Struct ContentFilterHook 

pub struct ContentFilterHook { /* private fields */ }

A hook that filters sensitive words from streaming output.

When on_stream_chunk is invoked, it checks the token for any of the configured sensitive words. If found, the token is either filtered (dropped) or replaced with a placeholder.

Example

use lc_agents::hooks::ContentFilterHook;

let hook = ContentFilterHook::new(vec!["secret".to_string(), "password".to_string()]);
let executor = AgentExecutor::new(agent, tools).hook(hook);

Implementations

impl ContentFilterHook

pub fn new(sensitive_words: Vec<String>) -> Self

Creates a new ContentFilterHook with the given sensitive words.

pub fn with_placeholder(self, placeholder: impl Into<String>) -> Self

Sets the placeholder for replaced words.

pub fn with_drop_token(self, drop: bool) -> Self

Sets whether to drop entire tokens containing sensitive words.

Trait Implementations

impl AgentHook for ContentFilterHook

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

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

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_before_tool_call(&self, _ctx: &mut ToolCallContext) -> ToolCallAction

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

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

Called after a tool call. Can modify the result.

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.