chore(models): 开工前清理 + 去掉 mm1 的残留注释序号

- tests/test_models.py：模块级 pytestmark -> 逐条 @pytest.mark.skip（决策 26）；
  该文件的 5 条测试仍然全跳过，只是形式上与其它测试文件对齐了。
- models/metrics.py：rmse / mae / r2_score 的注释 TODO(L0) -> TODO(L1)
  （roadmap 的 L0 12 项里没有这三个指标，它们属于 L1 的 models 清单）。
- simulate.py：用户去掉 # 4. 封装返回 这行残留序号注释（无代码变化）。

校验：pytest 204 passed / 28 skipped；ruff 0；pyright 0

src/mcm_toolkit/models/metrics.py

@@ -24,13 +24,13 @@ __all__ = [
 
 def rmse(y_true: Any, y_pred: Any) -> float:
     """均方根误差。与 y 同量纲，最常用。"""
-    # TODO(L0)
+    # TODO(L1)
     raise NotImplementedError
 
 
 def mae(y_true: Any, y_pred: Any) -> float:
     """平均绝对误差。对离群值比 RMSE 稳健。"""
-    # TODO(L0)
+    # TODO(L1)
     raise NotImplementedError
 
 
@@ -48,7 +48,7 @@ def smape(y_true: Any, y_pred: Any) -> float:
 
 def r2_score(y_true: Any, y_pred: Any) -> float:
     """决定系数 R²。注意：加变量一定会升高，跨模型比较要看 adjusted_r2。"""
-    # TODO(L0)
+    # TODO(L1)
     raise NotImplementedError
 
 

src/mcm_toolkit/solve/simulate.py

@@ -772,7 +772,6 @@ def mm1_metrics(arrival_rate: float, service_rate: float) -> Any:
         W = 1.0 / (service_rate - arrival_rate) # 平均逗留时间
         Wq = W - 1.0 / service_rate             # 平均等待时间
 
-        # 4. 封装返回
         metrics = {
             "rho": float(rho),
             "L": float(L),

tests/test_models.py

@@ -5,9 +5,10 @@ from __future__ import annotations
 import numpy as np
 import pytest
 
-pytestmark = pytest.mark.skip(reason="未实现：见 docs/03-roadmap.md L1")
+_NOT_IMPLEMENTED = "未实现：见 docs/03-roadmap.md L1"
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_fit_linear_recovers_known_coefficients(linear_data):
     """真值 y = 2x + 1，拟合系数应在 1% 内。"""
     from mcm_toolkit.models import fit_linear
@@ -18,6 +19,7 @@ def test_fit_linear_recovers_known_coefficients(linear_data):
     assert np.isclose(r.params["intercept"], 1.0, atol=0.05)
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_fit_polynomial_matches_numpy(linear_data):
     from mcm_toolkit.models import fit_polynomial
 
@@ -26,6 +28,7 @@ def test_fit_polynomial_matches_numpy(linear_data):
     assert np.allclose(r.params["coef"], np.polyfit(x, y, 2), rtol=1e-6)
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_metrics_known_values():
     from mcm_toolkit.models import mae, r2_score, rmse
 
@@ -36,6 +39,7 @@ def test_metrics_known_values():
     assert r2_score(y_true, y_pred) < 1.0
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_r2_is_one_for_perfect_fit():
     from mcm_toolkit.models import r2_score
 
@@ -43,6 +47,7 @@ def test_r2_is_one_for_perfect_fit():
     assert np.isclose(r2_score(y, y), 1.0)
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_compare_models_returns_table_sorted_by_first_metric(linear_data):
     from mcm_toolkit.models import compare_models, fit_linear, fit_polynomial