fix: handle non-ISO-8859-1 characters in fetch headers and Content-Disposition (#1673)

* fix: handle non-ISO-8859-1 characters in fetch headers and Content-Disposition

Browser Headers API rejects characters above U+00FF. The x-opencode-directory header carries raw filesystem paths, which breaks when paths contain Chinese/CJK characters. Also fixes Content-Disposition for non-ASCII filenames per RFC 5987.

* refactor: export header sanitization helpers, deduplicate, add tests

Export isLatin1Safe and sanitizeHeadersForBrowser from runtime-fetch.ts so VS Code webview can import them instead of duplicating the logic. Add tests: isLatin1Safe boundary checks, sanitizeHeadersForBrowser encoding/deduplication, runtimeFetch round-trip encode/decode, and Content-Disposition RFC 5987 output for both ASCII and non-ASCII filenames.

* fix: mark encoded directory headers

---------

Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>

packages/web/server/lib/fs/routes.js

@@ -883,7 +883,13 @@ export const registerFsRoutes = (app, dependencies) => {
       const download = req.query.download === 'true';
       if (download) {
         const fileName = path.basename(canonicalPath);
-        res.setHeader('Content-Disposition', `attachment; filename="${fileName}"`);
+        // RFC 5987: use filename*= for non-ASCII filenames, with ASCII-only
+        // filename= as fallback for older clients.
+        const asciiOnly = fileName.replace(/[^\u0000-\u007F]/g, '');
+        const fallback = asciiOnly || 'file';
+        // Percent-encode the raw UTF-8 bytes for filename*=
+        const encoded = encodeURIComponent(fileName);
+        res.setHeader('Content-Disposition', `attachment; filename="${fallback}"; filename*=UTF-8''${encoded}`);
       }
 
       const content = await fsPromises.readFile(canonicalPath);

packages/web/server/lib/fs/routes.test.js

@@ -596,3 +596,42 @@ describe('fs exec git-read cache', () => {
     expect(calls.length).toBe(afterFill + 2);
   });
 });
+
+describe('fs raw download Content-Disposition', () => {
+  it('uses RFC 5987 filename*= encoding for non-ASCII filenames on download', async () => {
+    const fsPromises = {
+      realpath: vi.fn(async (targetPath) => targetPath),
+      stat: vi.fn(async () => ({ isFile: () => true, size: 6 })),
+      readFile: vi.fn(async () => Buffer.from('content')),
+    };
+    const handler = registerRaw(fsPromises);
+
+    const res = await callRaw(handler, {
+      path: '/repo/文件.txt',
+      download: 'true',
+    });
+
+    expect(res.statusCode).toBe(200);
+    const cd = res.getHeader('content-disposition');
+    expect(cd).toContain("filename*=UTF-8''");
+    expect(cd).toContain(encodeURIComponent('文件.txt'));
+    // ASCII fallback strips non-ASCII chars, leaving extension
+    expect(cd).toContain('filename=".txt"');
+  });
+
+  it('uses plain filename for ASCII-only filenames on download', async () => {
+    const fsPromises = {
+      realpath: vi.fn(async (targetPath) => targetPath),
+      stat: vi.fn(async () => ({ isFile: () => true, size: 6 })),
+      readFile: vi.fn(async () => Buffer.from('content')),
+    };
+    const handler = registerRaw(fsPromises);
+
+    const res = await callRaw(handler, { path: '/repo/readme.txt', download: 'true' });
+
+    expect(res.statusCode).toBe(200);
+    const cd = res.getHeader('content-disposition');
+    expect(cd).toContain('filename="readme.txt"');
+    expect(cd).toContain("filename*=UTF-8''readme.txt");
+  });
+});