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

docs/ouroboros/80_implementation_audit.md

@@ -35,7 +35,7 @@ Updated: 2026-03-02
 | REQ-V2-004 | 4중 청산 로직 (Hard/BE/ATR Trailing/Model) | `src/strategy/exit_rules.py` | ⚠️ 부분 (`#369`) |
 | REQ-V2-005 | Triple Barrier 라벨링 | `src/analysis/triple_barrier.py` | ✅ 완료 |
 | REQ-V2-006 | Walk-Forward + Purge/Embargo 검증 | `src/analysis/walk_forward_split.py` | ✅ 완료 |
-| REQ-V2-007 | 비용/슬리피지/체결실패 모델 필수 | `src/analysis/backtest_cost_guard.py` | ⚠️ 부분 (`#368`) |
+| REQ-V2-007 | 비용/슬리피지/체결실패 모델 필수 | `src/analysis/backtest_cost_guard.py`, `src/analysis/backtest_pipeline.py` | ✅ 완료 |
 | REQ-V2-008 | Kill Switch 실행 순서 (Block→Cancel→Refresh→Reduce→Snapshot) | `src/core/kill_switch.py` | ⚠️ 부분 (`#377`) |
 
 ### 1.3 v3 구현 상태: 부분 완료 (2026-03-02 기준)

src/analysis/backtest_cost_guard.py

@@ -11,6 +11,7 @@ class BacktestCostModel:
     commission_bps: float | None = None
     slippage_bps_by_session: dict[str, float] | None = None
     failure_rate_by_session: dict[str, float] | None = None
+    partial_fill_rate_by_session: dict[str, float] | None = None
     unfavorable_fill_required: bool = True
 
 
@@ -31,6 +32,7 @@ def validate_backtest_cost_model(
 
     slippage = model.slippage_bps_by_session or {}
     failure = model.failure_rate_by_session or {}
+    partial = model.partial_fill_rate_by_session or {}
 
     missing_slippage = [s for s in required_sessions if s not in slippage]
     if missing_slippage:
@@ -43,6 +45,12 @@ def validate_backtest_cost_model(
         raise ValueError(
             f"missing failure_rate_by_session for sessions: {', '.join(missing_failure)}"
         )
+    missing_partial = [s for s in required_sessions if s not in partial]
+    if missing_partial:
+        raise ValueError(
+            "missing partial_fill_rate_by_session for sessions: "
+            f"{', '.join(missing_partial)}"
+        )
 
     for sess, bps in slippage.items():
         if not math.isfinite(bps) or bps < 0:
@@ -50,3 +58,6 @@ def validate_backtest_cost_model(
     for sess, rate in failure.items():
         if not math.isfinite(rate) or rate < 0 or rate > 1:
             raise ValueError(f"failure rate must be within [0,1] for session={sess}")
+    for sess, rate in partial.items():
+        if not math.isfinite(rate) or rate < 0 or rate > 1:
+            raise ValueError(f"partial fill rate must be within [0,1] for session={sess}")

src/analysis/backtest_pipeline.py

@@ -13,6 +13,11 @@ from statistics import mean
 from typing import Literal, cast
 
 from src.analysis.backtest_cost_guard import BacktestCostModel, validate_backtest_cost_model
+from src.analysis.backtest_execution_model import (
+    BacktestExecutionModel,
+    ExecutionAssumptions,
+    ExecutionRequest,
+)
 from src.analysis.triple_barrier import TripleBarrierSpec, label_with_triple_barrier
 from src.analysis.walk_forward_split import WalkForwardFold, generate_walk_forward_splits
 
@@ -50,6 +55,10 @@ class BacktestFoldResult:
     train_label_distribution: dict[int, int]
     test_label_distribution: dict[int, int]
     baseline_scores: list[BaselineScore]
+    execution_adjusted_avg_return_bps: float
+    execution_adjusted_trade_count: int
+    execution_rejected_count: int
+    execution_partial_count: int
 
 
 @dataclass(frozen=True)
@@ -84,6 +93,14 @@ def run_v2_backtest_pipeline(
         else sorted({bar.session_id for bar in bars})
     )
     validate_backtest_cost_model(model=cost_model, required_sessions=resolved_sessions)
+    execution_model = BacktestExecutionModel(
+        ExecutionAssumptions(
+            slippage_bps_by_session=cost_model.slippage_bps_by_session or {},
+            failure_rate_by_session=cost_model.failure_rate_by_session or {},
+            partial_fill_rate_by_session=cost_model.partial_fill_rate_by_session or {},
+            seed=0,
+        )
+    )
 
     highs = [float(bar.high) for bar in bars]
     lows = [float(bar.low) for bar in bars]
@@ -131,6 +148,26 @@ def run_v2_backtest_pipeline(
         test_labels = [ordered_labels[i] for i in fold.test_indices]
         if not test_labels:
             continue
+        execution_returns_bps: list[float] = []
+        execution_rejected = 0
+        execution_partial = 0
+        for rel_idx in fold.test_indices:
+            entry_bar_index = normalized_entries[rel_idx]
+            bar = bars[entry_bar_index]
+            trade = _simulate_execution_adjusted_return_bps(
+                execution_model=execution_model,
+                bar=bar,
+                label=ordered_labels[rel_idx],
+                side=side,
+                spec=triple_barrier_spec,
+                commission_bps=float(cost_model.commission_bps or 0.0),
+            )
+            if trade["status"] == "REJECTED":
+                execution_rejected += 1
+                continue
+            execution_returns_bps.append(float(trade["return_bps"]))
+            if trade["status"] == "PARTIAL":
+                execution_partial += 1
         fold_results.append(
             BacktestFoldResult(
                 fold_index=fold_idx,
@@ -146,6 +183,12 @@ def run_v2_backtest_pipeline(
                         accuracy=_score_constant(_m1_pred(train_labels), test_labels),
                     ),
                 ],
+                execution_adjusted_avg_return_bps=(
+                    mean(execution_returns_bps) if execution_returns_bps else 0.0
+                ),
+                execution_adjusted_trade_count=len(execution_returns_bps),
+                execution_rejected_count=execution_rejected,
+                execution_partial_count=execution_partial,
             )
         )
 
@@ -198,3 +241,58 @@ def _build_run_id(*, n_entries: int, n_folds: int, sessions: Sequence[str]) -> s
 def fold_has_leakage(fold: WalkForwardFold) -> bool:
     """Utility for tests/verification: True when train/test overlap exists."""
     return bool(set(fold.train_indices).intersection(fold.test_indices))
+
+
+def _simulate_execution_adjusted_return_bps(
+    *,
+    execution_model: BacktestExecutionModel,
+    bar: BacktestBar,
+    label: int,
+    side: int,
+    spec: TripleBarrierSpec,
+    commission_bps: float,
+) -> dict[str, float | str]:
+    qty = 100
+    entry_req = ExecutionRequest(
+        side="BUY" if side == 1 else "SELL",
+        session_id=bar.session_id,
+        qty=qty,
+        reference_price=float(bar.close),
+    )
+    entry_fill = execution_model.simulate(entry_req)
+    if entry_fill.status == "REJECTED":
+        return {"status": "REJECTED", "return_bps": 0.0}
+
+    exit_qty = entry_fill.filled_qty
+    if label == 1:
+        gross_return_bps = spec.take_profit_pct * 10000.0
+    elif label == -1:
+        gross_return_bps = -spec.stop_loss_pct * 10000.0
+    else:
+        gross_return_bps = 0.0
+
+    if side == 1:
+        exit_price = float(bar.close) * (1.0 + gross_return_bps / 10000.0)
+    else:
+        exit_price = float(bar.close) * (1.0 - gross_return_bps / 10000.0)
+
+    exit_req = ExecutionRequest(
+        side="SELL" if side == 1 else "BUY",
+        session_id=bar.session_id,
+        qty=exit_qty,
+        reference_price=max(0.01, exit_price),
+    )
+    exit_fill = execution_model.simulate(exit_req)
+    if exit_fill.status == "REJECTED":
+        return {"status": "REJECTED", "return_bps": 0.0}
+
+    fill_ratio = min(entry_fill.filled_qty, exit_fill.filled_qty) / qty
+    cost_bps = (
+        float(entry_fill.slippage_bps)
+        + float(exit_fill.slippage_bps)
+        + (2.0 * float(commission_bps))
+    )
+    net_return_bps = (gross_return_bps * fill_ratio) - cost_bps
+    is_partial = entry_fill.status == "PARTIAL" or exit_fill.status == "PARTIAL"
+    status = "PARTIAL" if is_partial else "FILLED"
+    return {"status": status, "return_bps": net_return_bps}

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

workflow/session-handover.md

@@ -89,3 +89,19 @@
 - next_ticket: #316
 - process_gate_checked: process_ticket=#306,#308 merged_to_feature_branch=yes
 - risks_or_notes: 모니터 판정을 liveness 중심에서 policy invariant(FORBIDDEN) 중심으로 전환
+
+### 2026-03-01 | session=codex-v3-stream-next-ticket
+- branch: feature/v3-session-policy-stream
+- docs_checked: docs/workflow.md, docs/commands.md, docs/agent-constraints.md
+- open_issues_reviewed: #368, #369, #370, #371, #374, #375, #376, #377, #381
+- next_ticket: #368
+- process_gate_checked: process_ticket=#306,#308 merged_to_feature_branch=yes
+- risks_or_notes: 비블로킹 소견은 합당성(정확성/안정성/유지보수성) 기준으로 반영하고, 미반영 시 근거를 코멘트로 남긴다.
+
+### 2026-03-01 | session=codex-issue368-start
+- branch: feature/issue-368-backtest-cost-execution
+- docs_checked: docs/workflow.md, docs/commands.md, docs/agent-constraints.md
+- open_issues_reviewed: #368
+- next_ticket: #368
+- process_gate_checked: process_ticket=#306,#308 merged_to_feature_branch=yes
+- risks_or_notes: TASK-V2-012 구현 갭 보완을 위해 cost guard + execution-adjusted fold metric + 회귀 테스트를 함께 반영한다.