@genroc/eval-node 0.0.0-edge.f85ea85 → 0.0.0-edge.f8ffa72f

package/dist/import.js

@@ -0,0 +1,377 @@
+#!/usr/bin/env node
+// The code-phase resolver: manifest on stdin, `{"code": [...]}` on stdout, non-zero exit
+// with the diagnostic on stderr. genctl never parses TypeScript and this never parses YAML
+// — the manifest is the whole contract. See specs/source-resolution.md.
+//
+// Two modes, one binary: "types" writes the declarations an editor needs and returns no
+// code; "build" typechecks and bundles. A separate types hook would mean a second `tsc`
+// over the same project.
+import { existsSync } from "node:fs";
+import { access, writeFile } from "node:fs/promises";
+import { builtinModules } from "node:module";
+import { dirname, join, resolve } from "node:path";
+import commonjs from "@rollup/plugin-commonjs";
+import json from "@rollup/plugin-json";
+import { nodeResolve } from "@rollup/plugin-node-resolve";
+import { rollup } from "rollup";
+import ts from "typescript";
+function die(message) {
+    console.error(message);
+    process.exit(1);
+}
+async function exists(path) {
+    try {
+        await access(path);
+        return true;
+    }
+    catch {
+        return false;
+    }
+}
+// ── JSON Schema → TypeScript ───────────────────────────────────────────────────
+/** Only genroc's keyword set is handled; anything else its strict decoder would have
+ *  refused before this ran (internal/schema, allowedKeywords). */
+function tsType(s, used) {
+    if (s === undefined || s === null)
+        return "unknown";
+    if (typeof s.$ref === "string") {
+        const name = s.$ref.replace(/^#\/\$defs\//, "");
+        used.add(name);
+        return identifier(name);
+    }
+    if (Array.isArray(s.enum)) {
+        return s.enum.map((v) => JSON.stringify(v)).join(" | ") || "never";
+    }
+    if (Array.isArray(s.anyOf))
+        return union(s.anyOf.map((a) => tsType(a, used)));
+    if (Array.isArray(s.oneOf))
+        return union(s.oneOf.map((a) => tsType(a, used)));
+    if (Array.isArray(s.allOf)) {
+        return s.allOf.map((a) => tsType(a, used)).join(" & ") || "unknown";
+    }
+    const types = s.type === undefined ? [] : Array.isArray(s.type) ? s.type : [s.type];
+    if (types.length === 0) {
+        // The top type: `{}` means unknown, not "an empty object". specs/unknown-type.md.
+        return s.properties ? objectType(s, used) : "unknown";
+    }
+    return union(types.map((t) => scalarType(t, s, used)));
+}
+function scalarType(t, s, used) {
+    switch (t) {
+        case "object":
+            return objectType(s, used);
+        case "array":
+            return s.items ? `Array<${tsType(s.items, used)}>` : "unknown[]";
+        case "string":
+            return "string";
+        case "number":
+        case "integer":
+            return "number";
+        case "boolean":
+            return "boolean";
+        case "null":
+            return "null";
+        default:
+            return "unknown";
+    }
+}
+function objectType(s, used) {
+    const props = s.properties ?? {};
+    const required = new Set(s.required ?? []);
+    const lines = [];
+    for (const [key, sub] of Object.entries(props)) {
+        const doc = typeof sub.description === "string"
+            ? `  /** ${sub.description} */\n`
+            : "";
+        lines.push(`${doc}  ${propKey(key)}${required.has(key) ? "" : "?"}: ${nest(tsType(sub, used))};`);
+    }
+    if (s.additionalProperties && typeof s.additionalProperties === "object") {
+        lines.push(`  [key: string]: ${nest(tsType(s.additionalProperties, used))};`);
+    }
+    if (lines.length === 0)
+        return "Record<string, unknown>";
+    return `{\n${lines.join("\n")}\n}`;
+}
+/** Every line but the first, which is already placed by the property that opens it. */
+const nest = (t) => t.replace(/\n/g, "\n  ");
+function union(parts) {
+    const seen = [...new Set(parts)];
+    return seen.length === 0 ? "unknown" : seen.join(" | ");
+}
+const IDENT = /^[A-Za-z_$][A-Za-z0-9_$]*$/;
+const propKey = (k) => (IDENT.test(k) ? k : JSON.stringify(k));
+const identifier = (n) => IDENT.test(n) ? n : `Def_${n.replace(/[^A-Za-z0-9_$]/g, "_")}`;
+/** Emits one named type per reachable $def rather than inlining: a task output may
+ *  reference itself (specs/recursive-type-inference.md) and inlining would not terminate. */
+function declarations(at) {
+    const { site, where } = at;
+    const defs = where.$defs ?? {};
+    const used = new Set();
+    const input = tsType(site.types?.Input, used);
+    const output = tsType(site.types?.Output, used);
+    const emitted = [];
+    const done = new Set();
+    while (true) {
+        const next = [...used].find((n) => !done.has(n));
+        if (next === undefined)
+            break;
+        done.add(next);
+        const body = tsType(defs[next], used);
+        emitted.push(`export type ${identifier(next)} = ${body};`);
+    }
+    return [
+        "// Generated by genroc. Do not edit - regenerate with `genctl types`.",
+        `// ${where.name}  (${address(site.pointer)})`,
+        "",
+        ...emitted,
+        emitted.length ? "" : "",
+        `export type Input = ${input};`,
+        "",
+        `export type Output = ${output};`,
+        "",
+    ].join("\n");
+}
+/** Keyed by the script's PATH, not the task id: keyed by task, renaming a task would break
+ *  the author's `import type` line with the error landing nowhere near the rename. */
+function typesPathFor(scriptPath) {
+    return scriptPath.replace(/\.[^.\/]+$/, "") + ".genroc.d.ts";
+}
+// ── typecheck ──────────────────────────────────────────────────────────────────
+/** The nearest tsconfig above the script — the one the author's editor already reads. Two
+ *  different configs mean a red editor over a clean apply, or the reverse. The walk stops at
+ *  the project root: above it is not this project. */
+async function nearestTsconfig(from, root) {
+    for (let dir = from;; dir = dirname(dir)) {
+        const candidate = join(dir, "tsconfig.json");
+        if (await exists(candidate))
+            return candidate;
+        if (dir === root || dirname(dir) === dir)
+            return null;
+    }
+}
+async function typecheck(sites) {
+    // One program per distinct base config: `extends` takes a single base, so merging two would
+    // check each script under the other author's options.
+    const groups = new Map();
+    for (const at of sites) {
+        const base = (await nearestTsconfig(dirname(at.file), root)) ?? "";
+        const group = groups.get(base);
+        if (group)
+            group.push(at);
+        else
+            groups.set(base, [at]);
+    }
+    const diagnostics = [];
+    for (const [base, group] of groups) {
+        const config = {
+            ...(base ? { extends: base } : {}),
+            compilerOptions: {
+                noEmit: true,
+                strict: true,
+                skipLibCheck: true,
+                moduleDetection: "force",
+                module: "preserve",
+                target: "esnext",
+                // `lib` DESCRIBES the realm and is written after `extends` so a base cannot widen it:
+                // a worker thread has no document, whatever an author's config claims.
+                lib: ["esnext", "webworker"],
+                // `types` is the author's, and it is how a script opts into the node globals —
+                // the worker realm has them, so refusing the declarations would only lie. With no
+                // base config there is nothing to opt in with, so the default stays none.
+                ...(base ? {} : { types: [] }),
+            },
+            files: group.flatMap((s) => [s.file, typesPathFor(s.file)]),
+            // `files` overrides the base's, but a base `include` survives beside it and would
+            // drag the author's whole tree in, to be checked under the worker lib.
+            include: [],
+        };
+        // Never written: the name only anchors `@types` lookup at the root. It must not be
+        // `tsconfig.json`: that is the base the config `extends` whenever the author keeps one at
+        // the root, and tsc refuses a config that extends its own path as circular.
+        const parsed = ts.parseJsonConfigFileContent(config, ts.sys, root, undefined, join(root, "tsconfig.genroc.json"));
+        const program = ts.createProgram({
+            rootNames: parsed.fileNames,
+            options: parsed.options,
+            projectReferences: parsed.projectReferences,
+            configFileParsingDiagnostics: parsed.errors,
+        });
+        diagnostics.push(...parsed.errors, ...ts.getPreEmitDiagnostics(program));
+    }
+    if (diagnostics.length > 0) {
+        // The diagnostics are the whole type check: this is what genctl surfaces, and the reason a
+        // failed import never produces a string.
+        die(ts
+            .formatDiagnostics(diagnostics, {
+            getCanonicalFileName: (f) => f,
+            getCurrentDirectory: () => root,
+            getNewLine: () => "\n",
+        })
+            .trimEnd());
+    }
+}
+// ── bundle ─────────────────────────────────────────────────────────────────────
+/** Transpiles only. The typecheck above already ran over the author's OWN tsconfig, and a
+ *  second opinion from a config they do not control could fail a build they cannot fix. */
+const transpile = {
+    name: "genroc-transpile",
+    transform(code, id) {
+        if (!id.endsWith(".ts") && !id.endsWith(".tsx"))
+            return null;
+        const out = ts.transpileModule(code, {
+            fileName: id,
+            compilerOptions: {
+                target: ts.ScriptTarget.ESNext,
+                module: ts.ModuleKind.ESNext,
+                verbatimModuleSyntax: false,
+                jsx: id.endsWith(".tsx") ? ts.JsxEmit.ReactJSX : undefined,
+            },
+        });
+        return { code: out.outputText, map: out.sourceMapText ?? null };
+    },
+};
+const BUILTIN = new Set([
+    ...builtinModules,
+    ...builtinModules.map((m) => `node:${m}`),
+]);
+/** Resolves imports through TYPESCRIPT, using the same config the typecheck ran under, so a
+ *  `paths` alias that compiles also bundles. Reimplementing `paths` here would be a second
+ *  resolver to keep in agreement with tsc; this one cannot disagree.
+ *  A package resolving to a `.d.ts` is declined — that is a type, not the implementation —
+ *  which leaves node_modules to nodeResolve. */
+function tsResolve(configPath) {
+    let options = {};
+    if (configPath) {
+        const read = ts.readConfigFile(configPath, ts.sys.readFile);
+        options = ts.parseJsonConfigFileContent(read.config ?? {}, ts.sys, dirname(configPath)).options;
+    }
+    return {
+        name: "genroc-ts-resolve",
+        resolveId(source, importer) {
+            if (!importer || BUILTIN.has(source))
+                return null;
+            const { resolvedModule } = ts.resolveModuleName(source, importer, options, ts.sys);
+            if (!resolvedModule || resolvedModule.isExternalLibraryImport)
+                return null;
+            return resolvedModule.resolvedFileName.endsWith(".d.ts")
+                ? null
+                : resolvedModule.resolvedFileName;
+        },
+    };
+}
+/** Bundles to a self-contained ES module, which is what the evaluator imports: the default
+ *  export it calls is the author's own, so nothing wraps or rewrites the code between the two.
+ *  Bundling is entirely the importer's job, so a definition version pins its code forever. */
+async function bundle(at) {
+    const site = at.site;
+    // Builtins are EXTERNALISED as imports the realm resolves natively. Anything else
+    // unresolved is a REFUSAL, not an external: rollup's default is to leave it as an import
+    // of a module that will not be there, which bundles clean and fails at runtime.
+    const built = await rollup({
+        input: at.file,
+        external: (id) => BUILTIN.has(id),
+        plugins: [
+            tsResolve(await nearestTsconfig(dirname(at.file), root)),
+            nodeResolve({ extensions: [".ts", ".tsx", ".mjs", ".js", ".json"] }),
+            commonjs(),
+            // A `.json` import is a data file inlined at build time, which the previous bundler
+            // did natively; without it rollup hands the JSON to the JS parser.
+            json(),
+            transpile,
+        ],
+        onwarn(warning) {
+            if (warning.code === "UNRESOLVED_IMPORT") {
+                die(`${at.file}: cannot resolve ${warning.exporter ?? "an import"} — is it installed?`);
+            }
+        },
+    }).catch((e) => die(`${at.file}: ${e instanceof Error ? e.message : String(e)}`));
+    const { output } = await built.generate({
+        format: "es",
+        inlineDynamicImports: true,
+    });
+    await built.close();
+    // Refused here rather than in the realm: the evaluator can only report it against a running
+    // instance, and the file it names is on this machine.
+    if (!output[0].exports.includes("default")) {
+        die(`${at.file}: a script must \`export default\` the function to run`);
+    }
+    return output[0].code;
+}
+// ── main ───────────────────────────────────────────────────────────────────────
+const stdin = await new Promise((resolve, reject) => {
+    let raw = "";
+    process.stdin.setEncoding("utf8");
+    process.stdin.on("data", (c) => (raw += c));
+    process.stdin.on("end", () => resolve(raw));
+    process.stdin.on("error", reject);
+});
+const manifest = JSON.parse(stdin);
+// genctl runs a resolver with the project root as its cwd, so the manifest need not say so.
+const root = process.cwd();
+if (!manifest || !Array.isArray(manifest.processes))
+    die("stdin is not a genroc resolver manifest");
+/** A pointer as the address it is, so a generated comment or an error can be pasted into
+ *  `genctl schema`. A key no identifier can spell is bracketed, as the grammar spells it. */
+function address(pointer) {
+    return pointer
+        .map((seg) => typeof seg === "string" && /^[A-Za-z_][A-Za-z0-9_]*$/.test(seg)
+        ? `.${seg}`
+        : `[${JSON.stringify(seg)}]`)
+        .join("")
+        .replace(/^\./, "");
+}
+const located = manifest.processes.flatMap((where) => where.sites.map((site) => ({
+    site,
+    where,
+    file: resolve(where.dir, site.argument),
+})));
+// genctl is agnostic about what a script is for; the contract that an evaluation request carries
+// its module in `code` is THIS resolver's, so it is the one that checks a directive landed there.
+// `child` is the shape the scaffold uses — a call to a process that forwards to the evaluator —
+// and `external` is the same request made directly.
+for (const at of located) {
+    // Two halves, from the two places that carry them: the action's KIND is a field, and WHERE in
+    // it the directive sits is the pointer. A child call is the shape the scaffold generates — to a
+    // process that forwards to the evaluator — and an external task is the same request made
+    // directly.
+    const kind = at.site.level === "action" ? (at.site.action ?? "") : "";
+    const slot = at.site.pointer.slice(-2).join(".");
+    if ((kind !== "child" && kind !== "external") || slot !== "input.code") {
+        die(`${join(at.where.dir, at.where.file)}: ${address(at.site.pointer)}: an evaluated script ` +
+            "belongs in the `code` field of a child or external task's input, and this is " +
+            `${kind ? `a ${kind} task's ` : ""}\`${slot}\`.`);
+    }
+}
+// genctl no longer stats the argument — it does not know it is a file — so the resolver that
+// does is the one that must say when it is not there.
+for (const at of located) {
+    if (!existsSync(at.file)) {
+        die(`${join(at.where.dir, at.where.file)}: ${address(at.site.pointer)}: ` +
+            `"$import: ${at.site.argument}" names no file (looked at ${at.file})`);
+    }
+}
+// One script at two sites with different input types is a refusal, not a union: the union
+// is sound and would typecheck a body that is wrong at one of the sites.
+const byPath = new Map();
+for (const at of located) {
+    const seen = byPath.get(at.file);
+    if (seen &&
+        JSON.stringify(seen.site.types) !== JSON.stringify(at.site.types)) {
+        die(`${at.file} is imported at ${address(seen.site.pointer)} and ` +
+            `${address(at.site.pointer)} with different input types.\n` +
+            "Split it into two scripts, or make the two call sites pass the same shape.");
+    }
+    byPath.set(at.file, at);
+}
+for (const at of byPath.values()) {
+    await writeFile(typesPathFor(at.file), declarations(at));
+}
+if (manifest.mode === "types") {
+    console.log(JSON.stringify(manifest, null, 2));
+    process.exit(0);
+}
+await typecheck([...byPath.values()]);
+const code = [];
+for (const at of located) {
+    code.push(await bundle(at));
+}
+process.stdout.write(JSON.stringify({ code }));

package/dist/realm.js

@@ -0,0 +1,113 @@
+// The evaluation realm. One Worker per execution: a fresh global object per script, and a
+// thread the host can kill mid-loop — the only thing that bounds a synchronous busy loop.
+// eval.ts owns the budget and does the killing; nothing here knows about time.
+//
+// Everything that touches the script's VALUE lives on this side of the boundary — loading,
+// classifying, serialising — because this is the only realm the value exists in.
+var __rewriteRelativeImportExtension = (this && this.__rewriteRelativeImportExtension) || function (path, preserveJsx) {
+    if (typeof path === "string" && /^\.\.?\//.test(path)) {
+        return path.replace(/\.(tsx)$|((?:\.d)?)((?:\.[^./]+?)?)\.([cm]?)ts$/i, function (m, tsx, d, ext, cm) {
+            return tsx ? preserveJsx ? ".jsx" : ".js" : d && (!ext || !cm) ? m : (d + ext + "." + cm.toLowerCase() + "js");
+        });
+    }
+    return path;
+};
+import { registerHooks } from "node:module";
+import { parentPort } from "node:worker_threads";
+// The script is IMPORTED as a module under a URL of our own, not compiled from a string: its
+// frames then carry the author's own line numbers, and an `import` of a node builtin resolves
+// the way it does everywhere else.
+const SCRIPT_URL = "script:main";
+const STACK_BYTES = 2_048;
+// The only channel a load hook has to the source. Written per request and read once — a realm
+// evaluates one script and is then discarded, so no second execution can observe it.
+let source = "";
+registerHooks({
+    resolve: (specifier, context, next) => specifier === SCRIPT_URL ? { url: SCRIPT_URL, shortCircuit: true } : next(specifier, context),
+    load: (url, context, next) => url === SCRIPT_URL ? { format: "module", source, shortCircuit: true } : next(url, context),
+});
+/** Keeps the frames that are the script's own. Everything below the last of them is runner
+ *  plumbing the author cannot act on, and V8 puts this file's path in it. */
+function scriptStack(err) {
+    if (!(err instanceof Error) || typeof err.stack !== "string")
+        return undefined;
+    const lines = err.stack.split("\n");
+    let last = 0;
+    for (let i = 0; i < lines.length; i++)
+        if (lines[i].includes(SCRIPT_URL))
+            last = i;
+    const stack = lines.slice(0, last + 1).join("\n");
+    return stack.length > STACK_BYTES ? stack.slice(0, STACK_BYTES) : stack;
+}
+function describe(err, kind) {
+    if (err instanceof Error) {
+        return { kind, name: err.name, message: err.message, stack: scriptStack(err) };
+    }
+    // A script may throw a non-Error (`throw {code: "x"}`), so name/message must not assume one.
+    return { kind, name: "Thrown", message: safeText(err) };
+}
+function safeText(v) {
+    try {
+        return typeof v === "string" ? v : JSON.stringify(v) ?? String(v);
+    }
+    catch {
+        return String(v);
+    }
+}
+/** A module that will not parse, or names an import nothing resolves, is broken code — only
+ *  editing it helps. Anything else thrown by the import is the module's top level running,
+ *  which is the script throwing. */
+function unloadable(err) {
+    const code = err?.code;
+    return err instanceof SyntaxError || (typeof code === "string" && code.startsWith("ERR_MODULE"));
+}
+async function run(req) {
+    source = req.code;
+    let main;
+    try {
+        main = (await import(__rewriteRelativeImportExtension(SCRIPT_URL))).default;
+    }
+    catch (err) {
+        return { ok: false, failure: describe(err, unloadable(err) ? "compile_error" : "threw") };
+    }
+    if (typeof main !== "function") {
+        const got = main === undefined ? "no default export" : `a ${typeof main}`;
+        return {
+            ok: false,
+            failure: {
+                kind: "compile_error",
+                name: "NoDefaultExport",
+                message: `a script must export default a function; this one has ${got}`,
+            },
+        };
+    }
+    let value;
+    try {
+        value = await main(req.input);
+    }
+    catch (err) {
+        return { ok: false, failure: describe(err, "threw") };
+    }
+    try {
+        // undefined stringifies to undefined, not "undefined"; an empty body is how genroc
+        // spells null, which is the right reading of a script that returned nothing.
+        return { ok: true, body: value === undefined ? "" : JSON.stringify(value) ?? "" };
+    }
+    catch (err) {
+        return { ok: false, failure: describe(err, "nonserializable") };
+    }
+}
+// The realm's stdio is a pipe to the host thread, and eval.ts terminates this thread the moment
+// the reply lands — so whatever a script wrote last is still in the pipe when it dies. An empty
+// write's callback fires once the queue ahead of it has drained, which makes the reply a barrier
+// for `console` and a direct process.stdout.write alike: both are this stream.
+function flush(stream) {
+    return new Promise((resolve) => stream.write("", () => resolve()));
+}
+// Non-null because this module only ever runs as a worker entry point; a null port here
+// would mean eval.ts loaded it as a plain module, which nothing does.
+parentPort.on("message", async (req) => {
+    const reply = await run(req);
+    await Promise.all([flush(process.stdout), flush(process.stderr)]);
+    parentPort.postMessage(reply);
+});