Skip to main content
Generation pipeline hook payloads.

​
Classes

​
CLASS GenerationPreCallPayload

Payload for generation_pre_call — before LLM backend call. Attributes:
  • action: The [Component](../../core/base#class-component) or [CBlock](../../core/base#class-cblock) about to be sent to the backend.
  • context: The [Context](../../core/base#class-context) being used for this generation call.
  • model_options: Dict of model options (writable — plugins may adjust temperature, etc.).
  • format: Optional BaseModel subclass for constrained decoding (writable).
  • tool_calls: Whether tool calls are enabled for this generation (writable).

​
CLASS GenerationPostCallPayload

Payload for generation_post_call — fires once the model output is fully computed. For lazy [ModelOutputThunk](../../core/base#class-modeloutputthunk) objects this hook fires inside ModelOutputThunk.astream after post_process completes, so model_output.value is guaranteed to be available. For already-computed thunks (e.g. cached responses) it fires before generate_from_context returns. Attributes:
  • prompt: The formatted prompt sent to the backend (str or list of message dicts).
  • model_output: The fully-computed [ModelOutputThunk](../../core/base#class-modeloutputthunk).
  • latency_ms: Elapsed milliseconds from the generate_from_context call to when the value was fully materialized.