fix: normalize file extension to lowercase before parsing (#6996) (#7105)

Files uploaded with an uppercase or mixed-case extension (e.g. `123.PDF`,
`report.Docx`) failed to be parsed because the readFile worker matches the
extension against a lowercase switch (`'pdf'`, `'docx'`, ...), so an
uppercase suffix fell through to the default branch and threw
"... is not supported".

Normalize the extension to lowercase once at the lowest common entry point
`readFileContentByBuffer`, instead of at each business-layer call site. This
keeps business-layer behavior unchanged and covers all callers
(chat upload, external url, dataset, local file) in a single place.

Adds regression tests covering upper/mixed-case extensions.

Fixes #6996

Co-authored-by: DadaVinqi <DadaVinqi@users.noreply.github.com>

packages/service/common/file/read/utils.ts

@@ -49,7 +49,7 @@ export const readFileContentByBuffer = async ({
   teamId,
   tmbId,
 
-  extension,
+  extension: rawExtension,
   buffer,
   encoding,
   customPdfParse = false,
@@ -74,6 +74,9 @@ export const readFileContentByBuffer = async ({
 }): Promise<{
   rawText: string;
 }> => {
+  // 归一化扩展名为小写，避免大写/混合大小写后缀（如 .PDF）无法匹配解析器（#6996）
+  const extension = rawExtension.toLowerCase();
+
   const parseMarkdownImages = (rawText: string) =>
     parseMarkdownBase64Images(rawText, {
       parseBase64: true,

packages/service/test/common/file/read/utils.test.ts

@@ -581,4 +581,41 @@ describe('readFileContentByBuffer', () => {
     expect(result.rawText).toBe('text with');
     expect(result.rawText).not.toContain('data:image/png;base64');
   });
+  it('应将大写扩展名归一化为小写后再传给解析器（#6996）', async () => {
+    const buffer = Buffer.from('pdf content');
+
+    const result = await readFileContentByBuffer({
+      teamId,
+      tmbId,
+      extension: 'PDF',
+      buffer,
+      encoding: 'utf-8'
+    });
+
+    // 解析器应收到小写扩展名，从而命中对应分支而非报 "not supported"
+    expect(mockReadRawContentFromBuffer).toHaveBeenLastCalledWith(
+      expect.objectContaining({
+        extension: 'pdf'
+      })
+    );
+    expect(result.rawText).toBe('parsed-pdf-content');
+  });
+
+  it('应将混合大小写扩展名归一化为小写', async () => {
+    const buffer = Buffer.from('docx content');
+
+    await readFileContentByBuffer({
+      teamId,
+      tmbId,
+      extension: 'Docx',
+      buffer,
+      encoding: 'utf-8'
+    });
+
+    expect(mockReadRawContentFromBuffer).toHaveBeenLastCalledWith(
+      expect.objectContaining({
+        extension: 'docx'
+      })
+    );
+  });
 });