Help Center/ CodeArts Agent/ User Guide (Console)/ Agent Settings

Updated on 2026-07-30 GMT+08:00

Agent Settings

You can manage agents, skills, rules, knowledge bases, and repository indexes on the CodeArts Agent console. After these resources are created, they can be used on the CodeArts Agent client.

Agents

You can manage your custom agents on the Agents page, such as creating, editing, enabling, and deleting the agents. The agents can be synchronized and used on the CodeArts Agent client.

CodeArts Agent supports two types of agents: client-side agents (created on the client) and cloud-side agents (created on the console). When a user logs in to the CodeArts Agent client, the system will locally cache the cloud-side agents which are available to the user. Then, the client will update the cache every 24 hours to keep the agents in sync with the cloud.

**Table 1** Classification of custom agents
Creation Method	Scope of Application	Description
Local	Project	Effective only for the current project, distributed along with the repository, and stored locally. Storage directory: ./ .codeartsdoer/agents in the root directory of the project
Local	User	Effective for all projects of the current user, and stored locally Local storage directory: %USERPROFILE%/.codeartsdoer/agents/
Cloud	Enterprise	Available to all enterprise users, created by enterprise administrators, and stored in the cloud. When a user logs in to the CodeArts Agent client, the system automatically caches the cloud agents accessible to the user to the local directory: %USERPROFILE%/.codeartsdoer/cache/enterprise/agents/.
	Team	Restricted to designated teams, created by enterprise or team administrators, and stored in the cloud. When a user logs in to the CodeArts Agent client, the system automatically caches the cloud agents accessible to the user to the local directory: %USERPROFILE%/.codeartsdoer/cache/team/agents/.
	User	Available only to the creator and stored in the cloud. When a user logs in to the CodeArts Agent client, the system automatically caches the cloud agents accessible to the user to the local directory: %USERPROFILE%/.codeartsdoer/cache/user/agents/.

Log in to the CodeArts Agent console.
In the navigation pane on the left, choose Agent Settings > Agents.
Click Create Agent.

Set agent parameters and click Create and Enable.

**Table 2** Parameters for creating an agent
Parameter	Description
Agent icon	The system provides various preset icons for agents. Click on the icon to select a preferred style.
Agent name	Name of the custom agent to be created. Naming convention: 2 to 20 characters, consisting of letters, digits, underscores, and hyphens (-), and must start with a letter.
Agent type	Working mode of the agent, which affects its behavior logic and capability boundary. Primary/Sub-agent: It can be used as a sub-agent to be called by a primary agent or as a primary agent to call a sub-agent. Primary agent: It runs independently to process user requests and cannot be called by other agents. Sub-agent: It can be called by primary agents to perform specific tasks.
Description	A brief explanation of what the agent does to help users understand its functionality, with a maximum of 5,000 characters.
Applied to	Application scope of the custom agent, which cannot be modified after creation. Individual: Only the creator can use it. Team: It is available only to specified teams and can be created by enterprise administrators or team administrators. Enterprise: It is available to all enterprise members and can be created only by enterprise administrators.
Available team space	This parameter is displayed only when Applied To is set to Team. It specifies the teams that can use the agent. Enterprise administrators can view all teams but can select only one, while team administrators can only view and select the team they belong to.
Prompt	System instructions that define the role, tone, workflow, and rules/specifications of the agent.
Built-in tools	Built-in, out-of-the-box tools provided by the agent. Read: used to retrieve and view files. Edit: used to add, modify, or delete files. Terminal: used to run system commands in the command line environment. Preview: used to preview the generated frontend page in real time. Webfetch: used to capture and read web page content.
Skills	Skills associated with the agent to enable it to perform certain specialized tasks. NOTE: CodeArts Agent has no hard limit on the number of associated skills, but it is recommended that the number not exceed 20 to ensure optimal user experience.

View the created agent.
- Return to the Agent Management page. You can view the created agent in the agent list.
  Figure 1 Viewing the target agent on the Agents page
- On CodeArts IDE, open the settings page and click Agents. Then click to manually refresh the page. After the refresh is complete, open the target tab (for example, User) to view the target agent.
  Figure 2 Viewing the target agent on the settings page
- In the input box on the chat page, click Agent. Verify that the target agent is displayed in the custom agent list.
  
  If you create a sub-agent, it will not be displayed in the custom agent list.

Table 3 shows the operation permissions of different roles on managing cloud custom agents.

**Table 3** Operation permissions of different roles on cloud custom agents
Role	Enterprise Agent	Team Agent	User Agent (Operations Except Editing)	User Agent (Editing)
Enterprise administrators	All operations on all agents.	All operations on all agents.	All operations except editing on all agents.	Editing on agents created by themselves.
Team administrators	No operation permissions.	All operations on agents created by members of their own team.	All operations except editing on agents created by members of their own team.	Editing on agents created by themselves.
Members (of an enterprise or a team)	No operation permissions.	No operation permissions.	All operations except editing on agents created by themselves.	Editing on agents created by themselves.

**Table 4** Managing cloud custom agents
Operation	Procedure
Enabling or disabling a cloud custom agent	Log in to the CodeArts Agent console. In the navigation pane on the left, choose Agent Settings > Agents. In the agent list, click / next to an agent to enable or disable it.
Editing a cloud custom agent	Log in to the CodeArts Agent console. In the navigation pane on the left, choose Agent Settings > Agents. In the agent list, click Edit in the Operation column of the target agent to edit it.
Copying a cloud custom agent	When you need to reuse mature configurations, iterate multiple versions in parallel, share team templates, or isolate tasks, you can achieve this by copying agents. Log in to the CodeArts Agent console. In the navigation pane on the left, choose Agent Settings > Agents. In the agent list, click Copy in the Operation column of the target agent. System built-in agents cannot be copied. Adjust the configuration as required (or retain the default settings) and click Create and Enable to quickly generate a new agent.
Deleting a cloud custom agent	Log in to the CodeArts Agent console. In the navigation pane on the left, choose Agent Settings > Agents. Check the status of the target agent. If it is enabled, disable it first. If it is disabled, go to the next step to delete the agent. Click Delete in the Operation column of the target agent. The Delete Agent dialog box is displayed. Enter DELETE or click Autofill, and then click OK to delete the agent. Deleted agents cannot be restored. Ensure that the agent is no longer needed before performing this operation.

Skills & Rules

You can manage your skills and rules on the Skills & Rules page, such as creating, editing, enabling, and deleting skills and rules. The skills and rules can be synchronized and used on the CodeArts Agent client.

There are two types of skills: client-side skills (created on the client) and cloud-side skills (created on the console). Meanwhile, these skills are classified into enterprise-level, team-level, project-level, and user-level skills.

**Table 5** Classification of custom skills
Creation Method	Scope of Application	Description
Local	Project	Applied to the current project and stored in a local path Storage directory: ./.codeartsdoer/skills/ in the root directory of the project
Local	User	Effective for all projects of the current user, and stored locally Local storage directory: %USERPROFILE%/.codeartsdoer/skills
Cloud	Enterprise	Skills unified across the enterprise, available to all members, created by the enterprise administrator, and stored in the cloud.
	Team	Skills unified across the team, available to specific teams, created by the enterprise administrator or team administrator, and stored in the cloud.
	User	Available only to the user and stored in the cloud.

If skills with the same name exist, the skill invocation priority is as follows: cloud enterprise skills > cloud team skills > local project skills > local user skills > cloud user skills > built-in system skills.

There are two types of rules: client-side rules (created on the client) and cloud-side rules (created on the console). Meanwhile, these rules are classified into enterprise-level, team-level, project-level, and user-level rules. To create client-side user-level rules, see Creating Cloud-Side Rules in IDE.

**Table 6** Rule types
Creation Method	Scope of Application	Description
Local	Project	Effective only for the current project, distributed along with the repository, and stored locally. Rule file storage directory: ./.codeartsdoer/rule in the root directory of the project.
Local	User	Effective for all projects of the current user, formulated based on personal habits or preferences, and stored locally. Local storage directory: %USERPROFILE%/.codeartsdoer/rule
Cloud	Enterprise	Rules unified across the enterprise, available to all members, created by the enterprise administrator, and stored in the cloud.
	Team	Rules unified across the team, available to specific teams, created by the enterprise administrator or team administrator, and stored in the cloud.
	User	Rules formulated based on personal habits or preferences, available only to the members themselves, and stored in the cloud.

If rules with the same name exist, the rule invocation priority is as follows: cloud enterprise rules > cloud team rules > local project rules > local user rules > cloud user rules.

To create an enterprise skill, a team skill, or user skill on the cloud, perform the following steps: Before creating a cloud skill, ensure that you have purchased CodeArts Agent basic or professional edition.

Log in to the CodeArts Agent console.
In the navigation pane on the left, choose Agent Settings > Skills and Rules. The skill and rule lists are displayed.
On the Skills tab, click Add Skill in the upper right corner. The Add Skill dialog box is displayed.
Right-click in the blue box area and upload the target skill ZIP file from the local. Alternatively, drag and drop the local skill ZIP file to the blue box area and click OK.
- The skill ZIP file must conform to the required directory structure; otherwise, the import may fail. For example, the root directory of each skill folder must contain a SKILL.md file, which must include the skill name, description, and other details in YAML format.
- Only one ZIP file can be uploaded at a time. The file can contain multiple skill folders, and the total file size cannot exceed 5 MB.
Figure 3 Creating a skill

Set parameters for creating a cloud skill as instructed in Table 7.

Figure 4 Creating a cloud skill
Click to enlarge

**Table 7** Cloud skill parameters
Parameter	Description
Change	If you need to re-upload a skill ZIP file, click Change and re-upload it as instructed in 4.
Applied To	Private: available only to yourself and will not be shared with other users. Team: available to specified teams and can be created by enterprise administrators or team administrators. Enterprise: available to all members of the entire enterprise, and can only be created by enterprise administrators.
Teams	This parameter is displayed only when Applied To is set to Team. Select a team from the drop-down list. If no team has been created, create one first. Enterprise administrators can view and select all teams, while team administrators can only view and select the team they belong to.
Tag	(Optional) Several types of tags have been preset in CodeArts Agent. Select tags from the drop-down list as required.

Click Confirm and Enable to complete the skill creation.

On the Skills tab, view the created skill. To immediately view the created cloud skill on the client, go to the corresponding skill tab (Enterprise/Team/User) under Skills and Rules on the client, and click or choose > Update in the skills area. Then the cloud skill is synchronized to the client.
- The CodeArts Agent client automatically synchronizes cloud skills every 24 hours.
- The CodeArts Agent client synchronizes only enabled skills.

Table 8 shows the operation permissions of different roles on managing cloud skills.

**Table 8** Operation permissions of different roles on cloud skills
Role	Enterprise Skill	Team Skill	User Skill (Operations Except Editing)	User Skill (Editing)
Enterprise administrators	All operations on all skills.	All operations on all skills.	All operations except editing on all skills.	Editing on skills created by themselves.
Team administrators	The following operations can be performed: View cloud skill details. Favorite or unfavorite skills.	All operations on skills created by members of their own team.	All operations except editing on skills created by members of their own team.	Editing on skills created by themselves.
Team members	The following operations can be performed: View cloud skill details. Favorite or unfavorite skills.	The following operations can be performed on skills created by members of their own team: View cloud skill details. Favorite or unfavorite skills.	All operations except editing on skills created by themselves.	Editing on skills created by themselves.
Enterprise members	The following operations can be performed: View cloud skill details. Favorite or unfavorite skills.	No operation permissions.	All operations except editing on skills created by themselves.	Editing on skills created by themselves.

**Table 9** Managing Cloud Skills
Operation	Procedure
Viewing cloud skill details	On the CodeArts Agent console, choose Skills & Rules, click the Skills tab, and then click the name of the target skill to view its details. On the settings page of CodeArts Agent IDE, choose Skills and Rules. Go to the corresponding skill tab (Enterprise/Team/User). Hover the cursor on the target skill and click to view the skill details.
Editing cloud skills	On the CodeArts Agent console, choose Skills & Rules, click the Skills tab, and view the status of the target skill. If it is enabled, disable it first. If it is disabled, go to the next step to edit the skill. Click Edit next to the target skill.
Deleting a cloud skill	On the CodeArts Agent console, choose Skills & Rules, click the Skills tab, and view the status of the target skill. If it is enabled, disable it first. If it is disabled, go to the next step to delete the skill. Click Delete next to the target skill. The target skill is successfully deleted when it is removed from the skill list. CAUTION: Deleting a skill will affect the agents using it. Deleted skills cannot be recovered. Exercise caution when performing this operation.
Enabling or disabling a cloud skill	Use either of the following methods to enable or disable a cloud skill: On the CodeArts Agent console, choose Skills & Rules, click the Skills tab, and click / next to the target skill. On the settings page of CodeArts Agent IDE, choose Skills and Rules. Go to the corresponding skill tab (Enterprise/Team/User). Toggle a target skill on or off. Only enabled skills can be synchronized to the CodeArts Agent client.
Adding a cloud skill to favorites or removing it	On the CodeArts Agent console, choose Skills & Rules, click the Skills tab, and click Favorite or Unfavorite next to the target skill. View the favorites on the Favorites tab.
Batch deleting cloud skills	On the CodeArts Agent console, choose Skills & Rules, click the Skills tab, and view the status of the target skill. If it is enabled, disable it first. If it is disabled, go to the next step to delete the skill. Select the target skills and choose More > Batch Delete in the upper right corner. A confirmation dialog box is displayed. Enter DELETE or click Autofill, and then click OK. The target skill is successfully deleted when it is removed from the skill list.
Batch enabling or disabling cloud skills	Use either of the following methods to batch enable or disable cloud skills: On the CodeArts Agent console, choose Skills & Rules, and click the Skills tab. Select the target skills and click Batch Enable or choose More > Batch Disable in the upper right corner. On the settings page of CodeArts Agent IDE, choose Skills and Rules. Go to the corresponding skill tab (Enterprise/Team). Click in the upper right corner. Select the target skills and click Enable or Disable in the upper right corner. On the settings page of CodeArts Agent IDE, choose Settings > Skills and Rules > User. Choose > Batch Operate in the upper right corner. Select the target skills and click Enable or Disable in the upper right corner. Only enabled skills can be synchronized to the CodeArts Agent client.
Batch adding cloud skills to favorites or removing them	On the CodeArts Agent console, choose Skills & Rules, and click the Skills tab. Select the target skills and choose More > Batch Favorite or More > Batch Unfavorite in the upper right corner. View the favorites on the Favorites tab.

To create an enterprise rule, a team rule, or user rule on the cloud, perform the following steps:

Log in to the CodeArts Agent console.
In the navigation pane on the left, choose Agent Settings > Skills and Rules. The skill and rule lists are displayed.
On the Rules tab, click Add Rule in the upper right corner. The Add Rule dialog box is displayed.

Set the parameters based on Table 10.

Figure 5 Creating a cloud rule
Click to enlarge

**Table 10** Cloud rule parameters
Parameter	Description
Name	Name of the rule to be created. Naming rules: Enter 1 to 64 characters. Only letters, digits, underscores (_), hyphens (-), and periods (.) are allowed.
Content	Customize one or more rules. The value can contain a maximum of 50,000 characters. Example: requiring the system to always respond using Python.
Application Scope	Application scope of a rule, that is, where the rule takes effect. Auto Apply: The rule applies to all chats by default and is automatically identified by the system. Manual Call: The rule does not take effect automatically. You must enter # in the chat area and select a specific rule from the list to apply it.
Applied To	Private: available only to the members themselves and will not be shared with other users. Enterprise: available to all members of the entire enterprise, and can only be created by enterprise administrators. Team: available to specified teams and can be created by enterprise administrators or team administrators.
Teams	This parameter is displayed only when Applied To is set to Team. Select a team from the drop-down list. If no team has been created, create one first. Enterprise administrators can view and select all teams, while team administrators can only view and select the team they belong to.
Tag	(Optional) Several types of tags have been preset in CodeArts Agent. Select tags from the drop-down list as required.
Brief Description	(Optional) Description of the rule. Enter up to 1,024 characters.

Click Confirm and Enable to complete the rule creation.

On the Rules tab, view the created rule. To immediately view the created cloud rule on the client, go to the corresponding rule tab (Enterprise/Team/User) under Skills and Rules on the client, and click in the rules area. Then the cloud rule is synchronized to the client.
- The CodeArts Agent client automatically synchronizes cloud rules every 24 hours.
- The CodeArts Agent client synchronizes only enabled rules.

Table 11 shows the operation permissions of different roles on managing cloud rules.

**Table 11** Operation permissions of different roles on cloud rules
Role	Enterprise Rule	Team Rule	User Rule (Operations Except Editing)	User Rule (Editing)
Enterprise administrators	All operations on all rules.	All operations on all rules.	All operations except editing on all rules.	Editing on rules created by themselves.
Team administrators	The following operations can be performed: Favorite or unfavorite rules. Modify the application scope of cloud rules.	All operations on rules created by members of their own team (including the team administrator).	All operations except editing on rules created by members of their own team (including the team administrator).	Editing on rules created by themselves.
Team members	The following operations can be performed: Favorite or unfavorite rules. Modify the application scope of cloud rules.	The following operations can be performed on rules created by members of their own team (including the team administrator): Favorite or unfavorite rules. Modify the application scope of cloud rules.	All operations except editing on rules created by themselves.	Editing on rules created by themselves.
Enterprise members	The following operations can be performed: Favorite or unfavorite rules. Modify the application scope of cloud rules.	No operation permissions.	All operations except editing on rules created by themselves.	Editing on rules created by themselves.

**Table 12** Managing cloud rules
Operation	Procedure
Editing a cloud rule	On the CodeArts Agent console, choose Skills & Rules, click the Rules tab, and view the status of the target rule. If it is enabled, disable it first. If it is disabled, go to the next step to edit the rule. Click Edit next to the target rule.
Deleting a cloud rule	On the CodeArts Agent console, choose Skills & Rules, click the Rules tab, and view the status of the target rule. If it is enabled, disable it first. If it is disabled, go to the next step to delete the rule. Click Delete next to the target rule. The target rule disappears from the list once successfully deleted. CAUTION: Deleting a rule will affect the agents using it. Deleted rules cannot be recovered. Exercise caution when performing this operation.
Enabling or disabling a cloud rule	On the CodeArts Agent console, choose Skills & Rules, click the Rules tab, and click / next to the target rule. Only enabled rules can be synchronized to the CodeArts Agent client.
Adding a cloud rule to favorites or removing it	On the CodeArts Agent console, choose Skills & Rules, click the Rules tab, and click Favorite or Unfavorite next to the target rule. View the favorites on the Favorites tab.
Batch deleting cloud rules	On the CodeArts Agent console, choose Skills & Rules, click the Rules tab, and view the status of the target rule. If it is enabled, disable it first. If it is disabled, go to the next step to delete the rule. Select the target rules and choose More > Batch Delete in the upper right corner. A confirmation dialog box is displayed. Enter DELETE or click Autofill, and then click OK. The target rule disappears from the list once successfully deleted.
Batch enabling or disabling cloud rules	On the CodeArts Agent console, choose Skills & Rules, and click the Rules tab. Select the target rules and click Batch Enable or choose More > Batch Disable in the upper right corner. Only enabled rules can be synchronized to the CodeArts Agent client.
Batch adding cloud rules to favorites or removing them	On the CodeArts Agent console, choose Skills & Rules, and click the Rules tab. Select the target rules and choose More > Batch Favorite or More > Batch Unfavorite in the upper right corner. View the favorites on the Favorites tab.
Modifying the application scope of cloud enterprise rules or team rules	On the settings page of CodeArts Agent IDE, choose Skills and Rules > Enterprise > Rules or Skills and Rules > Team > Rules. Locate the target rule and click the switch next to it. : You need to manually apply the rule. : The system automatically identifies the rule and applies it.
Batch modifying the application scope of cloud enterprise rules or team rules	On the settings page of CodeArts Agent IDE, choose Skills and Rules > Enterprise > Rules or Skills and Rules > Team > Rules. Click in the upper right corner. Select the target rules and click Enable or Disable in the upper right corner.

Knowledge Space

You can upload enterprise internal documents and technical materials to the Knowledge Space page for unified management. The knowledge can serve as contextual reference to improve the accuracy of the agent's responses. Knowledge spaces can only be created and managed on the console, and only accounts with seats enabled can perform related operations.

Create a knowledge space.

A knowledge space is used to manage multiple knowledge bases in one place. Before creating a knowledge base, you need to create a knowledge space.

On the Knowledge page, click Create Space and set parameters by referring to Table 13.

Figure 6 Creating a knowledge space
Click to enlarge

**Table 13** Parameters for creating a knowledge space
Parameter	Description
Name	Indicates the name of the knowledge space to be created. Naming rules: The name cannot start with an underscore (_) and can contain a maximum of 18 characters, including letters, digits, underscores (_), and hyphens (-).
Visible To	Controls the access permissions of members. Private: available only to members themselves. Team: available only to team members and created by the enterprise administrator or team administrator. Enterprise: available to all enterprise members and created by the enterprise administrator.
Teams	This parameter is displayed only when Visible To is set to Team. Select a team from the drop-down list; only the teams which the current account belongs to are displayed.
Tag	(Optional) Indicates the tags to be added to the knowledge space for content classification and management. A maximum of 10 tags can be selected. If you have not created any tags yet, follow the operations below to create them. Otherwise, proceed to the next step. Select Add from the drop-down list. In the displayed dialog box, enter a tag name containing a maximum of 32 characters and click OK. Select the target tag.
Description	(Optional) Indicates the description of the knowledge space. A maximum of 300 characters are allowed. A detailed description helps CodeArts Agent accurately understand the knowledge scope, improving retrieval and matching precision.

Click OK.
In the knowledge space list, you can view the created one.

Create a knowledge base.

Create a knowledge base within a knowledge space and specify its type and source. This ensures a clear information structure and easy retrieval.

Select your desired knowledge space from the list to view its detailed information.
Click Create Knowledge Base in the upper right corner.

Configure basic information by referring to Table 14.

Figure 7 Creating a knowledge base
Click to enlarge

**Table 14** Basic parameters of a knowledge base
Parameter	Description
Name	Indicates the name of the knowledge base to be created. Naming rules: The name cannot start with an underscore (_) and can contain a maximum of 32 characters, including letters, digits, underscores (_), and hyphens (-).
Knowledge Type	Indicates the knowledge base type. You can select Unstructured or Structured. Unstructured: Data does not have a fixed format. Structured: Data has fixed formats, fields, and structures.
Data Source	Indicates the data source of the knowledge base. You can select Local file or Code. When Knowledge Type is set to Unstructured, the following data sources are supported: Local file: The code base mainly contains textual content, such as articles, reports, and books. Supported formats include TXT, DOCX, PDF, MD, CSV, XLS, and XLSX. Code: Only ZIP packages containing Java, Python, C, C++, or Vue code files are supported. When Knowledge Type is set to Structured, only local JSON files are supported.
Knowledge Description	(Optional) Indicates the description of the knowledge base content. A maximum of 300 characters are allowed. A detailed description helps guide the agent to call and utilize the knowledge base more accurately.

Click Next and complete the content import configuration by referring to Table 15.

**Table 15** Content import configuration parameters
Parameter	Description
Embedding Model	Select an embedding model to vectorize the uploaded files/code. The following models are available. bge-m3: a multilingual 1024-dimensional text embedding model that supports hybrid retrieval (dense, sparse, and multi-vector representation). It supports a maximum text length of 8,192 tokens, making it ideal for complex, multilingual scenarios. m3e-base: a general-purpose 768-dimensional embedding model for Chinese and English text, suitable for most basic semantic understanding and retrieval tasks. bge-large-zh-v1.5: a Chinese-specific model optimized for tasks such as retrieval, classification, clustering, and semantic matching. paraphrase-multilingual-MiniLM-L12-v2: a 364-dimensional multilingual embedding model that excels in text similarity calculations, ideal for speed-sensitive scenarios. VESO-v1.3: a specific model deeply optimized for code, delivering outstanding performance in code vectorization and search tasks.
Splitter	This parameter is displayed when Knowledge Type is set to Unstructured and Data Source is set to Local file. The way your content is split depends on the splitter you choose. Different languages can use different splitters for optimal results. By paragraph: Splits text by double line breaks (\n\n) or paragraph structure. By line: Splits text by single line breaks (\n). By sentence (for English): Splits text by sentence boundaries. By character: Splits text into individual characters (including whitespace characters).
Chunk Length	This parameter is displayed when Knowledge Type is set to Unstructured and Data Source is set to Local file. Range: 50 to 1,200 characters. Default value: 1,000 characters.
Chunk Overlap	This parameter is displayed when Knowledge Type is set to Unstructured and Data Source is set to Local file. Overlap between sequential chunks: 0 to chunk length (default value: 0).
Child Splitter	This parameter is displayed when Knowledge Type is set to Unstructured and Data Source is set to Local file. Applied when a chunk exceeds the maximum allowed length. Currently, the following child splitters are supported: By character: Splits text into individual characters (including whitespace characters). By sentence (for English): Splits text by sentence boundaries. By word (for English): Splits text by whitespace characters.
Index Fields	This parameter is displayed when Knowledge Type is set to Structured. Enter the JSON keys to be used as index fields during retrieval. Up to 20 fields are supported, separated by English commas (,).
Filter Fields	This parameter is displayed when Knowledge Type is set to Structured. Enter the JSON keys to be used as filter criteria during retrieval. Up to 2 fields are supported, separated by English commas (,).
Indexed Field	This parameter is displayed when Data Source is set to Code. Select indexed fields to specify which data fields the system needs to build indexes for in advance. During retrieval, the agent will perform keyword matching only against these indexed fields. For example, if function body is selected as an indexed field, the agent will prioritize matching keywords within the function body section of the code when a user enters a search query.
Use Sliding Window	This parameter is displayed when Data Source is set to Code. Once enabled, complex functions are segmented into chunks to improve search accuracy.

Click OK.
In the knowledge base list, you can view the created one.

Import files.

After creating a knowledge base, you can upload various local documents to it. Once uploaded, the system automatically cleans the data and builds indexes, ensuring that your imported content can be quickly retrieved and called for instant knowledge accumulation.

Click the name of your desired knowledge base in the list to view its detailed information.
Click Import File in the upper right corner.

Select target code files or other files from the local and click OK to return to the knowledge base page.

Figure 8 Uploading code files or other files
Click to enlarge

You can upload code files or other files based on your required knowledge type. The maximum size for a single file or ZIP package is 20 MB, and the maximum capacity for a single knowledge base is 50 MB.

**Table 16** Description for file importing
Knowledge Type	Data Source	Description
Unstructured	Local files	TXT, DOCX, PDF, MD, CSV, XLS, and XLSX files are supported.
Unstructured	Code	Only ZIP packages containing Java, Python, C, C++, or Vue code files are supported.
Structured	Local files	Only JSON files are supported.

View the import result.
When Ingestion Status changes from Uploading to Ingested, the file import is successful.

Table 17 shows the operation permissions of different roles on managing knowledge bases.

**Table 17** Operation permissions of different roles on knowledge bases
Role	Enterprise Knowledge Base	Team Knowledge Base	User Knowledge Base
Enterprise administrators	All operations on all knowledge bases.	All operations on the knowledge bases of the team which the enterprise administrator belongs to.	All operations on the knowledge bases created by themselves.
Team administrators	The following operations can be performed: Test hit rates of knowledge bases. View operation history on knowledge bases.	All operations on knowledge bases created by members of their own team (including the team administrator).	All operations on the knowledge bases created by themselves.
Team members	The following operations can be performed: Test hit rates of knowledge bases. View operation history on knowledge bases.	The following operations can be performed on knowledge bases created by members of their own team (including the team administrator): Test hit rates of knowledge bases. View operation history on knowledge bases.	All operations on the knowledge bases created by themselves.
Enterprise members	The following operations can be performed: Test hit rates of knowledge bases. View operation history on knowledge bases.	No operation permissions.	All operations on the knowledge bases created by themselves.

**Table 18** Managing knowledge bases
Operation	Procedure
Editing a knowledge space	On the knowledge space page, click on the target knowledge space and choose Edit.
Deleting a knowledge space	Before deleting a knowledge space, you must clear all knowledge bases in the space. On the knowledge space page, click on the target knowledge space and choose Delete. The Delete Knowledge Space dialog box is displayed. Click Autofill. The system automatically enters DELETE. Click OK to delete the knowledge space. The target knowledge space has been removed from the knowledge space page, indicating that the deletion was successful. CAUTION: Deleting a knowledge space will delete all resources within it. Once confirmed, data cannot be recovered; make a backup before this operation.
Testing the hit rate of a knowledge base	The hit rate test is designed to run search queries against the knowledge base to verify the accuracy and relevance of retrieval results. On the knowledge space page, click Hit Test in the upper right corner. Select up to 10 knowledge bases to be tested. Select the field to be retrieved from the drop-down list. Select a retrieval mode. Text: Based on keyword matching; best suited for exact-word matches and short queries. Vector: Based on semantic similarity; understanding context and synonyms, making it ideal for natural language queries. Hybrid: Combining text and vector retrieval, using weighted fusion of both results. This generally yields better performance, especially for complex semantic queries. Enter the content you want to search (maximum 1,000 characters). Set the number of returned results. Click Debug. You can view the final results under Chunks.
Deleting a knowledge base	When content is severely outdated and holds no retention value, or contains critical errors where correction is too costly or impossible, follow the steps below to delete the knowledge base. On the knowledge space page, click the knowledge space where the target knowledge base is located to view its details. Locate the row that contains the target knowledge base, and click Delete. The Delete Knowledge Base dialog box is displayed. Click Autofill. The system automatically enters DELETE. Click OK to delete the knowledge base. The target knowledge base has been removed from the knowledge space details page, indicating that the deletion was successful. CAUTION: Deleting a knowledge base will delete all data within it. The deleted data cannot be recovered. Ensure that you have backed up important data before this operation.
Batch deleting knowledge bases	Deleting knowledge bases one by one manually is inefficient; you can batch delete knowledge bases through the following steps: On the knowledge space page, click the knowledge space where the target knowledge base is located to view its details. Click Batch Delete in the upper right corner and select the target knowledge bases. Click Delete. The Batch Delete Knowledge Bases dialog box is displayed. Click Autofill. The system automatically enters DELETE. Click OK to delete the knowledge bases. The target knowledge bases have been removed from the knowledge space details page, indicating that the deletion was successful. CAUTION: Deleting a knowledge base will delete all data within it. The deleted data cannot be recovered. Ensure that you have backed up important data before this operation.
Viewing operation history on knowledge bases	On the knowledge space page, click the knowledge space where the target knowledge base is located to view its details. Click History in the upper right corner to view the operation logs of all knowledge bases in the knowledge space.
Re-importing a file	If file upload fails, check your network connection or file format, and click Reimport to try again. On the knowledge space page, click the knowledge space where the target knowledge base is located to view its details. Click the name of the target knowledge base to view its details. Click Reimport in the upper right corner and view the import result.
Deleting a file	When dealing with a small number of files, deleting them one by one is more intuitive and flexible, making it easier to locate and clear specific content. On the knowledge space page, click the knowledge space where the target knowledge base is located to view its details. Click the name of the target knowledge base to view its details. Click Delete next to the target file. The Delete File dialog box is displayed. Click Autofill. The system automatically enters DELETE. Click OK to delete the file. The target file has been removed from the knowledge base details page, indicating that the deletion was successful. CAUTION: Deleted files will be permanently cleared and cannot be recovered. Ensure that you have backed up important data before this operation.
Batch deleting files	Deleting many files one by one manually is inefficient; you can also batch delete files using the following steps: This is ideal for scenarios such as knowledge base restructuring, version iterations, and deduplication, helping you keep your knowledge base organized. On the knowledge space page, click the knowledge space where the target knowledge base is located to view its details. Click the name of the target knowledge base to view its details. Click Batch Delete in the upper right corner and select the target files. Click Delete. The Batch Delete Files dialog box is displayed. Click Autofill. The system automatically enters DELETE. Click OK to delete the files. The target files have been removed from the knowledge base details page, indicating that the deletion was successful. CAUTION: Deleted files will be permanently cleared and cannot be recovered. Ensure that you have backed up important data before this operation.

Repository Index

Repository Index helps you quickly search and retrieve relevant information within your codebase, supporting both client-side indexes and cloud-side indexes. Client-side indexes are built on the CodeArts Agent client, and cloud-side indexes are built on the CodeArts Agent console. Only accounts with enabled seats can create and delete the cloud indexes.

**Table 19** Differences between local user indexes and cloud indexes
Dimension	Local User Index	Cloud Index
Used by	Current user	Enterprise: available to all enterprise members and created by the enterprise administrator, team administrator, enterprise members, or team members. Team: available only to team members and created by the enterprise administrator, team administrator, or team members. User: available only to members themselves.
Repository type	Unlimited	Git and GitHub repositories are supported.

If your account has been assigned a seat, you can create cloud repository indexes. If not, you cannot create them.

Log in to the CodeArts Agent console.
In the navigation pane on the left, choose Agent Settings > Repository Index.
Click Create Index.

Set basic index information by referring to Table 20 and click Next.

**Table 20** Repository index parameters
Parameter	Description
Visible To	Visible scope of the repository index. User: available only to members themselves. Team: available only to team members and created by the enterprise administrator, team administrator, or team members. Enterprise: available to all enterprise members and created by the enterprise administrator, team administrator, enterprise members, or team members.
Teams	This parameter is displayed only when Visible To is set to Team. Select a team from the drop-down list; only the teams which the current account belongs to are displayed.
Code Source	Source of the code repository that you want to index. Git: a general Git repository. GitHub: a GitHub repository, which can be a public repository or an authorized private repository.
Authorization Method	Method to authorize the system to access your code source. Authorize by Service: Select a service endpoint from the drop-down list. The endpoint corresponds to the connection information of the GitHub or Git repository. If no service endpoint has been created, click Add to create one by referring to Table 21. Authorize by Personal Token: Authorize access requests using an access token generated from your personal account.
Default Branch	This parameter is displayed only when Code Source is set to Git. Enter the branch name of a Git repository. The branch name can contain a maximum of 200 characters.

Figure 9 Creating a service endpoint
Click to enlarge

**Table 21** Service endpoint parameters
Parameter	Description
Connection Name	Name of the custom repository to be connected. Naming rules: The name can contain letters, digits, underscores (_), and hyphens (-), but cannot start with an underscore.
Git URL	This parameter is displayed only when Code Source is set to Git. HTTPS access address of the Git repository
User Name	This parameter is displayed only when Code Source is set to Git. User name for HTTPS authentication of the Git repository.
Password or Access Token	This parameter is displayed only when Code Source is set to Git. Password or access token for HTTPS authentication of the Git repository.
Access Token	This parameter is displayed only when Code Source is set to Github. Access token for HTTPS authentication of the GitHub repository.

Select the repository and language, and click OK to finish creating the index.

On the repository index page, view the newly created repository index. When its status changes from parsing to parsing completed, the repository index has been successfully parsed.
Return to the CodeArts Agent IDE client and open the Git, Repo, or GitHub repository project. CodeArts Agent automatically downloads team repository indexes from the cloud.

After the team repository indexes are successfully downloaded, the progress displayed on the page reaches 100%.

If the number of files in the repository is greater than 50,000, click Create Index to manually build the repository index.
(Optional) Use the index in the intelligent Q&A mode.

To use the index in the intelligent Q&A mode, first ensure that the indexing process is completed. Then, at the bottom of the input box on the chat panel, click to search for indexes. When the icon changes to , the index function is enabled.

Table 22 shows the operation permissions of different roles to delete repository indexes.

**Table 22** Scope of repository indexes that can be deleted by different roles
Role	Enterprise-Level Repository Index	Team-Level Repository Index	User-Level Repository Index
Enterprise administrator	All repository indexes	All repository indexes of the administrator's team	All repository indexes created by the user
Team administrator	All repository indexes created by the user	All repository indexes created by team administrator and members of the team managed by the team administrator	All repository indexes created by the user
Team member	All repository indexes created by the user	All repository indexes created by the user	All repository indexes created by the user
Enterprise member	All repository indexes created by the user	No operation permissions.	All repository indexes created by the user

**Table 23** Repository index management on the console
Operation	Procedure
Delete a specified repository index.	When there are only several indexes, you can delete them one by one. On the Repository Index page, locate the target index, and click Delete in the Operation column. The Delete Repository Index dialog box is displayed. Confirm the information, and click Autofill. The system automatically enters DELETE. Then, click OK. The target index cannot be found on the Repository Index page, indicating that the deletion is successful. CAUTION: The deleted index cannot be restored. Exercise caution when you perform this operation.
Delete the repository indexes in a batch.	If there are many indexes, you can delete them in batches. In the upper right corner of the Repository Index page, click Batch Delete and select the indexes to be deleted. Click Delete. The Delete Repository Index dialog box is displayed. Confirm the information, and click Autofill. The system automatically enters DELETE. Then, click OK. The target indexes cannot be found on the Repository Index page, indicating that the deletion is successful. CAUTION: The deleted indexes cannot be restored. Exercise caution when you perform this operation.

Previous topic: Operation Logs

Next topic: My Token Usage

Feedback

Was this page helpful?

Helpful Not helpful

Provide feedback

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.

The system is busy. Please try again later.

For any further questions, feel free to contact us through the chatbot.

Chatbot