Open-source AI browser agent for Chrome and Firefox (monorepo) ðŸ§
JavaScript ai-agentai-agentsai-toolsbrowser-aibrowser-automationbrowser-extensionchrome-aichrome-devtoolschrome-extensionchrome-extensionsfirefox-addonfirefox-addonsfirefox-extensionfirefox-extensionsgemmagemma4minimaxoffline-aioffline-llmqwen
fix(chrome): retry PDF.js import, derive viewer path, guard double response
Codex release-state teste2ccc2e92a6f
diff --git a/src/chrome/src/agent/pdf-extraction.js b/src/chrome/src/agent/pdf-extraction.jsindex 70a8d89ca..27c951545 100644--- a/src/chrome/src/agent/pdf-extraction.js+++ b/src/chrome/src/agent/pdf-extraction.js@@ -11,9 +11,17 @@ export const PDF_EXTRACTION_READY_MESSAGE = 'offscreen-pdf-extract-ready';export const PDF_PASSTHROUGH_MAX_BYTES = 16 * 1024 * 1024;const ALLOWED_PDF_PROTOCOLS = new Set(['http:', 'https:', 'file:']);-const PDF_HANDLER_PAGE = 'src/ui/pdf-handler.html';+const DEFAULT_PDF_HANDLER_PAGE = 'src/ui/pdf-handler.html';const BASE64_MAX_INPUT_BYTES = 32 * 1024 * 1024;+// Derived from the manifest for the same reason as the background path below:+// renaming the viewer page would otherwise make read_pdf report a bogus+// "must use http:, https:, or file:" on our own PDF tabs.+function pdfHandlerPage(runtime) {+ const manifest = typeof runtime?.getManifest === 'function' ? runtime.getManifest() : null;+ return manifest?.mime_types_handler?.['application/pdf']?.handler_url || DEFAULT_PDF_HANDLER_PAGE;+}+// When the native MIME handler owns a PDF tab, the tab URL is our own viewer// page wrapping the real URL in ?url=. read_pdf falls back to the tab URL when// called without an explicit one, so unwrap it before the scheme check.@@ -22,7 +30,7 @@ function unwrapPdfHandlerUrl(url, runtime = globalThis.chrome?.runtime) {if (typeof runtime?.getURL !== 'function') return url;let handler;try {- handler = new URL(runtime.getURL(PDF_HANDLER_PAGE));+ handler = new URL(runtime.getURL(pdfHandlerPage(runtime)));} catch {return url;}diff --git a/src/chrome/src/offscreen/pdf-extraction-host.js b/src/chrome/src/offscreen/pdf-extraction-host.jsindex 26332406b..6287eb1bc 100644--- a/src/chrome/src/offscreen/pdf-extraction-host.js+++ b/src/chrome/src/offscreen/pdf-extraction-host.js@@ -8,6 +8,9 @@ import {isTrustedPdfExtractionSender,normalizePdfUrl,} from '../agent/pdf-extraction.js';++const PDF_MESSAGE_TYPES = new Set([PDF_EXTRACTION_MESSAGE, PDF_EXTRACTION_READY_MESSAGE]);+let pdfjsPromise = null;function getPdfjs() {@@ -17,18 +20,38 @@ function getPdfjs() {chrome.runtime.getURL('vendor/pdfjs/pdf.worker.mjs');return pdfjs;});+ // The offscreen document outlives any single read, so never memoize a+ // rejection: one transient import failure would otherwise make every+ // later read_pdf fail until the document is torn down.+ pdfjsPromise.catch(() => { pdfjsPromise = null; });}return pdfjsPromise;}chrome.runtime.onMessage.addListener((message, sender, sendResponse) => {- if (![PDF_EXTRACTION_MESSAGE, PDF_EXTRACTION_READY_MESSAGE].includes(message?.type)) return false;+ if (!PDF_MESSAGE_TYPES.has(message?.type)) return false;++ // A 16 MB PDF answers with ~21 MB of base64, and an oversized or+ // unserializable reply makes sendResponse throw. Without this guard that+ // throw would reach the catch below and call sendResponse a second time on+ // an already-closed channel, hiding the original failure.+ let responded = false;+ const respond = (payload) => {+ if (responded) return;+ responded = true;+ try {+ sendResponse(payload);+ } catch (error) {+ console.warn('[pdf-extraction-host] failed to deliver response', error);+ }+ };+if (!isTrustedPdfExtractionSender(sender)) {- sendResponse({ ok: false, ready: false, error: 'Unauthorized PDF extraction sender.' });+ respond({ ok: false, ready: false, error: 'Unauthorized PDF extraction sender.' });return false;}if (message.type === PDF_EXTRACTION_READY_MESSAGE) {- sendResponse({ ok: true, ready: true });+ respond({ ok: true, ready: true });return false;}@@ -47,9 +70,9 @@ chrome.runtime.onMessage.addListener((message, sender, sendResponse) => {const pdfjs = await getPdfjs();const result = await extractPdfTextFromBytes(pdfjs, bytes, message.options || {});if (passthrough) result._pdfBase64 = bytesToBase64(passthrough);- sendResponse({ ok: true, result });+ respond({ ok: true, result });})().catch((error) => {- sendResponse({ ok: false, error: error?.message || String(error) });+ respond({ ok: false, error: error?.message || String(error) });});return true;diff --git a/test/pdf-read.mjs b/test/pdf-read.mjsindex 88e876701..32742a4a4 100644--- a/test/pdf-read.mjs+++ b/test/pdf-read.mjs@@ -27,6 +27,9 @@ async function testMv3PdfExtractionUsesTheSharedOffscreenHost() {assert.match(host, /extractPdfTextFromBytes/);assert.match(host, /isTrustedPdfExtractionSender\(sender\)/);assert.match(offscreenHtml, /<script type="module" src="pdf-extraction-host\.js"><\/script>/);+ // The offscreen document outlives any single read, so a failed PDF.js import+ // must not be memoized into every later read_pdf.+ assert.match(host, /pdfjsPromise\.catch\(\(\) => \{ pdfjsPromise = null; \}\);/);}async function testPdfUrlAndSenderBoundaries() {@@ -74,6 +77,22 @@ async function testPdfUrlAndSenderBoundaries() {/must use http.*https.*file/i,'An unwrapped inner URL must still pass the scheme allowlist.');+ // The viewer page follows the manifest too, so renaming it cannot start+ // rejecting our own PDF tabs with a bogus scheme error.+ const renamedHandlerRuntime = {+ ...runtime,+ getManifest: () => ({ mime_types_handler: { 'application/pdf': { handler_url: 'src/ui/viewer.html' } } }),+ };+ assert.equal(+ normalizePdfUrl(+ `${runtime.getURL('src/ui/viewer.html')}?url=${encodeURIComponent('https://example.test/paper.pdf')}&tabId=7`,+ renamedHandlerRuntime),+ 'https://example.test/paper.pdf');+ assert.throws(+ () => normalizePdfUrl(handlerUrl, renamedHandlerRuntime),+ /must use http.*https.*file/i,+ 'Only the manifest-declared viewer page may unwrap an inner URL.');+let fetchCalls = 0;const originalFetch = globalThis.fetch;globalThis.fetch = async () => {