Struct FilteredToolExecutor 

pub struct FilteredToolExecutor { /* private fields */ }

Wraps an ErasedToolExecutor and enforces a ToolPolicy plus an optional additional denylist (disallowed).

All calls are checked against the policy and the denylist before being forwarded to the inner executor. The denylist is evaluated first — a tool in disallowed is blocked even if policy would allow it (deny wins). Rejected calls return a descriptive ToolError.

Implementations

impl FilteredToolExecutor

pub fn new(inner: Arc<dyn ErasedToolExecutor>, policy: ToolPolicy) -> Self

Create a new filtered executor with the given policy and no additional denylist.

Use with_disallowed when the agent definition also specifies tools.except entries.

pub fn with_disallowed( inner: Arc<dyn ErasedToolExecutor>, policy: ToolPolicy, disallowed: Vec<String>, ) -> Self

Create a new filtered executor with an additional denylist.

Tools in disallowed are blocked regardless of the base policy (deny wins over allow).

Trait Implementations

impl ErasedToolExecutor for FilteredToolExecutor

fn execute_tool_call_confirmed_erased<'a>( &'a self, call: &'a ToolCall, ) -> Pin<Box<dyn Future<Output = Result<Option<ToolOutput>, ToolError>> + Send + 'a>>

Same policy as execute_tool_call_erased: the confirmed path must go through the same allow/deny check, not bypass it. Mirrors the removed trait default’s behavior (delegate to execute_tool_call_erased) while preserving the policy enforcement already present there.

fn execute_erased<'a>( &'a self, response: &'a str, ) -> Pin<Box<dyn Future<Output = Result<Option<ToolOutput>, ToolError>> + Send + 'a>>

fn execute_confirmed_erased<'a>( &'a self, response: &'a str, ) -> Pin<Box<dyn Future<Output = Result<Option<ToolOutput>, ToolError>> + Send + 'a>>

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

fn execute_tool_call_erased<'a>( &'a self, call: &'a ToolCall, ) -> Pin<Box<dyn Future<Output = Result<Option<ToolOutput>, ToolError>> + Send + 'a>>

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_erased(&self, tool_id: &str) -> bool

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

fn requires_confirmation_erased(&self, call: &ToolCall) -> bool

Return true when call would require user confirmation before execution.

fn checkpoint_undo_erased(&self, n: usize) -> CheckpointActionResult

Undo the last n checkpointed write commands.

fn checkpoint_redo_erased(&self) -> CheckpointActionResult

Redo the last undone checkpoint.

fn checkpoint_list_erased(&self) -> CheckpointListResult

List the current undo stack entries and redo depth.

fn is_tool_speculatable_erased(&self, tool_id: &str) -> bool

Whether a tool call can be safely dispatched speculatively.