seo 0.17.1 → 0.17.2

package/dist/index.d.ts

@@ -773,13 +773,13 @@ declare const RULE_DEFINITIONS: readonly [{
   readonly title: "Large HTML response";
   readonly category: "performance";
   readonly defaultSeverity: "low";
-  readonly whyItMatters: "Large HTML takes longer to download and parse before the browser can even start the rest of the page.";
-  readonly howToFix: "Trim duplicated markup, remove heavy inline data, split non-critical content, and move large scripts or styles out of the HTML response.";
-  readonly impactIfIgnored: "Pages can feel slow on mobile connections and crawlers spend more time processing each URL.";
-  readonly howToVerify: "Re-run the crawl and confirm sizeBytes is below the large HTML threshold for normal pages.";
+  readonly whyItMatters: "Googlebot reads only the first 2MB of uncompressed HTML for Google Search and indexes the page as if the file ended there. When the h1 or main element, or most of the visible text, sits past that cut, Google may index the page without its main content. Large HTML is also slow to download and parse.";
+  readonly howToFix: "Move the main content earlier and trim what comes before it: large inline CSS, inline SVG, JSON data and duplicated markup. Load non-critical styles and scripts as separate files.";
+  readonly impactIfIgnored: "Content past the 2MB cut is not indexed, and every page of the template carries the same weight on slow connections.";
+  readonly howToVerify: "Re-run the crawl and confirm sizeBytes is under 2,097,152, or that mainContentStartBytes is well before it and few visible words sit after it. The word split is a heuristic from the raw HTML.";
   readonly agentHints: {
-    readonly evidenceFields: ["page.sizeBytes", "issue.evidence.thresholdBytes"];
-    readonly suggestedCommands: ["seo crawl <url> --json"];
+    readonly evidenceFields: ["page.sizeBytes", "issue.evidence.thresholdBytes", "issue.evidence.mainContentStartBytes", "issue.evidence.bytesAfterLimit", "issue.evidence.visibleWordsAfterLimit", "issue.evidence.indexingRisk"];
+    readonly suggestedCommands: ["seo crawl <url> --mode page --json"];
   };
 }, {
   readonly id: "no_compression";
@@ -2548,233 +2548,6 @@ export declare function contentOptimizationReport(input: {
   refresh?: boolean;
   js?: boolean | 'auto';
 }): Promise<ContentOptimizationReport>;
-export type CrawlPageSnapshot = {
-  url: string;
-  finalUrl: string;
-  status: number;
-  contentType?: string;
-  responseHeaders?: Record<string, string>;
-  responseTimeMs?: number;
-  sizeBytes?: number;
-  usedJs?: boolean;
-  fetchSource?: 'cache' | 'network' | 'rendered';
-  cacheState?: 'hit' | 'miss' | 'bypass';
-  fetchDiagnostics?: PageFetchDiagnostics;
-  auditScope?: 'full' | 'status';
-  accessBlock?: AccessBlockEvidence;
-  blocked?: boolean;
-  contentAuditAllowed?: boolean;
-  crawlDepth?: number;
-  error?: string;
-  robotsTxt?: {
-    url: string;
-    allowed: boolean | null;
-    availability: 'available' | 'absent' | 'access-blocked' | 'rate-limited' | 'unreachable' | 'unreadable';
-    status?: number;
-    error?: string;
-    matchedLine?: string;
-  };
-  title?: string;
-  metaDescription?: string;
-  canonical?: string;
-  canonicalRaw?: string;
-  canonicalStatus?: CanonicalEvidence['status'];
-  canonicalCandidates?: CanonicalCandidate[];
-  metaRobots?: string;
-  xRobotsTag?: string;
-  h1?: string;
-  h1Count?: number;
-  h2Count?: number;
-  h3Count?: number;
-  indexable: boolean;
-  indexability?: string;
-  declaredIndexability?: 'indexable-candidate' | 'noindex' | 'robots-blocked' | 'canonical-conflict' | 'canonical-hint-other' | 'meta-refresh' | 'not-html' | 'unknown';
-  extractionStatus?: 'complete' | 'failed' | 'not-applicable' | 'unknown-media-type';
-  extractionError?: string;
-  wordCount: number;
-  contentExtraction?: ContentExtractionDiagnostics;
-  warnings?: string[];
-  contentHash: string;
-  mainContentHash?: string;
-  textRatio?: number;
-  contentSample?: string;
-  contentSketch?: ContentSketch;
-  softAuthenticationGate?: {
-    kind: 'login-form';
-    indicators: string[];
-    formActionPath?: string;
-  };
-  metaRefresh?: {
-    targetUrl: string;
-    delaySeconds: number;
-  };
-  tabbedContent?: {
-    groups: number;
-    panels: number;
-    retainedPanels: number;
-    truncated: boolean;
-    panelSketches: Array<{
-      label?: string;
-      sketch: ContentSketch;
-    }>;
-  };
-  lang?: string;
-  hasViewport?: boolean;
-  isHttps?: boolean;
-  hasHsts?: boolean;
-  compression?: string;
-  hreflang?: Array<{
-    hreflang: string;
-    href: string;
-  }>;
-  mixedContentCount?: number;
-  mixedContentSamples?: string[];
-  imagesTotal?: number;
-  imagesMissingAlt?: number;
-  oversizedImageCandidates?: Array<{
-    src: string;
-    width?: number;
-    height?: number;
-    detectedFrom: string;
-  }>;
-  outgoingInternalCount: number;
-  outgoingExternalCount?: number;
-  internalInlinkCount?: number;
-  internalLinkAuthorityScore?: number;
-  sampleInternalLinks?: string[];
-  sampleExternalLinks?: string[];
-  internalAnchorSamples?: Array<{
-    href: string;
-    text: string;
-  }>;
-  externalAnchorSamples?: Array<{
-    href: string;
-    text: string;
-  }>;
-  markdownAlternates?: string[];
-  describedBy?: string[];
-  externalLinkChecks?: ExternalLinkCheck[];
-  schemaTypes?: string[];
-  structuredDataFormats?: Array<'json-ld' | 'microdata' | 'rdfa'>;
-  googleRichResults?: GoogleRichResultAssessment[];
-  googleRichResultsSelection?: GoogleRichResultAssessmentSelection;
-  schemaSameAs?: string[];
-  schemaSameAsEvidence?: Array<{
-    url: string;
-    block: number;
-    path: string;
-    subjectId?: string;
-    subjectTypes: string[];
-  }>;
-  invalidSchemaSameAs?: Array<{
-    block: number;
-    path: string;
-    value: string;
-  }>;
-  socialProfileLinks?: string[];
-  invalidJsonLdCount?: number;
-  invalidJsonLdSamples?: Array<{
-    snippet: string;
-    error: string;
-  }>;
-  unrecognizedJsonLdTypes?: Array<{
-    block: number;
-    path: string;
-    value: string;
-    reason: 'missing-schema-context' | 'unresolved-context' | 'unsupported-vocabulary';
-  }>;
-  openGraphTitle?: string;
-  openGraphDescription?: string;
-  openGraphImage?: string;
-  twitterCard?: string;
-  author?: string;
-  hasDate?: boolean;
-  geo?: {
-    semanticHtml: boolean;
-    structuredData: boolean;
-    hasAuthor: boolean;
-    hasDate: boolean;
-    questionHeadings: number;
-    listCount?: number;
-    tableCount?: number;
-    structuredBlocks: number;
-    answerable: boolean;
-    hasFaqSchema?: boolean;
-    hasQapageSchema?: boolean;
-    hasLlmsTxt?: boolean;
-    llmsTxtUrl?: string;
-    llmsTxtStatus?: number;
-  };
-  searchMetrics?: {
-    clicks: number;
-    impressions: number;
-    ctr: number;
-    position: number;
-  };
-  topQuery?: {
-    query: string;
-    clicks: number;
-    impressions: number;
-    ctr: number;
-    position: number;
-  };
-  analytics?: {
-    sessions: number;
-    totalUsers?: number;
-    conversions?: number;
-  };
-};
-export type ExternalLinkCheckState = 'available' | 'confirmed-broken' | 'transient' | 'provider-blocked' | 'rate-limited' | 'method-rejected' | 'unavailable';
-export type ExternalLinkCheckAttempt = {
-  method: 'HEAD' | 'GET';
-  status?: number;
-  error?: string;
-};
-export type ExternalLinkCheck = {
-  url: string;
-  status?: number;
-  error?: string;
-  state?: ExternalLinkCheckState;
-  attempts?: ExternalLinkCheckAttempt[];
-};
-export type CrawlResponseObservation = {
-  requestedUrl: string;
-  outcome: 'response';
-  finalUrl: string;
-  status: number;
-  contentType?: string;
-  durationMs?: number;
-  redirectChain?: PageFetchDiagnostics['redirectChain'];
-  accessBlock?: AccessBlockEvidence;
-  robotsTxt?: NonNullable<CrawlPageSnapshot['robotsTxt']>;
-} & ({
-  extraction: 'complete' | 'not-applicable' | 'unknown-media-type';
-} | {
-  extraction: 'failed';
-  extractionError: string;
-});
-export type CrawlRequestObservation = CrawlResponseObservation | {
-  requestedUrl: string;
-  outcome: 'skipped';
-  durationMs?: number;
-  reason: 'robots-disallowed' | 'robots-deferred';
-  robotsTxt: NonNullable<CrawlPageSnapshot['robotsTxt']>;
-  extraction: 'not-applicable';
-} | {
-  requestedUrl: string;
-  outcome: 'skipped';
-  durationMs?: number;
-  reason: 'origin-backpressure';
-  error: string;
-  extraction: 'not-applicable';
-} | {
-  requestedUrl: string;
-  outcome: 'failure';
-  durationMs?: number;
-  failureKind: 'dns' | 'tls' | 'timeout' | 'redirect-limit' | 'redirect-loop' | 'aborted' | 'unknown';
-  error: string;
-  extraction: 'not-applicable';
-};
 export type SitemapInvalidLoc = {
   sitemapUrl: string;
   kind: 'url' | 'sitemap';
@@ -3260,6 +3033,246 @@ export declare function createCrawlReport(input: {
   generatedAt?: string;
 }): CrawlReport;
 export declare function normalizeLoadedCrawlReport(report: CrawlReport): CrawlReport;
+type GooglebotCutEvidence = {
+  limitBytes: number;
+  bytesAfterLimit: number;
+  /** Byte offset of the first <h1> or <main>, whichever comes first. */
+  mainContentStartBytes?: number;
+  mainContentMarker?: 'h1' | 'main';
+  mainContentStart: 'before-limit' | 'near-limit' | 'after-limit' | 'not-found';
+  /** Heuristic: words of text outside tags, scripts and styles. */
+  visibleWordsBeforeLimit: number;
+  visibleWordsAfterLimit: number;
+};
+export type CrawlPageSnapshot = {
+  url: string;
+  finalUrl: string;
+  status: number;
+  contentType?: string;
+  responseHeaders?: Record<string, string>;
+  responseTimeMs?: number;
+  sizeBytes?: number;
+  /** Set only when the HTML is over Googlebot's 2MB limit. */
+  googlebotCut?: GooglebotCutEvidence;
+  usedJs?: boolean;
+  fetchSource?: 'cache' | 'network' | 'rendered';
+  cacheState?: 'hit' | 'miss' | 'bypass';
+  fetchDiagnostics?: PageFetchDiagnostics;
+  auditScope?: 'full' | 'status';
+  accessBlock?: AccessBlockEvidence;
+  blocked?: boolean;
+  contentAuditAllowed?: boolean;
+  crawlDepth?: number;
+  error?: string;
+  robotsTxt?: {
+    url: string;
+    allowed: boolean | null;
+    availability: 'available' | 'absent' | 'access-blocked' | 'rate-limited' | 'unreachable' | 'unreadable';
+    status?: number;
+    error?: string;
+    matchedLine?: string;
+  };
+  title?: string;
+  metaDescription?: string;
+  canonical?: string;
+  canonicalRaw?: string;
+  canonicalStatus?: CanonicalEvidence['status'];
+  canonicalCandidates?: CanonicalCandidate[];
+  metaRobots?: string;
+  xRobotsTag?: string;
+  h1?: string;
+  h1Count?: number;
+  h2Count?: number;
+  h3Count?: number;
+  indexable: boolean;
+  indexability?: string;
+  declaredIndexability?: 'indexable-candidate' | 'noindex' | 'robots-blocked' | 'canonical-conflict' | 'canonical-hint-other' | 'meta-refresh' | 'not-html' | 'unknown';
+  extractionStatus?: 'complete' | 'failed' | 'not-applicable' | 'unknown-media-type';
+  extractionError?: string;
+  wordCount: number;
+  contentExtraction?: ContentExtractionDiagnostics;
+  warnings?: string[];
+  contentHash: string;
+  mainContentHash?: string;
+  textRatio?: number;
+  contentSample?: string;
+  contentSketch?: ContentSketch;
+  softAuthenticationGate?: {
+    kind: 'login-form';
+    indicators: string[];
+    formActionPath?: string;
+  };
+  metaRefresh?: {
+    targetUrl: string;
+    delaySeconds: number;
+  };
+  tabbedContent?: {
+    groups: number;
+    panels: number;
+    retainedPanels: number;
+    truncated: boolean;
+    panelSketches: Array<{
+      label?: string;
+      sketch: ContentSketch;
+    }>;
+  };
+  lang?: string;
+  hasViewport?: boolean;
+  isHttps?: boolean;
+  hasHsts?: boolean;
+  compression?: string;
+  hreflang?: Array<{
+    hreflang: string;
+    href: string;
+  }>;
+  mixedContentCount?: number;
+  mixedContentSamples?: string[];
+  imagesTotal?: number;
+  imagesMissingAlt?: number;
+  oversizedImageCandidates?: Array<{
+    src: string;
+    width?: number;
+    height?: number;
+    detectedFrom: string;
+  }>;
+  outgoingInternalCount: number;
+  outgoingExternalCount?: number;
+  internalInlinkCount?: number;
+  internalLinkAuthorityScore?: number;
+  sampleInternalLinks?: string[];
+  sampleExternalLinks?: string[];
+  internalAnchorSamples?: Array<{
+    href: string;
+    text: string;
+  }>;
+  externalAnchorSamples?: Array<{
+    href: string;
+    text: string;
+  }>;
+  markdownAlternates?: string[];
+  describedBy?: string[];
+  externalLinkChecks?: ExternalLinkCheck[];
+  schemaTypes?: string[];
+  structuredDataFormats?: Array<'json-ld' | 'microdata' | 'rdfa'>;
+  googleRichResults?: GoogleRichResultAssessment[];
+  googleRichResultsSelection?: GoogleRichResultAssessmentSelection;
+  schemaSameAs?: string[];
+  schemaSameAsEvidence?: Array<{
+    url: string;
+    block: number;
+    path: string;
+    subjectId?: string;
+    subjectTypes: string[];
+  }>;
+  invalidSchemaSameAs?: Array<{
+    block: number;
+    path: string;
+    value: string;
+  }>;
+  socialProfileLinks?: string[];
+  invalidJsonLdCount?: number;
+  invalidJsonLdSamples?: Array<{
+    snippet: string;
+    error: string;
+  }>;
+  unrecognizedJsonLdTypes?: Array<{
+    block: number;
+    path: string;
+    value: string;
+    reason: 'missing-schema-context' | 'unresolved-context' | 'unsupported-vocabulary';
+  }>;
+  openGraphTitle?: string;
+  openGraphDescription?: string;
+  openGraphImage?: string;
+  twitterCard?: string;
+  author?: string;
+  hasDate?: boolean;
+  geo?: {
+    semanticHtml: boolean;
+    structuredData: boolean;
+    hasAuthor: boolean;
+    hasDate: boolean;
+    questionHeadings: number;
+    listCount?: number;
+    tableCount?: number;
+    structuredBlocks: number;
+    answerable: boolean;
+    hasFaqSchema?: boolean;
+    hasQapageSchema?: boolean;
+    hasLlmsTxt?: boolean;
+    llmsTxtUrl?: string;
+    llmsTxtStatus?: number;
+  };
+  searchMetrics?: {
+    clicks: number;
+    impressions: number;
+    ctr: number;
+    position: number;
+  };
+  topQuery?: {
+    query: string;
+    clicks: number;
+    impressions: number;
+    ctr: number;
+    position: number;
+  };
+  analytics?: {
+    sessions: number;
+    totalUsers?: number;
+    conversions?: number;
+  };
+};
+export type ExternalLinkCheckState = 'available' | 'confirmed-broken' | 'transient' | 'provider-blocked' | 'rate-limited' | 'method-rejected' | 'unavailable';
+export type ExternalLinkCheckAttempt = {
+  method: 'HEAD' | 'GET';
+  status?: number;
+  error?: string;
+};
+export type ExternalLinkCheck = {
+  url: string;
+  status?: number;
+  error?: string;
+  state?: ExternalLinkCheckState;
+  attempts?: ExternalLinkCheckAttempt[];
+};
+export type CrawlResponseObservation = {
+  requestedUrl: string;
+  outcome: 'response';
+  finalUrl: string;
+  status: number;
+  contentType?: string;
+  durationMs?: number;
+  redirectChain?: PageFetchDiagnostics['redirectChain'];
+  accessBlock?: AccessBlockEvidence;
+  robotsTxt?: NonNullable<CrawlPageSnapshot['robotsTxt']>;
+} & ({
+  extraction: 'complete' | 'not-applicable' | 'unknown-media-type';
+} | {
+  extraction: 'failed';
+  extractionError: string;
+});
+export type CrawlRequestObservation = CrawlResponseObservation | {
+  requestedUrl: string;
+  outcome: 'skipped';
+  durationMs?: number;
+  reason: 'robots-disallowed' | 'robots-deferred';
+  robotsTxt: NonNullable<CrawlPageSnapshot['robotsTxt']>;
+  extraction: 'not-applicable';
+} | {
+  requestedUrl: string;
+  outcome: 'skipped';
+  durationMs?: number;
+  reason: 'origin-backpressure';
+  error: string;
+  extraction: 'not-applicable';
+} | {
+  requestedUrl: string;
+  outcome: 'failure';
+  durationMs?: number;
+  failureKind: 'dns' | 'tls' | 'timeout' | 'redirect-limit' | 'redirect-loop' | 'aborted' | 'unknown';
+  error: string;
+  extraction: 'not-applicable';
+};
 export declare function auditCrawlRequests(requests: CrawlRequestObservation[]): CrawlIssue[];
 export declare function auditCrawlPages(pages: CrawlPageSnapshot[], opts?: {
   startUrl?: string;
@@ -3383,6 +3396,23 @@ export declare const crawlPageSnapshotSchema: z.ZodObject<{
   responseHeaders: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
   responseTimeMs: z.ZodOptional<z.ZodNumber>;
   sizeBytes: z.ZodOptional<z.ZodNumber>;
+  googlebotCut: z.ZodOptional<z.ZodObject<{
+    limitBytes: z.ZodNumber;
+    bytesAfterLimit: z.ZodNumber;
+    mainContentStartBytes: z.ZodOptional<z.ZodNumber>;
+    mainContentMarker: z.ZodOptional<z.ZodEnum<{
+      h1: "h1";
+      main: "main";
+    }>>;
+    mainContentStart: z.ZodEnum<{
+      "before-limit": "before-limit";
+      "near-limit": "near-limit";
+      "after-limit": "after-limit";
+      "not-found": "not-found";
+    }>;
+    visibleWordsBeforeLimit: z.ZodNumber;
+    visibleWordsAfterLimit: z.ZodNumber;
+  }, z.core.$strip>>;
   usedJs: z.ZodOptional<z.ZodBoolean>;
   fetchSource: z.ZodOptional<z.ZodEnum<{
     cache: "cache";
@@ -4577,6 +4607,23 @@ export declare const crawlReportSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     responseHeaders: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
     responseTimeMs: z.ZodOptional<z.ZodNumber>;
     sizeBytes: z.ZodOptional<z.ZodNumber>;
+    googlebotCut: z.ZodOptional<z.ZodObject<{
+      limitBytes: z.ZodNumber;
+      bytesAfterLimit: z.ZodNumber;
+      mainContentStartBytes: z.ZodOptional<z.ZodNumber>;
+      mainContentMarker: z.ZodOptional<z.ZodEnum<{
+        h1: "h1";
+        main: "main";
+      }>>;
+      mainContentStart: z.ZodEnum<{
+        "before-limit": "before-limit";
+        "near-limit": "near-limit";
+        "after-limit": "after-limit";
+        "not-found": "not-found";
+      }>;
+      visibleWordsBeforeLimit: z.ZodNumber;
+      visibleWordsAfterLimit: z.ZodNumber;
+    }, z.core.$strip>>;
     usedJs: z.ZodOptional<z.ZodBoolean>;
     fetchSource: z.ZodOptional<z.ZodEnum<{
       cache: "cache";
@@ -5924,6 +5971,23 @@ export declare const crawlReportSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     responseHeaders: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
     responseTimeMs: z.ZodOptional<z.ZodNumber>;
     sizeBytes: z.ZodOptional<z.ZodNumber>;
+    googlebotCut: z.ZodOptional<z.ZodObject<{
+      limitBytes: z.ZodNumber;
+      bytesAfterLimit: z.ZodNumber;
+      mainContentStartBytes: z.ZodOptional<z.ZodNumber>;
+      mainContentMarker: z.ZodOptional<z.ZodEnum<{
+        h1: "h1";
+        main: "main";
+      }>>;
+      mainContentStart: z.ZodEnum<{
+        "before-limit": "before-limit";
+        "near-limit": "near-limit";
+        "after-limit": "after-limit";
+        "not-found": "not-found";
+      }>;
+      visibleWordsBeforeLimit: z.ZodNumber;
+      visibleWordsAfterLimit: z.ZodNumber;
+    }, z.core.$strip>>;
     usedJs: z.ZodOptional<z.ZodBoolean>;
     fetchSource: z.ZodOptional<z.ZodEnum<{
       cache: "cache";
@@ -7271,6 +7335,23 @@ export declare const crawlReportSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     responseHeaders: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
     responseTimeMs: z.ZodOptional<z.ZodNumber>;
     sizeBytes: z.ZodOptional<z.ZodNumber>;
+    googlebotCut: z.ZodOptional<z.ZodObject<{
+      limitBytes: z.ZodNumber;
+      bytesAfterLimit: z.ZodNumber;
+      mainContentStartBytes: z.ZodOptional<z.ZodNumber>;
+      mainContentMarker: z.ZodOptional<z.ZodEnum<{
+        h1: "h1";
+        main: "main";
+      }>>;
+      mainContentStart: z.ZodEnum<{
+        "before-limit": "before-limit";
+        "near-limit": "near-limit";
+        "after-limit": "after-limit";
+        "not-found": "not-found";
+      }>;
+      visibleWordsBeforeLimit: z.ZodNumber;
+      visibleWordsAfterLimit: z.ZodNumber;
+    }, z.core.$strip>>;
     usedJs: z.ZodOptional<z.ZodBoolean>;
     fetchSource: z.ZodOptional<z.ZodEnum<{
       cache: "cache";
@@ -8620,6 +8701,23 @@ export declare const crawlerSchemas: {
       responseHeaders: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
       responseTimeMs: z.ZodOptional<z.ZodNumber>;
       sizeBytes: z.ZodOptional<z.ZodNumber>;
+      googlebotCut: z.ZodOptional<z.ZodObject<{
+        limitBytes: z.ZodNumber;
+        bytesAfterLimit: z.ZodNumber;
+        mainContentStartBytes: z.ZodOptional<z.ZodNumber>;
+        mainContentMarker: z.ZodOptional<z.ZodEnum<{
+          h1: "h1";
+          main: "main";
+        }>>;
+        mainContentStart: z.ZodEnum<{
+          "before-limit": "before-limit";
+          "near-limit": "near-limit";
+          "after-limit": "after-limit";
+          "not-found": "not-found";
+        }>;
+        visibleWordsBeforeLimit: z.ZodNumber;
+        visibleWordsAfterLimit: z.ZodNumber;
+      }, z.core.$strip>>;
       usedJs: z.ZodOptional<z.ZodBoolean>;
       fetchSource: z.ZodOptional<z.ZodEnum<{
         cache: "cache";
@@ -9967,6 +10065,23 @@ export declare const crawlerSchemas: {
       responseHeaders: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
       responseTimeMs: z.ZodOptional<z.ZodNumber>;
       sizeBytes: z.ZodOptional<z.ZodNumber>;
+      googlebotCut: z.ZodOptional<z.ZodObject<{
+        limitBytes: z.ZodNumber;
+        bytesAfterLimit: z.ZodNumber;
+        mainContentStartBytes: z.ZodOptional<z.ZodNumber>;
+        mainContentMarker: z.ZodOptional<z.ZodEnum<{
+          h1: "h1";
+          main: "main";
+        }>>;
+        mainContentStart: z.ZodEnum<{
+          "before-limit": "before-limit";
+          "near-limit": "near-limit";
+          "after-limit": "after-limit";
+          "not-found": "not-found";
+        }>;
+        visibleWordsBeforeLimit: z.ZodNumber;
+        visibleWordsAfterLimit: z.ZodNumber;
+      }, z.core.$strip>>;
       usedJs: z.ZodOptional<z.ZodBoolean>;
       fetchSource: z.ZodOptional<z.ZodEnum<{
         cache: "cache";
@@ -11314,6 +11429,23 @@ export declare const crawlerSchemas: {
       responseHeaders: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
       responseTimeMs: z.ZodOptional<z.ZodNumber>;
       sizeBytes: z.ZodOptional<z.ZodNumber>;
+      googlebotCut: z.ZodOptional<z.ZodObject<{
+        limitBytes: z.ZodNumber;
+        bytesAfterLimit: z.ZodNumber;
+        mainContentStartBytes: z.ZodOptional<z.ZodNumber>;
+        mainContentMarker: z.ZodOptional<z.ZodEnum<{
+          h1: "h1";
+          main: "main";
+        }>>;
+        mainContentStart: z.ZodEnum<{
+          "before-limit": "before-limit";
+          "near-limit": "near-limit";
+          "after-limit": "after-limit";
+          "not-found": "not-found";
+        }>;
+        visibleWordsBeforeLimit: z.ZodNumber;
+        visibleWordsAfterLimit: z.ZodNumber;
+      }, z.core.$strip>>;
       usedJs: z.ZodOptional<z.ZodBoolean>;
       fetchSource: z.ZodOptional<z.ZodEnum<{
         cache: "cache";
@@ -12787,6 +12919,23 @@ export declare const crawlerSchemas: {
     responseHeaders: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
     responseTimeMs: z.ZodOptional<z.ZodNumber>;
     sizeBytes: z.ZodOptional<z.ZodNumber>;
+    googlebotCut: z.ZodOptional<z.ZodObject<{
+      limitBytes: z.ZodNumber;
+      bytesAfterLimit: z.ZodNumber;
+      mainContentStartBytes: z.ZodOptional<z.ZodNumber>;
+      mainContentMarker: z.ZodOptional<z.ZodEnum<{
+        h1: "h1";
+        main: "main";
+      }>>;
+      mainContentStart: z.ZodEnum<{
+        "before-limit": "before-limit";
+        "near-limit": "near-limit";
+        "after-limit": "after-limit";
+        "not-found": "not-found";
+      }>;
+      visibleWordsBeforeLimit: z.ZodNumber;
+      visibleWordsAfterLimit: z.ZodNumber;
+    }, z.core.$strip>>;
     usedJs: z.ZodOptional<z.ZodBoolean>;
     fetchSource: z.ZodOptional<z.ZodEnum<{
       cache: "cache";
@@ -13596,6 +13745,23 @@ export declare const crawlerJsonSchemas: {
       responseHeaders: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
       responseTimeMs: z.ZodOptional<z.ZodNumber>;
       sizeBytes: z.ZodOptional<z.ZodNumber>;
+      googlebotCut: z.ZodOptional<z.ZodObject<{
+        limitBytes: z.ZodNumber;
+        bytesAfterLimit: z.ZodNumber;
+        mainContentStartBytes: z.ZodOptional<z.ZodNumber>;
+        mainContentMarker: z.ZodOptional<z.ZodEnum<{
+          h1: "h1";
+          main: "main";
+        }>>;
+        mainContentStart: z.ZodEnum<{
+          "before-limit": "before-limit";
+          "near-limit": "near-limit";
+          "after-limit": "after-limit";
+          "not-found": "not-found";
+        }>;
+        visibleWordsBeforeLimit: z.ZodNumber;
+        visibleWordsAfterLimit: z.ZodNumber;
+      }, z.core.$strip>>;
       usedJs: z.ZodOptional<z.ZodBoolean>;
       fetchSource: z.ZodOptional<z.ZodEnum<{
         cache: "cache";
@@ -14943,6 +15109,23 @@ export declare const crawlerJsonSchemas: {
       responseHeaders: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
       responseTimeMs: z.ZodOptional<z.ZodNumber>;
       sizeBytes: z.ZodOptional<z.ZodNumber>;
+      googlebotCut: z.ZodOptional<z.ZodObject<{
+        limitBytes: z.ZodNumber;
+        bytesAfterLimit: z.ZodNumber;
+        mainContentStartBytes: z.ZodOptional<z.ZodNumber>;
+        mainContentMarker: z.ZodOptional<z.ZodEnum<{
+          h1: "h1";
+          main: "main";
+        }>>;
+        mainContentStart: z.ZodEnum<{
+          "before-limit": "before-limit";
+          "near-limit": "near-limit";
+          "after-limit": "after-limit";
+          "not-found": "not-found";
+        }>;
+        visibleWordsBeforeLimit: z.ZodNumber;
+        visibleWordsAfterLimit: z.ZodNumber;
+      }, z.core.$strip>>;
       usedJs: z.ZodOptional<z.ZodBoolean>;
       fetchSource: z.ZodOptional<z.ZodEnum<{
         cache: "cache";
@@ -16290,6 +16473,23 @@ export declare const crawlerJsonSchemas: {
       responseHeaders: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
       responseTimeMs: z.ZodOptional<z.ZodNumber>;
       sizeBytes: z.ZodOptional<z.ZodNumber>;
+      googlebotCut: z.ZodOptional<z.ZodObject<{
+        limitBytes: z.ZodNumber;
+        bytesAfterLimit: z.ZodNumber;
+        mainContentStartBytes: z.ZodOptional<z.ZodNumber>;
+        mainContentMarker: z.ZodOptional<z.ZodEnum<{
+          h1: "h1";
+          main: "main";
+        }>>;
+        mainContentStart: z.ZodEnum<{
+          "before-limit": "before-limit";
+          "near-limit": "near-limit";
+          "after-limit": "after-limit";
+          "not-found": "not-found";
+        }>;
+        visibleWordsBeforeLimit: z.ZodNumber;
+        visibleWordsAfterLimit: z.ZodNumber;
+      }, z.core.$strip>>;
       usedJs: z.ZodOptional<z.ZodBoolean>;
       fetchSource: z.ZodOptional<z.ZodEnum<{
         cache: "cache";
@@ -17763,6 +17963,23 @@ export declare const crawlerJsonSchemas: {
     responseHeaders: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
     responseTimeMs: z.ZodOptional<z.ZodNumber>;
     sizeBytes: z.ZodOptional<z.ZodNumber>;
+    googlebotCut: z.ZodOptional<z.ZodObject<{
+      limitBytes: z.ZodNumber;
+      bytesAfterLimit: z.ZodNumber;
+      mainContentStartBytes: z.ZodOptional<z.ZodNumber>;
+      mainContentMarker: z.ZodOptional<z.ZodEnum<{
+        h1: "h1";
+        main: "main";
+      }>>;
+      mainContentStart: z.ZodEnum<{
+        "before-limit": "before-limit";
+        "near-limit": "near-limit";
+        "after-limit": "after-limit";
+        "not-found": "not-found";
+      }>;
+      visibleWordsBeforeLimit: z.ZodNumber;
+      visibleWordsAfterLimit: z.ZodNumber;
+    }, z.core.$strip>>;
     usedJs: z.ZodOptional<z.ZodBoolean>;
     fetchSource: z.ZodOptional<z.ZodEnum<{
       cache: "cache";
@@ -22116,6 +22333,7 @@ type WeekData = {
   end: string;
   account: string;
   sites: WeekSite[];
+  first?: boolean;
 };
 type WeekGoogleUpdate = {
   name: string;