Single-agent baseline that hands the whole search loop to one Claude Code CLI session, run inside the task's own container image by default (subscription-only billing): Claude edits the solution and runs the task's own evaluator, and the framework scores checkpoints with that same evaluator. A run scored on the host (general.eval_mode: local) gets the session as a host subprocess instead.
"""Claude Code — single-agent CLI baseline: the whole search loop runs inside one local
``claude -p`` session, billed to the operator's claude.ai subscription by default.
scaffold.py -> ClaudeCodeScaffold (the controller; the five loop components are inert here —
Claude Code subsumes selection, prompting, and proposal)
"""
from __future__ import annotations
from .scaffold import ClaudeCodeScaffold
__all__ = ["ClaudeCodeScaffold"]