The full table of Qoder CLI CN settings, defaults, environment variables, and file paths
This page lists all
A JSON Schema is available for editor autocompletion at
Underlines misspelled words in the prompt input as you type, using an
Words are checked conservatively: text inside backticks, paths, URLs, flags, email addresses, words containing an interior capital, and words in scripts a Latin dictionary cannot judge are all skipped, as is the word the cursor is currently in. Spell checking applies to the interactive prompt input only.
settings.json configuration groups, key fields, defaults, and whether a restart is required, plus the supported environment variables. For settings file layering and merge rules, see Settings Files and Precedence.
Settings file locations:
| Layer | Path |
|---|---|
| User | ~/.qoder-cn/settings.json |
| Project | <project>/.qoder/settings.json |
| Local | <project>/.qoder/settings.local.json |
schemas/settings.schema.json in the project.
Top-level settings
| Setting | Type | Default | Restart | Description |
|---|---|---|---|---|
mcpServers | object | {} | Yes | MCP server configuration. See MCP Reference. |
outputStyle | string | none | Yes | Name of the active output style. The general.outputStyle form is also accepted; top level wins. |
language | string | none | Yes | Preferred language for AI responses (e.g. "Chinese"). |
vpcInstanceName | string | none | Yes | VPC private deployment instance name (CN edition only). |
agent | string | none | Yes | Name of the Agent used for the main thread. |
enabledPlugins | object | {} | Yes | Plugin enablement map (plugin ID → true/false). See Plugins. |
hooks | object | {} | No | Hooks configured per event. See Hooks Reference. |
spellcheck
Underlines misspelled words in the prompt input as you type, using an aspell, hunspell, or ispell installation found on PATH. Off by default; no process starts until spellcheck.enabled is true, and nothing happens if no checker is installed.
Read from user-level settings and the --settings flag only. The whole block from the highest-precedence of those two applies — the block is taken as a unit rather than merged field by field, so the block that wins must carry every value it needs. A spellcheck block in project-level or local-level settings is ignored, because these values decide which program is run.
| Setting | Type | Default | Restart | Description |
|---|---|---|---|---|
spellcheck.enabled | boolean | false | No | Turn on spell checking of the prompt input. |
spellcheck.checker | enum | auto | No | Which checker to run: auto/aspell/hunspell/ispell. auto takes the first one found on PATH. |
spellcheck.language | string | none | No | Dictionary passed to the checker as-is (aspell --lang, hunspell -d, ispell -d), e.g. en_GB. Must be a plain dictionary name; otherwise the checker's own default dictionary applies. |
spellcheck.color | string | Theme error color | No | Color of misspelled words, which are also underlined: a color name such as red, #rrggbb, rgb(r,g,b), ansi256(n), or ansi:<name>. |
general
| Setting | Type | Default | Restart | Description |
|---|---|---|---|---|
general.preferredEditor | string | none | No | Preferred editor for opening files. |
general.vimMode | boolean | false | No | Enable Vim keybindings. |
general.defaultPermissionMode | enum | default | No | Default permission mode: default/accept_edits/plan/auto/bypass_permissions/dont_ask. |
general.enableAutoUpdate | boolean | true | No | Enable auto-update. |
general.enableNotifications | boolean | false | No | Enable run-event notifications. |
general.maxAttempts | number | 10 | No | Maximum attempts for main-conversation model requests (capped at 10). |
general.retryFetchErrors | boolean | true | No | Automatically retry on fetch failed-style network request errors. |
general.fileCheckpointing.enabled | boolean | true | Yes | Enable file checkpointing (code rewind). |
general.plan.enabled | boolean | true | Yes | Enable Plan mode. |
general.plan.directory | string | system temp dir | Yes | Directory where plan artifacts are stored. |
general.plan.modelRouting | boolean | true | No | Automatically switch models between the Plan and implementation phases. |
general.sessionRetention.enabled | boolean | true | No | Enable automatic session cleanup. |
general.sessionRetention.maxAge | string | 30d | No | Automatically delete sessions older than this duration. |
general.sessionRetention.minRetention | string | 1d | No | Minimum retention period (safety floor). |
output
| Setting | Type | Default | Description |
|---|---|---|---|
output.format | enum | text | CLI output format: text or json. |
ui
| Setting | Type | Default | Restart | Description |
|---|---|---|---|---|
ui.theme | string | none | No | Color theme name. |
ui.autoThemeSwitching | boolean | true | No | Automatically switch light/dark themes based on the terminal background. |
ui.terminalBackgroundPollingInterval | number | 60 | No | Terminal background color polling interval (seconds). |
ui.customThemes | object | {} | No | Custom theme definitions. |
ui.inlineThinkingMode | enum | full | No | Inline thinking display: off/full. |
ui.dynamicWindowTitle | boolean | true | No | Update the window title with status icons. |
ui.hideBanner | boolean | false | No | Hide the startup banner. |
ui.hideFooter | boolean | false | No | Hide the footer. |
ui.hideTips | boolean | false | No | Hide tips. |
ui.showLineNumbers | boolean | true | No | Show line numbers in the conversation. |
ui.compactToolOutput | boolean | true | No | Display tool output compactly. |
ui.copyFullResponse | boolean | false | No | /copy always copies the full response. |
ui.loadingPhrases | enum | off | No | Loading display: tips/witty/all/off. |
ui.errorVerbosity | enum | low | No | Recoverable error verbosity: low/full. |
ui.customWittyPhrases | string[] | [] | No | Custom loading phrases. |
ui.footer.* | object | {} | No | Footer item configuration (items/showLabels/hideCWD/hideModelInfo, etc.). |
ui.rotatingInfoLine.enabled | boolean | true | No | Rotating info line above the input box. |
ui.rotatingInfoLine.intervalMs | number | 4000 | No | Rotation interval in milliseconds. |
ui.useAlternateBuffer | boolean | false | Yes | Use the alternate screen buffer. |
ui.accessibility.screenReader | boolean | false | Yes | Screen reader mode, outputting plain text. |
ui.showMemoryUsage | boolean | false | No | Show memory usage information in the interface. |
ui.showSpinner | boolean | true | No | Show a loading animation during operations. |
ui.terminalBuffer | boolean | true | Yes | Use the new terminal buffer architecture for rendering. |
ui.renderProcess | boolean | true | Yes | Enable the Ink render process. |
ui.incrementalRendering | boolean | true | Yes | Incremental rendering — less flicker but possible rendering artifacts; supported only with ui.useAlternateBuffer enabled. |
model / modelConfigs
| Setting | Type | Default | Restart | Description |
|---|---|---|---|---|
model.name | string | none | No | The conversation model. |
model.reasoningEffort | enum | none | No | Reasoning effort: disabled/off/none/low/medium/high/xhigh/max. |
model.contextWindow | number | none | No | Explicit context window (tokens). |
model.maxSessionTurns | number | -1 | No | Maximum turns retained per session; -1 for unlimited. |
model.summarizeToolOutput | object | none | No | Per-tool output summarization token budgets. |
modelConfigs.aliases | object | built-in | No | Model configuration alias presets. |
modelConfigs.customAliases | object | {} | No | Custom aliases, merged over the built-ins. |
modelConfigs.overrides | array | [] | No | Configuration overrides applied by match conditions (keyed by model or alias); the most specific match wins. |
modelConfigs.customOverrides | array | [] | No | Custom overrides, appended to the built-in overrides. |
context
| Setting | Type | Default | Restart | Description |
|---|---|---|---|---|
context.fileName | string/string[] | AGENTS.md | No | Context file name(s) loaded into memory. |
context.importFormat | enum | none | No | Memory import format: tree/flat. |
context.discoveryMaxDirs | number | 200 | No | Maximum directories for memory discovery. |
context.memoryBoundaryMarkers | string[] | ['.git'] | Yes | Boundary markers for upward memory discovery. |
context.loadMemoryFromIncludeDirectories | boolean | false | No | Load memory from additional trusted directories. |
context.fileFiltering.respectGitIgnore | boolean | true | Yes | Respect .gitignore when searching. |
context.fileFiltering.enableRecursiveFileSearch | boolean | true | Yes | Search recursively for @ reference completion. |
agentsMdExcludes | string[] | [] | Yes | Exclude project/local memory files by glob. A top-level key, manual configuration only. |
tools
| Setting | Type | Default | Restart | Description |
|---|---|---|---|---|
tools.sandbox | boolean/string/object | none | Yes | Sandboxed execution environment. |
tools.sandboxAllowedPaths | string[] | [] | Yes | Additional paths accessible in the sandbox. |
tools.sandboxNetworkAccess | boolean | false | Yes | Whether the sandbox allows network access. |
tools.shell.pager | string | cat | No | Pager command for shell output. |
tools.shell.inactivityTimeout | number | 300 | No | Timeout in seconds for shell commands with no output. |
tools.core | string[] | none | Yes | Built-in tool allowlist. |
tools.exclude | string[] | none | Yes | Tool names excluded from discovery. |
tools.useRipgrep | boolean | true | No | Use ripgrep for content search. |
tools.disableLLMCorrection | boolean | true | Yes | Disable LLM correction in editing tools. |
mcp
| Setting | Type | Default | Restart | Description |
|---|---|---|---|---|
mcp.allowed | string[] | none | Yes | Allowed MCP server list. |
mcp.excluded | string[] | none | Yes | Excluded MCP server list. |
mcp.enableAllProjectMcpServers | boolean | false | Yes | Auto-approve all project-level MCP servers. |
mcp.enabledProjectMcpServers | string[] | [] | Yes | List of individually approved project-level MCP server names. |
mcp.lazyLoad | boolean | false | Yes | Lazily load MCP tools (exposes meta tools). |
security
| Setting | Type | Default | Restart | Description |
|---|---|---|---|---|
security.folderTrust.enabled | boolean | true | Yes | Enable folder trust. |
security.toolSandboxing | boolean | false | Yes | Tool-level sandbox isolation. |
security.disableYoloMode | boolean | false | Yes | Disable the bypass_permissions (YOLO) permission mode. |
security.blockGitExtensions | boolean | false | Yes | Block installing/loading extensions from Git. |
security.allowedExtensions | string[] | [] | Yes | Regex allowlist of extension sources. |
security.environmentVariableRedaction.enabled | boolean | false | Yes | Redact environment variables that may contain secrets. |
security.enableConseca | boolean | false | Yes | Enable context-aware security checks. |
permissions
| Setting | Type | Default | Restart | Description |
|---|---|---|---|---|
permissions.allow | string[] | [] | No | List of automatically allowed permission rules. For rule syntax, see Permissions and Directory Trust. |
permissions.ask | string[] | [] | No | List of permission rules requiring confirmation. |
permissions.deny | string[] | [] | No | List of permission rules always denied. |
permissions.additionalDirectories | string[] | [] | No | Additional trusted directories added to the workspace context (corresponds to /add-dir). |
permissions.trustDirectories | string[] | [] | No | Directories explicitly trusted by the user; stored in the user-level configuration and never overridden by the project level. |
autoMode | object | {} | No | Auto-mode classifier soft-steering rules (allow/soft_deny/environment). A top-level key, read only from the user-level and local configuration. |
allowManagedPermissionRulesOnly | boolean | false | No | Use only permission rules from managed policies. A top-level key, mainly for organization-managed policies. |
privacy / aiCodeStatistics
| Setting | Type | Default | Restart | Description |
|---|---|---|---|---|
privacy.usageStatisticsEnabled | boolean | true | No | Share usage data; turning it off enters privacy mode. |
aiCodeStatistics.enabled | boolean | true | Yes | Record and report AI-generated code statistics. |
advanced
| Setting | Type | Default | Restart | Description |
|---|---|---|---|---|
advanced.autoConfigureMemory | boolean | true | Yes | Automatically configure the Node.js memory limit. |
advanced.dnsResolutionOrder | string | none | Yes | DNS resolution order. |
advanced.excludedEnvVars | string[] | ['DEBUG','DEBUG_MODE'] | No | Environment variables excluded from project context. |
agents.overrides | object | {} | Yes | Override configuration per Agent name (enablement, tools, model, run limits, etc.). For fields, see Subagents. |
statusLine
| Setting | Type | Default | Description |
|---|---|---|---|
statusLine.type | string | command | Status line type. |
statusLine.command | string | "" | Shell command that produces the status line, receiving session data JSON via stdin. |
statusLine.padding | number | 0 | Horizontal padding characters. |
statusLine.colors | object | {} | Custom colors for the built-in default status line's segments (such as model, branch, separator). |
Environment variables
Qoder-related
| Environment variable | Description |
|---|---|
QODERCN_PERSONAL_ACCESS_TOKEN | Personal Access Token (PAT); when set, PAT authentication is used automatically. |
QODERCN_CONFIG_DIR | User config directory location (default ~/.qoder-cn). |
QODERCN_MODEL | The model to use. |
QODERCN_WORKING_DIR | The working directory. |
QODERCN_SESSION_ID | Session ID. |
QODERCN_SESSION_NAME | Session name. |
QODERCN_PERMISSION_MODE | Permission mode. |
QODERCN_APPEND_SYSTEM_PROMPT | Append to the system prompt. |
QODER_MCP_LAZY | Set to 1 to enable MCP lazy loading. |
QODERCN_SANDBOX | Sandbox command or switch. |
QODERCN_SANDBOX_IMAGE | Custom sandbox image. |
QODERCN_SANDBOX_IMAGE_DEFAULT | Default sandbox image. |
QODERCN_SANDBOX_PROXY_COMMAND | Proxy command inside the sandbox. |
SANDBOX | Injected by the sandbox environment to detect being inside a sandbox and avoid nesting (usually no need to set manually). |
QODER_ASR_URL | Speech recognition service address. |
QODERCN_SUBAGENT_MODEL | The model used by subagents. |
QODERCN_MEMORY | Set to 1 to enable auto-memory (interactive sessions only). |
QODERCN_MEMORY_USER | Set to 1 to also enable user-level auto-memory; effective only when QODERCN_MEMORY is enabled. |
Network proxy
| Environment variable | Description |
|---|---|
HTTP_PROXY / http_proxy | Proxy address for HTTP requests. |
HTTPS_PROXY / https_proxy | Proxy address for HTTPS requests. |
NO_PROXY / no_proxy | Comma-separated list of hosts that bypass the proxy. |
NODE_EXTRA_CA_CERTS | Path to an additional CA certificate file (PEM format). |
SSL_CERT_FILE | Path to a trusted certificate file, for self-signed or corporate root certificate environments. |
Next steps
- Configuration layering and merge rules: Settings Files and Precedence.
- Network and proxy configuration: Network, Proxy, and VPC.