seo 0.16.0 → 0.17.0

package/dist/index.d.ts

@@ -1753,6 +1753,7 @@ export interface UrlInspectionRequest {
   accountEmail?: string;
   languageCode?: string;
   quotaLimit?: number;
+  signal?: AbortSignal;
 }
 export interface UrlInspectionResult {
   inspectionResult?: {
@@ -2831,7 +2832,7 @@ export declare function fetchSitemapUrls(input: {
   limit?: number;
   maxNested?: number;
 }): Promise<SitemapFetchResult>;
-export declare const CRAWL_SKIP_REASONS: readonly ["asset-url", "configured-exclusion", "duplicate-normalization", "invalid-url", "memory-pressure", "off-origin", "origin-backpressure", "queue-safety-limit", "query-variant-limit", "robots-disallowed", "robots-uncertain", "legacy-unclassified"];
+export declare const CRAWL_SKIP_REASONS: readonly ["asset-url", "cdn-utility-url", "configured-exclusion", "duplicate-normalization", "invalid-url", "memory-pressure", "off-origin", "origin-backpressure", "queue-safety-limit", "query-variant-limit", "robots-disallowed", "robots-uncertain", "legacy-unclassified"];
 export type CrawlSkipReason = (typeof CRAWL_SKIP_REASONS)[number];
 export type CrawlSkipImpact = 'coverage-affecting' | 'non-impacting';
 export type CrawlSkipReasonCount = {
@@ -2854,6 +2855,9 @@ export declare function normalizeCrawlSkipReasonCounts(input: {
 };
 export declare function crawlSkipReasonCountsFromRecord(input?: Partial<Record<CrawlSkipReason, number>>): CrawlSkipReasonCount[];
 type CrawlStatusPhase = 'started' | 'url_queued' | 'url_skipped' | 'page_started' | 'page_completed' | 'page_failed' | 'page_skipped' | 'external_links_started' | 'external_links_completed' | 'cancelled' | 'completed';
+export declare function fetchFailureKind(error: unknown, signal?: AbortSignal): Extract<CrawlRequestObservation, {
+  outcome: 'failure';
+}>['failureKind'];
 export type CrawlOneResult = {
   request?: CrawlRequestObservation;
   page?: CrawlPageSnapshot;
@@ -2879,6 +2883,7 @@ type CrawlSiteChecks = {
   };
 };
 type CrawlAiAvailability = 'available' | 'absent' | 'access-blocked' | 'rate-limited' | 'unreachable';
+type CrawlFetchErrorKind = 'dns' | 'tls' | 'timeout' | 'redirect-limit' | 'too-large' | 'aborted' | 'unknown';
 type CrawlAiBotAccess = {
   userAgent: string;
   purpose: 'search' | 'training' | 'other';
@@ -2908,6 +2913,7 @@ type CrawlAiSignals = {
     contentType?: string;
     servesHtml?: boolean;
     error?: string;
+    errorKind?: CrawlFetchErrorKind;
     sitemapUrls: string[];
     contentSignals?: string[];
     botAccess: CrawlAiBotAccess[];
@@ -2920,6 +2926,7 @@ type CrawlAiSignals = {
     contentType?: string;
     servesHtml?: boolean;
     error?: string;
+    errorKind?: CrawlFetchErrorKind;
     links?: {
       found: number;
       checked: number;
@@ -3267,6 +3274,8 @@ export declare function reviewObservations(report: CrawlReport, filters?: Omit<T
 export type CrawlOutputFormat = 'pretty' | 'json' | 'csv' | 'html' | 'markdown' | 'junit';
 export declare function renderCrawlCsv(report: CrawlReport): string;
 export declare function renderCrawlPagesCsv(report: CrawlReport): string;
+/** The caveat a report must lead with when the crawl read too little. */
+export declare function crawlCoverageCaveat(report: CrawlReport): string | undefined;
 export declare function renderCrawlPretty(report: CrawlReport, fixes?: TopFix[]): string;
 export declare function renderCrawlJunit(report: CrawlReport): string;
 export declare function renderCrawlHtml(report: CrawlReport, fixes?: TopFix[]): string;
@@ -4323,6 +4332,7 @@ export declare const crawlReportSummarySchema: z.ZodObject<{
       "robots-disallowed": "robots-disallowed";
       "origin-backpressure": "origin-backpressure";
       "asset-url": "asset-url";
+      "cdn-utility-url": "cdn-utility-url";
       "configured-exclusion": "configured-exclusion";
       "duplicate-normalization": "duplicate-normalization";
       "memory-pressure": "memory-pressure";
@@ -4490,6 +4500,7 @@ export declare const crawlReportSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         "robots-disallowed": "robots-disallowed";
         "origin-backpressure": "origin-backpressure";
         "asset-url": "asset-url";
+        "cdn-utility-url": "cdn-utility-url";
         "configured-exclusion": "configured-exclusion";
         "duplicate-normalization": "duplicate-normalization";
         "memory-pressure": "memory-pressure";
@@ -5300,6 +5311,15 @@ export declare const crawlReportSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
       contentType: z.ZodOptional<z.ZodString>;
       servesHtml: z.ZodOptional<z.ZodBoolean>;
       error: z.ZodOptional<z.ZodString>;
+      errorKind: z.ZodOptional<z.ZodEnum<{
+        unknown: "unknown";
+        timeout: "timeout";
+        dns: "dns";
+        tls: "tls";
+        "redirect-limit": "redirect-limit";
+        aborted: "aborted";
+        "too-large": "too-large";
+      }>>;
       sitemapUrls: z.ZodArray<z.ZodString>;
       contentSignals: z.ZodOptional<z.ZodArray<z.ZodString>>;
       botAccess: z.ZodArray<z.ZodObject<{
@@ -5328,6 +5348,15 @@ export declare const crawlReportSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
       contentType: z.ZodOptional<z.ZodString>;
       servesHtml: z.ZodOptional<z.ZodBoolean>;
       error: z.ZodOptional<z.ZodString>;
+      errorKind: z.ZodOptional<z.ZodEnum<{
+        unknown: "unknown";
+        timeout: "timeout";
+        dns: "dns";
+        tls: "tls";
+        "redirect-limit": "redirect-limit";
+        aborted: "aborted";
+        "too-large": "too-large";
+      }>>;
       links: z.ZodOptional<z.ZodObject<{
         found: z.ZodNumber;
         checked: z.ZodNumber;
@@ -5807,6 +5836,7 @@ export declare const crawlReportSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         "robots-disallowed": "robots-disallowed";
         "origin-backpressure": "origin-backpressure";
         "asset-url": "asset-url";
+        "cdn-utility-url": "cdn-utility-url";
         "configured-exclusion": "configured-exclusion";
         "duplicate-normalization": "duplicate-normalization";
         "memory-pressure": "memory-pressure";
@@ -6617,6 +6647,15 @@ export declare const crawlReportSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
       contentType: z.ZodOptional<z.ZodString>;
       servesHtml: z.ZodOptional<z.ZodBoolean>;
       error: z.ZodOptional<z.ZodString>;
+      errorKind: z.ZodOptional<z.ZodEnum<{
+        unknown: "unknown";
+        timeout: "timeout";
+        dns: "dns";
+        tls: "tls";
+        "redirect-limit": "redirect-limit";
+        aborted: "aborted";
+        "too-large": "too-large";
+      }>>;
       sitemapUrls: z.ZodArray<z.ZodString>;
       contentSignals: z.ZodOptional<z.ZodArray<z.ZodString>>;
       botAccess: z.ZodArray<z.ZodObject<{
@@ -6645,6 +6684,15 @@ export declare const crawlReportSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
       contentType: z.ZodOptional<z.ZodString>;
       servesHtml: z.ZodOptional<z.ZodBoolean>;
       error: z.ZodOptional<z.ZodString>;
+      errorKind: z.ZodOptional<z.ZodEnum<{
+        unknown: "unknown";
+        timeout: "timeout";
+        dns: "dns";
+        tls: "tls";
+        "redirect-limit": "redirect-limit";
+        aborted: "aborted";
+        "too-large": "too-large";
+      }>>;
       links: z.ZodOptional<z.ZodObject<{
         found: z.ZodNumber;
         checked: z.ZodNumber;
@@ -7124,6 +7172,7 @@ export declare const crawlReportSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         "robots-disallowed": "robots-disallowed";
         "origin-backpressure": "origin-backpressure";
         "asset-url": "asset-url";
+        "cdn-utility-url": "cdn-utility-url";
         "configured-exclusion": "configured-exclusion";
         "duplicate-normalization": "duplicate-normalization";
         "memory-pressure": "memory-pressure";
@@ -7934,6 +7983,15 @@ export declare const crawlReportSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
       contentType: z.ZodOptional<z.ZodString>;
       servesHtml: z.ZodOptional<z.ZodBoolean>;
       error: z.ZodOptional<z.ZodString>;
+      errorKind: z.ZodOptional<z.ZodEnum<{
+        unknown: "unknown";
+        timeout: "timeout";
+        dns: "dns";
+        tls: "tls";
+        "redirect-limit": "redirect-limit";
+        aborted: "aborted";
+        "too-large": "too-large";
+      }>>;
       sitemapUrls: z.ZodArray<z.ZodString>;
       contentSignals: z.ZodOptional<z.ZodArray<z.ZodString>>;
       botAccess: z.ZodArray<z.ZodObject<{
@@ -7962,6 +8020,15 @@ export declare const crawlReportSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
       contentType: z.ZodOptional<z.ZodString>;
       servesHtml: z.ZodOptional<z.ZodBoolean>;
       error: z.ZodOptional<z.ZodString>;
+      errorKind: z.ZodOptional<z.ZodEnum<{
+        unknown: "unknown";
+        timeout: "timeout";
+        dns: "dns";
+        tls: "tls";
+        "redirect-limit": "redirect-limit";
+        aborted: "aborted";
+        "too-large": "too-large";
+      }>>;
       links: z.ZodOptional<z.ZodObject<{
         found: z.ZodNumber;
         checked: z.ZodNumber;
@@ -8443,6 +8510,7 @@ export declare const crawlerSchemas: {
           "robots-disallowed": "robots-disallowed";
           "origin-backpressure": "origin-backpressure";
           "asset-url": "asset-url";
+          "cdn-utility-url": "cdn-utility-url";
           "configured-exclusion": "configured-exclusion";
           "duplicate-normalization": "duplicate-normalization";
           "memory-pressure": "memory-pressure";
@@ -9253,6 +9321,15 @@ export declare const crawlerSchemas: {
         contentType: z.ZodOptional<z.ZodString>;
         servesHtml: z.ZodOptional<z.ZodBoolean>;
         error: z.ZodOptional<z.ZodString>;
+        errorKind: z.ZodOptional<z.ZodEnum<{
+          unknown: "unknown";
+          timeout: "timeout";
+          dns: "dns";
+          tls: "tls";
+          "redirect-limit": "redirect-limit";
+          aborted: "aborted";
+          "too-large": "too-large";
+        }>>;
         sitemapUrls: z.ZodArray<z.ZodString>;
         contentSignals: z.ZodOptional<z.ZodArray<z.ZodString>>;
         botAccess: z.ZodArray<z.ZodObject<{
@@ -9281,6 +9358,15 @@ export declare const crawlerSchemas: {
         contentType: z.ZodOptional<z.ZodString>;
         servesHtml: z.ZodOptional<z.ZodBoolean>;
         error: z.ZodOptional<z.ZodString>;
+        errorKind: z.ZodOptional<z.ZodEnum<{
+          unknown: "unknown";
+          timeout: "timeout";
+          dns: "dns";
+          tls: "tls";
+          "redirect-limit": "redirect-limit";
+          aborted: "aborted";
+          "too-large": "too-large";
+        }>>;
         links: z.ZodOptional<z.ZodObject<{
           found: z.ZodNumber;
           checked: z.ZodNumber;
@@ -9760,6 +9846,7 @@ export declare const crawlerSchemas: {
           "robots-disallowed": "robots-disallowed";
           "origin-backpressure": "origin-backpressure";
           "asset-url": "asset-url";
+          "cdn-utility-url": "cdn-utility-url";
           "configured-exclusion": "configured-exclusion";
           "duplicate-normalization": "duplicate-normalization";
           "memory-pressure": "memory-pressure";
@@ -10570,6 +10657,15 @@ export declare const crawlerSchemas: {
         contentType: z.ZodOptional<z.ZodString>;
         servesHtml: z.ZodOptional<z.ZodBoolean>;
         error: z.ZodOptional<z.ZodString>;
+        errorKind: z.ZodOptional<z.ZodEnum<{
+          unknown: "unknown";
+          timeout: "timeout";
+          dns: "dns";
+          tls: "tls";
+          "redirect-limit": "redirect-limit";
+          aborted: "aborted";
+          "too-large": "too-large";
+        }>>;
         sitemapUrls: z.ZodArray<z.ZodString>;
         contentSignals: z.ZodOptional<z.ZodArray<z.ZodString>>;
         botAccess: z.ZodArray<z.ZodObject<{
@@ -10598,6 +10694,15 @@ export declare const crawlerSchemas: {
         contentType: z.ZodOptional<z.ZodString>;
         servesHtml: z.ZodOptional<z.ZodBoolean>;
         error: z.ZodOptional<z.ZodString>;
+        errorKind: z.ZodOptional<z.ZodEnum<{
+          unknown: "unknown";
+          timeout: "timeout";
+          dns: "dns";
+          tls: "tls";
+          "redirect-limit": "redirect-limit";
+          aborted: "aborted";
+          "too-large": "too-large";
+        }>>;
         links: z.ZodOptional<z.ZodObject<{
           found: z.ZodNumber;
           checked: z.ZodNumber;
@@ -11077,6 +11182,7 @@ export declare const crawlerSchemas: {
           "robots-disallowed": "robots-disallowed";
           "origin-backpressure": "origin-backpressure";
           "asset-url": "asset-url";
+          "cdn-utility-url": "cdn-utility-url";
           "configured-exclusion": "configured-exclusion";
           "duplicate-normalization": "duplicate-normalization";
           "memory-pressure": "memory-pressure";
@@ -11887,6 +11993,15 @@ export declare const crawlerSchemas: {
         contentType: z.ZodOptional<z.ZodString>;
         servesHtml: z.ZodOptional<z.ZodBoolean>;
         error: z.ZodOptional<z.ZodString>;
+        errorKind: z.ZodOptional<z.ZodEnum<{
+          unknown: "unknown";
+          timeout: "timeout";
+          dns: "dns";
+          tls: "tls";
+          "redirect-limit": "redirect-limit";
+          aborted: "aborted";
+          "too-large": "too-large";
+        }>>;
         sitemapUrls: z.ZodArray<z.ZodString>;
         contentSignals: z.ZodOptional<z.ZodArray<z.ZodString>>;
         botAccess: z.ZodArray<z.ZodObject<{
@@ -11915,6 +12030,15 @@ export declare const crawlerSchemas: {
         contentType: z.ZodOptional<z.ZodString>;
         servesHtml: z.ZodOptional<z.ZodBoolean>;
         error: z.ZodOptional<z.ZodString>;
+        errorKind: z.ZodOptional<z.ZodEnum<{
+          unknown: "unknown";
+          timeout: "timeout";
+          dns: "dns";
+          tls: "tls";
+          "redirect-limit": "redirect-limit";
+          aborted: "aborted";
+          "too-large": "too-large";
+        }>>;
         links: z.ZodOptional<z.ZodObject<{
           found: z.ZodNumber;
           checked: z.ZodNumber;
@@ -13323,6 +13447,7 @@ export declare const crawlerJsonSchemas: {
           "robots-disallowed": "robots-disallowed";
           "origin-backpressure": "origin-backpressure";
           "asset-url": "asset-url";
+          "cdn-utility-url": "cdn-utility-url";
           "configured-exclusion": "configured-exclusion";
           "duplicate-normalization": "duplicate-normalization";
           "memory-pressure": "memory-pressure";
@@ -14133,6 +14258,15 @@ export declare const crawlerJsonSchemas: {
         contentType: z.ZodOptional<z.ZodString>;
         servesHtml: z.ZodOptional<z.ZodBoolean>;
         error: z.ZodOptional<z.ZodString>;
+        errorKind: z.ZodOptional<z.ZodEnum<{
+          unknown: "unknown";
+          timeout: "timeout";
+          dns: "dns";
+          tls: "tls";
+          "redirect-limit": "redirect-limit";
+          aborted: "aborted";
+          "too-large": "too-large";
+        }>>;
         sitemapUrls: z.ZodArray<z.ZodString>;
         contentSignals: z.ZodOptional<z.ZodArray<z.ZodString>>;
         botAccess: z.ZodArray<z.ZodObject<{
@@ -14161,6 +14295,15 @@ export declare const crawlerJsonSchemas: {
         contentType: z.ZodOptional<z.ZodString>;
         servesHtml: z.ZodOptional<z.ZodBoolean>;
         error: z.ZodOptional<z.ZodString>;
+        errorKind: z.ZodOptional<z.ZodEnum<{
+          unknown: "unknown";
+          timeout: "timeout";
+          dns: "dns";
+          tls: "tls";
+          "redirect-limit": "redirect-limit";
+          aborted: "aborted";
+          "too-large": "too-large";
+        }>>;
         links: z.ZodOptional<z.ZodObject<{
           found: z.ZodNumber;
           checked: z.ZodNumber;
@@ -14640,6 +14783,7 @@ export declare const crawlerJsonSchemas: {
           "robots-disallowed": "robots-disallowed";
           "origin-backpressure": "origin-backpressure";
           "asset-url": "asset-url";
+          "cdn-utility-url": "cdn-utility-url";
           "configured-exclusion": "configured-exclusion";
           "duplicate-normalization": "duplicate-normalization";
           "memory-pressure": "memory-pressure";
@@ -15450,6 +15594,15 @@ export declare const crawlerJsonSchemas: {
         contentType: z.ZodOptional<z.ZodString>;
         servesHtml: z.ZodOptional<z.ZodBoolean>;
         error: z.ZodOptional<z.ZodString>;
+        errorKind: z.ZodOptional<z.ZodEnum<{
+          unknown: "unknown";
+          timeout: "timeout";
+          dns: "dns";
+          tls: "tls";
+          "redirect-limit": "redirect-limit";
+          aborted: "aborted";
+          "too-large": "too-large";
+        }>>;
         sitemapUrls: z.ZodArray<z.ZodString>;
         contentSignals: z.ZodOptional<z.ZodArray<z.ZodString>>;
         botAccess: z.ZodArray<z.ZodObject<{
@@ -15478,6 +15631,15 @@ export declare const crawlerJsonSchemas: {
         contentType: z.ZodOptional<z.ZodString>;
         servesHtml: z.ZodOptional<z.ZodBoolean>;
         error: z.ZodOptional<z.ZodString>;
+        errorKind: z.ZodOptional<z.ZodEnum<{
+          unknown: "unknown";
+          timeout: "timeout";
+          dns: "dns";
+          tls: "tls";
+          "redirect-limit": "redirect-limit";
+          aborted: "aborted";
+          "too-large": "too-large";
+        }>>;
         links: z.ZodOptional<z.ZodObject<{
           found: z.ZodNumber;
           checked: z.ZodNumber;
@@ -15957,6 +16119,7 @@ export declare const crawlerJsonSchemas: {
           "robots-disallowed": "robots-disallowed";
           "origin-backpressure": "origin-backpressure";
           "asset-url": "asset-url";
+          "cdn-utility-url": "cdn-utility-url";
           "configured-exclusion": "configured-exclusion";
           "duplicate-normalization": "duplicate-normalization";
           "memory-pressure": "memory-pressure";
@@ -16767,6 +16930,15 @@ export declare const crawlerJsonSchemas: {
         contentType: z.ZodOptional<z.ZodString>;
         servesHtml: z.ZodOptional<z.ZodBoolean>;
         error: z.ZodOptional<z.ZodString>;
+        errorKind: z.ZodOptional<z.ZodEnum<{
+          unknown: "unknown";
+          timeout: "timeout";
+          dns: "dns";
+          tls: "tls";
+          "redirect-limit": "redirect-limit";
+          aborted: "aborted";
+          "too-large": "too-large";
+        }>>;
         sitemapUrls: z.ZodArray<z.ZodString>;
         contentSignals: z.ZodOptional<z.ZodArray<z.ZodString>>;
         botAccess: z.ZodArray<z.ZodObject<{
@@ -16795,6 +16967,15 @@ export declare const crawlerJsonSchemas: {
         contentType: z.ZodOptional<z.ZodString>;
         servesHtml: z.ZodOptional<z.ZodBoolean>;
         error: z.ZodOptional<z.ZodString>;
+        errorKind: z.ZodOptional<z.ZodEnum<{
+          unknown: "unknown";
+          timeout: "timeout";
+          dns: "dns";
+          tls: "tls";
+          "redirect-limit": "redirect-limit";
+          aborted: "aborted";
+          "too-large": "too-large";
+        }>>;
         links: z.ZodOptional<z.ZodObject<{
           found: z.ZodNumber;
           checked: z.ZodNumber;
@@ -18209,9 +18390,9 @@ export declare const providerIdSchema: z.ZodString;
 export type ProviderId = z.infer<typeof providerIdSchema>;
 export type ExternalServiceId = string;
 export declare const providerCapabilitySchema: z.ZodEnum<{
+  "serp-snapshot": "serp-snapshot";
   "keyword-metrics": "keyword-metrics";
   "keyword-discovery": "keyword-discovery";
-  "serp-snapshot": "serp-snapshot";
   "domain-overview": "domain-overview";
   "ranked-keywords": "ranked-keywords";
   "relevant-pages": "relevant-pages";
@@ -18373,11 +18554,110 @@ type ResolvedCrawlSiteDependencies = {
   fetchLandingPageValues: typeof fetchLandingPageValues;
   landingValueForUrl: typeof landingValueForUrl;
   now: () => Date;
+  /** Waits out a rate-limit cool-down. Tests inject a zero delay. */
+  sleep: (ms: number, signal?: AbortSignal) => Promise<void>;
   memoryUsage: () => Pick<NodeJS.MemoryUsage, 'rss' | 'heapUsed' | 'external'>;
   totalMemory: () => number;
 };
 type CrawlSiteDependencies = Partial<ResolvedCrawlSiteDependencies>;
 export declare function crawlSite(input: CrawlConfigInput, dependencies?: CrawlSiteDependencies): Promise<CrawlReport>;
+export declare const SITE_FACTS_MAX_SITES = 1000;
+export declare const SITE_FACTS_DEFAULT_CONCURRENCY = 8;
+export declare const SITE_FACTS_MAX_CONCURRENCY = 16;
+export declare const SITE_FACTS_TIMEOUT_MS = 5000;
+export type SiteHomepageFacts = {
+  url: string;
+  outcome: 'response' | 'failed' | 'skipped';
+  skipReason?: 'robots-disallowed' | 'robots-unknown';
+  availability?: CrawlAiAvailability;
+  status?: number;
+  finalUrl?: string;
+  redirects?: NonNullable<PageFetchResult['diagnostics']['redirectChain']>;
+  contentType?: string;
+  accessBlock?: {
+    provider: string;
+    kind: string;
+  };
+  responseTimeMs?: number;
+  sizeBytes?: number;
+  title?: string;
+  metaDescription?: string;
+  h1?: string;
+  lang?: string;
+  canonical?: string;
+  metaRobots?: string;
+  xRobotsTag?: string;
+  indexable?: boolean;
+  indexability?: string;
+  markdownAlternates?: string[];
+  contentSignal?: string;
+  linkRelations?: string[];
+  error?: string;
+  errorKind?: CrawlFetchErrorKind;
+};
+export type SiteRobotsFacts = Omit<NonNullable<CrawlAiSignals['robotsTxt']>, 'sitemapUrls'> & {
+  sitemapUrls: string[];
+  sitemapCount: number;
+  homepageAllowed: boolean | null;
+};
+export type SiteLlmsFacts = NonNullable<CrawlAiSignals['llmsTxt']> & {
+  sizeBytes?: number;
+  startsWithH1?: boolean;
+  h1?: string;
+  sameSiteLinks?: number;
+};
+export type SiteFactsRow = {
+  type: 'site';
+  input: string;
+  origin?: string;
+  error?: string;
+  checkedAt?: string;
+  robotsTxt?: SiteRobotsFacts;
+  homepage?: SiteHomepageFacts;
+  llmsTxt?: SiteLlmsFacts;
+};
+type AvailabilityCounts = Record<CrawlAiAvailability, number> & {
+  failed: number;
+};
+export type SiteFactsSummary = {
+  type: 'summary';
+  status: 'complete' | 'cancelled';
+  sites: number;
+  checked: number;
+  invalid: number;
+  duplicatesRemoved: number;
+  maxSites: number;
+  concurrency: number;
+  timeoutMs: number;
+  durationMs: number;
+  robotsTxt: AvailabilityCounts;
+  homepage: AvailabilityCounts & {
+    skipped: number;
+  };
+  llmsTxt: AvailabilityCounts & {
+    startsWithH1: number;
+  };
+  botAccess: Array<{
+    userAgent: string;
+    purpose: CrawlAiBotAccess['purpose'];
+    allowed: number;
+    blocked: number;
+    unknown: number;
+  }>;
+};
+type Fetch = typeof publicHttpFetch;
+export type SiteFactsInput = {
+  sites: string[];
+  concurrency?: number;
+  respectRobots?: boolean;
+  signal?: AbortSignal;
+  onRow: (row: SiteFactsRow) => Promise<void> | void;
+};
+export type SiteFactsDependencies = {
+  fetch?: Fetch;
+  now?: () => Date;
+};
+export declare function checkSites(input: SiteFactsInput, dependencies?: SiteFactsDependencies): Promise<SiteFactsSummary>;
 type QueryFlag = 'likely-automated' | 'navigational-other';
 declare const QUERY_FLAG_METHOD: {
   readonly id: "query_flags_v1";
@@ -20592,6 +20872,7 @@ export type IndexCoverageReportDependencies = {
   now: () => Date;
 };
 export declare function indexCoverageSignals(input: IndexCoverageReportInput, dependencies?: IndexCoverageReportDependencies): Promise<IndexCoverageReport>;
+type RedirectOutcome = 'done' | 'loop' | 'too_many' | 'timeout' | 'error';
 export type RedirectTraceStep = {
   url: string;
   status: number;
@@ -20606,7 +20887,9 @@ export type RedirectTraceReport = {
   generatedAt: string;
   summary: {
     hops: number;
-    finalStatus: number;
+    finalStatus: number | null;
+    outcome: RedirectOutcome;
+    error?: string;
     finalIndexable?: boolean;
     issues: RedirectTraceIssue[];
   };
@@ -21521,6 +21804,7 @@ type PageFacts = {
   h1: string | null;
   canonical: string | null;
   robots: string | null;
+  google_noindex: boolean | null;
   www_authenticate?: string;
   error?: string;
 };
@@ -21541,7 +21825,7 @@ type CommandDeps = {
   searchAnalytics: SearchAnalyticsQuery;
   checkPages: (urls: string[]) => Promise<PageFacts[]>;
   liveCheck: (url: string) => Promise<LiveCheck>;
-  inspect: (site: string, url: string) => Promise<IndexStatus>;
+  inspect: (site: string, url: string, signal?: AbortSignal) => Promise<IndexStatus>;
   inspectionQuota?: (site: string) => Promise<{
     used: number;
     limit: number;
@@ -21553,7 +21837,7 @@ type CommandDeps = {
     }>;
     save: (site: string, url: string, status: IndexStatus) => void;
   };
-  pageMarkdown?: (url: string) => Promise<PageMarkdown>;
+  pageMarkdown?: (url: string, limit?: number) => Promise<PageMarkdown>;
   call: Caller;
   bing?: () => Promise<BingCall | null>;
   bingConnect?: string;
@@ -21562,6 +21846,7 @@ type CommandDeps = {
   week?: () => Promise<WeekData | null>;
   startAudit?: (site: string) => Promise<StartAudit>;
   issues?: IssueStore;
+  progress?: ProgressReporter;
   now?: () => Date;
 };
 type StartAudit = {
@@ -21744,10 +22029,16 @@ export declare function openCloudLink(url: string): Promise<void>;
 type LintSource = {
   path: string;
   text: string;
+  note?: string;
+  partial?: string;
 } | {
   path: string;
   skipped: string;
 };
+type ResearchStore = {
+  get(key: string): Promise<string | null>;
+  put(key: string, value: string, ttlSeconds: number): Promise<void>;
+};
 export type TokenStorageMode = 'keychain' | 'file';
 export type TokenStorageStatus = {
   configured: TokenStorageMode;
@@ -21858,6 +22149,7 @@ export declare function nodeCommandDeps(options: {
   account?: string;
   refresh?: boolean;
 }): CommandDeps;
+export declare function localResearchStore(refresh?: boolean): ResearchStore;
 export declare const LOCAL_BING_CONNECT = "Connect Bing on your seoskill.dev account and run `seo login`, or run `seo providers bing connect` with an API key from Bing Webmaster Tools (Settings, API access).";
 export declare function localBing(): Promise<BingCall | null>;
 export declare function localAccounts(): Promise<GoogleAccount[]>;
@@ -22624,5 +22916,5 @@ export declare function parseOlderThan(input?: string): number | undefined;
 export declare function formatRelativeExpiry(expiresAt: number): string;
 export declare function isoDate(daysAgo?: number): string;
 export declare const SEO_VERSION: string;
-export { type AiReferralDataSource, type AiReferralMetrics, type AiReferralQueryEvidence, type AiReferralReport, type AiReferralSourceDefinition, type AnalyzeCannibalImportRowsInput, type AnalyzeCannibalRowsInput, type AnalyzeDecayInput, type AnalyzeQuickWinsInput, type AnalyzeSecondPageInput, type AnalyzeStrikingDistanceInput, type CannibalAnalysis, type CannibalImportAnalysis, type CannibalImportItem, type CannibalImportPage, type CannibalImportReport, type CannibalImportSelection, type CannibalItem, type CannibalPage, type CannibalReport, type CannibalSelection, type CannibalSuppression, type CannibalSuppressionReason, type CrawlAiAvailability, type CrawlAiBotAccess, type CrawlAiLinkCheck, type CrawlAiResourceSignal, type CrawlAiSignals, type CrawlSiteChecks, type CrawlSiteDependencies, type CrawlStatusPhase, type CtrUnderperformer, type CtrUnderperformerSelection, type DataForSeoAccountSnapshot, type DataForSeoClientOptions, type DecayAnalysis, type DecayComparison, type DecayDiagnosis, type DecayGroup, type DecayItem, type DecayMetrics, type DecayReport, type DecaySelection, type DecaySignal, type FetchPageOptions, type FetchRateControls, type Ga4AccountSummary, type Ga4PropertySummary, type GoogleAccessTokenClient, type InternalLinkSuggestion, type InternalLinksPage, type InternalLinksReport, type JavaScriptRenderingInput, type JavaScriptRenderingMode, type OAuthClientConfig, type PageOpportunityAnalysis, type PageOpportunityAnalysisInput, type PageOpportunityBenchmark, type PageOpportunityItem, type PageOpportunitySelection, type PageOpportunityType, type PageOpportunityVerification, type PageRenderer, type QueryClusterPage, type QueryClusterRow, type QuickWinAnalysis, type QuickWinGroup, type QuickWinItem, type QuickWinSelection, type QuickWinTemplateRecommendation, SEO_PROVIDER_API_VERSION, type SearchStatusIncident, type SearchUpdate, type SecondPageAnalysis, type SecondPageItem, type SecondPageQuery, type SecondPageRecommendation, type SecondPageReport, type SecondPageSelection, type SegmentDimension, type SegmentImpactItem, type SegmentImpactReport, type SegmentImpactSelection, type SegmentPeriodEvidence, type SegmentRange, SeoAnalyticsConnection, SeoAnalyticsLandingPageResult, SeoLandingPageVisitRow, SeoLandingPageVisitsCapability, SeoLandingPageVisitsResult, SeoProviderActionAdapter, SeoProviderActivate, SeoProviderApiVersion, SeoProviderCapabilityAdapter, SeoProviderCapabilityId, SeoProviderConnection, SeoProviderConnectionAdapter, SeoProviderConnectionField, SeoProviderHost, SeoProviderJson, SeoProviderJsonSchema, SeoProviderKind, SeoProviderRegistration, SeoProviderRequest, SeoProviderRuntime, SeoSearchMarket, SeoSerpLocalPackResult, SeoSerpOrganicResult, SeoSerpSnapshotCapability, SeoSerpSnapshotResult, type StrikingDistanceAnalysis, type StrikingDistanceAnalysisGroup, type StrikingDistanceAnalysisItem, type TelemetryErrorCategory, type TelemetryFailureClassification, type TelemetryFailureContext, type TelemetryFailureReason, type TelemetryOperation, type UnmatchedSegment, pageTechnicalSignals as technicalPageSignals };
+export { type AiReferralDataSource, type AiReferralMetrics, type AiReferralQueryEvidence, type AiReferralReport, type AiReferralSourceDefinition, type AnalyzeCannibalImportRowsInput, type AnalyzeCannibalRowsInput, type AnalyzeDecayInput, type AnalyzeQuickWinsInput, type AnalyzeSecondPageInput, type AnalyzeStrikingDistanceInput, type CannibalAnalysis, type CannibalImportAnalysis, type CannibalImportItem, type CannibalImportPage, type CannibalImportReport, type CannibalImportSelection, type CannibalItem, type CannibalPage, type CannibalReport, type CannibalSelection, type CannibalSuppression, type CannibalSuppressionReason, type CrawlAiAvailability, type CrawlAiBotAccess, type CrawlAiLinkCheck, type CrawlAiResourceSignal, type CrawlAiSignals, type CrawlFetchErrorKind, type CrawlSiteChecks, type CrawlSiteDependencies, type CrawlStatusPhase, type CtrUnderperformer, type CtrUnderperformerSelection, type DataForSeoAccountSnapshot, type DataForSeoClientOptions, type DecayAnalysis, type DecayComparison, type DecayDiagnosis, type DecayGroup, type DecayItem, type DecayMetrics, type DecayReport, type DecaySelection, type DecaySignal, type FetchPageOptions, type FetchRateControls, type Ga4AccountSummary, type Ga4PropertySummary, type GoogleAccessTokenClient, type InternalLinkSuggestion, type InternalLinksPage, type InternalLinksReport, type JavaScriptRenderingInput, type JavaScriptRenderingMode, type OAuthClientConfig, type PageOpportunityAnalysis, type PageOpportunityAnalysisInput, type PageOpportunityBenchmark, type PageOpportunityItem, type PageOpportunitySelection, type PageOpportunityType, type PageOpportunityVerification, type PageRenderer, type QueryClusterPage, type QueryClusterRow, type QuickWinAnalysis, type QuickWinGroup, type QuickWinItem, type QuickWinSelection, type QuickWinTemplateRecommendation, SEO_PROVIDER_API_VERSION, type SearchStatusIncident, type SearchUpdate, type SecondPageAnalysis, type SecondPageItem, type SecondPageQuery, type SecondPageRecommendation, type SecondPageReport, type SecondPageSelection, type SegmentDimension, type SegmentImpactItem, type SegmentImpactReport, type SegmentImpactSelection, type SegmentPeriodEvidence, type SegmentRange, SeoAnalyticsConnection, SeoAnalyticsLandingPageResult, SeoLandingPageVisitRow, SeoLandingPageVisitsCapability, SeoLandingPageVisitsResult, SeoProviderActionAdapter, SeoProviderActivate, SeoProviderApiVersion, SeoProviderCapabilityAdapter, SeoProviderCapabilityId, SeoProviderConnection, SeoProviderConnectionAdapter, SeoProviderConnectionField, SeoProviderHost, SeoProviderJson, SeoProviderJsonSchema, SeoProviderKind, SeoProviderRegistration, SeoProviderRequest, SeoProviderRuntime, SeoSearchMarket, SeoSerpLocalPackResult, SeoSerpOrganicResult, SeoSerpSnapshotCapability, SeoSerpSnapshotResult, type StrikingDistanceAnalysis, type StrikingDistanceAnalysisGroup, type StrikingDistanceAnalysisItem, type TelemetryErrorCategory, type TelemetryFailureClassification, type TelemetryFailureContext, type TelemetryFailureReason, type TelemetryOperation, type UnmatchedSegment, pageTechnicalSignals as technicalPageSignals };
 //# sourceMappingURL=index.d.ts.map