Changelog for the Qoder CN Visual Studio Code plugin.
Thank you for your continued support and trust in the Tongyi Lingma VSCode plugin. To provide you with a higher-quality and more powerful intelligent coding experience, we sincerely recommend that you upgrade to the new Qoder CN IDE (download link: https://lingma.aliyun.com/download).
About the New Qoder CN IDE Experience
To continuously improve your development efficiency and user experience, we have launched the more feature-rich and higher-performance Qoder CN IDE. As a new-generation intelligent development tool launched by Alibaba Cloud, Qoder CN IDE has been comprehensively optimized and upgraded, integrating richer AI coding capabilities, a smoother interaction experience, and complete enterprise-grade capabilities.
Product Upgrade Recommendation
Considering the long-term development of the product ecosystem and the continuous optimization of user experience, we recommend the following:
Hi, Tongyi Lingma added the coding agent with autonomous decision-making, environment awareness, and tool usage capabilities. Based on developer coding task descriptions, it can use tools such as project retrieval, file editing, and terminal to modify multiple files within the project, performing end-to-end coding tasks.
We aim to build a simple-to-use coding assistant. During a session, developers can freely switch between AI Chat, File Edit, and Agent modes based on scenarios and question difficulty, maximizing work efficiency.
At the same time, we aim to make Lingma more efficient in executing coding tasks. We have built in related tools and strengthened its capabilities:
Jointly launched by Alibaba Cloud Yunxiao and Tongyi Lab, the Tongyi-based intelligent coding assistant — Qoder CN — has the following capabilities:
VSCode Upgrade Recommendation
Thank you for your continued support and trust in the Tongyi Lingma VSCode plugin. To provide you with a higher-quality and more powerful intelligent coding experience, we sincerely recommend that you upgrade to the new Qoder CN IDE (download link: https://lingma.aliyun.com/download).
About the New Qoder CN IDE Experience
To continuously improve your development efficiency and user experience, we have launched the more feature-rich and higher-performance Qoder CN IDE. As a new-generation intelligent development tool launched by Alibaba Cloud, Qoder CN IDE has been comprehensively optimized and upgraded, integrating richer AI coding capabilities, a smoother interaction experience, and complete enterprise-grade capabilities.
Product Upgrade Recommendation
Considering the long-term development of the product ecosystem and the continuous optimization of user experience, we recommend the following:
- Recommended to use Qoder CN IDE: If you want to get the latest features and best experience, we sincerely recommend migrating to Qoder CN IDE to enjoy more complete intelligent coding services.
- Adjustment to VSCode plugin support: If you encounter any issues or inconvenience while using the VSCode plugin, we recommend switching to Qoder CN IDE, where we will provide you with more stable and reliable technical support.
- Feature update notice: Going forward, our product innovation and feature iteration will mainly focus on Qoder CN IDE and the Qoder CN JetBrains plugin. Updates to the VSCode plugin will slow down. If you have any questions or need upgrade assistance, please feel free to submit a ticket to contact our technical support team. Thank you again for your understanding and support!
V2.5.0
2025-12-22 (2.5.19)
- Fixed defects
2025-12-18 (2.5.18)
- The Qoder CN VS Code plugin and JetBrains plugin now have separate version tracks. In future releases, the two plugins will remain independent in terms of login state, session records, and data.
2025-02-10 (2.5.17)
- Fixed defects
2025-07-19 (2.5.16)
- Fixed defects
2025-07-10 (2.5.15)
- Supports configuring multiple AI rules for a project
- Improved MCP service header configuration experience
- Supports clicking to view modified files in chat replies
- Improved code completion speed
- Improved error messages for path anomalies
2025-06-27 (2.5.14)
- Improved the search experience when adding context, supporting simultaneous searching of files, folders, etc.
- Supports adding open files as context
- MCP services support Streamable HTTP
- Improved memory generation
- Improved some UI experiences in MCP services
- Fixed defects
2025-06-19 (2.5.13)
- Code problem fixes (Problem) support Agent mode responses
- Fixed several defects
2025-06-12 (2.5.12)
- Supports Shift-drag of files and folders into the chat window input as context (VS Code 1.100 or later)
- Improved MCP tool parameter configuration experience
- Improved pasting of project code into the chat window input
- Fixed several defects
2025-06-05 (2.5.8)
- The MCP marketplace supports English descriptions
- Fixed an issue where language preference was not followed when tools were enabled in AI Chat mode
2025-05-29 (2.5.8)
- AI Chat (Ask) mode supports tools such as project and code retrieval and web search
- Agent mode adds support for web search tools
- Agent mode supports selecting file directories (#folder)
- Improved personal settings page loading performance
- Fixed occasional account errors in SSH Remote scenarios
- Fixed an occasional issue where pasted images were not recognized
2025-05-22 (2.5.7)
- MCP tool execution in Agent mode supports configurable auto-execution
- Improved the auto-execution whitelist experience for terminal commands, supporting one-click whitelist addition during sessions
- Improved file modification accuracy — automatic retry on failure
- Improved inline chat code change generation
2025-05-15 (2.5.5)
- Added session mode selection suggestion prompt
- Supports one-click repair when MCP services connect abnormally
- Improved output in Agent mode when using the qwen3-thinking model
- Reduced likelihood of flowchart generation under the code explanation instruction
- Fixed occasional project retrieval output compatibility issues when switching between Agent and File Edit modes
2025-05-13 (2.5.4)
- Improved large-file modification in AI Chat scenarios
2025-05-09 (2.5.3)
- Added Inline Edit feature, which can be triggered with ⌘ ⇧ I (Ctrl Shift I)
- Fixed a delay in list updates after MCP service JSON file changes
2025-05-04 (2.5.1)
- Fixed an occasional issue where action buttons were invisible during MCP tool execution.
- Fixed an issue where the personal settings page displayed abnormally on Windows.
2025-04-30 (2.5.0)
Hi, Tongyi Lingma added the coding agent with autonomous decision-making, environment awareness, and tool usage capabilities. Based on developer coding task descriptions, it can use tools such as project retrieval, file editing, and terminal to modify multiple files within the project, performing end-to-end coding tasks.
We aim to build a simple-to-use coding assistant. During a session, developers can freely switch between AI Chat, File Edit, and Agent modes based on scenarios and question difficulty, maximizing work efficiency.
At the same time, we aim to make Lingma more efficient in executing coding tasks. We have built in related tools and strengthened its capabilities:
- Tool usage: Autonomously uses more than a dozen built-in coding tools, such as read/write file, code query, and error troubleshooting. Also supports MCP tool configuration and integrates with the ModelScope MCP marketplace, allowing developers to freely configure.
- Terminal command execution: When performing coding tasks, it can autonomously decide which commands to run, automatically writing commands and running the terminal, greatly improving coding task execution efficiency.
- Project-level changes: Based on the developer's task description, it autonomously breaks down tasks and modifies multiple code files in the project. Through multiple dialogs, it supports incremental iteration or snapshot rollback, collaborating with the developer to complete coding tasks.
- Automatic project awareness: Based on the developer's task description, it can automatically perceive the project framework, technology stack, required code files, error information, and other in-project information — no need to manually add project context, making task description easier.
- Memory awareness: Supports LLM-based autonomous memory. During conversations with Lingma, rich memories about the developer, project, issues, and other topics gradually form — the more you use it, the better it understands you.
- Supports navigation to files, methods, and definitions within the project in AI Chat.
- Supports adding project directories when adding context in AI Chat.
- Supports specifying a knowledge base (Enterprise Edition) when adding context in AI Chat.
- Supports multi-select for files, directories, gitCommit, etc. when adding context in AI Chat.
V2.3.0
2025-04-18 (2.3.0)
- Supports Alibaba Cloud International account login.
- The AI Chat input box supports Shift + Enter for line breaks.
- Removed the offline completion mode toggle from the status bar.
- Improved the search box focus experience when selecting context.
V2.2.0
2025-03-31 (2.2.0)
- Supports developer login for the International Dedicated Edition.
V2.1.0
2025-03-14 (2.1.5)
- When entering text in the AI Chat window, related code files can be recommended based on the selected file.
- Supports configuring Project Rules.
- Enhanced Go language effectiveness in inline code completion scenarios.
- Supports one-click issue reporting when startup fails.
- Supports web login when using Qoder CN on the ModelScope platform.
- Fixed several defects.
2025-02-20 (2.1.2)
- The plugin supports switching between Personal Edition and Enterprise Edition member identities.
- Improved inline completion effectiveness for Java inner class invocation scenarios.
- Improved inline completion similarity awareness.
- Improved automatic context inclusion when selecting input history in the input box.
- Improved full-file awareness when selecting code snippets in AI Chat.
- Improved model reply timeout.
2025-02-12 (2.1.1)
- Fixed an issue where model selection was not clickable in some scenarios.
2025-02-11 (2.1.0)
- AI Chat and AI Developer support model selection.
V2.0.0
2025-01-23 (2.0.8)
- Enhanced AI Developer memory for ongoing session history.
- Mermaid language is now not rendered as a diagram by default, and supports one-click collapse.
- Improved code explanation replies to be more concise.
- Improved apply speed for large-file snippet modifications in AI Developer.
- Improved file path when AI Developer creates new files.
- Fixed an issue where image Q&A failed when questions were asked before image processing completed.
- Fixed occasional multiple triggers when the cursor was in the middle of a tag during completion.
2025-01-16 (2.0.7)
- Supports one-click submission of Qoder CN plugin error logs.
- Improved the experience of resolving startup issues with one-click repair.
- Improved code file generation from images in AI Developer.
- Enhanced SQL generation in code completion scenarios.
2025-01-13 (2.0.4)
- Improved code generation from images in AI Chat.
- AI Developer supports generating code change files in the project from images.
- Enterprise Dedicated Edition accounts support web login in SSH Remote scenarios.
- Fixed an occasional issue where language could not be recognized when generating files in an empty project.
2024-12-24 (2.0.0)
- Hi, Qoder CN added AI Developer capabilities with multi-file code modification and tool usage capabilities, helping developers complete coding tasks end-to-end, such as feature implementation, issue resolution, unit test case generation, and batch code changes. We also upgraded the developer interaction interface with Qoder CN, adding a unified view for managing changed files and a code change review view. Developers only need to describe requirements in natural language and Qoder CN can modify multiple files and present them for developer review and adoption, greatly improving coding productivity. We hope you enjoy the Qoder CN AI Developer coding experience.
V1.4
2024-12-13 (1.4.15)
- Continuously enhanced cross-file awareness for Java and Go.
2024-11-29 (1.4.13)
- Improved cross-file completion for Java and Go.
- Enterprise code generation enhancement now supports C/C++.
- Fixed an issue where .ipynb files could not be selected when choosing context files.
2024-11-21 (1.4.11)
- AI Chat added support for codeChanges and gitCommit context.
- AI Chat multimodal image Q&A supports copy-paste of images.
- Simplified AI Chat shortcut instruction names.
- Improved default context inclusion logic in AI Chat.
2024-11-15 (1.4.10)
- When adding context, search supports fuzzy matching.
- Improved default context reset logic when creating a new session.
- Input box interaction supports shortcut operations.
- Fixed an issue where irrelevant context did not enter a stale state after selecting an instruction.
2024-11-14 (1.4.9)
- Input interaction upgraded to support free combination of context and input text.
- Added support for selecting single or multiple code files as context.
- Added multimodal Q&A mode — after selecting an image, you can perform code generation or issue analysis combining the image content.
- Unit test generation supports awareness of repository POM file configuration.
2024-11-01 (1.4.6)
- AI Chat supports session deletion and copy.
- Fixed defects (various tracking issues).
2024-10-24 (1.4.5)
- Improved local project Q&A effectiveness.
- Fixed various tracking data misalignment issues.
2024-10-17 (1.4.4)
- AI Chat supports Mermaid language preview mode.
- Code completion supports Kotlin cross-file import.
- Code completion strengthens whole-project awareness for Java and Go.
- Improved the in-flight status of the pre-filter security check in AI Chat.
- Improved the copy for enterprise knowledge base Q&A.
2024-09-26 (1.4.3)
- Supports Enterprise Standard Edition developers using personal token login.
- Enhanced library awareness for Python and C#, improving generation.
- Improved personal info page visuals to better match IDE themes.
- Enterprise custom instructions extended IDE compatibility with Windows 7.
2024-09-13 (1.4.0)
- Added enterprise custom instructions.
- Improved prompts on login exceptions.
- Improved Go language generation.
- Improved inline rendering with support for streaming completion.
V1.3
2024-09-04 (1.3.12)
- Enterprise Edition supports AI Chat and code generation filters.
- Improved inline code problem interaction — quickly trigger fix suggestion Q&A on focus.
- Fixed issues with line-breaking after closing tags and parentheses.
- Fixed occasional incomplete extraction of the installation package.
2024-08-22 (1.3.11)
- Optimized library-level awareness and analysis for Go, improving generation.
- Fixed defects.
2024-08-16 (1.3.10)
- Added Enterprise code generation enhancement, supporting JS/TS and Vue.
- Enhanced project awareness during Java generation.
- Enhanced display of the current login identity.
- Improved the position of the inline shortcut entry — unified above the modifier.
- Fixed an issue where code block actions did not stay fixed when scrolling content in AI Chat.
2024-08-07 (1.3.8)
- Fixed occasional layout disorder of code blocks during Q&A.
- Improved inline code generation performance.
2024-08-01 (1.3.7)
- Supports @terminal Q&A for quickly generating commands with one-click execution.
- Supports selecting content in the terminal and right-clicking to explain (VS Code 1.83.0 and above).
- Fixed issues such as overflowing input box prompts and lost selected code during Q&A.
2024-07-25 (1.3.6)
- Supports setting the display language of the various interfaces in Qoder CN.
- Supports setting the preferred language for AI Chat and commit message generation.
- Improved AI Chat input box height and input interaction.
- Improved inline code generation for front-end languages.
- Improved inline code generation performance and trigger logic.
- Improved default naming when creating new files from code blocks in AI Chat.
- Fixed an occasional recognition error for non-code snippets in Q&A.
- Fixed a display issue for @workspace referenced files.
2024-07-13 (1.3.5)
- Added support for configuring the visible developer scope by department for enterprise knowledge bases.
- Supports displaying and viewing reference knowledge snippets during enterprise knowledge base Q&A.
- Improved prompts for no-permission and expiration when using enterprise member identity.
2024-07-04 (1.3.2)
- Improved remote development login — defaults to the Alibaba Cloud login page.
- Improved cross-file generation for Java, Go, and C#.
- Improved local parsing and indexing performance for Java, Python, Go, and C++ projects.
- Enhanced awareness of the current codebase during inline code generation.
- Improved bracket closing and indentation in inline code generation.
2024-06-18 (1.3.1)
- Changed the default shortcut for the code optimization command (Option/Alt+Shift+O changed to Option/Alt+Shift+M).
- Added usage caps for Q&A and inline generation (does not affect usage).
- Improved the no-permission prompt copy for enterprise member identity.
2024-06-06 (1.3.0)
- Supports @workspace for requirement understanding and Q&A based on the current codebase.
- Supports commit message generation.
- Supports generating fix suggestions for code problems (Problem).
- The AI Chat window now allows feedback after a downvote — please share more.
- Improved trigger timing for inline code generation.
- Fixed defects.
V1.2
2024-05-21 (1.2.16)
- Fixed defects.
2024-05-23 (1.2.15)
- Supports enterprise private knowledge base Q&A.
- After selecting features such as generate comments, explain code, or generate unit tests, supports entering auxiliary information and reply requirements.
- Code blocks in the AI Chat window support direct edit and save after viewing Diff.
- The input box supports typing while a reply is in progress.
- Improved naming rules for new unit test files.
- Inline shortcut entries support Kotlin, Go, Python, etc.
- Improved trigger timing for inline code generation.
- Fixed permission issues caused by local storage path modification.
2024-04-28 (1.2.14)
- Supports line-by-line acceptance of inline suggested code.
- Vue supports inline shortcut action entries.
- Improved startup exception guidance.
- Improved guidance for configuring non-triggering programming languages.
- Improved bracket matching logic after completion.
2024-04-24 (1.2.13)
- Fixed a storage path sync issue across different devices with the same account.
2024-04-17 (1.2.10/1.2.11)
- Improved streaming smoothness of AI Chat replies.
- Supports modifying the plugin's local storage path.
- Improved /help content.
- Fixed defects.
2024-04-10 (1.2.9)
- After selecting code, supports triggering generate comments, code optimization, and other actions via shortcuts.
- Fixed issues such as truncated AI Chat replies and error prompts after login.
2024-03-20 (1.2.5)
- Extended IDE version compatibility to 1.68.0 and above.
- Improved comment generation, ensuring inline comments and function-level comments are complete.
- Fixed defects.
2024-03-04 (1.2.4)
- Tongyi brand Logo upgraded.
- Fixed defects.
2024-02-05 (1.2.3)
- Improved the no-permission prompt during Q&A.
- Fixed defects.
2024-01-31 (1.2.2)
- Fixed defects.
2024-01-30 (1.2.1)
- Supports custom configuration of programming languages that do not trigger inline generation.
- Compatible with Windows 7 operating system; extended IDE version compatibility to 1.70.0 and above.
- Improved unit test generation for Java and Python.
- Improved the prompt for identity selection after login.
2024-01-21 (1.2.0)
- Supports enterprise member identity selection on login.
- Improved upvote/downvote operations in AI Chat.
- Fixed occasional rendering issues in AI Chat when asking follow-up questions after stopping.
V1.1
2024-01-09 (1.1.0)
- Added Alibaba Cloud account AK/SK login, addressing WebIDE, Remote SSH, Docker, and WSL usage scenarios.
- Changed remote development login to use AK/SK.
- Improved code block interaction in AI Chat — can be operated on at any time.
- Improved follow-up logic in AI Chat.
V1.0
2023-12-26 (1.0.10)
- AI Chat now supports viewing historical sessions.
- HTTP Proxy supports the Socks5 protocol.
- Supports configuring whether IDE native completion and inline code suggestions display simultaneously.
- Improved local model service presentation during code completion.
- Improved line height of text in Q&A replies.
- Fixed bracket indentation issues in inline generation scenarios.
- Fixed Markdown table rendering issues.
2023-12-11 (1.0.9)
- Added a new feature — Code Optimization, quickly identifying code problems and providing optimization suggestions.
- Supports HTTP Proxy configuration.
- Supports focusing the input box when opening the AI Chat panel, improving Q&A experience and efficiency.
- Supports up/down keys for switching input history in the AI Chat input box.
- Fixed abnormal Markdown line height display.
- Fixed occasional display issues with upvote/downvote icons.
2023-12-07 (1.0.8)
- AI Chat supports including different selected code snippets when asking questions.
- Improved AI Chat UI performance and stability.
- Improved AI Chat layout and style details.
- Fixed occasional card jitter in AI Chat.
- Fixed occasional failure of horizontal scrolling in AI Chat code blocks.
- Fixed the issue where the candidate count setting did not take effect.
2023-11-28 (1.0.7)
- Improved content paragraphs in AI Chat for better readability.
- Fixed code block recognition errors in AI Chat.
- Fixed input box style compatibility issues with high-contrast themes.
- Fixed occasional login failures.
2023-11-22 (1.0.6)
- Fixed some defects.
2023-11-21 (1.0.5)
- Code blocks uniformly support new file creation.
- Improved process lifecycle logic.
- Fixed some defects.
2023-11-13 (1.0.4)
- Supports WSL.
- Supports Dev Container.
- Improved empty directory detection.
- Fixed mixed Chinese/English copy issues in Tips.
2023-11-08 (1.0.3)
- Enhanced startup compatibility on Windows.
- Fixed some defects.
2023-11-01 (1.0.2)
- Fixed some defects.
2023-10-28 (1.0.1)
- Fixed some defects.
2023-10-25 (1.0.0)
Jointly launched by Alibaba Cloud Yunxiao and Tongyi Lab, the Tongyi-based intelligent coding assistant — Qoder CN — has the following capabilities:
- Line-level/function-level real-time continuation.
- Natural language code generation.
- Unit test generation.
- Code comment generation.
- Code explanation.
- R&D AI Chat.