/**
 * Stat-walk benchmark for the manifest builder (US-002).
 *
 * The acceptance bar is a cost bar, not a correctness one: a 70,000-file HQ
 * root must be enumerable in under 2 seconds and under 64 MB of resident
 * growth, because this runs in the background on a laptop that is also
 * running the user's editor. A regression here does not break the audit — it
 * makes the machine feel slow, which is the failure mode that gets the whole
 * feature switched off.
 *
 * The measurement is deliberately narrow:
 *
 *   - the fixture is built ONCE in `beforeAll` and excluded from the timing;
 *   - files are empty, so the numbers describe directory traversal + `lstat`,
 *     not disk throughput;
 *   - `hashPolicy: "ledger-only"` guarantees not a single byte of content is
 *     read, so sha256 throughput cannot mask a walk regression;
 *   - only `walkStats.walkMs` is asserted — the builder's own measurement of
 *     the walk, not the harness's view of the whole call.
 */
export {};
//# sourceMappingURL=build-manifest.bench.test.d.ts.map