Config¶
Configuration models for experiment runs. All models use Pydantic for validation.
config
¶
Pydantic models for run configuration.
SessionMode
¶
Bases: str, Enum
SessionConfig
¶
Bases: BaseModel
Configuration for a single session within a run.
AgentConfig
¶
Bases: BaseModel
Definition of a subagent available to the main agent.
JudgeConfig
¶
Bases: BaseModel
Auto-judge: an LLM that evaluates the running trajectory against a rubric.
The judge runs every every_n_turns agent turns, sees the trajectory so
far, and returns a structured verdict (flagged + reason + confidence). If a
verdict is flagged and early_exit is set, the session stops after the
current turn. The judge runs independently of the agent engine, so it can
judge both Claude Code and Codex runs.
HookCommandConfig
¶
Bases: BaseModel
Shell command run before or after an experiment.
RunConfig
¶
Bases: BaseModel
Top-level run configuration.
load_config(path)
¶
Load a RunConfig from a YAML file.
build_provider_env(config)
¶
Build environment variable dict passed to the engine.
Returns a dict — does NOT mutate os.environ.