Struct ApprovalHook 

pub struct ApprovalHook { /* private fields */ }

A hook that requires user approval before each tool call.

When on_before_tool_call is invoked, it always returns ToolCallAction::Reject with a message indicating approval is needed. In a real application, this would block on user input (e.g., via a channel or callback).

Example

use lc_agents::hooks::ApprovalHook;

let hook = ApprovalHook::new();
let executor = AgentExecutor::new(agent, tools).hook(hook);

Implementations

impl ApprovalHook

pub fn new() -> Self

Creates a new ApprovalHook that requires manual approval.

pub fn auto_approve() -> Self

Creates an ApprovalHook that automatically approves all tool calls.

pub fn with_auto_approve(self, auto_approve: bool) -> Self

Sets the auto-approve mode.

Trait Implementations

impl AgentHook for ApprovalHook

fn on_before_tool_call(&self, ctx: &mut ToolCallContext) -> ToolCallAction

Called before a tool call. Can approve, reject, modify, or skip.

fn on_before_completion(&self, _ctx: &mut CompletionContext) -> CompletionAction

Called before an LLM completion. Can modify messages or reject the call.

fn on_after_completion( &self, _ctx: &mut CompletionResult, ) -> Result<(), HookError>

Called after an LLM completion. Can modify the response.

fn on_after_tool_call( &self, _ctx: &mut ToolResultContext, ) -> Result<(), HookError>

Called after a tool call. Can modify the result.

fn on_stream_chunk(&self, chunk: &str) -> StreamAction

Called for each streaming token. Can filter, replace, or forward.

fn on_agent_start(&self, _input: &str) -> Result<(), HookError>

Called when the agent starts execution.

fn on_agent_end(&self, _output: &str) -> Result<(), HookError>

Called when the agent finishes execution.

fn on_error(&self, _error: &HookError) -> ErrorAction

Called when an error occurs. Can retry, ignore, or propagate.

impl Default for ApprovalHook

fn default() -> Self

Returns the “default value” for a type.