Struct Cli 

pub struct Cli {

    pub prompt: Option<String>,
    pub cwd: Option<PathBuf>,
    pub harness: Option<Harness>,
    pub api_schema: Option<String>,
    pub model: Option<String>,
    pub settings: Option<String>,
    pub no_session_persistence: bool,
    pub continue_session: bool,
    pub resume: Option<String>,
    pub max_turns: Option<u32>,
    pub output_format: OutputFormat,
    pub restricted: bool,
    pub dangerously_skip_permissions: bool,
    pub strip_identity: bool,
    pub stream: bool,
    pub no_project_instructions: bool,
    pub add_dir: Vec<PathBuf>,
    pub effort: Option<EffortArg>,
}

Minimal headless runner for the locode engine: one JSON report on stdout (ADR-0009), diagnostics on stderr, exit code from the run’s status.

Fields

prompt: Option<String>

The task prompt. - or omitted reads the prompt from stdin.

cwd: Option<PathBuf>

Workspace root / working directory (the path-jail root). Defaults to the current directory.

harness: Option<Harness>

Harness pack selecting the toolset + system prompt. Omitted ⇒ the settings harness default (ADR-0024 §1.4), else claude.

api_schema: Option<String>

Provider wire schema: anthropic, openai-responses, or mock (keyless CI) — plus any custom providers the binary registered (ADR-0015). Unknown names fail pre-run listing the available set. Omitted ⇒ the settings api_schema default (ADR-0024 §1.4 — the project layers may not set it), else anthropic.

model: Option<String>

Model id override. Omitted ⇒ the settings model default, else the wire’s built-in default (ADR-0024 §1.4 — same precedence chain as every other knob; there is deliberately no model env var).

settings: Option<String>

Extra settings layer: a path to a JSON file, or inline JSON (highest- precedence settings layer, ADR-0024 §1.2).

no_session_persistence: bool

Do not write (or append to) a session trace for this run — nothing lands under ~/.locode/sessions (ADR-0024 §2; Claude Code’s --no-session-persistence). --continue/--resume still read.

continue_session: bool

Continue the newest session started in this cwd (ADR-0024 §2.5): the recovered transcript seeds the run and the same rollout keeps appending.

resume: Option<String>

Resume the session with this id — found in this cwd’s sessions first, then anywhere (ADR-0024 §2.5).

max_turns: Option<u32>

Hard ceiling on sample→dispatch turns. Unlimited when omitted (ADR-0005 amendment — no studied harness caps turns by default).

output_format: OutputFormat

stdout contract: json = one Report; stream-json = Event JSONL; text = the final message.

restricted: bool

Restrict file access to the working directory and ask before each tool call. Incomplete — there is no way to record an answer yet, so every call asks again. Off by default.

dangerously_skip_permissions: bool

Accepted for compatibility and does nothing — this is the default now. Use --restricted to turn the restrictions on.

strip_identity: bool

Strip harness identity sentences from the rendered system prompt (A/B contamination control; default = faithful reproduction).

stream: bool

Stream the model turn (SSE) instead of one buffered call (ADR-0021). Needed for unbounded output — Anthropic rejects non-streaming requests that may exceed ~10 min. The stream-json trace stays whole-message: token deltas are assembled but not written to it.

no_project_instructions: bool

Skip project-instruction loading (AGENTS.md) — the --bare-style disable (ADR-0023). Auto-discovery is otherwise on by default.

add_dir: Vec<PathBuf>

Add a directory the agent may read and write, beyond the working directory. Repeatable. Its AGENTS.md and .agents/skills are picked up too — the point of pointing at a subtree of a large monorepo.

effort: Option<EffortArg>

How hard the model should think. Omitted uses the effort setting, then the API’s own default.

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 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.