types
diapason.learning.optimize.types
¶
Core data types for the optimization framework.
BenchmarkScore
dataclass
¶
Per-benchmark metrics from a multi-benchmark evaluation trial.
ObjectiveSpec
dataclass
¶
A single optimization objective.
OptimizationRun
dataclass
¶
Complete optimization session.
SampleScore
dataclass
¶
Per-sample metrics from an evaluation trial.
SearchDimension
dataclass
¶
One tunable dimension in the config space.
SearchSpace
dataclass
¶
The full space of configs the optimizer can propose.
to_prompt_description()
¶
Render search space as structured text for the LLM optimizer.
TrialConfig
dataclass
¶
A single candidate configuration proposed by the optimizer.
to_recipe()
¶
Map params back to Recipe fields.
TrialFeedback
dataclass
¶
Structured feedback from trial analysis.
TrialResult
dataclass
¶
Result of evaluating a trial, with both scalar and textual feedback.