@genroc/eval-node 0.0.0-edge.f85ea85 → 0.0.0-edge.fb8c06a

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/import.ts CHANGED
@@ -1,3 +1,4 @@
1
+ #!/usr/bin/env node
1
2
  // The code-phase resolver: manifest on stdin, `{"code": [...]}` on stdout, non-zero exit
2
3
  // with the diagnostic on stderr. genctl never parses TypeScript and this never parses YAML
3
4
  // — the manifest is the whole contract. See specs/source-resolution.md.
@@ -7,9 +8,10 @@
7
8
  // over the same project.
8
9
 
9
10
  import { spawn } from "node:child_process";
11
+ import { existsSync } from "node:fs";
10
12
  import { access, mkdir, writeFile } from "node:fs/promises";
11
13
  import { builtinModules } from "node:module";
12
- import { dirname, join, relative } from "node:path";
14
+ import { dirname, join, relative, resolve } from "node:path";
13
15
  import { fileURLToPath } from "node:url";
14
16
 
15
17
  import commonjs from "@rollup/plugin-commonjs";
@@ -21,20 +23,37 @@ import ts from "typescript";
21
23
  type Schema = Record<string, any>;
22
24
 
23
25
  type Site = {
24
- resolver: string;
25
- process: string;
26
+ // Which namespace the directive sits in: `process`, `task` or `action`.
27
+ level: "process" | "task" | "action";
26
28
  task?: string;
27
- pointer: string;
28
- path: string;
29
- input?: Schema;
30
- output?: Schema;
29
+ // What the site IS, at action level: the action's type, and the process a child call names.
30
+ action?: string;
31
+ child?: string;
32
+ // The slot as a path of keys and indices, so nothing has to unescape a JSON Pointer.
33
+ pointer: (string | number)[];
34
+ // Everything after `$<resolver>:`, verbatim. genctl does not read it as a path — that is
35
+ // this resolver's reading of it.
36
+ argument: string;
37
+ // What .genroc asked genctl to type, keyed by the name it chose. This resolver reads Input
38
+ // and Output; which ADDRESS each came from is the config's business, not ours.
39
+ types?: Record<string, Schema>;
40
+ };
41
+
42
+ type ManifestProcess = {
43
+ name: string;
44
+ // The definition's own location, split because a relative argument is relative to the
45
+ // DIRECTORY — joining is ours to do, and this is the base.
46
+ dir: string;
47
+ file: string;
48
+ sites: Site[];
49
+ // Only what this process's fragments reach — a `$ref` in `types` points here.
50
+ $defs?: Record<string, Schema>;
31
51
  };
32
52
 
33
53
  type Manifest = {
34
54
  mode: "types" | "build";
35
55
  root: string;
36
- schemas: Record<string, Schema>;
37
- sites: Site[];
56
+ processes: ManifestProcess[];
38
57
  };
39
58
 
40
59
  function die(message: string): never {
@@ -71,13 +90,16 @@ function tsType(s: Schema | undefined, used: Set<string>): string {
71
90
  if (Array.isArray(s.enum)) {
72
91
  return s.enum.map((v: unknown) => JSON.stringify(v)).join(" | ") || "never";
73
92
  }
74
- if (Array.isArray(s.anyOf)) return union(s.anyOf.map((a: Schema) => tsType(a, used)));
75
- if (Array.isArray(s.oneOf)) return union(s.oneOf.map((a: Schema) => tsType(a, used)));
93
+ if (Array.isArray(s.anyOf))
94
+ return union(s.anyOf.map((a: Schema) => tsType(a, used)));
95
+ if (Array.isArray(s.oneOf))
96
+ return union(s.oneOf.map((a: Schema) => tsType(a, used)));
76
97
  if (Array.isArray(s.allOf)) {
77
98
  return s.allOf.map((a: Schema) => tsType(a, used)).join(" & ") || "unknown";
78
99
  }
79
100
 
80
- const types: string[] = s.type === undefined ? [] : Array.isArray(s.type) ? s.type : [s.type];
101
+ const types: string[] =
102
+ s.type === undefined ? [] : Array.isArray(s.type) ? s.type : [s.type];
81
103
  if (types.length === 0) {
82
104
  // The top type: `{}` means unknown, not "an empty object". specs/unknown-type.md.
83
105
  return s.properties ? objectType(s, used) : "unknown";
@@ -110,8 +132,13 @@ function objectType(s: Schema, used: Set<string>): string {
110
132
  const required = new Set<string>(s.required ?? []);
111
133
  const lines: string[] = [];
112
134
  for (const [key, sub] of Object.entries(props)) {
113
- const doc = typeof sub.description === "string" ? ` /** ${sub.description} */\n` : "";
114
- lines.push(`${doc} ${propKey(key)}${required.has(key) ? "" : "?"}: ${tsType(sub, used)};`);
135
+ const doc =
136
+ typeof sub.description === "string"
137
+ ? ` /** ${sub.description} */\n`
138
+ : "";
139
+ lines.push(
140
+ `${doc} ${propKey(key)}${required.has(key) ? "" : "?"}: ${tsType(sub, used)};`,
141
+ );
115
142
  }
116
143
  if (s.additionalProperties && typeof s.additionalProperties === "object") {
117
144
  lines.push(` [key: string]: ${tsType(s.additionalProperties, used)};`);
@@ -127,9 +154,13 @@ function union(parts: string[]): string {
127
154
 
128
155
  const IDENT = /^[A-Za-z_$][A-Za-z0-9_$]*$/;
129
156
  const propKey = (k: string) => (IDENT.test(k) ? k : JSON.stringify(k));
130
- const identifier = (n: string) => (IDENT.test(n) ? n : `Def_${n.replace(/[^A-Za-z0-9_$]/g, "_")}`);
157
+ const identifier = (n: string) =>
158
+ IDENT.test(n) ? n : `Def_${n.replace(/[^A-Za-z0-9_$]/g, "_")}`;
131
159
 
132
- function deref(s: Schema | undefined, defs: Record<string, Schema>): Schema | undefined {
160
+ function deref(
161
+ s: Schema | undefined,
162
+ defs: Record<string, Schema>,
163
+ ): Schema | undefined {
133
164
  let cur = s;
134
165
  for (let i = 0; cur && typeof cur.$ref === "string" && i < 16; i++) {
135
166
  cur = defs[cur.$ref.replace(/^#\/\$defs\//, "")];
@@ -137,22 +168,14 @@ function deref(s: Schema | undefined, defs: Record<string, Schema>): Schema | un
137
168
  return cur;
138
169
  }
139
170
 
140
- /** The manifest's `input` is the type of the whole ACTION input — for /eval that is
141
- * `{code, input, timeout_ms, …}`, and only its `input` field is bound as the script's
142
- * parameter. genroc cannot know that; this file owns the evaluator's wire contract, so
143
- * the navigation belongs here rather than in genctl. */
144
- function scriptInput(site: Site, defs: Record<string, Schema>): Schema | undefined {
145
- const action = deref(site.input, defs);
146
- const bound = action?.properties?.input;
147
- return bound ?? site.input;
148
- }
149
-
150
171
  /** Emits one named type per reachable $def rather than inlining: a task output may
151
172
  * reference itself (specs/recursive-type-inference.md) and inlining would not terminate. */
152
- function declarations(site: Site, defs: Record<string, Schema>): string {
173
+ function declarations(at: Located): string {
174
+ const { site, where } = at;
175
+ const defs = where.$defs ?? {};
153
176
  const used = new Set<string>();
154
- const input = tsType(scriptInput(site, defs), used);
155
- const output = tsType(site.output, used);
177
+ const input = tsType(site.types?.Input, used);
178
+ const output = tsType(site.types?.Output, used);
156
179
 
157
180
  const emitted: string[] = [];
158
181
  const done = new Set<string>();
@@ -166,7 +189,7 @@ function declarations(site: Site, defs: Record<string, Schema>): string {
166
189
 
167
190
  return [
168
191
  "// Generated by genroc. Do not edit - regenerate with `genctl types`.",
169
- `// ${site.process}${site.task ? ` / ${site.task}` : ""} (${site.pointer})`,
192
+ `// ${where.name} (${address(site.pointer)})`,
170
193
  "",
171
194
  ...emitted,
172
195
  emitted.length ? "" : "",
@@ -188,7 +211,10 @@ function typesPathFor(scriptPath: string): string {
188
211
  /** The nearest tsconfig above the script — the one the author's editor already reads. Two
189
212
  * different configs mean a red editor over a clean apply, or the reverse. The walk stops at
190
213
  * the project root: above it is not this project. */
191
- async function nearestTsconfig(from: string, root: string): Promise<string | null> {
214
+ async function nearestTsconfig(
215
+ from: string,
216
+ root: string,
217
+ ): Promise<string | null> {
192
218
  for (let dir = from; ; dir = dirname(dir)) {
193
219
  const candidate = join(dir, "tsconfig.json");
194
220
  if (await exists(candidate)) return candidate;
@@ -196,7 +222,7 @@ async function nearestTsconfig(from: string, root: string): Promise<string | nul
196
222
  }
197
223
  }
198
224
 
199
- async function typecheck(root: string, sites: Site[]): Promise<void> {
225
+ async function typecheck(sites: Located[]): Promise<void> {
200
226
  // NOT `.genroc`: that is the project config FILE, and a directory of the same name cannot
201
227
  // coexist with it. The suffix is what keeps the scratch area out of its way.
202
228
  const dir = join(root, ".genroc-cache");
@@ -204,12 +230,12 @@ async function typecheck(root: string, sites: Site[]): Promise<void> {
204
230
 
205
231
  // One tsc per distinct base config: `extends` takes a single base, so merging two would
206
232
  // check each script under the other author's options.
207
- const groups = new Map<string, Site[]>();
208
- for (const site of sites) {
209
- const base = (await nearestTsconfig(dirname(site.path), root)) ?? "";
233
+ const groups = new Map<string, Located[]>();
234
+ for (const at of sites) {
235
+ const base = (await nearestTsconfig(dirname(at.file), root)) ?? "";
210
236
  const group = groups.get(base);
211
- if (group) group.push(site);
212
- else groups.set(base, [site]);
237
+ if (group) group.push(at);
238
+ else groups.set(base, [at]);
213
239
  }
214
240
 
215
241
  let n = 0;
@@ -231,12 +257,18 @@ async function typecheck(root: string, sites: Site[]): Promise<void> {
231
257
  // base config there is nothing to opt in with, so the default stays none.
232
258
  ...(base ? {} : { types: [] }),
233
259
  },
234
- files: group.flatMap((s) => [relative(dir, s.path), relative(dir, typesPathFor(s.path))]),
260
+ files: group.flatMap((s) => [
261
+ relative(dir, s.file),
262
+ relative(dir, typesPathFor(s.file)),
263
+ ]),
235
264
  // `files` overrides the base's, but a base `include` survives beside it and would
236
265
  // drag the author's whole tree in, to be checked under the worker lib.
237
266
  include: [],
238
267
  };
239
- const configPath = join(dir, groups.size === 1 ? "tsconfig.json" : `tsconfig.${n++}.json`);
268
+ const configPath = join(
269
+ dir,
270
+ groups.size === 1 ? "tsconfig.json" : `tsconfig.${n++}.json`,
271
+ );
240
272
  await write(configPath, JSON.stringify(config, null, 2));
241
273
  await runTsc(root, configPath);
242
274
  }
@@ -284,7 +316,10 @@ const transpile: Plugin = {
284
316
  },
285
317
  };
286
318
 
287
- const BUILTIN = new Set([...builtinModules, ...builtinModules.map((m) => `node:${m}`)]);
319
+ const BUILTIN = new Set([
320
+ ...builtinModules,
321
+ ...builtinModules.map((m) => `node:${m}`),
322
+ ]);
288
323
 
289
324
  /** Resolves imports through TYPESCRIPT, using the same config the typecheck ran under, so a
290
325
  * `paths` alias that compiles also bundles. Reimplementing `paths` here would be a second
@@ -295,31 +330,44 @@ function tsResolve(configPath: string | null): Plugin {
295
330
  let options: ts.CompilerOptions = {};
296
331
  if (configPath) {
297
332
  const read = ts.readConfigFile(configPath, ts.sys.readFile);
298
- options = ts.parseJsonConfigFileContent(read.config ?? {}, ts.sys, dirname(configPath)).options;
333
+ options = ts.parseJsonConfigFileContent(
334
+ read.config ?? {},
335
+ ts.sys,
336
+ dirname(configPath),
337
+ ).options;
299
338
  }
300
339
  return {
301
340
  name: "genroc-ts-resolve",
302
341
  resolveId(source, importer) {
303
342
  if (!importer || BUILTIN.has(source)) return null;
304
- const { resolvedModule } = ts.resolveModuleName(source, importer, options, ts.sys);
305
- if (!resolvedModule || resolvedModule.isExternalLibraryImport) return null;
306
- return resolvedModule.resolvedFileName.endsWith(".d.ts") ? null : resolvedModule.resolvedFileName;
343
+ const { resolvedModule } = ts.resolveModuleName(
344
+ source,
345
+ importer,
346
+ options,
347
+ ts.sys,
348
+ );
349
+ if (!resolvedModule || resolvedModule.isExternalLibraryImport)
350
+ return null;
351
+ return resolvedModule.resolvedFileName.endsWith(".d.ts")
352
+ ? null
353
+ : resolvedModule.resolvedFileName;
307
354
  },
308
355
  };
309
356
  }
310
357
 
311
- /** Bundles to CJS and wraps it as an async function BODY, which is what /eval compiles.
312
- * The runtime stays unchanged: bundling is entirely the importer's job, and the string it
313
- * produces is self-contained, so a definition version pins its code forever. */
314
- async function bundle(site: Site, root: string): Promise<string> {
315
- // Builtins are EXTERNALISED as `require` calls that worker.ts satisfies. Anything else
316
- // unresolved is a REFUSAL, not an external: rollup's default is to leave it as a require
358
+ /** Bundles to a self-contained ES module, which is what the evaluator imports: the default
359
+ * export it calls is the author's own, so nothing wraps or rewrites the code between the two.
360
+ * Bundling is entirely the importer's job, so a definition version pins its code forever. */
361
+ async function bundle(at: Located): Promise<string> {
362
+ const site = at.site;
363
+ // Builtins are EXTERNALISED as imports the realm resolves natively. Anything else
364
+ // unresolved is a REFUSAL, not an external: rollup's default is to leave it as an import
317
365
  // of a module that will not be there, which bundles clean and fails at runtime.
318
366
  const built = await rollup({
319
- input: site.path,
367
+ input: at.file,
320
368
  external: (id) => BUILTIN.has(id),
321
369
  plugins: [
322
- tsResolve(await nearestTsconfig(dirname(site.path), root)),
370
+ tsResolve(await nearestTsconfig(dirname(at.file), root)),
323
371
  nodeResolve({ extensions: [".ts", ".tsx", ".mjs", ".js", ".json"] }),
324
372
  commonjs(),
325
373
  // A `.json` import is a data file inlined at build time, which the previous bundler
@@ -329,23 +377,26 @@ async function bundle(site: Site, root: string): Promise<string> {
329
377
  ],
330
378
  onwarn(warning) {
331
379
  if (warning.code === "UNRESOLVED_IMPORT") {
332
- die(`${site.path}: cannot resolve ${warning.exporter ?? "an import"} — is it installed?`);
380
+ die(
381
+ `${at.file}: cannot resolve ${warning.exporter ?? "an import"} — is it installed?`,
382
+ );
333
383
  }
334
384
  },
335
- }).catch((e: unknown) => die(`${site.path}: ${e instanceof Error ? e.message : String(e)}`));
385
+ }).catch((e: unknown) =>
386
+ die(`${at.file}: ${e instanceof Error ? e.message : String(e)}`),
387
+ );
336
388
 
337
- const { output } = await built.generate({ format: "cjs", exports: "auto", inlineDynamicImports: true });
389
+ const { output } = await built.generate({
390
+ format: "es",
391
+ inlineDynamicImports: true,
392
+ });
338
393
  await built.close();
339
- const cjs = output[0].code;
340
- return [
341
- "var module = { exports: {} }, exports = module.exports;",
342
- cjs,
343
- "var __genroc_main = module.exports.default ?? module.exports;",
344
- 'if (typeof __genroc_main !== "function") {',
345
- ` throw new Error(${JSON.stringify(`${site.path} has no default export function`)});`,
346
- "}",
347
- "return await __genroc_main(input);",
348
- ].join("\n");
394
+ // Refused here rather than in the realm: the evaluator can only report it against a running
395
+ // instance, and the file it names is on this machine.
396
+ if (!output[0].exports.includes("default")) {
397
+ die(`${at.file}: a script must \`export default\` the function to run`);
398
+ }
399
+ return output[0].code;
349
400
  }
350
401
 
351
402
  // ── main ───────────────────────────────────────────────────────────────────────
@@ -358,40 +409,99 @@ const stdin: string = await new Promise((resolve, reject) => {
358
409
  process.stdin.on("error", reject);
359
410
  });
360
411
  const manifest = JSON.parse(stdin) as Manifest;
361
- if (!manifest || !Array.isArray(manifest.sites)) die("stdin is not a genroc resolver manifest");
412
+ // genctl runs a resolver with the project root as its cwd, so the manifest need not say so.
413
+ const root = process.cwd();
414
+ if (!manifest || !Array.isArray(manifest.processes))
415
+ die("stdin is not a genroc resolver manifest");
416
+
417
+ /** Every site with the process it sits in and the file its argument names, in the manifest's own
418
+ * order — which is the order `code` must answer in. genctl passes the argument verbatim, so
419
+ * joining it to the definition's directory is this resolver's business: only it knows the
420
+ * argument is a path at all. */
421
+ type Located = { site: Site; where: ManifestProcess; file: string };
422
+
423
+ /** A pointer as the address it is, so a generated comment or an error can be pasted into
424
+ * `genctl schema`. A key no identifier can spell is bracketed, as the grammar spells it. */
425
+ function address(pointer: (string | number)[]): string {
426
+ return pointer
427
+ .map((seg) =>
428
+ typeof seg === "string" && /^[A-Za-z_][A-Za-z0-9_]*$/.test(seg)
429
+ ? `.${seg}`
430
+ : `[${JSON.stringify(seg)}]`,
431
+ )
432
+ .join("")
433
+ .replace(/^\./, "");
434
+ }
435
+ const located: Located[] = manifest.processes.flatMap((where) =>
436
+ where.sites.map((site) => ({
437
+ site,
438
+ where,
439
+ file: resolve(where.dir, site.argument),
440
+ })),
441
+ );
442
+
443
+ // genctl is agnostic about what a script is for; the contract that an evaluation request carries
444
+ // its module in `code` is THIS resolver's, so it is the one that checks a directive landed there.
445
+ // `child` is the shape the scaffold uses — a call to a process that forwards to the evaluator —
446
+ // and `external` is the same request made directly.
447
+ for (const at of located) {
448
+ // Two halves, from the two places that carry them: the action's KIND is a field, and WHERE in
449
+ // it the directive sits is the pointer. A child call is the shape the scaffold generates — to a
450
+ // process that forwards to the evaluator — and an external task is the same request made
451
+ // directly.
452
+ const kind = at.site.level === "action" ? (at.site.action ?? "") : "";
453
+ const slot = at.site.pointer.slice(-2).join(".");
454
+ if ((kind !== "child" && kind !== "external") || slot !== "input.code") {
455
+ die(
456
+ `${join(at.where.dir, at.where.file)}: ${address(at.site.pointer)}: an evaluated script ` +
457
+ "belongs in the `code` field of a child or external task's input, and this is " +
458
+ `${kind ? `a ${kind} task's ` : ""}\`${slot}\`.`,
459
+ );
460
+ }
461
+ }
462
+
463
+ // genctl no longer stats the argument — it does not know it is a file — so the resolver that
464
+ // does is the one that must say when it is not there.
465
+ for (const at of located) {
466
+ if (!existsSync(at.file)) {
467
+ die(
468
+ `${join(at.where.dir, at.where.file)}: ${address(at.site.pointer)}: ` +
469
+ `"$import: ${at.site.argument}" names no file (looked at ${at.file})`,
470
+ );
471
+ }
472
+ }
362
473
 
363
474
  // One script at two sites with different input types is a refusal, not a union: the union
364
475
  // is sound and would typecheck a body that is wrong at one of the sites.
365
- const byPath = new Map<string, Site>();
366
- for (const site of manifest.sites) {
367
- const seen = byPath.get(site.path);
368
- const defsOf = (x: Site) => (manifest.schemas[x.process]?.$defs ?? {}) as Record<string, Schema>;
476
+ const byPath = new Map<string, Located>();
477
+ for (const at of located) {
478
+ const seen = byPath.get(at.file);
369
479
  if (
370
480
  seen &&
371
- JSON.stringify(scriptInput(seen, defsOf(seen))) !==
372
- JSON.stringify(scriptInput(site, defsOf(site)))
481
+ JSON.stringify(seen.site.types) !== JSON.stringify(at.site.types)
373
482
  ) {
374
483
  die(
375
- `${site.path} is imported at ${seen.pointer} and ${site.pointer} with different input types.\n` +
484
+ `${at.file} is imported at ${address(seen.site.pointer)} and ` +
485
+ `${address(at.site.pointer)} with different input types.\n` +
376
486
  "Split it into two scripts, or make the two call sites pass the same shape.",
377
487
  );
378
488
  }
379
- byPath.set(site.path, site);
489
+ byPath.set(at.file, at);
380
490
  }
381
491
 
382
- for (const site of byPath.values()) {
383
- const defs = (manifest.schemas[site.process]?.$defs ?? {}) as Record<string, Schema>;
384
- await write(typesPathFor(site.path), declarations(site, defs));
492
+ for (const at of byPath.values()) {
493
+ await write(typesPathFor(at.file), declarations(at));
385
494
  }
386
495
 
387
496
  if (manifest.mode === "types") {
497
+ console.log(JSON.stringify(manifest, null, 2));
388
498
  process.exit(0);
389
499
  }
390
500
 
391
- await typecheck(manifest.root, [...byPath.values()]);
501
+ await typecheck([...byPath.values()]);
392
502
 
393
503
  const code: string[] = [];
394
- for (const site of manifest.sites) {
395
- code.push(await bundle(site, manifest.root));
504
+ for (const at of located) {
505
+ code.push(await bundle(at));
396
506
  }
397
507
  process.stdout.write(JSON.stringify({ code }));
package/package.json CHANGED
@@ -1,11 +1,13 @@
1
1
  {
2
2
  "name": "@genroc/eval-node",
3
- "version": "0.0.0-edge.f85ea85",
3
+ "version": "0.0.0-edge.fb8c06a",
4
4
  "type": "module",
5
5
  "engines": {
6
6
  "node": ">=24"
7
7
  },
8
8
  "scripts": {
9
+ "build": "tsc -p tsconfig.build.json",
10
+ "prepublishOnly": "npm run build",
9
11
  "work": "node worker.ts",
10
12
  "typecheck": "tsc --noEmit"
11
13
  },
@@ -28,11 +30,11 @@
28
30
  },
29
31
  "homepage": "https://genroc.org",
30
32
  "bin": {
31
- "genroc-import": "bin/import.mjs",
32
- "genroc-eval-node": "bin/worker.mjs"
33
+ "genroc-import": "dist/import.js",
34
+ "genroc-eval-node": "dist/worker.js"
33
35
  },
34
36
  "files": [
35
- "bin",
37
+ "dist",
36
38
  "*.ts",
37
39
  "tsconfig.json",
38
40
  "README.md"
package/realm.ts CHANGED
@@ -2,88 +2,45 @@
2
2
  // thread the host can kill mid-loop — the only thing that bounds a synchronous busy loop.
3
3
  // eval.ts owns the budget and does the killing; nothing here knows about time.
4
4
  //
5
- // Everything that touches the script's VALUE lives on this side of the boundary — compiling,
5
+ // Everything that touches the script's VALUE lives on this side of the boundary — loading,
6
6
  // classifying, serialising — because this is the only realm the value exists in.
7
7
 
8
- import { createRequire } from "node:module";
8
+ import { registerHooks } from "node:module";
9
9
  import { parentPort } from "node:worker_threads";
10
10
 
11
11
  import type { EvalFailure, FailureKind, WorkerReply, WorkerRequest } from "./eval.ts";
12
12
 
13
- const AsyncFunction = async function () {}.constructor as new (
14
- ...args: string[]
15
- ) => (...args: unknown[]) => Promise<unknown>;
16
-
17
- const STRICT = '"use strict";\n';
18
-
19
- // Bundled `node:*` imports survive as `require` calls — the importer externalises builtins and
20
- // inlines everything else — and a function built by the AsyncFunction constructor has no
21
- // `require` in scope. Passing one in is what makes an import of a builtin work at runtime rather than at
22
- // typecheck only. Resolution is anchored here, which is right: only builtins reach it.
23
- const scriptRequire = createRequire(import.meta.url);
13
+ // The script is IMPORTED as a module under a URL of our own, not compiled from a string: its
14
+ // frames then carry the author's own line numbers, and an `import` of a node builtin resolves
15
+ // the way it does everywhere else.
16
+ const SCRIPT_URL = "script:main";
24
17
  const STACK_BYTES = 2_048;
25
18
 
26
- /**
27
- * Line offset the AsyncFunction preamble adds, measured rather than assumed: the generated
28
- * wrapper's shape is engine-specific, and a hardcoded number silently misreports every
29
- * script's error location the day it changes.
30
- */
31
- const lineOffset: Promise<number> = (async () => {
32
- // Same parameter list as a real compile: the preamble is what is being measured.
33
- const probe = new AsyncFunction("input", "require", STRICT + "throw new Error('probe');");
34
- try {
35
- await probe();
36
- return 0;
37
- } catch (err) {
38
- return reportedLine(err) - 1;
39
- }
40
- })();
41
-
42
- // V8 marks a frame compiled by the AsyncFunction constructor with the site that CALLED the
43
- // constructor, then the script's OWN position:
44
- // at inner (eval at run (file:///…/worker.ts:107:10), <anonymous>:6:9)
45
- // `eval at` is therefore what separates script frames from runner plumbing — matched without
46
- // the function name, which is whatever encloses the `new AsyncFunction` below. The LAST such
47
- // frame is the body's top level: frames interleave, since a script can throw inside a native
48
- // callback.
49
- const SCRIPT_FRAME = /\(eval at /;
50
- // The trailing `<anonymous>:LINE:COL` — the script's position, after the host file's own.
51
- const POSITION = /<anonymous>:(\d+):(\d+)\)?\s*$/;
52
- // ` at name (` — absent on the top-level frame, which V8 names `eval`.
53
- const FRAME_NAME = /^\s*at\s+(?:async\s+)?([^\s(]+)\s*\(/;
19
+ // The only channel a load hook has to the source. Written per request and read once — a realm
20
+ // evaluates one script and is then discarded, so no second execution can observe it.
21
+ let source = "";
54
22
 
55
- /** Line number of the throw as the engine reported it, or 1 if the stack is unreadable. */
56
- function reportedLine(err: unknown): number {
57
- const stack = err instanceof Error && typeof err.stack === "string" ? err.stack : "";
58
- const frame = stack.split("\n").find((l) => SCRIPT_FRAME.test(l)) ?? "";
59
- const m = frame.match(POSITION);
60
- return m ? Number(m[1]) : 1;
61
- }
23
+ registerHooks({
24
+ resolve: (specifier, context, next) =>
25
+ specifier === SCRIPT_URL ? { url: SCRIPT_URL, shortCircuit: true } : next(specifier, context),
26
+ load: (url, context, next) =>
27
+ url === SCRIPT_URL ? { format: "module", source, shortCircuit: true } : next(url, context),
28
+ });
62
29
 
63
- /** Renumbers each script frame to the line the AUTHOR wrote and drops the runner's own.
64
- * Rewriting the whole location is also what keeps the runner's path out of a script's
65
- * stack V8 puts it inside every compiled frame. */
66
- function scriptStack(err: unknown, offset: number): string | undefined {
30
+ /** Keeps the frames that are the script's own. Everything below the last of them is runner
31
+ * plumbing the author cannot act on, and V8 puts this file's path in it. */
32
+ function scriptStack(err: unknown): string | undefined {
67
33
  if (!(err instanceof Error) || typeof err.stack !== "string") return undefined;
68
34
  const lines = err.stack.split("\n");
69
- let boundary = -1;
70
- for (let i = 0; i < lines.length; i++) if (SCRIPT_FRAME.test(lines[i]!)) boundary = i;
71
- const frames = (boundary >= 0 ? lines.slice(0, boundary + 1) : lines.slice(0, 1))
72
- .map((line) => {
73
- const pos = line.match(POSITION);
74
- if (!pos) return line; // the `Error: message` header and native frames, kept as-is
75
- const name = line.match(FRAME_NAME)?.[1];
76
- const at = name && name !== "eval" && name !== "anonymous" ? `at ${name} ` : "at ";
77
- const indent = line.match(/^\s*/)![0];
78
- return `${indent}${at}(script:${Math.max(1, Number(pos[1]) - offset)}:${pos[2]})`;
79
- })
80
- .join("\n");
81
- return frames.length > STACK_BYTES ? frames.slice(0, STACK_BYTES) : frames;
35
+ let last = 0;
36
+ for (let i = 0; i < lines.length; i++) if (lines[i]!.includes(SCRIPT_URL)) last = i;
37
+ const stack = lines.slice(0, last + 1).join("\n");
38
+ return stack.length > STACK_BYTES ? stack.slice(0, STACK_BYTES) : stack;
82
39
  }
83
40
 
84
- function describe(err: unknown, kind: FailureKind, offset: number): EvalFailure {
41
+ function describe(err: unknown, kind: FailureKind): EvalFailure {
85
42
  if (err instanceof Error) {
86
- return { kind, name: err.name, message: err.message, stack: scriptStack(err, offset) };
43
+ return { kind, name: err.name, message: err.message, stack: scriptStack(err) };
87
44
  }
88
45
  // A script may throw a non-Error (`throw {code: "x"}`), so name/message must not assume one.
89
46
  return { kind, name: "Thrown", message: safeText(err) };
@@ -97,23 +54,40 @@ function safeText(v: unknown): string {
97
54
  }
98
55
  }
99
56
 
57
+ /** A module that will not parse, or names an import nothing resolves, is broken code — only
58
+ * editing it helps. Anything else thrown by the import is the module's top level running,
59
+ * which is the script throwing. */
60
+ function unloadable(err: unknown): boolean {
61
+ const code = (err as { code?: unknown } | null)?.code;
62
+ return err instanceof SyntaxError || (typeof code === "string" && code.startsWith("ERR_MODULE"));
63
+ }
64
+
100
65
  async function run(req: WorkerRequest): Promise<WorkerReply> {
101
- const offset = await lineOffset;
66
+ source = req.code;
102
67
 
103
- let fn: (...args: unknown[]) => Promise<unknown>;
68
+ let main: unknown;
104
69
  try {
105
- // No compile cache: the realm is discarded after this execution, so a cache in it could
106
- // never be hit. Repeated compilation is the price of the fresh global object.
107
- fn = new AsyncFunction("input", "require", STRICT + req.code);
70
+ main = (await import(SCRIPT_URL)).default;
108
71
  } catch (err) {
109
- return { ok: false, failure: describe(err, "compile_error", offset) };
72
+ return { ok: false, failure: describe(err, unloadable(err) ? "compile_error" : "threw") };
73
+ }
74
+ if (typeof main !== "function") {
75
+ const got = main === undefined ? "no default export" : `a ${typeof main}`;
76
+ return {
77
+ ok: false,
78
+ failure: {
79
+ kind: "compile_error",
80
+ name: "NoDefaultExport",
81
+ message: `a script must export default a function; this one has ${got}`,
82
+ },
83
+ };
110
84
  }
111
85
 
112
86
  let value: unknown;
113
87
  try {
114
- value = await fn(req.input, scriptRequire);
88
+ value = await (main as (input: unknown) => unknown)(req.input);
115
89
  } catch (err) {
116
- return { ok: false, failure: describe(err, "threw", offset) };
90
+ return { ok: false, failure: describe(err, "threw") };
117
91
  }
118
92
 
119
93
  try {
@@ -121,12 +95,22 @@ async function run(req: WorkerRequest): Promise<WorkerReply> {
121
95
  // spells null, which is the right reading of a script that returned nothing.
122
96
  return { ok: true, body: value === undefined ? "" : JSON.stringify(value) ?? "" };
123
97
  } catch (err) {
124
- return { ok: false, failure: describe(err, "nonserializable", offset) };
98
+ return { ok: false, failure: describe(err, "nonserializable") };
125
99
  }
126
100
  }
127
101
 
102
+ // The realm's stdio is a pipe to the host thread, and eval.ts terminates this thread the moment
103
+ // the reply lands — so whatever a script wrote last is still in the pipe when it dies. An empty
104
+ // write's callback fires once the queue ahead of it has drained, which makes the reply a barrier
105
+ // for `console` and a direct process.stdout.write alike: both are this stream.
106
+ function flush(stream: NodeJS.WriteStream): Promise<void> {
107
+ return new Promise((resolve) => stream.write("", () => resolve()));
108
+ }
109
+
128
110
  // Non-null because this module only ever runs as a worker entry point; a null port here
129
111
  // would mean eval.ts loaded it as a plain module, which nothing does.
130
112
  parentPort!.on("message", async (req: WorkerRequest) => {
131
- parentPort!.postMessage(await run(req));
113
+ const reply = await run(req);
114
+ await Promise.all([flush(process.stdout), flush(process.stderr)]);
115
+ parentPort!.postMessage(reply);
132
116
  });