feat: Add PDF parser selection to Agent Begin and Await Response comp… (#13325)

### Issue: #12756

### What problem does this PR solve?

When users upload files through Agent's Begin or Await Response
components, the parsing is hardcoded to "Plain Text", ignoring all other
available parsers (DeepDOC, TCADP, Docling, MinerU, PaddleOCR). This PR
adds a PDF parser dropdown to these components so users can select the
appropriate parser for their file inputs.


### Changes

**Backend**
- `agent/component/fillup.py` - Added `layout_recognize` param to
`UserFillUpParam`, forwarded to `FileService.get_files()`
- `agent/component/begin.py` - Same forwarding in `Begin._invoke()`
- `agent/canvas.py` - Extract Begin's `layout_recognize` for `sys.files`
parsing, added param to `get_files_async()` / `get_files()`
- `api/db/services/file_service.py` - Added `layout_recognize` param to
`parse()` and `get_files()`, replacing hardcoded `"Plain Text"`
- `rag/app/naive.py` - Added `"plain text"` and `"tcadp parser"` aliases
to PARSERS dict to match dropdown values after `.lower()`

**Frontend**
- `web/src/pages/agent/form/begin-form/index.tsx` - Show
`LayoutRecognizeFormField` dropdown when file inputs exist
- `web/src/pages/agent/form/begin-form/schema.ts` - Added
`layout_recognize` to Zod schema
- `web/src/pages/agent/form/user-fill-up-form/index.tsx` - Same dropdown
for Await Response component


### Type of change

- [x] New Feature (non-breaking change which adds functionality)

api/db/services/file_service.py

@@ -519,7 +519,7 @@ class FileService(CommonService):
         return "\n\n".join(res)
 
     @staticmethod
-    def parse(filename, blob, img_base64=True, tenant_id=None):
+    def parse(filename, blob, img_base64=True, tenant_id=None, layout_recognize=None):
         from rag.app import audio, email, naive, picture, presentation
         from api.apps import current_user
 
@@ -527,7 +527,7 @@ class FileService(CommonService):
             pass
 
         FACTORY = {ParserType.PRESENTATION.value: presentation, ParserType.PICTURE.value: picture, ParserType.AUDIO.value: audio, ParserType.EMAIL.value: email}
-        parser_config = {"chunk_token_num": 16096, "delimiter": "\n!?;。；！？", "layout_recognize": "Plain Text"}
+        parser_config = {"chunk_token_num": 16096, "delimiter": "\n!?;。；！？", "layout_recognize": layout_recognize or "Plain Text"}
         kwargs = {"lang": "English", "callback": dummy, "parser_config": parser_config, "from_page": 0, "to_page": 100000, "tenant_id": current_user.id if current_user else tenant_id}
         file_type = filename_type(filename)
         if img_base64 and file_type == FileType.VISUAL.value:
@@ -663,7 +663,7 @@ class FileService(CommonService):
         return structured(file.filename, filename_type(file.filename), file.read(), file.content_type)
 
     @staticmethod
-    def get_files(files: Union[None, list[dict]], raw: bool = False) -> Union[list[str], tuple[list[str], list[dict]]]:
+    def get_files(files: Union[None, list[dict]], raw: bool = False, layout_recognize: str = None) -> Union[list[str], tuple[list[str], list[dict]]]:
         if not files:
             return  []
         def image_to_base64(file):
@@ -679,7 +679,7 @@ class FileService(CommonService):
                 else:
                     threads.append(exe.submit(image_to_base64, file))
                 continue
-            threads.append(exe.submit(FileService.parse, file["name"], FileService.get_blob(file["created_by"], file["id"]), True, file["created_by"]))
+            threads.append(exe.submit(FileService.parse, file["name"], FileService.get_blob(file["created_by"], file["id"]), True, file["created_by"], layout_recognize))
     
         if raw:
             return [th.result() for th in threads], imgs