mcp-scraper 0.66.7 → 0.67.0

package/dist/{server-KSVJ4X4V.js → server-MFVYRB6I.js}

@@ -10,13 +10,13 @@ import {
   queuedCommonsDocumentCount,
   semanticCommonsEntityScores,
   typeFromMime
-} from "./chunk-EVOBJYBE.js";
+} from "./chunk-LN6N3YLK.js";
 import {
   REQUIRED_LOCATION_STATE_CODES,
   importHostedCensusPlacesCsv,
   importHostedZipGroupsCsv,
   listActiveHostedLocationDatasets
-} from "./chunk-HBZENASD.js";
+} from "./chunk-Y46YNQMM.js";
 import {
   cancelPendingLeadListEnrichmentRows,
   claimLeadListEnrichmentOutbox,
@@ -43,7 +43,7 @@ import {
   saveLeadListEnrichmentRowResult,
   setInitializingLeadListEnrichmentConcurrencyLock,
   stableCanonicalJson
-} from "./chunk-JZPSG4NR.js";
+} from "./chunk-UL4ZKAWZ.js";
 import {
   ANALYTICS_CONTENT_SORTS,
   AnalyticsRepositoryError,
@@ -108,7 +108,7 @@ import {
   harvestProblemResponse,
   publicErrorBoundary,
   serializeHarvestProblem
-} from "./chunk-LVXRWJJJ.js";
+} from "./chunk-2LXTOAKS.js";
 import "./chunk-OZJMVCDK.js";
 import {
   BACKUP_LAST_RESORT_ATTEMPTS,
@@ -127,7 +127,7 @@ import {
   resolveKernelProxyId,
   serpArrivalUrl,
   withRuntimeUserAgent
-} from "./chunk-CGOMGGOF.js";
+} from "./chunk-62LEXS5O.js";
 import {
   ApiErrorResponseSchema,
   ArtifactTemplatePresetKeySchema,
@@ -199,7 +199,7 @@ import {
   resolveDeploymentProfile,
   resolveLocalSourcebookSchemaType,
   transcribeMediaUrl
-} from "./chunk-Z5QQEWXA.js";
+} from "./chunk-XOOKZYZG.js";
 import {
   auditImageUrls,
   auditImages,
@@ -210,7 +210,7 @@ import {
   sanitizeAttempts,
   sanitizeHarvestResult,
   sanitizeOutboundDiagnostics
-} from "./chunk-F434YJPV.js";
+} from "./chunk-2L4C4DAZ.js";
 import {
   browserServiceApiKey,
   browserServiceProfileName,
@@ -220,7 +220,7 @@ import {
   recordKernelSession,
   recordVendorUsage,
   runWithCostContext
-} from "./chunk-U2UHJWFW.js";
+} from "./chunk-ES25GP6C.js";
 import {
   listWorkflowDefinitions,
   runWorkflow,
@@ -256,7 +256,7 @@ import {
 } from "./chunk-GGZEC22A.js";
 import {
   PACKAGE_VERSION
-} from "./chunk-7KB5QTHP.js";
+} from "./chunk-GT63KEUB.js";
 import {
   SITE_EXTRACT_ARTIFACT_PREFIX,
   abandonExtractSettlement,
@@ -287,7 +287,7 @@ import {
   setExtractJobTotal,
   settleExtractJob,
   terminalExtractJobStatus
-} from "./chunk-HWGQVP3Q.js";
+} from "./chunk-LCGTNWOT.js";
 import {
   createPrivateArtifact,
   privateArtifactOwnerId,
@@ -451,7 +451,7 @@ import {
   softDeleteInboxMessage,
   upsertPageSnapshot,
   verifyPassword
-} from "./chunk-HZDJ5UZ4.js";
+} from "./chunk-65FTMB7G.js";
 
 // src/blog/registry.ts
 var posts = [
@@ -6312,7 +6312,8 @@ function firstJsonLdImage(value) {
   }
   return null;
 }
-function firstContentImage(html) {
+function contentImages(html) {
+  const images = [];
   for (const match of html.matchAll(/<img\b[^>]*>/gi)) {
     const tag = match[0];
     const attr = (name) => tag.match(new RegExp(`\\b${name}\\s*=\\s*(?:"([^"]+)"|'([^']+)'|([^\\s>]+))`, "i"))?.slice(1).find(Boolean) ?? null;
@@ -6323,30 +6324,36 @@ function firstContentImage(html) {
     const width = Number(attr("width") ?? 0);
     const height = Number(attr("height") ?? 0);
     if (width > 0 && width < 200 || height > 0 && height < 120) continue;
-    return candidate;
+    images.push(candidate);
   }
-  return null;
+  return images;
 }
-function resolveFeaturedImage(input) {
+function resolveFeaturedImageCandidates(input) {
   const replay = parseWaybackReplayUrl(input.pageUrl);
   const baseUrl = replay?.originalUrl ?? input.pageUrl;
   const candidates = [
     { value: input.meta["og:image"] ?? input.meta["og:image:url"] ?? input.meta["og:image:secure_url"], source: "og:image" },
     { value: input.meta["twitter:image"] ?? input.meta["twitter:image:src"], source: "twitter:image" },
     { value: firstJsonLdImage(input.schema), source: "json-ld" },
-    { value: firstContentImage(input.html), source: "content-image" }
+    ...contentImages(input.html).map((value) => ({ value, source: "content-image" }))
   ];
+  const seen = /* @__PURE__ */ new Set();
+  const resolved = [];
   for (const candidate of candidates) {
     if (!candidate.value) continue;
     const url = safeHttpUrl(candidate.value, baseUrl);
-    if (!url) continue;
-    return {
+    if (!url || seen.has(url)) continue;
+    seen.add(url);
+    resolved.push({
       url,
       archivedUrl: replay ? buildWaybackReplayUrl(replay.timestamp, url, "im_") : null,
       source: candidate.source
-    };
+    });
   }
-  return null;
+  return resolved;
+}
+function resolveFeaturedImage(input) {
+  return resolveFeaturedImageCandidates(input)[0] ?? null;
 }
 
 // src/api/site-extractor.ts
@@ -9545,7 +9552,7 @@ var siteExtractFn = inngest.createFunction(
       });
     }) : null;
     const finalized = await step.run("finalize", async () => {
-      const { assembleExtractArtifacts } = await import("./extract-bundle-RW7CVIRF.js");
+      const { assembleExtractArtifacts } = await import("./extract-bundle-QQIYJSBW.js");
       const current = await getExtractJob(jobId2);
       if (!current) throw new Error("extract job disappeared before finalization");
       const stored = await assembleExtractArtifacts(current, { branding, imageAudit });
@@ -10505,7 +10512,7 @@ async function resolveUsZipsPath(requestedPath) {
 async function loadZipGroups(stateAbbr, requestedPath, warnings, sourceMode) {
   const mode = resolvedLocationDataMode({ zipSource: sourceMode });
   if (mode === "hosted") {
-    const { getHostedZipGroups } = await import("./location-data-repository-EPCNGMOM.js");
+    const { getHostedZipGroups } = await import("./location-data-repository-G72M7DTN.js");
     const hosted = await getHostedZipGroups(stateAbbr);
     if (!hosted.dataset) {
       throw new DirectoryLocationError(
@@ -10568,7 +10575,7 @@ async function resolveDirectoryMarkets(options, config = {}) {
   const sourceUrl = censusStateUrl(state.fips);
   const warnings = [];
   if (resolvedLocationDataMode(config) === "hosted") {
-    const { queryHostedLocationMarkets } = await import("./location-data-repository-EPCNGMOM.js");
+    const { queryHostedLocationMarkets } = await import("./location-data-repository-G72M7DTN.js");
     const hosted = await queryHostedLocationMarkets({
       state: state.abbr,
       minPopulation: options.minPopulation,
@@ -12055,7 +12062,7 @@ function summarizePersistedLeadRows(rows, warnings = []) {
 async function settlePersistedLeadListEnrichment(jobId2) {
   const jobs = await listLeadListEnrichmentJobsNeedingSettlement(100);
   const job = jobs.find((candidate) => candidate.id === jobId2);
-  const { getLeadListEnrichmentJob: getLeadListEnrichmentJob2 } = await import("./lead-list-enrichment-repository-PZYE6TDP.js");
+  const { getLeadListEnrichmentJob: getLeadListEnrichmentJob2 } = await import("./lead-list-enrichment-repository-CXLVIV3R.js");
   const current = job ?? await getLeadListEnrichmentJob2(jobId2);
   if (!current) return null;
   const rows = await listLeadListEnrichmentRows(jobId2);
@@ -12111,7 +12118,7 @@ async function reconcileLeadListEnrichmentSettlements(limit = 25) {
         const persisted = job.result ?? summarizePersistedLeadRows(rows, job.warnings);
         const status = job.cancelRequestedAt ? "cancelled" : persisted.failedRows > 0 && persisted.completeRows > 0 ? "partial" : persisted.failedRows > 0 ? "cancelled" : persisted.rowsWithContacts > 0 ? "complete" : "empty";
         if (persisted.failedRows > 0 && persisted.completeRows === 0 && !job.cancelRequestedAt) {
-          const { failLeadListEnrichmentJob: failLeadListEnrichmentJob2 } = await import("./lead-list-enrichment-repository-PZYE6TDP.js");
+          const { failLeadListEnrichmentJob: failLeadListEnrichmentJob2 } = await import("./lead-list-enrichment-repository-CXLVIV3R.js");
           await failLeadListEnrichmentJob2({
             jobId: job.id,
             errorCode: "lead_list_all_rows_failed",
@@ -35066,7 +35073,9 @@ import { isIP } from "net";
 var COMMONS_IMAGE_MAX_BYTES = 10 * 1024 * 1024;
 var COMMONS_IMAGE_MAX_REDIRECTS = 3;
 var COMMONS_IMAGE_FETCH_TIMEOUT_MS = 2e4;
-var COMMONS_IMAGE_RETRY_GUIDANCE = "Call commons_host_image with a different stable public HTTPS image URL or imageBase64, replace featuredImage.url with the returned URL, validate again, then retry commons_submit_entity with the same idempotency key.";
+var COMMONS_IMAGE_PAGE_MAX_BYTES = 2 * 1024 * 1024;
+var COMMONS_IMAGE_MAX_PAGE_CANDIDATES = 12;
+var COMMONS_IMAGE_RETRY_GUIDANCE = "Call commons_host_image with imageBase64, an owner-authorized artifactId, a public HTTPS image URL, or a public HTTPS webpage containing a usable featured image. Replace featuredImage.url with the returned permanent URL, validate again, then retry commons_submit_entity with the same idempotency key.";
 var CommonsImageError = class extends Error {
   constructor(code, message, httpStatus = 400, retryable = false, retryGuidance = COMMONS_IMAGE_RETRY_GUIDANCE) {
     super(message);
@@ -35139,6 +35148,9 @@ async function assertPublicHttpsUrl(rawUrl) {
   if (url.protocol !== "https:") {
     throw new CommonsImageError("image_url_not_https", "Commons image sources must be https URLs.");
   }
+  if (url.username || url.password) {
+    throw new CommonsImageError("image_url_invalid", "Commons image source URLs cannot contain embedded credentials.");
+  }
   const hostname = url.hostname.replace(/^\[|\]$/g, "");
   const addresses = isIP(hostname) ? [{ address: hostname }] : await dnsLookup(hostname, { all: true }).catch(() => []);
   if (!addresses.length) {
@@ -35149,7 +35161,28 @@ async function assertPublicHttpsUrl(rawUrl) {
   }
   return url;
 }
-async function downloadImage(sourceUrl) {
+async function readResponseBytes(response, maxBytes) {
+  const declaredLength = Number(response.headers.get("content-length") ?? "0");
+  if (declaredLength > maxBytes) {
+    throw new CommonsImageError("image_too_large", `Source exceeds the ${maxBytes} byte limit.`, 413);
+  }
+  if (!response.body) return Buffer.alloc(0);
+  const reader = response.body.getReader();
+  const chunks = [];
+  let total = 0;
+  while (true) {
+    const { done, value } = await reader.read();
+    if (done) break;
+    total += value.byteLength;
+    if (total > maxBytes) {
+      await reader.cancel().catch(() => void 0);
+      throw new CommonsImageError("image_too_large", `Source exceeds the ${maxBytes} byte limit.`, 413);
+    }
+    chunks.push(Buffer.from(value));
+  }
+  return Buffer.concat(chunks, total);
+}
+async function downloadPublicSource(sourceUrl) {
   let current = sourceUrl;
   for (let redirect = 0; redirect <= COMMONS_IMAGE_MAX_REDIRECTS; redirect += 1) {
     const url = await assertPublicHttpsUrl(current);
@@ -35184,15 +35217,11 @@ async function downloadImage(sourceUrl) {
         retryable
       );
     }
-    const declaredLength = Number(response.headers.get("content-length") ?? "0");
-    if (declaredLength > COMMONS_IMAGE_MAX_BYTES) {
-      throw new CommonsImageError("image_too_large", `Image exceeds the ${COMMONS_IMAGE_MAX_BYTES} byte limit.`, 413);
-    }
-    const bytes = Buffer.from(await response.arrayBuffer());
-    if (bytes.length > COMMONS_IMAGE_MAX_BYTES) {
-      throw new CommonsImageError("image_too_large", `Image exceeds the ${COMMONS_IMAGE_MAX_BYTES} byte limit.`, 413);
-    }
-    return bytes;
+    return {
+      bytes: await readResponseBytes(response, COMMONS_IMAGE_MAX_BYTES),
+      finalUrl: url.toString(),
+      contentType: (response.headers.get("content-type") ?? "").split(";")[0].trim().toLowerCase()
+    };
   }
   throw new CommonsImageError("image_redirect_limit", "Image source exceeded the redirect limit.");
 }
@@ -35205,6 +35234,114 @@ function decodeBase64Image(value) {
   }
   return bytes;
 }
+function safeProvenanceUrl(rawUrl) {
+  try {
+    const url = new URL(rawUrl);
+    url.username = "";
+    url.password = "";
+    url.search = "";
+    url.hash = "";
+    return url.toString();
+  } catch {
+    return null;
+  }
+}
+function looksLikeHtml(bytes, declaredType) {
+  if (declaredType === "text/html" || declaredType === "application/xhtml+xml") return true;
+  const prefix = bytes.subarray(0, 512).toString("utf8").trimStart().toLowerCase();
+  return prefix.startsWith("<!doctype html") || prefix.startsWith("<html") || prefix.startsWith("<head");
+}
+async function resolveCommonsImageSource(input) {
+  const supplied = [input.sourceUrl, input.imageBase64, input.artifactId].filter((value) => Boolean(value)).length;
+  if (supplied === 0) {
+    throw new CommonsImageError("image_source_missing", "Provide exactly one of sourceUrl, imageBase64, or artifactId.");
+  }
+  if (supplied !== 1) {
+    throw new CommonsImageError("image_source_ambiguous", "Provide only one image source: sourceUrl, imageBase64, or artifactId.");
+  }
+  if (input.sourceUrl && input.sourceType) {
+    throw new CommonsImageError("image_source_type_invalid", "sourceType applies only to imageBase64 or artifactId, not sourceUrl.");
+  }
+  if (input.imageBase64) {
+    return {
+      bytes: decodeBase64Image(input.imageBase64),
+      sourceUrl: null,
+      sourcePageUrl: null,
+      sourceKind: input.sourceType ?? "uploaded",
+      selectionSource: "provided_bytes"
+    };
+  }
+  if (input.artifactId) {
+    const bytes = await readOwnedImageSourceArtifact({ artifactId: input.artifactId, ownerId: String(input.userId) });
+    if (!bytes) {
+      throw new CommonsImageError("image_artifact_not_found", "The image artifact was not found, expired, or is not owned by this account.", 422);
+    }
+    if (bytes.length > COMMONS_IMAGE_MAX_BYTES) {
+      throw new CommonsImageError("image_too_large", `Image exceeds the ${COMMONS_IMAGE_MAX_BYTES} byte limit.`, 413);
+    }
+    return {
+      bytes,
+      sourceUrl: null,
+      sourcePageUrl: null,
+      sourceKind: input.sourceType ?? "artifact",
+      selectionSource: "artifact"
+    };
+  }
+  const requestedUrl = String(input.sourceUrl);
+  const downloaded = await downloadPublicSource(requestedUrl);
+  if (sniffImageFormat(downloaded.bytes)) {
+    return {
+      bytes: downloaded.bytes,
+      sourceUrl: safeProvenanceUrl(downloaded.finalUrl),
+      sourcePageUrl: null,
+      sourceKind: "direct_url",
+      selectionSource: "direct_url"
+    };
+  }
+  if (!looksLikeHtml(downloaded.bytes, downloaded.contentType)) {
+    throw new CommonsImageError(
+      "image_format_unsupported",
+      "The supplied URL returned neither a supported image nor an HTML webpage with a discoverable image.",
+      415
+    );
+  }
+  if (downloaded.bytes.length > COMMONS_IMAGE_PAGE_MAX_BYTES) {
+    throw new CommonsImageError("image_page_too_large", `Webpage exceeds the ${COMMONS_IMAGE_PAGE_MAX_BYTES} byte discovery limit.`, 413);
+  }
+  const html = downloaded.bytes.toString("utf8");
+  const document2 = loadHtmlDocument(html);
+  const candidates = resolveFeaturedImageCandidates({
+    html,
+    meta: document2.meta,
+    schema: document2.schema,
+    pageUrl: downloaded.finalUrl
+  }).slice(0, COMMONS_IMAGE_MAX_PAGE_CANDIDATES);
+  if (!candidates.length) {
+    throw new CommonsImageError("page_image_not_found", "The webpage did not expose a usable featured or content image.", 422);
+  }
+  let sawRetryableFailure = false;
+  for (const candidate of candidates) {
+    try {
+      const image = await downloadPublicSource(candidate.url);
+      if (!sniffImageFormat(image.bytes)) continue;
+      return {
+        bytes: image.bytes,
+        sourceUrl: safeProvenanceUrl(image.finalUrl),
+        sourcePageUrl: safeProvenanceUrl(downloaded.finalUrl),
+        sourceKind: "webpage",
+        selectionSource: candidate.source
+      };
+    } catch (error) {
+      if (error instanceof CommonsImageError && error.retryable) sawRetryableFailure = true;
+    }
+  }
+  throw new CommonsImageError(
+    "page_image_candidates_unusable",
+    "The webpage exposed image candidates, but none returned supported public image bytes.",
+    422,
+    sawRetryableFailure
+  );
+}
 function commonsImageBlobStore() {
   const token6 = process.env.COMMONS_IMAGE_READ_WRITE_TOKEN?.trim() || process.env.COMMONS_IMAGE_BLOB_READ_WRITE_TOKEN?.trim() || process.env.BLOB_READ_WRITE_TOKEN?.trim();
   return token6 ? new VercelBlobStore(token6) : getBlobStore();
@@ -35236,6 +35373,9 @@ async function findCommonsHostedImageByUrl(rawUrl) {
     bytes: Number(row.bytes),
     digest: String(row.digest),
     sourceUrl: row.source_url ? String(row.source_url) : null,
+    sourcePageUrl: null,
+    sourceKind: "registered",
+    selectionSource: "registered",
     reused: true
   };
 }
@@ -35243,10 +35383,12 @@ var hostOverride = null;
 async function hostCommonsImage(input) {
   if (hostOverride) return hostOverride(input);
   await ensureCommonsImageSchema();
-  if (!input.sourceUrl && !input.imageBase64) {
-    throw new CommonsImageError("image_source_missing", "Provide either sourceUrl or imageBase64.");
+  if (input.sourceUrl && !input.imageBase64 && !input.artifactId && !input.sourceType) {
+    const registered6 = await findCommonsHostedImageByUrl(input.sourceUrl);
+    if (registered6) return registered6;
   }
-  const bytes = input.imageBase64 ? decodeBase64Image(input.imageBase64) : await downloadImage(String(input.sourceUrl));
+  const resolved = await resolveCommonsImageSource(input);
+  const bytes = resolved.bytes;
   const contentType = sniffImageFormat(bytes);
   if (!contentType) {
     throw new CommonsImageError(
@@ -35268,7 +35410,10 @@ async function hostCommonsImage(input) {
       contentType: String(reusable.content_type),
       bytes: Number(reusable.bytes),
       digest: digest2,
-      sourceUrl: reusable.source_url ? String(reusable.source_url) : null,
+      sourceUrl: resolved.sourceUrl,
+      sourcePageUrl: resolved.sourcePageUrl,
+      sourceKind: resolved.sourceKind,
+      selectionSource: resolved.selectionSource,
       reused: true
     };
   }
@@ -35297,14 +35442,25 @@ async function hostCommonsImage(input) {
       stored.url,
       contentType,
       bytes.length,
-      input.sourceUrl ?? null,
+      resolved.sourceUrl,
       input.alt ?? null,
       input.license ?? null,
       input.attribution ?? null,
       (/* @__PURE__ */ new Date()).toISOString()
     ]
   });
-  return { id, url: stored.url, contentType, bytes: bytes.length, digest: digest2, sourceUrl: input.sourceUrl ?? null, reused: false };
+  return {
+    id,
+    url: stored.url,
+    contentType,
+    bytes: bytes.length,
+    digest: digest2,
+    sourceUrl: resolved.sourceUrl,
+    sourcePageUrl: resolved.sourcePageUrl,
+    sourceKind: resolved.sourceKind,
+    selectionSource: resolved.selectionSource,
+    reused: false
+  };
 }
 async function hostEntityImages(input) {
   const rewrite = { mediaUrls: /* @__PURE__ */ new Map(), dropped: [] };
@@ -38738,11 +38894,13 @@ commonsApp.get("/publications/:subdomain", async (c) => {
 var HostImageSchema = z33.object({
   sourceUrl: z33.string().url().optional(),
   imageBase64: z33.string().min(16).optional(),
+  artifactId: z33.string().min(1).max(500).optional(),
+  sourceType: z33.enum(["uploaded", "ai_generated"]).optional(),
   alt: z33.string().max(500).optional(),
   license: z33.string().max(240).optional(),
   attribution: z33.string().max(500).optional()
-}).strict().refine((body) => Boolean(body.sourceUrl || body.imageBase64), {
-  message: "Provide either sourceUrl or imageBase64."
+}).strict().refine((body) => [body.sourceUrl, body.imageBase64, body.artifactId].filter(Boolean).length === 1, {
+  message: "Provide exactly one of sourceUrl, imageBase64, or artifactId."
 });
 commonsApp.post("/images", auth2, async (c) => {
   const parsed = HostImageSchema.safeParse(await c.req.json().catch(() => ({})));
@@ -49896,7 +50054,7 @@ app.get("/cron/tick", async (c) => {
     return c.json({ error: "Unauthorized" }, 401);
   }
   const startedAt = Date.now();
-  const { drainQueue } = await import("./worker-IBLGV272.js");
+  const { drainQueue } = await import("./worker-JGWV2LID.js");
   const budget = { maxJobs: 10, deadlineMs: startedAt + CRON_TICK_DRAIN_BUDGET_MS };
   const origin = `${new URL(c.req.url).protocol}//${new URL(c.req.url).host}`;
   const unfinished = [];
@@ -49974,8 +50132,8 @@ app.post("/api/internal/extract-refinalize/:id", async (c) => {
     finishExtractJob: finishExtractJob2,
     terminalExtractJobStatus: terminalExtractJobStatus2,
     extractJobLimitInfo: extractJobLimitInfo2
-  } = await import("./site-extract-repository-CZ7SVT3Z.js");
-  const { assembleExtractArtifacts } = await import("./extract-bundle-RW7CVIRF.js");
+  } = await import("./site-extract-repository-7EP6UX6I.js");
+  const { assembleExtractArtifacts } = await import("./extract-bundle-QQIYJSBW.js");
   const existing = await getExtractJob2(jobId2);
   if (!existing) return c.json({ error: "job not found" }, 404);
   if (existing.status !== "failed") {
@@ -50002,7 +50160,7 @@ app.post("/api/internal/extract-refinalize/:id", async (c) => {
   if (!updated) return c.json({ error: "job state changed during re-finalization" }, 409);
   let settlement = "already_settled_or_refunded";
   if (job.billedMc == null && job.userId != null) {
-    const { settleExtractJob: settleExtractJob3, countSuccessfulPages: countSuccessfulPages2 } = await import("./site-extract-repository-CZ7SVT3Z.js");
+    const { settleExtractJob: settleExtractJob3, countSuccessfulPages: countSuccessfulPages2 } = await import("./site-extract-repository-7EP6UX6I.js");
     const heldMc = Number(job.options.heldMc ?? 0);
     const successful = await countSuccessfulPages2(jobId2);
     const usedMc = Math.min(successful * MC_COSTS.page_scrape, heldMc);

package/dist/{site-extract-repository-CZ7SVT3Z.js → site-extract-repository-7EP6UX6I.js}

@@ -28,10 +28,10 @@ import {
   setExtractJobTotal,
   settleExtractJob,
   terminalExtractJobStatus
-} from "./chunk-HWGQVP3Q.js";
+} from "./chunk-LCGTNWOT.js";
 import "./chunk-DNM65UCK.js";
 import "./chunk-AYJHI2FK.js";
-import "./chunk-HZDJ5UZ4.js";
+import "./chunk-65FTMB7G.js";
 export {
   abandonExtractSettlement,
   claimFailedExtractJobForRefinalize,

package/dist/{worker-IBLGV272.js → worker-JGWV2LID.js}

@@ -5,19 +5,19 @@ import {
   harvestProblemEnvelope,
   harvestProblemResponse,
   serializeHarvestProblem
-} from "./chunk-LVXRWJJJ.js";
+} from "./chunk-2LXTOAKS.js";
 import "./chunk-OZJMVCDK.js";
 import {
   harvest
-} from "./chunk-CGOMGGOF.js";
+} from "./chunk-62LEXS5O.js";
 import {
   sanitizeAttempts,
   sanitizeHarvestResult
-} from "./chunk-F434YJPV.js";
+} from "./chunk-2L4C4DAZ.js";
 import {
   browserServiceApiKey,
   runWithCostContext
-} from "./chunk-U2UHJWFW.js";
+} from "./chunk-ES25GP6C.js";
 import "./chunk-77LQV73B.js";
 import {
   MC_COSTS,
@@ -30,7 +30,7 @@ import {
   debitMc,
   failJob,
   listHarvestAttempts
-} from "./chunk-HZDJ5UZ4.js";
+} from "./chunk-65FTMB7G.js";
 
 // src/api/worker.ts
 var MAX_CONCURRENT = 2;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mcp-scraper",
-  "version": "0.66.7",
+  "version": "0.67.0",
   "description": "MCP server for MCP Scraper web intelligence tools",
   "type": "module",
   "main": "./dist/index.cjs",