Struct Explanation 

pub struct Explanation {
    pub overall: Verdict,
    pub segments: Vec<SegmentReport>,
    pub parsed: bool,
    pub stateful: bool,
}

A per-segment breakdown of why a command would or would not auto-approve.

“Segment” means a top-level list element — the pieces a user separates with &&, ||, ;, or &. This is the granularity that matters for the common failure mode: one un-allowlisted command torpedoing an otherwise-safe chain.

Fields

overall: Verdict

segments: Vec<SegmentReport>

parsed: bool

False when the input could not be parsed at all.

stateful: bool

True when segments share shell state (a cd, export, assignment, or source) so that splitting them into separate calls would break them.

Implementations

impl Explanation

pub fn is_allowed(&self) -> bool

pub fn should_surface(&self) -> bool

Whether this explanation is worth injecting into an agent’s context automatically. The teachable case is a mix: an otherwise-auto-approving chain dragged into a manual prompt by one un-allowlisted segment. A single denied command, or an all-denied chain, carries no chaining lesson — so we stay quiet and let the normal approval flow handle it.

pub fn render(&self) -> String

A model- and human-readable breakdown: which segments auto-approve, which don’t, and what to actually do about it.

Trait Implementations

impl Clone for Explanation

fn clone(&self) -> Explanation

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Explanation

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

Formats the value using the given formatter.

impl Eq for Explanation

impl PartialEq for Explanation

fn eq(&self, other: &Explanation) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for Explanation