@genroc/eval-node 0.0.0-edge.f77553c → 0.0.0-edge.f8a2edb

package/dist/realm.js

@@ -2,80 +2,46 @@
 // 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 — compiling,
+// 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.
-import { createRequire } from "node:module";
+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";
-const AsyncFunction = async function () { }.constructor;
-const STRICT = '"use strict";\n';
-// Bundled `node:*` imports survive as `require` calls — the importer externalises builtins and
-// inlines everything else — and a function built by the AsyncFunction constructor has no
-// `require` in scope. Passing one in is what makes an import of a builtin work at runtime rather than at
-// typecheck only. Resolution is anchored here, which is right: only builtins reach it.
-const scriptRequire = createRequire(import.meta.url);
+// 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;
-/**
- * Line offset the AsyncFunction preamble adds, measured rather than assumed: the generated
- * wrapper's shape is engine-specific, and a hardcoded number silently misreports every
- * script's error location the day it changes.
- */
-const lineOffset = (async () => {
-    // Same parameter list as a real compile: the preamble is what is being measured.
-    const probe = new AsyncFunction("input", "require", STRICT + "throw new Error('probe');");
-    try {
-        await probe();
-        return 0;
-    }
-    catch (err) {
-        return reportedLine(err) - 1;
-    }
-})();
-// V8 marks a frame compiled by the AsyncFunction constructor with the site that CALLED the
-// constructor, then the script's OWN position:
-//   at inner (eval at run (file:///…/worker.ts:107:10), <anonymous>:6:9)
-// `eval at` is therefore what separates script frames from runner plumbing — matched without
-// the function name, which is whatever encloses the `new AsyncFunction` below. The LAST such
-// frame is the body's top level: frames interleave, since a script can throw inside a native
-// callback.
-const SCRIPT_FRAME = /\(eval at /;
-// The trailing `<anonymous>:LINE:COL` — the script's position, after the host file's own.
-const POSITION = /<anonymous>:(\d+):(\d+)\)?\s*$/;
-// `    at name (` — absent on the top-level frame, which V8 names `eval`.
-const FRAME_NAME = /^\s*at\s+(?:async\s+)?([^\s(]+)\s*\(/;
-/** Line number of the throw as the engine reported it, or 1 if the stack is unreadable. */
-function reportedLine(err) {
-    const stack = err instanceof Error && typeof err.stack === "string" ? err.stack : "";
-    const frame = stack.split("\n").find((l) => SCRIPT_FRAME.test(l)) ?? "";
-    const m = frame.match(POSITION);
-    return m ? Number(m[1]) : 1;
-}
-/** Renumbers each script frame to the line the AUTHOR wrote and drops the runner's own.
- *  Rewriting the whole location is also what keeps the runner's path out of a script's
- *  stack — V8 puts it inside every compiled frame. */
-function scriptStack(err, offset) {
+// 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 boundary = -1;
+    let last = 0;
     for (let i = 0; i < lines.length; i++)
-        if (SCRIPT_FRAME.test(lines[i]))
-            boundary = i;
-    const frames = (boundary >= 0 ? lines.slice(0, boundary + 1) : lines.slice(0, 1))
-        .map((line) => {
-        const pos = line.match(POSITION);
-        if (!pos)
-            return line; // the `Error: message` header and native frames, kept as-is
-        const name = line.match(FRAME_NAME)?.[1];
-        const at = name && name !== "eval" && name !== "anonymous" ? `at ${name} ` : "at ";
-        const indent = line.match(/^\s*/)[0];
-        return `${indent}${at}(script:${Math.max(1, Number(pos[1]) - offset)}:${pos[2]})`;
-    })
-        .join("\n");
-    return frames.length > STACK_BYTES ? frames.slice(0, STACK_BYTES) : frames;
+        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, offset) {
+function describe(err, kind) {
     if (err instanceof Error) {
-        return { kind, name: err.name, message: err.message, stack: scriptStack(err, offset) };
+        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) };
@@ -88,23 +54,39 @@ function safeText(v) {
         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) {
-    const offset = await lineOffset;
-    let fn;
+    source = req.code;
+    let main;
     try {
-        // No compile cache: the realm is discarded after this execution, so a cache in it could
-        // never be hit. Repeated compilation is the price of the fresh global object.
-        fn = new AsyncFunction("input", "require", STRICT + req.code);
+        main = (await import(__rewriteRelativeImportExtension(SCRIPT_URL))).default;
     }
     catch (err) {
-        return { ok: false, failure: describe(err, "compile_error", offset) };
+        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 fn(req.input, scriptRequire);
+        value = await main(req.input);
     }
     catch (err) {
-        return { ok: false, failure: describe(err, "threw", offset) };
+        return { ok: false, failure: describe(err, "threw") };
     }
     try {
         // undefined stringifies to undefined, not "undefined"; an empty body is how genroc
@@ -112,11 +94,20 @@ async function run(req) {
         return { ok: true, body: value === undefined ? "" : JSON.stringify(value) ?? "" };
     }
     catch (err) {
-        return { ok: false, failure: describe(err, "nonserializable", offset) };
+        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) => {
-    parentPort.postMessage(await run(req));
+    const reply = await run(req);
+    await Promise.all([flush(process.stdout), flush(process.stderr)]);
+    parentPort.postMessage(reply);
 });

package/dist/worker.js

@@ -5,7 +5,7 @@
 //
 // See README.md for the contract, and specs/external-task-queue.md for the queue itself.
 import { readFileSync } from "node:fs";
-import { evaluate } from "./eval.js";
+import { Cancelled, evaluate } from "./eval.js";
 const SERVER = (process.env.GENROC_SERVER ?? "http://localhost:8448").replace(/\/$/, "");
 const WORKER_ID = process.env.WORKER_ID ?? `evaluator-${process.pid}`;
 // The credential, when the server runs with --auth token. A worker needs exactly the `worker`
@@ -185,7 +185,7 @@ async function answer(token, outcome) {
     console.error(`genroc refused the outcome for ${token}: ${JSON.stringify(data)}`);
     await release(token);
 }
-async function run(job) {
+async function run(job, signal) {
     let resolved;
     try {
         resolved = await resolveObjects(job);
@@ -206,9 +206,17 @@ async function run(job) {
     }
     let result;
     try {
-        result = await evaluate(req);
+        result = await evaluate(req, signal);
     }
     catch (err) {
+        // Cancelled is not a fault: the process was stopped while this ran. The claim still goes
+        // back — the row is terminal, so nothing re-claims it, and the release is what stops it
+        // waiting out a lease nobody is serving.
+        if (err instanceof Cancelled) {
+            console.log(`cancelled: ${job.token}`);
+            await release(job.token);
+            return;
+        }
         // The RUNNER faulted, not the script — the one class where a retry can help. There is no
         // error code for it on purpose: releasing the claim is how a queue spells "retryable", and
         // it puts the task in front of a different worker instead of burning the definition's
@@ -245,11 +253,22 @@ async function renewLoop() {
             tokens,
             lease_ms: LEASE_MS,
         });
-        // A short count means a claim lapsed and was taken over. Nothing to do about it — the work
-        // continues and its answer will be refused — but say so, because it is the signal that
-        // LEASE_MS is too short for what these scripts actually take.
-        if (ok && data?.renewed < tokens.length) {
-            console.error(`renewed ${data.renewed}/${tokens.length} claims; a lease lapsed under load`);
+        if (!ok)
+            continue;
+        // Cancelled: the process was stopped, so the evaluation is abandoned and the claim handed
+        // back. Aborting first is the point of the list — waiting for the script to finish would
+        // keep burning a core on work an operator has already stopped. The release rides run()'s
+        // own catch, so nothing is released twice.
+        for (const token of (data?.cancelled ?? [])) {
+            inFlight.get(token)?.abort.abort();
+        }
+        // Lost: someone else holds this claim now. The work continues and its answer will be
+        // refused — that is not fixable here — but say so, because it is the signal that LEASE_MS
+        // is too short for what these scripts actually take. Deliberately NOT released: the claim
+        // is the new holder's, and releasing would bump the epoch out from under it.
+        const lost = (data?.lost ?? []);
+        if (lost.length) {
+            console.error(`lost ${lost.length}/${tokens.length} claims; a lease lapsed under load`);
         }
     }
 }
@@ -258,8 +277,9 @@ async function pollLoop() {
         const free = CONCURRENCY - inFlight.size;
         const jobs = free > 0 ? await claim(free) : [];
         for (const job of jobs) {
-            inFlight.set(job.token, job);
-            void run(job).finally(() => inFlight.delete(job.token));
+            const abort = new AbortController();
+            inFlight.set(job.token, { job, abort });
+            void run(job, abort.signal).finally(() => inFlight.delete(job.token));
         }
         // Only idle when there was nothing to take: a full queue should be drained at the speed the
         // realms allow, not at the poll interval.

package/eval.ts

@@ -1,6 +1,7 @@
-// Evaluation core: run a code string in its OWN realm and classify every outcome into one of
-// the failure kinds in README.md. Nothing here knows about genroc — worker.ts is the only
-// thing that talks to the queue — so this stays testable and the containment stays swappable.
+// Evaluation core: import a script module in its OWN realm, call its default export, and
+// classify every outcome into one of the failure kinds in README.md. Nothing here knows about
+// genroc — worker.ts is the only thing that talks to the queue — so this stays testable and
+// the containment stays swappable.
 //
 // The containment is a Worker per execution (realm.ts). It is what makes the budget real:
 // a synchronous busy loop never yields, so no in-process timer can interrupt it, and only a
@@ -9,6 +10,7 @@
 import { Worker } from "node:worker_threads";
 
 export type EvalRequest = {
+  /** An ES module whose default export is the function to run; `input` is its argument. */
   code: string;
   input?: unknown;
   timeout_ms?: number;
@@ -55,14 +57,32 @@ class RealmFault extends Error {
   }
 }
 
-export async function evaluate(req: EvalRequest): Promise<EvalResult> {
+/** Thrown when `signal` aborts: the work was cancelled server-side, so there is no outcome to
+ *  report and worker.ts must release rather than answer. Distinct from RealmFault because the
+ *  runner did not fault -- nothing is wrong, the answer is simply no longer wanted. */
+export class Cancelled extends Error {
+  constructor() {
+    super("cancelled");
+    this.name = "Cancelled";
+  }
+}
+
+export async function evaluate(req: EvalRequest, signal?: AbortSignal): Promise<EvalResult> {
   const budget = typeof req.timeout_ms === "number" ? req.timeout_ms : DEFAULT_TIMEOUT_MS;
 
   const worker = new Worker(REALM_URL);
   let timer: ReturnType<typeof setTimeout> | undefined;
+  let onAbort: (() => void) | undefined;
   try {
     return await new Promise<EvalResult>((resolve, reject) => {
       timer = setTimeout(() => resolve(timedOut(budget)), budget);
+      // The abort is wired to the same promise as the budget, so both settle through the one
+      // finally below -- which is what guarantees the thread is gone before either returns.
+      if (signal) {
+        if (signal.aborted) reject(new Cancelled());
+        onAbort = () => reject(new Cancelled());
+        signal.addEventListener("abort", onAbort, { once: true });
+      }
       worker.once("message", (reply: WorkerReply) => resolve(reply));
       // A script may end its own realm (`process.exit()`), which is not a throw and would
       // otherwise present as a hang until the budget expired. Our own terminate() raises
@@ -73,6 +93,7 @@ export async function evaluate(req: EvalRequest): Promise<EvalResult> {
     });
   } finally {
     clearTimeout(timer);
+    if (signal && onAbort) signal.removeEventListener("abort", onAbort);
     // Awaited, and the whole point: on the timeout path a thread is still burning a core, and
     // resolving before it is gone would report an evaluation the machine is still running.
     await worker.terminate();