feat(freehire-search): search returns each hit's full description (#251)

The skill queried /api/v1/jobs/search, whose `description` is the search
index's truncated preview — and the CLI dropped it entirely, so a result
carried only title/company/location/date/url. Reading a posting therefore
meant a `detail` call per hit, which is exactly what job-scraper's Step 2
prescribes: "fetch full detail with that portal's `detail` command".

freehire exposes a search endpoint for programmatic consumers,
/api/v1/agent/jobs/search: same query, ranking, facets and pagination, but
asked to (`include_description=true`) it replaces the preview with the
posting's full description read from the database, rendered as
`description_format=markdown|text|html`. Reproduce the difference:

  curl -s "https://freehire.me/api/v1/jobs/search?q=golang&limit=1" \
    | jq -r '.data[0].description | length'          # preview, capped
  curl -s "https://freehire.me/api/v1/agent/jobs/search?q=golang&limit=1\
&include_description=true&description_format=markdown" \
    | jq -r '.data[0].description | length'          # full text

So `search` now calls that endpoint, always asking for full descriptions,
and each JSON result carries `description` verbatim — no client-side HTML
stripping, since the API already rendered it. Markdown is the default
because it preserves the headings and requirement lists /rank reasons over;
`--description-format text|html` selects the others. The flag is validated
client-side: the API answers an unrecognized format with raw HTML rather
than an error, so a typo would silently change the output instead of
failing.

`table` and `plain` stay description-free — a full posting body would swamp
a scannable list — and `detail` is untouched, for looking one posting up by
slug (including a closed one, absent from search).

One behaviour change beyond the endpoint: a 404 from the search path used
to be folded into an empty result set. On the agent endpoint a 404 means
the instance predates it — a self-hosted freehire behind FREEHIRE_API_URL —
so it is now reported as an error naming the path, instead of a plausible
"no results" that hides the misconfiguration.

Tests cover the requested URL and params, verbatim (unstripped) markdown,
the null-when-absent case, the 404-is-an-error contract, and the flag
validation. All network-free.
This commit is contained in:
Ilya Strelov
2026-07-28 21:19:24 +02:00
committed by GitHub
parent 1c74a57c5e
commit e3af401087
9 changed files with 220 additions and 22 deletions
@@ -15,12 +15,32 @@ function captureStdout(): { get: () => string } {
return { get: () => buf };
}
function mockFetch(status: number, body: unknown): void {
globalThis.fetch = (async () =>
new Response(typeof body === "string" ? body : JSON.stringify(body), {
/** Stub fetch with a canned response; the return value exposes the URL it was called with. */
function mockFetch(status: number, body: unknown): { url: () => string } {
let requested = "";
globalThis.fetch = (async (input: string | URL | Request) => {
requested = typeof input === "string" ? input : input instanceof URL ? input.href : input.url;
return new Response(typeof body === "string" ? body : JSON.stringify(body), {
status,
headers: { "content-type": "application/json" },
})) as typeof fetch;
});
}) as typeof fetch;
return { url: () => requested };
}
/** The query params of the URL the mocked fetch was called with. */
function requestedParams(mock: { url: () => string }): URLSearchParams {
return new URL(mock.url()).searchParams;
}
function captureStderr(): { get: () => string; restore: () => void } {
let buf = "";
const original = process.stderr.write;
process.stderr.write = ((chunk: string | Uint8Array) => {
buf += chunk.toString();
return true;
}) as typeof process.stderr.write;
return { get: () => buf, restore: () => (process.stderr.write = original) };
}
function job(overrides: Partial<FreehireJob> = {}): FreehireJob {
@@ -56,6 +76,7 @@ const searchOpts = {
page: 1,
limit: 25,
format: "json" as const,
descriptionFormat: "markdown" as const,
regions: [] as string[],
countries: [] as string[],
cities: [] as string[],
@@ -80,6 +101,61 @@ describe("runSearch (mocked fetch)", () => {
expect(parsed.results[0].date).toBe("2026-07-06T00:00:00Z");
});
test("queries the agent endpoint asking for full descriptions", async () => {
const mock = mockFetch(200, { data: [job()], meta: { total: 1 } });
captureStdout();
await runSearch({ ...searchOpts, query: "backend" });
expect(new URL(mock.url()).pathname).toBe("/api/v1/agent/jobs/search");
expect(requestedParams(mock).get("include_description")).toBe("true");
expect(requestedParams(mock).get("description_format")).toBe("markdown");
});
test("asks for the requested description format", async () => {
const mock = mockFetch(200, { data: [job()], meta: { total: 1 } });
captureStdout();
await runSearch({ ...searchOpts, descriptionFormat: "text", query: "backend" });
expect(requestedParams(mock).get("description_format")).toBe("text");
});
test("carries each hit's description verbatim, in the server's format", async () => {
const markdown = "## About the role\n\n- Write Go\n- Ship things";
mockFetch(200, { data: [job({ description: markdown })], meta: { total: 1 } });
const out = captureStdout();
await runSearch({ ...searchOpts, query: "backend" });
expect(JSON.parse(out.get()).results[0].description).toBe(markdown);
});
test("a hit with no description carries null, not an empty string", async () => {
mockFetch(200, { data: [job({ description: "" })], meta: { total: 1 } });
const out = captureStdout();
await runSearch({ ...searchOpts, query: "backend" });
expect(JSON.parse(out.get()).results[0].description).toBeNull();
});
// A self-hosted freehire predating /agent/jobs/search answers 404, which apiGet
// maps to null. Reporting that as "no results" would hide a broken endpoint
// behind an empty, plausible-looking result set.
test("a 404 from the search endpoint is an error, not an empty result set", async () => {
mockFetch(404, { error: "not found" });
const err = captureStderr();
const out = captureStdout();
const code = await runSearch({ ...searchOpts, query: "backend" });
err.restore();
expect(code).toBe(1);
expect(out.get()).toBe("");
expect(JSON.parse(err.get()).error).toMatch(/agent\/jobs\/search/);
});
test("empty result set yields an empty results array", async () => {
mockFetch(200, { data: [], meta: { total: 0 } });
const out = captureStdout();