wx44wx/ai-video-fullstack
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add workflow support and enhance runtime configuration in models and services

Browse Source 
- Introduce RuntimeModelResource and RuntimeKnowledgeBase classes to manage workflow resources.
- Update AssistantConfig to include workflow_model_resources and workflow_knowledge_bases for better integration.
- Refactor validation and processing logic in routes and services to accommodate workflow types.
- Implement dynamic variable support for workflow assistants and enhance graph normalization.
- Add ToolExecutor for reusable tool execution across different assistant types.
- Update various services to ensure compatibility with new workflow features and improve error handling.
This commit is contained in:
Xin Wang
2026-07-13 16:13:27 +08:00
parent 6108b00007
commit 32aef14ddb
27 changed files with 2563 additions and 910 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
backend/services/brains/registry.py
View File

@@ -14,7 +14,7 @@ from services.brains.workflow_brain import WorkflowBrain
def _workflow(cfg: AssistantConfig) -> Brain:
return WorkflowBrain(cfg.graph)
return WorkflowBrain(cfg)
BRAIN_FACTORIES: dict[str, Callable[[AssistantConfig], Brain]] = {