Skip to main content
Sampling pipeline hook payloads.

​
Classes

​
CLASS SamplingLoopStartPayload

Payload for sampling_loop_start — when sampling strategy begins. Attributes:
  • strategy_name: Class name of the sampling strategy (e.g. "RejectionSamplingStrategy").
  • action: The [Component](../../core/base#class-component) being sampled.
  • context: The [Context](../../core/base#class-context) at the start of sampling.
  • requirements: List of [Requirement](../../core/requirement#class-requirement) instances to validate against.
  • loop_budget: Maximum number of sampling iterations allowed (writable).

​
CLASS SamplingIterationPayload

Payload for sampling_iteration — after each sampling attempt. Attributes:
  • iteration: 1-based iteration number within the sampling loop.
  • action: The [Component](../../core/base#class-component) used for this attempt.
  • result: The [ModelOutputThunk](../../core/base#class-modeloutputthunk) produced by this attempt.
  • validation_results: List of (Requirement, ValidationResult) tuples.
  • all_validations_passed: True when every requirement in validation_results passed for this iteration (i.e., the sampling attempt succeeded).
  • valid_count: Number of requirements that passed.
  • total_count: Total number of requirements evaluated.

​
CLASS SamplingRepairPayload

Payload for sampling_repair — when repair is invoked after validation failure. Attributes:
  • repair_type: Kind of repair (strategy-dependent, e.g. "rejection", "template").
  • failed_action: The [Component](../../core/base#class-component) that failed validation.
  • failed_result: The [ModelOutputThunk](../../core/base#class-modeloutputthunk) that failed validation.
  • failed_validations: List of (Requirement, ValidationResult) tuples that failed.
  • repair_action: The repaired [Component](../../core/base#class-component) to use for the next attempt.
  • repair_context: The [Context](../../core/base#class-context) to use for the next attempt.
  • repair_iteration: 1-based iteration at which the repair was triggered.

​
CLASS SamplingLoopEndPayload

Payload for sampling_loop_end — when sampling completes. Attributes:
  • success: True if at least one attempt passed all requirements.
  • iterations_used: Total number of iterations the loop executed.
  • final_result: The selected [ModelOutputThunk](../../core/base#class-modeloutputthunk) (best success or best failure).
  • final_action: The [Component](../../core/base#class-component) that produced final_result.
  • final_context: The [Context](../../core/base#class-context) associated with final_result.
  • failure_reason: Human-readable reason when success is False.
  • all_results: List of [ModelOutputThunk](../../core/base#class-modeloutputthunk) from every iteration.
  • all_validations: Nested list — all_validations[i] is the list of (Requirement, ValidationResult) tuples for iteration i.