feat(api): Add image multimodal support for LLMNode (#17372)

Enhance `LLMNode` with multimodal capability, introducing support for
image outputs.

This implementation extracts base64-encoded images from LLM responses,
saves them to the storage service, and records the file metadata in the
`ToolFile` table. In conversations, these images are rendered as
markdown-based inline images.
Additionally, the images are included in the LLMNode's output as
file variables, enabling subsequent nodes in the workflow to utilize them.

To integrate file outputs into workflows, adjustments to the frontend code
are necessary.

For multimodal output functionality, updates to related model configurations
are required. Currently, this capability has been applied exclusively to
Google's Gemini models.

Close #15814.

Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>

api/core/app/task_pipeline/message_cycle_manage.py

@@ -24,7 +24,7 @@ from core.app.entities.task_entities import (
     WorkflowTaskState,
 )
 from core.llm_generator.llm_generator import LLMGenerator
-from core.tools.tool_file_manager import ToolFileManager
+from core.tools.signature import sign_tool_file
 from extensions.ext_database import db
 from models.model import AppMode, Conversation, MessageAnnotation, MessageFile
 from services.annotation_service import AppAnnotationService
@@ -154,7 +154,7 @@ class MessageCycleManage:
             if message_file.url.startswith("http"):
                 url = message_file.url
             else:
-                url = ToolFileManager.sign_file(tool_file_id=tool_file_id, extension=extension)
+                url = sign_tool_file(tool_file_id=tool_file_id, extension=extension)
 
             return MessageFileStreamResponse(
                 task_id=self._application_generate_entity.task_id,