = target ? (await domainRatings([target], drKey)).get(bareDomain(target)) : void 0;
 	const hasTargetDr = targetDr !== void 0 && targetDr !== null;
 	return {
@@ -36203,6 +36459,8 @@ async function runResearch(input, keys, options) {
 				...partial ? ["Partial: DataForSEO could not fetch some pages of results, so rows may be missing."] : [],
 				...missed.length ? [`Partial: ${input.provider} failed for ${missed.join(", ")}, so those keywords have no rows. Ask for them again.`] : [],
 				...noData.length ? [noDataNote(input, noData)] : [],
+				...byDr ? [rows.length > GAP_RATED ? `Sorted by Domain Rating for the top ${GAP_RATED} rows by DataForSEO rank; the ${rows.length - GAP_RATED} rows after them follow by rank, with no Domain Rating.` : "Sorted by Domain Rating, then DataForSEO rank."] : [],
+				...leftOut?.length ? [`Left out ${leftOut.length} link lists, URL shorteners and directories that link to most sites (a guess from the host name): ${leftOut.join(", ")}.`] : [],
 				...floor ? [`Cut at ${floor.field} ${floor.value}: at least one site has more than 1,000 referring domains, and only its top 1,000 were read, so domains below ${floor.field} ${floor.value} are left out rather than guessed.`] : [],
 				...unresolved ? [unresolvedNote(input, unresolved, rows.length)] : [],
 				...note ? [note] : [],
@@ -36226,7 +36484,8 @@ async function runResearch(input, keys, options) {
 			noDataKeywords: noData,
 			...input.action === "link_gap" ? {
 				competitors: input.competitors ?? [],
-				cutAt: floor ?? null
+				cutAt: floor ?? null,
+				leftOut: leftOut ?? []
 			} : {},
 			total: rated.rows.length,
 			offset,
@@ -36242,6 +36501,24 @@ function noDataNote(input, keywords) {
 function unresolvedNote(input, count, total) {
 	return `${count} of ${total} results have no exact page: ${input.provider} returned Google redirect links for them. Their domain and url_hint come from Google's breadcrumb, which is shortened.${input.provider === "dataforseo" ? " For exact pages, use provider ahrefs." : ""}`;
 }
+const GAP_RATED = 200;
+async function sortedByDomainRating(rows, key) {
+	const top = rows.slice(0, GAP_RATED);
+	const ratings = await domainRatings(top.map((row) => String(row.domain ?? "")), key, GAP_RATED);
+	const withDr = (row, rated) => {
+		const { domain = null, ...rest } = row;
+		return {
+			domain,
+			domain_rating: rated ? ratings.get(bareDomain(String(domain ?? ""))) ?? null : null,
+			...rest
+		};
+	};
+	const dr = (row) => Number(row.domain_rating ?? -1);
+	return {
+		rows: [...top.map((row) => withDr(row, true)).sort((a, b) => dr(b) - dr(a) || Number(b.rank ?? 0) - Number(a.rank ?? 0) || String(a.domain).localeCompare(String(b.domain))), ...rows.slice(GAP_RATED).map((row) => withDr(row, false))],
+		added: true
+	};
+}
 // packages/core/src/commands/sitemap-urls.ts
 const MAX_FILES = 20;
 const MAX_URLS = 5e4;
@@ -37103,7 +37380,7 @@ const SHARED_TOOLS = [
 					offset: input.offset,
 					questions: input.keywords,
 					tasks: input.tasks
-				}, await surface.keys(), surface.deps, more);
+				}, await surface.keys(), surface.deps, (offset, tasks) => `seo_research with the same provider, action and target, tasks ${JSON.stringify(tasks)}, detail "rows", offset ${offset}. Passing the tasks reads these answers back at no cost; without them every question is asked and paid for again`);
 			}
 			return runResearch(input, await surface.keys(), {
 				drKey: surface.drKey,
@@ -39947,6 +40224,6 @@ function isoDate(daysAgo = 0) {
 	date.setUTCDate(date.getUTCDate() - daysAgo);
 	return date.toISOString().slice(0, 10);
 }
-export { AHREFS_API_KEY_ENV, AHREFS_API_KEY_SECRET, AI_REFERRAL_SOURCES, AI_REFERRAL_SOURCES_VERSION, ANALYTICS_PROVIDER_IDS, AUDIT_PAGE_RULE_IDS, AhrefsClient, BING_API_KEY_ENV, BING_API_KEY_SECRET, BROWSER_USER_AGENT, CANNIBAL_MAXIMUM_DOMINANT_SHARE, CANNIBAL_MINIMUM_PAGE_IMPRESSIONS, CANNIBAL_MINIMUM_PAGE_SHARE, CLICKY_SITEKEY_ENV, CLICKY_SITE_KEYS_SECRET, CLOUD_SIGN_IN, CLOUD_URL, CRAWL_SKIP_REASONS, CTR_DEFAULT_LIMIT, CTR_MAX_LIMIT, CTR_MAX_MIN_IMPRESSIONS, DATAFORSEO_CREDENTIAL_SECRET, DATAFORSEO_LOGIN_ENV, DATAFORSEO_PASSWORD_ENV, DEFAULT_MAX_PAGES, DEFAULT_SEARCH_CONSOLE_EXPORT_ROW_LIMIT, DEFAULT_UNREACHED_PAGE_LIMIT, DataForSeoClient, DecisionModelError, DecisionRunner, GSC_FINAL_DATA_LAG_DAYS, GSC_TIME_ZONE, GoogleApiError, INCIDENTS_URL, JsonFileStorageAdapter, LINK_ROLES, LINT_MAX_FILES, LOCAL_BING_CONNECT, LOCAL_SIGN_IN, LOG_MAX_AGE_MS, LOG_MAX_FILE_BYTES, LOG_MAX_TOTAL_BYTES, LocalCredentialsProvider, MANAGED_PROVIDER_SECRET_NAMES, MAX_CRAWL_CONCURRENCY, MAX_CRAWL_DEPTH, MAX_CRAWL_PAGES, MAX_CRAWL_TIMEOUT_MS, MAX_MAX_PAGES, MAX_SEARCH_CONSOLE_EXPORT_FILES, MAX_SEARCH_CONSOLE_EXPORT_ROW_LIMIT, PAGE_TYPES, PROVIDER_ERROR_CODES, PROVIDER_SECRET_NAMES, ProviderError, ProviderExtensionRegistry, RESEARCH_IMPORT_COLUMN_KEYS, ResponseSizeLimitError, SEARCH_INTENTS, SEO_CRAWLER_IDENTITY, SEO_CRAWLER_TOKEN, SEO_CRAWLER_USER_AGENT, SEO_PROVIDER_API_VERSION, SEO_VERSION, SERP_TITLE_REFERENCE_WIDTH_PX, SERP_TITLE_WIDTH_PROFILE, SITEMAP_FILE_URL_LIMIT, SITE_CHECK_MAX_ISSUES, SITE_CHECK_MAX_PAGES, STEP_CHANGE_RULES, SeoError, ServiceAccountAccessTokenClient, SessionLedger, TELEMETRY_AGENTS, TELEMETRY_ENDPOINT, TELEMETRY_ERROR_CATEGORIES, TELEMETRY_EVENTS, TELEMETRY_FAILURE_CONTEXTS, TELEMETRY_FAILURE_REASONS, TELEMETRY_NOTICE, TELEMETRY_OPERATIONS, TELEMETRY_REPORTS, TELEMETRY_SCHEMA_VERSION, TELEMETRY_TIMEOUT_MS, TYPESAFE_API_KEY_ENV, agentActionsView, aiReferralSourceForValue, aiReferralsReport, analyticsConnectionLabel, analyticsConnectionProviderId, analyticsConnectionSchema, analyticsProviderDetails, analyticsProviderSchema, analyzeAiReferralRows, analyzeCannibalImportRows, analyzeCannibalRows, analyzeCtrUnderperformersFromRows, analyzeDecay, analyzeIndexCoverageSignals, analyzePageOpportunitiesFromRows, analyzeQueryClustersFromRows, analyzeQuickWinsFromRows, analyzeSecondPageRows, analyzeSegmentRows, analyzeStrikingDistanceRows, analyzeTrafficAnomalyRows, assertCrawlConfigLimits, assertUrlMatchesGscProperty, auditCrawlPages, auditCrawlRequests, auditPage, authStatus, bearerFetch, boundedSitemapInventory, buildAgentFindings, buildQueryClusterReportFromRows, buildTelemetryPayload, builtPagePath, cacheDb, cannibalDataStatus, cannibalImportReport, cannibalReport, cannibalReportWith, changeWindow, checkBuiltSite, checkDatabaseReadiness, classifyTelemetryFailure, clearCache, cloudAccountFor, cloudBing, cloudCredentials, cloudGoogleEmails, cloudGoogleToken, cloudKeys, cloudLinked, cloudLogout, cloudWeek, clusterQueryRows, combineRobotsValues, compareSegmentRows, configSchema, contentCoverageRecommendation, contentCoverageType, contentOptimizationFromPageOpportunities, contentOptimizationReport, countLabel, crawlConfigHash, crawlConfigSchema, crawlDefinitionId, crawlFixToQueueItem, crawlImplementationQueueWorkflow, crawlIssueGroupSchema, crawlIssueSchema, crawlOne, crawlPageSnapshotSchema, crawlReportSchema, crawlReportSummarySchema, crawlRequestObservationSchema, crawlRunId, crawlSite, crawlSkipImpact, crawlSkipReasonCountsFromRecord, crawlStatusOnly, crawlTopFixSchema, crawlerJsonSchemas, crawlerRuleCategorySchema, crawlerRuleIdSchema, crawlerRuleInfoSchema, crawlerRuleRecommendationSchema, crawlerRuleSeveritySchema, crawlerSchemas, createAuthorizedClient, createCrawlReport, createCtrBenchmarkContext, createGoogleAccessTokenClient, createLogger, createPageRenderer, ctrUnderperformersReport, ctrUnderperformersReportWith, decayClusterDrafts, decayComparisonRange, decayingReport, decayingReportWith, deleteAhrefsApiKey, deleteBingApiKey, deleteClickySiteKey, deleteDataForSeoCredentials, deleteManagedProviderSecrets, deleteProviderExtensionAccount, deleteProviderExtensionCredentials, deleteProviderSecret, deleteTokens, deriveBrandTerms, describeInstalledProviderExtension, detectAgentName, detectBrandTerms, detectTelemetryAgent, diagnoseCsvFiles, diagnoseProperty, diagnosePropertyWorkflow, effectiveRobotsDirectives, effectiveSnippetControl, ensurePrivateDatabaseFiles, ensureSeoCliDirs, estimateSerpTitleWidth, expectedCtrForPosition, explainRule, fetchCruxFieldData, fetchPage, fetchPageStatus, fetchSearchStatusIncidents, fetchSitemapUrls, fileSize, finalGscDateRange, findOverlappingSearchUpdates, finishCloudLogin, formatRelativeExpiry, ga4MatchReason, ga4PropertyIdFromName, ga4ReportQualityWarnings, ga4RequestCanUseCache, ga4RowsToObjects, getAuthModeStatus, getCacheStats, getClientConfig, getDb, getPrivacySnapshot, getSeoCliPaths, getServiceAccountConfig, getServiceAccountStatus, getTelemetryStatus, getTokenStorageStatus, googleJson, groupCrawlIssues, hasMetaRobotsDirective, hasRule, hasXRobotsDirective, hashKey, indexCoverageSignals, inferTemplateMovement, initializeTelemetry, inspectProviderPackage, inspectSearchConsoleUrl, inspectUrl, installProviderPackage, installedProviderPackageSchema, installedProviderPackagesSchema, internalLinksReport, internalLinksReportWith, interpretUpdateCorrelation, isBrandQuery, isNewerVersion, isSkippableReportError, isTelemetryCi, isTelemetryOperation, isTelemetryReport, isoDate, isoWeek, latestFinalGscDate, linkRecover, linkRecoverRecommendation, lintPaths, listAnalyticsAccounts, listAnalyticsDataStreams, listGa4AccountSummaries, listGa4DataStreams, listGoogleAccounts, listInstalledProviderExtensions, listRules, listSearchConsoleSites, listSearchUpdates, listSites, loadInstalledProviderExtensions, loadProviderExtensions, loadProviderPackage, loadSearchConsoleExport, localAccounts, localBing, localCredentialsProvider, localError, localGoogleFetch, localInternalLinksDependencies, localRefreshClicky, localResearchKeys, loginWithLoopback, makeRunId, matchGa4WebStreams, measureCoverage, metaRobotsDirectives, migrateLegacyMacConfig, missingOAuthClientMessage, missingSharedClientLoginMessage, nodeCommandDeps, normalizeBrandText, normalizeClickySiteId, normalizeClickySiteKey, normalizeCrawlConfig, normalizeCrawlSkipReasonCounts, normalizeForCoverage, normalizeHttpUrl, normalizeJavaScriptRenderingMode, normalizeLoadedCrawlReport, normalizeProviderExtensionAccount, normalizedResearchColumnName, notSignedIn, noteCacheWrite, openCloudLink, pageEvidenceRecommendation, pageOpportunitiesReport, parseOlderThan, pendingCloudLogin, performanceAudit, performanceReportIsCacheable, plural, providerCapabilitySchema, providerConnectionFieldSchema, providerExactVersionSchema, providerExtensionIdSchema, providerIdSchema, providerIntegritySchema, providerKindSchema, providerPackageManifestSchema, providerPackageNameSchema, providerPreferenceSchema, providerRegistrationSchema, providerRequestJson, providerRequestText, pruneLogs, publicHttpFetch, queryClusterReport, queryClusterTokens, queryContentCoverageFromPage, queryContentFieldsFromPage, queryFieldCoverage, queryOpportunityRecommendation, queryPageMetrics, queryPageTopQuery, queryPagesMetrics, queryPagesMetricsBatch, queryPagesTopQueries, queryPagesTopQueriesBatch, querySearchAnalytics, quickWinsCsvRows, quickWinsReport, quickWinsReportWith, readAhrefsApiKey, readAllTokens, readBingApiKey, readBoundedResponseText, readClickySiteKey, readClickySiteKeys, readConfig, readDataForSeoCredentials, readInstalledProviderPackages, readJson, readJsonOrUndefined, readLintFiles, readOauthClient, readProviderExtensionAccount, readProviderExtensionCredentials, readProviderSecret, readTokens, recommendationForRule, reconcileExportPagesWithCrawl, redirectTrace, refreshAuthToken, refreshPrioritiesCsvFiles, refreshPrioritiesWorkflow, registrableDomain, removeInstalledProviderPackage, renderCrawlCsv, renderCrawlHtml, renderCrawlJunit, renderCrawlMarkdownTickets, renderCrawlPagesCsv, renderCrawlPretty, renderCsv, renderPresentationTablesMarkdown, renderWorkflowMarkdown, reportNarrative, requestHeaders, requirePageVerification, researchImportColumns, resetSeoData, resolveLocalSite, resolveSegmentRanges, resolveSeoCliPaths, reviewObservations, roundedPosition, runAnalyticsProviderLandingPages, runAnalyticsReport, runDoctor, runGa4Report, runProviderExtensionAction, runtimeForProvider, safeProviderAdapterError, saveInstalledProviderPackage, searchAnalyticsRows, searchUpdatesFromIncidents, secondPage, secondPageWith, segmentComparisonRange, segmentImpact, segmentRangeDays, seoErrorEnvelope, sessionSourceInListFilter, setActiveGoogleAccount, setTelemetryEnabled, setTokenStorageMode, shiftIsoDate, shouldExcludeBrandQuery, siteStartUrl, snapshotFetchedPage, startCloudLogin, strikingDistance, strikingDistanceWith, summarizeCrawlReport, pageTechnicalSignals as technicalPageSignals, telemetryErrorCategory, toSeoError, tokenSchema, tokenStoreSchema, topFixes, trackTelemetryCommandFailed, trackTelemetryReportComplete, trackTelemetryReportFailed, trackTelemetryReportStart, trackTelemetrySetupComplete, trafficAnomaly, trafficAnomalyWith, typesafeDecisionModel, unavailableSegmentImpactReport, unicodeTokens, uninstallProviderExtension, updateCorrelation, updateNotice, updatePostmortemCsvFiles, updatePostmortemWorkflow, urlInspectionQuota, validateResearchImportColumnSources, verifyAnalyticsProvider, verifyProviderExtension, verifyQueryContent, verifyQueryContentWith, withAgentReportContract, withRankingHistory, workflowPresentation, writeAhrefsApiKey, writeBingApiKey, writeClickySiteKey, writeConfig, writeDataForSeoCredentials, writeInstalledProviderPackages, writeOauthClient, writeProviderExtensionAccount, writeProviderExtensionCredentials, writeProviderSecret, writeToCache, writeTokens, xRobotsDirectives };
+export { AHREFS_API_KEY_ENV, AHREFS_API_KEY_SECRET, AI_REFERRAL_SOURCES, AI_REFERRAL_SOURCES_VERSION, ANALYTICS_PROVIDER_IDS, AUDIT_PAGE_RULE_IDS, AhrefsClient, BING_API_KEY_ENV, BING_API_KEY_SECRET, BROWSER_USER_AGENT, CANNIBAL_MAXIMUM_DOMINANT_SHARE, CANNIBAL_MINIMUM_PAGE_IMPRESSIONS, CANNIBAL_MINIMUM_PAGE_SHARE, CLICKY_SITEKEY_ENV, CLICKY_SITE_KEYS_SECRET, CLOUD_SIGN_IN, CLOUD_URL, CRAWL_SKIP_REASONS, CTR_DEFAULT_LIMIT, CTR_MAX_LIMIT, CTR_MAX_MIN_IMPRESSIONS, DATAFORSEO_CREDENTIAL_SECRET, DATAFORSEO_LOGIN_ENV, DATAFORSEO_PASSWORD_ENV, DEFAULT_MAX_PAGES, DEFAULT_SEARCH_CONSOLE_EXPORT_ROW_LIMIT, DEFAULT_UNREACHED_PAGE_LIMIT, DataForSeoClient, DecisionModelError, DecisionRunner, GSC_FINAL_DATA_LAG_DAYS, GSC_TIME_ZONE, GoogleApiError, INCIDENTS_URL, JsonFileStorageAdapter, LINK_ROLES, LINT_MAX_FILES, LOCAL_BING_CONNECT, LOCAL_SIGN_IN, LOG_MAX_AGE_MS, LOG_MAX_FILE_BYTES, LOG_MAX_TOTAL_BYTES, LocalCredentialsProvider, MANAGED_PROVIDER_SECRET_NAMES, MAX_CRAWL_CONCURRENCY, MAX_CRAWL_DEPTH, MAX_CRAWL_PAGES, MAX_CRAWL_TIMEOUT_MS, MAX_MAX_PAGES, MAX_SEARCH_CONSOLE_EXPORT_FILES, MAX_SEARCH_CONSOLE_EXPORT_ROW_LIMIT, PAGE_TYPES, PROVIDER_ERROR_CODES, PROVIDER_SECRET_NAMES, ProviderError, ProviderExtensionRegistry, RESEARCH_IMPORT_COLUMN_KEYS, ResponseSizeLimitError, SEARCH_INTENTS, SEO_CRAWLER_IDENTITY, SEO_CRAWLER_TOKEN, SEO_CRAWLER_USER_AGENT, SEO_PROVIDER_API_VERSION, SEO_VERSION, SERP_TITLE_REFERENCE_WIDTH_PX, SERP_TITLE_WIDTH_PROFILE, SITEMAP_FILE_URL_LIMIT, SITE_CHECK_MAX_ISSUES, SITE_CHECK_MAX_PAGES, STEP_CHANGE_RULES, SeoError, ServiceAccountAccessTokenClient, SessionLedger, TELEMETRY_AGENTS, TELEMETRY_ENDPOINT, TELEMETRY_ERROR_CATEGORIES, TELEMETRY_EVENTS, TELEMETRY_FAILURE_CONTEXTS, TELEMETRY_FAILURE_REASONS, TELEMETRY_NOTICE, TELEMETRY_OPERATIONS, TELEMETRY_REPORTS, TELEMETRY_SCHEMA_VERSION, TELEMETRY_TIMEOUT_MS, TYPESAFE_API_KEY_ENV, agentActionsView, aiReferralSourceForValue, aiReferralsReport, analyticsConnectionLabel, analyticsConnectionProviderId, analyticsConnectionSchema, analyticsProviderDetails, analyticsProviderSchema, analyzeAiReferralRows, analyzeCannibalImportRows, analyzeCannibalRows, analyzeCtrUnderperformersFromRows, analyzeDecay, analyzeIndexCoverageSignals, analyzePageOpportunitiesFromRows, analyzeQueryClustersFromRows, analyzeQuickWinsFromRows, analyzeSecondPageRows, analyzeSegmentRows, analyzeStrikingDistanceRows, analyzeTrafficAnomalyRows, assertCrawlConfigLimits, assertUrlMatchesGscProperty, auditCrawlPages, auditCrawlRequests, auditPage, authStatus, bearerFetch, boundedSitemapInventory, buildAgentFindings, buildQueryClusterReportFromRows, buildTelemetryPayload, builtPagePath, cacheDb, cannibalDataStatus, cannibalImportReport, cannibalReport, cannibalReportWith, changeWindow, checkBuiltSite, checkDatabaseReadiness, classifyTelemetryFailure, clearCache, cloudAccountFor, cloudBing, cloudCredentials, cloudGoogleEmails, cloudGoogleToken, cloudKeys, cloudLinked, cloudLogout, cloudWeek, clusterQueryRows, combineRobotsValues, compareSegmentRows, configSchema, contentCoverageRecommendation, contentCoverageType, contentOptimizationFromPageOpportunities, contentOptimizationReport, countLabel, crawlConfigHash, crawlConfigSchema, crawlCoverageCaveat, crawlDefinitionId, crawlFixToQueueItem, crawlImplementationQueueWorkflow, crawlIssueGroupSchema, crawlIssueSchema, crawlOne, crawlPageSnapshotSchema, crawlReportSchema, crawlReportSummarySchema, crawlRequestObservationSchema, crawlRunId, crawlSite, crawlSkipImpact, crawlSkipReasonCountsFromRecord, crawlStatusOnly, crawlTopFixSchema, crawlerJsonSchemas, crawlerRuleCategorySchema, crawlerRuleIdSchema, crawlerRuleInfoSchema, crawlerRuleRecommendationSchema, crawlerRuleSeveritySchema, crawlerSchemas, createAuthorizedClient, createCrawlReport, createCtrBenchmarkContext, createGoogleAccessTokenClient, createLogger, createPageRenderer, ctrUnderperformersReport, ctrUnderperformersReportWith, decayClusterDrafts, decayComparisonRange, decayingReport, decayingReportWith, deleteAhrefsApiKey, deleteBingApiKey, deleteClickySiteKey, deleteDataForSeoCredentials, deleteManagedProviderSecrets, deleteProviderExtensionAccount, deleteProviderExtensionCredentials, deleteProviderSecret, deleteTokens, deriveBrandTerms, describeInstalledProviderExtension, detectAgentName, detectBrandTerms, detectTelemetryAgent, diagnoseCsvFiles, diagnoseProperty, diagnosePropertyWorkflow, effectiveRobotsDirectives, effectiveSnippetControl, ensurePrivateDatabaseFiles, ensureSeoCliDirs, estimateSerpTitleWidth, expectedCtrForPosition, explainRule, fetchCruxFieldData, fetchPage, fetchPageStatus, fetchSearchStatusIncidents, fetchSitemapUrls, fileSize, finalGscDateRange, findOverlappingSearchUpdates, finishCloudLogin, formatRelativeExpiry, ga4MatchReason, ga4PropertyIdFromName, ga4ReportQualityWarnings, ga4RequestCanUseCache, ga4RowsToObjects, getAuthModeStatus, getCacheStats, getClientConfig, getDb, getPrivacySnapshot, getSeoCliPaths, getServiceAccountConfig, getServiceAccountStatus, getTelemetryStatus, getTokenStorageStatus, googleJson, groupCrawlIssues, hasMetaRobotsDirective, hasRule, hasXRobotsDirective, hashKey, indexCoverageSignals, inferTemplateMovement, initializeTelemetry, inspectProviderPackage, inspectSearchConsoleUrl, inspectUrl, installProviderPackage, installedProviderPackageSchema, installedProviderPackagesSchema, internalLinksReport, internalLinksReportWith, interpretUpdateCorrelation, isBrandQuery, isNewerVersion, isSkippableReportError, isTelemetryCi, isTelemetryOperation, isTelemetryReport, isoDate, isoWeek, latestFinalGscDate, linkRecover, linkRecoverRecommendation, lintPaths, listAnalyticsAccounts, listAnalyticsDataStreams, listGa4AccountSummaries, listGa4DataStreams, listGoogleAccounts, listInstalledProviderExtensions, listRules, listSearchConsoleSites, listSearchUpdates, listSites, loadInstalledProviderExtensions, loadProviderExtensions, loadProviderPackage, loadSearchConsoleExport, localAccounts, localBing, localCredentialsProvider, localError, localGoogleFetch, localInternalLinksDependencies, localRefreshClicky, localResearchKeys, loginWithLoopback, makeRunId, matchGa4WebStreams, measureCoverage, metaRobotsDirectives, migrateLegacyMacConfig, missingOAuthClientMessage, missingSharedClientLoginMessage, nodeCommandDeps, normalizeBrandText, normalizeClickySiteId, normalizeClickySiteKey, normalizeCrawlConfig, normalizeCrawlSkipReasonCounts, normalizeForCoverage, normalizeHttpUrl, normalizeJavaScriptRenderingMode, normalizeLoadedCrawlReport, normalizeProviderExtensionAccount, normalizedResearchColumnName, notSignedIn, noteCacheWrite, openCloudLink, pageEvidenceRecommendation, pageOpportunitiesReport, parseOlderThan, pendingCloudLogin, performanceAudit, performanceReportIsCacheable, plural, providerCapabilitySchema, providerConnectionFieldSchema, providerExactVersionSchema, providerExtensionIdSchema, providerIdSchema, providerIntegritySchema, providerKindSchema, providerPackageManifestSchema, providerPackageNameSchema, providerPreferenceSchema, providerRegistrationSchema, providerRequestJson, providerRequestText, pruneLogs, publicHttpFetch, queryClusterReport, queryClusterTokens, queryContentCoverageFromPage, queryContentFieldsFromPage, queryFieldCoverage, queryOpportunityRecommendation, queryPageMetrics, queryPageTopQuery, queryPagesMetrics, queryPagesMetricsBatch, queryPagesTopQueries, queryPagesTopQueriesBatch, querySearchAnalytics, quickWinsCsvRows, quickWinsReport, quickWinsReportWith, readAhrefsApiKey, readAllTokens, readBingApiKey, readBoundedResponseText, readClickySiteKey, readClickySiteKeys, readConfig, readDataForSeoCredentials, readInstalledProviderPackages, readJson, readJsonOrUndefined, readLintFiles, readOauthClient, readProviderExtensionAccount, readProviderExtensionCredentials, readProviderSecret, readTokens, recommendationForRule, reconcileExportPagesWithCrawl, redirectTrace, refreshAuthToken, refreshPrioritiesCsvFiles, refreshPrioritiesWorkflow, registrableDomain, removeInstalledProviderPackage, renderCrawlCsv, renderCrawlHtml, renderCrawlJunit, renderCrawlMarkdownTickets, renderCrawlPagesCsv, renderCrawlPretty, renderCsv, renderPresentationTablesMarkdown, renderWorkflowMarkdown, reportNarrative, requestHeaders, requirePageVerification, researchImportColumns, resetSeoData, resolveLocalSite, resolveSegmentRanges, resolveSeoCliPaths, reviewObservations, roundedPosition, runAnalyticsProviderLandingPages, runAnalyticsReport, runDoctor, runGa4Report, runProviderExtensionAction, runtimeForProvider, safeProviderAdapterError, saveInstalledProviderPackage, searchAnalyticsRows, searchUpdatesFromIncidents, secondPage, secondPageWith, segmentComparisonRange, segmentImpact, segmentRangeDays, seoErrorEnvelope, sessionSourceInListFilter, setActiveGoogleAccount, setTelemetryEnabled, setTokenStorageMode, shiftIsoDate, shouldExcludeBrandQuery, siteStartUrl, snapshotFetchedPage, startCloudLogin, strikingDistance, strikingDistanceWith, summarizeCrawlReport, pageTechnicalSignals as technicalPageSignals, telemetryErrorCategory, toSeoError, tokenSchema, tokenStoreSchema, topFixes, trackTelemetryCommandFailed, trackTelemetryReportComplete, trackTelemetryReportFailed, trackTelemetryReportStart, trackTelemetrySetupComplete, trafficAnomaly, trafficAnomalyWith, typesafeDecisionModel, unavailableSegmentImpactReport, unicodeTokens, uninstallProviderExtension, updateCorrelation, updateNotice, updatePostmortemCsvFiles, updatePostmortemWorkflow, urlInspectionQuota, validateResearchImportColumnSources, verifyAnalyticsProvider, verifyProviderExtension, verifyQueryContent, verifyQueryContentWith, withAgentReportContract, withRankingHistory, workflowPresentation, writeAhrefsApiKey, writeBingApiKey, writeClickySiteKey, writeConfig, writeDataForSeoCredentials, writeInstalledProviderPackages, writeOauthClient, writeProviderExtensionAccount, writeProviderExtensionCredentials, writeProviderSecret, writeToCache, writeTokens, xRobotsDirectives };
 
 //# sourceMappingURL=index.js.map