Help Center/ CodeArts Agent/ User Guide (IDE)/ Settings/ Global Settings of the IDE
Updated on 2026-07-29 GMT+08:00
View PDF
Share

Global Settings of the IDE

Click in the upper right corner of CodeArts Agent IDE to open the settings page. Then you can customize the global settings based on your preferences and habits.

Account

View information about the current login account.

  • If you are logged out, click Log In to access the login page.
  • If you are logged in, the name and ID of your current account are displayed. Click Log Out to log out of the current account.

General

Figure 1 General
Table 1 General configuration items

Type

Configuration Item

Description

Basic settings

Theme

Choose the visual style for the CodeArts Agent IDE interface.

Currently, dark and light themes are supported, and you can also choose More to install other themes from the marketplace. Switch freely based on your environment and personal preference to improve coding comfort and visual experience.

Language

Choose the language for button labels and other text. Switch between Simplified Chinese and English as needed.

Preference settings

Editor

Set editor parameters.

Click Configure to open the editor settings page and adjust editor features like fonts, workspace, and windows for a personalized development setup.

Shortcut Keys

Customize shortcut keys.

Click Configure to customize shortcuts for CodeArts Agent IDE tasks and boost your productivity.

Quick actions

Command Palette

Click Open to access the command palette. Type keywords to find and run commands easily in CodeArts Agent IDE.

Chats

Figure 2 Display of gutter icons
Table 2 Configuration items

Type

Configuration Item

Description

Chat settings

Response Language

Determine the response language for the model during chats. Choose a specific language or let the model adapt to the user's input language automatically, ensuring flexibility across various situations. Available choices include:

  • Auto: The model detects the question's language and responds accordingly.
  • Chinese: The model responds exclusively in Chinese, no matter what language the question uses.
  • English: The model responds exclusively in English, no matter what language the question uses.

Send Shortcut

Press Enter to send a message, Ctrl+Enter to start a new line: After entering a prompt in the input box, press Enter to send it. If you want to wrap the line and continue typing, press Ctrl+Enter.

Press Ctrl+Enter to send a message, Enter to start a new line: After entering a prompt in the input box, press Ctrl+Enter to send it. If you want to wrap the line and continue typing, press Enter.

Voice Settings

Customize the language displayed after speech-to-text conversion. Select one of the following options from the drop-down list:

  • Chinese: Regardless of whether the voice input is in Chinese, English, or a mix of both, the system converts it into the corresponding language (Chinese, English, or mixed of both).
  • English: Regardless of whether the voice input is in Chinese, English, or a mix of both, the system automatically converts it into English.

Basic settings

Font Size

Set the font size on the CodeArts Agent interface.

Gutter Icons

Gutter icons, as shown in Figure 2, are shortcut icons displayed next to definition lines of functions, classes, and other elements in the gutter area of the code editor. They are used to quickly perform common development operations.

Select the desired features (such as code explanation, commenting, optimization, and unit testing) from the drop-down list. The selected features will be displayed in the gutter area next to the corresponding code line. Click the icon and select the corresponding function to quickly perform operations on functions, classes, and other elements, improving development efficiency.

Advanced settings

Minimum Log Level

Choose the minimum log level needed to maintain both system efficiency and effective troubleshooting.

  • Configuration principles: You are advised to set the log level to Debug. Debug logs record internal code execution details during development and debugging, making it easier to locate and troubleshoot problems that occur during code execution.
  • Log level: Log levels increase in severity like this: Debug, Info, Warn, and Error.
    • Debug: records detailed internal information during runtime, such as request details and process steps. This level is mainly used for debugging and fault locating in the development phase.
    • Info: records key status information during normal runtime, such as service startup and request processing summaries, to help you understand the basic system workflow.
    • Warn: records potential issues that may affect system stability, such as missing configurations and insufficient resources. These issues do not directly cause program interruption.
    • Error: records errors that have caused some functions to be abnormal or operations to fail, such as API calling failures and data parsing errors. These errors require timely attention and rectification.

Agents

Terminal Command Running Mode

Select a policy for the agent to execute terminal commands based on your security requirements. By default, all terminal commands must be manually approved by you before execution.

  • Running in Sandbox: Operations are performed automatically in a secure sandbox by default.
  • Auto Running: The agent directly executes all commands without your approval.

    For security purposes, you are advised to select Auto Running only when necessary. In this mode, the agent bypasses all security checks and may perform high-risk operations without notifications.

  • Manual Running: Before executing any command, the agent sends a confirmation prompt to you. You need to manually confirm it.

Terminal Command Running Mode > Command Whitelist

Add the prefix of a specific command to the whitelist as required. Commands added to the whitelist bypass the sandbox mechanism and are executed outside the sandbox.

NOTE:

This configuration item is displayed only when Terminal Command Running Mode is set to Running in Sandbox.

Terminal Command Running Mode > Custom Sandbox Settings

By configuring the sandbox.json file, you can customize files and the network access scopes for processes within the current project's sandbox environment.

NOTE:

This configuration item is displayed only when Terminal Command Running Mode is set to Running in Sandbox.

Terminal Command Running Mode > Network Access

The agent provides three network access policies for you to choose from. Configure access control rules based on actual service requirements and security levels.

  • Network-wide: Access to all internal and external network resources is allowed.
  • Local: Only the local network (LAN/intranet) can be accessed. Access to the Internet is not allowed.
  • Blocked: All network connections are blocked, and access to internal or external resources is prohibited.
  • Custom: Allows you to modify the JSON policy configuration file to customize the file and network access scope for processes within the project sandbox environment.
NOTE:

This configuration item is displayed only when Terminal Command Running Mode is set to Running in Sandbox.

Auto-approve > Edit

Allow the agent to call tools like edit, write, and deleteFile to edit files on your computer.

Auto-approve > Browser Access

Allow the agent to access websites in the browser.

Auto-approve > Web Crawler

Allow the agent to access and capture specified web page content.

Agent security policy

Dotfile Protection

When enabled, the agent is not allowed to modify configuration files starting with a dot, such as .env and .gitignore.

Edit Scope Protection

When enabled, the agent can only add, modify, and delete files in the current project directory. It cannot edit files in other directories.

Read Scope Protection

When enabled, the agent can only access and read files in the current project directory. It cannot access files in other directories.

Intelligent Q&A

Suggested Questions

When enabled, the system predicts three relevant questions using your preferences and conversation history after answering your question. Click these suggestions to ask them instantly. For details, see Suggested Questions.

Agents

Agents are programming assistants tailored for diverse development scenarios. CodeArts Agent not only provides various built-in agents but also supports custom agent capabilities. By configuring prompts, skills, and tool sets within a custom agent as required, you can create a dedicated assistant to handle complex development tasks more efficiently.

  • Enterprise agents: available to all enterprise users, created by enterprise administrators, and stored in the cloud.
  • Team agents: restricted to designated teams, created by enterprise or team administrators, and stored in the cloud.
  • Project agents: effective only for the current project, distributed along with the repository, and stored locally.
  • User agents: comprised of local and cloud agents.
    • Local user agents: take effect for all projects under the current user and are stored locally.
    • Cloud user agents: are available only to the creator and are stored on the cloud.
  • Built-in system agents: The system provides multiple out-of-the-box agents that require no manual creation, aiming to provide efficient programming assistance for various development scenarios.

For details about built-in agents and custom agents, see Built-in Agents and Custom Agents, respectively.

Models

In addition to system built-in models, enterprise members can also connect third-party large language models to CodeArts Agent IDE. If you have purchased the CodeArts Agent professional edition, you can also add third-party models on the console.

For details about models, see Models.

Code Generation

Figure 3 Code generation
Table 3 Code generation settings

Type

Configuration Item

Description

Basic settings

Code Generation

When enabled, CodeArts Agent provides code generation features, such as real-time suggestions while typing and full code generation via keyboard shortcuts.

Do Not Disturb

When enabled, code generation and chat prompts will be hidden to help you focus on coding. Specify this parameter based on your requirements.

Hide Code Generation Shortcut Hints: Shortcut tips that appear during code selection will not be displayed if this option is toggled on.

Advanced settings

Inline Generation

When enabled, CodeArts Agent instantly generates code for the current line as you type code (before hitting Enter). These suggestions appear within 75 to 1,000 ms.

You can also adjust the debounce delay to prevent accidental triggers. The debounce delay (ms) sets the waiting time before triggering inline generation (ranging from 75 to 1,000 ms).

NOTE:

The tool stops suggesting code if the system faces heavy loads or encounters complex code contexts.

Block Generation

When enabled, CodeArts Agent will suggest ways to complete the smallest code block as soon as you hit Enter.

NOTE:

The tool stops generating code blocks if the system faces heavy loads or encounters complex code contexts.

Intelligent Truncation

When enabled, CodeArts Agent detects the code context and generates full code blocks automatically.

Java, C, C++, and Python are currently supported.

MCP

CodeArts 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. You can add an MCP server here. For details, see MCP.

Skills and Rules

You can view and configure skills and rules for enterprises, teams, projects, and users. This ensures consistent yet adaptable workflows tailored to general standards or individual preferences.

  • Enterprise skills and rules: Standardized skill libraries and business rules that are centrally built, managed, and distributed at the company or large organization level. The core objective is to eliminate execution deviations and ensure that different teams and individuals strictly adhere to unified operation standards, security protocols, and process guidelines in complex business scenarios. This enhances overall operational consistency and controllability.
  • Team skills and rules: Skills and rules that are uniformly configured for teams or departments to standardize team operations and ensure consistent operations among all members. Only team administrators or department administrators can create, modify, and delete these skills and rules. Common members can only use them.
  • Project skills and rules: Skills and rules that apply only to the current project. Bound to the project repository, they are distributed alongside it to address specific project needs.
  • User skills and rules are classified into local and cloud ones.
    • Local ones: effective for all projects of the current user, formulated based on personal habits or preferences, and stored locally.
    • Cloud ones: formulated based on personal habits or preferences, available only to the members themselves, and stored in the cloud.
  • Built-in skills and rules: basic skills preset in the system, globally available, and ready to use out of the box. They provide stable, continuous baseline functionality and can be used directly without any additional configuration.
  • Skill marketplace: a hub of multiple ready-to-use skills designed to help rapidly boost development efficiency.

For details about how to configure skills and rules, see Skills and Rules, respectively.

Memory

Memory allows CodeArts Agent to adapt to how you work. The agent will record your habits and preferences, such as your preferred answer style and language.

For details, see Memory.

Repository Index

The repository index function is designed to enhance code retrieval efficiency. CodeArts Agent supports building both local user indexes and cloud shared indexes, allowing flexible adaptation based on your actual needs to achieve efficient information retrieval and management.

For details about repository indexes, see Repository Index.

Lab Features

Language Server Protocol (LSP) is a standardized protocol for providing language services. By decoupling language services from the IDE, LSP enables an independent language server process to deliver core capabilities such as code analysis, error diagnosis, fast navigation, and code refactoring.

CodeArts Agent now features a built-in local LSP function. When enabled, the agent can leverage definitions and symbol data from language services for more precise code comprehension and modification.

For details, see LSP.

Knowledge Base

CodeArts Agent enhances chat capabilities by utilizing knowledge bases as context. Developers can upload internal documents and technical resources to improve response accuracy.

For details, see Knowledge Bases.

About CodeArts Agent

Table 4 Configuration items

Type

Configuration Item

Description

About CodeArts Agent

Check for Updates

After you click Check for Updates, the system automatically checks the current version. Meanwhile, the update status appears in the upper right corner of CodeArts Agent IDE. Hovering over it allows you to view the upgrade progress, new features, and error alerts in real time, keeping you informed throughout the upgrade process for a smoother experience.

Product Homepage

Visit the official website of CodeArts Agent and get the latest installation package.

Documents

Read the CodeArts Agent documents for quickstart and usage tips.

What's New

Access the latest updates of CodeArts Agent.

FAQs

Access frequently-asked questions to quickly get guidance and solve problems when using CodeArts Agent.

Knowledge Base Mgmt

Access the knowledge base module on the CodeArts Agent console to handle and use all your knowledge resources efficiently.

Privacy Statement

Visit the privacy statement page of CodeArts Agent to review its terms and guidelines.

Feedback

Open the feedback page to share issues or suggestions. Your input helps us enhance the service.

Version Updates

Update Preferences

When enabled, the system will automatically download and install updates whenever a new version is detected.

  • Check every 12 hours: The system will automatically check for updates every 12 hours while running.
  • Check on each startup: The system will only perform a version check automatically when the IDE starts up, without repeated checks during runtime.

Show Release Notes After Update

When enabled, a window will automatically pop up after each update is completed to display the release notes for the current update.
Parent Topic: Settings