@ainyc/canonry 2.14.0 → 2.14.1

package/dist/{chunk-LD7Y4K4G.js → chunk-3T64Y7GR.js}

@@ -39,6 +39,7 @@ import {
   locationContextSchema,
   missingDependency,
   normalizeProjectDomain,
+  normalizeUrlPath,
   notFound,
   notImplemented,
   parseRunError,
@@ -59,7 +60,7 @@ import {
   visibilityStateFromAnswerMentioned,
   windowCutoff,
   wordpressEnvSchema
-} from "./chunk-RNMMN2WI.js";
+} from "./chunk-QTS7VZXN.js";
 import {
   IntelligenceService,
   agentMemory,
@@ -97,7 +98,7 @@ import {
   runs,
   schedules,
   usageCounters
-} from "./chunk-UM6RDSRJ.js";
+} from "./chunk-FV6PY5UE.js";
 
 // src/telemetry.ts
 import crypto from "crypto";
@@ -8661,6 +8662,7 @@ async function ga4Routes(app, opts) {
               projectId: project.id,
               date: row.date,
               landingPage: row.landingPage,
+              landingPageNormalized: normalizeUrlPath(row.landingPage),
               sessions: row.sessions,
               organicSessions: row.organicSessions,
               users: row.users,
@@ -8785,11 +8787,11 @@ async function ga4Routes(app, opts) {
       periodEnd: gaTrafficSummaries.periodEnd
     }).from(gaTrafficSummaries).where(eq19(gaTrafficSummaries.projectId, project.id)).get();
     const rows = app.db.select({
-      landingPage: gaTrafficSnapshots.landingPage,
+      landingPage: sql5`COALESCE(${gaTrafficSnapshots.landingPageNormalized}, ${gaTrafficSnapshots.landingPage})`,
       sessions: sql5`SUM(${gaTrafficSnapshots.sessions})`,
       organicSessions: sql5`SUM(${gaTrafficSnapshots.organicSessions})`,
       users: sql5`SUM(${gaTrafficSnapshots.users})`
-    }).from(gaTrafficSnapshots).where(and8(...snapshotConditions)).groupBy(gaTrafficSnapshots.landingPage).orderBy(sql5`SUM(${gaTrafficSnapshots.sessions}) DESC`).limit(limit).all();
+    }).from(gaTrafficSnapshots).where(and8(...snapshotConditions)).groupBy(sql5`COALESCE(${gaTrafficSnapshots.landingPageNormalized}, ${gaTrafficSnapshots.landingPage})`).orderBy(sql5`SUM(${gaTrafficSnapshots.sessions}) DESC`).limit(limit).all();
     const aiReferrals = app.db.select({
       source: gaAiReferrals.source,
       medium: gaAiReferrals.medium,
@@ -9046,11 +9048,11 @@ async function ga4Routes(app, opts) {
     const project = resolveProject(app.db, request.params.name);
     requireGa4Connection(opts, project.name, project.canonicalDomain);
     const trafficPages = app.db.select({
-      landingPage: gaTrafficSnapshots.landingPage,
+      landingPage: sql5`COALESCE(${gaTrafficSnapshots.landingPageNormalized}, ${gaTrafficSnapshots.landingPage})`,
       sessions: sql5`SUM(${gaTrafficSnapshots.sessions})`,
       organicSessions: sql5`SUM(${gaTrafficSnapshots.organicSessions})`,
       users: sql5`SUM(${gaTrafficSnapshots.users})`
-    }).from(gaTrafficSnapshots).where(eq19(gaTrafficSnapshots.projectId, project.id)).groupBy(gaTrafficSnapshots.landingPage).orderBy(sql5`SUM(${gaTrafficSnapshots.sessions}) DESC`).all();
+    }).from(gaTrafficSnapshots).where(eq19(gaTrafficSnapshots.projectId, project.id)).groupBy(sql5`COALESCE(${gaTrafficSnapshots.landingPageNormalized}, ${gaTrafficSnapshots.landingPage})`).orderBy(sql5`SUM(${gaTrafficSnapshots.sessions}) DESC`).all();
     return {
       pages: trafficPages.map((r) => ({
         landingPage: r.landingPage,

package/dist/{chunk-UM6RDSRJ.js → chunk-FV6PY5UE.js}

@@ -310,6 +310,14 @@ var gaTrafficSnapshots = sqliteTable("ga_traffic_snapshots", {
   projectId: text("project_id").notNull().references(() => projects.id, { onDelete: "cascade" }),
   date: text("date").notNull(),
   landingPage: text("landing_page").notNull(),
+  /**
+   * Canonicalized form of `landingPage` produced by `normalizeUrlPath()` in
+   * `@ainyc/canonry-contracts`. Nullable so existing rows survive migration;
+   * new GA4 sync writes populate it. Per-page aggregations should
+   * `GROUP BY COALESCE(landing_page_normalized, landing_page)` so
+   * partially-backfilled state still aggregates correctly.
+   */
+  landingPageNormalized: text("landing_page_normalized"),
   sessions: integer("sessions").notNull().default(0),
   organicSessions: integer("organic_sessions").notNull().default(0),
   users: integer("users").notNull().default(0),
@@ -318,6 +326,7 @@ var gaTrafficSnapshots = sqliteTable("ga_traffic_snapshots", {
 }, (table) => [
   index("idx_ga_traffic_project_date").on(table.projectId, table.date),
   index("idx_ga_traffic_page").on(table.landingPage),
+  index("idx_ga_traffic_page_normalized").on(table.projectId, table.date, table.landingPageNormalized),
   index("idx_ga_traffic_run").on(table.syncRunId)
 ]);
 var gaAiReferrals = sqliteTable("ga_ai_referrals", {
@@ -1049,7 +1058,17 @@ var MIGRATIONS = [
      WHEN discovery_date IS NOT NULL THEN 0
      ELSE NULL
    END
-   WHERE created_at < '2026-04-22T00:00:00Z'`
+   WHERE created_at < '2026-04-22T00:00:00Z'`,
+  // v44: Canonicalized landing-page column for ga_traffic_snapshots.
+  // Populated by GA4 sync via normalizeUrlPath() in
+  // @ainyc/canonry-contracts. Nullable; existing rows are filled in by
+  // `canonry backfill normalized-paths`. Read queries should
+  // `GROUP BY COALESCE(landing_page_normalized, landing_page)` so
+  // partially-backfilled state still aggregates correctly.
+  // See plans/ai-attribution-research.md "Step 1 — data hygiene".
+  `ALTER TABLE ga_traffic_snapshots ADD COLUMN landing_page_normalized TEXT`,
+  `CREATE INDEX IF NOT EXISTS idx_ga_traffic_page_normalized
+     ON ga_traffic_snapshots(project_id, date, landing_page_normalized)`
 ];
 function isDuplicateColumnError(err) {
   if (!(err instanceof Error)) return false;

package/dist/{chunk-RNMMN2WI.js → chunk-QTS7VZXN.js}

@@ -1790,6 +1790,97 @@ function summarizeCheckResults(results) {
   return summary;
 }
 
+// ../contracts/src/url-normalize.ts
+var STRIP_KEYS = /* @__PURE__ */ new Set([
+  // Click identifiers
+  "fbclid",
+  "gclid",
+  "msclkid",
+  "ttclid",
+  "li_fat_id",
+  "igshid",
+  "yclid",
+  "dclid",
+  "gbraid",
+  "wbraid",
+  // Mailchimp
+  "mc_cid",
+  "mc_eid",
+  // Google Analytics linkers
+  "_ga",
+  "_gl",
+  // Google Tag Manager debug
+  "gtm_latency",
+  "gtm_debug"
+]);
+function shouldStrip(key) {
+  if (STRIP_KEYS.has(key)) return true;
+  if (key.startsWith("utm_")) return true;
+  return false;
+}
+function parseQuery(query) {
+  if (query === "") return [];
+  return query.split("&").map((pair) => {
+    const eq = pair.indexOf("=");
+    if (eq === -1) return { key: pair, value: null };
+    return { key: pair.slice(0, eq), value: pair.slice(eq + 1) };
+  });
+}
+function encodeQuery(pairs) {
+  return pairs.map((p) => p.value === null ? p.key : `${p.key}=${p.value}`).join("&");
+}
+function collapseRootIndex(path2) {
+  if (path2 === "/index.html" || path2 === "/index.php") return "/";
+  return path2;
+}
+function dropTrailingSlash(path2) {
+  if (path2.length > 1 && path2.endsWith("/")) {
+    return path2.replace(/\/+$/, "");
+  }
+  return path2;
+}
+function normalizeUrlPath(input) {
+  if (input == null) return null;
+  const trimmed = input.trim();
+  if (trimmed === "") return null;
+  if (trimmed === "(not set)") return null;
+  let pathPart;
+  let queryPart;
+  if (/^https?:\/\//i.test(trimmed)) {
+    let url;
+    try {
+      url = new URL(trimmed);
+    } catch {
+      return null;
+    }
+    pathPart = url.pathname || "/";
+    queryPart = url.search.startsWith("?") ? url.search.slice(1) : url.search;
+  } else {
+    let raw = trimmed;
+    const hashIdx = raw.indexOf("#");
+    if (hashIdx !== -1) raw = raw.slice(0, hashIdx);
+    const qIdx = raw.indexOf("?");
+    if (qIdx === -1) {
+      pathPart = raw;
+      queryPart = "";
+    } else {
+      pathPart = raw.slice(0, qIdx);
+      queryPart = raw.slice(qIdx + 1);
+    }
+  }
+  if (pathPart === "") pathPart = "/";
+  pathPart = collapseRootIndex(pathPart);
+  pathPart = dropTrailingSlash(pathPart);
+  const pairs = parseQuery(queryPart).filter((p) => !shouldStrip(p.key));
+  pairs.sort((a, b) => {
+    if (a.key < b.key) return -1;
+    if (a.key > b.key) return 1;
+    return 0;
+  });
+  if (pairs.length === 0) return pathPart;
+  return `${pathPart}?${encodeQuery(pairs)}`;
+}
+
 // src/client.ts
 function createApiClient() {
   const config = loadConfig();
@@ -2522,6 +2613,7 @@ export {
   CheckScopes,
   CheckCategories,
   summarizeCheckResults,
+  normalizeUrlPath,
   createApiClient,
   ApiClient
 };

package/dist/cli.js

@@ -17,7 +17,7 @@ import {
   setGoogleAuthConfig,
   showFirstRunNotice,
   trackEvent
-} from "./chunk-LD7Y4K4G.js";
+} from "./chunk-3T64Y7GR.js";
 import {
   CcReleaseSyncStatuses,
   CheckScopes,
@@ -37,6 +37,7 @@ import {
   getConfigPath,
   isEndpointMissing,
   loadConfig,
+  normalizeUrlPath,
   notificationEventSchema,
   printCliError,
   providerQuotaPolicySchema,
@@ -44,17 +45,18 @@ import {
   saveConfig,
   saveConfigPatch,
   usageError
-} from "./chunk-RNMMN2WI.js";
+} from "./chunk-QTS7VZXN.js";
 import {
   apiKeys,
   competitors,
   createClient,
+  gaTrafficSnapshots,
   migrate,
   parseJsonColumn,
   projects,
   querySnapshots,
   runs
-} from "./chunk-UM6RDSRJ.js";
+} from "./chunk-FV6PY5UE.js";
 import "./chunk-MLKGABMK.js";
 
 // src/cli.ts
@@ -160,7 +162,7 @@ Usage: ${spec.usage}`, {
 }
 
 // src/commands/backfill.ts
-import { and, eq, inArray } from "drizzle-orm";
+import { and, eq, inArray, isNull } from "drizzle-orm";
 var SNAPSHOT_BATCH_SIZE = 500;
 async function backfillAnswerVisibilityCommand(opts) {
   const config = loadConfig();
@@ -301,8 +303,75 @@ async function backfillAnswerVisibilityCommand(opts) {
   console.log(`  Reparsed: ${reparsed}`);
   console.log(`  Errors:   ${providerErrors}`);
 }
+function backfillNormalizedPaths(db, opts) {
+  const baseConditions = [isNull(gaTrafficSnapshots.landingPageNormalized)];
+  if (opts?.projectId) {
+    baseConditions.push(eq(gaTrafficSnapshots.projectId, opts.projectId));
+  }
+  const rows = db.select({
+    id: gaTrafficSnapshots.id,
+    landingPage: gaTrafficSnapshots.landingPage
+  }).from(gaTrafficSnapshots).where(and(...baseConditions)).all();
+  let updated = 0;
+  let unchanged = 0;
+  if (rows.length > 0) {
+    db.transaction((tx) => {
+      for (const row of rows) {
+        const next = normalizeUrlPath(row.landingPage);
+        if (next === null) {
+          unchanged++;
+          continue;
+        }
+        tx.update(gaTrafficSnapshots).set({ landingPageNormalized: next }).where(eq(gaTrafficSnapshots.id, row.id)).run();
+        updated++;
+      }
+    });
+  }
+  return { examined: rows.length, updated, unchanged };
+}
+async function backfillNormalizedPathsCommand(opts) {
+  const config = loadConfig();
+  const db = createClient(config.database);
+  migrate(db);
+  const projectFilter = opts?.project?.trim();
+  let projectId;
+  if (projectFilter) {
+    const project = db.select({ id: projects.id }).from(projects).where(eq(projects.name, projectFilter)).get();
+    if (!project) {
+      const result2 = {
+        project: projectFilter,
+        examined: 0,
+        updated: 0,
+        unchanged: 0
+      };
+      if (opts?.format === "json") {
+        console.log(JSON.stringify(result2, null, 2));
+        return;
+      }
+      console.log(`Backfill normalized-paths: project "${projectFilter}" not found.`);
+      return;
+    }
+    projectId = project.id;
+  }
+  const { examined, updated, unchanged } = backfillNormalizedPaths(db, { projectId });
+  const result = {
+    project: projectFilter ?? null,
+    examined,
+    updated,
+    unchanged
+  };
+  if (opts?.format === "json") {
+    console.log(JSON.stringify(result, null, 2));
+    return;
+  }
+  console.log("Normalized-path backfill complete.\n");
+  if (projectFilter) console.log(`  Project:   ${projectFilter}`);
+  console.log(`  Examined:  ${examined}`);
+  console.log(`  Updated:   ${updated}`);
+  console.log(`  Unchanged: ${unchanged}`);
+}
 async function backfillInsightsCommand(project, opts) {
-  const { IntelligenceService } = await import("./intelligence-service-54F3NGPM.js");
+  const { IntelligenceService } = await import("./intelligence-service-AEI46KC5.js");
   const config = loadConfig();
   const db = createClient(config.database);
   migrate(db);
@@ -498,14 +567,28 @@ var BACKFILL_CLI_COMMANDS = [
       });
     }
   },
+  {
+    path: ["backfill", "normalized-paths"],
+    usage: "canonry backfill normalized-paths [--project <name>] [--format json]",
+    options: {
+      project: stringOption()
+    },
+    allowPositionals: false,
+    run: async (input) => {
+      await backfillNormalizedPathsCommand({
+        project: getString(input.values, "project"),
+        format: input.format
+      });
+    }
+  },
   {
     path: ["backfill"],
-    usage: "canonry backfill <answer-visibility|insights> [options]",
+    usage: "canonry backfill <answer-visibility|insights|normalized-paths> [options]",
     run: async (input) => {
       unknownSubcommand(input.positionals[0], {
         command: "backfill",
-        usage: "canonry backfill <answer-visibility|insights> [options]",
-        available: ["answer-visibility", "insights"]
+        usage: "canonry backfill <answer-visibility|insights|normalized-paths> [options]",
+        available: ["answer-visibility", "insights", "normalized-paths"]
       });
     }
   }
@@ -7072,6 +7155,18 @@ async function serveCommand(format = "text") {
   config.port = port;
   const db = createClient(config.database);
   migrate(db);
+  try {
+    const result = backfillNormalizedPaths(db);
+    if (result.updated > 0 && format === "text") {
+      console.log(
+        `Migrated ${result.updated} GA landing-page row${result.updated === 1 ? "" : "s"} to canonical form.`
+      );
+    }
+  } catch (err) {
+    const msg = err instanceof Error ? err.message : String(err);
+    process.stderr.write(`warning: normalized-path backfill skipped: ${msg}
+`);
+  }
   const app = await createServer({ config, db });
   let shuttingDown = false;
   const shutdown = (signal) => {

package/dist/index.js

@@ -1,10 +1,10 @@
 import {
   createServer
-} from "./chunk-LD7Y4K4G.js";
+} from "./chunk-3T64Y7GR.js";
 import {
   loadConfig
-} from "./chunk-RNMMN2WI.js";
-import "./chunk-UM6RDSRJ.js";
+} from "./chunk-QTS7VZXN.js";
+import "./chunk-FV6PY5UE.js";
 import "./chunk-MLKGABMK.js";
 export {
   createServer,

package/dist/{intelligence-service-54F3NGPM.js → intelligence-service-AEI46KC5.js}

@@ -1,6 +1,6 @@
 import {
   IntelligenceService
-} from "./chunk-UM6RDSRJ.js";
+} from "./chunk-FV6PY5UE.js";
 import "./chunk-MLKGABMK.js";
 export {
   IntelligenceService

package/dist/mcp.js

@@ -10,7 +10,7 @@ import {
   projectUpsertRequestSchema,
   runTriggerRequestSchema,
   scheduleUpsertRequestSchema
-} from "./chunk-RNMMN2WI.js";
+} from "./chunk-QTS7VZXN.js";
 import "./chunk-MLKGABMK.js";
 
 // src/mcp/cli.ts

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ainyc/canonry",
-  "version": "2.14.0",
+  "version": "2.14.1",
   "type": "module",
   "description": "Agent-first open-source AEO operating platform - track how answer engines cite your domain",
   "license": "FSL-1.1-ALv2",
@@ -63,17 +63,17 @@
     "@ainyc/canonry-api-routes": "0.0.0",
     "@ainyc/canonry-contracts": "0.0.0",
     "@ainyc/canonry-db": "0.0.0",
-    "@ainyc/canonry-intelligence": "0.0.0",
     "@ainyc/canonry-integration-bing": "0.0.0",
     "@ainyc/canonry-integration-commoncrawl": "0.0.0",
+    "@ainyc/canonry-intelligence": "0.0.0",
     "@ainyc/canonry-integration-google": "0.0.0",
-    "@ainyc/canonry-integration-wordpress": "0.0.0",
     "@ainyc/canonry-provider-cdp": "0.0.0",
     "@ainyc/canonry-provider-claude": "0.0.0",
     "@ainyc/canonry-provider-gemini": "0.0.0",
+    "@ainyc/canonry-integration-wordpress": "0.0.0",
     "@ainyc/canonry-provider-local": "0.0.0",
-    "@ainyc/canonry-provider-perplexity": "0.0.0",
-    "@ainyc/canonry-provider-openai": "0.0.0"
+    "@ainyc/canonry-provider-openai": "0.0.0",
+    "@ainyc/canonry-provider-perplexity": "0.0.0"
   },
   "scripts": {
     "build": "tsx scripts/copy-agent-assets.ts && tsup && tsx build-web.ts",