♻️ refactor: remove redundant update-status call from GatewayStreamNotifier

Gateway now handles session completion directly in pushEvent when it receives agent_runtime_end, so the separate update-status HTTP call is no longer needed. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
🐛 fix(web-crawler): prevent happy-dom CSS parsing crash in htmlToMarkdown
2026-06-14 03:30:19 +00:00 · 2026-04-08 13:21:18 +08:00 · 2026-04-08 12:40:02 +08:00
3 changed files with 44 additions and 11 deletions
@@ -50,6 +50,39 @@ describe('htmlToMarkdown', () => {
    expect(result.content.length).toBeLessThan(html.length);
  }, 20000);

+  it('should not crash on HTML with invalid CSS selectors (LOBE-6869)', () => {
+    // Regression: happy-dom throws TypeError on pages with CSS selectors it cannot parse.
+    // htmlToMarkdown must not propagate this — it should fall back to raw HTML conversion.
+    const html = `
+      <html><head>
+        <style>:is(.foo, :has(> .bar)) { color: red }</style>
+      </head><body>
+        <script type="application/ld+json">{"@type":"Article","name":"Test"}</script>
+        <p>Valid content here</p>
+      </body></html>`;
+
+    const result = htmlToMarkdown(html, { url: 'https://example.com', filterOptions: {} });
+
+    expect(result).toBeDefined();
+    expect(result.content).toContain('Valid content');
+  });
+
+  it('should not crash on HTML with external stylesheet links (LOBE-6869)', () => {
+    // Regression: happy-dom's HTMLLinkElement.#loadStyleSheet can crash on CSS parsing.
+    // disableCSSFileLoading should prevent this path entirely.
+    const html = `
+      <html><head>
+        <link rel="stylesheet" href="https://example.com/styles.css">
+      </head><body>
+        <p>Content with external CSS</p>
+      </body></html>`;
+
+    const result = htmlToMarkdown(html, { url: 'https://example.com', filterOptions: {} });
+
+    expect(result).toBeDefined();
+    expect(result.content).toContain('Content with external CSS');
+  });
+
  it('should not truncate HTML under 1 MB', () => {
    const html = '<html><body><p>Small content</p></body></html>';

@@ -31,13 +31,21 @@ export const htmlToMarkdown = (
  { url, filterOptions }: { filterOptions: FilterOptions; url: string },
 ): HtmlToMarkdownOutput => {
  const html = rawHtml.length > MAX_HTML_SIZE ? rawHtml.slice(0, MAX_HTML_SIZE) : rawHtml;
-  const window = new Window({ url });
+  const window = new Window({
+    settings: { disableCSSFileLoading: true, disableJavaScriptEvaluation: true },
+    url,
+  });

  const document = window.document;
  document.body.innerHTML = html;

-  // @ts-expect-error reason: Readability expects a Document type
-  const parsedContent = new Readability(document).parse();
+  let parsedContent: ReturnType<Readability<string>['parse']> = null;
+  try {
+    // @ts-expect-error reason: Readability expects a Document type
+    parsedContent = new Readability(document).parse();
+  } catch {
+    // happy-dom may throw on pages with invalid CSS selectors — fall back to raw HTML
+  }

  const useReadability = filterOptions.enableReadability ?? true;

@@ -96,14 +96,6 @@ export class GatewayStreamNotifier implements IStreamEventManager {
      type: 'agent_runtime_end',
    });

-    const status =
-      reason === 'error' ? 'error' : reason === 'interrupted' ? 'interrupted' : 'completed';
-    this.httpPost('/api/operations/update-status', {
-      operationId,
-      status,
-      summary: reasonDetail,
-    });
-
    return result;
  }