pub fn decode_ollama_stream(
runner: Symbol,
model: &str,
body: &[u8],
include_raw: bool,
) -> Result<Expr>Expand description
Decodes a newline-delimited Ollama streaming response body into a single
canonical model-response transcript attributed to runner and model.
Concatenates the text of every chunk, derives the stop reason from the final
chunk, and folds in token-usage counts; when include_raw is set, the raw
chunks are attached as a raw-provider-response list. Errors if no chunks
are present.