"""A GPU agent that fell back to the CPU reads as DEGRADED, not running (#4410).

Both runtimes fall back without raising, so a CPU-bound agent leases, works
and checks in exactly like a healthy one. On 2026-09-24 one had been doing so
since a driver update left a stale CDI spec; the only sign was a line in the
agent's own log. The agent now sends its startup report on every lease and
heartbeat, and the System view derives the state from it.
"""

from __future__ import annotations

from backend.app.api.gpu import _accel_detail
from backend.app.api.system_health import _SEVERITY, _learned_state

GPU = {"torch": {"device": "cuda"}, "onnx": {"device": "cuda"}}
CPU = {
    "torch": {"device": "cpu"},
    "onnx": {"device": "cpu", "error": "cudaGetDeviceCount: unknown error (999)"},
}


def test_a_running_agent_on_the_gpu_is_ok():
    state, detail = _learned_state("GPU agent", "ok", 5, {"accel": GPU})
    assert state == "ok"
    assert detail == "GPU agent is running"


def test_a_running_agent_on_the_cpu_is_degraded_and_says_why():
    state, detail = _learned_state("GPU agent", "ok", 5, {"accel": CPU})
    assert state == "degraded"
    assert "onnx (cudaGetDeviceCount: unknown error (999))" in detail
    assert "torch (cpu)" in detail


def test_an_agent_that_never_reported_is_not_called_degraded():
    """An older agent build sends no `accel`: that is not-yet-known, not slow."""
    assert _learned_state("GPU agent", "ok", 5, {})[0] == "ok"


def test_stopped_outranks_degraded():
    """Whether a quiet agent is still running is the more urgent question."""
    state, _ = _learned_state("GPU agent", "down", 900, {"accel": CPU})
    assert state == "down"
    assert _SEVERITY["stale"] > _SEVERITY["degraded"] > _SEVERITY["unknown"]


def test_the_lease_keeps_only_a_bounded_report():
    """Written on every lease by a client the server does not control."""
    body = {"accel": {
        "torch": {"device": "cpu", "error": "x" * 5000, "extra": "dropped"},
        "onnx": "not a dict",
    }}
    kept = _accel_detail(body)["accel"]
    assert kept == {"torch": {"device": "cpu", "error": "x" * 200}}


def test_a_lease_without_a_report_adds_nothing():
    assert _accel_detail({}) == {}
    assert _accel_detail({"accel": None}) == {}