Lite LLMConsumption Capturing Prompt Executor
LiteLLM variant: reads inputTokensCount / outputTokensCount / totalTokensCount from the response metadata.
Functions
Returns the consumption accumulated since the previous call (or since construction), then resets the accumulator. Returns null when nothing was captured.
Pre-resolved-model overload of execute; captures consumption the same way.
Runs the call through delegate and accumulates any LLMConsumption reported by extractConsumption for the returned response. Accumulation is thread-safe.
Pre-resolved-model overload of executeStreaming; also captures nothing.
Delegates streaming to delegate; no consumption is captured from streamed frames.
Executes prompt against model, requesting a structured response of type OutputStructT, and returns the parsed data.
Delegates model resolution, so the wrapped executor keeps its fallback/routing behaviour.