Qoder CN IDE enters full public beta, the coding agent gains planning capabilities, and project awareness and memory awareness have been improved.
Qoder CN IDE enters full public beta with a redesigned interface for a better experience. Combined with the latest Qwen model capabilities, it supports parallel tool invocation and deeply optimizes coding effectiveness, making complex coding tasks more efficient and accurate. At the same time, the coding agent has been upgraded with new planning capabilities (To-do), message queueing, and improvements to project awareness and memory awareness, making agent-based coding more aligned with project scenarios and developer habits.
The coding agent supports configurable automatic execution mode, which developers can enable based on their scenarios. When enabled, developers can also configure a terminal command denylist, greatly improving coding task execution efficiency while ensuring security.
The visual presentation of tool invocations in the AI Chat window has been improved, with visual distinctions based on the importance of the tool and scenario. For example, query-type tool displays are downplayed while terminal execution tools are emphasized, allowing developers to quickly grasp key information within the session flow.
Developers can configure multiple AI execution rules for the same project based on their development scenarios, and can configure how they take effect: always effective, model decision, effective for specified files, or manually included, giving developers greater flexibility.
Qoder CN IDE Enters Full Public Beta
Qoder CN IDE enters full public beta with a redesigned interface for a better experience. Combined with the latest Qwen model capabilities, it supports parallel tool invocation and deeply optimizes coding effectiveness, making complex coding tasks more efficient and accurate. At the same time, the coding agent has been upgraded with new planning capabilities (To-do), message queueing, and improvements to project awareness and memory awareness, making agent-based coding more aligned with project scenarios and developer habits.
Agent Supports Fully Automatic Execution
The coding agent supports configurable automatic execution mode, which developers can enable based on their scenarios. When enabled, developers can also configure a terminal command denylist, greatly improving coding task execution efficiency while ensuring security.
Improved Tool Presentation
The visual presentation of tool invocations in the AI Chat window has been improved, with visual distinctions based on the importance of the tool and scenario. For example, query-type tool displays are downplayed while terminal execution tools are emphasized, allowing developers to quickly grasp key information within the session flow.
Project-Level Multi-AI-Rule Configuration
Developers can configure multiple AI execution rules for the same project based on their development scenarios, and can configure how they take effect: always effective, model decision, effective for specified files, or manually included, giving developers greater flexibility.
More Capability Improvements
- Adding context in AI Chat has been changed to trigger a picker window by typing @ before adding;
- AI Chat (Ask) mode now supports retrieval tool invocation by default, and can be turned off in settings;
- After selecting code lines in the code editor area, right-click actions can be added directly to the chat window as context;
- Improved inline chat editing experience, strengthening the file editing scenario experience;
- Issue reporting now supports adding images;
- Removed the model selection entry point and file editing mode to simplify developer choices.