Fix: preserve doc generator download metadata in message (#14626)

### What problem does this PR solve?

preserve doc generator download metadata

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

agent/component/docs_generator.py

@@ -49,6 +49,7 @@ class DocGeneratorParam(ComponentParamBase):
         self.watermark_text = ""
         self.add_page_numbers = True
         self.add_timestamp = True
+        self.include_download_info_in_content = False
         self.font_size = 12
         self.outputs = {
             "download": {"value": "", "type": "string"},
@@ -131,6 +132,7 @@ class DocGenerator(Message, ABC):
                     "mime_type": mime_type,
                     "size": file_size,
                     "base64": file_base64,
+                    "include_download_info_in_content": self._param.include_download_info_in_content,
                 }
                 self.set_output("download", json.dumps(download_info))
                 return download_info

agent/component/message.py

@@ -75,6 +75,22 @@ class Message(ComponentBase):
             key in value for key in ("doc_id", "filename", "mime_type")
         )
 
+    @staticmethod
+    def _download_info_includes_content(value: Any) -> bool:
+        return isinstance(value, dict) and bool(value.get("include_download_info_in_content"))
+
+    @staticmethod
+    def _normalize_download_info(value: Any) -> Any:
+        if isinstance(value, list):
+            return [Message._normalize_download_info(item) for item in value]
+
+        if not isinstance(value, dict):
+            return value
+
+        normalized = value.copy()
+        normalized.pop("include_download_info_in_content", None)
+        return normalized
+
     def _extract_downloads(self, value: Any) -> list[dict[str, Any]]:
         if isinstance(value, str):
             try:
@@ -100,7 +116,19 @@ class Message(ComponentBase):
         extracted_downloads = self._extract_downloads(value)
         if extracted_downloads:
             if downloads is not None:
-                downloads.extend(extracted_downloads)
+                downloads.extend(self._normalize_download_info(item) for item in extracted_downloads)
+            if any(self._download_info_includes_content(item) for item in extracted_downloads):
+                if isinstance(value, str):
+                    try:
+                        value = json.loads(value)
+                    except Exception:
+                        return value
+                try:
+                    return json.dumps(self._normalize_download_info(value), ensure_ascii=False)
+                except Exception:
+                    if fallback_to_str:
+                        return str(value)
+                    return ""
             return ""
 
         if value is None:

web/src/pages/agent/constant/index.tsx

@@ -973,6 +973,7 @@ export const initialDocGeneratorValues = {
   watermark_text: '',
   add_page_numbers: true,
   add_timestamp: true,
+  include_download_info_in_content: false,
   font_size: 12,
   outputs: {
     download: { type: 'string' },

web/src/pages/agent/form/doc-generator-form/index.tsx

@@ -11,9 +11,9 @@ import { Input } from '@/components/ui/input';
 import { RAGFlowSelect } from '@/components/ui/select';
 import { Switch } from '@/components/ui/switch';
 import { zodResolver } from '@hookform/resolvers/zod';
-import { t } from 'i18next';
 import { memo, useEffect, useMemo } from 'react';
 import { useForm } from 'react-hook-form';
+import { useTranslation } from 'react-i18next';
 import { z } from 'zod';
 import { INextOperatorForm } from '../../interface';
 import { FormWrapper } from '../components/form-wrapper';
@@ -23,6 +23,7 @@ import { useValues } from './use-values';
 import { useWatchFormChange } from './use-watch-form-change';
 
 function DocGeneratorForm({ node }: INextOperatorForm) {
+  const { t } = useTranslation();
   const values = useValues(node);
 
   const FormSchema = z.object({
@@ -34,6 +35,7 @@ function DocGeneratorForm({ node }: INextOperatorForm) {
     watermark: z.string().optional(),
     add_page_numbers: z.boolean(),
     add_timestamp: z.boolean(),
+    include_download_info_in_content: z.boolean(),
     font_size: z.coerce.number().min(12, 'Font size must be at least 12'),
     outputs: z.object({
       download: z.object({ type: z.string() }),
@@ -113,6 +115,29 @@ function DocGeneratorForm({ node }: INextOperatorForm) {
             )}
           />
 
+          <FormField
+            control={form.control}
+            name="include_download_info_in_content"
+            render={({ field }) => (
+              <FormItem className="flex flex-row items-center justify-between gap-4">
+                <div className="space-y-1">
+                  <FormLabel>
+                    {t(
+                      'flow.includeDownloadInfoInContent',
+                      'Append download info to content',
+                    )}
+                  </FormLabel>
+                </div>
+                <FormControl>
+                  <Switch
+                    checked={field.value}
+                    onCheckedChange={field.onChange}
+                  />
+                </FormControl>
+              </FormItem>
+            )}
+          />
+
           <FormField
             control={form.control}
             name="filename"

web/src/pages/agent/form/doc-generator-form/use-values.ts

@@ -21,6 +21,8 @@ export const useValues = (node?: Node) => {
       watermark_text: nextValues.watermark_text,
       add_page_numbers: nextValues.add_page_numbers,
       add_timestamp: nextValues.add_timestamp,
+      include_download_info_in_content:
+        nextValues.include_download_info_in_content ?? false,
       font_size: Math.max(12, Number(nextValues.font_size) || 12),
       outputs: initialDocGeneratorValues.outputs,
     };