Enum LlmResponse 

pub enum LlmResponse {
    Stream(LlmResponseStream),
    Agg(AggLlmResponse),
}

A model response: either a live Stream of events or a terminal buffered LlmResponse::Agg response.

Not Clone — the Stream variant owns a single-consumption stream. A buffered backend returns Agg directly; a streaming one returns Stream and the consumer drives it, folding to an AggLlmResponse when it needs the whole response.

Variants

Stream(LlmResponseStream)

Live, single-consumption response stream.

Agg(AggLlmResponse)

Fully buffered terminal response.

Implementations

impl LlmResponse

pub fn as_agg(&self) -> Option<&AggLlmResponse>

Borrow the aggregate; None while this is still a stream.

pub async fn into_agg(self) -> Result<AggLlmResponse, LlmClientError>

Reduce to the buffered aggregate: return an Agg unchanged, or drive a Stream to completion, folding its normalized chunks into an AggLlmResponse via ResponseAccumulator. A stream item error aborts with Err, as does an in-band LlmResponseChunk::DecodeError (as ResponseTranslation) or LlmResponseChunk::StreamError (as UpstreamHttp).

pub fn selected_model(&self) -> Option<&str>

Returns the model recorded by a buffered response.

Returns None for a live stream because reading its model-bearing LlmResponseChunk::MessageStart event would consume the stream.