AI Clinical Dev Team
|
84bf1c86ab
|
feat: Day 14-17 - Frontend Chat Interface completed
Frontend:
- Create MessageList component with streaming animation
- Create MessageInput component with @knowledge base support
- Create ModelSelector component (DeepSeek/Qwen/Gemini)
- Implement conversationApi with SSE streaming
- Update AgentChatPage integrate all components
- Add Markdown rendering (react-markdown + remark-gfm)
- Add code highlighting (react-syntax-highlighter)
- Add vite-env.d.ts for environment variables
Features:
- Real-time streaming output with cursor animation
- Markdown and code block rendering
- Model switching (DeepSeek-V3, Qwen3-72B, Gemini Pro)
- @Knowledge base selector (UI ready)
- Auto-scroll to bottom
- Shift+Enter for new line, Enter to send
- Beautiful message bubble design
Build: Frontend build successfully (7.94s, 1.9MB)
New Files:
- components/chat/MessageList.tsx (170 lines)
- components/chat/MessageList.css (150 lines)
- components/chat/MessageInput.tsx (145 lines)
- components/chat/MessageInput.css (60 lines)
- components/chat/ModelSelector.tsx (110 lines)
- components/chat/ModelSelector.css (35 lines)
- api/conversationApi.ts (170 lines)
- src/vite-env.d.ts (9 lines)
Total: ~850 lines of new code
|
2025-10-10 20:52:30 +08:00 |
|
AI Clinical Dev Team
|
864a0b1906
|
feat: Day 10-11 - Agent Configuration System completed
Backend:
- Create agents.yaml config file with 12 agents definition
- Create Prompt templates for topic-evaluation agent
- Implement agentService.ts for loading and managing agent configs
- Create agentController.ts with CRUD operations
- Create agent routes (GET /agents, /agents/:id, etc.)
- Register agent routes in main server
Frontend:
- Create agentApi.ts service module
- Update AgentChatPage to dynamically load agent config from API
- Add loading state and error handling
- Display agent details (description, category, model)
Build: Both frontend and backend build successfully
|
2025-10-10 20:13:08 +08:00 |
|