freehire-search: lean search uses the web endpoint; drop unread params (#631)

semantic_ratio and include_description are both reported in
meta.ignored_params. With include_description ignored, the agent endpoint
hydrates every full body from the database, and --no-description threw
that payload away client-side. Send --no-description to /api/v1/jobs/search,
which serves only the preview, and stop sending the two unread params.
This commit is contained in:
Ilya Strelov authored and GitHub committed 2026-10-18 21:38:40 +02:00
1 parent ce9b656829
commit 0f6480d32e
6 files changed
+31 -27

No files matched your search

+1 -1
View File
@@ -3,7 +3,7 @@
CLI for searching the [freehire.me](https://freehire.me) job aggregator across
**many markets** (tech-focused), via its public JSON API.
**Data source**: freehire.me REST API (`/api/v1/agent/jobs/search`, `/api/v1/jobs/facets`, `/api/v1/jobs/{slug}`).
**Data source**: freehire.me REST API (`/api/v1/agent/jobs/search`, `/api/v1/jobs/search` for `--no-description`, `/api/v1/jobs/facets`, `/api/v1/jobs/{slug}`).
**Authentication**: None required — reads are public (only tracking mutations need a key, and those are out of scope here).
**Dependencies**: None (plain `bun` + `fetch`). `bun install` is optional and only pulls dev type defs.
@@ -6,6 +6,12 @@ import { apiGet, toResult, writeError, type FreehireJob, type JobResult } from "
// follow-up `detail` per hit.
const SEARCH_PATH = "/api/v1/agent/jobs/search"
// The web search: identical query surface, but each hit carries only the index's
// truncated preview. --no-description uses it, because the agent endpoint reads
// every full body from the database whether or not the caller wants them - the
// lean mode would otherwise pay the expensive request and discard its payload.
const LEAN_SEARCH_PATH = "/api/v1/jobs/search"
/** How the API renders each result's full description. */
export type DescriptionFormat = "markdown" | "text" | "html"
@@ -40,13 +46,7 @@ function buildQuery(opts: SearchOpts): URLSearchParams {
if (opts.query) p.set("q", opts.query)
p.set("limit", String(opts.limit))
p.set("offset", String((opts.page - 1) * opts.limit))
p.set("semantic_ratio", "0") // keyword search; the semantic index is opt-in
// The agent endpoint serves the index's truncated preview unless asked to
// rehydrate each hit from the database, so both params travel together -
// unless the caller opted out of hydration entirely (--no-description).
const hydrate = opts.includeDescription !== false
p.set("include_description", hydrate ? "true" : "false")
if (hydrate) p.set("description_format", opts.descriptionFormat)
if (opts.includeDescription !== false) p.set("description_format", opts.descriptionFormat)
if (opts.jobage > 0 && opts.jobage < 9999) p.set("posted_within_days", String(opts.jobage))
if (opts.workMode) p.set("work_mode", opts.workMode)
if (opts.company) p.set("company_slug", opts.company)
@@ -112,22 +112,22 @@ function renderPlain(rows: JobResult[]): string {
export async function runSearch(opts: SearchOpts): Promise<number> {
try {
const env = await apiGet<FreehireJob[]>(`${SEARCH_PATH}?${buildQuery(opts).toString()}`)
const path = opts.includeDescription === false ? LEAN_SEARCH_PATH : SEARCH_PATH
const env = await apiGet<FreehireJob[]>(`${path}?${buildQuery(opts).toString()}`)
// A 404 here is a missing endpoint, not a missing job: a freehire instance
// older than the agent search surface answers that way, and reporting it as
// an empty result set would hide the misconfiguration behind plausible output.
if (!env) {
writeError(
`${SEARCH_PATH} not found — this freehire instance predates the agent search endpoint; upgrade it or unset FREEHIRE_API_URL to use the hosted API`,
`${path} not found — this freehire instance predates the search endpoint; upgrade it or unset FREEHIRE_API_URL to use the hosted API`,
"SEARCH_FAILED",
)
return 1
}
let rows = (env.data ?? []).map(toResult)
// The API currently returns description bodies regardless of
// include_description=false (verified live 2026-08-19), and the cost this
// flag exists to avoid is the ~73% of CLI output the bodies occupy in
// agent context - so the lean mode strips them client-side either way.
// The web search still carries each hit's truncated preview, and the cost
// this flag exists to avoid is the share of CLI output descriptions occupy
// in agent context - so the lean mode drops them client-side.
if (opts.includeDescription === false) {
rows = rows.map((r) => ({ ...r, description: null }))
}
@@ -108,8 +108,10 @@ describe("runSearch (mocked fetch)", () => {
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");
// Neither is read by the API (it lists both in meta.ignored_params).
expect(requestedParams(mock).get("include_description")).toBeNull();
expect(requestedParams(mock).get("semantic_ratio")).toBeNull();
});
test("skips description hydration when includeDescription is false", async () => {
@@ -122,10 +124,11 @@ describe("runSearch (mocked fetch)", () => {
const out = captureStdout();
await runSearch({ ...searchOpts, query: "backend", includeDescription: false });
expect(requestedParams(mock).get("include_description")).toBe("false");
// The agent endpoint hydrates every body regardless of what it is asked, so
// the lean pass goes to the web search, which serves only the preview.
expect(new URL(mock.url()).pathname).toBe("/api/v1/jobs/search");
expect(requestedParams(mock).get("description_format")).toBeNull();
// The live API ignores include_description=false and sends bodies anyway
// (verified 2026-08-19), so the lean guarantee is enforced client-side.
// The preview is still a description, so the lean guarantee is enforced client-side.
const parsed = JSON.parse(out.get());
expect(parsed.results[0].description).toBeNull();
});
@@ -55,7 +55,7 @@ describe("named search flags require their documented values", () => {
expect(params.getAll("skills")).toEqual(["go", "kubernetes"]);
expect(params.get("company_slug")).toBe("acme");
expect(params.get("work_mode")).toBe("remote");
expect(params.get("include_description")).toBe("false");
expect(requests[0].pathname).toBe("/api/v1/jobs/search");
} finally {
server.stop(true);
}