Struct SkillLoaderExecutor 

pub struct SkillLoaderExecutor { /* private fields */ }

Tool executor that loads a full skill body by name from the shared registry.

Delegates trust resolution, integrity checking, sanitization, and quarantine wrapping to a shared SkillTrustGate (crate-private) — the same pipeline invoke_skill (crate::skill_invoker::SkillInvokeExecutor) uses, so the two tools cannot drift apart.

Implementations

impl SkillLoaderExecutor

pub fn new( registry: Arc<RwLock<SkillRegistry>>, trust_snapshot: Arc<RwLock<HashMap<String, SkillTrustSnapshot>>>, ) -> Self

Create a new executor with shared registry and trust snapshot.

trust_snapshot must be the same Arc shared with SkillInvokeExecutor (see agent_setup::build_skill_executors in the binary crate) so load_skill and invoke_skill see identical trust state within a turn.

Examples

use std::collections::HashMap;
use std::sync::Arc;

use parking_lot::RwLock;
use zeph_core::SkillLoaderExecutor;
use zeph_skills::registry::SkillRegistry;

let registry = Arc::new(RwLock::new(SkillRegistry::empty()));
let trust_snapshot = Arc::new(RwLock::new(HashMap::new()));
let _executor = SkillLoaderExecutor::new(registry, trust_snapshot);

pub fn with_turn_trust_floor(self, turn_trust_floor: TurnTrustFloor) -> Self

Wires the shared per-turn trust floor (#6701) so a load_skill preview of a Quarantined body folds the turn’s trust down for its remainder — see SkillTrustGate::with_turn_trust_floor.

Trait Implementations

impl Clone for SkillLoaderExecutor

fn clone(&self) -> SkillLoaderExecutor

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SkillLoaderExecutor

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

Formats the value using the given formatter.

impl ToolExecutor for SkillLoaderExecutor

async fn execute( &self, _response: &str, ) -> Result<Option<ToolOutput>, ToolError>

Parse response for fenced tool blocks and execute them.

fn tool_definitions(&self) -> Vec<ToolDef>

Return the tool definitions this executor can handle.

async fn execute_tool_call( &self, call: &ToolCall, ) -> Result<Option<ToolOutput>, ToolError>

Execute a structured tool call. Returns Ok(None) if call.tool_id is not handled.

fn requires_confirmation(&self, _call: &ToolCall) -> bool

Return true when call would require user confirmation before execution.

fn execute_tool_call_confirmed( &self, call: &ToolCall, ) -> impl Future<Output = Result<Option<ToolOutput>, ToolError>> + Send

Execute a structured tool call bypassing confirmation checks.

fn checkpoint_undo(&self, _n: usize) -> CheckpointActionResult

Undo the last n checkpointed write commands.

fn checkpoint_redo(&self) -> CheckpointActionResult

Redo the last undone checkpoint.

fn checkpoint_list(&self) -> CheckpointListResult

List the current undo stack entries and redo depth.

fn is_tool_speculatable(&self, _tool_id: &str) -> bool

Whether a tool call can be safely dispatched speculatively (before the LLM finishes).

fn execute_confirmed( &self, response: &str, ) -> impl Future<Output = Result<Option<ToolOutput>, ToolError>> + Send

Execute bypassing confirmation checks (called after user approves).

fn set_skill_env(&self, _env: Option<HashMap<String, String>>)

Inject environment variables for the currently active skill. No-op by default.

fn set_effective_trust(&self, _level: SkillTrustLevel)

Set the effective trust level for the currently active skill. No-op by default.

fn is_tool_retryable(&self, _tool_id: &str) -> bool

Whether the executor can safely retry this tool call on a transient error.