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/remoteok/manifest.ts

@@ -0,0 +1,190 @@
+/**
+ * Remote OK public feed.
+ *
+ * https://remoteok.com/api — single JSON endpoint that returns the entire
+ * active remote-jobs board in one shot. The first array element is metadata
+ * (legal/attribution); jobs follow.
+ *
+ * No auth, no server-side pagination, no per-term query — we fetch once per
+ * pipeline run and apply each `searchTerm` as a case-insensitive filter over
+ * `position` + `tags` so the orchestrator's per-term iteration still works.
+ *
+ * Per Remote OK's TOS we send a descriptive User-Agent so they can identify
+ * traffic; we do not strip the legal/attribution element from the response.
+ */
+
+import type {
+  ExtractorManifest,
+  ExtractorRunResult,
+} from "@shared/types/extractors";
+import type { CreateJobInput } from "@shared/types/jobs";
+
+const API_URL = "https://remoteok.com/api";
+const USER_AGENT =
+  "Mozilla/5.0 (compatible; JobOps/1.0; +https://github.com/) job-search pipeline";
+
+interface RemoteOkJob {
+  id?: string | number;
+  slug?: string;
+  position?: string;
+  company?: string;
+  company_logo?: string;
+  logo?: string;
+  location?: string;
+  tags?: string[];
+  description?: string;
+  url?: string;
+  apply_url?: string;
+  date?: string;
+  epoch?: number;
+  salary_min?: number;
+  salary_max?: number;
+}
+
+interface RemoteOkLegalEntry {
+  legal?: string;
+  last_updated?: number;
+}
+
+type RemoteOkResponseEntry = RemoteOkJob | RemoteOkLegalEntry;
+
+function asString(value: unknown): string | undefined {
+  if (typeof value !== "string") return undefined;
+  const trimmed = value.trim();
+  return trimmed ? trimmed : undefined;
+}
+
+function isJobEntry(entry: RemoteOkResponseEntry): entry is RemoteOkJob {
+  return (
+    "id" in entry || "position" in entry || "url" in entry || "slug" in entry
+  );
+}
+
+function tagMatchesTerm(job: RemoteOkJob, normalizedTerm: string): boolean {
+  if (!normalizedTerm) return true;
+  const haystack = [
+    job.position ?? "",
+    ...(Array.isArray(job.tags) ? job.tags : []),
+  ]
+    .join(" ")
+    .toLowerCase();
+  return haystack.includes(normalizedTerm);
+}
+
+function mapJob(job: RemoteOkJob): CreateJobInput | null {
+  const jobUrl = asString(job.url) ?? asString(job.apply_url);
+  if (!jobUrl) return null;
+
+  // Remote OK reports salary as raw numbers; 0 means "not specified".
+  const minSalary =
+    typeof job.salary_min === "number" && job.salary_min > 0
+      ? job.salary_min
+      : undefined;
+  const maxSalary =
+    typeof job.salary_max === "number" && job.salary_max > 0
+      ? job.salary_max
+      : undefined;
+
+  const tags = Array.isArray(job.tags)
+    ? job.tags.filter((tag): tag is string => typeof tag === "string")
+    : [];
+
+  return {
+    source: "remoteok",
+    sourceJobId: job.id != null ? String(job.id) : asString(job.slug),
+    title: asString(job.position) ?? "Unknown Title",
+    employer: asString(job.company) ?? "Unknown Employer",
+    jobUrl,
+    applicationLink: asString(job.apply_url) ?? jobUrl,
+    location: asString(job.location) ?? "Remote",
+    isRemote: true,
+    datePosted: asString(job.date),
+    jobDescription: asString(job.description),
+    companyLogo: asString(job.company_logo) ?? asString(job.logo),
+    disciplines: tags.length > 0 ? tags.join(", ") : undefined,
+    salaryMinAmount: minSalary,
+    salaryMaxAmount: maxSalary,
+    salaryCurrency: minSalary || maxSalary ? "USD" : undefined,
+    salaryInterval: minSalary || maxSalary ? "yearly" : undefined,
+  };
+}
+
+async function fetchAll(): Promise<RemoteOkJob[]> {
+  const response = await fetch(API_URL, {
+    headers: {
+      Accept: "application/json",
+      "User-Agent": USER_AGENT,
+    },
+  });
+  if (!response.ok) {
+    throw new Error(`Remote OK request failed with status ${response.status}`);
+  }
+  const body = (await response.json()) as RemoteOkResponseEntry[];
+  if (!Array.isArray(body)) return [];
+  return body.filter(isJobEntry);
+}
+
+export const manifest: ExtractorManifest = {
+  id: "remoteok",
+  displayName: "Remote OK",
+  providesSources: ["remoteok"],
+  async run(context): Promise<ExtractorRunResult> {
+    if (context.shouldCancel?.()) return { success: true, jobs: [] };
+
+    const maxJobsPerTerm = context.settings.remoteokMaxJobsPerTerm
+      ? Number.parseInt(context.settings.remoteokMaxJobsPerTerm, 10)
+      : 100;
+
+    const terms = context.searchTerms.length > 0 ? context.searchTerms : [""];
+
+    let allJobs: RemoteOkJob[];
+    try {
+      allJobs = await fetchAll();
+    } catch (error) {
+      const message = error instanceof Error ? error.message : "Unknown error";
+      return { success: false, jobs: [], error: message };
+    }
+
+    const seen = new Set<string>();
+    const out: CreateJobInput[] = [];
+
+    for (let i = 0; i < terms.length; i += 1) {
+      if (context.shouldCancel?.()) break;
+      const term = terms[i].trim();
+      const normalizedTerm = term.toLowerCase();
+      context.onProgress?.({
+        phase: "list",
+        termsProcessed: i,
+        termsTotal: terms.length,
+        currentUrl: term || "(all remote)",
+        detail: `Remote OK: term ${i + 1}/${terms.length}`,
+      });
+
+      let collected = 0;
+      for (const job of allJobs) {
+        if (collected >= maxJobsPerTerm) break;
+        if (!tagMatchesTerm(job, normalizedTerm)) continue;
+        const mapped = mapJob(job);
+        if (!mapped) continue;
+        const key = mapped.sourceJobId || mapped.jobUrl;
+        if (seen.has(key)) continue;
+        seen.add(key);
+        out.push(mapped);
+        collected += 1;
+      }
+
+      context.onProgress?.({
+        phase: "list",
+        termsProcessed: i + 1,
+        termsTotal: terms.length,
+        currentUrl: term || "(all remote)",
+        jobPagesProcessed: out.length,
+        detail: `Remote OK: completed term ${i + 1}/${terms.length} (${collected} matched)`,
+      });
+    }
+
+    return { success: true, jobs: out };
+  },
+};
+
+export default manifest;