"""Tests for the DGR-001 performance contract metadata."""

from __future__ import annotations

import json

from meshnet_node.performance_contract import DEFAULT_CONTRACT, SCHEMA_VERSION, main


def test_default_contract_is_architecture_aligned_and_small():
    """The baseline stays on DeepSeek2 and uses the smallest DeepSeek-family GGUF.

    Tags: performance, model, gguf
    """
    payload = DEFAULT_CONTRACT.to_dict()

    assert payload["schema_version"] == SCHEMA_VERSION
    assert payload["story_id"] == "DGR-001"
    assert payload["model_target"] == {
        "name": "DeepSeek-V2-Lite-Chat",
        "architecture": "deepseek2",
        "safetensors_repo": "deepseek-ai/DeepSeek-V2-Lite-Chat",
        "safetensors_precision": "bfloat16",
        "gguf_repo": "second-state/DeepSeek-V2-Lite-Chat-GGUF",
        "gguf_quant": "Q2_K",
        "gguf_size_gb": 6.43,
        "comparison_policy": (
            "same model/revision, closest practical low-footprint precision pair: "
            "BF16 safetensors versus Q2_K GGUF"
        ),
        "rationale": (
            "Smallest DeepSeek-family benchmark anchor that still points toward "
            "DeepSeek-V4-Flash; keeps the runtime on the DeepSeek2 path instead "
            "of falling back to a tiny but architecture-mismatched smoke model."
        ),
    }
    assert payload["benchmark_lanes"] == [
        {
            "id": "transformers-safetensors-cpu",
            "runtime": "transformers",
            "device": "cpu",
            "recipe": "current safetensors recipe",
            "concurrency_levels": [1, 4],
        },
        {
            "id": "llama-cpp-gguf-cpu",
            "runtime": "llama.cpp",
            "device": "cpu",
            "recipe": "whole-model GGUF recipe",
            "concurrency_levels": [1, 4],
        },
        {
            "id": "transformers-safetensors-gpu",
            "runtime": "transformers",
            "device": "gpu",
            "recipe": "current safetensors recipe",
            "concurrency_levels": [1, 4],
        },
        {
            "id": "llama-cpp-gguf-gpu",
            "runtime": "llama.cpp",
            "device": "gpu",
            "recipe": "whole-model GGUF recipe",
            "concurrency_levels": [1, 4],
        },
    ]
    assert "ttft_ms" in payload["metrics"]
    assert "output_drift" in payload["metrics"]
    assert "meaningful speed or fit benefit" in payload["stop_condition"]
    assert any("mounted drive" in note for note in payload["notes"])


def test_contract_cli_writes_json(tmp_path, capsys):
    """The contract can be emitted as a machine-readable artifact.

    Tags: performance, artifact
    """
    output = tmp_path / "performance-contract.json"

    assert main(["--json-out", str(output)]) == 0
    written = json.loads(output.read_text(encoding="utf-8"))

    assert written == DEFAULT_CONTRACT.to_dict()
    assert str(output) in capsys.readouterr().out