fix(build): register onnxruntime-node's native bin/ as a standalone asset (#9687)

Docker/standalone builds of the LLMLingua SLM compression tier failed at
runtime with "Error: libonnxruntime.so.1: cannot open shared object file:
No such file or directory" (open-sse/services/compression/engines/llmlingua's
worker, via @huggingface/transformers -> onnxruntime-node).

onnxruntime-node's dist/binding.js is a normal JS file Next.js's standalone
trace bundles correctly, but binding.js dlopen()s a platform-specific native
library shipped under bin/napi-v3/<platform>/<arch>/libonnxruntime.so.1 — a
dynamic native load static file tracing can't see (same blind-spot class as
the separate colocateLlmlinguaOptionals stub bug, just for a .so instead of
a JS import, via NATIVE_ASSET_ENTRIES instead). That directory was simply
never registered, unlike better-sqlite3's native binary, which already goes
through the exact same mechanism correctly.

Fix: add an entry for onnxruntime-node/bin, mirroring the existing
better-sqlite3 entry. Confirmed against a real Docker build of the
Dockerfile's own post-build verification step: this was the very next
failure once the separate llmlingua-2 stub bug was fixed and the build
progressed far enough to reach it.

Covered by tests/unit/assemble-standalone-onnxruntime-native-asset.test.ts
(fails against the pre-fix code on both assertions, passes after).

(cherry picked from commit 8c98a59f26)

scripts/build/assembleStandalone.mjs

@@ -48,10 +48,7 @@
 import fs from "node:fs/promises";
 import fsSync from "node:fs";
 import path from "node:path";
-import {
-  colocateLlmlinguaOptionals,
-  SEED_PACKAGES,
-} from "./colocateOptionals.mjs";
+import { colocateLlmlinguaOptionals, SEED_PACKAGES } from "./colocateOptionals.mjs";
 
 /**
  * Check whether a path exists (async).
@@ -78,7 +75,7 @@ async function exists(targetPath) {
  * (relative to projectRoot) and destination (relative to outDir) can be joined
  * for either path/platform. @type {{label:string, src:string[], dest:string[]}[]}
  */
-const NATIVE_ASSET_ENTRIES = [
+export const NATIVE_ASSET_ENTRIES = [
   {
     label: "wreq-js native runtime",
     src: ["node_modules", "wreq-js", "rust"],
@@ -90,13 +87,17 @@ const NATIVE_ASSET_ENTRIES = [
     dest: ["node_modules", "better-sqlite3", "build"],
   },
   {
-    // #8847: Bun (and npx -g global installs) resolve better-sqlite3's native
-    // binary from prebuilds/ instead of build/Release/, so the compiled build/
-    // copy alone leaves a hollow package that falls back to sql.js (OOM under
-    // Bun). Ship the prebuilds alongside the compiled binary.
-    label: "better-sqlite3 prebuilds (Bun / global installs)",
-    src: ["node_modules", "better-sqlite3", "prebuilds"],
-    dest: ["node_modules", "better-sqlite3", "prebuilds"],
+    // onnxruntime-node's dist/binding.js dlopen()s a platform-specific
+    // libonnxruntime.so.1 shipped under bin/napi-v3/<platform>/<arch>/ — a
+    // *dynamic* native load Next.js's standalone file trace can't see (same
+    // blind spot class as the LLMLingua closure below, just for a .so instead
+    // of a JS import). Without this the standalone bundle boots with
+    // "Error: libonnxruntime.so.1: cannot open shared object file: No such
+    // file or directory" the first time transformers/llmlingua actually try
+    // to run ONNX inference.
+    label: "onnxruntime-node native binaries (libonnxruntime .so + .node addon)",
+    src: ["node_modules", "onnxruntime-node", "bin"],
+    dest: ["node_modules", "onnxruntime-node", "bin"],
   },
   {
     // TPROXY IP_TRANSPARENT addon (Fase 3 / Epic A). Built by build-tproxy-native
@@ -759,8 +760,7 @@ export function assembleStandalone({
       rootDir: projectRoot,
       targetNodeModulesDir: path.join(resolvedOutDir, "node_modules"),
       seeds: [...SEED_PACKAGES, "@huggingface/transformers"],
-      log: (message) =>
-        console.log(`[assembleStandalone] ${message.trim()}`),
+      log: (message) => console.log(`[assembleStandalone] ${message.trim()}`),
     });
   }
 

tests/unit/assemble-standalone-onnxruntime-native-asset.test.ts

@@ -0,0 +1,65 @@
+/**
+ * Regression test — onnxruntime-node's native libonnxruntime.so.1 was never
+ * registered in NATIVE_ASSET_ENTRIES, so the standalone bundle shipped
+ * dist/binding.js (traced by Next.js as a normal JS require) without its
+ * sibling native bin/ directory (loaded via a dynamic dlopen() Next's static
+ * file trace can't see — the same blind-spot class as the LLMLingua closure,
+ * for a .so instead of a JS import). The bundle then failed at runtime with
+ * "Error: libonnxruntime.so.1: cannot open shared object file: No such file
+ * or directory" the first time transformers/llmlingua tried to run ONNX
+ * inference — reproduced live via the Dockerfile's post-build verification
+ * step once the separate llmlingua-2 stub bug (#9653-adjacent fix) was
+ * resolved and the build progressed far enough to reach this package.
+ */
+import test from "node:test";
+import assert from "node:assert/strict";
+import { mkdtempSync, mkdirSync, writeFileSync, existsSync, rmSync } from "node:fs";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+
+import {
+  NATIVE_ASSET_ENTRIES,
+  syncStandaloneNativeAssets,
+} from "../../scripts/build/assembleStandalone.mjs";
+
+test("NATIVE_ASSET_ENTRIES registers onnxruntime-node's native bin/ directory", () => {
+  const entry = NATIVE_ASSET_ENTRIES.find(
+    (e) => e.src.join("/") === "node_modules/onnxruntime-node/bin"
+  );
+  assert.ok(entry, "onnxruntime-node/bin must be a registered native asset entry");
+  assert.deepEqual(entry.dest, ["node_modules", "onnxruntime-node", "bin"]);
+});
+
+test("syncStandaloneNativeAssets copies onnxruntime-node's libonnxruntime.so.1 into the standalone bundle", async () => {
+  const root = mkdtempSync(join(tmpdir(), "omniroute-assemble-onnx-"));
+  try {
+    // Mirror the real package's shape: dist/binding.js (traced fine by Next)
+    // plus the platform-specific native .so under bin/napi-v3/<platform>/<arch>/.
+    const pkgDir = join(root, "node_modules", "onnxruntime-node");
+    mkdirSync(join(pkgDir, "dist"), { recursive: true });
+    writeFileSync(join(pkgDir, "dist", "binding.js"), "// native binding loader\n");
+    const soDir = join(pkgDir, "bin", "napi-v3", "linux", "x64");
+    mkdirSync(soDir, { recursive: true });
+    writeFileSync(join(soDir, "libonnxruntime.so.1"), "fake-shared-library-bytes");
+
+    const outDir = join(root, ".build", "next", "standalone");
+    mkdirSync(outDir, { recursive: true });
+
+    const changed = await syncStandaloneNativeAssets(root, undefined, { log: () => {} }, outDir);
+    assert.equal(changed, true);
+
+    const destSo = join(
+      outDir,
+      "node_modules",
+      "onnxruntime-node",
+      "bin",
+      "napi-v3",
+      "linux",
+      "x64",
+      "libonnxruntime.so.1"
+    );
+    assert.ok(existsSync(destSo), "libonnxruntime.so.1 must be copied into the standalone bundle");
+  } finally {
+    rmSync(root, { recursive: true, force: true });
+  }
+});