mcp-scraper 0.73.0 → 0.73.1

package/CHANGELOG.md

@@ -4,6 +4,13 @@ All notable changes to MCP Scraper are documented here. The format is based on [
 
 ## [Unreleased]
 
+## [0.73.1] - 2026-08-28
+
+### Fixed
+
+- Applied additive, idempotent X-Ray schema changes as individually committed statements so production reads cannot deadlock against a release-long DDL transaction and an interrupted migration can resume safely.
+- Reused the earliest confirmed person when a verified email, phone, account ID, or order identity already belongs to the Site graph, preventing a normalized account ID from splitting a legacy email-keyed journey.
+
 ## [0.73.0] - 2026-08-27
 
 ### Added
@@ -27,6 +34,7 @@ All notable changes to MCP Scraper are documented here. The format is based on [
 - Prevented cross-Site identity, privacy, and Journey references; removed subject-specific export/provider payload remnants on withdrawal or deletion; and normalized unknown/deleted references to zero-discovery responses.
 - Normalized PostgreSQL timestamp projections and reconciled consent-withdrawal responses with the strict public REST contract.
 - Made consented login and first-party form resolution self-initialize an approved Site-scoped primary identity graph, so older Sites persist stable person references and masked profiles without manual namespace setup.
+- Retried the authenticated browser identity handoff during the bounded Pixel/consent bootstrap window, preventing a consent-readiness race from leaving a signed-in visitor anonymous for the rest of the page.
 
 ## [0.72.7] - 2026-08-27
 
@@ -1308,7 +1316,8 @@ All notable changes to MCP Scraper are documented here. The format is based on [
 - Write actions remain unavailable until the account owner explicitly enables them.
 - Provider-specific connection data is normalized into one agent-facing contract.
 
-[Unreleased]: https://github.com/VilovietaSEO/mcp-scraper/compare/v0.73.0...HEAD
+[Unreleased]: https://github.com/VilovietaSEO/mcp-scraper/compare/v0.73.1...HEAD
+[0.73.1]: https://github.com/VilovietaSEO/mcp-scraper/compare/v0.73.0...v0.73.1
 [0.73.0]: https://github.com/VilovietaSEO/mcp-scraper/compare/v0.72.7...v0.73.0
 [0.72.7]: https://github.com/VilovietaSEO/mcp-scraper/compare/v0.72.6...v0.72.7
 [0.72.6]: https://github.com/VilovietaSEO/mcp-scraper/compare/v0.72.5...v0.72.6

package/README.md

@@ -173,7 +173,7 @@ Build the branded one-click bundle:
 npm run build:mcpb
 ```
 
-The generated bundle is written to `build/mcpb/mcp-scraper-<version>.mcpb` and copied to `public/downloads/` for the hosted download. The current public bundle is `https://mcpscraper.dev/downloads/mcp-scraper.mcpb` (`0.73.0`, SHA-256 `570d31a9b16833b89de8ea5296e5d97b3d4696336c94651739b716a0bda81ce6`). Install it by opening or dragging it into Claude Desktop. Claude displays the `MCP Scraper` install card, icon, API-key configuration field, and manually curated current-release message from the bundle manifest.
+The generated bundle is written to `build/mcpb/mcp-scraper-<version>.mcpb` and copied to `public/downloads/` for the hosted download. The current public bundle is `https://mcpscraper.dev/downloads/mcp-scraper.mcpb` (`0.73.1`, SHA-256 `6d28c003fa95efba8867529ea8b9546e1213bbbe0575f03342b8bbe054535550`). Install it by opening or dragging it into Claude Desktop. Claude displays the `MCP Scraper` install card, icon, API-key configuration field, and manually curated current-release message from the bundle manifest.
 
 The MCPB install exposes every tool — web-intelligence plus all `browser_*` tools — through the one `mcp-scraper` server.
 

package/dist/{analytics-repository-MSLJBHLU.js → analytics-repository-7XYPQ2YJ.js}

@@ -84,7 +84,7 @@ import {
   updateAnalyticsPixel,
   upsertAnalyticsAdSpend,
   upsertAnalyticsHostGroup
-} from "./chunk-5EWXRBEH.js";
+} from "./chunk-M6XDENOO.js";
 import "./chunk-PJEEKOUM.js";
 import "./chunk-WEFPBAAG.js";
 export {

package/dist/bin/api-server.js

@@ -17,7 +17,7 @@ loadDotEnv();
 async function main() {
   const [{ serve }, { app }, { startWorker }, { migrate }] = await Promise.all([
     import("@hono/node-server"),
-    import("../server-N6MCRSQW.js"),
+    import("../server-663CRTGY.js"),
     import("../worker-CBK5DWEE.js"),
     import("../db-566MOHHD.js")
   ]);
@@ -25,7 +25,7 @@ async function main() {
   try {
     await migrate();
     if (process.env.ANALYTICS_DATABASE_URL) {
-      const { migrateAnalytics } = await import("../analytics-repository-MSLJBHLU.js");
+      const { migrateAnalytics } = await import("../analytics-repository-7XYPQ2YJ.js");
       await migrateAnalytics();
     }
     startWorker();

package/dist/bin/mcp-scraper-cli.js

@@ -13,7 +13,7 @@ import "../chunk-VXLU74YZ.js";
 import "../chunk-GGZEC22A.js";
 import {
   PACKAGE_VERSION
-} from "../chunk-JIWGG7Z4.js";
+} from "../chunk-NLPFY2IF.js";
 
 // src/cli/human-cli.ts
 import { Command } from "commander";

package/dist/bin/mcp-scraper-install.js

@@ -4,7 +4,7 @@ import {
 } from "../chunk-Q2J23DHY.js";
 import {
   PACKAGE_VERSION
-} from "../chunk-JIWGG7Z4.js";
+} from "../chunk-NLPFY2IF.js";
 
 // bin/mcp-scraper-install.ts
 var noColor = process.argv.includes("--no-color") || process.env.NO_COLOR !== void 0 || process.env.FORCE_COLOR === "0" || !process.stdout.isTTY;

package/dist/bin/mcp-stdio-server.js

@@ -13,7 +13,7 @@ import {
   registerScheduledResultsMcpTools,
   registerSerpIntelligenceCaptureTools,
   resolveDeploymentProfile
-} from "../chunk-KRIIVDV2.js";
+} from "../chunk-G75QXTBE.js";
 import "../chunk-PGJQDMC2.js";
 import "../chunk-T3MZISOF.js";
 import "../chunk-7RQULQF3.js";
@@ -26,7 +26,7 @@ import "../chunk-VXLU74YZ.js";
 import "../chunk-GGZEC22A.js";
 import {
   PACKAGE_VERSION
-} from "../chunk-JIWGG7Z4.js";
+} from "../chunk-NLPFY2IF.js";
 import "../chunk-DNM65UCK.js";
 import "../chunk-EQJRPDUS.js";
 import "../chunk-WEFPBAAG.js";

package/dist/{chunk-KRIIVDV2.js → chunk-G75QXTBE.js}

@@ -32,7 +32,7 @@ import {
 } from "./chunk-VXLU74YZ.js";
 import {
   PACKAGE_VERSION
-} from "./chunk-JIWGG7Z4.js";
+} from "./chunk-NLPFY2IF.js";
 import {
   createPrivateArtifact,
   privateArtifactOwnerId,

package/dist/{chunk-5EWXRBEH.js → chunk-M6XDENOO.js}

@@ -860,7 +860,6 @@ async function closeAnalyticsPool() {
 async function migrateAnalytics() {
   const db = getAnalyticsPool();
   const client = await db.connect();
-  await client.query("BEGIN");
   try {
     await client.query(`
       CREATE TABLE IF NOT EXISTS analytics_schema_migrations (
@@ -2607,9 +2606,7 @@ async function migrateAnalytics() {
       VALUES ('2026-08-05.1'), ('2026-08-05.2'), ('2026-08-05.3'), ('2026-08-05.4'), ('2026-08-05.5'), ('2026-08-05.6'), ('2026-08-05.7'), ('2026-08-05.8'), ('2026-08-05.9'), ('2026-08-05.10'), ('2026-08-05.11'), ('2026-08-05.12'), ('2026-08-05.13'), ('2026-08-05.14'), ('2026-08-26.1'), ('2026-08-26.2'), ('2026-08-26.3'), ('2026-08-26.4'), ('2026-08-27.1')
       ON CONFLICT (version) DO NOTHING
     `);
-    await client.query("COMMIT");
   } catch (error) {
-    await client.query("ROLLBACK");
     throw error;
   } finally {
     client.release();
@@ -4903,6 +4900,140 @@ async function backfillAnalyticsConfirmedHistory(client, input) {
     conversions: conversions.rowCount ?? 0
   };
 }
+async function resolveAndMergeConfirmedAnalyticsPerson(client, input) {
+  const matches = await client.query(
+    `SELECT p.id
+       FROM analytics_people p
+       JOIN (
+         SELECT DISTINCT e.person_id
+           FROM analytics_identity_nodes n
+           JOIN analytics_identity_edges e ON e.identity_node_id=n.id AND e.site_id=n.site_id
+          WHERE n.site_id=$1 AND EXISTS (
+            SELECT 1 FROM jsonb_to_recordset($2::jsonb) signal(kind text,value_hmac text)
+             WHERE signal.kind=n.kind AND signal.value_hmac=n.value_hmac
+          )
+       ) matched ON matched.person_id=p.id
+      WHERE p.site_id=$1 AND (p.namespace_id=$3 OR p.namespace_id IS NULL)
+      ORDER BY p.first_seen_at ASC,p.id ASC
+      FOR UPDATE OF p`,
+    [
+      input.siteId,
+      JSON.stringify(input.signals.map((signal) => ({ kind: signal.kind, value_hmac: signal.valueHmac }))),
+      input.namespaceId
+    ]
+  );
+  const canonicalId = matches.rows[0]?.id;
+  if (!canonicalId) {
+    const inserted = await client.query(
+      `INSERT INTO analytics_people(id, site_id, namespace_id, crm_person_ref, public_ref) VALUES ($1,$2,$3,$4,$5)
+       ON CONFLICT(site_id, crm_person_ref) DO UPDATE SET last_seen_at = now(),
+         namespace_id=COALESCE(analytics_people.namespace_id,EXCLUDED.namespace_id),
+         public_ref=COALESCE(analytics_people.public_ref,EXCLUDED.public_ref) RETURNING id`,
+      [randomUUID2(), input.siteId, input.namespaceId, input.crmPersonRef, newAnalyticsPersonPublicRef()]
+    );
+    return inserted.rows[0].id;
+  }
+  await client.query(
+    `UPDATE analytics_people SET last_seen_at=now(),
+       namespace_id=COALESCE(namespace_id,$2),public_ref=COALESCE(public_ref,$3)
+      WHERE id=$1 AND site_id=$4`,
+    [canonicalId, input.namespaceId, newAnalyticsPersonPublicRef(), input.siteId]
+  );
+  const duplicateIds = matches.rows.slice(1).map((row) => row.id);
+  if (duplicateIds.length === 0) return canonicalId;
+  await client.query(
+    `DELETE FROM analytics_identity_edges duplicate
+      USING analytics_identity_edges canonical
+      WHERE duplicate.site_id=$1 AND duplicate.person_id=ANY($2::uuid[])
+        AND canonical.site_id=duplicate.site_id AND canonical.person_id=$3
+        AND canonical.identity_node_id=duplicate.identity_node_id
+        AND canonical.evidence_kind=duplicate.evidence_kind`,
+    [input.siteId, duplicateIds, canonicalId]
+  );
+  await client.query(
+    `UPDATE analytics_identity_edges SET person_id=$3,namespace_id=$4
+      WHERE site_id=$1 AND person_id=ANY($2::uuid[])`,
+    [input.siteId, duplicateIds, canonicalId, input.namespaceId]
+  );
+  for (const table of [
+    "analytics_form_submissions",
+    "analytics_events",
+    "analytics_conversions",
+    "analytics_sessions",
+    "analytics_attribution_touches",
+    "analytics_external_events",
+    "analytics_restricted_data",
+    "analytics_crm_outbound_jobs"
+  ]) {
+    await client.query(
+      `UPDATE ${table} SET person_id=$3 WHERE site_id=$1 AND person_id=ANY($2::uuid[])`,
+      [input.siteId, duplicateIds, canonicalId]
+    );
+  }
+  await client.query(
+    "UPDATE analytics_activation_jobs SET person_id=$2 WHERE person_id=ANY($1::uuid[])",
+    [duplicateIds, canonicalId]
+  );
+  await client.query(
+    `UPDATE analytics_candidate_associations SET promoted_person_id=$3,namespace_id=$4
+      WHERE site_id=$1 AND promoted_person_id=ANY($2::uuid[])`,
+    [input.siteId, duplicateIds, canonicalId, input.namespaceId]
+  );
+  await client.query(
+    `DELETE FROM analytics_candidate_promotions duplicate
+      USING analytics_candidate_promotions canonical
+      WHERE duplicate.site_id=$1 AND duplicate.person_id=ANY($2::uuid[])
+        AND canonical.site_id=duplicate.site_id AND canonical.person_id=$3
+        AND canonical.association_id=duplicate.association_id`,
+    [input.siteId, duplicateIds, canonicalId]
+  );
+  await client.query(
+    `UPDATE analytics_candidate_promotions SET person_id=$3,namespace_id=$4
+      WHERE site_id=$1 AND person_id=ANY($2::uuid[])`,
+    [input.siteId, duplicateIds, canonicalId, input.namespaceId]
+  );
+  await client.query(
+    `DELETE FROM analytics_crm_person_mappings duplicate
+      USING analytics_crm_person_mappings canonical
+      WHERE duplicate.site_id=$1 AND duplicate.person_id=ANY($2::uuid[])
+        AND canonical.site_id=duplicate.site_id AND canonical.person_id=$3
+        AND canonical.connection_id=duplicate.connection_id`,
+    [input.siteId, duplicateIds, canonicalId]
+  );
+  await client.query(
+    `UPDATE analytics_crm_person_mappings SET person_id=$3,namespace_id=$4
+      WHERE site_id=$1 AND person_id=ANY($2::uuid[])`,
+    [input.siteId, duplicateIds, canonicalId, input.namespaceId]
+  );
+  await client.query(
+    `DELETE FROM analytics_prediction_results duplicate
+      USING analytics_prediction_results canonical
+      WHERE duplicate.site_id=$1 AND duplicate.person_id=ANY($2::uuid[])
+        AND canonical.site_id=duplicate.site_id AND canonical.person_id=$3
+        AND canonical.manifest_id=duplicate.manifest_id`,
+    [input.siteId, duplicateIds, canonicalId]
+  );
+  for (const table of ["analytics_score_evaluations", "analytics_prediction_results"]) {
+    await client.query(
+      `UPDATE ${table} SET person_id=$3,namespace_id=$4
+        WHERE site_id=$1 AND person_id=ANY($2::uuid[])`,
+      [input.siteId, duplicateIds, canonicalId, input.namespaceId]
+    );
+  }
+  await client.query(
+    "UPDATE analytics_identity_profile_access_audits SET person_id=$3 WHERE site_id=$1 AND person_id=ANY($2::uuid[])",
+    [input.siteId, duplicateIds, canonicalId]
+  );
+  await client.query(
+    "UPDATE analytics_identity_tombstones SET person_id=$3 WHERE site_id=$1 AND person_id=ANY($2::uuid[])",
+    [input.siteId, duplicateIds, canonicalId]
+  );
+  await client.query(
+    "DELETE FROM analytics_people WHERE site_id=$1 AND id=ANY($2::uuid[])",
+    [input.siteId, duplicateIds]
+  );
+  return canonicalId;
+}
 async function linkAnalyticsIdentityInTransaction(client, input) {
   const stable = input.customerId || input.orderId || input.email || input.phone;
   if (!stable) return null;
@@ -4924,14 +5055,12 @@ async function linkAnalyticsIdentityInTransaction(client, input) {
     signals: tombstoneSignals
   });
   const crmPersonRef = `XRay::${identityHmac("person_ref", stable).slice(0, 24)}`;
-  const person = await client.query(
-    `INSERT INTO analytics_people(id, site_id, namespace_id, crm_person_ref, public_ref) VALUES ($1,$2,$3,$4,$5)
-     ON CONFLICT(site_id, crm_person_ref) DO UPDATE SET last_seen_at = now(),
-       namespace_id=COALESCE(analytics_people.namespace_id,EXCLUDED.namespace_id),
-       public_ref=COALESCE(analytics_people.public_ref,EXCLUDED.public_ref) RETURNING id`,
-    [randomUUID2(), input.siteId, namespaceId, crmPersonRef, newAnalyticsPersonPublicRef()]
-  );
-  const personId = person.rows[0].id;
+  const personId = await resolveAndMergeConfirmedAnalyticsPerson(client, {
+    siteId: input.siteId,
+    namespaceId,
+    crmPersonRef,
+    signals: tombstoneSignals
+  });
   const signals = [];
   if (input.visitorId)
     signals.push({ kind: "visitor_id", value: input.visitorId, evidence: "pixel_identify", confidence: 0.98 });
@@ -4995,21 +5124,20 @@ async function linkAnalyticsFormIdentity(input) {
       return { personId: null, linkedSignals: 0 };
     }
     const namespaceId = await ensurePrimaryAnalyticsIdentityNamespace(client, input.siteId, "form");
+    const deterministicSignals = [
+      ...input.email ? [{ kind: "email", valueHmac: identityHmac("email", input.email) }] : [],
+      ...input.phone ? [{ kind: "phone", valueHmac: identityHmac("phone", input.phone) }] : []
+    ];
     await assertAnalyticsIdentitySignalsNotTombstoned(client, {
       siteId: input.siteId,
-      signals: [
-        ...input.email ? [{ kind: "email", valueHmac: identityHmac("email", input.email) }] : [],
-        ...input.phone ? [{ kind: "phone", valueHmac: identityHmac("phone", input.phone) }] : []
-      ]
+      signals: deterministicSignals
+    });
+    const personId = await resolveAndMergeConfirmedAnalyticsPerson(client, {
+      siteId: input.siteId,
+      namespaceId,
+      crmPersonRef: input.crmPersonRef,
+      signals: deterministicSignals
     });
-    const person = await client.query(
-      `INSERT INTO analytics_people(id, site_id, namespace_id, crm_person_ref, public_ref) VALUES ($1,$2,$3,$4,$5)
-       ON CONFLICT(site_id, crm_person_ref) DO UPDATE SET last_seen_at = now(),
-         namespace_id=COALESCE(analytics_people.namespace_id,EXCLUDED.namespace_id),
-         public_ref=COALESCE(analytics_people.public_ref,EXCLUDED.public_ref) RETURNING id`,
-      [randomUUID2(), input.siteId, namespaceId, input.crmPersonRef, newAnalyticsPersonPublicRef()]
-    );
-    const personId = person.rows[0].id;
     const signals = [];
     if (input.visitorId)
       signals.push({

package/dist/{chunk-JIWGG7Z4.js → chunk-NLPFY2IF.js}

@@ -1,5 +1,5 @@
 // src/version.ts
-var PACKAGE_VERSION = "0.73.0";
+var PACKAGE_VERSION = "0.73.1";
 
 export {
   PACKAGE_VERSION

package/dist/{server-N6MCRSQW.js → server-663CRTGY.js}

@@ -153,7 +153,7 @@ import {
   upsertAnalyticsAdSpend,
   upsertAnalyticsHostGroup,
   verifyAnalyticsWebhookSignature
-} from "./chunk-5EWXRBEH.js";
+} from "./chunk-M6XDENOO.js";
 import {
   claimServiceConnectionAction,
   ensureServiceConnectionsSchema,
@@ -280,7 +280,7 @@ import {
   resolveDeploymentProfile,
   resolveLocalSourcebookSchemaType,
   transcribeMediaUrl
-} from "./chunk-KRIIVDV2.js";
+} from "./chunk-G75QXTBE.js";
 import {
   auditImageUrls,
   auditImages,
@@ -345,7 +345,7 @@ import {
 } from "./chunk-GGZEC22A.js";
 import {
   PACKAGE_VERSION
-} from "./chunk-JIWGG7Z4.js";
+} from "./chunk-NLPFY2IF.js";
 import {
   SITE_EXTRACT_ARTIFACT_PREFIX,
   abandonExtractSettlement,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mcp-scraper",
-  "version": "0.73.0",
+  "version": "0.73.1",
   "description": "MCP server for MCP Scraper web intelligence tools",
   "type": "module",
   "main": "./dist/index.cjs",