Struct ChainedHook 

pub struct ChainedHook<A, B> { /* private fields */ }

Combine two PromptHooks into one. See module docs for combination semantics.

When ChainedHook::observe_with sets a conversation ID, the chain also emits synthetic tool.skipped / tool.terminated events for tool calls whose combined action is Skip / Terminate. This closes the tool.invoked / tool.completed correlation gap when chaining a telemetry hook with a gating hook.

Implementations

impl<A, B> ChainedHook<A, B>

pub fn new(a: A, b: B) -> Self

Build a chained hook running a before b for every lifecycle event. By default the chain emits no synthetic terminal events; use ChainedHook::observe_with to opt in.

pub fn observe_with(self, conversation_id: impl Into<String>) -> Self

Opt in to synthetic tool.skipped / tool.terminated event emission stamped with conversation_id. Use the same conversation ID configured on the chain’s telemetry hook so pair-correlation by call_id works end-to-end.

Trait Implementations

impl<A: Clone, B: Clone> Clone for ChainedHook<A, B>

fn clone(&self) -> ChainedHook<A, B>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<A: Debug, B: Debug> Debug for ChainedHook<A, B>

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

Formats the value using the given formatter.

impl<A, B, M> PromptHook<M> for ChainedHook<A, B>

where A: PromptHook<M>, B: PromptHook<M>, M: CompletionModel,

async fn on_completion_call( &self, prompt: &Message, history: &[Message], ) -> HookAction

Called before the prompt is sent to the model

async fn on_completion_response( &self, prompt: &Message, response: &CompletionResponse<M::Response>, ) -> HookAction

Called after the prompt is sent to the model and a response is received.

async fn on_tool_call( &self, tool_name: &str, tool_call_id: Option<String>, internal_call_id: &str, args: &str, ) -> ToolCallHookAction

Called before a tool is invoked.

async fn on_tool_result( &self, tool_name: &str, tool_call_id: Option<String>, internal_call_id: &str, args: &str, result: &str, ) -> HookAction

Called after a tool is invoked (and a result has been returned).

fn on_text_delta( &self, _text_delta: &str, _aggregated_text: &str, ) -> impl Future<Output = HookAction> + Send

Called when receiving a text delta (streaming responses only)

fn on_tool_call_delta( &self, _tool_call_id: &str, _internal_call_id: &str, _tool_name: Option<&str>, _tool_call_delta: &str, ) -> impl Future<Output = HookAction> + Send

Called when receiving a tool call delta (streaming_responses_only). tool_name is Some on the first delta for a tool call, None on subsequent deltas.

fn on_stream_completion_response_finish( &self, _prompt: &Message, _response: &<M as CompletionModel>::StreamingResponse, ) -> impl Future<Output = HookAction> + Send

Called after the model provider has finished streaming a text response from their completion API to the client.