Struct PermissionRequest 

pub struct PermissionRequest {

    pub request_version: PermissionRequest_RequestVersion,
    pub id: String,
    pub agent: ActorId,
    pub instance: Option<InstanceId>,
    pub human: Option<ActorId>,
    pub model: Option<String>,
    pub tool: Option<String>,
    pub action: ActionName,
    pub target: Option<String>,
    pub risk: Option<RiskClass>,
    pub danger_tags: Option<Vec<DangerTag>>,
    pub duration_seconds: Option<i64>,
    pub reason: String,
    pub proof_level_offered: Option<ProofLevel>,
    pub requested_at: Timestamp,
    pub context: Option<Value>,
}

An AI agent’s typed request to acquire authority for a specific action, target, and duration. The daemon validates the request, runs the policy engine, optionally collects approvals, and replies with a PermissionGrant or a denial. See TF-0006 “dynamic permission negotiation”.

Fields

request_version: PermissionRequest_RequestVersion

Version of the permission-request schema itself.

id: String

Stable identifier for this request; copied into the matching PermissionGrant.

agent: ActorId

Agent actor making the request.

instance: Option<InstanceId>

Specific running instance of the agent.

human: Option<ActorId>

Human principal the agent is acting on behalf of.

model: Option<String>

Provider-prefixed model identifier (e.g. anthropic:claude-opus-4-7).

tool: Option<String>

Tool the agent intends to invoke once the permission is granted.

action: ActionName

Dotted action name being requested.

target: Option<String>

Target the action will operate on (file path, record id, URL, …).

risk: Option<RiskClass>

Agent’s self-declared risk class for the action.

danger_tags: Option<Vec<DangerTag>>

Danger tags the agent already knows apply.

duration_seconds: Option<i64>

Maximum lifetime the agent is asking for; the daemon may cap it.

reason: String

Human-readable rationale visible to approvers.

proof_level_offered: Option<ProofLevel>

Highest proof level the agent can produce if challenged.

requested_at: Timestamp

When the request was created.

context: Option<Value>

Free-form context the daemon and approvers can use.

Trait Implementations

impl Clone for PermissionRequest

fn clone(&self) -> PermissionRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PermissionRequest

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for PermissionRequest

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for PermissionRequest

impl PartialEq for PermissionRequest

fn eq(&self, other: &PermissionRequest) -> 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 Serialize for PermissionRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for PermissionRequest