feat: workplace filter, job dedup, company skip docs, deploy notes

- Add remote/orchestrator filter by workplace (remote, not remote, unknown) with URL param
- Expose isRemote on job list API; canonicalize URLs and source_job_id dedup on import
- Onboarding: optional VITE_SKIP_RXRESUME_ONBOARDING for RxResume-free onboarding
- Scoring UI + docs for company skip list; pipeline-run dedup note
- Vitest: TZ=UTC for stable time-based tests
- DEPLOY_GITEA_VM_CRON_TELEGRAM.md for VM/cron/Telegram ops

Made-with: Cursor

shared/src/index.ts

@@ -1,4 +1,5 @@
 export * from "./extractors";
+export * from "./job-url-canonical";
 export * from "./location-support";
 export * from "./types";
 export * from "./utils/type-conversion";

shared/src/job-url-canonical.test.ts

@@ -0,0 +1,27 @@
+import { describe, expect, it } from "vitest";
+import { canonicalizeJobUrl } from "./job-url-canonical";
+
+describe("canonicalizeJobUrl", () => {
+  it("strips tracking query params and normalizes host", () => {
+    const a =
+      "https://www.example.com/jobs/123?utm_source=linkedin&role=eng&utm_medium=social";
+    const b = "http://example.com/jobs/123?role=eng";
+    expect(canonicalizeJobUrl(a)).toBe(canonicalizeJobUrl(b));
+  });
+
+  it("removes trailing slash on path", () => {
+    expect(canonicalizeJobUrl("https://example.com/path/")).toBe(
+      "https://example.com/path",
+    );
+  });
+
+  it("sorts query params for stable comparison", () => {
+    const a = "https://example.com/x?b=2&a=1";
+    const b = "https://example.com/x?a=1&b=2";
+    expect(canonicalizeJobUrl(a)).toBe(canonicalizeJobUrl(b));
+  });
+
+  it("returns trimmed non-URL strings unchanged", () => {
+    expect(canonicalizeJobUrl("  not a url  ")).toBe("not a url");
+  });
+});

shared/src/job-url-canonical.ts

@@ -0,0 +1,61 @@
+/**
+ * Normalize job listing URLs so the same role is not stored twice when only
+ * tracking params, scheme, or trivial path differences differ.
+ */
+
+const TRACKING_QUERY_PREFIXES = ["utm_", "stm_"] as const;
+
+const DROP_QUERY_KEYS = new Set([
+  "ref",
+  "src",
+  "fbclid",
+  "gclid",
+  "mc_eid",
+  "icid",
+]);
+
+export function canonicalizeJobUrl(raw: string): string {
+  const trimmed = raw.trim();
+  if (!trimmed) return trimmed;
+
+  try {
+    const u = new URL(trimmed);
+    u.hash = "";
+
+    let host = u.hostname.toLowerCase();
+    if (host.startsWith("www.")) host = host.slice(4);
+    u.hostname = host;
+    u.protocol = "https:";
+
+    for (const key of [...u.searchParams.keys()]) {
+      const lower = key.toLowerCase();
+      if (
+        DROP_QUERY_KEYS.has(lower) ||
+        TRACKING_QUERY_PREFIXES.some((prefix) => lower.startsWith(prefix))
+      ) {
+        u.searchParams.delete(key);
+      }
+    }
+
+    const sortedKeys = [...u.searchParams.keys()].sort((a, b) =>
+      a.localeCompare(b),
+    );
+    const next = new URLSearchParams();
+    for (const k of sortedKeys) {
+      for (const v of u.searchParams.getAll(k)) {
+        next.append(k, v);
+      }
+    }
+    u.search = next.toString() ? `?${next.toString()}` : "";
+
+    let path = u.pathname;
+    if (path.length > 1 && path.endsWith("/")) {
+      path = path.slice(0, -1);
+    }
+    u.pathname = path || "/";
+
+    return u.toString();
+  } catch {
+    return trimmed;
+  }
+}

shared/src/types/jobs.ts

@@ -213,6 +213,7 @@ export type JobListItem = Pick<
   | "salaryMinAmount"
   | "salaryMaxAmount"
   | "salaryCurrency"
+  | "isRemote"
   | "discoveredAt"
   | "appliedAt"
   | "updatedAt"