Struct PlanModeExecutor 

pub struct PlanModeExecutor { /* private fields */ }

Wraps an ErasedToolExecutor for Plan permission mode.

Exposes the real tool catalog via tool_definitions_erased() so the LLM can reference existing tools in its plan, but blocks all execution methods with ToolError::Blocked. This implements read-only planning: the agent sees what tools exist but cannot invoke them.

Implementations

impl PlanModeExecutor

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

Wrap inner with plan-mode restrictions.

Trait Implementations

impl ErasedToolExecutor for PlanModeExecutor

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 is_tool_retryable_erased(&self, _tool_id: &str) -> bool

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

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

fn set_effective_trust(&self, _level: SkillTrustLevel)

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