generateStream
abstract fun generateStream(prompt: String, callback: NativeLlmStreamCallback): NativeLlmCancelHandle(source)
Streams prompt token-by-token through callback — real per-token output (Apple's LanguageModelSession.streamResponse), not a single-emission replay of generate. Returns a NativeLlmCancelHandle the Kotlin side calls when its collecting coroutine is cancelled, so Stop/screen-leave actually halts native generation instead of only stopping the Kotlin side from listening — the same contract MediaPipeOnDeviceLlm's Android backend already honors for its own callbackFlow.