@canonry/canonry 4.154.0 → 4.155.0

package/dist/{chunk-ANSQ6JNO.js → chunk-OSHRDV36.js}

@@ -81,7 +81,7 @@ import {
   trafficConnectWordpressRequestSchema,
   trafficEventKindSchema,
   trafficSeriesGranularitySchema
-} from "./chunk-NNW7TJUZ.js";
+} from "./chunk-VIKPFI6F.js";
 
 // src/config.ts
 import fs from "fs";
@@ -4907,6 +4907,78 @@ var getApiV1ProjectsByNameTechnicalAeoTrend = (options) => {
     ...options
   });
 };
+var getApiV1ProjectsByNameTechnicalAeoCrawl = (options) => {
+  return (options.client ?? client).get({
+    security: [
+      {
+        scheme: "bearer",
+        type: "http"
+      }
+    ],
+    url: "/api/v1/projects/{name}/technical-aeo/crawl",
+    ...options
+  });
+};
+var getApiV1ProjectsByNameTechnicalAeoCrawlPages = (options) => {
+  return (options.client ?? client).get({
+    security: [
+      {
+        scheme: "bearer",
+        type: "http"
+      }
+    ],
+    url: "/api/v1/projects/{name}/technical-aeo/crawl/pages",
+    ...options
+  });
+};
+var getApiV1ProjectsByNameTechnicalAeoStructure = (options) => {
+  return (options.client ?? client).get({
+    security: [
+      {
+        scheme: "bearer",
+        type: "http"
+      }
+    ],
+    url: "/api/v1/projects/{name}/technical-aeo/structure",
+    ...options
+  });
+};
+var getApiV1ProjectsByNameTechnicalAeoInternalLinks = (options) => {
+  return (options.client ?? client).get({
+    security: [
+      {
+        scheme: "bearer",
+        type: "http"
+      }
+    ],
+    url: "/api/v1/projects/{name}/technical-aeo/internal-links",
+    ...options
+  });
+};
+var getApiV1ProjectsByNameTechnicalAeoInternalLinksNeighbors = (options) => {
+  return (options.client ?? client).get({
+    security: [
+      {
+        scheme: "bearer",
+        type: "http"
+      }
+    ],
+    url: "/api/v1/projects/{name}/technical-aeo/internal-links/neighbors",
+    ...options
+  });
+};
+var getApiV1ProjectsByNameTechnicalAeoDeadLinks = (options) => {
+  return (options.client ?? client).get({
+    security: [
+      {
+        scheme: "bearer",
+        type: "http"
+      }
+    ],
+    url: "/api/v1/projects/{name}/technical-aeo/dead-links",
+    ...options
+  });
+};
 var postApiV1ProjectsByNameTechnicalAeoRuns = (options) => {
   return (options.client ?? client).post({
     security: [
@@ -7041,6 +7113,96 @@ var ApiClient = class {
       })
     );
   }
+  /** Persisted full-crawl metadata. This never synthesizes a graph from legacy audit rows. */
+  async getTechnicalAeoCrawl(project, opts) {
+    return this.invoke(
+      () => getApiV1ProjectsByNameTechnicalAeoCrawl({
+        client: this.heyClient,
+        path: { name: project },
+        query: { runId: opts?.runId }
+      })
+    );
+  }
+  /** Bounded, cursor-paged crawl nodes. */
+  async getTechnicalAeoCrawlPages(project, opts) {
+    return this.invoke(
+      () => getApiV1ProjectsByNameTechnicalAeoCrawlPages({
+        client: this.heyClient,
+        path: { name: project },
+        query: {
+          runId: opts?.runId,
+          inventoryEligible: opts?.inventoryEligible,
+          fetchState: opts?.fetchState,
+          indexabilityState: opts?.indexabilityState,
+          auditState: opts?.auditState,
+          sort: opts?.sort,
+          cursor: opts?.cursor,
+          limit: opts?.limit !== void 0 ? String(opts.limit) : void 0
+        }
+      })
+    );
+  }
+  /** One bounded path level from a persisted crawl. */
+  async getTechnicalAeoStructure(project, opts) {
+    return this.invoke(
+      () => getApiV1ProjectsByNameTechnicalAeoStructure({
+        client: this.heyClient,
+        path: { name: project },
+        query: {
+          runId: opts?.runId,
+          parentPath: opts?.parentPath,
+          cursor: opts?.cursor,
+          limit: opts?.limit !== void 0 ? String(opts.limit) : void 0
+        }
+      })
+    );
+  }
+  /** Bounded, cursor-paged internal crawl edges. */
+  async getTechnicalAeoInternalLinks(project, opts) {
+    return this.invoke(
+      () => getApiV1ProjectsByNameTechnicalAeoInternalLinks({
+        client: this.heyClient,
+        path: { name: project },
+        query: {
+          runId: opts?.runId,
+          sourceUrl: opts?.sourceUrl,
+          targetUrl: opts?.targetUrl,
+          followable: opts?.followable,
+          cursor: opts?.cursor,
+          limit: opts?.limit !== void 0 ? String(opts.limit) : void 0
+        }
+      })
+    );
+  }
+  /** Bounded inbound/outbound internal edges for one crawl node. */
+  async getTechnicalAeoInternalLinkNeighbors(project, opts) {
+    return this.invoke(
+      () => getApiV1ProjectsByNameTechnicalAeoInternalLinksNeighbors({
+        client: this.heyClient,
+        path: { name: project },
+        query: {
+          runId: opts.runId,
+          nodeKey: opts.nodeKey,
+          url: opts.url,
+          limit: opts.limit !== void 0 ? String(opts.limit) : void 0
+        }
+      })
+    );
+  }
+  /** Dead-link state/findings; `disabled` means the crawl did not opt in. */
+  async getTechnicalAeoDeadLinks(project, opts) {
+    return this.invoke(
+      () => getApiV1ProjectsByNameTechnicalAeoDeadLinks({
+        client: this.heyClient,
+        path: { name: project },
+        query: {
+          runId: opts?.runId,
+          cursor: opts?.cursor,
+          limit: opts?.limit !== void 0 ? String(opts.limit) : void 0
+        }
+      })
+    );
+  }
   async triggerSiteAudit(project, body) {
     return this.invoke(
       () => postApiV1ProjectsByNameTechnicalAeoRuns({
@@ -8209,10 +8371,61 @@ var technicalAeoTrendInputSchema = z3.object({
   project: projectNameSchema,
   limit: z3.number().int().positive().max(365).optional()
 });
+var technicalAeoCrawlInputSchema = z3.object({
+  project: projectNameSchema,
+  runId: runIdSchema.optional().describe("Historical crawl-bearing site-audit run ID. Omit for the latest persisted crawl.")
+});
+var technicalAeoCrawlPagesInputSchema = z3.object({
+  project: projectNameSchema,
+  runId: runIdSchema.optional(),
+  inventoryEligible: z3.boolean().optional().describe("Filter Canonry technical-inventory eligibility. This is not actual Google index coverage."),
+  fetchState: z3.string().min(1).optional().describe("Filter crawler fetch state, for example html, redirect, non-html, or fetch-error."),
+  indexabilityState: z3.string().min(1).optional().describe("Filter crawler-derived indexability state. This is not Google index coverage."),
+  auditState: z3.string().min(1).optional().describe("Filter audit state."),
+  sort: z3.enum(["url", "path", "score-asc", "score-desc"]).optional(),
+  cursor: z3.string().min(1).optional().describe("Opaque cursor from the previous crawl-pages result."),
+  limit: z3.number().int().positive().max(200).optional()
+});
+var technicalAeoStructureInputSchema = z3.object({
+  project: projectNameSchema,
+  runId: runIdSchema.optional(),
+  parentPath: z3.string().min(1).optional().describe("Path whose immediate children to list. Defaults to /. This never returns a whole site tree."),
+  cursor: z3.string().min(1).optional().describe("Opaque cursor from the previous structure result."),
+  limit: z3.number().int().positive().max(100).optional()
+});
+var technicalAeoInternalLinksInputSchema = z3.object({
+  project: projectNameSchema,
+  runId: runIdSchema.optional(),
+  sourceUrl: z3.string().url().optional(),
+  targetUrl: z3.string().url().optional(),
+  followable: z3.boolean().optional(),
+  cursor: z3.string().min(1).optional().describe("Opaque cursor from the previous internal-links result."),
+  limit: z3.number().int().positive().max(200).optional()
+});
+var technicalAeoLinkNeighborsInputSchema = z3.object({
+  project: projectNameSchema,
+  runId: runIdSchema.optional(),
+  nodeKey: z3.string().min(1).optional(),
+  url: z3.string().url().optional(),
+  limit: z3.number().int().positive().max(100).optional()
+}).refine((value) => Boolean(value.nodeKey || value.url), {
+  message: "Provide nodeKey or url.",
+  path: ["nodeKey"]
+});
+var technicalAeoDeadLinksInputSchema = z3.object({
+  project: projectNameSchema,
+  runId: runIdSchema.optional(),
+  cursor: z3.string().min(1).optional().describe("Opaque cursor from the previous dead-links result."),
+  limit: z3.number().int().positive().max(200).optional()
+});
 var technicalAeoRunInputSchema = z3.object({
   project: projectNameSchema,
   sitemapUrl: z3.string().url().optional().describe("Override the sitemap URL. Defaults to https://<canonicalDomain>/sitemap.xml."),
-  limit: z3.number().int().positive().max(2e3).optional().describe("Cap pages audited (highest sitemap <priority> first).")
+  limit: z3.number().int().positive().max(2e3).optional().describe("Deprecated compatibility alias for maxPages."),
+  maxPages: z3.number().int().positive().max(5e4).optional().describe("Maximum pages crawled and audited. Defaults to 1,000; hard maximum 50,000."),
+  maxEdges: z3.number().int().positive().max(1e6).optional().describe("Maximum link observations retained for this crawl. Defaults to 100,000; hard maximum 1,000,000."),
+  maxDepth: z3.number().int().min(0).max(100).optional().describe("Maximum internal-link depth from the root page."),
+  checkDeadLinks: z3.boolean().optional().describe("Opt in to internal dead-link checks. Omitted and false both disable checks.")
 });
 var AGENT_WEBHOOK_EVENTS = [
   notificationEventSchema.enum["run.completed"],
@@ -10060,10 +10273,106 @@ var canonryMcpTools = [
     openApiOperations: ["GET /api/v1/projects/{name}/technical-aeo/trend"],
     handler: (client2, input) => client2.getTechnicalAeoTrend(input.project, input.limit !== void 0 ? { limit: input.limit } : void 0)
   }),
+  defineTool({
+    name: "canonry_technical_aeo_crawl",
+    title: "Get persisted Technical AEO crawl",
+    description: "Read persisted full-crawl metadata for the latest or selected Technical AEO site-audit run: root URL, crawl/indexability/link-score versions, effective budgets, completeness, counts, and explicit dead-link check state. This does not fabricate a graph from older scorecard-only audits.",
+    access: "read",
+    tier: "monitoring",
+    inputSchema: technicalAeoCrawlInputSchema,
+    annotations: readAnnotations(),
+    openApiOperations: ["GET /api/v1/projects/{name}/technical-aeo/crawl"],
+    handler: (client2, input) => client2.getTechnicalAeoCrawl(input.project, { runId: input.runId })
+  }),
+  defineTool({
+    name: "canonry_technical_aeo_crawl_pages",
+    title: "List Technical AEO crawl pages",
+    description: "Read one bounded, cursor-paged list of canonical crawl nodes. Filter crawler-derived indexability and audit state, then follow nextCursor; this is technical inventory eligibility, not a claim about Google index coverage.",
+    access: "read",
+    tier: "monitoring",
+    inputSchema: technicalAeoCrawlPagesInputSchema,
+    annotations: readAnnotations(),
+    openApiOperations: ["GET /api/v1/projects/{name}/technical-aeo/crawl/pages"],
+    handler: (client2, input) => client2.getTechnicalAeoCrawlPages(input.project, {
+      runId: input.runId,
+      inventoryEligible: input.inventoryEligible,
+      fetchState: input.fetchState,
+      indexabilityState: input.indexabilityState,
+      auditState: input.auditState,
+      sort: input.sort,
+      cursor: input.cursor,
+      limit: input.limit
+    })
+  }),
+  defineTool({
+    name: "canonry_technical_aeo_structure",
+    title: "List Technical AEO site structure",
+    description: "Read one bounded level of the persisted site hierarchy below parentPath. Follow nextCursor for more siblings; request a child path separately rather than attempting to materialize the entire website tree.",
+    access: "read",
+    tier: "monitoring",
+    inputSchema: technicalAeoStructureInputSchema,
+    annotations: readAnnotations(),
+    openApiOperations: ["GET /api/v1/projects/{name}/technical-aeo/structure"],
+    handler: (client2, input) => client2.getTechnicalAeoStructure(input.project, {
+      runId: input.runId,
+      parentPath: input.parentPath,
+      cursor: input.cursor,
+      limit: input.limit
+    })
+  }),
+  defineTool({
+    name: "canonry_technical_aeo_internal_links",
+    title: "List Technical AEO internal links",
+    description: "Read a bounded, cursor-paged list of persisted internal crawl edges. Filter by source URL, target URL, or followability. Use the neighbors tool for one page rather than loading a graph.",
+    access: "read",
+    tier: "monitoring",
+    inputSchema: technicalAeoInternalLinksInputSchema,
+    annotations: readAnnotations(),
+    openApiOperations: ["GET /api/v1/projects/{name}/technical-aeo/internal-links"],
+    handler: (client2, input) => client2.getTechnicalAeoInternalLinks(input.project, {
+      runId: input.runId,
+      sourceUrl: input.sourceUrl,
+      targetUrl: input.targetUrl,
+      followable: input.followable,
+      cursor: input.cursor,
+      limit: input.limit
+    })
+  }),
+  defineTool({
+    name: "canonry_technical_aeo_link_neighbors",
+    title: "Get Technical AEO page link neighbors",
+    description: "Read bounded inbound and outbound internal links for exactly one crawl node, selected by nodeKey or URL. It returns independent truncation flags for inbound and outbound edges, not a transitive traversal.",
+    access: "read",
+    tier: "monitoring",
+    inputSchema: technicalAeoLinkNeighborsInputSchema,
+    annotations: readAnnotations(),
+    openApiOperations: ["GET /api/v1/projects/{name}/technical-aeo/internal-links/neighbors"],
+    handler: (client2, input) => client2.getTechnicalAeoInternalLinkNeighbors(input.project, {
+      runId: input.runId,
+      nodeKey: input.nodeKey,
+      url: input.url,
+      limit: input.limit
+    })
+  }),
+  defineTool({
+    name: "canonry_technical_aeo_dead_links",
+    title: "List Technical AEO dead links",
+    description: "Read the persisted dead-link check state and a bounded, cursor-paged list of findings. A disabled result means the crawl was run without opt-in checks; it never means zero dead links.",
+    access: "read",
+    tier: "monitoring",
+    inputSchema: technicalAeoDeadLinksInputSchema,
+    annotations: readAnnotations(),
+    openApiOperations: ["GET /api/v1/projects/{name}/technical-aeo/dead-links"],
+    handler: (client2, input) => client2.getTechnicalAeoDeadLinks(input.project, {
+      runId: input.runId,
+      cursor: input.cursor,
+      limit: input.limit
+    })
+  }),
   defineTool({
     name: "canonry_technical_aeo_run",
     title: "Run Technical AEO site audit",
-    description: "Trigger a site-audit run: crawl the project sitemap and audit every reachable page across the aeo-audit ranking factors. Returns {runId, status}; the audit runs in the background (a large site can take minutes). Idempotent \u2014 if a site-audit is already in flight it returns that run. Poll canonry_run_get with the returned runId, then read canonry_technical_aeo_score.",
+    description: "Start a site-audit run. The run discovers root, sitemap, and linked pages. Its unattended default is 1,000 pages and 100,000 link observations; callers may explicitly raise either to its hard maximum. It returns {runId, status} and continues in the background. If an active run has identical effective options, this tool returns it; different options are refused. Poll canonry_run_get, then read the crawl and score tools.",
     access: "write",
     tier: "monitoring",
     inputSchema: technicalAeoRunInputSchema,
@@ -10071,7 +10380,11 @@ var canonryMcpTools = [
     openApiOperations: ["POST /api/v1/projects/{name}/technical-aeo/runs"],
     handler: (client2, input) => client2.triggerSiteAudit(input.project, {
       sitemapUrl: input.sitemapUrl,
-      limit: input.limit
+      limit: input.limit,
+      maxPages: input.maxPages,
+      maxEdges: input.maxEdges,
+      maxDepth: input.maxDepth,
+      checkDeadLinks: input.checkDeadLinks
     })
   }),
   // ----- OpenAI ads (ChatGPT ads) -----

package/dist/{chunk-NNW7TJUZ.js → chunk-VIKPFI6F.js}

@@ -8441,6 +8441,7 @@ var snapshotReportSchema = z23.object({
 
 // ../contracts/src/technical-aeo.ts
 import { z as z24 } from "zod";
+var nullableRunStatusSchema = z24.union([runStatusSchema, z24.null()]);
 var siteAuditFactorStatusSchema = z24.enum(["pass", "partial", "fail"]);
 var SiteAuditFactorStatuses = siteAuditFactorStatusSchema.enum;
 function factorStatusFromScore(score) {
@@ -8475,7 +8476,7 @@ var siteAuditScoreSchema = z24.object({
   project: z24.string(),
   hasData: z24.boolean(),
   runId: z24.string().nullable(),
-  runStatus: runStatusSchema.nullable(),
+  runStatus: nullableRunStatusSchema,
   sitemapUrl: z24.string().nullable(),
   auditedAt: z24.string().nullable(),
   aggregateScore: z24.number(),
@@ -8523,12 +8524,194 @@ var siteAuditTrendResponseSchema = z24.object({
   project: z24.string(),
   points: z24.array(siteAuditTrendPointSchema).default([])
 });
+var siteCrawlDeadLinkStateSchema = z24.enum(["disabled", "complete", "partial", "unavailable"]);
+var SiteCrawlDeadLinkStates = siteCrawlDeadLinkStateSchema.enum;
+var siteCrawlCountsSchema = z24.object({
+  pagesDiscovered: z24.number().int().nonnegative(),
+  pagesFetched: z24.number().int().nonnegative(),
+  pagesEligible: z24.number().int().nonnegative(),
+  edges: z24.number().int().nonnegative(),
+  findings: z24.number().int().nonnegative()
+});
+var siteCrawlDeadLinksSummarySchema = z24.discriminatedUnion("state", [
+  z24.object({ state: z24.literal("unavailable") }),
+  z24.object({ state: z24.literal("disabled") }),
+  z24.object({ state: z24.literal("complete"), checked: z24.number().int().nonnegative(), found: z24.number().int().nonnegative() }),
+  z24.object({ state: z24.literal("partial"), checked: z24.number().int().nonnegative(), found: z24.number().int().nonnegative() })
+]);
+var siteCrawlSummarySchema = z24.object({
+  project: z24.string(),
+  hasCrawlData: z24.boolean(),
+  legacyAuditAvailable: z24.boolean(),
+  runId: z24.string().nullable(),
+  runStatus: nullableRunStatusSchema,
+  rootUrl: z24.string().nullable(),
+  crawlSchemaVersion: z24.string().nullable().optional(),
+  engineVersion: z24.string().nullable().optional(),
+  normalizationVersion: z24.string().nullable().optional(),
+  indexabilityVersion: z24.string().nullable().optional(),
+  linkScoreVersion: z24.string().nullable().optional(),
+  effectiveOptions: z24.record(z24.string(), z24.unknown()).default({}),
+  complete: z24.boolean(),
+  termination: z24.string().nullable(),
+  detailsAvailable: z24.boolean(),
+  counts: siteCrawlCountsSchema,
+  deadLinks: siteCrawlDeadLinksSummarySchema
+});
+var siteCrawlPageSchema = z24.object({
+  nodeKey: z24.string(),
+  url: z24.string(),
+  finalUrl: z24.string().nullable(),
+  path: z24.string(),
+  parentPath: z24.string(),
+  discoverySource: z24.string(),
+  fetchState: z24.string(),
+  httpStatus: z24.number().int().nullable(),
+  canonicalUrl: z24.string().nullable(),
+  indexabilityState: z24.string(),
+  indexabilityReasons: z24.array(z24.string()).default([]),
+  auditState: z24.string(),
+  auditScore: z24.number().nullable(),
+  inventoryEligible: z24.boolean(),
+  depth: z24.number().int().nullable(),
+  inboundUniqueEdges: z24.number().int().nonnegative(),
+  outboundUniqueEdges: z24.number().int().nonnegative(),
+  inboundOccurrences: z24.number().int().nonnegative(),
+  outboundOccurrences: z24.number().int().nonnegative(),
+  linkScoreRaw: z24.number().nullable(),
+  linkScoreNormalized: z24.number().nullable()
+});
+var siteCrawlPagesResponseSchema = z24.object({
+  project: z24.string(),
+  hasCrawlData: z24.boolean(),
+  runId: z24.string().nullable(),
+  total: z24.number().int().nonnegative(),
+  nextCursor: z24.string().nullable(),
+  pages: z24.array(siteCrawlPageSchema).default([])
+});
+var siteCrawlStructureChildSchema = z24.object({
+  path: z24.string(),
+  /** URL of the exact folder landing page, null for a synthetic hierarchy node. */
+  url: z24.string().nullable(),
+  hasPage: z24.boolean(),
+  pageCount: z24.number().int().positive(),
+  inventoryEligibleCount: z24.number().int().nonnegative(),
+  fetchedCount: z24.number().int().nonnegative()
+});
+var siteCrawlStructureResponseSchema = z24.object({
+  project: z24.string(),
+  hasCrawlData: z24.boolean(),
+  runId: z24.string().nullable(),
+  parentPath: z24.string(),
+  nextCursor: z24.string().nullable(),
+  children: z24.array(siteCrawlStructureChildSchema).default([])
+});
+var siteCrawlEdgeSchema = z24.object({
+  edgeKey: z24.string(),
+  sourceNodeKey: z24.string(),
+  sourceUrl: z24.string(),
+  targetNodeKey: z24.string().nullable(),
+  targetUrl: z24.string(),
+  relation: z24.string(),
+  internal: z24.boolean(),
+  followable: z24.boolean(),
+  occurrences: z24.number().int().positive(),
+  followableOccurrences: z24.number().int().nonnegative(),
+  nofollowOccurrences: z24.number().int().nonnegative(),
+  anchors: z24.array(z24.string()).default([])
+});
+var siteCrawlInternalLinksResponseSchema = z24.object({
+  project: z24.string(),
+  hasCrawlData: z24.boolean(),
+  runId: z24.string().nullable(),
+  total: z24.number().int().nonnegative(),
+  nextCursor: z24.string().nullable(),
+  edges: z24.array(siteCrawlEdgeSchema).default([])
+});
+var siteCrawlNeighborsResponseSchema = z24.object({
+  project: z24.string(),
+  hasCrawlData: z24.boolean(),
+  runId: z24.string().nullable(),
+  nodeKey: z24.string().nullable(),
+  url: z24.string().nullable(),
+  inbound: z24.array(siteCrawlEdgeSchema).default([]),
+  outbound: z24.array(siteCrawlEdgeSchema).default([]),
+  inboundTruncated: z24.boolean(),
+  outboundTruncated: z24.boolean()
+});
+var siteCrawlDeadLinkSchema = z24.object({
+  findingKey: z24.string(),
+  severity: z24.string(),
+  sourceNodeKey: z24.string().nullable(),
+  sourceUrl: z24.string().nullable(),
+  targetNodeKey: z24.string().nullable(),
+  targetUrl: z24.string().nullable(),
+  evidence: z24.record(z24.string(), z24.unknown()).default({})
+});
+var siteCrawlDeadLinksResponseSchema = z24.discriminatedUnion("state", [
+  z24.object({ project: z24.string(), runId: z24.string().nullable(), state: z24.literal("unavailable"), legacyAuditAvailable: z24.boolean() }),
+  z24.object({ project: z24.string(), runId: z24.string(), state: z24.literal("disabled"), checkDeadLinks: z24.literal(false) }),
+  z24.object({
+    project: z24.string(),
+    runId: z24.string(),
+    state: z24.literal("complete"),
+    checkDeadLinks: z24.literal(true),
+    checked: z24.number().int().nonnegative(),
+    found: z24.number().int().nonnegative(),
+    total: z24.number().int().nonnegative(),
+    nextCursor: z24.string().nullable(),
+    deadLinks: z24.array(siteCrawlDeadLinkSchema).default([])
+  }),
+  z24.object({
+    project: z24.string(),
+    runId: z24.string(),
+    state: z24.literal("partial"),
+    checkDeadLinks: z24.literal(true),
+    checked: z24.number().int().nonnegative(),
+    found: z24.number().int().nonnegative(),
+    total: z24.number().int().nonnegative(),
+    nextCursor: z24.string().nullable(),
+    deadLinks: z24.array(siteCrawlDeadLinkSchema).default([])
+  })
+]);
+var SITE_AUDIT_DEFAULT_PAGE_LIMIT = 1e3;
+var SITE_AUDIT_MAX_PAGE_LIMIT = 5e4;
+var SITE_AUDIT_DEFAULT_EDGE_LIMIT = 1e5;
+var SITE_AUDIT_MAX_EDGE_LIMIT = 1e6;
 var siteAuditRunRequestSchema = z24.object({
-  /** Override the sitemap URL. Defaults to `https://<canonicalDomain>/sitemap.xml`. */
+  /** @deprecated Prefer the configured project sitemap; retained for compatibility. */
   sitemapUrl: z24.string().url().optional(),
-  /** Cap the number of pages audited (highest sitemap `<priority>` first). */
-  limit: z24.number().int().positive().max(2e3).optional()
-});
+  /** @deprecated Prefer `maxPages`; retained for compatibility. */
+  limit: z24.number().int().positive().max(2e3).optional(),
+  /** Crawl page budget. When omitted, Canonry crawls up to 1,000 pages. */
+  maxPages: z24.number().int().positive().max(5e4).optional(),
+  /** Internal-link observation budget. When omitted, Canonry retains up to 100,000 edges. */
+  maxEdges: z24.number().int().positive().max(1e6).optional(),
+  /** Maximum crawl depth from the root. */
+  maxDepth: z24.number().int().min(0).max(100).optional(),
+  /** Off by default; derives findings only from observed internal targets. External links are never probed. */
+  checkDeadLinks: z24.boolean().default(false)
+});
+function normalizeSiteAuditRunRequest(request) {
+  return {
+    schemaVersion: 1,
+    sitemapUrl: request.sitemapUrl ? new URL(request.sitemapUrl).toString() : null,
+    maxPages: request.maxPages ?? request.limit ?? SITE_AUDIT_DEFAULT_PAGE_LIMIT,
+    maxEdges: request.maxEdges ?? SITE_AUDIT_DEFAULT_EDGE_LIMIT,
+    maxDepth: request.maxDepth ?? null,
+    checkDeadLinks: request.checkDeadLinks === true
+  };
+}
+function siteAuditRequestIdentity(request) {
+  return JSON.stringify([
+    request.schemaVersion,
+    request.sitemapUrl,
+    request.maxPages,
+    request.maxEdges,
+    request.maxDepth,
+    request.checkDeadLinks
+  ]);
+}
 var siteAuditRunResponseSchema = z24.object({
   runId: z24.string(),
   status: runStatusSchema
@@ -14145,7 +14328,19 @@ export {
   siteAuditScoreSchema,
   siteAuditPagesResponseSchema,
   siteAuditTrendResponseSchema,
+  siteCrawlSummarySchema,
+  siteCrawlPagesResponseSchema,
+  siteCrawlStructureResponseSchema,
+  siteCrawlInternalLinksResponseSchema,
+  siteCrawlNeighborsResponseSchema,
+  siteCrawlDeadLinksResponseSchema,
+  SITE_AUDIT_DEFAULT_PAGE_LIMIT,
+  SITE_AUDIT_MAX_PAGE_LIMIT,
+  SITE_AUDIT_DEFAULT_EDGE_LIMIT,
+  SITE_AUDIT_MAX_EDGE_LIMIT,
   siteAuditRunRequestSchema,
+  normalizeSiteAuditRunRequest,
+  siteAuditRequestIdentity,
   siteAuditRunResponseSchema,
   schedulableRunKindSchema,
   SchedulableRunKinds,