analysis: apply execution-adjusted cost model in v2 backtest pipeline (#368)

tests/test_backtest_cost_guard.py

@@ -10,6 +10,7 @@ def test_valid_backtest_cost_model_passes() -> None:
         commission_bps=5.0,
         slippage_bps_by_session={"KRX_REG": 10.0, "US_PRE": 50.0},
         failure_rate_by_session={"KRX_REG": 0.01, "US_PRE": 0.08},
+        partial_fill_rate_by_session={"KRX_REG": 0.1, "US_PRE": 0.2},
         unfavorable_fill_required=True,
     )
     validate_backtest_cost_model(model=model, required_sessions=["KRX_REG", "US_PRE"])
@@ -20,6 +21,7 @@ def test_missing_required_slippage_session_raises() -> None:
         commission_bps=5.0,
         slippage_bps_by_session={"KRX_REG": 10.0},
         failure_rate_by_session={"KRX_REG": 0.01, "US_PRE": 0.08},
+        partial_fill_rate_by_session={"KRX_REG": 0.1, "US_PRE": 0.2},
         unfavorable_fill_required=True,
     )
     with pytest.raises(ValueError, match="missing slippage_bps_by_session.*US_PRE"):
@@ -31,6 +33,7 @@ def test_missing_required_failure_rate_session_raises() -> None:
         commission_bps=5.0,
         slippage_bps_by_session={"KRX_REG": 10.0, "US_PRE": 50.0},
         failure_rate_by_session={"KRX_REG": 0.01},
+        partial_fill_rate_by_session={"KRX_REG": 0.1, "US_PRE": 0.2},
         unfavorable_fill_required=True,
     )
     with pytest.raises(ValueError, match="missing failure_rate_by_session.*US_PRE"):
@@ -42,6 +45,7 @@ def test_invalid_failure_rate_range_raises() -> None:
         commission_bps=5.0,
         slippage_bps_by_session={"KRX_REG": 10.0},
         failure_rate_by_session={"KRX_REG": 1.2},
+        partial_fill_rate_by_session={"KRX_REG": 0.1},
         unfavorable_fill_required=True,
     )
     with pytest.raises(ValueError, match="failure rate must be within"):
@@ -53,6 +57,7 @@ def test_unfavorable_fill_requirement_cannot_be_disabled() -> None:
         commission_bps=5.0,
         slippage_bps_by_session={"KRX_REG": 10.0},
         failure_rate_by_session={"KRX_REG": 0.02},
+        partial_fill_rate_by_session={"KRX_REG": 0.1},
         unfavorable_fill_required=False,
     )
     with pytest.raises(ValueError, match="unfavorable_fill_required must be True"):
@@ -65,6 +70,7 @@ def test_non_finite_commission_rejected(bad_commission: float) -> None:
         commission_bps=bad_commission,
         slippage_bps_by_session={"KRX_REG": 10.0},
         failure_rate_by_session={"KRX_REG": 0.02},
+        partial_fill_rate_by_session={"KRX_REG": 0.1},
         unfavorable_fill_required=True,
     )
     with pytest.raises(ValueError, match="commission_bps"):
@@ -77,7 +83,33 @@ def test_non_finite_slippage_rejected(bad_slippage: float) -> None:
         commission_bps=5.0,
         slippage_bps_by_session={"KRX_REG": bad_slippage},
         failure_rate_by_session={"KRX_REG": 0.02},
+        partial_fill_rate_by_session={"KRX_REG": 0.1},
         unfavorable_fill_required=True,
     )
     with pytest.raises(ValueError, match="slippage bps"):
         validate_backtest_cost_model(model=model, required_sessions=["KRX_REG"])
+
+
+def test_missing_required_partial_fill_session_raises() -> None:
+    model = BacktestCostModel(
+        commission_bps=5.0,
+        slippage_bps_by_session={"KRX_REG": 10.0, "US_PRE": 50.0},
+        failure_rate_by_session={"KRX_REG": 0.01, "US_PRE": 0.08},
+        partial_fill_rate_by_session={"KRX_REG": 0.1},
+        unfavorable_fill_required=True,
+    )
+    with pytest.raises(ValueError, match="missing partial_fill_rate_by_session.*US_PRE"):
+        validate_backtest_cost_model(model=model, required_sessions=["KRX_REG", "US_PRE"])
+
+
+@pytest.mark.parametrize("bad_rate", [-0.1, 1.1, float("nan")])
+def test_invalid_partial_fill_rate_range_raises(bad_rate: float) -> None:
+    model = BacktestCostModel(
+        commission_bps=5.0,
+        slippage_bps_by_session={"KRX_REG": 10.0},
+        failure_rate_by_session={"KRX_REG": 0.02},
+        partial_fill_rate_by_session={"KRX_REG": bad_rate},
+        unfavorable_fill_required=True,
+    )
+    with pytest.raises(ValueError, match="partial fill rate must be within"):
+        validate_backtest_cost_model(model=model, required_sessions=["KRX_REG"])

tests/test_backtest_pipeline_integration.py

@@ -35,6 +35,7 @@ def _cost_model() -> BacktestCostModel:
         commission_bps=3.0,
         slippage_bps_by_session={"KRX_REG": 10.0, "US_PRE": 50.0},
         failure_rate_by_session={"KRX_REG": 0.01, "US_PRE": 0.08},
+        partial_fill_rate_by_session={"KRX_REG": 0.1, "US_PRE": 0.2},
         unfavorable_fill_required=True,
     )
 
@@ -71,6 +72,9 @@ def test_pipeline_happy_path_returns_fold_and_artifact_contract() -> None:
         assert names == {"B0", "B1", "M1"}
         for score in fold.baseline_scores:
             assert 0.0 <= score.accuracy <= 1.0
+        assert fold.execution_adjusted_trade_count >= 0
+        assert fold.execution_rejected_count >= 0
+        assert fold.execution_partial_count >= 0
 
 
 def test_pipeline_cost_guard_fail_fast() -> None:
@@ -78,6 +82,7 @@ def test_pipeline_cost_guard_fail_fast() -> None:
         commission_bps=3.0,
         slippage_bps_by_session={"KRX_REG": 10.0},
         failure_rate_by_session={"KRX_REG": 0.01},
+        partial_fill_rate_by_session={"KRX_REG": 0.1},
         unfavorable_fill_required=True,
     )
     try:
@@ -166,3 +171,56 @@ def test_pipeline_rejects_minutes_spec_when_timestamp_missing() -> None:
         assert "BacktestBar.timestamp is required" in str(exc)
     else:
         raise AssertionError("expected timestamp validation error")
+
+
+def test_pipeline_execution_adjusted_returns_reflect_cost_and_fill_assumptions() -> None:
+    base_cfg = dict(
+        bars=_bars(),
+        entry_indices=[0, 1, 2, 3, 4, 5, 6, 7],
+        side=1,
+        triple_barrier_spec=TripleBarrierSpec(
+            take_profit_pct=0.02,
+            stop_loss_pct=0.01,
+            max_holding_minutes=3,
+        ),
+        walk_forward=WalkForwardConfig(
+            train_size=4,
+            test_size=2,
+            step_size=2,
+            purge_size=1,
+            embargo_size=1,
+            min_train_size=3,
+        ),
+    )
+
+    optimistic = BacktestCostModel(
+        commission_bps=0.0,
+        slippage_bps_by_session={"KRX_REG": 0.0, "US_PRE": 0.0},
+        failure_rate_by_session={"KRX_REG": 0.0, "US_PRE": 0.0},
+        partial_fill_rate_by_session={"KRX_REG": 0.0, "US_PRE": 0.0},
+        unfavorable_fill_required=True,
+    )
+    conservative = BacktestCostModel(
+        commission_bps=10.0,
+        slippage_bps_by_session={"KRX_REG": 20.0, "US_PRE": 60.0},
+        failure_rate_by_session={"KRX_REG": 0.2, "US_PRE": 0.4},
+        partial_fill_rate_by_session={"KRX_REG": 0.5, "US_PRE": 0.7},
+        unfavorable_fill_required=True,
+    )
+
+    opt_out = run_v2_backtest_pipeline(cost_model=optimistic, **base_cfg)
+    cons_out = run_v2_backtest_pipeline(cost_model=conservative, **base_cfg)
+
+    opt_avg = sum(
+        f.execution_adjusted_avg_return_bps for f in opt_out.folds
+    ) / len(opt_out.folds)
+    cons_avg = sum(
+        f.execution_adjusted_avg_return_bps for f in cons_out.folds
+    ) / len(cons_out.folds)
+    assert cons_avg < opt_avg
+
+    opt_trades = sum(f.execution_adjusted_trade_count for f in opt_out.folds)
+    cons_trades = sum(f.execution_adjusted_trade_count for f in cons_out.folds)
+    cons_rejected = sum(f.execution_rejected_count for f in cons_out.folds)
+    assert cons_trades <= opt_trades
+    assert cons_rejected >= 0