harbor_agents
Harbor glue classes - agent + environment (harbor 0.13.2).
These subclass harbor base classes, so harbor is imported at module top.
Our own code never imports this module directly - harbor loads these by the
string import_path recorded in the job/agent config at runtime (see
:mod:evsys_sdk.training.harbor_engine). That keeps the optional [harbor]
extra out of the base import path.
- :class:
NoOpEnvironment- sandbox-freeBaseEnvironment(no container). - :class:
BasicLoopAgent- drivesChat(\<llm>)on-policy, records token-levelrollout_detailsonto theAgentContext, and writes the completion to the agent dir so the verifier can read it. The default agent.model_clientpicks the sampler:"tinker"(on-policyTinkerLLM) or"litellm"(any provider litellm supports, for benchmarking closed/API models through the same path). Users can also plug anyBaseAgentviaagent_import_path. - :class:
EvsysVerifier- a harborBaseVerifierthat wraps our registered verifier fns. It runs host-side (no container exec): reads the completion the agent wrote + the per-task spec (fn_name/expected/params) materialized into the task dir, and returns the reward as a harborVerifierResult. Used in SHARED mode (a dummytests/test.sh, written by the materializer, satisfies harbor's task-load check and is never executed).
attribute__all__= ['BasicLoopAgent', 'EvsysVerifier', 'NoOpEnvironment']func_read_text(path) -> strparampathPathReturns
strfunc_read_json(path) -> dict[str, Any]parampathPathReturns
dict[str, typing.Any]