Struct Cli 

pub struct Cli {

    pub color: Color,
    pub workspace_path: Option<PathBuf>,
    pub model: Option<String>,
    pub provider: Option<String>,
    pub api_key_env: String,
    pub workspace: Option<PathBuf>,
    pub enable_tree_sitter: bool,
    pub performance_monitoring: bool,
    pub research_preview: bool,
    pub security_level: String,
    pub show_file_diffs: bool,
    pub max_concurrent_ops: usize,
    pub api_rate_limit: usize,
    pub max_tool_calls: usize,
    pub debug: bool,
    pub verbose: bool,
    pub config: Option<PathBuf>,
    pub log_level: String,
    pub no_color: bool,
    pub theme: Option<String>,
    pub skip_confirmations: bool,
    pub full_auto: bool,
    pub command: Option<Commands>,
}

Main CLI structure for vtcode with advanced features

Fields

color: Color

Color output selection (auto, always, never)

workspace_path: Option<PathBuf>

Optional positional path to run vtcode against a different workspace

model: Option<String>

LLM Model ID with latest model support

Available providers & models: • gemini-2.5-flash-preview-05-20 - Latest fast Gemini model (default) • gemini-2.5-flash - Fast, cost-effective • gemini-2.5-pro - Latest, most capable • gpt-5 - OpenAI’s latest • claude-sonnet-4-20250514 - Anthropic’s latest • qwen/qwen3-4b-2507 - Qwen3 local model • deepseek-reasoner - DeepSeek reasoning model • x-ai/grok-code-fast-1 - OpenRouter Grok fast coding model • qwen/qwen3-coder - OpenRouter Qwen3 Coder optimized for IDE usage • grok-2-latest - xAI Grok flagship model

provider: Option<String>

LLM Provider with expanded support

Available providers: • gemini - Google Gemini (default) • openai - OpenAI GPT models • anthropic - Anthropic Claude models • deepseek - DeepSeek models • openrouter - OpenRouter marketplace models • xai - xAI Grok models

Example: –provider deepseek

api_key_env: String

API key environment variable\n\nAuto-detects based on provider:\n• Gemini: GEMINI_API_KEY\n• OpenAI: OPENAI_API_KEY\n• Anthropic: ANTHROPIC_API_KEY\n• DeepSeek: DEEPSEEK_API_KEY\n• OpenRouter: OPENROUTER_API_KEY\n• xAI: XAI_API_KEY\n\nOverride: –api-key-env CUSTOM_KEY

workspace: Option<PathBuf>

Workspace root directory for file operations

Security: All file operations restricted to this path Default: Current directory

enable_tree_sitter: bool

Enable tree-sitter code analysis

Features: • AST-based code parsing • Symbol extraction and navigation • Intelligent refactoring suggestions • Multi-language support (Rust, Python, JS, TS, Go, Java)

performance_monitoring: bool

Enable performance monitoring

Tracks: • Token usage and API costs • Response times and latency • Tool execution metrics • Memory usage patterns

research_preview: bool

Enable research-preview features

Includes: • Advanced context compression • Conversation summarization • Enhanced error recovery • Decision transparency tracking

security_level: String

Security level for tool execution

Options: • strict - Maximum security, prompt for all tools • moderate - Balance security and usability • permissive - Minimal restrictions (not recommended)

show_file_diffs: bool

Show diffs for file changes in chat interface

Features: • Real-time diff rendering • Syntax highlighting • Line-by-line changes • Before/after comparison

max_concurrent_ops: usize

Maximum concurrent async operations

Default: 5 Higher values: Better performance but more resource usage

api_rate_limit: usize

Maximum API requests per minute

Default: 30 Purpose: Prevents rate limiting

max_tool_calls: usize

Maximum tool calls per session

Default: 10 Purpose: Prevents runaway execution

debug: bool

Enable debug output for troubleshooting

Shows: • Tool call details • API request/response • Internal agent state • Performance metrics

verbose: bool

Enable verbose logging

Includes: • Detailed operation logs • Context management info • Agent coordination details

config: Option<PathBuf>

Configuration file path

Supported formats: TOML Default locations: ./vtcode.toml, ~/.vtcode/vtcode.toml

log_level: String

Log level (error, warn, info, debug, trace)

Default: info

no_color: bool

Disable color output

Useful for: Log files, CI/CD pipelines

theme: Option<String>

Select UI theme for ANSI styling (e.g., ciapre-dark, ciapre-blue)

skip_confirmations: bool

Skip safety confirmations

Warning: Reduces security, use with caution

full_auto: bool

Enable full-auto mode (no interaction)

Runs the agent without pausing for approvals. Requires enabling in configuration.

command: Option<Commands>

Implementations

impl Cli

pub fn get_model(&self) -> String

Get the model to use, with fallback to default

pub fn load_config(&self) -> Result<ConfigFile, Box<dyn Error>>

Load configuration from a simple TOML-like file without external deps

Supported keys (top-level): model, api_key_env, verbose, log_level, workspace Example: model = “gemini-2.5-flash-preview-05-20” api_key_env = “GEMINI_API_KEY” verbose = true log_level = “info” workspace = “/path/to/workspace”

pub fn get_workspace(&self) -> PathBuf

Get the effective workspace path

pub fn get_api_key_env(&self) -> String

Get the effective API key environment variable

Automatically infers the API key environment variable based on the provider when the current value matches the default or is not explicitly set.

pub fn is_verbose(&self) -> bool

Check if verbose mode is enabled

pub fn is_tree_sitter_enabled(&self) -> bool

Check if tree-sitter analysis is enabled

pub fn is_performance_monitoring_enabled(&self) -> bool

Check if performance monitoring is enabled

pub fn is_research_preview_enabled(&self) -> bool

Check if research-preview features are enabled

pub fn get_security_level(&self) -> &str

Get the security level

pub fn is_debug_mode(&self) -> bool

Check if debug mode is enabled (includes verbose)

Trait Implementations

impl Args for Cli

fn group_id() -> Option<Id>

Report the ArgGroup::id for this set of arguments

fn augment_args<'b>(__clap_app: Command) -> Command

Append to Command so it can instantiate Self via FromArgMatches::from_arg_matches_mut

fn augment_args_for_update<'b>(__clap_app: Command) -> Command

Append to Command so it can instantiate self via FromArgMatches::update_from_arg_matches_mut

impl CommandFactory for Cli

fn command<'b>() -> Command

Build a Command that can instantiate Self.

fn command_for_update<'b>() -> Command

Build a Command that can update self.

impl Debug for Cli

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Cli

fn default() -> Self

Returns the “default value” for a type.

impl FromArgMatches for Cli

fn from_arg_matches(__clap_arg_matches: &ArgMatches) -> Result<Self, Error>

Instantiate Self from ArgMatches, parsing the arguments as needed.

fn from_arg_matches_mut( __clap_arg_matches: &mut ArgMatches, ) -> Result<Self, Error>

Instantiate Self from ArgMatches, parsing the arguments as needed.

fn update_from_arg_matches( &mut self, __clap_arg_matches: &ArgMatches, ) -> Result<(), Error>

Assign values from ArgMatches to self.

fn update_from_arg_matches_mut( &mut self, __clap_arg_matches: &mut ArgMatches, ) -> Result<(), Error>

Assign values from ArgMatches to self.

impl Parser for Cli

fn parse() -> Self

Parse from std::env::args_os(), exit on error.

fn try_parse() -> Result<Self, Error>

Parse from std::env::args_os(), return Err on error.

fn parse_from<I, T>(itr: I) -> Self

where I: IntoIterator<Item = T>, T: Into<OsString> + Clone,

Parse from iterator, exit on error.

fn try_parse_from<I, T>(itr: I) -> Result<Self, Error>

where I: IntoIterator<Item = T>, T: Into<OsString> + Clone,

Parse from iterator, return Err on error.

fn update_from<I, T>(&mut self, itr: I)

where I: IntoIterator<Item = T>, T: Into<OsString> + Clone,

Update from iterator, exit on error.

fn try_update_from<I, T>(&mut self, itr: I) -> Result<(), Error>

where I: IntoIterator<Item = T>, T: Into<OsString> + Clone,

Update from iterator, return Err on error.