default/best_of_n

"""Best-of-N — give the LLM N attempts at the same parent before committing to the global best.

Ported from SkyDiscover's ``BestOfNDatabase`` (UC Berkeley Sky Computing Lab). One module per component:

  population.py        -> BestOfNPopulation     (keep-all archive)
  selection_policy.py  -> BestOfNPolicy         (reuse parent N times, then switch to the global best)
  prompt_builder.py    -> BestOfNPromptBuilder  (the default multi-section template)
  proposer.py          -> BestOfNProposer       (SEARCH/REPLACE diff)
  evaluator.py         -> BestOfNEvaluator      (task-supplied)
  memory.py            -> BestOfNMemory         (none)
  scaffold.py          -> BestOfNScaffold       (the orchestrator that composes the six)

A single parent is reused until N **valid** children have been produced from it — N independent
variations from one starting point — before the search commits to the current global best and
repeats. Faithful to SkyDiscover, a failed (parse/invalid) attempt is a free retry that does not
spend the budget; the ``best_of_n_attempts`` variant instead spends one unit per attempt. Larger N
deepens exploitation of a single program state; N=1 approaches Top-K.
"""
from __future__ import annotations

from ...config import GalapagosConfig
from ...models import GalapagosModel
from ..base_scaffold import GalapagosScaffold
from ..registry import register_scaffold
# one module per component (the Best-of-N scaffold method)
from .memory import BestOfNMemory
from .population import BestOfNPopulation
from .prompt_builder import BestOfNPromptBuilder
from .proposer import BestOfNProposer
from .selection_policy import BestOfNPolicy


@register_scaffold("best_of_n")
class BestOfNScaffold(GalapagosScaffold):
    name = "best_of_n"

    @classmethod
    def build_components(cls, config: GalapagosConfig, model: GalapagosModel | None) -> dict:
        seed = int(config.seed)
        sel = config.selection_policy
        return {
            "population": BestOfNPopulation(capacity=config.population.capacity),
            "selection_policy": BestOfNPolicy(
                seed=seed,
                n=int(sel.best_of_n),
                num_inspirations=int(sel.num_inspirations),
            ),
            "prompt_builder": BestOfNPromptBuilder(),
            "proposer": BestOfNProposer(),
            "memory": BestOfNMemory(),
        }