client.py

"""StabilizerForge environment client (sync + async via openenv core)."""
from __future__ import annotations

from typing import Any

from openenv.core import EnvClient
from openenv.core.client_types import StepResult
from openenv.core.env_server.types import State

from .models import StabilizerAction, StabilizerObservation


class StabilizerForgeEnv(EnvClient[StabilizerAction, StabilizerObservation, State]):
    """Client for the StabilizerForge environment server.

    Example:
        with StabilizerForgeEnv(base_url="http://localhost:8000") as client:
            result = client.reset(task_id="steane_7_1_3")
            result = client.step(StabilizerAction(op="H", qubits=[0]))
            ...
            result = client.step(StabilizerAction(op="FINALIZE"))
    """

    def _step_payload(self, action: StabilizerAction) -> dict[str, Any]:
        return {"op": action.op, "qubits": list(action.qubits)}

    def _parse_result(
        self, payload: dict[str, Any]
    ) -> StepResult[StabilizerObservation]:
        obs_data = payload.get("observation", {})
        observation = StabilizerObservation(**obs_data) if obs_data else StabilizerObservation()
        # Top-level done/reward override what's inside observation if present
        if "done" in payload:
            observation.done = bool(payload.get("done"))
        if "reward" in payload:
            observation.reward = payload.get("reward")
        return StepResult(
            observation=observation,
            reward=payload.get("reward"),
            done=payload.get("done", False),
        )

    def _parse_state(self, payload: dict[str, Any]) -> State:
        return State(
            episode_id=payload.get("episode_id"),
            step_count=payload.get("step_count", 0),
        )