fix(jobnet-search): keep canonical portal url and emit destination in applyUrl (closes #701) (#706)

* fix(jobnet-search): keep canonical portal url and emit destination in applyUrl (closes #701)

* docs(jobnet-search): document canonical url and applyUrl split (#701)

* changelog: place the #706 entry under [Unreleased]

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Mads Lorentzen <madslorentzen_17@hotmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

.agents/skills/jobnet-search/cli/README.md

@@ -154,7 +154,8 @@ bun run src/cli.ts search \
       "location": "Viborg",
       "date": "2026-03-13",
       "deadline": "2026-04-05",
-      "url": "https://jobnet.dk/find-job/9ef43bce-d82b-4ea1-a098-7ff6520f99be"
+      "url": "https://jobnet.dk/find-job/9ef43bce-d82b-4ea1-a098-7ff6520f99be",
+      "applyUrl": null
     }
   ]
 }
@@ -162,7 +163,7 @@ bun run src/cli.ts search \
 
 > **Note**: The `description` field (raw HTML) is intentionally omitted from `search` results for brevity. Use `detail` to retrieve the full job description.
 
-> **Note**: Every result also carries the cross-portal contract fields `company`, `location`, `date`, `deadline` and `url` - derived respectively from `hiringOrgName`, `postalDistrictName`/`municipality`, and the destination URL (the employer's `jobAdUrl` for external ads, or `/find-job/{jobAdId}` for internal ones). `/scrape` Step 2 expects search output to include title, company, location, date, and URL, and dates follow the `YYYY-MM-DD` convention of the other portal CLIs. The API's `1900-01-01` deadline sentinel (deadline not disclosed) maps to `null`. The native fields above are preserved unchanged.
+> **Note**: Every result also carries the cross-portal contract fields `company`, `location`, `date`, `deadline`, `url`, and `applyUrl` - derived respectively from `hiringOrgName`, `postalDistrictName`/`municipality`, and the canonical portal URL `https://jobnet.dk/find-job/{jobAdId}`. `url` is always canonical on jobnet.dk for all ads so that deduplication, health checks, and `/apply` host routing identify the portal correctly. External ads carry their employer ATS destination in `applyUrl` (and `jobAdUrl`), while internal ads set `applyUrl` to `null`. `/scrape` Step 2 expects search output to include title, company, location, date, and URL, and dates follow the `YYYY-MM-DD` convention of the other portal CLIs. The API's `1900-01-01` deadline sentinel (deadline not disclosed) maps to `null`. The native fields above are preserved unchanged.
 
 > **Note**: `resultsPerPage` and `pageNumber` must always be provided — omitting them while also providing `searchString` causes the API to return error 1014 ("Fejl i formatering af inputs").
 
@@ -365,10 +366,10 @@ https://jobnet.dk/find-job/{jobAdId}
 ```
 
 The legacy `https://jobnet.dk/job/{jobAdId}` route redirects anonymous visitors into the
-MitID login flow, so it is never emitted. External ads (`isExternal: true`) 404 on `/find-job/`
+MitID login flow, so it is never emitted. External ads (`isExternal: true`) return 404 in a browser
-and hit the login wall on `/job/` - the search command routes external ads to their destination
+on `/find-job/` and hit the login wall on `/job/`. The search command keeps `url` canonical
-in `jobAdUrl` (falling back to `/find-job/{jobAdId}` when missing or not http(s)) instead of
+as `https://jobnet.dk/find-job/{jobAdId}` for all ads to preserve portal identity and route
-emitting a broken link.
+to `jobnet detail`, while providing the external destination in `applyUrl` (and `jobAdUrl`).
 
 Company logo images (prefix relative logoUrl from API):
 

.agents/skills/jobnet-search/cli/src/commands/search.ts

@@ -99,8 +99,9 @@ export function occupationId(value: string): string {
 /**
  * Return the destination URL for an external ad, if it has a valid http(s)
  * jobAdUrl. Only an absolute http(s) URL is used: the value is employer-supplied
- * and downstream steps fetch it. Anything else returns null and the caller keeps
+ * and downstream steps fetch it. Emitted in `applyUrl` (and `jobAdUrl`); `url`
- * the jobnet.dk route to preserve a unique URL for /scrape deduplication.
+ * always keeps the canonical jobnet.dk route across all postings. Anything
+ * else returns null.
  */
 export function externalAdUrl(job: Pick<JobAdRaw, "isExternal" | "jobAdUrl">): string | null {
   const raw = job.jobAdUrl?.trim()
@@ -140,6 +141,9 @@ export function createSearchOutput(data: SearchApiResponse, flags: SearchFlags)
       // /scrape contract aliases (add-portal.md: every result carries at least
       // id, title, company, location, date, url). `id` is the jobAdId - the
       // value `detail` takes - under the name every other portal CLI uses.
+      // `url` stays canonical on jobnet.dk for all postings (internal and external)
+      // so deduplication, health checks, and /apply host routing (#562) identify
+      // the portal correctly; external ATS destinations are emitted as `applyUrl`.
       id: job.jobAdId,
       company: job.hiringOrgName,
       location: job.postalDistrictName ?? job.municipality ?? null,
@@ -147,7 +151,8 @@ export function createSearchOutput(data: SearchApiResponse, flags: SearchFlags)
       deadline: job.applicationDeadline && !job.applicationDeadline.startsWith("1900-01-01")
         ? job.applicationDeadline.slice(0, 10)
         : null,
-      url: destination ?? `https://jobnet.dk/find-job/${job.jobAdId}`,
+      url: `https://jobnet.dk/find-job/${job.jobAdId}`,
+      applyUrl: destination,
     }
   })
 

.agents/skills/jobnet-search/cli/tests/search-normalization.test.ts

@@ -148,7 +148,8 @@ describe("Jobnet search normalization", () => {
       location: "København Ø",
       date: "2026-07-02",
       deadline: "2026-08-01",
-      url: "https://example.com/jobs/job-2",
+      url: "https://jobnet.dk/find-job/job-2",
+      applyUrl: "https://example.com/jobs/job-2",
       jobAdUrl: "https://example.com/jobs/job-2",
     });
     expect(output.results[0].hiringOrgName).toBe("Acme");
@@ -157,30 +158,35 @@ describe("Jobnet search normalization", () => {
     expect(output.results[0].id).toBe(output.results[0].jobAdId);
   });
 
-  test("external ads emit destination jobAdUrl as url, or fallback to find-job link when missing/invalid", () => {
+  test("external ads keep canonical find-job url and provide destination as applyUrl and jobAdUrl", () => {
     const response = apiResponse();
-    // External ad with valid http(s) jobAdUrl emits that URL
+    // External ad with valid http(s) jobAdUrl emits canonical url and destination applyUrl/jobAdUrl
     response.jobAds[1].isExternal = true;
     response.jobAds[1].jobAdUrl = "https://employer.example/apply";
     const withUrl = createSearchOutput(response, { ...flags, limit: undefined });
-    expect(withUrl.results[1].url).toBe("https://employer.example/apply");
+    expect(withUrl.results[1].url).toBe("https://jobnet.dk/find-job/job-2");
+    expect(withUrl.results[1].applyUrl).toBe("https://employer.example/apply");
     expect(withUrl.results[1].jobAdUrl).toBe("https://employer.example/apply");
+    expect(withUrl.results[1].isExternal).toBe(true);
 
-    // External ad without jobAdUrl falls back to find-job link to preserve a unique URL for /scrape deduplication
+    // External ad without jobAdUrl keeps canonical find-job url and null applyUrl/jobAdUrl
     response.jobAds[1].jobAdUrl = null;
     const withoutUrl = createSearchOutput(response, { ...flags, limit: undefined });
     expect(withoutUrl.results[1].url).toBe("https://jobnet.dk/find-job/job-2");
+    expect(withoutUrl.results[1].applyUrl).toBeNull();
     expect(withoutUrl.results[1].jobAdUrl).toBeNull();
     expect(withoutUrl.results[1].isExternal).toBe(true);
 
-    // External ad with non-http(s) scheme falls back to find-job link and clears jobAdUrl
+    // External ad with non-http(s) scheme keeps canonical find-job url and null applyUrl/jobAdUrl
     response.jobAds[1].jobAdUrl = "javascript:alert(1)";
     const invalidUrl = createSearchOutput(response, { ...flags, limit: undefined });
     expect(invalidUrl.results[1].url).toBe("https://jobnet.dk/find-job/job-2");
+    expect(invalidUrl.results[1].applyUrl).toBeNull();
     expect(invalidUrl.results[1].jobAdUrl).toBeNull();
 
-    // Internal ad always keeps find-job link
+    // Internal ad always keeps find-job link and null applyUrl
     expect(withoutUrl.results[0].url).toBe("https://jobnet.dk/find-job/job-1");
+    expect(withoutUrl.results[0].applyUrl).toBeNull();
     expect(withoutUrl.results[0].isExternal).toBe(false);
   });
 

CHANGELOG.md

@@ -328,6 +328,19 @@ per-file diff commands.
   no total deadline. `size=` in the status line is now the saved file's size on both paths, and step 3
   of `09-web-research.md` says an exit 1 can come from a redirect target's policy.
 
+- **`jobnet-search` keeps canonical portal URLs for external ads and emits destination in `applyUrl`**
+  (#706, fixes #701, `.agents/skills/jobnet-search/cli/src/commands/search.ts`,
+  `tests/search-normalization.test.ts`) - external job ads in search results emitted the
+  external employer ATS link directly in `url` (#557), which tripped `/scrape`'s Step 4.75 degraded
+  scan ("URLs that do not point at the portal") and caused `/apply` and `/rank`'s host-based routing
+  (#562) to send the posting to `WebFetch` on an ATS application form rather than `jobnet detail`.
+  `createSearchOutput` now keeps `url` canonical as `https://jobnet.dk/find-job/<id>` across all
+  ads (preserving identity, deduplication, and portal routing to `detail`), while emitting the
+  external employer ATS destination in `applyUrl` (matching the `applyUrl` field name on `detail`
+  in `jobindex` and `jobdanmark`) alongside `jobAdUrl`. For external ads, `url` is Jobnet's
+  canonical identity link, which 404s in a browser, and the employer page is `applyUrl` (search) or
+  the `Apply:` line of `detail`.
+
 ### Security
 
 - **CI no longer leaves the job token in `.git/config` or expands a PR-controlled name into a