Name new corpus programs instead of numbering them (#2270)

AGENTS.md

@@ -46,6 +46,8 @@ SCRIPTC_TEST_WORKERS=4 SCRIPTC_SAN=1 pnpm test  # sanitized lane
 
 Corpus programs are differential tests against Node: every program runs under Node and as a compiled native binary, and stdout, stderr, and exit codes must match byte-for-byte. A new feature lands with corpus programs that pin its behavior both ways.
 
+Name a new corpus program after what it tests, without a number: lowercase words joined by hyphens, such as `tests/corpus/intersection-restated-members.ts`, or a directory such as `tests/corpus/<name>/main.ts` for a multi-file program. Parallel changes kept taking the same next number; with names, two changes collide only when they add the same name, which git reports as a conflict. Leave existing numbered programs as they are: never rename or renumber them, and name a new program even when it extends a numbered family.
+
 Record a new or remeasured program's CI cost (used to balance the test shards) in `tests/harness/corpus-costs/<program>.json`, not in `tests/harness/corpus-costs.json`; see the README there.
 
 Before opening a PR that adds or changes corpus, diagnostic, or frontend fixtures, run `pnpm test:ts7 --baselines-only`. This fast completeness check uses the same fixture discovery as the parity suite; it does not type-check or replace behavioral parity. Generate missing preflight/order baselines, review their diagnostics and module order, and run the affected `order-parity.test.ts` batches before pushing. Keep existing baseline entries unchanged unless the corresponding behavior intentionally changes. The full `pnpm test:ts7` command also checks completeness before starting its sweep.

scripts/lowering-order.mjs

@@ -16,13 +16,16 @@
  *     [--seeds 1,2,3] [--jobs 8] [--entry <file.ts>]... [--out <dir>]
  *     [--fail-on names|content]
  *
+ * --stride and --offset sample the top-level corpus programs by number, or by
+ * a hash of the name of a program without one.
+ *
  * Needs a built compiler (pnpm build). Writes <out>/results.json and prints
  * a ranking of fields by the programs whose IR they change. With --fail-on,
  * it exits with status 1 when some program's IR differs between orders:
  * in any way (names), or beyond names and ids (content). */
 import { spawn } from "node:child_process";
 import { createHash } from "node:crypto";
-import { mkdirSync, readFileSync, readdirSync, writeFileSync } from "node:fs";
+import { mkdirSync, readFileSync, readdirSync, statSync, writeFileSync } from "node:fs";
 import { cpus, tmpdir } from "node:os";
 import { basename, join, resolve } from "node:path";
 import { fileURLToPath, pathToFileURL } from "node:url";
@@ -306,12 +309,25 @@ if (values["fail-on"] !== undefined && !["names", "content"].includes(values["fa
 const out = resolve(values.out);
 mkdirSync(out, { recursive: true });
 const seeds = values.seeds.split(",").filter(Boolean);
+/** A top-level corpus program's sampling key: its number, or, for a program
+ * named without one, a stable hash of its name (FNV-1a). */
+const programKey = (name) =>
+  /^\d+-/.test(name)
+    ? Number.parseInt(name, 10)
+    : [...name].reduce((h, c) => Math.imul(h ^ c.charCodeAt(0), 16777619) >>> 0, 2166136261);
+/** Numbered programs by number, then the named ones by name. */
+const programOrder = (a, b) =>
+  /^\d+-/.test(a) !== /^\d+-/.test(b)
+    ? /^\d+-/.test(a)
+      ? -1
+      : 1
+    : programKey(a) - programKey(b) || (a < b ? -1 : a > b ? 1 : 0);
 const corpus = join(root, "tests/corpus");
 const programs = [
   ...readdirSync(corpus)
-    .filter((name) => /^\d+-.*\.ts$/.test(name))
-    .filter((name) => Number.parseInt(name, 10) % Number(values.stride) === Number(values.offset))
-    .sort((a, b) => Number.parseInt(a, 10) - Number.parseInt(b, 10))
+    .filter((name) => /^[\w-]+\.ts$/.test(name) && statSync(join(corpus, name)).isFile())
+    .filter((name) => programKey(name) % Number(values.stride) === Number(values.offset))
+    .sort(programOrder)
     .slice(0, Number(values.limit))
     .map((name) => join(corpus, name)),
   ...values.entry.map((entry) => resolve(entry)),

scripts/refresh-cli-profile.mjs

@@ -7,8 +7,9 @@
  * Builds an instrumented native compiler for this Linux host, runs it on the
  * training builds below, and merges the raw profiles it writes into one
  * sparse indexed profile. The training builds are tsc-ts (a cold `speed`
- * build, then a rebuild after an edit), every seventh corpus program at the
- * default optimization and a further slice in `dev`, and the runtime
+ * build, then a rebuild after an edit), every seventh top-level corpus
+ * program (by number, or by a hash of the name of a program without one) at
+ * the default optimization and a further slice in `dev`, and the runtime
  * benchmark workloads. Run it on a quiet Linux x64 host after changes that
  * move much compiler code; a stale profile only loses part of its gain. A
  * refresh takes about 11 minutes on 16 cores.
@@ -126,16 +127,30 @@ async function pool(tasks) {
   return passed;
 }
 
-const programNumber = (name) => Number.parseInt(name, 10);
+/** A top-level corpus program's sampling key: its number, or, for a program
+ * named without one, a stable hash of its name (FNV-1a). */
+const programKey = (name) =>
+  /^\d+-/.test(name)
+    ? Number.parseInt(name, 10)
+    : [...name].reduce((h, c) => Math.imul(h ^ c.charCodeAt(0), 16777619) >>> 0, 2166136261);
+/** Numbered programs by number, then the named ones by name. */
+const programOrder = (a, b) =>
+  /^\d+-/.test(a) !== /^\d+-/.test(b)
+    ? /^\d+-/.test(a)
+      ? -1
+      : 1
+    : programKey(a) - programKey(b) || (a < b ? -1 : a > b ? 1 : 0);
 const corpus = readdirSync(join(root, "tests/corpus"))
-  .filter((name) => /^\d+-.*\.ts$/.test(name))
-  .sort((a, b) => programNumber(a) - programNumber(b));
+  .filter(
+    (name) => /^[\w-]+\.ts$/.test(name) && statSync(join(root, "tests/corpus", name)).isFile(),
+  )
+  .sort(programOrder);
 const training = [
   ...corpus
-    .filter((name) => programNumber(name) % 7 === 0)
+    .filter((name) => programKey(name) % 7 === 0)
     .map((name) => ({ file: join(root, "tests/corpus", name), optimization: "release" })),
   ...corpus
-    .filter((name) => programNumber(name) % 14 === 7)
+    .filter((name) => programKey(name) % 14 === 7)
     .map((name) => ({ file: join(root, "tests/corpus", name), optimization: "dev" })),
   ...readdirSync(join(root, "benchmarks/runtime/workloads"))
     .filter((name) => name.endsWith(".ts"))