What Is the CodeArts Agent Extension?
The CodeArts Agent extension can be installed in Visual Studio Code and JetBrains IDEs. It delivers core capabilities such as code generation, code completion, R&D knowledge Q&A, and unit test case generation, significantly enhancing developers' R&D efficiency and providing a high-quality intelligent coding experience.
Application Scenarios
- Rapid development of new projects
You can get started and deliver projects faster by quickly generating the project framework, service code, and prototype based on the CodeArts Agent capabilities.
- Developer-friendly code maintenance
CodeArts Agent can parse the project code repository and identify semantics and service logic. It accelerates onboarding for legacy systems and streamlines ongoing maintenance and iteration.
- Smart coding and creative development
CodeArts Agent helps with code writing, completion, and generation across all scenarios, adapting to multiple tech stacks and significantly reducing the repetitive coding work.
- Code quality control
Both the explore and standard modes balance development flexibility and compliance requirements. Built-in coding specifications and security monitoring ensure code security, compliance, and maintainability.
- Debugging and bug fixes
CodeArts Agent can intelligently analyze logs and code stacks to locate root cause issues. It will then provide a solution and automatically generate code to rectify the fault.
- Collaborative creation and retention of knowledge assets
CodeArts Agent helps accumulate project knowledge and common development skills and unify coding standards, which accelerates employee onboarding and improves R&D collaboration efficiency.
Function Description
The table below lists the main functions of the CodeArts Agent extension available for Visual Studio Code and JetBrains IDEs.
| Function | Description |
|---|---|
| Agents | An agent is used to understand developer needs and plans tasks automatically. It enables full process automation from requirement analysis to coding, boosting efficiency in end-to-end development. For more information, see Agent Chats. |
| Code generation | The agent can generate context-based code suggestions in the editor. Code generation can be triggered either automatically or through shortcut keys. For more information, see Code Generation. |
| Intelligent Q&A | The agent delivers end-to-end support for requirement analysis, coding, testing, and release. It acts as a conversational sidekick that keeps your team in flow by bringing the right project knowledge when you need it. As the conversation continues, it maintains multi-turn context, cutting time-to-answer. For more information, see Intelligent Q&A. |
| Unit testing | The agent provides end-to-end test case generation, covering test design, test case generation, and intelligent test case repair. For more information, see Unit Test Agent. |
| Context | The agent introduces context information to improve Q&A accuracy. Context helps the agent understand the background and intent of your question better to generate more practical and valuable answers. For more information, see Adding Context. |
| Multimodal input |
For more information, see Multimodal Input. |
| Repository indexing | The agent parses and indexes code to help you quickly search for and retrieve related information from code repositories. For more information, see Repository Indexing. |
| MCP | The agent connects to an MCP server using the Model Context Protocol (MCP). It leverages the server's extra tools and resources to enhance its capabilities. For more information, see MCP. |
| Skills | Professional knowledge can be encapsulated into skills. You can select the most appropriate skills according to specific development scenarios and collaboration needs, achieving flexible and efficient code management. For more information, see Skills. |
| Skill auto-evolution | Skill auto-evolution is an AI capability for continuous self-improvement. When enabled, after completing each task for you, the AI reviews how well it performed, retaining effective methods and refining areas that fell short. The more it is used, the more familiar it becomes with your habits, making it increasingly efficient at handling similar tasks over time. This saves you from manually updating settings. For more information, see Lab Features. |
| Chat history | You can view your chat history with the AI, including previous questions, answers, and context. For more information, see Chat History. |
| Hooks | With hooks, you can insert custom logic into key lifecycle points of the CodeArts Agent extension to extend functionality without modifying any existing code. For more information, see Hooks. |
| Slash commands | Slash commands are an efficient way to interact, allowing the agent to quickly execute common tasks within a chat. CodeArts Agent has been preconfigured with some common commands. You can also customize commands as needed. For more information, see Slash Commands. |
| Scheduled tasks | You can create scheduled tasks to automatically run preset operations and export results at custom times or intervals without manual effort. For more information, see Scheduled Tasks. NOTE: Scheduled task data is stored in the following local directories:
|
| Obtaining Logs | You can obtain and view log information to improve troubleshooting efficiency and locate and analyze problems in a timely manner. For more information, see Obtaining Logs. |
What is your overall rating for this page?
Thank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.
For any further questions, feel free to contact us through the chatbot.
Chatbot