Struct PolicySnapshot 

pub struct PolicySnapshot {
    pub allowed_tools: Vec<String>,
    pub allowed_models: Vec<String>,
    pub auto_approve_unrestricted: bool,
    pub max_tokens_per_call: Option<u32>,
}

Narrowed permissions the harness wants enforced by the CLI itself.

Materialized as --allowed-tools / --model flags (Claude), --full-access gating (Codex), settings.json permissions, etc.

Fields

allowed_tools: Vec<String>

Tool name allow-list. Empty means “no override — let the CLI use its default policy”.

allowed_models: Vec<String>

Model id allow-list. The harness picks the first that the CliRequest::model field intersects with.

auto_approve_unrestricted: bool

If true, the adapter is permitted to pass its “auto-approve” flag (--full-access, --yolo, …).

max_tokens_per_call: Option<u32>

Per-call token cap (used as a hint; not every CLI enforces it).

Trait Implementations

impl Clone for PolicySnapshot

fn clone(&self) -> PolicySnapshot

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PolicySnapshot

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

Formats the value using the given formatter.

impl Default for PolicySnapshot

fn default() -> PolicySnapshot

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for PolicySnapshot

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for PolicySnapshot

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

where __S: Serializer,

Serialize this value into the given Serde serializer.