Agent

Agent(
    llm: LLMProvider,
    db_path: str,
    plan_prompt: str,
    reason_prompt: str,
    act_prompt: str,
    k: int = 3,
    max_steps: int = 30,
    seed_trajectories: list[Trajectory] | None = None,
    on_step: Callable[[Step, StepContext], None] | None = None,
    curation_threshold: float = 0.3,
    curation_min_retrievals: int = 5,
    verify_trajectory: Callable[[Trajectory], bool] | None = None,
)

await agent.train(env, goal)
await agent.run(env, goal)
agent.train_sync(env, goal)
agent.run_sync(env, goal)
await agent.train_batch(env_factory, goals)
await agent.run_batch(env_factory, goals)
agent.get_stats()