feat(freehire-search): add --no-description for cheap discovery passes

A default search hydrates full bodies - ~73% of the payload, ~20k tokens
per query fed into agent context - while /scrape's own Step 2 says to
pre-filter by title before reading bodies. The flag keeps every other
field and drops the bodies (live 10-result search: ~58k -> ~10k chars);
hydration stays the default per the documented trade-off. The API
returns bodies regardless of include_description=false (verified live),
so the lean guarantee is enforced client-side. Review opportunity O1
(2026-08-19), approved as an enhancement.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Mads Lorentzen
2026-08-19 21:05:54 +02:00
co-authored by Claude Opus 5
parent c85640e30a
commit dd02c82485
5 changed files with 50 additions and 6 deletions
@@ -81,6 +81,8 @@ SEARCH FLAGS
--page <n> 1-indexed page. Default 1.
--limit, -n <n> Results per page (API limit). Default 25.
--format <fmt> json (default) | table | plain.
--no-description Skip description hydration for a cheap discovery pass
(results keep every other field; detail fetches the body).
--description-format markdown (default) | text | html — how each result's
full description is rendered (json output only).
@@ -124,7 +126,7 @@ function parseIntFlag(name: string, raw: string | boolean | string[]): number |
const KNOWN_FLAGS: Record<string, Set<string>> = {
search: new Set([
"query", "category", "city", "company", "country", "facet", "format", "jobage", "limit",
"page", "region", "remote", "seniority", "skill", "description-format", "help", "h",
"page", "region", "remote", "seniority", "skill", "description-format", "no-description", "help", "h",
]),
detail: new Set(["format", "description-format", "help", "h"]),
}
@@ -202,6 +204,7 @@ async function main(): Promise<number> {
limit: flags.limit ? Math.max(1, parseInt(flags.limit as string, 10)) : 25,
format: (["json", "table", "plain"].includes(fmt) ? fmt : "json") as SearchOpts["format"],
descriptionFormat: descFmt as DescriptionFormat,
includeDescription: flags["no-description"] === undefined,
regions: commaList(flags.region),
countries: commaList(flags.country),
cities: commaList(flags.city),
@@ -18,6 +18,10 @@ export interface SearchOpts {
limit: number
format: "json" | "table" | "plain"
descriptionFormat: DescriptionFormat
// Hydrate full description bodies (the documented default). False keeps a
// discovery pass cheap: bodies are ~73% of a default search payload, and
// /scrape pre-filters by title before reading bodies anyway.
includeDescription?: boolean
// Facet filters (already parsed into value lists; empty means unset).
regions: string[]
countries: string[]
@@ -38,9 +42,11 @@ function buildQuery(opts: SearchOpts): URLSearchParams {
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.
p.set("include_description", "true")
p.set("description_format", opts.descriptionFormat)
// 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.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)
@@ -117,7 +123,14 @@ export async function runSearch(opts: SearchOpts): Promise<number> {
)
return 1
}
const rows = (env.data ?? []).map(toResult)
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.
if (opts.includeDescription === false) {
rows = rows.map((r) => ({ ...r, description: null }))
}
const total = env.meta?.total ?? rows.length
if (opts.format === "table") {
@@ -112,6 +112,24 @@ describe("runSearch (mocked fetch)", () => {
expect(requestedParams(mock).get("description_format")).toBe("markdown");
});
test("skips description hydration when includeDescription is false", async () => {
// A default search hydrates ~20k tokens of description bodies per query,
// while /scrape's Step 2 says to pre-filter by title/snippet before
// reading bodies. --no-description keeps the discovery pass cheap;
// hydration stays the default (review opportunity O1, 2026-08-19).
const mock = mockFetch(200, { data: [job()], meta: { total: 1 } });
const out = captureStdout();
await runSearch({ ...searchOpts, query: "backend", includeDescription: false });
expect(requestedParams(mock).get("include_description")).toBe("false");
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.
const parsed = JSON.parse(out.get());
expect(parsed.results[0].description).toBeNull();
});
test("asks for the requested description format", async () => {
const mock = mockFetch(200, { data: [job()], meta: { total: 1 } });
captureStdout();