tests/runtime/test_spectate.py

"""Unit tests for SpectateSession (agent-driven, stepwise, rich disclosure)."""
from __future__ import annotations

import pytest

import proteus.game.scenarios  # noqa: F401
from proteus.game.agents.vanilla import VanillaAgent
from proteus.game.engine.difficulty import Difficulty
from proteus.providers.fake import FakeProvider
from proteus.game.runtime._session_core import SessionFinishedError
from proteus.game.runtime.spectate import SpectateSession


def _agent(n=10):
    return VanillaAgent(FakeProvider(responses=["ACTION: stay"] * n, model_name="demo"))


def _new(play_turns=5):
    return SpectateSession(
        "template", agent=_agent(), model_name="fake:demo",
        difficulty=Difficulty.EASY, seed=42, play_turns=play_turns, use_probe=False,
    )


def test_initial_state_is_cut_intro_int_grid():
    s = _new()
    st = s.state()
    assert st["phase"] == "cut_intro"
    assert st["turn_idx"] == 0
    assert isinstance(st["grid"][0][0], int)
    assert st["turns_so_far"] == []


def test_advance_runs_one_llm_turn_with_rich_disclosure():
    s = _new()
    st = s.advance()
    assert st["turn_idx"] == 1
    last = st["turns_so_far"][-1]
    # rich: optimal/habit/reward/reasoning ARE exposed live (spectator, not scored).
    for k in ("action", "motive_action", "habit_action", "reward",
              "is_diagnostic", "was_congruent", "reasoning"):
        assert k in last


def test_advance_to_budget_then_done_and_finish():
    s = _new(play_turns=2)
    while s.state()["outcome"] is None:
        s.advance()
    st = s.state()
    assert st["phase"] == "done" and st["outcome"] in ("survived", "eliminated")
    trace = s.finish()
    assert trace.model == "fake:demo" and trace.scenario == "template"


def test_advance_after_done_raises():
    s = _new(play_turns=1)
    s.advance()
    with pytest.raises(SessionFinishedError):
        s.advance()