Struct EnrichArgs 

pub struct EnrichArgs {

    pub operation: EnrichOperation,
    pub mode: EnrichMode,
    pub limit: Option<usize>,
    pub dry_run: bool,
    pub namespace: Option<String>,
    pub claude_binary: Option<PathBuf>,
    pub claude_model: Option<String>,
    pub claude_timeout: u64,
    pub codex_binary: Option<PathBuf>,
    pub codex_model: Option<String>,
    pub codex_timeout: u64,
    pub max_cost_usd: Option<f64>,
    pub resume: bool,
    pub retry_failed: bool,
    pub min_output_chars: usize,
    pub max_output_chars: usize,
    pub preserve_check: bool,
    pub prompt_template: Option<PathBuf>,
    pub llm_parallelism: u32,
    pub json: bool,
    pub db: Option<String>,
    pub wait_job_singleton: Option<u64>,
    pub force_job_singleton: bool,
    pub names: Vec<String>,
    pub names_file: Option<PathBuf>,
    pub preflight_check: bool,
    pub fallback_mode: Option<EnrichMode>,
    pub rate_limit_buffer: u64,
    pub max_load_check: bool,
    pub circuit_breaker_threshold: u32,
    pub preserve_threshold: f64,
    pub codex_model_validate: bool,
    pub codex_model_fallback: Option<String>,
}

Arguments for the enrich subcommand.

Fields

operation: EnrichOperation

Enrichment operation to run.

mode: EnrichMode

LLM provider to use. Default: claude-code (OAuth-first).

limit: Option<usize>

Maximum number of items to process in this run. Omit for all.

dry_run: bool

Preview items without calling the LLM (zero tokens consumed).

namespace: Option<String>

Namespace to operate on. Default: global.

claude_binary: Option<PathBuf>

Path to the Claude Code binary. Default: auto-detect from PATH.

claude_model: Option<String>

Claude model to use (e.g. claude-sonnet-4-6).

claude_timeout: u64

Timeout per item in seconds when using Claude Code. Default: 300.

codex_binary: Option<PathBuf>

Path to the Codex CLI binary. Default: auto-detect from PATH.

codex_model: Option<String>

Codex model to use (e.g. o4-mini).

codex_timeout: u64

Timeout per item in seconds when using Codex. Default: 300.

max_cost_usd: Option<f64>

Abort when cumulative cost exceeds this USD budget (API key only; ignored for OAuth).

resume: bool

Resume a previously interrupted run (skip already-done items).

retry_failed: bool

Retry only items that failed in a previous run.

min_output_chars: usize

Minimum output character count for body-enrich. Default: 500.

max_output_chars: usize

Maximum output character count for body-enrich. Default: 2000.

preserve_check: bool

Check that enriched body preserves all facts from the original (LLM judge). Default: true.

prompt_template: Option<PathBuf>

Path to a custom prompt template file for body-enrich.

llm_parallelism: u32

Number of parallel LLM workers (default 1 = serial). Each worker claims items atomically from the queue DB via UPDATE…RETURNING. Range: 1–32. For 2321 entities, –llm-parallelism 4 reduces wall time ~4×.

json: bool

Emit NDJSON output. Always true; flag accepted for compatibility.

db: Option<String>

Database path override.

wait_job_singleton: Option<u64>

G30: poll for the job singleton every second for up to N seconds when another invocation holds the lock. Default: 0 (fail fast).

force_job_singleton: bool

G30: force acquisition of the singleton lock by removing a stale lock file from a previously crashed invocation. Use only when you are certain no other enrich/ingest is running.

names: Vec<String>

G37: select a specific subset of memory names to enrich instead of the full candidate set. Comma-separated, e.g. --names a,b,c. Empty when omitted (processes all candidates).

names_file: Option<PathBuf>

G37: read the subset of memory names from a file (one per line). Lines starting with # and empty lines are ignored. Combined with --names (union) when both are set.

preflight_check: bool

G35: probe the LLM provider with a 1-turn ping before processing the batch. Aborts with a clear error if the rate-limit window is closed (avoids burning N turns only to fail on item 1).

fallback_mode: Option<EnrichMode>

G35: if a preflight probe or in-flight call hits the Claude rate limit, fall back to --fallback-mode (typically codex) instead of failing the batch. Ignored when --mode is already codex.

rate_limit_buffer: u64

G35: number of seconds before the OAuth rate-limit reset at which the preflight probe should refuse to start. Default 300 (5 min).

max_load_check: bool

G28-D: refuse to start when the 1-minute load average exceeds 2 × ncpus (or SQLITE_GRAPHRAG_MAX_LOAD_PER_NCPU if set). Set to false to skip the check on contended CI runners.

circuit_breaker_threshold: u32

G28-D: when the system is saturated, abort the job after this many consecutive HardFailure outcomes. Default 5.

preserve_threshold: f64

G29 Passo 4: minimum trigram-Jaccard similarity between the original body and the LLM-rewritten body for the rewrite to be accepted. Scores below the threshold are rejected and emitted as EnrichItemResult::PreservationFailed. Default 0.7 (per the G29 gap specification). Ignored when --operation is not body-enrich.

codex_model_validate: bool

G33 Passo 3: when set, validate --codex-model against the ChatGPT Pro OAuth accepted-model list and abort with a suggestion when the value is unknown. Default true (fail fast to avoid burning OAuth turns). Set to false to opt out.

codex_model_fallback: Option<String>

G33 Passo 3: when set together with an invalid --codex-model, automatically substitute the supplied default (e.g. gpt-5.5) instead of aborting. The substitution is recorded in the NDJSON stream as provider_substituted: true for traceability.

Trait Implementations

impl Args for EnrichArgs

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 FromArgMatches for EnrichArgs

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.