@canonry/canonry 7.70.0 → 7.71.0

package/dist/{chunk-6JGQT4OH.js → chunk-A3NSYJJL.js}

@@ -7905,7 +7905,13 @@ var siteCrawlInventorySummarySchema = z20.object({
   eligible: z20.number().int().nonnegative(),
   excluded: z20.number().int().nonnegative(),
   /** Disjoint primary reasons: their page counts sum to excluded. */
-  excludedReasons: z20.array(siteCrawlHealthReasonCountSchema).max(siteHealthReasonSchema.options.length)
+  excludedReasons: z20.array(siteCrawlHealthReasonCountSchema).max(siteHealthReasonSchema.options.length),
+  /**
+   * URL versions the audit set aside (see `siteCrawlUrlVersionOf`): not scored
+   * and not counted in fixes. A subset of `excluded`; 0 for a scan made before
+   * the audit set them aside, which scored every address.
+   */
+  urlVersions: z20.number().int().nonnegative().default(0)
 });
 var siteCrawlAvailableScanDatesSchema = z20.object({
   /** Most recent distinct visible crawl dates, newest first. Fewer rows than totalDates means the list is bounded. */
@@ -8082,6 +8088,24 @@ function deriveSiteHealthState(input) {
       return "unchecked";
   }
 }
+var siteCrawlUrlVersionFilterSchema = z20.enum(["include", "exclude", "only"]);
+var SiteCrawlUrlVersionFilters = siteCrawlUrlVersionFilterSchema.enum;
+var SITE_CRAWL_URL_VERSION_AUDIT_STATE = "url-version";
+function siteCrawlUrlVersionOf(input) {
+  if (input.fetchState !== SiteCrawlFetchStates.html || !input.canonicalUrl) return null;
+  let own;
+  let canonical;
+  try {
+    own = new URL(input.url);
+    canonical = new URL(input.canonicalUrl);
+  } catch {
+    return null;
+  }
+  if (own.search === "") return null;
+  if (hostOf(own.href) !== hostOf(canonical.href) || own.pathname !== canonical.pathname) return null;
+  if (own.search === canonical.search) return null;
+  return canonical.href;
+}
 var TEMPLATE_LINK_RATIO_THRESHOLD = 0.7;
 var TEMPLATE_LINK_MIN_FETCHED_PAGES = 15;
 var siteCrawlLinkPlacementSchema = z20.enum(["navigation", "content", "unknown"]);
@@ -8251,7 +8275,14 @@ var siteCrawlPageSchema = z20.object({
   linkScoreNormalized: percent().nullable(),
   healthState: siteHealthStateSchema,
   /** Concrete fetch/indexability reason; unknown never implies a canonical points elsewhere. */
-  healthReason: siteHealthReasonSchema.optional()
+  healthReason: siteHealthReasonSchema.optional(),
+  /**
+   * The page this address is a URL version of (its canonical), or null for a
+   * page. A URL version is not scored: its `auditState` is `url-version` and
+   * its `auditScore` null. Always null in a scan made before the audit set URL
+   * versions aside.
+   */
+  urlVersionOf: z20.string().nullable().default(null)
 });
 var siteCrawlAuditFindingSchema = z20.object({
   type: z20.enum(["found", "missing", "info", "timeout", "unreachable"]),
@@ -26709,6 +26740,10 @@ export {
   SiteCrawlIndexabilityReasons,
   deriveSiteHealthReason,
   deriveSiteHealthState,
+  siteCrawlUrlVersionFilterSchema,
+  SiteCrawlUrlVersionFilters,
+  SITE_CRAWL_URL_VERSION_AUDIT_STATE,
+  siteCrawlUrlVersionOf,
   TEMPLATE_LINK_RATIO_THRESHOLD,
   SiteHealthLinkClassificationSources,
   siteHealthTemplateDetectionSchema,

package/dist/{chunk-QBR7BWO6.js → chunk-AAPMP2T3.js}

@@ -7,27 +7,27 @@ import {
   reparseStoredResult4,
   reparseStoredResult5,
   resolveStoredApiResponse
-} from "./chunk-EIRIZPR6.js";
+} from "./chunk-K4S2T6C5.js";
 import {
   loadConfig
-} from "./chunk-6RI7JFFI.js";
+} from "./chunk-3NOFNFGV.js";
 import {
   isMachineFormat
 } from "./chunk-HGMYEDAQ.js";
 import {
   determineCitationState
-} from "./chunk-R7RTWOOV.js";
+} from "./chunk-ETMB45WP.js";
 import {
   backfillProjectAnswerMentions,
   competitorIdentityColumns,
   createRunCompetitorResolver,
   readMarketCompetitorNames,
   refreshSnapshotMentionIdentity
-} from "./chunk-JGO7LGVN.js";
+} from "./chunk-SZSJALQM.js";
 import {
   classifyAiUserFetch,
   classifyCrawler
-} from "./chunk-CNSLBHFP.js";
+} from "./chunk-WNBN4FYE.js";
 import {
   aiUserFetchEventsHourly,
   auditLog,
@@ -42,7 +42,7 @@ import {
   querySnapshots,
   rawEventSamples,
   runs
-} from "./chunk-XOCF2U54.js";
+} from "./chunk-EDQ4V4PJ.js";
 import {
   ProviderNames,
   RetrievalContracts,
@@ -59,7 +59,7 @@ import {
   extractRecommendedCompetitors,
   normalizeUrlPath,
   openRouterRouteModel
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/commands/backfill.ts
 import { setImmediate as yieldToEventLoop } from "timers/promises";
@@ -437,7 +437,7 @@ No DB writes performed. Re-run without --dry-run to apply.`);
   }
 }
 async function backfillInsightsCommand(project, opts) {
-  const { IntelligenceService } = await import("./intelligence-service-PAMFRLPE.js");
+  const { IntelligenceService } = await import("./intelligence-service-XDGWLXW4.js");
   const config = loadConfig();
   const db = createClient(config.database);
   migrate(db);

package/dist/{chunk-3ZF3T3OG.js → chunk-ALXQPMYR.js}

@@ -1,7 +1,7 @@
 import {
   API_PROVIDER_NAMES,
   ProviderNames
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/provider-registration.ts
 function isApiProviderRegistrable(name, entry) {

package/dist/{chunk-RSK7E53V.js → chunk-AVNEHYTZ.js}

@@ -8,7 +8,7 @@ import {
 } from "./chunk-HGMYEDAQ.js";
 import {
   describeError
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/commands/mcp.ts
 import fs from "fs";

package/dist/{chunk-BRT5GE3Z.js → chunk-C3ZH2HLV.js}

@@ -5,7 +5,7 @@ import {
   isStoredPageReadTool,
   isStoredReadTool,
   truncateToolResult
-} from "./chunk-DW3KF33I.js";
+} from "./chunk-OOXR7SZ5.js";
 import {
   CANONRY_MCP_TOOLKITS
 } from "./chunk-NDTU7FGL.js";
@@ -22,15 +22,15 @@ import {
   resolveApiKeyFor,
   resolveModelForProvider,
   validateAgentProviderRegistry
-} from "./chunk-6RI7JFFI.js";
+} from "./chunk-3NOFNFGV.js";
 import {
   CanonryMcpToolNames,
   canonryMcpTools
-} from "./chunk-QNSMMQJY.js";
+} from "./chunk-WE3SK5GQ.js";
 import {
   agentToolEvents,
   llmUsageEvents
-} from "./chunk-XOCF2U54.js";
+} from "./chunk-EDQ4V4PJ.js";
 import {
   MeasurementPortfolioLists,
   SeoCapabilities,
@@ -39,7 +39,7 @@ import {
   describeError,
   validationError,
   visibilityReportRequestSchema
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/agent/session.ts
 import fs3 from "fs";

package/dist/{chunk-RVEXUQHP.js → chunk-DEMNY4YE.js}

@@ -5,7 +5,7 @@ import {
   loadConfig,
   loadConfigRaw,
   saveConfigPatch
-} from "./chunk-6RI7JFFI.js";
+} from "./chunk-3NOFNFGV.js";
 import {
   CANONRY_NPM_PACKAGE_URL,
   compareSemver,
@@ -18,7 +18,7 @@ import {
   updateCheckEnvOptOut,
   upgradeCaveatFor,
   upgradeCommandFor
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/runtime-context.ts
 function cliRuntimeContext(env = process.env, stdio = process) {

package/dist/{chunk-RJSJNR76.js → chunk-DP5V4C3I.js}

@@ -2,18 +2,18 @@ import {
   configExists,
   loadConfigRaw,
   saveConfigPatch
-} from "./chunk-6RI7JFFI.js";
+} from "./chunk-3NOFNFGV.js";
 import {
   BUNDLED_SKILL_NAMES,
   installSkills
-} from "./chunk-JNRMODJS.js";
+} from "./chunk-NPHBHVAY.js";
 import {
   PACKAGE_VERSION
 } from "./chunk-AOJU5LKX.js";
 import {
   SKILL_MANIFEST_FILENAME,
   SkillsClients
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/skills-autosync.ts
 import fs from "fs";

package/dist/{chunk-XOCF2U54.js → chunk-EDQ4V4PJ.js}

@@ -20,7 +20,7 @@ import {
   templateLinkRatio,
   templateLinkUbiquityAvailable,
   validationError
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 import {
   __export
 } from "./chunk-MLKGABMK.js";
@@ -1415,6 +1415,13 @@ var siteCrawlPages = sqliteTable2("site_crawl_pages", {
    * column existed, which reads must report rather than treat as a state.
    */
   healthState: text2("health_state"),
+  /**
+   * The canonical page this address is a URL version of (contract
+   * `siteCrawlUrlVersionOf`), written at publish time; such a row is not
+   * scored. NULL for a page, and for every row of a scan published before the
+   * audit set URL versions aside.
+   */
+  urlVersionOf: text2("url_version_of"),
   auditState: text2("audit_state").notNull().default("pending"),
   auditScore: real("audit_score"),
   auditFields: text2("audit_fields", { mode: "json" }).$type().notNull().default({}),
@@ -8254,6 +8261,17 @@ var MIGRATION_VERSIONS = [
     statements: [
       `ALTER TABLE schedules ADD COLUMN enabled_at TEXT`
     ]
+  },
+  {
+    // The page a crawled address is a URL version of: a parameter copy whose
+    // canonical names the same path, which the audit no longer scores.
+    // Nullable with no default and no backfill: a scan published before this
+    // scored every address, so its rows truthfully read as pages.
+    version: 197,
+    name: "site-crawl-url-versions",
+    statements: [
+      `ALTER TABLE site_crawl_pages ADD COLUMN url_version_of TEXT`
+    ]
   }
 ];
 var AERO_LEDGER_REBUILDS = [

package/dist/{chunk-R7RTWOOV.js → chunk-ETMB45WP.js}

@@ -1,6 +1,6 @@
 import {
   hostMatchesDomain
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/citation-utils.ts
 function pickProjectCitedDomain(citedDomains, projectDomains) {

package/dist/{chunk-7W4KNDAW.js → chunk-FNVUPIMW.js}

@@ -5,7 +5,7 @@ import {
   siteCrawlGraphNodes,
   siteCrawlPages,
   siteCrawlSnapshots
-} from "./chunk-XOCF2U54.js";
+} from "./chunk-EDQ4V4PJ.js";
 import {
   SITE_CRAWL_GRAPH_MAX_EDGES,
   SITE_CRAWL_GRAPH_MAX_NODES,
@@ -15,7 +15,7 @@ import {
   factorStatusFromDistribution,
   factorStatusFromScore,
   roundPreservingTotal
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/site-audit-factors.ts
 function recordedSharePct(factor) {

package/dist/{chunk-PHHQVV3G.js → chunk-ILLWCY2P.js}

@@ -6,12 +6,12 @@ import {
 import {
   createApiClient,
   runWithUsageTags
-} from "./chunk-BGTJTKOJ.js";
+} from "./chunk-T6IV35KG.js";
 import {
   canonryMcpTools,
   mcpOutputSchema,
   toolOperationAccess
-} from "./chunk-QNSMMQJY.js";
+} from "./chunk-WE3SK5GQ.js";
 import {
   PACKAGE_VERSION
 } from "./chunk-AOJU5LKX.js";
@@ -24,7 +24,7 @@ import {
   isReadOnlyKey,
   restrictedWriteScopes,
   upgradeCaveatFor
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/mcp/server.ts
 import { randomUUID } from "crypto";

package/dist/{chunk-NHF3OGZN.js → chunk-IX7AKQBJ.js}

@@ -3,7 +3,7 @@ import {
   resolveCliAccess,
   resolveCliAccessForInvocation,
   windowOptions
-} from "./chunk-PJYXLC3D.js";
+} from "./chunk-2G3J62KV.js";
 import {
   emitJsonl
 } from "./chunk-Z7IUAJOF.js";
@@ -14,7 +14,7 @@ import {
 } from "./chunk-HGMYEDAQ.js";
 import {
   OperationAccesses
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/cli-catalog.ts
 import { createRequire } from "module";
@@ -111,7 +111,7 @@ async function dispatchRegisteredCommand(args, fallbackFormat, specs) {
     const accessValue = accessFilterFromArgs(argsWithoutHelp);
     validateAccessFilter(accessValue);
     if (fallbackFormat !== "text") {
-      const { printCliCatalog: printCliCatalog2 } = await import("./cli-catalog-ZBTUYNJA.js");
+      const { printCliCatalog: printCliCatalog2 } = await import("./cli-catalog-RYUJEUAY.js");
       const group2 = argsWithoutHelp.find((arg) => !arg.startsWith("--"));
       printCliCatalog2(specs, fallbackFormat, group2, accessValue);
       return true;

package/dist/{chunk-RPYSCFFA.js → chunk-JB4NDUWJ.js}

@@ -1,6 +1,6 @@
 import {
   cloudflareQueueNameSchema
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/cloudflare-traffic-config.ts
 function unsupportedDeliveryMode(deliveryMode) {

package/dist/{chunk-3LTLLHCD.js → chunk-JCECURGF.js}

@@ -2,13 +2,13 @@ import {
   bucketCliCommandDuration,
   isTelemetryEnabled,
   trackEvent
-} from "./chunk-RVEXUQHP.js";
+} from "./chunk-DEMNY4YE.js";
 import {
   getConfigDir
-} from "./chunk-6RI7JFFI.js";
+} from "./chunk-3NOFNFGV.js";
 import {
   currentOutcomeAttribution
-} from "./chunk-KDV5NQZH.js";
+} from "./chunk-U6EUBP4B.js";
 import {
   AGENT_NONE,
   OutcomeSurfaces,
@@ -19,7 +19,7 @@ import {
   integrationConnectionPropertiesSchema,
   normalizeAgentSlug,
   usageSurfaceSchema
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/outcome-telemetry.ts
 import fs from "fs";

package/dist/{chunk-42JQQZZQ.js → chunk-JEC5Z22M.js}

@@ -1,6 +1,6 @@
 import {
   pickProjectCitedDomain
-} from "./chunk-R7RTWOOV.js";
+} from "./chunk-ETMB45WP.js";
 import {
   GBP_INSIGHT_PROVIDER,
   PERSISTENT_GAP_THRESHOLD,
@@ -14,10 +14,10 @@ import {
   mergeGscQueryTotalsWithFallback,
   readGscQueryDailyRows,
   readLatestGscDataDate
-} from "./chunk-JGO7LGVN.js";
+} from "./chunk-SZSJALQM.js";
 import {
   getRequestContext
-} from "./chunk-KDV5NQZH.js";
+} from "./chunk-U6EUBP4B.js";
 import {
   competitors,
   gbpDailyMetrics,
@@ -35,7 +35,7 @@ import {
   queries,
   querySnapshots,
   runs
-} from "./chunk-XOCF2U54.js";
+} from "./chunk-EDQ4V4PJ.js";
 import {
   CitationStates,
   RunKinds,
@@ -45,7 +45,7 @@ import {
   effectiveDomains,
   redactLogString,
   redactLogValue
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/intelligence-service.ts
 import { eq, desc, asc, and, ne, or, inArray, gte, lte, isNull, sql, exists } from "drizzle-orm";

package/dist/{chunk-SSNKQTRX.js → chunk-JHCIMIB5.js}

@@ -1,13 +1,13 @@
 import {
   createApiClient
-} from "./chunk-BGTJTKOJ.js";
+} from "./chunk-T6IV35KG.js";
 import {
   emitJsonl
 } from "./chunk-Z7IUAJOF.js";
 import {
   measurementDraftOperationSchema,
   runMeasurementDraftAction
-} from "./chunk-ULUKHNE4.js";
+} from "./chunk-SNCRERSZ.js";
 import {
   isMachineFormat,
   systemError
@@ -37,7 +37,7 @@ import {
   unattributedAnswersLabel,
   uncheckedSourcesLabel,
   visibilityReportRequestSchema
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // src/commands/measurement-plan.ts
 import crypto from "crypto";

package/dist/{chunk-EIRIZPR6.js → chunk-K4S2T6C5.js}

@@ -1,6 +1,6 @@
 import {
   parseJsonColumn
-} from "./chunk-XOCF2U54.js";
+} from "./chunk-EDQ4V4PJ.js";
 import {
   AI_ENGINE_DOMAINS,
   AI_ENGINE_SELF_DOMAINS,
@@ -26,7 +26,7 @@ import {
   retryAfterDelayMs,
   usageCount,
   withRetry
-} from "./chunk-6JGQT4OH.js";
+} from "./chunk-A3NSYJJL.js";
 
 // ../provider-openai/src/normalize.ts
 import OpenAI from "openai";
@@ -1618,6 +1618,7 @@ function toRawQueryResult3(raw) {
     stopReason: raw.stopReason
   };
 }
+var QUERY_ONLY_PROMPT_TOKEN_LIMIT = 60;
 function readRetrievalStatus(rawResponse) {
   const response = rawResponse;
   if (usageCount(response.usageMetadata?.toolUsePromptTokenCount) > 0) return RetrievalStatuses.used;
@@ -1631,7 +1632,9 @@ function readRetrievalStatus(rawResponse) {
   }
   const parts = candidate.content?.parts;
   const hasAnswer = Array.isArray(parts) && parts.some((part) => !part.thought && typeof part.text === "string" && part.text.trim().length > 0);
-  return candidate.finishReason === FinishReason.STOP && hasAnswer ? RetrievalStatuses["not-used"] : RetrievalStatuses.unknown;
+  if (candidate.finishReason !== FinishReason.STOP || !hasAnswer) return RetrievalStatuses.unknown;
+  const promptTokens = usageCount(response.usageMetadata?.promptTokenCount);
+  return promptTokens > 0 && promptTokens <= QUERY_ONLY_PROMPT_TOKEN_LIMIT ? RetrievalStatuses["not-used"] : RetrievalStatuses.unknown;
 }
 var geminiAdapter = {
   name: "gemini",