feat(extractors): add 17 job source extractors and cross-source dedup

Adds extractor packages: arbeitnow, ashby, careerjet, fourdayweek,
greenhouse, himalayas, jobicy, jooble, lever, reed, remoteok, remotive,
themuse, usajobs, weworkremotely, workday — each with manifest, package
metadata and README.

Pipeline / shared:
- shared/job-fingerprint: stable hash for cross-source dedup, with tests
- discover-jobs: dedup via fingerprint and richer per-source merging
- jobs repository: fingerprint-aware upsert / lookup
- settings-registry, settings types/routes, demo-defaults: knobs for the
  new sources
- shared extractors index: register the new manifests
- location-support, profiles route: small fixes for the new sources

Tooling:
- scripts/smoke-extractors.ts to sanity-check each source locally
- scripts/jobber-cron-{cherepaha,dobkin}.env.example: per-host cron
  templates (CHANGEME placeholders only)
- .env.example: documented env vars for the new extractors
- .gitignore: ignore extractors/*/storage/ runtime caches (was ukvisajobs only)

Co-authored-by: Cursor <cursoragent@cursor.com>

extractors/ashby/README.md

@@ -0,0 +1,8 @@
+# ashby-extractor
+
+Public Ashby job-board feeds via
+`GET https://api.ashbyhq.com/posting-api/job-board/{company}`.
+
+- No auth.
+- Configure target slugs via `ashbyCompanies` (comma/newline) or
+  `ASHBY_COMPANIES` env.

extractors/ashby/manifest.ts

@@ -0,0 +1,185 @@
+/**
+ * Ashby public job board API.
+ *
+ * https://developers.ashbyhq.com/reference/posting-api-job-board
+ *   GET https://api.ashbyhq.com/posting-api/job-board/{company}
+ *
+ * No auth. Each entry in `ashbyCompanies` is fetched independently.
+ */
+
+import type {
+  ExtractorManifest,
+  ExtractorRunResult,
+} from "@shared/types/extractors";
+import type { CreateJobInput } from "@shared/types/jobs";
+
+interface AshbyAddress {
+  postalAddress?: {
+    addressLocality?: string;
+    addressRegion?: string;
+    addressCountry?: string;
+  };
+}
+interface AshbyJob {
+  id?: string;
+  title?: string;
+  jobUrl?: string;
+  applyUrl?: string;
+  publishedAt?: string;
+  employmentType?: string;
+  isRemote?: boolean;
+  team?: string;
+  department?: string;
+  location?: string;
+  locationName?: string;
+  secondaryLocations?: Array<{ location?: string; locationName?: string }>;
+  address?: AshbyAddress;
+  descriptionPlain?: string;
+  descriptionHtml?: string;
+}
+interface AshbyResponse {
+  jobs?: AshbyJob[];
+  apiVersion?: string;
+}
+
+function asString(value: unknown): string | undefined {
+  if (typeof value !== "string") return undefined;
+  const trimmed = value.trim();
+  return trimmed ? trimmed : undefined;
+}
+
+function readCompanies(raw: string | undefined): string[] {
+  if (!raw) return [];
+  try {
+    const parsed = JSON.parse(raw);
+    if (Array.isArray(parsed)) {
+      return parsed
+        .map((entry) => (typeof entry === "string" ? entry.trim() : ""))
+        .filter(Boolean);
+    }
+  } catch {
+    // fall through
+  }
+  return raw
+    .split(/[\n,;|]+/)
+    .map((entry) => entry.trim())
+    .filter(Boolean);
+}
+
+function locationFor(job: AshbyJob): string | undefined {
+  const primary =
+    asString(job.locationName) ?? asString(job.location) ?? undefined;
+  const secondary =
+    job.secondaryLocations
+      ?.map((entry) => asString(entry.locationName) ?? asString(entry.location))
+      .filter((value): value is string => Boolean(value)) ?? [];
+  const all = [primary, ...secondary].filter((value): value is string =>
+    Boolean(value),
+  );
+  return all.length > 0 ? all.join("; ") : undefined;
+}
+
+function mapJob(job: AshbyJob, company: string): CreateJobInput | null {
+  const jobUrl = asString(job.jobUrl) ?? asString(job.applyUrl);
+  if (!jobUrl) return null;
+  const employer = company
+    .split(/[-_]/)
+    .filter(Boolean)
+    .map((part) => part.charAt(0).toUpperCase() + part.slice(1))
+    .join(" ");
+  return {
+    source: "ashby",
+    sourceJobId: asString(job.id),
+    title: asString(job.title) ?? "Unknown Title",
+    employer: employer || company,
+    jobUrl,
+    applicationLink: asString(job.applyUrl) ?? jobUrl,
+    location: locationFor(job),
+    isRemote: typeof job.isRemote === "boolean" ? job.isRemote : undefined,
+    jobType: asString(job.employmentType),
+    jobFunction: asString(job.team),
+    companyIndustry: asString(job.department),
+    datePosted: asString(job.publishedAt),
+    jobDescription:
+      asString(job.descriptionPlain) ?? asString(job.descriptionHtml),
+  };
+}
+
+async function fetchCompany(company: string): Promise<AshbyJob[]> {
+  const url = `https://api.ashbyhq.com/posting-api/job-board/${encodeURIComponent(company)}`;
+  const response = await fetch(url, {
+    headers: { Accept: "application/json" },
+  });
+  if (response.status === 404) return [];
+  if (!response.ok) {
+    throw new Error(
+      `Ashby request for "${company}" failed with status ${response.status}`,
+    );
+  }
+  const body = (await response.json()) as AshbyResponse;
+  return Array.isArray(body.jobs) ? body.jobs : [];
+}
+
+export const manifest: ExtractorManifest = {
+  id: "ashby",
+  displayName: "Ashby (ATS)",
+  providesSources: ["ashby"],
+  async run(context): Promise<ExtractorRunResult> {
+    if (context.shouldCancel?.()) return { success: true, jobs: [] };
+
+    const companies = readCompanies(context.settings.ashbyCompanies);
+    if (companies.length === 0) {
+      return {
+        success: true,
+        jobs: [],
+        error:
+          "No Ashby companies configured. Set ASHBY_COMPANIES or the ashbyCompanies setting (comma- or newline-separated slugs).",
+      };
+    }
+
+    const seen = new Set<string>();
+    const out: CreateJobInput[] = [];
+
+    try {
+      for (let i = 0; i < companies.length; i += 1) {
+        if (context.shouldCancel?.()) break;
+        const company = companies[i];
+        context.onProgress?.({
+          phase: "list",
+          termsProcessed: i,
+          termsTotal: companies.length,
+          currentUrl: company,
+          detail: `Ashby: ${company} (${i + 1}/${companies.length})`,
+        });
+
+        let added = 0;
+        const jobs = await fetchCompany(company);
+        for (const job of jobs) {
+          const mapped = mapJob(job, company);
+          if (!mapped) continue;
+          const key = mapped.sourceJobId || mapped.jobUrl;
+          if (seen.has(key)) continue;
+          seen.add(key);
+          out.push(mapped);
+          added += 1;
+        }
+
+        context.onProgress?.({
+          phase: "list",
+          termsProcessed: i + 1,
+          termsTotal: companies.length,
+          currentUrl: company,
+          jobPagesProcessed: out.length,
+          detail: `Ashby: ${company} → ${added} jobs (${out.length} total)`,
+        });
+      }
+    } catch (error) {
+      const message = error instanceof Error ? error.message : "Unknown error";
+      return { success: false, jobs: out, error: message };
+    }
+
+    return { success: true, jobs: out };
+  },
+};
+
+export default manifest;

extractors/ashby/package.json

@@ -0,0 +1,17 @@
+{
+  "name": "ashby-extractor",
+  "version": "0.0.1",
+  "type": "module",
+  "description": "Ashby public ATS extractor",
+  "main": "manifest.ts",
+  "dependencies": {
+    "job-ops-shared": "^1.0.0"
+  },
+  "devDependencies": {
+    "@types/node": "^24.0.0",
+    "typescript": "~5.9.0"
+  },
+  "scripts": {
+    "check:types": "tsc --noEmit"
+  }
+}

extractors/ashby/tsconfig.json

@@ -0,0 +1,17 @@
+{
+  "compilerOptions": {
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "target": "ES2022",
+    "outDir": "dist",
+    "strict": true,
+    "noUnusedLocals": false,
+    "lib": ["ES2022", "DOM"],
+    "types": ["node"],
+    "baseUrl": ".",
+    "paths": {
+      "@shared/*": ["../../shared/src/*"]
+    }
+  },
+  "include": ["./manifest.ts", "./src/**/*"]
+}