Enum PolicyDecision 

pub enum PolicyDecision {
    Allow {
        risk: RiskClass,
        checkpoint: bool,
    },
    Ask {
        risk: RiskClass,
        checkpoint: bool,
    },
    Classify {
        risk: RiskClass,
        checkpoint: bool,
    },
    Deny {
        risk: RiskClass,
        reason: String,
    },
}

Variants

Allow

Fields

risk: RiskClass

checkpoint: bool

Ask

Fields

risk: RiskClass

checkpoint: bool

Classify

Auto mode only: a borderline action the rule engine won’t decide alone. The caller (the mermaid-cli policy gate) resolves it by asking the LLM classifier to vet the action against the user’s intent — aligned ⇒ proceed, otherwise escalate to a human approval. The runtime crate stays model-free; it only signals “needs vetting”.

Fields

risk: RiskClass

checkpoint: bool

Deny

Fields

risk: RiskClass

reason: String

Implementations

impl PolicyDecision

pub fn risk(&self) -> RiskClass

pub fn label(&self) -> &'static str

Trait Implementations

impl Clone for PolicyDecision

fn clone(&self) -> PolicyDecision

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PolicyDecision

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for PolicyDecision

fn deserialize<__D>( __deserializer: __D, ) -> Result<PolicyDecision, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for PolicyDecision

impl PartialEq for PolicyDecision

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for PolicyDecision

fn serialize<__S>( &self, __serializer: __S, ) -> Result<<__S as Serializer>::Ok, <__S as Serializer>::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for PolicyDecision