From 3b7f09ca673b448bbe7a8f699c79a37225f6839b Mon Sep 17 00:00:00 2001
From: Sylvester Kaczmarek
 <16242628+sylvesterkaczmarek@users.noreply.github.com>
Date: Tue, 18 Aug 2026 01:29:40 +0100
Subject: [PATCH 1/2] fix(knowledge): honor cancellation during PDF extraction

---
 sdk/typescript/src/knowledge-base.ts | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/sdk/typescript/src/knowledge-base.ts b/sdk/typescript/src/knowledge-base.ts
index 064b98ef3..1284eb420 100644
--- a/sdk/typescript/src/knowledge-base.ts
+++ b/sdk/typescript/src/knowledge-base.ts
@@ -83,7 +83,7 @@ export async function prepareKnowledgeBase(
       const extension = extname(document).toLowerCase();
       const text =
         extension === ".pdf"
-          ? await extractPdf(document, bytes)
+          ? await extractPdf(document, bytes, signal)
           : extension === ".docx"
             ? extractDocx(document, bytes)
             : decodeText(document, bytes);
@@ -150,7 +150,11 @@ function decodeText(path: string, bytes: Uint8Array): string {
   }
 }
 
-async function extractPdf(path: string, bytes: Uint8Array): Promise<string> {
+async function extractPdf(
+  path: string,
+  bytes: Uint8Array,
+  signal?: AbortSignal,
+): Promise<string> {
   try {
     const { getDocument, VerbosityLevel } = await import(
       "pdfjs-dist/legacy/build/pdf.mjs"
@@ -162,9 +166,14 @@ async function extractPdf(path: string, bytes: Uint8Array): Promise<string> {
     });
     try {
       const document = await loadingTask.promise;
+      signal?.throwIfAborted();
       const pages: string[] = [];
       for (let number = 1; number <= document.numPages; number++) {
-        const content = await (await document.getPage(number)).getTextContent();
+        signal?.throwIfAborted();
+        const page = await document.getPage(number);
+        signal?.throwIfAborted();
+        const content = await page.getTextContent();
+        signal?.throwIfAborted();
         pages.push(
           content.items
             .map((item) => ("str" in item ? item.str : ""))
@@ -176,6 +185,7 @@ async function extractPdf(path: string, bytes: Uint8Array): Promise<string> {
       await loadingTask.destroy();
     }
   } catch (error) {
+    if (signal?.aborted) signal.throwIfAborted();
     throw new Error(`Cannot extract text from knowledge base PDF: ${path}`, {
       cause: error,
     });

From 12650233cf479f02762ff7e0015b3570a341d0e2 Mon Sep 17 00:00:00 2001
From: Sylvester Kaczmarek
 <16242628+sylvesterkaczmarek@users.noreply.github.com>
Date: Tue, 18 Aug 2026 01:29:54 +0100
Subject: [PATCH 2/2] test(knowledge): cancel during PDF extraction

---
 .../knowledge-base-pdf-cancellation.test.ts   | 69 +++++++++++++++++++
 1 file changed, 69 insertions(+)
 create mode 100644 sdk/typescript/tests-ts/knowledge-base-pdf-cancellation.test.ts

diff --git a/sdk/typescript/tests-ts/knowledge-base-pdf-cancellation.test.ts b/sdk/typescript/tests-ts/knowledge-base-pdf-cancellation.test.ts
new file mode 100644
index 000000000..14eed344f
--- /dev/null
+++ b/sdk/typescript/tests-ts/knowledge-base-pdf-cancellation.test.ts
@@ -0,0 +1,69 @@
+import { mkdtemp, realpath, rm, writeFile } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { afterEach, describe, expect, spyOn, test } from "bun:test";
+import { prepareKnowledgeBase } from "../src/knowledge-base.js";
+
+const temporaryDirectories: string[] = [];
+
+afterEach(async () => {
+  await Promise.all(
+    temporaryDirectories
+      .splice(0)
+      .map((path) => rm(path, { recursive: true, force: true })),
+  );
+});
+
+function pdf(text: string): Uint8Array {
+  const escaped = text.replace(/[\\()]/gu, "\\$&");
+  const stream = `BT /F1 12 Tf 72 720 Td (${escaped}) Tj ET`;
+  const objects = [
+    "<< /Type /Catalog /Pages 2 0 R >>",
+    "<< /Type /Pages /Kids [3 0 R] /Count 1 >>",
+    "<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Resources << /Font << /F1 4 0 R >> >> /Contents 5 0 R >>",
+    "<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>",
+    `<< /Length ${Buffer.byteLength(stream)} >>\nstream\n${stream}\nendstream`,
+  ];
+  let output = "%PDF-1.4\n";
+  const offsets = [0];
+  for (const [index, object] of objects.entries()) {
+    offsets.push(Buffer.byteLength(output));
+    output += `${index + 1} 0 obj\n${object}\nendobj\n`;
+  }
+  const xref = Buffer.byteLength(output);
+  output += `xref\n0 ${offsets.length}\n0000000000 65535 f \n`;
+  for (const offset of offsets.slice(1)) {
+    output += `${String(offset).padStart(10, "0")} 00000 n \n`;
+  }
+  output += `trailer\n<< /Size ${offsets.length} /Root 1 0 R >>\nstartxref\n${xref}\n%%EOF\n`;
+  return new TextEncoder().encode(output);
+}
+
+describe("knowledge-base PDF cancellation", () => {
+  test("observes cancellation after PDF loading has started", async () => {
+    const root = await realpath(
+      await mkdtemp(join(tmpdir(), "codex-security-pdf-cancel-")),
+    );
+    temporaryDirectories.push(root);
+    const document = join(root, "architecture.pdf");
+    await writeFile(document, pdf("Payment service boundary"));
+
+    const controller = new AbortController();
+    const reason = new Error("PDF extraction canceled.");
+    let checks = 0;
+    const signalSpy = spyOn(controller.signal, "throwIfAborted");
+    signalSpy.mockImplementation(() => {
+      if (++checks === 3) controller.abort(reason);
+      if (controller.signal.aborted) throw controller.signal.reason;
+    });
+
+    try {
+      await expect(
+        prepareKnowledgeBase([document], controller.signal),
+      ).rejects.toBe(reason);
+      expect(checks).toBe(3);
+    } finally {
+      signalSpy.mockRestore();
+    }
+  });
+});