Qwen Code Settings

Configuration file for Qwen Code

Type object
File match **/.qwen/settings.json
Schema URL https://catalog.lintel.tools/schemas/schemastore/qwen-code-settings/latest.json
Source https://www.schemastore.org/qwen-code-settings.json

Validate with Lintel

npx @lintel/lintel check
Type: object

Configuration file for Qwen Code

Properties

$schema string

URL or path to the JSON schema for this configuration file

$version integer

Schema version identifier

general object

General configuration options

6 nested properties
preferredEditor string

The preferred editor to open files in

vimMode boolean

Enable Vim keybindings

Default: false
enableAutoUpdate boolean

Enable automatic update checks and installations on startup

Default: true
gitCoAuthor boolean

Automatically add a Co-authored-by trailer to git commit messages

Default: true
checkpointing object

Session checkpointing configuration

1 nested properties
enabled boolean

Enable session checkpointing for recovery

Default: false
defaultFileEncoding string

Default encoding for new files

Default: "utf-8"
Values: "utf-8" "utf-8-bom"
output object

Output configuration

1 nested properties
format string

The format of the CLI output

Default: "text"
Values: "text" "json"
ui object

User interface configuration

12 nested properties
theme string

The color theme for the UI

customThemes Record<string, object>

Custom theme definitions

hideWindowTitle boolean

Hide the window title bar

Default: false
hideTips boolean

Hide helpful tips in the UI

Default: false
hideBanner boolean

Hide the application banner

Default: false
hideFooter boolean

Hide the footer from the UI

Default: false
showMemoryUsage boolean

Display memory usage information in the UI

Default: false
showLineNumbers boolean

Show line numbers in code blocks in the CLI output

Default: true
showCitations boolean

Show citations for generated text in the chat

Default: true
enableWelcomeBack boolean

Show welcome back dialog when returning to a project with conversation history

Default: true
accessibility object

Accessibility configuration

2 nested properties
enableLoadingPhrases boolean

Enable loading phrases (disable for accessibility)

Default: true
screenReader boolean

Enables screen reader mode, adjusting the TUI for better compatibility

Default: false
customWittyPhrases string[]

Custom phrases to display during loading states

Default:
[]
ide object

IDE integration configuration

2 nested properties
enabled boolean

Enable IDE integration mode

Default: false
hasSeenNudge boolean

Whether the user has seen the IDE integration nudge

Default: false
privacy object

Privacy configuration

1 nested properties
usageStatisticsEnabled boolean

Enable collection of usage statistics

Default: true
model object

Model configuration

9 nested properties
name string

The Qwen model to use for conversations

maxSessionTurns integer

Maximum number of turns to keep in a session (-1 is unlimited)

Default: -1
chatCompression object

Chat history compression configuration

1 nested properties
contextPercentageThreshold number

Threshold for chat history compression as a percentage of token limit

Default: 0.7
min=0max=1
skipNextSpeakerCheck boolean

Skip the next speaker check

Default: false
skipLoopDetection boolean

Disables loop detection checks (use if false positives occur)

Default: false
skipStartupContext boolean

Skips sending the startup workspace context at session start

Default: false
enableOpenAILogging boolean

Enables logging of OpenAI API calls for debugging

Default: false
openAILoggingDir string

Custom directory path for OpenAI API logs

generationConfig object

Generation configuration parameters

7 nested properties
timeout number

Request timeout

contextWindowSize integer

Override model's maximum assumed context capacity

enableCacheControl boolean

Enable cache control

modalities object

Override auto-detected input modalities

4 nested properties
image boolean
pdf boolean
audio boolean
video boolean
customHeaders Record<string, string>

Custom HTTP headers for API requests

extra_body object

Additional body parameters (OpenAI-compatible providers only)

samplingParams object

Fine-tuning knobs (e.g., temperature, top_p, max_tokens)

3 nested properties
temperature number
top_p number
max_tokens integer
context object

Context configuration

5 nested properties
fileName string | string[]

The name of the context file(s)

importFormat string

The format to use when importing memory

includeDirectories string[]

Additional directories to include in the workspace context

Default:
[]
loadFromIncludeDirectories boolean

Controls behavior of /memory refresh for included directories

Default: false
fileFiltering object

File filtering configuration

4 nested properties
respectGitIgnore boolean

Respect .gitignore files when searching

Default: true
respectQwenIgnore boolean

Respect .qwenignore files when searching

Default: true
enableRecursiveFileSearch boolean

Enable recursive file searching for @ completions

Default: true
enableFuzzySearch boolean

Enable fuzzy search capabilities

Default: true
tools object

Tools configuration

12 nested properties
sandbox boolean | string

Sandbox execution environment (boolean or custom path string)

shell object

Shell configuration

1 nested properties
enableInteractiveShell boolean

Use node-pty for an interactive shell experience

Default: false
core string[]

Allowlist of built-in tools

exclude string[]

Tool names to exclude from discovery

allowed string[]

Tools that bypass the confirmation dialog

approvalMode string

Default approval mode for tool usage

Default: "default"
Values: "plan" "default" "auto-edit" "yolo"
discoveryCommand string

Command to run for tool discovery

callCommand string

Custom shell command for calling a specific discovered tool

useRipgrep boolean

Use ripgrep for file content search

Default: true
useBuiltinRipgrep boolean

Use the bundled ripgrep binary (requires tools.useRipgrep: true)

Default: true
truncateToolOutputThreshold integer

Truncate output if larger than this many characters

Default: 25000
truncateToolOutputLines integer

Maximum lines/entries kept when truncating output

Default: 1000
mcp object

MCP (Model Context Protocol) configuration

3 nested properties
serverCommand string

Command to start an MCP server

allowed string[]

Allowlist of MCP server names

excluded string[]

Denylist of MCP server names

security object

Security configuration

2 nested properties
folderTrust object

Folder trust configuration

1 nested properties
enabled boolean

Setting to track whether Folder trust is enabled

Default: false
auth object

Authentication configuration

3 nested properties
selectedType string

The currently selected authentication type

enforcedType string

The required auth type (useful for enterprises)

useExternal boolean

Whether to use an external authentication flow

advanced object

Advanced configuration options

5 nested properties
autoConfigureMemory boolean

Automatically configure Node.js memory limits

Default: false
dnsResolutionOrder string

The DNS resolution order

excludedEnvVars string[]

Environment variables to exclude from project context

Default:
[
  "DEBUG",
  "DEBUG_MODE"
]
tavilyApiKey string

API key for Tavily web search service

bugCommand object

Bug command configuration

1 nested properties
urlTemplate string

A URL that can contain {title} and {info} placeholders for the /bug command

mcpServers Record<string, object>

Model-Context Protocol server configurations

telemetry object

Telemetry configuration

7 nested properties
enabled boolean

Whether or not telemetry is enabled

target string

The destination for collected telemetry

Values: "local" "gcp"
otlpEndpoint string

The endpoint for the OTLP Exporter

otlpProtocol string

The protocol for the OTLP Exporter

Values: "grpc" "http"
logPrompts boolean

Whether or not to include the content of user prompts in the logs

outfile string

The file to write telemetry to when target is local

useCollector boolean

Whether to use an external OTLP collector