Struct Args 

pub struct Args {

    pub verbosity_shorthand: VerbosityShorthand,
    pub debug_verbosity: DebugVerbosity,
    pub quick_presets: QuickPresets,
    pub standard_presets: StandardPresets,
    pub unified_init: UnifiedInitFlags,
    pub legacy_init: LegacyInitFlag,
    pub agent_list: AgentListFlags,
    pub provider_list: ProviderListFlag,
    pub completion: CompletionFlag,
    pub work_guide_list: WorkGuideListFlag,
    pub template_commands: TemplateCommands,
    pub commit_plumbing: CommitPlumbingFlags,
    pub commit_display: CommitDisplayFlags,
    pub recovery: RecoveryFlags,
    pub rebase_flags: RebaseFlags,
    pub commit_msg: String,
    pub developer_iters: Option<u32>,
    pub reviewer_reviews: Option<u32>,
    pub preset: Option<Preset>,
    pub developer_agent: Option<String>,
    pub reviewer_agent: Option<String>,
    pub developer_model: Option<String>,
    pub reviewer_model: Option<String>,
    pub developer_provider: Option<String>,
    pub reviewer_provider: Option<String>,
    pub reviewer_json_parser: Option<String>,
    pub verbosity: Option<u8>,
    pub no_isolation: bool,
    pub review_depth: Option<String>,
    pub config: Option<PathBuf>,
    pub working_dir_override: Option<PathBuf>,
    pub init_prompt: Option<String>,
    pub interactive: bool,
    pub git_user_name: Option<String>,
    pub git_user_email: Option<String>,
    pub show_streaming_metrics: bool,
}

Ralph: PROMPT-driven agent orchestrator for git repos

Fields

verbosity_shorthand: VerbosityShorthand

Verbosity shorthand flags (–quiet, –full)

debug_verbosity: DebugVerbosity

Debug verbosity flag

quick_presets: QuickPresets

Quick preset mode flags

standard_presets: StandardPresets

Standard preset mode flags

unified_init: UnifiedInitFlags

Unified config initialization flags

legacy_init: LegacyInitFlag

Legacy initialization flag

agent_list: AgentListFlags

Agent listing flags

provider_list: ProviderListFlag

Provider listing flag

completion: CompletionFlag

Shell completion generation flag

work_guide_list: WorkGuideListFlag

Work Guide listing flag

template_commands: TemplateCommands

Template management commands

commit_plumbing: CommitPlumbingFlags

Commit message plumbing flags

commit_display: CommitDisplayFlags

Commit display plumbing flags

recovery: RecoveryFlags

Recovery command flags

rebase_flags: RebaseFlags

Rebase control flags

commit_msg: String

Commit message for the final commit

developer_iters: Option<u32>

Number of developer iterations (default: 5)

reviewer_reviews: Option<u32>

Number of review-fix cycles (N=0 skips review, N=1 is one review-fix cycle, etc.)

preset: Option<Preset>

Preset for common agent combinations

developer_agent: Option<String>

Developer/driver agent to use (from agent_chain.developer)

reviewer_agent: Option<String>

Reviewer agent to use (from agent_chain.reviewer)

developer_model: Option<String>

Developer model/provider override (e.g., “-m opencode/glm-4.7-free”)

reviewer_model: Option<String>

Reviewer model/provider override (e.g., “-m opencode/claude-sonnet-4”)

developer_provider: Option<String>

Developer provider override (e.g., “opencode”, “zai”, “anthropic”, “openai”) Use this to switch providers at runtime without changing agent config. Combined with the agent’s model to form the full model flag. Provider types: ‘opencode’ (Zen gateway), ‘zai’/‘zhipuai’ (Z.AI direct), ‘anthropic’/‘openai’ (direct API)

reviewer_provider: Option<String>

Reviewer provider override (e.g., “opencode”, “zai”, “anthropic”, “openai”) Use this to switch providers at runtime without changing agent config. Combined with the agent’s model to form the full model flag. Provider types: ‘opencode’ (Zen gateway), ‘zai’/‘zhipuai’ (Z.AI direct), ‘anthropic’/‘openai’ (direct API)

reviewer_json_parser: Option<String>

JSON parser for the reviewer agent (overrides agent config) Useful for testing different parsers with problematic agents

verbosity: Option<u8>

Verbosity level (0=quiet, 1=normal, 2=verbose, 3=full, 4=debug)

no_isolation: bool

Disable isolation mode (allow NOTES.md and ISSUES.md to persist)

review_depth: Option<String>

Review depth level (standard, comprehensive, security, incremental)

config: Option<PathBuf>

Path to configuration file (default: ~/.config/ralph-workflow.toml)

working_dir_override: Option<PathBuf>

Internal: Working directory override for testing. When set, app::run uses this path instead of discovering the repo root and does not change the global CWD. This enables test parallelism.

init_prompt: Option<String>

Initialize PROMPT.md from a Work Guide and exit

This is a legacy alias for --init <template>. Consider using --init instead.

Work Guides describe YOUR work to the AI (e.g., bug-fix, feature-spec). These are different from Agent Prompts which configure AI behavior.

Available Work Guides: quick, bug-fix, feature-spec, refactor, test, docs, cli-tool, web-api, performance-optimization, security-audit, api-integration, database-migration, dependency-update, data-pipeline, ui-component, code-review, debug-triage, release, tech-debt, onboarding

interactive: bool

Interactive mode: prompt to create PROMPT.md from template when missing

git_user_name: Option<String>

Git user name override (highest priority in identity resolution chain)

git_user_email: Option<String>

Git user email override (highest priority in identity resolution chain)

show_streaming_metrics: bool

Show streaming quality metrics at the end of agent output

Trait Implementations

impl Args for Args

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 Args

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 Args

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

Formats the value using the given formatter.

impl Default for Args

fn default() -> Args

Returns the “default value” for a type.

impl FromArgMatches for Args

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 Args

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.