Enum Commands 

pub enum Commands {
    Chat,
    Ask {
        prompt: String,
    },
    ChatVerbose,
    Analyze,
    Performance,
    Trajectory {
        file: Option<PathBuf>,
        top: usize,
    },
    Benchmark,
    CreateProject {
        name: String,
        features: Vec<String>,
    },
    CompressContext,
    Revert {
        turn: usize,
        partial: Option<String>,
    },
    Snapshots,
    CleanupSnapshots {
        max: usize,
    },
    Init,
    InitProject {
        name: Option<String>,
        force: bool,
        migrate: bool,
    },
    Config {
        output: Option<PathBuf>,
        global: bool,
    },
    ToolPolicy {
        command: ToolPolicyCommands,
    },
    Models {
        command: ModelCommands,
    },
    Security,
    TreeSitter,
    Man {
        command: Option<String>,
        output: Option<PathBuf>,
    },
}

Available commands with comprehensive features

Variants

Chat

Interactive AI coding assistant with advanced capabilities

Features: • Real-time code generation and editing • Tree-sitter powered analysis • Research-preview context management

Usage: vtcode chat

Ask

Single prompt mode - prints model reply without tools

Perfect for: • Quick questions • Code explanations • Simple queries

Example: vtcode ask “Explain Rust ownership”

Fields

prompt: String

ChatVerbose

Verbose interactive chat with enhanced transparency

Shows: • Tool execution details • API request/response • Performance metrics

Usage: vtcode chat-verbose

Analyze

Analyze workspace with tree-sitter integration

Provides: • Project structure analysis • Language detection • Code complexity metrics • Dependency insights • Symbol extraction

Usage: vtcode analyze

Performance

Display performance metrics and system status\n\nShows:\n• Token usage and API costs\n• Response times and latency\n• Tool execution statistics\n• Memory usage patterns\n\nUsage: vtcode performance

Trajectory

Pretty-print trajectory logs and show basic analytics

Sources: • .vtcode/logs/trajectory.jsonl (default) Options: • –file to specify an alternate path • –top to limit report rows (default: 10)

Shows: • Class distribution with percentages • Model usage statistics • Tool success rates with status indicators • Time range of logged activity

Fields

file: Option<PathBuf>

Optional path to trajectory JSONL file

top: usize

Number of top entries to show for each section

Benchmark

Benchmark against SWE-bench evaluation framework

Features: • Automated performance testing • Comparative analysis across models • Benchmark scoring and metrics • Optimization insights

Usage: vtcode benchmark

CreateProject

Create complete Rust project with advanced features

Features: • Web frameworks (Axum, Rocket, Warp) • Database integration • Authentication systems • Testing setup • Tree-sitter integration

Example: vtcode create-project myapp web,auth,db

Fields

name: String

features: Vec<String>

CompressContext

Compress conversation context for long-running sessions

Benefits: • Reduced token usage • Faster responses • Memory optimization • Context preservation

Usage: vtcode compress-context

Revert

**Revert agent to a previous snapshot

Features: • Revert to any previous turn • Partial reverts (memory, context, full) • Safe rollback with validation

Examples: vtcode revert –turn 5 vtcode revert –turn 3 –partial memory

Fields

turn: usize

Turn number to revert to

Required: Yes Example: 5

partial: Option<String>

Scope of revert operation

Options: memory, context, full Default: full Examples: –partial memory (revert conversation only) –partial context (revert decisions/errors only)

Snapshots

List all available snapshots

Shows: • Snapshot ID and turn number • Creation timestamp • Description • File size and compression status

Usage: vtcode snapshots

CleanupSnapshots

Clean up old snapshots

Features: • Remove snapshots beyond limit • Configurable retention policy • Safe deletion with confirmation

Examples: vtcode cleanup-snapshots vtcode cleanup-snapshots –max 20

Fields

max: usize

Maximum number of snapshots to keep

Default: 50 Example: –max 20

Init

Initialize project with enhanced dot-folder structure

Features: • Creates project directory structure • Sets up config, cache, embeddings directories • Creates .project metadata file • Tree-sitter parser setup

Usage: vtcode init

InitProject

Initialize project with dot-folder structure - sets up ~/.vtcode/projects/ structure

Features: • Creates project directory structure in ~/.vtcode/projects/ • Sets up config, cache, embeddings, and retrieval directories • Creates .project metadata file • Migrates existing config/cache files with user confirmation

Examples: vtcode init-project vtcode init-project –name my-project vtcode init-project –force

Fields

name: Option<String>

Project name - defaults to current directory name

force: bool

Force initialization - overwrite existing project structure

migrate: bool

Migrate existing files - move existing config/cache files to new structure

Config

**Generate configuration file - creates a vtcode.toml configuration file

Features: • Generate default configuration • Support for global (home directory) and local configuration • TOML format with comprehensive settings • Tree-sitter and performance monitoring settings

Examples: vtcode config vtcode config –output ./custom-config.toml vtcode config –global

Fields

output: Option<PathBuf>

Output file path - where to save the configuration file

global: bool

Create in user home directory - creates ~/.vtcode/vtcode.toml

ToolPolicy

Manage tool execution policies - control which tools the agent can use

Features: • Granular tool permissions • Security level presets • Audit logging • Safe tool execution

Examples: vtcode tool-policy status vtcode tool-policy allow file-write vtcode tool-policy deny shell-exec

Fields

command: ToolPolicyCommands

Models

Manage models and providers - configure and switch between LLM providers\n\nFeatures:\n• Support for latest models (DeepSeek, etc.)\n• Provider configuration and testing\n• Model performance comparison\n• API key management\n\nExamples:\n vtcode models list\n vtcode models set-provider deepseek\n vtcode models set-model deepseek-reasoner

Fields

command: ModelCommands

Security

Security and safety management\n\nFeatures:\n• Security scanning and vulnerability detection\n• Audit logging and monitoring\n• Access control management\n• Privacy protection settings\n\nUsage: vtcode security

TreeSitter

Tree-sitter code analysis tools\n\nFeatures:\n• AST-based code parsing\n• Symbol extraction and navigation\n• Code complexity analysis\n• Multi-language refactoring\n\nUsage: vtcode tree-sitter

Man

Generate or display man pages for VTCode commands\n\nFeatures:\n• Generate Unix man pages for all commands\n• Display detailed command documentation\n• Save man pages to files\n• Comprehensive help for all VTCode features\n\nExamples:\n vtcode man\n vtcode man chat\n vtcode man chat –output chat.1

Fields

command: Option<String>

Command name to generate man page for (optional)\n\nAvailable commands:\n• chat, ask, analyze, performance, benchmark\n• create-project, init, man\n\nIf not specified, shows main VTCode man page

output: Option<PathBuf>

Output file path to save man page\n\nFormat: Standard Unix man page format (.1, .8, etc.)\nDefault: Display to stdout

Trait Implementations

impl Debug for Commands

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

Formats the value using the given formatter.

impl FromArgMatches for Commands

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<'b>( &mut self, __clap_arg_matches: &mut ArgMatches, ) -> Result<(), Error>

Assign values from ArgMatches to self.

impl Subcommand for Commands

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

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

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

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

fn has_subcommand(__clap_name: &str) -> bool

Test whether Self can parse a specific subcommand