Merge remote-tracking branch 'origin/main' into codex/research-artifact-contract-20260821

README.md

@@ -10,7 +10,7 @@
 
 | 仓库 | 角色 |
 |---|---|
-| `quant_engine` | **纯回测核心**（alpha + execution + indicators + data_adapter + backtest + metrics） |
+| `quant_engine` | **纯研究核心**（alpha + execution + ledger + attribution + risk + metrics） |
 | `research_results` | 业务集成（47 个 proj 调度 + 注册 + 平台对接） |
 | `tushare2db_pro_aoge` | 数据层（行情 ELT） |
 | `research_platform` | 展示层（FastAPI + Next.js） |
@@ -19,14 +19,18 @@
 ## 模块
 
 - `alpha_factors` — 158 alpha 公式 + 24 基础算子（移植自 qlib alpha158）
-- `execution` — 执行仿真（成本/滑点/T+1/涨跌停/部分成交/价差）+ 多日 NAV + PnL 拆解（借鉴 hikyuu 部件化思想）
+- `execution` — A 股长仓执行仿真（成本/滑点/现金约束）+ 稀疏调仓/完整交易日 Ledger + 可投影成交与 NAV 审计；T+1、涨跌停、成交量与价差提供独立约束函数
 - `indicators` — 50+ 技术指标（MACD / KDJ / 布林 / ATR / ADX / 等）
 - `data_adapter` — 桥接 qtdb_pro 长表与新模块（rename / long-wide / 复权 / vwap 代理）
 - `backtest` — weight-based 多日仿真（rebalance_table / compute_nav / compare_to_benchmark）
-- `metrics` — 绩效（年化收益 / 波动率 / Sharpe / 最大回撤 / Calmar）
+- `portfolio_construction` — 多期因子分数 → Top-K → 等权目标权重表
+- `research_pipeline` — 因子日 → 下一真实交易日 → 显式执行价 → 日末估值 → 成本后绩效（防前视编排）
+- `artifact` — 版本化、确定性、存储中立的完整 research run 事实表与 manifest
+- `attribution` — 基于实际成交后持仓的隔夜 / 日内 / 交易成本逐日收益归因与闭合审计
+- `metrics` — 绝对绩效 + 严格日期对齐的 TE / IR / alpha / beta 基准相对绩效
 - `factor_library` — 通用方法（turnover / winsorize / IC / OLS / jb_test）
 - `portfolio_decomp` — 组合分解（risk_parity / mean_variance / 因子归因）
-- `risk` — 风险指标（边际 / 风险贡献）
+- `risk` — ndarray 低层风险公式 + 标签安全、可分组的 Euler 成分风险分解
 - `perf_stats` — 详细绩效（与 metrics 并存）
 - `logging` — 统一 logger（标准库 + 可选 loguru）
 
@@ -58,8 +62,13 @@ ruff check src/ tests/    # lint
 ```python
 from quant_engine.alpha_factors import alpha_001, alpha_005, ALPHA158_REGISTRY
 from quant_engine.execution import (
-    ExecutionConfig, simulate_with_daily_data, compute_realized_pnl,
+    ExecutionConfig, simulate_daily_ledger_with_audit,
+    simulate_multi_day_with_audit, simulate_with_daily_data,
 )
+from quant_engine.research_pipeline import (
+    run_factor_backtest_research, run_factor_execution_research,
+)
+from quant_engine.backtest import run_weight_backtest
 from quant_engine.indicators import macd, bollinger, kdj
 from quant_engine.data_adapter import (
     long_to_wide, wide_to_long, rename_tushare_columns,
@@ -70,8 +79,116 @@ from quant_engine.data_adapter import (
 
 # 端到端：qtdb_pro 长表 → 适配 → alpha158 → execution
 df = load_qtdb_daily(["000001.SZ"], "2024-01-01", with_adj=True)
-prices, volumes = prepare_execution_inputs(df)
+close_prices, volumes = prepare_execution_inputs(df)
-result = simulate_with_daily_data(prices, initial_cash=1_000_000.0)
+open_prices, _ = prepare_execution_inputs(df, price_col="open")
+result = simulate_with_daily_data(close_prices, initial_cash=1_000_000.0)
+
+# 已正确滞后的目标权重 → 现金约束执行 → 唯一来源的成交/拒绝/日末持仓/NAV
+execution = simulate_multi_day_with_audit(
+    target_weights_history=[
+        ("2024-01-02", {"000001.SZ": 1.0}),
+        ("2024-01-03", {"000001.SZ": 1.0}),
+    ],
+    price_history=[
+        ("2024-01-02", {"000001.SZ": 10.0}),
+        ("2024-01-03", {"000001.SZ": 10.5}),
+    ],
+    initial_cash=1_000_000.0,
+    config=ExecutionConfig(),
+)
+print(execution.nav_series)
+print(execution.daily_executions)
+
+# 多期因子分数（必须是 point-in-time 数据）→ Top-K → 下一交易日 open 执行
+factor_execution = run_factor_execution_research(
+    factor_scores,
+    top_k=20,
+    execution_prices=open_prices,
+    execution_price_field="open",
+    initial_cash=1_000_000.0,
+)
+
+# 推荐研究入口：同一交易日历上显式区分 open 成交和 close 估值。
+# 因子日保持现金，下一交易日成交后的真实持仓才参与当日收盘收益。
+factor_backtest = run_factor_backtest_research(
+    factor_scores,
+    top_k=20,
+    execution_prices=open_prices,
+    valuation_prices=close_prices,
+    execution_price_field="open",
+    valuation_price_field="close",
+    initial_cash=1_000_000.0,
+    config=ExecutionConfig(),
+)
+print(factor_backtest.nav)
+print(factor_backtest.returns)
+print(factor_backtest.stats())
+print(factor_backtest.execution.ledger_frame)
+print(factor_backtest.execution.trades_frame)
+print(factor_backtest.position_weights)  # 实际日末资产权重
+print(factor_backtest.cash_weights)
+
+# 所有分析都以实际成交后的 Ledger 为事实源，不直接使用目标权重伪造结果。
+attribution = factor_backtest.return_attribution()
+print(attribution.asset_contributions)
+print(attribution.transaction_cost)
+print(attribution.residual)  # 应接近 0；否则说明贡献未闭合到账本收益
+
+# benchmark_returns 必须与成本后 factor_backtest.returns 使用完全相同的日期索引。
+print(factor_backtest.benchmark_stats(benchmark_returns))
+
+# 下游稳定交付：显式提供代码版本、数据快照和时区，不在核心层写数据库。
+from quant_engine.artifact import build_research_run_artifact
+from quant_engine.data_adapter import prepare_asset_return_snapshot
+from quant_engine.risk import estimate_covariance_snapshot
+
+risk_date = factor_backtest.position_weights.index[-1].date()
+market_snapshot = prepare_asset_return_snapshot(
+    qtdb_daily_long,
+    source="qtdb_pro.hq_daily",
+    source_snapshot_id="<upstream-ingestion-snapshot-id>",
+    adjustment="qfq",
+)
+risk_snapshot = estimate_covariance_snapshot(
+    market_snapshot.returns,
+    as_of_date=risk_date,
+    lookback_sessions=252,
+    min_observations=120,
+    data_snapshot_id=market_snapshot.data_snapshot_id,
+)
+
+artifact = build_research_run_artifact(
+    factor_backtest,
+    run_id="research-run-001",
+    strategy_id="alpha-top20",
+    strategy_name="Alpha Top 20",
+    strategy_version="1.0.0",
+    engine_version="1.2.0",
+    code_revision="<git-sha>",
+    data_snapshot_id=market_snapshot.data_snapshot_id,
+    calendar="CN-A",
+    timezone="Asia/Shanghai",
+    started_at="2026-08-21T10:00:00+08:00",
+    finished_at="2026-08-21T10:01:00+08:00",
+    parameters={"top_k": 20, "lag_sessions": 1},
+    benchmark_id="000300.SH",
+    benchmark_returns=benchmark_returns,
+    risk_snapshots={risk_date: risk_snapshot},
+)
+print(artifact.manifest())
+
+# run_weight_backtest 是低层算子：只接受收益区间开始前已经生效的持仓权重。
+# 不要把 signal-date 的 factor_scores/decision_weights 直接传给它。
+backtest = run_weight_backtest(
+    weights=effective_holding_weights,
+    stock_returns=daily_returns,
+    initial_capital=1_000_000.0,
+    benchmark_nav=benchmark_nav,
+)
+print(factor_execution.schedule.signal_to_execution)
+print(factor_execution.execution.daily_executions)
+print(backtest.stats())
+print(backtest.benchmark_report())
 ```
 
 ## 与 research_results 的关系

docs/OPEN_SOURCE_REFERENCES.md

@@ -0,0 +1,64 @@
+# Open-source design references
+
+本项目采用“借鉴稳定语义、保留轻量实现”的策略。引入新量化能力前先检查成熟
+开源案例；除非维护成本和许可证收益明确优于本地小型实现，否则不增加框架级依赖。
+
+## 2026-08-21：成交后归因与相对绩效
+
+| 项目 | 借鉴内容 | 当前决策 |
+|---|---|---|
+| [Qlib](https://github.com/microsoft/qlib) | 信号时间与交易时间分离、成本前后超额收益分开报告 | 借鉴语义；不引入完整框架 |
+| [Zipline](https://github.com/quantopian/zipline) | Ledger / transaction / portfolio value 状态模型 | 以现有 `ExecutionSimulationResult` 承担事实源 |
+| [empyrical](https://github.com/quantopian/empyrical) | beta 协方差口径、alpha 几何年化、年化因子 | 移植小型公式；不增加老旧运行时依赖 |
+| [Riskfolio-Lib](https://github.com/dcajasn/Riskfolio-Lib) | Euler component risk 与分组/因子风险贡献 | 只实现当前需要的 pandas/numpy 标签安全封装 |
+| [PyPortfolioOpt](https://github.com/PyPortfolio/PyPortfolioOpt) | 协方差估计与优化器解耦 | 留作未来风险模型适配器参考 |
+
+当前核心不新增依赖。逐日收益归因必须从实际换仓前后持仓、成交记录、执行价和
+收盘估值推导；因子分数与目标权重只是意图，不能作为成交后归因事实源。
+
+## 2026-08-21：研究运行工件
+
+- 借鉴 [Qlib Recorder / RecordTemplate](https://github.com/microsoft/qlib/blob/main/qlib/workflow/record_temp.py)
+  将 signal、portfolio analysis 和 risk analysis 分成稳定事实，但不引入 Qlib 运行时；
+- 借鉴 [MLflow Tracking](https://mlflow.org/docs/latest/tracking/) 的 run / params /
+  metrics / artifacts 分层，但 MLflow 只保留为未来可选 exporter；
+- HTML、PNG 和 tearsheet 是可再生展示物，不能替代 NAV、成交、持仓、归因和绩效事实。
+
+因此 `ResearchRunArtifact` 使用显式 `schema_version`、`config_hash`、代码版本和数据
+快照身份，并提供确定性 JSON / SHA-256 manifest；核心层仍不写数据库或 artifact store。
+
+schema `1.1.0` 将 Qlib 的独立 risk-analysis artifact 思路与 Riskfolio-Lib 的 Euler
+component-risk 语义结合，但只保留本项目需要的轻量合同：协方差快照必须声明
+`snapshot_id`、`as_of_date`、收益频率和年化期数；风险从成交后的实际日末持仓计算，
+component risk 闭合到年化组合波动，percentage contribution 闭合到 1。未来日期、资产
+标签不完整和零方差组合都直接失败，不以默认值伪造结果。
+
+## 2026-08-21：协方差快照估计
+
+| 项目 | 借鉴内容 | 当前决策 |
+|---|---|---|
+| [PyPortfolioOpt risk models](https://github.com/PyPortfolio/PyPortfolioOpt/blob/main/pypfopt/risk_models.py) | 将收益输入、协方差估计器和组合优化解耦；sample / EWM / shrinkage 使用统一标签输出 | 借鉴可替换估计器边界，不引入完整包 |
+| [scikit-learn covariance](https://github.com/scikit-learn/scikit-learn/blob/main/sklearn/covariance/_shrunk_covariance.py) | 维护成熟的 Ledoit–Wolf / OAS shrinkage 实现 | 未来作为可选 adapter；不复制统计公式 |
+| [Qlib structured risk model](https://github.com/microsoft/qlib/blob/main/qlib/model/riskmodel/structured.py) | PCA/FA 结构化协方差和固定随机状态 | 留作因子风险模型阶段，不进入当前 baseline |
+
+当前 `estimate_covariance_snapshot` 只编排 pandas 的 sample covariance：先按 `as_of_date`
+截断，再取固定 session 窗口，使用 complete-case 行并拒绝历史不足；禁止 pandas 默认的
+pairwise 样本集合产生含义不一致的矩阵。snapshot ID 对窗口数据、缺失掩码、上游数据
+快照身份和估计参数做 SHA-256，追加未来数据不会改变历史快照。
+
+市场适配层现以 `AssetReturnSnapshot` 固化 simple-return 输入：上游 ingestion snapshot ID、
+数据源、价格字段、复权口径、规范化价格值和缺失掩码共同形成内容寻址 ID；不前向填充
+停牌/缺失价格。该 ID 同时传入协方差快照和研究运行工件，避免同一研究链出现两套数据
+身份。
+
+可选 shrinkage adapter 的评估结论是“保留边界，暂不实现”：当前运行依赖没有声明
+scikit-learn，本切片也不修改版本或锁文件。未来只有在依赖治理接受后，才以延迟导入
+直接调用 scikit-learn 的 `LedoitWolf` / `OAS`，并让估计器名称、库版本与参数进入
+snapshot identity；不复制成熟统计公式，也不让环境中偶然存在的包改变 baseline 行为。
+
+## hikyuu 的定位
+
+[hikyuu](https://github.com/fasiondog/hikyuu) 的 SG / MM / CN / PG 部件化思想、
+A 股交易约束和系统组合方式仍有借鉴价值；但其完整 C++/Python 运行时、对象模型和
+数据体系不适合作为本项目核心依赖。当前原则是按真实研究链路吸收边界设计，不复制
+其框架层级，也不为了“架构完整”预先建设尚无端到端需求的抽象。

docs/handoff/2026-08-21-ledger-attribution.md

@@ -0,0 +1,42 @@
+# Ledger-backed attribution handoff
+
+## Goal
+
+在 `ExecutionSimulationResult` 日频 Ledger 之上增加轻量、可审计的成交后分析层：
+
+- 逐日隔夜 / 日内资产收益贡献；
+- 佣金、印花税、滑点成本独立贡献；
+- 贡献闭合到成本后日收益并显式暴露 residual；
+- 严格日期对齐的 TE / IR / alpha / beta；
+- 标签安全且可分组的 Euler component risk。
+- 从 Ledger 股数和收盘估值投影的实际资产 / 现金权重。
+
+## Branch stack
+
+- 当前：`codex/ledger-attribution-20260821`
+- 基线：`codex/post-execution-ledger-20260821`
+- 再下层：`codex/core-contracts-20260821`（PR #2，尚待用户确认合并）
+
+本分支不得直接合并到 `main`。应按上述顺序逐层审阅；未经用户明确确认，不得合并
+L2 PR。
+
+## Open-source decision
+
+调研结论记录在 `docs/OPEN_SOURCE_REFERENCES.md`。Qlib、Zipline、empyrical、
+Riskfolio-Lib 和 PyPortfolioOpt 只作为时间语义、Ledger、相对指标与 Euler 风险贡献
+的设计参考；本阶段没有新增运行时依赖。
+
+## Verification
+
+- `pytest -q --cov=src --cov-report=term-missing`: 514 passed，9 个既有 SciPy warning，91% coverage；
+- `mypy --strict src/`: 15 source files passed；
+- 变更范围 `ruff check`: passed；
+- 全仓 Ruff：仅 13 个既有 `tests/governance/*` PT009；
+- workspace verify/status：passed，预期提示 quant_engine 非 main；
+- global Gitea workflow check：passed，23 个无关仓库 warning。
+
+## Next action
+
+先按堆叠顺序审阅 PR。基础 Ledger 分支完成后，再将本分支 rebase 到其最终提交，
+运行唯一一次 `ship --ready`；随后将稳定输出适配到 `research_results` 与
+`research_platform`，不要在核心层直接写数据库。

docs/handoff/2026-08-21-post-execution-ledger.md

@@ -0,0 +1,33 @@
+# Post-execution daily Ledger handoff
+
+## 状态
+
+- 分支：`codex/post-execution-ledger-20260821`
+- 基线：`codex/core-contracts-20260821`（PR #2，尚未获用户确认合并）
+- 本分支不得直接合并到 `main`；先等待 PR #2 合并，再整理基线并创建独立 PR。
+- 无账户、券商、数据库或实盘副作用。
+
+## 已完成
+
+- 新增稀疏调仓、完整交易日估值的 `simulate_daily_ledger_with_audit()`。
+- 显式分离 execution price 与 valuation price，支持下一日 open 成交、当日 close 估值。
+- 成交记录补齐 `side / quantity / price`，并提供 `trades_frame`。
+- 提供平台中立的 `ledger_frame`，不携带 `run_id`，不写数据库。
+- 新增 `run_factor_backtest_research()`：PIT 因子、下一交易日执行、日频 NAV、首日成本收益和标准绩效。
+- 研究区间从首条有效信号日开始，排除因子预热行情对绩效的稀释。
+
+## 验证
+
+- `pytest -q --cov=src --cov-report=term-missing`：500 passed，total coverage 91%。
+- `mypy --strict src/`：14 source files passed。
+- 本阶段文件 scoped Ruff：passed。
+- 全仓 Ruff：仅既有 governance tests 的 13 个 PT009 基线问题。
+- workspace verify/status：通过；仅提示功能分支不是引导基线 `main`。
+- 全局 Gitea workflow check：通过，23 个既有警告。
+
+## 继续步骤
+
+1. 获得用户对 PR #2 的明确合并确认并按 L2 流程合并。
+2. 将本分支整理到更新后的 `main`，重新运行相同全量验证。
+3. 为 Ledger 阶段创建独立 PR，执行唯一一次最终 `ship --ready`，等待用户确认合并。
+4. 后续在 `research_results` 增加业务投影适配器，再由 `research_platform` 持久化和展示；核心层继续保持无数据库写入。

docs/handoff/2026-08-21-research-artifact-contract.md

@@ -0,0 +1,57 @@
+# Research artifact contract handoff
+
+## Goal
+
+把完整可信研究链固化成存储中立、版本化、确定性的 `ResearchRunArtifact`，供
+`research_results` 持久化和 `research_platform` 查询：
+
+- run identity / schema version / config hash / code revision / data snapshot；
+- signal scores / decision weights / signal-to-execution mapping；
+- NAV / returns / benchmark / costs；
+- trades / realized positions / cash；
+- asset and daily return attribution；
+- performance including Sortino / TE / IR / alpha / beta；
+- reproducible covariance snapshots and annualized Euler component-risk facts；
+- canonical JSON / SHA-256 manifest。
+
+## Branch stack
+
+- 当前：`codex/research-artifact-contract-20260821`
+- 基线：`codex/ledger-attribution-20260821`（Draft PR #4）
+- 下层：Draft PR #3 → Ready PR #2 → `main`
+
+不得绕过堆叠顺序直接合并到 `main`。
+
+## Verification
+
+- `pytest -q`: 540 passed，9 个既有 SciPy warning；
+- data-adapter focused coverage 77%（包含未连接真实 ClickHouse 的 I/O 便捷函数）；
+- `mypy --strict src/`: 16 source files passed；
+- changed-scope Ruff: passed；
+- no runtime dependency added；
+- no database, network, broker or filesystem write side effect in artifact builder。
+- 三仓隔离 ClickHouse 黄金链路通过：市场价格 → return snapshot → covariance → artifact →
+  publisher → reader；使用随机 localhost 端口、tmpfs 和自动容器清理。
+
+## Current risk contract
+
+- artifact schema：`1.1.0`；
+- `CovarianceSnapshot` 对输入矩阵深拷贝并显式记录截至日、频率和年化期数；
+- `risk_snapshots` 按研究交易日映射，可只生成需要的风险观察日；
+- 使用成交后实际持仓，不包含现金风险资产；协方差资产标签必须与研究资产全集一致；
+- `covariance_as_of_date` 不得晚于 `trade_date`；无正组合方差时拒绝产物。
+- `estimate_covariance_snapshot` 从显式数据快照的日收益生成无前视、complete-case、
+  SHA-256 可复现的 per-period sample covariance；不包含 I/O 或未来行。
+- `prepare_asset_return_snapshot` 从规范化长表行情生成不前向填充的 simple daily returns；
+  显式 ingestion snapshot ID、源/字段/复权口径、价格值和缺失掩码共同形成
+  `asset-returns-v1:<sha256>`，并把同一 ID 传给 covariance 与 run artifact。
+- artifact builder fail closed：每个 `CovarianceSnapshot.data_snapshot_id` 必须与 run 级
+  `data_snapshot_id` 完全一致，禁止把其他行情快照的风险分解静默发布到当前研究运行。
+- shrinkage 适配器本轮不实现：scikit-learn 尚非声明依赖，未来只允许薄适配
+  `LedoitWolf` / `OAS`，不复制公式、不依赖环境偶然安装状态。
+
+## Next action
+
+保持 Draft PR #5，不绕过堆叠顺序合并；下游 `research_results` / `research_platform`
+继续在现有 Draft 分支消费同一数据 lineage。下一阶段优先把 ingestion snapshot ID 从
+真实 ELT 元数据接入调用方，再在依赖治理通过后单独交付可选 shrinkage adapter。

src/quant_engine/artifact.py

@@ -0,0 +1,580 @@
+"""Versioned, deterministic research-run artifacts for downstream adapters.
+
+This module is deliberately storage-neutral.  It snapshots a completed
+``FactorBacktestResult`` into queryable fact tables but never writes a database,
+starts a service, or talks to a broker.  ``research_results`` owns persistence;
+``research_platform`` owns read models and presentation.
+"""
+
+from __future__ import annotations
+
+import hashlib
+import json
+import math
+from collections.abc import Mapping
+from dataclasses import dataclass
+from datetime import date, datetime
+from typing import Any
+
+import numpy as np
+import pandas as pd
+
+from quant_engine.research_pipeline import FactorBacktestResult
+from quant_engine.risk import CovarianceSnapshot, labeled_component_risk
+
+RESEARCH_ARTIFACT_SCHEMA_VERSION = "1.1.0"
+
+RISK_COLUMNS = [
+    "run_id",
+    "trade_date",
+    "asset_id",
+    "weight",
+    "marginal_risk",
+    "component_risk",
+    "risk_contribution",
+    "covariance_snapshot_id",
+    "covariance_as_of_date",
+    "risk_measure",
+    "return_frequency",
+    "periods_per_year",
+]
+
+__all__ = [
+    "RESEARCH_ARTIFACT_SCHEMA_VERSION",
+    "ResearchRunArtifact",
+    "build_research_run_artifact",
+]
+
+
+def _frame_copy(frame: pd.DataFrame) -> pd.DataFrame:
+    return frame.copy(deep=True)
+
+
+@dataclass(frozen=True, slots=True, eq=False)
+class ResearchRunArtifact:
+    """Immutable-by-interface snapshot of one completed research run."""
+
+    schema_version: str
+    _run: pd.DataFrame
+    _signals: pd.DataFrame
+    _nav: pd.DataFrame
+    _trades: pd.DataFrame
+    _positions: pd.DataFrame
+    _attribution: pd.DataFrame
+    _attribution_daily: pd.DataFrame
+    _risk: pd.DataFrame
+    _performance: pd.DataFrame
+
+    @property
+    def run(self) -> pd.DataFrame:
+        return _frame_copy(self._run)
+
+    @property
+    def nav(self) -> pd.DataFrame:
+        return _frame_copy(self._nav)
+
+    @property
+    def signals(self) -> pd.DataFrame:
+        return _frame_copy(self._signals)
+
+    @property
+    def trades(self) -> pd.DataFrame:
+        return _frame_copy(self._trades)
+
+    @property
+    def positions(self) -> pd.DataFrame:
+        return _frame_copy(self._positions)
+
+    @property
+    def attribution(self) -> pd.DataFrame:
+        return _frame_copy(self._attribution)
+
+    @property
+    def attribution_daily(self) -> pd.DataFrame:
+        return _frame_copy(self._attribution_daily)
+
+    @property
+    def risk(self) -> pd.DataFrame:
+        return _frame_copy(self._risk)
+
+    @property
+    def performance(self) -> pd.DataFrame:
+        return _frame_copy(self._performance)
+
+    def table_frames(self) -> Mapping[str, pd.DataFrame]:
+        """Return isolated table snapshots keyed by stable logical table name."""
+        return {
+            "run": self.run,
+            "signals": self.signals,
+            "nav": self.nav,
+            "trades": self.trades,
+            "positions": self.positions,
+            "attribution": self.attribution,
+            "attribution_daily": self.attribution_daily,
+            "risk": self.risk,
+            "performance": self.performance,
+        }
+
+    def canonical_json(self) -> str:
+        """Serialize tables deterministically for checksums and artifact storage."""
+        payload = {
+            "schema_version": self.schema_version,
+            "tables": {
+                name: _frame_records(frame)
+                for name, frame in self._internal_table_frames().items()
+            },
+        }
+        return json.dumps(
+            payload,
+            ensure_ascii=False,
+            sort_keys=True,
+            separators=(",", ":"),
+            allow_nan=False,
+        )
+
+    @property
+    def content_sha256(self) -> str:
+        return hashlib.sha256(self.canonical_json().encode("utf-8")).hexdigest()
+
+    def manifest(self) -> Mapping[str, object]:
+        """Return a compact immutable identity and row-count manifest."""
+        return {
+            "schema_version": self.schema_version,
+            "run_id": str(self._run.at[0, "run_id"]),
+            "config_hash": str(self._run.at[0, "config_hash"]),
+            "content_sha256": self.content_sha256,
+            "tables": {
+                name: len(frame) for name, frame in self._internal_table_frames().items()
+            },
+        }
+
+    def _internal_table_frames(self) -> Mapping[str, pd.DataFrame]:
+        return {
+            "run": self._run,
+            "signals": self._signals,
+            "nav": self._nav,
+            "trades": self._trades,
+            "positions": self._positions,
+            "attribution": self._attribution,
+            "attribution_daily": self._attribution_daily,
+            "risk": self._risk,
+            "performance": self._performance,
+        }
+
+
+def _required_text(value: str, name: str, *, max_length: int | None = None) -> str:
+    normalized = value.strip()
+    if not normalized:
+        raise ValueError(f"{name} must be non-empty")
+    if max_length is not None and len(normalized) > max_length:
+        raise ValueError(f"{name} must contain at most {max_length} characters")
+    return normalized
+
+
+def _aware_timestamp(value: str | pd.Timestamp, name: str) -> pd.Timestamp:
+    try:
+        timestamp = pd.Timestamp(value)
+    except (TypeError, ValueError) as error:
+        raise ValueError(f"{name} must be a valid timestamp") from error
+    if timestamp.tzinfo is None:
+        raise ValueError(f"{name} must include a timezone")
+    return timestamp
+
+
+def _json_value(value: object) -> object:
+    if value is None or isinstance(value, str | bool | int):
+        return value
+    if isinstance(value, float):
+        return value if math.isfinite(value) else None
+    if isinstance(value, np.generic):
+        return _json_value(value.item())
+    if isinstance(value, pd.Timestamp):
+        return value.isoformat()
+    if isinstance(value, datetime):
+        return value.isoformat()
+    if isinstance(value, date):
+        return value.isoformat()
+    if isinstance(value, Mapping):
+        return {
+            str(key): _json_value(item)
+            for key, item in sorted(value.items(), key=lambda pair: str(pair[0]))
+        }
+    if isinstance(value, list | tuple):
+        return [_json_value(item) for item in value]
+    raise TypeError(f"value of type {type(value).__name__} is not JSON serializable")
+
+
+def _canonical_mapping_json(values: Mapping[str, object]) -> str:
+    normalized = _json_value(values)
+    return json.dumps(
+        normalized,
+        ensure_ascii=False,
+        sort_keys=True,
+        separators=(",", ":"),
+        allow_nan=False,
+    )
+
+
+def _frame_records(frame: pd.DataFrame) -> list[dict[str, object]]:
+    return [
+        {str(key): _json_value(value) for key, value in row.items()}
+        for row in frame.to_dict(orient="records")
+    ]
+
+
+def _build_nav(
+    result: FactorBacktestResult,
+    run_id: str,
+    benchmark_returns: pd.Series | None,
+) -> pd.DataFrame:
+    nav = result.execution.ledger_frame.copy(deep=True)
+    nav.insert(0, "run_id", run_id)
+    nav["trade_date"] = pd.to_datetime(nav["trade_date"]).dt.date
+    nav["total_cost"] = [
+        sum(execution.total_cost for execution in daily.executions)
+        for daily in result.execution.daily_executions
+    ]
+    if benchmark_returns is None:
+        nav["benchmark_nav"] = np.nan
+        nav["benchmark_return"] = np.nan
+        nav["excess_ret"] = np.nan
+    else:
+        benchmark = benchmark_returns.astype(float, copy=True)
+        nav["benchmark_nav"] = (1.0 + benchmark).cumprod().to_numpy()
+        nav["benchmark_return"] = benchmark.to_numpy()
+        nav["excess_ret"] = result.returns.to_numpy() - benchmark.to_numpy()
+    return nav
+
+
+def _build_signals(result: FactorBacktestResult, run_id: str) -> pd.DataFrame:
+    columns = [
+        "run_id",
+        "signal_date",
+        "execution_date",
+        "asset_id",
+        "factor_score",
+        "target_weight",
+    ]
+    rows: list[dict[str, object]] = []
+    for signal_date, scores in result.factor_scores.iterrows():
+        execution_date = pd.Timestamp(result.schedule.signal_to_execution.at[signal_date]).date()
+        for asset, score in scores.items():
+            rows.append(
+                {
+                    "run_id": run_id,
+                    "signal_date": pd.Timestamp(signal_date).date(),
+                    "execution_date": execution_date,
+                    "asset_id": asset,
+                    "factor_score": float(score),
+                    "target_weight": float(
+                        result.schedule.decision_weights.at[signal_date, asset]
+                    ),
+                }
+            )
+    return pd.DataFrame(rows, columns=columns)
+
+
+def _build_trades(result: FactorBacktestResult, run_id: str) -> pd.DataFrame:
+    trades = result.execution.trades_frame.copy(deep=True)
+    trades.insert(0, "run_id", run_id)
+    trades["trade_date"] = pd.to_datetime(trades["trade_date"]).dt.date
+    trades.insert(
+        1,
+        "trade_id",
+        [f"{run_id}:{sequence:08d}" for sequence in range(1, len(trades) + 1)],
+    )
+    signal_by_execution = {
+        pd.Timestamp(execution_date).date(): pd.Timestamp(signal_date).date()
+        for signal_date, execution_date in result.schedule.signal_to_execution.items()
+    }
+    trades["signal_id"] = [
+        f"{run_id}:signal:{signal_by_execution[trade_date].isoformat()}"
+        for trade_date in trades["trade_date"]
+    ]
+    trades["total_cost"] = trades["fee"] + trades["slippage"]
+    return trades
+
+
+def _build_positions(result: FactorBacktestResult, run_id: str) -> pd.DataFrame:
+    columns = [
+        "run_id",
+        "trade_date",
+        "asset_id",
+        "asset_type",
+        "quantity",
+        "mark_price",
+        "market_value",
+        "weight",
+    ]
+    rows: list[dict[str, object]] = []
+    weights = result.position_weights
+    cash_weights = result.cash_weights
+    for date_value, position in zip(
+        result.valuation_prices.index,
+        result.execution.positions,
+        strict=True,
+    ):
+        session_date = pd.Timestamp(date_value).date()
+        for asset, quantity in position.holdings.items():
+            mark_price = float(result.valuation_prices.at[date_value, asset])
+            rows.append(
+                {
+                    "run_id": run_id,
+                    "trade_date": session_date,
+                    "asset_id": asset,
+                    "asset_type": "security",
+                    "quantity": quantity,
+                    "mark_price": mark_price,
+                    "market_value": quantity * mark_price,
+                    "weight": float(weights.at[date_value, asset]),
+                }
+            )
+        rows.append(
+            {
+                "run_id": run_id,
+                "trade_date": session_date,
+                "asset_id": "CASH",
+                "asset_type": "cash",
+                "quantity": position.cash,
+                "mark_price": 1.0,
+                "market_value": position.cash,
+                "weight": float(cash_weights.at[date_value]),
+            }
+        )
+    return pd.DataFrame(rows, columns=columns)
+
+
+def _build_attribution(
+    result: FactorBacktestResult,
+    run_id: str,
+) -> tuple[pd.DataFrame, pd.DataFrame]:
+    contribution = result.return_attribution()
+    rows: list[dict[str, object]] = []
+    for date_value in contribution.overnight.index:
+        for asset in contribution.overnight.columns:
+            overnight = float(contribution.overnight.at[date_value, asset])
+            intraday = float(contribution.intraday.at[date_value, asset])
+            rows.append(
+                {
+                    "run_id": run_id,
+                    "trade_date": pd.Timestamp(date_value).date(),
+                    "asset_id": asset,
+                    "overnight": overnight,
+                    "intraday": intraday,
+                    "asset_total": overnight + intraday,
+                }
+            )
+    daily = pd.DataFrame(
+        {
+            "run_id": run_id,
+            "trade_date": contribution.total_return.index.date,
+            "transaction_cost": contribution.transaction_cost.to_numpy(),
+            "explained_return": contribution.explained_return.to_numpy(),
+            "residual": contribution.residual.to_numpy(),
+            "total_return": contribution.total_return.to_numpy(),
+        }
+    )
+    return pd.DataFrame(rows), daily
+
+
+def _risk_trade_date(value: object) -> date:
+    try:
+        timestamp = pd.Timestamp(value)
+    except (TypeError, ValueError) as error:
+        raise ValueError("risk snapshot keys must be valid trade dates") from error
+    if pd.isna(timestamp):
+        raise ValueError("risk snapshot keys must be valid trade dates")
+    return date(int(timestamp.year), int(timestamp.month), int(timestamp.day))
+
+
+def _build_risk(
+    result: FactorBacktestResult,
+    run_id: str,
+    data_snapshot_id: str,
+    risk_snapshots: Mapping[object, CovarianceSnapshot] | None,
+) -> pd.DataFrame:
+    if risk_snapshots is None:
+        return pd.DataFrame(columns=RISK_COLUMNS)
+    if not isinstance(risk_snapshots, Mapping):
+        raise TypeError("risk_snapshots must be a mapping")
+
+    session_by_date = {
+        pd.Timestamp(session).date(): session for session in result.position_weights.index
+    }
+    normalized: dict[date, CovarianceSnapshot] = {}
+    for raw_trade_date, snapshot in risk_snapshots.items():
+        trade_date = _risk_trade_date(raw_trade_date)
+        if trade_date in normalized:
+            raise ValueError(f"duplicate risk snapshot trade date: {trade_date}")
+        if trade_date not in session_by_date:
+            raise ValueError(f"risk snapshot trade date {trade_date} must be a result session")
+        if not isinstance(snapshot, CovarianceSnapshot):
+            raise TypeError("risk snapshot values must be CovarianceSnapshot instances")
+        if snapshot.as_of_date > trade_date:
+            raise ValueError(
+                f"covariance as_of_date {snapshot.as_of_date} must not be after trade date "
+                f"{trade_date}"
+            )
+        if snapshot.data_snapshot_id != data_snapshot_id:
+            raise ValueError("covariance snapshot data lineage differs from research run")
+        normalized[trade_date] = snapshot
+
+    weights_by_date = result.position_weights
+    rows: list[dict[str, object]] = []
+    for trade_date in sorted(normalized):
+        snapshot = normalized[trade_date]
+        session = session_by_date[trade_date]
+        weights = weights_by_date.loc[session].astype(float, copy=True)
+        annualized_covariance = snapshot.covariance * snapshot.periods_per_year
+        decomposition = labeled_component_risk(weights, annualized_covariance)
+        for asset_id in weights.index:
+            rows.append(
+                {
+                    "run_id": run_id,
+                    "trade_date": trade_date,
+                    "asset_id": asset_id,
+                    "weight": float(weights.loc[asset_id]),
+                    "marginal_risk": float(decomposition.marginal.loc[asset_id]),
+                    "component_risk": float(decomposition.component.loc[asset_id]),
+                    "risk_contribution": float(decomposition.percentage.loc[asset_id]),
+                    "covariance_snapshot_id": snapshot.snapshot_id,
+                    "covariance_as_of_date": snapshot.as_of_date,
+                    "risk_measure": "annualized_volatility",
+                    "return_frequency": snapshot.return_frequency,
+                    "periods_per_year": snapshot.periods_per_year,
+                }
+            )
+    return pd.DataFrame(rows, columns=RISK_COLUMNS)
+
+
+def _build_performance(
+    result: FactorBacktestResult,
+    run_id: str,
+    benchmark_returns: pd.Series | None,
+) -> pd.DataFrame:
+    stats = result.stats()
+    relative = (
+        result.benchmark_stats(benchmark_returns)
+        if benchmark_returns is not None
+        else {
+            "tracking_error": float("nan"),
+            "information_ratio": float("nan"),
+            "alpha": float("nan"),
+            "beta": float("nan"),
+        }
+    )
+    total_return = float(result.nav.iloc[-1] - 1.0)
+    return pd.DataFrame(
+        [
+            {
+                "run_id": run_id,
+                "total_ret": total_return,
+                "ann_ret": stats["ann_return"],
+                "ann_volatility": stats["ann_volatility"],
+                "sharpe": stats["sharpe"],
+                "sortino": stats["sortino"],
+                "max_dd": stats["max_drawdown"],
+                "calmar": stats["calmar"],
+                "win_rate": stats["win_rate"],
+                "tracking_error": relative["tracking_error"],
+                "ir": relative["information_ratio"],
+                "alpha": relative["alpha"],
+                "beta": relative["beta"],
+                "n_trades": len(result.execution.trades_frame),
+                "n_days": len(result.returns),
+            }
+        ]
+    )
+
+
+def build_research_run_artifact(
+    result: FactorBacktestResult,
+    *,
+    run_id: str,
+    strategy_id: str,
+    strategy_name: str,
+    strategy_version: str,
+    engine_version: str,
+    code_revision: str,
+    data_snapshot_id: str,
+    calendar: str,
+    timezone: str,
+    started_at: str | pd.Timestamp,
+    finished_at: str | pd.Timestamp,
+    parameters: Mapping[str, object],
+    benchmark_id: str | None = None,
+    benchmark_returns: pd.Series | None = None,
+    risk_snapshots: Mapping[object, CovarianceSnapshot] | None = None,
+) -> ResearchRunArtifact:
+    """Snapshot one successful factor backtest into schema-versioned fact tables."""
+    if not isinstance(result, FactorBacktestResult):
+        raise TypeError("result must be a FactorBacktestResult")
+    if result.nav.empty:
+        raise ValueError("result must contain at least one research session")
+    normalized_run_id = _required_text(run_id, "run_id", max_length=64)
+    normalized_strategy_id = _required_text(strategy_id, "strategy_id")
+    normalized_strategy_name = _required_text(strategy_name, "strategy_name")
+    normalized_strategy_version = _required_text(strategy_version, "strategy_version")
+    normalized_engine_version = _required_text(engine_version, "engine_version")
+    normalized_code_revision = _required_text(code_revision, "code_revision")
+    normalized_snapshot = _required_text(data_snapshot_id, "data_snapshot_id")
+    normalized_calendar = _required_text(calendar, "calendar")
+    normalized_timezone = _required_text(timezone, "timezone")
+    if not isinstance(parameters, Mapping):
+        raise TypeError("parameters must be a mapping")
+
+    started = _aware_timestamp(started_at, "started_at")
+    finished = _aware_timestamp(finished_at, "finished_at")
+    if finished < started:
+        raise ValueError("finished_at must not precede started_at")
+    if (benchmark_id is None) != (benchmark_returns is None):
+        raise ValueError("benchmark_id and benchmark_returns must be provided together")
+    normalized_benchmark = ""
+    if benchmark_id is not None:
+        normalized_benchmark = _required_text(benchmark_id, "benchmark_id")
+        result.benchmark_stats(benchmark_returns)
+
+    params_json = _canonical_mapping_json(parameters)
+    config_hash = hashlib.sha256(params_json.encode("utf-8")).hexdigest()
+    run = pd.DataFrame(
+        [
+            {
+                "schema_version": RESEARCH_ARTIFACT_SCHEMA_VERSION,
+                "run_id": normalized_run_id,
+                "strategy_id": normalized_strategy_id,
+                "strategy_name": normalized_strategy_name,
+                "strategy_version": normalized_strategy_version,
+                "engine_version": normalized_engine_version,
+                "code_revision": normalized_code_revision,
+                "config_hash": config_hash,
+                "data_snapshot_id": normalized_snapshot,
+                "benchmark_id": normalized_benchmark,
+                "benchmark_alignment_policy": (
+                    "exact_session_index" if benchmark_returns is not None else "none"
+                ),
+                "frequency": "1d",
+                "calendar": normalized_calendar,
+                "timezone": normalized_timezone,
+                "initial_capital": result.execution.initial_cash,
+                "start_date": result.nav.index[0].date(),
+                "end_date": result.nav.index[-1].date(),
+                "status": "success",
+                "started_at": started,
+                "finished_at": finished,
+                "params_json": params_json,
+            }
+        ]
+    )
+    attribution, attribution_daily = _build_attribution(result, normalized_run_id)
+    return ResearchRunArtifact(
+        schema_version=RESEARCH_ARTIFACT_SCHEMA_VERSION,
+        _run=run,
+        _signals=_build_signals(result, normalized_run_id),
+        _nav=_build_nav(result, normalized_run_id, benchmark_returns),
+        _trades=_build_trades(result, normalized_run_id),
+        _positions=_build_positions(result, normalized_run_id),
+        _attribution=attribution,
+        _attribution_daily=attribution_daily,
+        _risk=_build_risk(result, normalized_run_id, normalized_snapshot, risk_snapshots),
+        _performance=_build_performance(result, normalized_run_id, benchmark_returns),
+    )

src/quant_engine/attribution.py

@@ -0,0 +1,141 @@
+"""Post-execution daily return attribution derived from the portfolio ledger.
+
+The ledger is the source of truth: previous-close holdings explain overnight
+PnL, current-close holdings explain intraday PnL, and actual execution costs
+remain a separate contribution.  Target weights and factor scores are not
+accepted here because they are intentions rather than realized positions.
+"""
+
+from __future__ import annotations
+
+import math
+from dataclasses import dataclass
+
+import pandas as pd
+
+from quant_engine.execution import ExecutionSimulationResult
+
+__all__ = ["DailyReturnAttribution", "compute_daily_return_attribution"]
+
+
+@dataclass(frozen=True, slots=True, eq=False)
+class DailyReturnAttribution:
+    """Auditable decomposition of each net portfolio return."""
+
+    overnight: pd.DataFrame
+    intraday: pd.DataFrame
+    transaction_cost: pd.Series
+    residual: pd.Series
+    total_return: pd.Series
+
+    @property
+    def asset_contributions(self) -> pd.DataFrame:
+        """Return the combined overnight and intraday contribution by asset."""
+        return self.overnight + self.intraday
+
+    @property
+    def explained_return(self) -> pd.Series:
+        """Return asset contributions plus execution costs, before residual."""
+        explained = self.asset_contributions.sum(axis=1) + self.transaction_cost
+        return explained.rename("explained_return")
+
+
+def _validate_prices(
+    execution: ExecutionSimulationResult,
+    execution_prices: pd.DataFrame,
+    valuation_prices: pd.DataFrame,
+) -> pd.DatetimeIndex:
+    if not isinstance(execution_prices, pd.DataFrame):
+        raise TypeError("execution_prices must be a pandas DataFrame")
+    if not isinstance(valuation_prices, pd.DataFrame):
+        raise TypeError("valuation_prices must be a pandas DataFrame")
+    if not isinstance(execution_prices.index, pd.DatetimeIndex):
+        raise TypeError("execution_prices must use a DatetimeIndex")
+    if not execution_prices.index.equals(valuation_prices.index):
+        raise ValueError("execution and valuation prices must use matching trading calendars")
+    if not execution_prices.columns.equals(valuation_prices.columns):
+        raise ValueError("execution and valuation prices must use matching asset labels")
+
+    ledger_index = pd.DatetimeIndex(pd.Timestamp(position.date) for position in execution.positions)
+    if not ledger_index.equals(execution_prices.index):
+        raise ValueError("ledger and price histories must use matching trading calendars")
+    if len(execution.positions) != len(execution.daily_executions):
+        raise ValueError("ledger positions and executions must have matching lengths")
+    return execution_prices.index.copy()
+
+
+def _price_for_held_asset(
+    prices: pd.DataFrame,
+    date: pd.Timestamp,
+    asset: str,
+    stage: str,
+) -> float:
+    if asset not in prices.columns:
+        raise ValueError(f"missing {stage} price for held asset {asset} on {date}")
+    price = float(prices.at[date, asset])
+    if not math.isfinite(price) or price <= 0:
+        raise ValueError(f"invalid {stage} price for held asset {asset} on {date}")
+    return price
+
+
+def compute_daily_return_attribution(
+    execution: ExecutionSimulationResult,
+    execution_prices: pd.DataFrame,
+    valuation_prices: pd.DataFrame,
+) -> DailyReturnAttribution:
+    """Decompose net daily returns using realized pre/post-execution holdings.
+
+    For each session, previous-close shares earn the move from the previous
+    close to the current execution price; current-close shares earn the move
+    from execution price to current close.  Actual commissions, stamp tax and
+    slippage are divided by the same previous NAV denominator.  ``residual``
+    exposes any failure of those components to close to the ledger return.
+    """
+    index = _validate_prices(execution, execution_prices, valuation_prices)
+    columns = execution_prices.columns.copy()
+    overnight = pd.DataFrame(0.0, index=index.copy(), columns=columns)
+    intraday = pd.DataFrame(0.0, index=index.copy(), columns=columns)
+    cost = pd.Series(0.0, index=index.copy(), name="transaction_cost")
+
+    previous_holdings: dict[str, float] = {}
+    previous_nav = execution.initial_cash
+    for row_number, (date, position, daily) in enumerate(
+        zip(index, execution.positions, execution.daily_executions, strict=True)
+    ):
+        if previous_nav <= 0 or not math.isfinite(previous_nav):
+            raise ValueError(f"previous portfolio value must be positive and finite on {date}")
+
+        for asset, shares in previous_holdings.items():
+            execution_price = _price_for_held_asset(
+                execution_prices, date, asset, "execution"
+            )
+            previous_close = _price_for_held_asset(
+                valuation_prices, index[row_number - 1], asset, "previous valuation"
+            )
+            overnight.at[date, asset] = shares * (execution_price - previous_close) / previous_nav
+
+        for asset, shares in position.holdings.items():
+            execution_price = _price_for_held_asset(
+                execution_prices, date, asset, "execution"
+            )
+            close_price = _price_for_held_asset(valuation_prices, date, asset, "valuation")
+            intraday.at[date, asset] = shares * (close_price - execution_price) / previous_nav
+
+        cost.at[date] = -sum(item.total_cost for item in daily.executions) / previous_nav
+        previous_holdings = position.holdings
+        previous_nav = position.portfolio_value
+
+    total_return = pd.Series(
+        execution.daily_returns.to_numpy(copy=True),
+        index=index.copy(),
+        name="total_return",
+    )
+    explained = (overnight + intraday).sum(axis=1) + cost
+    residual = (total_return - explained).rename("residual")
+    return DailyReturnAttribution(
+        overnight=overnight,
+        intraday=intraday,
+        transaction_cost=cost,
+        residual=residual,
+        total_return=total_return,
+    )

src/quant_engine/backtest.py

@@ -13,29 +13,28 @@
 
 ```python
 from quant_engine.backtest import (
-    compute_nav_from_weights,    # 调仓表 → 净值
+    rebalance_periodic,           # 周期性再平衡
-    rebalance_table,              # 周期性再平衡
+    run_weight_backtest,          # 权重 → 统一结果对象
-    compare_to_benchmark,         # 策略 vs 基准
     weights_to_long_short,        # 多空组合
 )
 
-# 1. 调仓表 → 净值
+# 调仓表 → 净值、收益、绩效与基准报告
-nav = compute_nav_from_weights(
+rebalance_table = rebalance_periodic(target_weights, rebalance_dates, returns.index)
+result = run_weight_backtest(
     weights=rebalance_table,    # 每周/每月调仓
     stock_returns=returns,      # 个股日收益
     initial_capital=1.0,
+    benchmark_nav=benchmark_nav,
 )
-
+print(result.stats())
-# 2. 跟基准比
+print(result.benchmark_report())
-result = compare_to_benchmark(nav, benchmark_nav)
-print(result.summary())
 ```
 """
 
 from __future__ import annotations
 
-from pathlib import Path
 from collections.abc import Mapping, Sequence
+from dataclasses import dataclass
 
 import numpy as np
 import pandas as pd
@@ -46,6 +45,26 @@ from quant_engine.metrics import summary as metrics_summary
 logger = get_logger(__name__)
 
 
+@dataclass(frozen=True, slots=True, eq=False)
+class BacktestResult:
+    """一次权重回测的稳定结果快照。"""
+
+    nav: pd.Series
+    returns: pd.Series
+    weights: pd.DataFrame
+    benchmark_nav: pd.Series | None = None
+
+    def stats(self, rf: float = 0.0) -> Mapping[str, float]:
+        """返回标准绩效指标。"""
+        return metrics_summary(self.returns, rf)
+
+    def benchmark_report(self, rf: float = 0.0) -> pd.DataFrame:
+        """返回策略与基准的对比报告。"""
+        if self.benchmark_nav is None:
+            raise ValueError("benchmark_nav is required for benchmark comparison")
+        return compare_to_benchmark(self.nav, self.benchmark_nav, rf)
+
+
 # ── 调仓表 → 净值 ──────────────────────────────────────
 
 
@@ -57,8 +76,9 @@ def compute_nav_from_weights(
 ) -> pd.Series:
     """从调仓表（日期 × 股票权重）+ 个股日收益 → 净值曲线。
 
-    假设：在调仓日之间权重不变（**前向填充**）。
+    假设：输入是该收益测量区间开始前已经生效的持仓权重，并在调仓日之间
-    调仓日的权重 = `weights.loc[rebalance_date]`。
+    保持不变（**前向填充**）。本函数不会把信号日自动解释为执行日；因子分数
+    应先经交易日历调度和实际执行时点处理，避免把同一时点未知的收益计入。
 
     Args:
         weights: 调仓日 × 股票代码 的权重 DataFrame（**0~1**，行和 ≤ 1）
@@ -113,6 +133,29 @@ def compute_returns_from_nav(nav: pd.Series) -> pd.Series:
     return nav.pct_change().fillna(0.0)
 
 
+def run_weight_backtest(
+    weights: pd.DataFrame,
+    stock_returns: pd.DataFrame,
+    initial_capital: float = 1.0,
+    tc_rate: float = 0.0,
+    benchmark_nav: pd.Series | None = None,
+) -> BacktestResult:
+    """执行权重回测并返回隔离于调用方输入的结果快照。"""
+    weights_snapshot = weights.copy(deep=True)
+    nav = compute_nav_from_weights(
+        weights=weights_snapshot,
+        stock_returns=stock_returns,
+        initial_capital=initial_capital,
+        tc_rate=tc_rate,
+    )
+    return BacktestResult(
+        nav=nav,
+        returns=compute_returns_from_nav(nav),
+        weights=weights_snapshot,
+        benchmark_nav=None if benchmark_nav is None else benchmark_nav.copy(deep=True),
+    )
+
+
 # ── 调仓工具 ──────────────────────────────────────
 
 
@@ -131,6 +174,9 @@ def rebalance_periodic(
     Returns:
         调仓表 DataFrame（all_dates × 股票代码）
     """
+    if all_dates.empty:
+        return pd.DataFrame(index=all_dates, columns=target_weights.index, dtype=float)
+
     table = pd.DataFrame(0.0, index=all_dates, columns=target_weights.index)
     for date in rebalance_dates:
         if date not in all_dates:
@@ -201,6 +247,8 @@ def compare_to_benchmark(
     """
     # 对齐 index
     common = strategy_nav.index.intersection(benchmark_nav.index)
+    if common.empty:
+        raise ValueError("strategy and benchmark must have overlapping dates")
     s = strategy_nav.loc[common]
     b = benchmark_nav.loc[common]
 

src/quant_engine/data_adapter.py

@@ -6,22 +6,27 @@
 - execution.py 需要**宽表**（date × stock_code）prices / volumes
 - Tushare 字段命名：`ts_code / vol(手) / amount(千元) / pct_chg`，且**无 vwap 字段**
 
-本模块提供 6 个纯函数，让新模块直接吃 qtdb_pro 真实数据：
+本模块提供可组合的数据适配函数，让新模块直接吃 qtdb_pro 真实数据：
 1. `long_to_wide()` — 长表 → 宽表（date × stock_code）
 2. `wide_to_long()` — 宽表 → 长表
 3. `rename_tushare_columns()` — 列名映射（ts_code→stock_code, vol→volume 等）
 4. `add_vwap_proxy()` — vwap 代理（Tushare 无 vwap 字段）
 5. `apply_adj_factor()` — 复权（hq_daily × hq_adj_factor 前复权）
 6. `prepare_stock_series()` — 单股提取（alpha_factors 输入）
-7. `prepare_execution_inputs()` — execution 输入（prices + volumes 宽表）
+7. `prepare_asset_return_snapshot()` — 带稳定 lineage 的资产日收益
-8. `load_qtdb_daily()` — 便捷加载（qtdb_pro.hq_daily + 可选复权）
+8. `prepare_execution_inputs()` — execution 输入（prices + volumes 宽表）
+9. `load_qtdb_daily()` — 便捷加载（qtdb_pro.hq_daily + 可选复权）
 
 全部纯 pandas/numpy，零新依赖，mypy strict 兼容。
 """
 
 from __future__ import annotations
 
+import hashlib
+import json
 from collections.abc import Mapping, Sequence
+from dataclasses import dataclass
+from datetime import date
 from typing import Any
 
 import numpy as np
@@ -32,12 +37,14 @@ from quant_engine.logging import get_logger
 logger = get_logger(__name__)
 
 __all__ = [
+    "AssetReturnSnapshot",
     "long_to_wide",
     "wide_to_long",
     "rename_tushare_columns",
     "add_vwap_proxy",
     "apply_adj_factor",
     "prepare_stock_series",
+    "prepare_asset_return_snapshot",
     "prepare_execution_inputs",
     "load_qtdb_daily",
 ]
@@ -57,6 +64,107 @@ TUSHARE_RENAME: dict[str, str] = {
 }
 
 
+@dataclass(frozen=True, slots=True, init=False, eq=False)
+class AssetReturnSnapshot:
+    """Immutable-by-interface daily return matrix with reproducible lineage."""
+
+    data_snapshot_id: str
+    source: str
+    source_snapshot_id: str
+    price_field: str
+    adjustment: str
+    return_method: str
+    start_date: date
+    end_date: date
+    sessions: int
+    assets: tuple[str, ...]
+    _returns: pd.DataFrame
+
+    def __init__(
+        self,
+        *,
+        data_snapshot_id: str,
+        source: str,
+        source_snapshot_id: str,
+        price_field: str,
+        adjustment: str,
+        return_method: str,
+        start_date: date,
+        end_date: date,
+        assets: tuple[str, ...],
+        returns: pd.DataFrame,
+    ) -> None:
+        for value, name in (
+            (data_snapshot_id, "data_snapshot_id"),
+            (source, "source"),
+            (source_snapshot_id, "source_snapshot_id"),
+            (price_field, "price_field"),
+            (adjustment, "adjustment"),
+            (return_method, "return_method"),
+        ):
+            if not isinstance(value, str) or not value.strip():
+                raise ValueError(f"{name} must be non-empty")
+        if returns.empty or not isinstance(returns.index, pd.DatetimeIndex):
+            raise ValueError("returns must contain a DatetimeIndex and at least one session")
+        if tuple(returns.columns) != assets:
+            raise ValueError("assets must match returns columns")
+        if start_date > end_date:
+            raise ValueError("start_date must not be after end_date")
+
+        object.__setattr__(self, "data_snapshot_id", data_snapshot_id.strip())
+        object.__setattr__(self, "source", source.strip())
+        object.__setattr__(self, "source_snapshot_id", source_snapshot_id.strip())
+        object.__setattr__(self, "price_field", price_field.strip())
+        object.__setattr__(self, "adjustment", adjustment.strip())
+        object.__setattr__(self, "return_method", return_method.strip())
+        object.__setattr__(self, "start_date", start_date)
+        object.__setattr__(self, "end_date", end_date)
+        object.__setattr__(self, "sessions", len(returns))
+        object.__setattr__(self, "assets", assets)
+        object.__setattr__(self, "_returns", returns.copy(deep=True))
+
+    @property
+    def returns(self) -> pd.DataFrame:
+        """Return an isolated copy so callers cannot mutate the snapshot."""
+        return self._returns.copy(deep=True)
+
+
+def _non_empty(value: str, name: str) -> str:
+    if not isinstance(value, str) or not value.strip():
+        raise ValueError(f"{name} must be non-empty")
+    return value.strip()
+
+
+def _asset_return_snapshot_id(
+    prices: pd.DataFrame,
+    *,
+    source: str,
+    source_snapshot_id: str,
+    price_field: str,
+    adjustment: str,
+) -> str:
+    values = prices.to_numpy(dtype=float, copy=True)
+    missing = np.isnan(values)
+    normalized = np.where(missing, 0.0, values).astype("<f8", copy=False)
+    metadata = {
+        "adjustment": adjustment,
+        "assets": [str(asset) for asset in prices.columns],
+        "price_field": price_field,
+        "return_method": "simple",
+        "schema": "asset-returns-v1",
+        "sessions": [timestamp.date().isoformat() for timestamp in prices.index],
+        "shape": list(values.shape),
+        "source": source,
+        "source_snapshot_id": source_snapshot_id,
+    }
+    digest = hashlib.sha256(
+        json.dumps(metadata, sort_keys=True, separators=(",", ":")).encode("utf-8")
+    )
+    digest.update(missing.astype(np.uint8, copy=False).tobytes(order="C"))
+    digest.update(normalized.tobytes(order="C"))
+    return f"asset-returns-v1:{digest.hexdigest()}"
+
+
 def long_to_wide(
     df: pd.DataFrame,
     value_col: str = "close",
@@ -283,10 +391,104 @@ def prepare_stock_series(
     return series_map
 
 
+def prepare_asset_return_snapshot(
+    df: pd.DataFrame,
+    *,
+    source: str,
+    source_snapshot_id: str,
+    price_col: str = "close",
+    adjustment: str = "none",
+    stock_col: str = "stock_code",
+    date_col: str = "trade_date",
+) -> AssetReturnSnapshot:
+    """Build deterministic simple daily returns from a long market-price table.
+
+    ``source_snapshot_id`` must identify the upstream ingestion snapshot. The
+    resulting ID additionally fingerprints canonical price values and their
+    missing mask, so changed contents cannot retain the same downstream identity.
+    Missing prices are never forward-filled.
+    """
+    normalized_source = _non_empty(source, "source")
+    normalized_source_snapshot_id = _non_empty(
+        source_snapshot_id,
+        "source_snapshot_id",
+    )
+    normalized_price_col = _non_empty(price_col, "price_col")
+    normalized_adjustment = _non_empty(adjustment, "adjustment")
+    if not isinstance(df, pd.DataFrame):
+        raise TypeError("df must be a pandas DataFrame")
+    if df.empty:
+        raise ValueError("df must contain market prices")
+    required = {date_col, stock_col, normalized_price_col}
+    missing_columns = sorted(required.difference(df.columns))
+    if missing_columns:
+        raise ValueError(f"prepare_asset_return_snapshot: missing columns={missing_columns}")
+
+    market = df[[date_col, stock_col, normalized_price_col]].copy()
+    if any(not isinstance(asset, str) or not asset.strip() for asset in market[stock_col]):
+        raise ValueError("asset labels must be non-empty strings")
+    market[stock_col] = market[stock_col].str.strip()
+    try:
+        normalized_dates = pd.to_datetime(market[date_col], errors="raise")
+    except (TypeError, ValueError) as error:
+        raise ValueError("trade dates must be valid dates") from error
+    if normalized_dates.isna().any():
+        raise ValueError("trade dates must be valid dates")
+    market[date_col] = normalized_dates.dt.normalize()
+    if market.duplicated(subset=[date_col, stock_col]).any():
+        raise ValueError("duplicate asset/session prices are not allowed")
+
+    try:
+        market[normalized_price_col] = pd.to_numeric(
+            market[normalized_price_col],
+            errors="raise",
+        )
+    except (TypeError, ValueError) as error:
+        raise ValueError("prices must be numeric") from error
+    observed_prices = market[normalized_price_col].dropna().to_numpy(dtype=float)
+    if observed_prices.size == 0 or not np.isfinite(observed_prices).all():
+        raise ValueError("prices must contain positive finite observations")
+    if (observed_prices <= 0.0).any():
+        raise ValueError("prices must contain positive finite observations")
+
+    prices = market.pivot(
+        index=date_col,
+        columns=stock_col,
+        values=normalized_price_col,
+    ).sort_index()
+    prices = prices.reindex(sorted(str(asset) for asset in prices.columns), axis="columns")
+    prices = prices.astype(float)
+    if len(prices) < 2:
+        raise ValueError("market prices must contain at least two sessions")
+    returns = prices.pct_change(fill_method=None)
+    assets = tuple(str(asset) for asset in prices.columns)
+    snapshot_id = _asset_return_snapshot_id(
+        prices,
+        source=normalized_source,
+        source_snapshot_id=normalized_source_snapshot_id,
+        price_field=normalized_price_col,
+        adjustment=normalized_adjustment,
+    )
+    return AssetReturnSnapshot(
+        data_snapshot_id=snapshot_id,
+        source=normalized_source,
+        source_snapshot_id=normalized_source_snapshot_id,
+        price_field=normalized_price_col,
+        adjustment=normalized_adjustment,
+        return_method="simple",
+        start_date=prices.index[0].date(),
+        end_date=prices.index[-1].date(),
+        assets=assets,
+        returns=returns,
+    )
+
+
 def prepare_execution_inputs(
     df: pd.DataFrame,
     stock_col: str = "stock_code",
     date_col: str = "trade_date",
+    *,
+    price_col: str = "close",
 ) -> tuple[pd.DataFrame, pd.DataFrame]:
     """长表行情 → execution 输入（prices + volumes 宽表）。
 
@@ -294,10 +496,11 @@ def prepare_execution_inputs(
         df: 长表行情（含 close / volume 列，Tushare rename 后）
         stock_col: 股票代码列名
         date_col: 日期列名
+        price_col: 执行价字段，默认 close；防前视研究可显式选择下一交易日 open
 
     Returns:
         (prices_wide, volumes_wide)：
-        - prices_wide: date × stock_code，值=close
+        - prices_wide: date × stock_code，值=price_col
         - volumes_wide: date × stock_code，值=volume（若无 volume 列则全 1.0）
 
     Examples:
@@ -313,9 +516,9 @@ def prepare_execution_inputs(
     """
     if df.empty:
         return pd.DataFrame(), pd.DataFrame()
-    if "close" not in df.columns:
+    if price_col not in df.columns:
-        raise ValueError(f"prepare_execution_inputs: 缺 close 列，实际列={list(df.columns)}")
+        raise ValueError(f"prepare_execution_inputs: 缺 {price_col} 列，实际列={list(df.columns)}")
-    prices = long_to_wide(df, value_col="close", date_col=date_col, stock_col=stock_col)
+    prices = long_to_wide(df, value_col=price_col, date_col=date_col, stock_col=stock_col)
     if "volume" in df.columns:
         volumes = long_to_wide(df, value_col="volume", date_col=date_col, stock_col=stock_col)
     else:

src/quant_engine/execution.py

@@ -10,7 +10,9 @@
 借鉴 hikyuu SG/MM/CN/PG 部件化思想（不引入 hikyuu 框架）：
 - ExecutionConfig：佣金 + 印花税 + 滑点 + 最小交易额 + 止损/止盈阈值
 - simulate_execution()：从目标权重 → 实际成交金额（应用成本/滑点）
-- simulate_multi_day()：多日组合仿真（NAV 序列 + 调仓记录）
+- simulate_daily_ledger_with_audit()：稀疏调仓 + 完整交易日收盘估值 Ledger
+- simulate_multi_day_with_audit()：目标权重差额调仓（成交/拒绝/持仓/NAV）
+- simulate_multi_day()：兼容的多日日末持仓快照入口
 - check_stop_loss_take_profit()：止损/止盈触发判定
 - run_end_to_end_poc()：signal → 调仓 → 执行 → NAV 端到端 POC
 
@@ -19,8 +21,9 @@
 
 from __future__ import annotations
 
+import math
 from collections.abc import Mapping
-from dataclasses import dataclass
+from dataclasses import dataclass, replace
 from typing import Any
 
 import pandas as pd
@@ -101,6 +104,9 @@ class ExecutionResult:
     net_cash_flow: float  # 净现金流（买入为负，卖出为正）
     partial_fill_pct: float = 1.0  # 实际成交占目标的比例（1.0 = 全部成交）
     blocked_reason: str = ""  # 阻塞原因（如涨跌停停牌）
+    side: str = ""  # buy / sell；未成交记录也保留目标方向
+    quantity: float = 0.0  # 实际成交股数
+    price: float = 0.0  # 未含滑点的参考执行价
 
 
 def _apply_costs(
@@ -344,19 +350,458 @@ class DailyExecution:
     """单日执行记录。"""
 
     date: str
-    executions: list[ExecutionResult]
+    executions: tuple[ExecutionResult, ...]
     nav_before: float
     nav_after: float
     rebalance_triggered: bool
 
 
-def simulate_multi_day(
+@dataclass(frozen=True)
+class ExecutionSimulationResult:
+    """单次多日仿真的持仓与执行审计结果。"""
+
+    initial_cash: float
+    positions: tuple[DailyPosition, ...]
+    daily_executions: tuple[DailyExecution, ...]
+
+    @property
+    def nav_series(self) -> pd.Series:
+        """返回按日期索引的日末 NAV 副本。"""
+        return pd.Series(
+            [position.portfolio_value for position in self.positions],
+            index=[position.date for position in self.positions],
+            dtype=float,
+        )
+
+    @property
+    def normalized_nav_series(self) -> pd.Series:
+        """返回以初始资金为 1 的净值曲线副本。"""
+        nav = self.nav_series
+        if self.initial_cash == 0:
+            return pd.Series(0.0, index=nav.index, dtype=float)
+        return nav / self.initial_cash
+
+    @property
+    def daily_returns(self) -> pd.Series:
+        """返回逐日收益；首日相对初始资金计算，保留首日交易成本。"""
+        nav = self.nav_series
+        if nav.empty:
+            return nav
+        returns = nav.pct_change()
+        returns.iloc[0] = (
+            nav.iloc[0] / self.initial_cash - 1.0 if self.initial_cash != 0 else 0.0
+        )
+        return returns.fillna(0.0)
+
+    @property
+    def trades_frame(self) -> pd.DataFrame:
+        """返回可投影到平台成交明细的实际成交表，不包含纯拒绝记录。"""
+        columns = [
+            "trade_date",
+            "ts_code",
+            "side",
+            "qty",
+            "price",
+            "amount",
+            "fee",
+            "slippage",
+        ]
+        rows = [
+            {
+                "trade_date": daily.date,
+                "ts_code": execution.stock_code,
+                "side": execution.side,
+                "qty": execution.quantity,
+                "price": execution.price,
+                "amount": execution.executed_value,
+                "fee": execution.commission + execution.stamp_tax,
+                "slippage": execution.slippage_cost,
+            }
+            for daily in self.daily_executions
+            for execution in daily.executions
+            if execution.quantity > 0
+        ]
+        return pd.DataFrame(rows, columns=columns)
+
+    @property
+    def ledger_frame(self) -> pd.DataFrame:
+        """返回稳定的日频 Ledger 投影，不附加运行元数据或写数据库。"""
+        columns = [
+            "trade_date",
+            "portfolio_value",
+            "nav",
+            "pnl",
+            "pnl_pct",
+            "position_value",
+            "cash",
+            "turnover",
+        ]
+        previous_value = self.initial_cash
+        rows: list[dict[str, float | str]] = []
+        daily_returns = self.daily_returns
+        for index, (position, daily) in enumerate(
+            zip(self.positions, self.daily_executions, strict=True)
+        ):
+            daily_turnover = sum(
+                execution.executed_value
+                for execution in daily.executions
+                if execution.quantity > 0
+            )
+            turnover_rate = daily_turnover / daily.nav_before if daily.nav_before > 0 else 0.0
+            rows.append(
+                {
+                    "trade_date": position.date,
+                    "portfolio_value": position.portfolio_value,
+                    "nav": (
+                        position.portfolio_value / self.initial_cash
+                        if self.initial_cash != 0
+                        else 0.0
+                    ),
+                    "pnl": position.portfolio_value - previous_value,
+                    "pnl_pct": float(daily_returns.iloc[index]),
+                    "position_value": position.portfolio_value - position.cash,
+                    "cash": position.cash,
+                    "turnover": turnover_rate,
+                }
+            )
+            previous_value = position.portfolio_value
+        return pd.DataFrame(rows, columns=columns)
+
+    @property
+    def total_costs(self) -> float:
+        """汇总实际成交产生的成本。"""
+        return sum(
+            execution.total_cost
+            for daily in self.daily_executions
+            for execution in daily.executions
+        )
+
+    @property
+    def total_turnover(self) -> float:
+        """汇总实际成交金额。"""
+        return sum(
+            execution.executed_value
+            for daily in self.daily_executions
+            for execution in daily.executions
+        )
+
+    @property
+    def total_rebalances(self) -> int:
+        """返回至少有一笔实际成交的调仓日数量。"""
+        return sum(daily.rebalance_triggered for daily in self.daily_executions)
+
+    @property
+    def final_portfolio_value(self) -> float:
+        """返回最后一个日末 NAV；空输入时返回初始资金。"""
+        if not self.positions:
+            return self.initial_cash
+        return self.positions[-1].portfolio_value
+
+    @property
+    def return_pct(self) -> float:
+        """返回相对初始资金的百分比收益。"""
+        if self.initial_cash == 0:
+            return 0.0
+        return (self.final_portfolio_value / self.initial_cash - 1.0) * 100.0
+
+
+def _blocked_execution(stock_code: str, target_value: float, reason: str) -> ExecutionResult:
+    """构造未成交但可审计的执行记录。"""
+    return ExecutionResult(
+        stock_code=stock_code,
+        target_value=target_value,
+        executed_value=0.0,
+        commission=0.0,
+        stamp_tax=0.0,
+        slippage_cost=0.0,
+        total_cost=0.0,
+        net_cash_flow=0.0,
+        partial_fill_pct=0.0,
+        blocked_reason=reason,
+        side="buy" if target_value > 0 else "sell" if target_value < 0 else "",
+    )
+
+
+def _validate_target_weights(date: str, targets: Mapping[str, float]) -> dict[str, float]:
+    """校验并复制单日长仓目标权重。"""
+    normalized: dict[str, float] = {}
+    for stock_code, raw_weight in targets.items():
+        try:
+            weight = float(raw_weight)
+        except (TypeError, ValueError) as error:
+            raise ValueError(f"target weights on {date!r} must be numeric") from error
+        if not math.isfinite(weight) or weight < 0:
+            raise ValueError(f"target weights on {date!r} must be finite and non-negative")
+        normalized[stock_code] = weight
+    if sum(normalized.values()) > 1.0 + 1e-12:
+        raise ValueError(f"target weights on {date!r} must sum to at most 1.0")
+    return normalized
+
+
+def _partially_fill_buy(
+    desired: ExecutionResult,
+    fill_pct: float,
+    config: ExecutionConfig,
+) -> ExecutionResult:
+    """按同一比例缩放买入，保留原始目标金额供审计。"""
+    actual_target_value = desired.target_value * fill_pct
+    executed_value, commission, stamp_tax, slippage_cost = _apply_costs(
+        actual_target_value,
+        True,
+        config,
+    )
+    total_cost = commission + stamp_tax + slippage_cost
+    return ExecutionResult(
+        stock_code=desired.stock_code,
+        target_value=desired.target_value,
+        executed_value=executed_value,
+        commission=commission,
+        stamp_tax=stamp_tax,
+        slippage_cost=slippage_cost,
+        total_cost=total_cost,
+        net_cash_flow=-(executed_value + commission + stamp_tax),
+        partial_fill_pct=fill_pct,
+        blocked_reason="insufficient_cash_partial_fill",
+    )
+
+
+def _rebalance_at_prices(
+    date: str,
+    targets: Mapping[str, float],
+    prices: Mapping[str, float],
+    cash: float,
+    holdings: dict[str, float],
+    config: ExecutionConfig,
+) -> tuple[float, tuple[ExecutionResult, ...], float, float]:
+    """在单一执行时点按目标权重差额调仓，并原地更新 holdings。"""
+    normalized_targets = _validate_target_weights(date, targets)
+    for held_code in holdings:
+        held_price = prices.get(held_code)
+        if held_price is None or not math.isfinite(held_price) or held_price <= 0:
+            raise ValueError(f"missing price for held asset {held_code} on {date!r}")
+
+    nav_before = cash + sum(
+        shares * prices.get(stock_code, 0.0)
+        for stock_code, shares in holdings.items()
+    )
+    effective_targets = dict.fromkeys(holdings, 0.0)
+    effective_targets.update(normalized_targets)
+    buy_weights: dict[str, float] = {}
+    sell_weights: dict[str, float] = {}
+    rejected: list[ExecutionResult] = []
+
+    for stock_code, target_weight in effective_targets.items():
+        price = prices.get(stock_code)
+        target_value = float(target_weight) * nav_before
+        if price is None or not math.isfinite(price) or price <= 0:
+            if target_value != 0 or holdings.get(stock_code, 0.0) != 0:
+                rejected.append(_blocked_execution(stock_code, target_value, "missing_price"))
+            continue
+
+        current_value = holdings.get(stock_code, 0.0) * price
+        trade_value = target_value - current_value
+        if abs(trade_value) < config.min_trade_amount or math.isclose(
+            trade_value, 0.0, abs_tol=1e-12
+        ):
+            continue
+        if nav_before == 0:
+            rejected.append(_blocked_execution(stock_code, trade_value, "zero_nav"))
+            continue
+        destination = buy_weights if trade_value > 0 else sell_weights
+        destination[stock_code] = trade_value / nav_before
+
+    sell_executions = simulate_execution(sell_weights, nav_before, config)
+    filled: list[ExecutionResult] = []
+    for raw_execution in sell_executions:
+        price = prices[raw_execution.stock_code]
+        quantity = abs(raw_execution.target_value) / price
+        execution = replace(
+            raw_execution,
+            side="sell",
+            quantity=quantity,
+            price=price,
+        )
+        held = holdings.get(execution.stock_code, 0.0)
+        holdings[execution.stock_code] = max(0.0, held - quantity)
+        if holdings[execution.stock_code] < 1e-6:
+            del holdings[execution.stock_code]
+        cash += execution.net_cash_flow
+        filled.append(execution)
+
+    desired_buys = simulate_execution(buy_weights, nav_before, config)
+    required_cash = sum(-execution.net_cash_flow for execution in desired_buys)
+    buy_fill_pct = min(1.0, max(cash, 0.0) / required_cash) if required_cash > 0 else 1.0
+    for desired in desired_buys:
+        if buy_fill_pct == 0:
+            rejected.append(
+                _blocked_execution(desired.stock_code, desired.target_value, "insufficient_cash")
+            )
+            continue
+        raw_execution = (
+            desired
+            if buy_fill_pct == 1.0
+            else _partially_fill_buy(desired, buy_fill_pct, config)
+        )
+        price = prices[raw_execution.stock_code]
+        quantity = abs(raw_execution.target_value) * raw_execution.partial_fill_pct / price
+        execution = replace(
+            raw_execution,
+            side="buy",
+            quantity=quantity,
+            price=price,
+        )
+        holdings[execution.stock_code] = holdings.get(execution.stock_code, 0.0) + quantity
+        cash += execution.net_cash_flow
+        if math.isclose(cash, 0.0, abs_tol=1e-9):
+            cash = 0.0
+        filled.append(execution)
+
+    executions = (*filled, *rejected)
+    nav_after = cash + sum(
+        shares * prices.get(stock_code, 0.0)
+        for stock_code, shares in holdings.items()
+    )
+    return cash, executions, nav_before, nav_after
+
+
+def _validate_sparse_daily_histories(
+    target_weights_history: list[tuple[str, dict[str, float]]],
+    execution_price_history: list[tuple[str, dict[str, float]]],
+    valuation_price_history: list[tuple[str, dict[str, float]]],
+) -> tuple[
+    dict[str, dict[str, float]],
+    dict[str, dict[str, float]],
+    list[tuple[str, dict[str, float]]],
+]:
+    """校验稀疏调仓与完整估值日历，并隔离调用方可变输入。"""
+    target_dates = [date for date, _ in target_weights_history]
+    execution_dates = [date for date, _ in execution_price_history]
+    valuation_dates = [date for date, _ in valuation_price_history]
+    if len(set(target_dates)) != len(target_dates):
+        raise ValueError("target_weights_history must contain unique dates")
+    if len(set(execution_dates)) != len(execution_dates):
+        raise ValueError("execution_price_history must contain unique dates")
+    if len(set(valuation_dates)) != len(valuation_dates):
+        raise ValueError("valuation_price_history must contain unique dates")
+    if execution_dates != target_dates:
+        raise ValueError("execution price dates must exactly match target weight dates")
+
+    valuation_positions = {date: index for index, date in enumerate(valuation_dates)}
+    missing_dates = [date for date in target_dates if date not in valuation_positions]
+    if missing_dates:
+        raise ValueError(f"target dates must belong to valuation calendar: {missing_dates}")
+    positions = [valuation_positions[date] for date in target_dates]
+    if positions != sorted(positions):
+        raise ValueError("target weights must follow valuation calendar order")
+
+    targets = {date: dict(values) for date, values in target_weights_history}
+    execution_prices = {date: dict(values) for date, values in execution_price_history}
+    valuation_prices = [(date, dict(values)) for date, values in valuation_price_history]
+    return targets, execution_prices, valuation_prices
+
+
+def _simulate_daily_ledger(
+    target_weights_history: list[tuple[str, dict[str, float]]],
+    execution_price_history: list[tuple[str, dict[str, float]]],
+    valuation_price_history: list[tuple[str, dict[str, float]]],
+    initial_cash: float,
+    config: ExecutionConfig,
+) -> ExecutionSimulationResult:
+    targets_by_date, execution_prices_by_date, valuation_history = (
+        _validate_sparse_daily_histories(
+            target_weights_history,
+            execution_price_history,
+            valuation_price_history,
+        )
+    )
+    cash = initial_cash
+    holdings: dict[str, float] = {}
+    positions: list[DailyPosition] = []
+    daily_executions: list[DailyExecution] = []
+
+    for date, valuation_prices in valuation_history:
+        targets = targets_by_date.get(date)
+        if targets is None:
+            executions: tuple[ExecutionResult, ...] = ()
+            nav_before = 0.0
+            nav_after = 0.0
+            rebalance_triggered = False
+        else:
+            cash, executions, nav_before, nav_after = _rebalance_at_prices(
+                date,
+                targets,
+                execution_prices_by_date[date],
+                cash,
+                holdings,
+                config,
+            )
+            rebalance_triggered = any(execution.quantity > 0 for execution in executions)
+
+        for held_code in holdings:
+            valuation_price = valuation_prices.get(held_code)
+            if (
+                valuation_price is None
+                or not math.isfinite(valuation_price)
+                or valuation_price <= 0
+            ):
+                raise ValueError(
+                    f"missing valuation price for held asset {held_code} on {date!r}"
+                )
+        portfolio_value = cash + sum(
+            shares * valuation_prices[stock_code]
+            for stock_code, shares in holdings.items()
+        )
+        if targets is None:
+            nav_before = portfolio_value
+            nav_after = portfolio_value
+        positions.append(DailyPosition(date, cash, dict(holdings), portfolio_value))
+        daily_executions.append(
+            DailyExecution(
+                date=date,
+                executions=executions,
+                nav_before=nav_before,
+                nav_after=nav_after,
+                rebalance_triggered=rebalance_triggered,
+            )
+        )
+
+    return ExecutionSimulationResult(
+        initial_cash=initial_cash,
+        positions=tuple(positions),
+        daily_executions=tuple(daily_executions),
+    )
+
+
+def simulate_daily_ledger_with_audit(
+    target_weights_history: list[tuple[str, dict[str, float]]],
+    execution_price_history: list[tuple[str, dict[str, float]]],
+    valuation_price_history: list[tuple[str, dict[str, float]]],
+    initial_cash: float,
+    config: ExecutionConfig | None = None,
+) -> ExecutionSimulationResult:
+    """以稀疏调仓和完整日历运行成交后持仓 Ledger。
+
+    执行价只用于调仓日现金与股数变化，估值价用于每个交易日日末 NAV；二者
+    显式分离，从而支持“下一日 open 成交、同日 close 估值”的无前视研究。
+    """
+    if not math.isfinite(initial_cash) or initial_cash <= 0:
+        raise ValueError(f"initial_cash must be positive and finite, got {initial_cash}")
+    return _simulate_daily_ledger(
+        target_weights_history,
+        execution_price_history,
+        valuation_price_history,
+        initial_cash,
+        ExecutionConfig() if config is None else config,
+    )
+
+
+def simulate_multi_day_with_audit(
     target_weights_history: list[tuple[str, dict[str, float]]],
     price_history: list[tuple[str, dict[str, float]]],
     initial_cash: float,
     config: ExecutionConfig | None = None,
-) -> list[DailyPosition]:
+) -> ExecutionSimulationResult:
-    """多日组合仿真（NAV 序列）。
+    """按目标权重差额推进组合，并返回唯一事实来源的审计结果。
 
     Args:
         target_weights_history: [(date, {stock_code: target_weight})]
@@ -365,97 +810,45 @@ def simulate_multi_day(
         config: 执行配置
 
     Returns:
-        DailyPosition 列表（每日 NAV 快照）。
+        日末持仓快照与逐日成交记录组成的结构化审计结果。
 
     Note:
         - 调仓频率 = target_weights_history 的频率（每日 / 每周 / 每月都行）
-        - 每日先按当日 close 估值，再按当日 target 调仓（下一交易日生效）
+        - 每日先按当日 close 估值，再交易“目标市值 - 当前市值”的差额
-        - 此处简化：调仓使用当日 close 价格
+        - 此处简化为当日 close 成交；调用方必须传入已正确滞后的目标权重
     """
-    if config is None:
+    if not math.isfinite(initial_cash) or initial_cash < 0:
-        config = ExecutionConfig()
+        raise ValueError(f"initial_cash must be finite and non-negative, got {initial_cash}")
     if len(target_weights_history) != len(price_history):
         raise ValueError("target_weights_history and price_history must have same length")
-    if not target_weights_history:
+    for (date, _), (price_date, _) in zip(target_weights_history, price_history, strict=True):
-        return []
+        if date != price_date:
-    cash = initial_cash
+            raise ValueError(
-    holdings: dict[str, float] = {}
+                f"target and price dates must match, got {date!r} and {price_date!r}"
-    positions: list[DailyPosition] = []
-    for (date, targets), (_, prices) in zip(target_weights_history, price_history, strict=True):
-        # 1) 先按当日收盘价估值
-        portfolio_value = cash + sum(
-            shares * prices.get(code, 0.0) for code, shares in holdings.items()
-        )
-        positions.append(
-            DailyPosition(
-                date=date,
-                cash=cash,
-                holdings=dict(holdings),
-                portfolio_value=portfolio_value,
             )
-        )
+    return _simulate_daily_ledger(
-        # 2) 计算 effective_targets（包含需要平仓的零权重）
+        target_weights_history,
-        effective_targets: dict[str, float] = dict(targets)
+        price_history,
-        for held_code in holdings:
+        price_history,
-            if held_code not in effective_targets:
+        initial_cash,
-                effective_targets[held_code] = 0.0
+        ExecutionConfig() if config is None else config,
-        # 3) 调仓（只对非零目标调用 simulate_execution）
+    )
-        non_zero_targets = {k: v for k, v in effective_targets.items() if v != 0}
+
-        results = simulate_execution(non_zero_targets, portfolio_value, config)
+
-        # 4) 处理零目标（平仓）：构造 ExecutionResult，shares = held（全部卖出）
+def simulate_multi_day(
-        for stock_code, weight in effective_targets.items():
+    target_weights_history: list[tuple[str, dict[str, float]]],
-            if weight == 0 and stock_code in holdings and holdings[stock_code] > 0:
+    price_history: list[tuple[str, dict[str, float]]],
-                price = prices.get(stock_code, 0.0)
+    initial_cash: float,
-                if price > 0:
+    config: ExecutionConfig | None = None,
-                    held = holdings[stock_code]
+) -> list[DailyPosition]:
-                    # 全部卖出：target_shares = held
+    """兼容入口：返回多日仿真的日末持仓快照。"""
-                    # executed_value = held * price（考虑滑点）
+    result = simulate_multi_day_with_audit(
-                    slippage_factor = 1.0 - config.slippage_bps / 10000.0
+        target_weights_history,
-                    target_value = -held * price
+        price_history,
-                    executed_value = target_value * slippage_factor
+        initial_cash,
-                    commission = abs(executed_value) * config.commission_bps / 10000.0
+        config,
-                    stamp_tax = abs(executed_value) * config.stamp_tax_bps / 10000.0
+    )
-                    slippage_cost = abs(executed_value - target_value)
+    return list(result.positions)
-                    # 标记净卖出 shares = held
-                    results.append(
-                        ExecutionResult(
-                            stock_code=stock_code,
-                            target_value=target_value,
-                            executed_value=executed_value,
-                            commission=commission,
-                            stamp_tax=stamp_tax,
-                            slippage_cost=slippage_cost,
-                            total_cost=commission + stamp_tax + slippage_cost,
-                            net_cash_flow=executed_value - commission - stamp_tax,
-                        )
-                    )
-        # 5) 应用执行结果到持仓
-        for r in results:
-            cost = r.executed_value + r.commission + r.stamp_tax
-            proceeds = r.executed_value - r.commission - r.stamp_tax
-            price = prices.get(r.stock_code, 0.0)
-            if r.target_value > 0:
-                # 买入：shares = 正数 executed_value / price，cash 减少 cost
-                shares = r.executed_value / price if price > 0 else 0.0
-                holdings[r.stock_code] = holdings.get(r.stock_code, 0.0) + shares
-                cash -= cost
-            else:
-                # 卖出：cash 增加 proceeds 的绝对值（proceeds 本是负的）
-                held = holdings.get(r.stock_code, 0.0)
-                if held > 0:
-                    # 如果是 zero-target 触发的全卖（target_value 与持仓市值近似），全部卖出
-                    if abs(r.target_value) >= held * price * 0.95:
-                        sell_shares = held
-                    else:
-                        target_shares = abs(r.executed_value) / price if price > 0 else held
-                        sell_shares = min(held, target_shares)
-                    holdings[r.stock_code] = held - sell_shares
-                    if holdings[r.stock_code] < 1e-6:
-                        del holdings[r.stock_code]
-                # proceeds 是负的（target_value 负），cash += proceeds 实际是减去
-                # 但卖出是现金流入，所以应该 cash += abs(proceeds)
-                cash += abs(proceeds)
-    return positions
 
 
 def run_end_to_end_poc(
@@ -486,64 +879,16 @@ def run_end_to_end_poc(
         config = ExecutionConfig()
     if len(signals) != len(prices):
         raise ValueError("signals and prices must have same length")
-    positions = simulate_multi_day(signals, prices, initial_cash, config)
+    audit = simulate_multi_day_with_audit(signals, prices, initial_cash, config)
-    nav_series = pd.Series(
-        [p.portfolio_value for p in positions], index=[p.date for p in positions]
-    )
-    # 计算 total_costs / total_turnover（重放所有执行）
-    total_cost_acc = 0.0
-    total_turnover_acc = 0.0
-    rebalance_count = 0
-    cash = initial_cash
-    holdings: dict[str, float] = {}
-    for (date, targets), (_, price_map) in zip(signals, prices, strict=True):
-        portfolio_value = cash + sum(
-            shares * price_map.get(code, 0.0) for code, shares in holdings.items()
-        )
-        if targets:
-            rebalance_count += 1
-        # 自动平仓：持仓但不在 target 中的股票
-        effective_targets: dict[str, float] = dict(targets)
-        for held_code in holdings:
-            if held_code not in effective_targets:
-                effective_targets[held_code] = 0.0
-        results = simulate_execution(effective_targets, portfolio_value, config)
-        total_cost_acc += total_costs(results)
-        total_turnover_acc += total_turnover(results)
-        for r in results:
-            cost = r.executed_value + r.commission + r.stamp_tax
-            proceeds = r.executed_value - r.commission - r.stamp_tax
-            if r.target_value > 0:
-                shares = (
-                    r.executed_value / price_map[r.stock_code]
-                    if price_map[r.stock_code] > 0
-                    else 0.0
-                )
-                holdings[r.stock_code] = holdings.get(r.stock_code, 0.0) + shares
-                cash -= cost
-            else:
-                held = holdings.get(r.stock_code, 0.0)
-                if held > 0:
-                    sell_shares = min(
-                        held,
-                        abs(r.executed_value / price_map[r.stock_code])
-                        if price_map[r.stock_code] > 0
-                        else held,
-                    )
-                    holdings[r.stock_code] = held - sell_shares
-                    if holdings[r.stock_code] < 1e-6:
-                        del holdings[r.stock_code]
-                cash += proceeds
     return {
-        "positions": positions,
+        "positions": list(audit.positions),
-        "nav_series": nav_series,
+        "daily_executions": list(audit.daily_executions),
-        "total_costs": total_cost_acc,
+        "nav_series": audit.nav_series,
-        "total_turnover": total_turnover_acc,
+        "total_costs": audit.total_costs,
-        "total_rebalances": rebalance_count,
+        "total_turnover": audit.total_turnover,
-        "final_portfolio_value": nav_series.iloc[-1] if len(nav_series) > 0 else initial_cash,
+        "total_rebalances": audit.total_rebalances,
-        "return_pct": ((nav_series.iloc[-1] / initial_cash) - 1) * 100
+        "final_portfolio_value": audit.final_portfolio_value,
-        if len(nav_series) > 0
+        "return_pct": audit.return_pct,
-        else 0.0,
     }
 
 
@@ -667,7 +1012,10 @@ __all__ = [
     "apply_bid_ask_spread",
     "DailyPosition",
     "DailyExecution",
+    "ExecutionSimulationResult",
+    "simulate_daily_ledger_with_audit",
     "simulate_multi_day",
+    "simulate_multi_day_with_audit",
     "run_end_to_end_poc",
     "DailyPnL",
     "simulate_with_daily_data",

src/quant_engine/factor_library.py

@@ -312,8 +312,8 @@ def ols_regress(
     ss_tot = float(((y_arr - y_arr.mean()) ** 2).sum())
     r_sq = 1.0 - ss_res / ss_tot if ss_tot > 0 else np.nan
     sigma2 = ss_res / max(n - k, 1)
-    # 协方差矩阵 = sigma2 * (X'X)^-1
+    # 广义协方差矩阵 = sigma2 * (X'X)^+，伪逆兼容共线因子。
-    xtx_inv = np.linalg.inv(x_arr.T @ x_arr) if sigma2 > 0 else np.full((k, k), np.nan)
+    xtx_inv = np.linalg.pinv(x_arr.T @ x_arr) if sigma2 > 0 else np.full((k, k), np.nan)
     se = np.sqrt(np.diag(xtx_inv) * sigma2)
     t_vals = coef / se if sigma2 > 0 else np.full_like(coef, np.nan)
     if add_constant:
@@ -513,6 +513,8 @@ def apply_factor_direction(
     Returns:
         方向调整后的因子（同向 = 越大越好）
     """
+    if direction not in {"auto", "forward", "reverse"}:
+        raise ValueError(f"direction={direction!r} not supported (auto / forward / reverse)")
     if factor.empty:
         return factor.copy()
     if direction == "auto":
@@ -541,6 +543,8 @@ def cross_sectional_rank_with_direction(
     Returns:
         pd.Series（百分位排名 [0, 1]，越大越优）
     """
+    if direction not in {"auto", "forward", "reverse"}:
+        raise ValueError(f"direction={direction!r} not supported (auto / forward / reverse)")
     if df.empty or factor_col not in df.columns:
         return pd.Series(dtype=float)
     factor = df[factor_col]

src/quant_engine/metrics.py

@@ -65,13 +65,28 @@ def sharpe_ratio(r: pd.Series, rf: float = 0.0) -> float:
     return (annualized_return(r) - rf) / vol
 
 
+def sortino_ratio(r: pd.Series, rf: float = 0.0) -> float:
+    """Sortino = (年化收益 - rf) / 年化下行偏差。"""
+    r = _clean(r)
+    if len(r) < 2:
+        return 0.0
+    downside = np.minimum(r.to_numpy(dtype=float), 0.0)
+    downside_deviation = float(
+        np.sqrt(np.mean(np.square(downside))) * np.sqrt(TRADING_DAYS_PER_YEAR)
+    )
+    if downside_deviation == 0:
+        return 0.0
+    return (annualized_return(r) - rf) / downside_deviation
+
+
 def max_drawdown(r: pd.Series) -> float:
     """最大回撤（负数）。例如 -0.2 表示最大亏 20%。"""
     r = _clean(r)
     if len(r) < 2:
         return 0.0
     nav = (1 + r).cumprod()
-    peak = nav.cummax()
+    # 初始资金净值为 1；否则首个观测日的亏损会被误当成新的历史高点。
+    peak = nav.cummax().clip(lower=1.0)
     drawdown = (nav - peak) / peak
     return float(drawdown.min())
 
@@ -119,6 +134,7 @@ def summary(r: pd.Series, rf: float = 0.0) -> Mapping[str, float]:
         "ann_return": ann_ret,
         "ann_volatility": ann_vol,
         "sharpe": sharpe_ratio(r, rf),
+        "sortino": sortino_ratio(r, rf),
         "max_drawdown": mdd,
         "calmar": calmar_ratio(r),
         "win_rate": win_rate(r),
@@ -129,6 +145,62 @@ def summary(r: pd.Series, rf: float = 0.0) -> Mapping[str, float]:
     }
 
 
+def benchmark_summary(
+    portfolio_returns: pd.Series,
+    benchmark_returns: pd.Series,
+    *,
+    risk_free_daily: float = 0.0,
+    annualization: int = TRADING_DAYS_PER_YEAR,
+) -> Mapping[str, float]:
+    """计算成本后组合相对基准的严格对齐绩效。
+
+    与通用 ``summary`` 不同，本函数拒绝静默清洗或日期 inner join。alpha
+    使用日频回归截距的几何年化；基准方差不足时 alpha/beta 为 NaN，明确
+    表示回归不可估计。
+    """
+    portfolio, benchmark = _validate_benchmark_inputs(
+        portfolio_returns,
+        benchmark_returns,
+    )
+    if isinstance(annualization, bool) or not isinstance(annualization, int):
+        raise TypeError("annualization must be an integer")
+    if annualization <= 0:
+        raise ValueError("annualization must be positive")
+    if not np.isfinite(risk_free_daily):
+        raise ValueError("risk_free_daily must be finite")
+
+    active = portfolio - benchmark
+    active_std = float(active.std())
+    tracking_error = active_std * float(np.sqrt(annualization))
+    information_ratio = (
+        float(active.mean()) / active_std * float(np.sqrt(annualization))
+        if active_std >= 1e-30
+        else float("nan")
+    )
+
+    adjusted_portfolio = portfolio - risk_free_daily
+    adjusted_benchmark = benchmark - risk_free_daily
+    benchmark_variance = float(adjusted_benchmark.var())
+    if benchmark_variance < 1e-30:
+        beta = float("nan")
+        alpha = float("nan")
+    else:
+        beta = float(adjusted_portfolio.cov(adjusted_benchmark) / benchmark_variance)
+        alpha_daily = float((adjusted_portfolio - beta * adjusted_benchmark).mean())
+        alpha = (
+            float((1.0 + alpha_daily) ** annualization - 1.0)
+            if alpha_daily > -1.0
+            else float("nan")
+        )
+    return {
+        "n_observations": len(portfolio),
+        "tracking_error": tracking_error,
+        "information_ratio": information_ratio,
+        "alpha": alpha,
+        "beta": beta,
+    }
+
+
 # ── 内部 ──────────────────────────────────────
 
 
@@ -137,3 +209,29 @@ def _clean(r: pd.Series) -> pd.Series:
     if not isinstance(r, pd.Series):
         raise TypeError(f"expected pd.Series, got {type(r).__name__}")
     return r.replace([np.inf, -np.inf], np.nan).dropna()
+
+
+def _validate_benchmark_inputs(
+    portfolio_returns: pd.Series,
+    benchmark_returns: pd.Series,
+) -> tuple[pd.Series, pd.Series]:
+    if not isinstance(portfolio_returns, pd.Series):
+        raise TypeError("portfolio_returns must be a pandas Series")
+    if not isinstance(benchmark_returns, pd.Series):
+        raise TypeError("benchmark_returns must be a pandas Series")
+    if not portfolio_returns.index.equals(benchmark_returns.index):
+        raise ValueError("portfolio and benchmark returns must use matching indexes")
+    if not portfolio_returns.index.is_unique:
+        raise ValueError("portfolio and benchmark indexes must be unique")
+    if len(portfolio_returns) < 2:
+        raise ValueError("benchmark metrics require at least two observations")
+
+    portfolio = portfolio_returns.astype(float, copy=True)
+    benchmark = benchmark_returns.astype(float, copy=True)
+    if not np.isfinite(portfolio.to_numpy()).all() or not np.isfinite(
+        benchmark.to_numpy()
+    ).all():
+        raise ValueError("portfolio and benchmark returns must be finite")
+    if (portfolio < -1.0).any() or (benchmark < -1.0).any():
+        raise ValueError("simple returns cannot be less than -1")
+    return portfolio, benchmark

src/quant_engine/portfolio_construction.py

@@ -0,0 +1,104 @@
+"""因子分数到目标权重的轻量组合构建闭环。"""
+
+from __future__ import annotations
+
+import numpy as np
+import pandas as pd
+from pandas.api.types import is_numeric_dtype
+
+__all__ = [
+    "select_top_k",
+    "equal_weight",
+    "scores_to_target_weights",
+    "scores_to_weight_table",
+]
+
+
+def _validate_top_k(top_k: int) -> None:
+    if isinstance(top_k, bool) or not isinstance(top_k, int) or top_k <= 0:
+        raise ValueError("top_k must be positive")
+
+
+def _validate_gross_exposure(gross_exposure: float) -> None:
+    if not np.isfinite(gross_exposure) or gross_exposure < 0:
+        raise ValueError("gross_exposure must be finite and non-negative")
+
+
+def _validate_score_series(scores: pd.Series) -> None:
+    if not isinstance(scores, pd.Series):
+        raise TypeError(f"scores must be a pandas Series, got {type(scores).__name__}")
+    if not scores.index.is_unique:
+        raise ValueError("scores must contain unique asset labels")
+    if not is_numeric_dtype(scores.dtype):
+        raise TypeError("scores must contain numeric values")
+
+
+def select_top_k(scores: pd.Series, top_k: int, *, largest: bool = True) -> pd.Index:
+    """稳定选择最高或最低的 K 个有效因子分数。"""
+    _validate_top_k(top_k)
+    _validate_score_series(scores)
+    valid_scores = scores.dropna()
+    ordered = valid_scores.sort_values(ascending=not largest, kind="mergesort")
+    return ordered.iloc[:top_k].index.copy()
+
+
+def equal_weight(assets: pd.Index, *, gross_exposure: float = 1.0) -> pd.Series:
+    """在已选资产间等权分配指定总敞口。"""
+    _validate_gross_exposure(gross_exposure)
+    if not assets.is_unique:
+        raise ValueError("assets must contain unique asset labels")
+    if assets.empty:
+        return pd.Series(index=assets.copy(), dtype=float, name="weight")
+    weight = gross_exposure / len(assets)
+    return pd.Series(weight, index=assets.copy(), dtype=float, name="weight")
+
+
+def scores_to_target_weights(
+    scores: pd.Series,
+    top_k: int,
+    *,
+    gross_exposure: float = 1.0,
+    largest: bool = True,
+) -> pd.Series:
+    """把单期因子分数转换为完整股票池目标权重。"""
+    _validate_score_series(scores)
+    selected = select_top_k(scores, top_k, largest=largest)
+    selected_weights = equal_weight(selected, gross_exposure=gross_exposure)
+    result = pd.Series(0.0, index=scores.index.copy(), dtype=float, name="weight")
+    result.loc[selected_weights.index] = selected_weights
+    return result
+
+
+def scores_to_weight_table(
+    scores: pd.DataFrame,
+    top_k: int,
+    *,
+    gross_exposure: float = 1.0,
+    largest: bool = True,
+) -> pd.DataFrame:
+    """逐调仓日独立构建目标权重表，避免使用未来分数。"""
+    if not isinstance(scores, pd.DataFrame):
+        raise TypeError(f"scores must be a pandas DataFrame, got {type(scores).__name__}")
+    _validate_top_k(top_k)
+    _validate_gross_exposure(gross_exposure)
+    if not scores.index.is_unique:
+        raise ValueError("scores must contain unique rebalance dates")
+    if not scores.index.is_monotonic_increasing:
+        raise ValueError("scores rebalance dates must be in chronological order")
+    if not scores.columns.is_unique:
+        raise ValueError("scores must contain unique asset labels")
+    if not all(is_numeric_dtype(dtype) for dtype in scores.dtypes):
+        raise TypeError("scores must contain numeric values")
+    if scores.empty:
+        return pd.DataFrame(index=scores.index.copy(), columns=scores.columns.copy(), dtype=float)
+
+    rows = [
+        scores_to_target_weights(
+            row,
+            top_k,
+            gross_exposure=gross_exposure,
+            largest=largest,
+        ).to_numpy()
+        for _, row in scores.iterrows()
+    ]
+    return pd.DataFrame(rows, index=scores.index.copy(), columns=scores.columns.copy(), dtype=float)

src/quant_engine/research_pipeline.py

@@ -0,0 +1,401 @@
+"""可信研究链路：因子分数经交易日历滞后后进入执行与日频 Ledger。
+
+本模块只编排现有组合构建与执行组件，不连接账户、券商或实盘订单。
+时间契约借鉴 Qlib 的 prediction/trade time 分离与 Backtrader 的 next-bar
+执行语义：signal_date 上形成的目标权重，默认最早在下一交易时点执行。
+完整回测链路进一步分离 execution price 与日末 valuation price，非调仓日也
+持续盯市，并从真实成交后持仓派生日收益和绩效。
+"""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from dataclasses import dataclass
+
+import numpy as np
+import pandas as pd
+from pandas.api.types import is_numeric_dtype
+
+from quant_engine.attribution import DailyReturnAttribution, compute_daily_return_attribution
+from quant_engine.execution import (
+    ExecutionConfig,
+    ExecutionSimulationResult,
+    simulate_daily_ledger_with_audit,
+    simulate_multi_day_with_audit,
+)
+from quant_engine.metrics import benchmark_summary, summary as metrics_summary
+from quant_engine.portfolio_construction import scores_to_weight_table
+
+__all__ = [
+    "TargetWeightSchedule",
+    "FactorExecutionResult",
+    "FactorBacktestResult",
+    "schedule_target_weights",
+    "run_factor_execution_research",
+    "run_factor_backtest_research",
+]
+
+
+@dataclass(frozen=True, slots=True, eq=False)
+class TargetWeightSchedule:
+    """保留决策时间和执行时间的目标权重调度快照。"""
+
+    decision_weights: pd.DataFrame
+    signal_to_execution: pd.Series
+    execution_weights: pd.DataFrame
+    lag_sessions: int
+
+
+@dataclass(frozen=True, slots=True, eq=False)
+class FactorExecutionResult:
+    """因子到执行审计的一次可复现研究结果。"""
+
+    factor_scores: pd.DataFrame
+    execution_prices: pd.DataFrame
+    schedule: TargetWeightSchedule
+    execution_price_field: str
+    execution: ExecutionSimulationResult
+
+
+@dataclass(frozen=True, slots=True, eq=False)
+class FactorBacktestResult:
+    """因子、成交后日频 Ledger 与绩效的一次可复现快照。"""
+
+    factor_scores: pd.DataFrame
+    execution_prices: pd.DataFrame
+    valuation_prices: pd.DataFrame
+    schedule: TargetWeightSchedule
+    execution_price_field: str
+    valuation_price_field: str
+    execution: ExecutionSimulationResult
+
+    @property
+    def nav(self) -> pd.Series:
+        """返回以初始资金归一化为 1 的日频 NAV。"""
+        return pd.Series(
+            self.execution.normalized_nav_series.to_numpy(copy=True),
+            index=self.valuation_prices.index.copy(),
+            name="nav",
+        )
+
+    @property
+    def returns(self) -> pd.Series:
+        """返回包含首日成本影响的日频收益。"""
+        return pd.Series(
+            self.execution.daily_returns.to_numpy(copy=True),
+            index=self.valuation_prices.index.copy(),
+            name="returns",
+        )
+
+    @property
+    def position_weights(self) -> pd.DataFrame:
+        """按日末实际股数、收盘估值和账本 NAV 投影资产权重。"""
+        weights = pd.DataFrame(
+            0.0,
+            index=self.valuation_prices.index.copy(),
+            columns=self.valuation_prices.columns.copy(),
+        )
+        for date, position in zip(
+            self.valuation_prices.index,
+            self.execution.positions,
+            strict=True,
+        ):
+            if position.portfolio_value <= 0:
+                raise ValueError(f"portfolio value must be positive on {date}")
+            for asset, shares in position.holdings.items():
+                weights.at[date, asset] = (
+                    shares * float(self.valuation_prices.at[date, asset])
+                    / position.portfolio_value
+                )
+        return weights
+
+    @property
+    def cash_weights(self) -> pd.Series:
+        """返回与实际资产权重使用同一日末 NAV 分母的现金权重。"""
+        values = []
+        for date, position in zip(
+            self.valuation_prices.index,
+            self.execution.positions,
+            strict=True,
+        ):
+            if position.portfolio_value <= 0:
+                raise ValueError(f"portfolio value must be positive on {date}")
+            values.append(position.cash / position.portfolio_value)
+        return pd.Series(
+            values,
+            index=self.valuation_prices.index.copy(),
+            dtype=float,
+            name="cash_weight",
+        )
+
+    def stats(self, rf: float = 0.0) -> Mapping[str, float]:
+        """复用标准绩效口径计算指标。"""
+        return metrics_summary(self.returns, rf)
+
+    def return_attribution(self) -> DailyReturnAttribution:
+        """从实际成交后持仓与账本生成逐日净收益归因。"""
+        return compute_daily_return_attribution(
+            self.execution,
+            self.execution_prices,
+            self.valuation_prices,
+        )
+
+    def benchmark_stats(self, benchmark_returns: pd.Series) -> Mapping[str, float]:
+        """计算成本后日收益相对同日基准的 TE、IR、alpha 与 beta。"""
+        return benchmark_summary(self.returns, benchmark_returns)
+
+
+def _validate_datetime_index(index: pd.Index, name: str) -> pd.DatetimeIndex:
+    if not isinstance(index, pd.DatetimeIndex):
+        raise TypeError(f"{name} must use a DatetimeIndex")
+    if not index.is_unique:
+        raise ValueError(f"{name} must contain unique sessions")
+    if not index.is_monotonic_increasing:
+        raise ValueError(f"{name} must be in chronological order")
+    return index
+
+
+def _validate_decision_weights(decision_weights: pd.DataFrame) -> None:
+    if not isinstance(decision_weights, pd.DataFrame):
+        raise TypeError(
+            f"decision_weights must be a pandas DataFrame, got {type(decision_weights).__name__}"
+        )
+    _validate_datetime_index(decision_weights.index, "decision_weights index")
+    if not decision_weights.columns.is_unique:
+        raise ValueError("decision_weights must contain unique asset labels")
+    if not all(is_numeric_dtype(dtype) for dtype in decision_weights.dtypes):
+        raise TypeError("decision_weights must contain numeric values")
+    values = decision_weights.to_numpy(dtype=float)
+    if not np.isfinite(values).all() or (values < 0).any():
+        raise ValueError("decision_weights must be finite and non-negative")
+    if (decision_weights.sum(axis=1) > 1.0 + 1e-12).any():
+        raise ValueError("decision_weights rows must sum to at most 1.0")
+
+
+def _validate_execution_prices(execution_prices: pd.DataFrame) -> pd.DatetimeIndex:
+    if not isinstance(execution_prices, pd.DataFrame):
+        raise TypeError(
+            f"execution_prices must be a pandas DataFrame, got {type(execution_prices).__name__}"
+        )
+    calendar = _validate_datetime_index(execution_prices.index, "execution_prices index")
+    if not execution_prices.columns.is_unique:
+        raise ValueError("execution_prices must contain unique asset labels")
+    if not all(is_numeric_dtype(dtype) for dtype in execution_prices.dtypes):
+        raise TypeError("execution_prices must contain numeric values")
+    return calendar
+
+
+def schedule_target_weights(
+    decision_weights: pd.DataFrame,
+    trading_calendar: pd.DatetimeIndex,
+    *,
+    lag_sessions: int = 1,
+) -> TargetWeightSchedule:
+    """将信号日目标权重映射到后续真实交易日，不做整数行盲移位。
+
+    所有信号日必须属于 ``trading_calendar``，且日历必须包含每个信号对应的
+    未来执行日；无法执行的末尾信号会显式失败，避免被静默丢弃。
+    """
+    _validate_decision_weights(decision_weights)
+    calendar = _validate_datetime_index(trading_calendar, "trading_calendar")
+    if isinstance(lag_sessions, bool) or not isinstance(lag_sessions, int) or lag_sessions <= 0:
+        raise ValueError("lag_sessions must be a positive integer")
+
+    decision_snapshot = decision_weights.copy(deep=True)
+    if decision_snapshot.empty:
+        execution_weights = decision_snapshot.copy(deep=True)
+        execution_weights.index = pd.DatetimeIndex([], name="execution_date")
+        mapping = pd.Series(
+            calendar[:0],
+            index=decision_snapshot.index.copy(),
+            name="execution_date",
+        )
+        return TargetWeightSchedule(
+            decision_weights=decision_snapshot,
+            signal_to_execution=mapping,
+            execution_weights=execution_weights,
+            lag_sessions=lag_sessions,
+        )
+
+    signal_positions = calendar.get_indexer(decision_snapshot.index)
+    if (signal_positions < 0).any():
+        missing = decision_snapshot.index[signal_positions < 0]
+        raise ValueError(
+            "signal dates must be trading sessions; missing="
+            + ", ".join(str(date) for date in missing)
+        )
+
+    execution_positions = signal_positions + lag_sessions
+    if (execution_positions >= len(calendar)).any():
+        unavailable = decision_snapshot.index[execution_positions >= len(calendar)]
+        raise ValueError(
+            "trading_calendar lacks a future execution session for signal dates: "
+            + ", ".join(str(date) for date in unavailable)
+        )
+
+    execution_dates = calendar.take(execution_positions)
+    signal_to_execution = pd.Series(
+        execution_dates,
+        index=decision_snapshot.index.copy(),
+        name="execution_date",
+    )
+    execution_weights = decision_snapshot.copy(deep=True)
+    execution_weights.index = pd.DatetimeIndex(execution_dates, name="execution_date")
+    return TargetWeightSchedule(
+        decision_weights=decision_snapshot,
+        signal_to_execution=signal_to_execution,
+        execution_weights=execution_weights,
+        lag_sessions=lag_sessions,
+    )
+
+
+def run_factor_execution_research(
+    factor_scores: pd.DataFrame,
+    execution_prices: pd.DataFrame,
+    *,
+    top_k: int,
+    execution_price_field: str,
+    lag_sessions: int = 1,
+    gross_exposure: float = 1.0,
+    largest: bool = True,
+    initial_cash: float = 1_000_000.0,
+    config: ExecutionConfig | None = None,
+) -> FactorExecutionResult:
+    """运行因子分数 → 目标权重 → 下一交易时点 → 执行审计链路。
+
+    ``execution_prices`` 必须代表实际拟执行时点的价格矩阵，例如日频研究中
+    signal 日收盘生成分数后使用下一交易日 ``open``。价格字段名称被保存在
+    结果元数据中，但函数不会猜测或重写价格语义。
+    """
+    price_field = execution_price_field.strip()
+    if not price_field:
+        raise ValueError("execution_price_field must be non-empty")
+    calendar = _validate_execution_prices(execution_prices)
+
+    factor_snapshot = factor_scores.copy(deep=True)
+    decision_weights = scores_to_weight_table(
+        factor_snapshot,
+        top_k,
+        gross_exposure=gross_exposure,
+        largest=largest,
+    )
+    schedule = schedule_target_weights(
+        decision_weights,
+        calendar,
+        lag_sessions=lag_sessions,
+    )
+    price_snapshot = execution_prices.copy(deep=True)
+
+    target_history: list[tuple[str, dict[str, float]]] = []
+    price_history: list[tuple[str, dict[str, float]]] = []
+    for execution_date, weights in schedule.execution_weights.iterrows():
+        date_label = str(pd.Timestamp(execution_date))
+        target_history.append(
+            (date_label, {asset: float(weight) for asset, weight in weights.items()})
+        )
+        prices = price_snapshot.loc[execution_date]
+        price_history.append(
+            (date_label, {asset: float(price) for asset, price in prices.items()})
+        )
+
+    execution = simulate_multi_day_with_audit(
+        target_history,
+        price_history,
+        initial_cash,
+        config,
+    )
+    return FactorExecutionResult(
+        factor_scores=factor_snapshot,
+        execution_prices=price_snapshot,
+        schedule=schedule,
+        execution_price_field=price_field,
+        execution=execution,
+    )
+
+
+def run_factor_backtest_research(
+    factor_scores: pd.DataFrame,
+    execution_prices: pd.DataFrame,
+    valuation_prices: pd.DataFrame,
+    *,
+    top_k: int,
+    execution_price_field: str,
+    valuation_price_field: str,
+    lag_sessions: int = 1,
+    gross_exposure: float = 1.0,
+    largest: bool = True,
+    initial_cash: float = 1_000_000.0,
+    config: ExecutionConfig | None = None,
+) -> FactorBacktestResult:
+    """运行 PIT 因子到成交后日频 Ledger、收益与绩效的可信研究链路。"""
+    execution_field = execution_price_field.strip()
+    valuation_field = valuation_price_field.strip()
+    if not execution_field:
+        raise ValueError("execution_price_field must be non-empty")
+    if not valuation_field:
+        raise ValueError("valuation_price_field must be non-empty")
+
+    execution_calendar = _validate_execution_prices(execution_prices)
+    valuation_calendar = _validate_execution_prices(valuation_prices)
+    if not execution_calendar.equals(valuation_calendar):
+        raise ValueError("execution and valuation prices must use matching trading calendars")
+    if not execution_prices.columns.equals(valuation_prices.columns):
+        raise ValueError("execution and valuation prices must use matching asset labels")
+
+    factor_snapshot = factor_scores.copy(deep=True)
+    execution_snapshot = execution_prices.copy(deep=True)
+    valuation_snapshot = valuation_prices.copy(deep=True)
+    decision_weights = scores_to_weight_table(
+        factor_snapshot,
+        top_k,
+        gross_exposure=gross_exposure,
+        largest=largest,
+    )
+    schedule = schedule_target_weights(
+        decision_weights,
+        execution_calendar,
+        lag_sessions=lag_sessions,
+    )
+    if decision_weights.empty:
+        execution_window = execution_snapshot.iloc[:0].copy()
+        valuation_window = valuation_snapshot.iloc[:0].copy()
+    else:
+        research_start = decision_weights.index[0]
+        execution_window = execution_snapshot.loc[research_start:].copy()
+        valuation_window = valuation_snapshot.loc[research_start:].copy()
+
+    target_history: list[tuple[str, dict[str, float]]] = []
+    execution_history: list[tuple[str, dict[str, float]]] = []
+    for execution_date, weights in schedule.execution_weights.iterrows():
+        date_label = str(pd.Timestamp(execution_date))
+        target_history.append(
+            (date_label, {asset: float(weight) for asset, weight in weights.items()})
+        )
+        prices = execution_window.loc[execution_date]
+        execution_history.append(
+            (date_label, {asset: float(price) for asset, price in prices.items()})
+        )
+
+    valuation_history = [
+        (
+            str(pd.Timestamp(valuation_date)),
+            {asset: float(price) for asset, price in prices.items()},
+        )
+        for valuation_date, prices in valuation_window.iterrows()
+    ]
+    execution = simulate_daily_ledger_with_audit(
+        target_history,
+        execution_history,
+        valuation_history,
+        initial_cash,
+        config,
+    )
+    return FactorBacktestResult(
+        factor_scores=factor_snapshot,
+        execution_prices=execution_window,
+        valuation_prices=valuation_window,
+        schedule=schedule,
+        execution_price_field=execution_field,
+        valuation_price_field=valuation_field,
+        execution=execution,
+    )

src/quant_engine/risk.py

@@ -5,10 +5,310 @@
 
 from __future__ import annotations
 
-import numpy as np
+import hashlib
-from numpy.typing import NDArray
+import json
+from dataclasses import dataclass
+from datetime import date
 from typing import Any
 
+import numpy as np
+import pandas as pd
+from numpy.typing import NDArray
+
+__all__ = [
+    "ComponentRiskResult",
+    "CovarianceSnapshot",
+    "component_var",
+    "estimate_covariance_snapshot",
+    "labeled_component_risk",
+    "marginal_risk_contribution",
+    "risk_contribution",
+]
+
+
+@dataclass(frozen=True, slots=True, init=False, eq=False)
+class CovarianceSnapshot:
+    """Immutable-by-interface covariance input with explicit time semantics."""
+
+    snapshot_id: str
+    as_of_date: date
+    _covariance: pd.DataFrame
+    return_frequency: str
+    periods_per_year: int
+    method: str
+    window_start_date: date | None
+    window_end_date: date | None
+    observations: int | None
+    lookback_sessions: int | None
+    missing_policy: str
+    data_snapshot_id: str
+    input_sha256: str
+
+    def __init__(
+        self,
+        *,
+        snapshot_id: str,
+        as_of_date: str | date | pd.Timestamp,
+        covariance: pd.DataFrame,
+        return_frequency: str,
+        periods_per_year: int,
+        method: str = "provided",
+        window_start_date: str | date | pd.Timestamp | None = None,
+        window_end_date: str | date | pd.Timestamp | None = None,
+        observations: int | None = None,
+        lookback_sessions: int | None = None,
+        missing_policy: str = "provided",
+        data_snapshot_id: str = "",
+        input_sha256: str = "",
+    ) -> None:
+        if not isinstance(snapshot_id, str) or not snapshot_id.strip():
+            raise ValueError("snapshot_id must be non-empty")
+        if not isinstance(return_frequency, str) or not return_frequency.strip():
+            raise ValueError("return_frequency must be non-empty")
+        if isinstance(periods_per_year, bool) or not isinstance(periods_per_year, int):
+            raise TypeError("periods_per_year must be an integer")
+        if periods_per_year <= 0:
+            raise ValueError("periods_per_year must be positive")
+        if not isinstance(covariance, pd.DataFrame):
+            raise TypeError("covariance must be a pandas DataFrame")
+        if covariance.empty:
+            raise ValueError("covariance must contain at least one asset")
+        if not isinstance(method, str) or not method.strip():
+            raise ValueError("method must be non-empty")
+        if not isinstance(missing_policy, str) or not missing_policy.strip():
+            raise ValueError("missing_policy must be non-empty")
+        for value, name in (
+            (observations, "observations"),
+            (lookback_sessions, "lookback_sessions"),
+        ):
+            if value is not None and (
+                isinstance(value, bool) or not isinstance(value, int) or value <= 0
+            ):
+                raise ValueError(f"{name} must be a positive integer when provided")
+        if input_sha256 and (
+            len(input_sha256) != 64
+            or any(character not in "0123456789abcdef" for character in input_sha256)
+        ):
+            raise ValueError("input_sha256 must be a lowercase SHA-256 digest")
+
+        normalized_as_of = _normalized_date(as_of_date, "as_of_date")
+        normalized_window_start = (
+            None
+            if window_start_date is None
+            else _normalized_date(window_start_date, "window_start_date")
+        )
+        normalized_window_end = (
+            None
+            if window_end_date is None
+            else _normalized_date(window_end_date, "window_end_date")
+        )
+        if (normalized_window_start is None) != (normalized_window_end is None):
+            raise ValueError("window_start_date and window_end_date must be provided together")
+        if (
+            normalized_window_start is not None
+            and normalized_window_end is not None
+            and normalized_window_start > normalized_window_end
+        ):
+            raise ValueError("window_start_date must not be after window_end_date")
+        if normalized_window_end is not None and normalized_window_end > normalized_as_of:
+            raise ValueError("window_end_date must not be after as_of_date")
+
+        object.__setattr__(self, "snapshot_id", snapshot_id.strip())
+        object.__setattr__(self, "as_of_date", normalized_as_of)
+        object.__setattr__(self, "_covariance", covariance.copy(deep=True))
+        object.__setattr__(self, "return_frequency", return_frequency.strip())
+        object.__setattr__(self, "periods_per_year", periods_per_year)
+        object.__setattr__(self, "method", method.strip())
+        object.__setattr__(self, "window_start_date", normalized_window_start)
+        object.__setattr__(self, "window_end_date", normalized_window_end)
+        object.__setattr__(self, "observations", observations)
+        object.__setattr__(self, "lookback_sessions", lookback_sessions)
+        object.__setattr__(self, "missing_policy", missing_policy.strip())
+        object.__setattr__(self, "data_snapshot_id", data_snapshot_id.strip())
+        object.__setattr__(self, "input_sha256", input_sha256)
+
+    @property
+    def covariance(self) -> pd.DataFrame:
+        """Return an isolated copy so callers cannot mutate the snapshot."""
+        return self._covariance.copy(deep=True)
+
+
+def _normalized_date(value: object, name: str) -> date:
+    try:
+        timestamp = pd.Timestamp(value)
+    except (TypeError, ValueError) as error:
+        raise ValueError(f"{name} must be a valid date") from error
+    if pd.isna(timestamp):
+        raise ValueError(f"{name} must be a valid date")
+    return date(int(timestamp.year), int(timestamp.month), int(timestamp.day))
+
+
+def _positive_integer(value: int, name: str, *, minimum: int = 1) -> int:
+    if isinstance(value, bool) or not isinstance(value, int) or value < minimum:
+        raise ValueError(f"{name} must be an integer of at least {minimum}")
+    return value
+
+
+def _input_fingerprint(window: pd.DataFrame, session_dates: list[date]) -> str:
+    values = window.to_numpy(dtype=float, copy=True)
+    missing = np.isnan(values)
+    normalized = np.where(missing, 0.0, values).astype("<f8", copy=False)
+    metadata = {
+        "assets": [str(asset) for asset in window.columns],
+        "sessions": [session.isoformat() for session in session_dates],
+        "shape": list(values.shape),
+    }
+    digest = hashlib.sha256(
+        json.dumps(metadata, sort_keys=True, separators=(",", ":")).encode("utf-8")
+    )
+    digest.update(missing.astype(np.uint8, copy=False).tobytes(order="C"))
+    digest.update(normalized.tobytes(order="C"))
+    return digest.hexdigest()
+
+
+def estimate_covariance_snapshot(
+    asset_returns: pd.DataFrame,
+    *,
+    as_of_date: str | date | pd.Timestamp,
+    lookback_sessions: int,
+    min_observations: int,
+    data_snapshot_id: str,
+    return_frequency: str = "1d",
+    periods_per_year: int = 252,
+) -> CovarianceSnapshot:
+    """Estimate a deterministic per-period sample covariance without look-ahead.
+
+    The selected lookback window is truncated at ``as_of_date`` before any
+    calculation. Rows containing a missing asset return are removed as complete
+    cases, preventing pairwise sample sets from producing an ambiguous matrix.
+    """
+    if not isinstance(asset_returns, pd.DataFrame):
+        raise TypeError("asset_returns must be a pandas DataFrame")
+    if asset_returns.empty or asset_returns.shape[1] == 0:
+        raise ValueError("asset_returns must contain observations and assets")
+    if not isinstance(asset_returns.index, pd.DatetimeIndex):
+        raise TypeError("asset_returns index must be a DatetimeIndex")
+    if not asset_returns.index.is_unique or not asset_returns.index.is_monotonic_increasing:
+        raise ValueError("asset_returns index must be unique and strictly increasing")
+    if not asset_returns.columns.is_unique:
+        raise ValueError("asset_returns must contain unique asset labels")
+    if any(not isinstance(asset, str) or not asset.strip() for asset in asset_returns.columns):
+        raise ValueError("asset_returns asset labels must be non-empty strings")
+
+    lookback = _positive_integer(lookback_sessions, "lookback_sessions")
+    minimum = _positive_integer(min_observations, "min_observations", minimum=2)
+    if minimum > lookback:
+        raise ValueError("min_observations must not exceed lookback_sessions")
+    normalized_data_snapshot_id = data_snapshot_id.strip()
+    if not normalized_data_snapshot_id:
+        raise ValueError("data_snapshot_id must be non-empty")
+    normalized_as_of = _normalized_date(as_of_date, "as_of_date")
+
+    returns = asset_returns.astype(float, copy=True)
+    values = returns.to_numpy()
+    if np.isinf(values).any():
+        raise ValueError("asset_returns must not contain infinite values")
+    session_dates = [
+        _normalized_date(index_value, "asset_returns index") for index_value in returns.index
+    ]
+    if len(set(session_dates)) != len(session_dates):
+        raise ValueError("asset_returns must contain at most one observation per session date")
+    historical_mask = [session <= normalized_as_of for session in session_dates]
+    window = returns.loc[historical_mask].tail(lookback)
+    if window.empty:
+        raise ValueError("asset_returns contain no observations on or before as_of_date")
+    window_dates = [
+        _normalized_date(index_value, "asset_returns index") for index_value in window.index
+    ]
+    complete = window.dropna(axis=0, how="any")
+    if len(complete) < minimum:
+        raise ValueError(
+            f"complete observations must be at least {minimum}; received {len(complete)}"
+        )
+
+    covariance = complete.cov(ddof=1)
+    covariance_values = covariance.to_numpy()
+    if not np.isfinite(covariance_values).all():
+        raise ValueError("sample covariance must be finite")
+    input_sha256 = _input_fingerprint(window, window_dates)
+    identity = {
+        "as_of_date": normalized_as_of.isoformat(),
+        "assets": list(returns.columns),
+        "data_snapshot_id": normalized_data_snapshot_id,
+        "estimator": "sample-cov-v1",
+        "input_sha256": input_sha256,
+        "lookback_sessions": lookback,
+        "min_observations": minimum,
+        "missing_policy": "complete_case",
+        "observations": len(complete),
+        "periods_per_year": periods_per_year,
+        "return_frequency": return_frequency,
+        "window_end_date": window_dates[-1].isoformat(),
+        "window_start_date": window_dates[0].isoformat(),
+    }
+    identity_bytes = json.dumps(
+        identity,
+        sort_keys=True,
+        separators=(",", ":"),
+    ).encode("utf-8")
+    digest = hashlib.sha256(identity_bytes)
+    digest.update(covariance_values.astype("<f8", copy=False).tobytes(order="C"))
+    snapshot_id = f"sample-cov-v1:{digest.hexdigest()}"
+    return CovarianceSnapshot(
+        snapshot_id=snapshot_id,
+        as_of_date=normalized_as_of,
+        covariance=covariance,
+        return_frequency=return_frequency,
+        periods_per_year=periods_per_year,
+        method="sample",
+        window_start_date=window_dates[0],
+        window_end_date=window_dates[-1],
+        observations=len(complete),
+        lookback_sessions=lookback,
+        missing_policy="complete_case",
+        data_snapshot_id=normalized_data_snapshot_id,
+        input_sha256=input_sha256,
+    )
+
+
+@dataclass(frozen=True, slots=True, eq=False)
+class ComponentRiskResult:
+    """Label-preserving Euler decomposition of portfolio volatility."""
+
+    portfolio_volatility: float
+    marginal: pd.Series
+    component: pd.Series
+    percentage: pd.Series
+
+    def grouped_component(self, groups: pd.Series) -> pd.Series:
+        """Aggregate asset component risk by an explicitly aligned label series."""
+        if not isinstance(groups, pd.Series):
+            raise TypeError("groups must be a pandas Series")
+        if not groups.index.is_unique:
+            raise ValueError("groups must contain unique asset labels")
+        if not self.component.index.difference(groups.index).empty or not groups.index.difference(
+            self.component.index
+        ).empty:
+            raise ValueError("groups and component risk must use the same asset labels")
+        aligned = groups.reindex(self.component.index)
+        if aligned.isna().any():
+            raise ValueError("groups must contain a non-missing label for every asset")
+        grouped = self.component.groupby(aligned, sort=True).sum()
+        grouped.name = "component_risk"
+        return grouped
+
+
+def _validate_inputs(weights: NDArray[Any], cov: NDArray[Any]) -> tuple[NDArray[Any], NDArray[Any]]:
+    """Normalize a portfolio vector and its covariance matrix."""
+    w = np.asarray(weights, dtype=float).ravel()
+    covariance = np.asarray(cov, dtype=float)
+    k = w.size
+    if k == 0:
+        raise ValueError("weights must contain at least one asset")
+    if covariance.shape != (k, k):
+        raise ValueError(f"cov shape {covariance.shape} does not match weights length {k}")
+    return w, covariance
+
 
 def risk_contribution(weights: NDArray[Any], cov: NDArray[Any]) -> NDArray[Any]:
     """风险贡献率 (RC_i): w_i * (Σw)_i / w'Σw。
@@ -25,11 +325,8 @@ def risk_contribution(weights: NDArray[Any], cov: NDArray[Any]) -> NDArray[Any]:
     Returns:
         RC: 风险贡献向量 (k,), Σ=1
     """
-    w = np.asarray(weights, dtype=float).ravel()
+    w, cov = _validate_inputs(weights, cov)
-    cov = np.asarray(cov, dtype=float)
     k = w.size
-    if cov.shape != (k, k):
-        raise ValueError(f"cov 形状 {cov.shape} 与 weights 长度 {k} 不匹配")
 
     port_var = float(w @ cov @ w)
     if port_var <= 0:
@@ -41,13 +338,78 @@ def risk_contribution(weights: NDArray[Any], cov: NDArray[Any]) -> NDArray[Any]:
 
 def marginal_risk_contribution(weights: NDArray[Any], cov: NDArray[Any]) -> NDArray[Any]:
     """边际风险贡献 (MRC_i): (Σw)_i。"""
-    w = np.asarray(weights, dtype=float).ravel()
+    w, cov = _validate_inputs(weights, cov)
-    cov = np.asarray(cov, dtype=float)
     return cov @ w  # type: ignore[no-any-return]
 
 
 def component_var(weights: NDArray[Any], cov: NDArray[Any]) -> NDArray[Any]:
     """成分方差: w_i · (Σw)_i; 与 RC 的关系 RC_i = CV_i / w'Σw。"""
-    w = np.asarray(weights, dtype=float).ravel()
+    w, cov = _validate_inputs(weights, cov)
-    cov = np.asarray(cov, dtype=float)
     return w * (cov @ w)  # type: ignore[no-any-return]
+
+
+def labeled_component_risk(
+    weights: pd.Series,
+    covariance: pd.DataFrame,
+) -> ComponentRiskResult:
+    """Return a label-safe Euler decomposition that sums to portfolio volatility.
+
+    The covariance matrix may use a different asset order, but its row and
+    column label sets must exactly match ``weights``.  Invalid or indefinite
+    covariance input is rejected instead of silently producing misleading risk
+    percentages.
+    """
+    if not isinstance(weights, pd.Series):
+        raise TypeError("weights must be a pandas Series")
+    if not isinstance(covariance, pd.DataFrame):
+        raise TypeError("covariance must be a pandas DataFrame")
+    if weights.empty:
+        raise ValueError("weights must contain at least one asset")
+    if not weights.index.is_unique:
+        raise ValueError("weights must contain unique asset labels")
+    if not covariance.index.is_unique or not covariance.columns.is_unique:
+        raise ValueError("covariance must contain unique asset labels")
+    if not weights.index.difference(covariance.index).empty or not covariance.index.difference(
+        weights.index
+    ).empty:
+        raise ValueError("weights and covariance must use the same asset labels")
+    if not weights.index.difference(covariance.columns).empty or not covariance.columns.difference(
+        weights.index
+    ).empty:
+        raise ValueError("weights and covariance must use the same asset labels")
+
+    aligned_weights = weights.astype(float, copy=True)
+    aligned_covariance = covariance.reindex(
+        index=weights.index,
+        columns=weights.index,
+    ).astype(float, copy=True)
+    weight_values = aligned_weights.to_numpy()
+    covariance_values = aligned_covariance.to_numpy()
+    if not np.isfinite(weight_values).all():
+        raise ValueError("weights must be finite")
+    if not np.isfinite(covariance_values).all():
+        raise ValueError("covariance must be finite")
+    if not np.allclose(covariance_values, covariance_values.T, rtol=1e-10, atol=1e-12):
+        raise ValueError("covariance must be symmetric")
+    eigenvalues = np.linalg.eigvalsh(covariance_values)
+    scale = max(1.0, float(np.max(np.abs(eigenvalues))))
+    if float(eigenvalues.min()) < -1e-10 * scale:
+        raise ValueError("covariance must be positive semidefinite")
+
+    portfolio_variance = float(weight_values @ covariance_values @ weight_values)
+    if portfolio_variance <= 0 or not np.isfinite(portfolio_variance):
+        raise ValueError("weights and covariance must produce positive portfolio variance")
+    portfolio_volatility = float(np.sqrt(portfolio_variance))
+    marginal_values = covariance_values @ weight_values / portfolio_volatility
+    component_values = weight_values * marginal_values
+    percentage_values = component_values / portfolio_volatility
+    return ComponentRiskResult(
+        portfolio_volatility=portfolio_volatility,
+        marginal=pd.Series(marginal_values, index=weights.index.copy(), name="marginal_risk"),
+        component=pd.Series(component_values, index=weights.index.copy(), name="component_risk"),
+        percentage=pd.Series(
+            percentage_values,
+            index=weights.index.copy(),
+            name="risk_contribution",
+        ),
+    )

tests/test_artifact.py

@@ -0,0 +1,309 @@
+"""Stable research-run artifact contracts for downstream persistence."""
+
+from __future__ import annotations
+
+import json
+from datetime import date
+
+import pandas as pd
+import pytest
+
+from quant_engine.artifact import (
+    RESEARCH_ARTIFACT_SCHEMA_VERSION,
+    ResearchRunArtifact,
+    build_research_run_artifact,
+)
+from quant_engine.execution import ExecutionConfig
+from quant_engine.research_pipeline import FactorBacktestResult, run_factor_backtest_research
+from quant_engine.risk import CovarianceSnapshot
+
+
+def _backtest_result() -> FactorBacktestResult:
+    dates = pd.date_range("2026-01-05", periods=4, freq="B")
+    scores = pd.DataFrame(
+        {"A": [2.0, 0.0], "B": [1.0, 3.0]},
+        index=dates[:2],
+    )
+    opens = pd.DataFrame(
+        {"A": [10.0, 10.0, 15.0, 15.0], "B": [20.0, 20.0, 20.0, 21.0]},
+        index=dates,
+    )
+    closes = pd.DataFrame(
+        {"A": [10.0, 12.0, 15.0, 15.0], "B": [20.0, 20.0, 18.0, 21.0]},
+        index=dates,
+    )
+    return run_factor_backtest_research(
+        scores,
+        opens,
+        closes,
+        top_k=1,
+        execution_price_field="open",
+        valuation_price_field="close",
+        initial_cash=1_000.0,
+        config=ExecutionConfig(
+            commission_bps=0,
+            stamp_tax_bps=0,
+            slippage_bps=0,
+            min_trade_amount=0,
+        ),
+    )
+
+
+def _build(
+    result: FactorBacktestResult,
+    *,
+    parameters: dict[str, object] | None = None,
+    risk_snapshots: dict[date, CovarianceSnapshot] | None = None,
+) -> ResearchRunArtifact:
+    benchmark = pd.Series(
+        [0.0, 0.01, -0.01, 0.02],
+        index=result.returns.index,
+        name="benchmark_return",
+    )
+    return build_research_run_artifact(
+        result,
+        run_id="run-20260105-a",
+        strategy_id="alpha-top1",
+        strategy_name="Alpha Top 1",
+        strategy_version="1.0.0",
+        engine_version="1.2.0",
+        code_revision="3b1ad07",
+        data_snapshot_id="qtdb-pro-20260108-v1",
+        calendar="CN-A",
+        timezone="Asia/Shanghai",
+        started_at="2026-01-08T10:00:00+08:00",
+        finished_at="2026-01-08T10:01:00+08:00",
+        parameters=parameters or {"top_k": 1, "lag_sessions": 1},
+        benchmark_id="000300.SH",
+        benchmark_returns=benchmark,
+        risk_snapshots=risk_snapshots,
+    )
+
+
+def test_research_artifact_projects_versioned_queryable_fact_tables() -> None:
+    result = _backtest_result()
+
+    artifact = _build(result)
+
+    assert artifact.schema_version == RESEARCH_ARTIFACT_SCHEMA_VERSION
+    assert artifact.run.loc[0, "run_id"] == "run-20260105-a"
+    assert artifact.run.loc[0, "benchmark_alignment_policy"] == "exact_session_index"
+    assert artifact.nav["run_id"].unique().tolist() == ["run-20260105-a"]
+    assert artifact.nav["pnl_pct"].tolist() == pytest.approx(result.returns.tolist())
+    assert artifact.nav["benchmark_return"].tolist() == pytest.approx(
+        [0.0, 0.01, -0.01, 0.02]
+    )
+    assert artifact.signals.columns.tolist() == [
+        "run_id",
+        "signal_date",
+        "execution_date",
+        "asset_id",
+        "factor_score",
+        "target_weight",
+    ]
+    first_signal = artifact.signals[
+        artifact.signals["signal_date"] == result.factor_scores.index[0].date()
+    ]
+    assert first_signal.set_index("asset_id").loc["A", "factor_score"] == 2.0
+    assert first_signal.set_index("asset_id").loc["A", "target_weight"] == 1.0
+    assert first_signal["execution_date"].unique().tolist() == [
+        result.schedule.signal_to_execution.iloc[0].date()
+    ]
+    assert set(artifact.trades["side"]) == {"buy", "sell"}
+    assert artifact.trades["trade_id"].is_unique
+    assert artifact.trades["trade_id"].str.startswith("run-20260105-a:").all()
+    assert artifact.trades["signal_id"].str.startswith("run-20260105-a:signal:").all()
+    assert {"security", "cash"}.issubset(set(artifact.positions["asset_type"]))
+    assert artifact.positions.groupby("trade_date")["weight"].sum().tolist() == pytest.approx(
+        [1.0, 1.0, 1.0, 1.0]
+    )
+    assert set(artifact.attribution.columns) == {
+        "run_id",
+        "trade_date",
+        "asset_id",
+        "overnight",
+        "intraday",
+        "asset_total",
+    }
+    assert artifact.attribution_daily["residual"].abs().max() < 1e-12
+    assert artifact.risk.empty
+    assert artifact.risk.columns.tolist() == [
+        "run_id",
+        "trade_date",
+        "asset_id",
+        "weight",
+        "marginal_risk",
+        "component_risk",
+        "risk_contribution",
+        "covariance_snapshot_id",
+        "covariance_as_of_date",
+        "risk_measure",
+        "return_frequency",
+        "periods_per_year",
+    ]
+    assert artifact.performance.loc[0, "n_trades"] == len(artifact.trades)
+    assert artifact.performance.loc[0, "ir"] == pytest.approx(
+        result.benchmark_stats(pd.Series([0.0, 0.01, -0.01, 0.02], index=result.returns.index))[
+            "information_ratio"
+        ]
+    )
+    assert "sortino" in artifact.performance.columns
+
+
+def test_research_artifact_projects_annualized_risk_from_actual_positions() -> None:
+    result = _backtest_result()
+    trade_date = result.position_weights.index[-1].date()
+    covariance = pd.DataFrame(
+        [[0.0001, 0.00002], [0.00002, 0.0004]],
+        index=["A", "B"],
+        columns=["A", "B"],
+    )
+    snapshot = CovarianceSnapshot(
+        snapshot_id="cov-20260107-v1",
+        as_of_date="2026-01-07",
+        covariance=covariance,
+        return_frequency="1d",
+        periods_per_year=252,
+        data_snapshot_id="qtdb-pro-20260108-v1",
+    )
+
+    artifact = _build(result, risk_snapshots={trade_date: snapshot})
+
+    risk = artifact.risk.set_index("asset_id")
+    expected_weights = result.position_weights.loc[pd.Timestamp(trade_date)]
+    assert artifact.schema_version == "1.1.0"
+    assert risk.index.tolist() == ["A", "B"]
+    assert risk["weight"].tolist() == pytest.approx(expected_weights.tolist())
+    assert risk["covariance_snapshot_id"].unique().tolist() == ["cov-20260107-v1"]
+    assert risk["covariance_as_of_date"].unique().tolist() == [date(2026, 1, 7)]
+    assert risk["risk_measure"].unique().tolist() == ["annualized_volatility"]
+    assert risk["return_frequency"].unique().tolist() == ["1d"]
+    assert risk["periods_per_year"].unique().tolist() == [252]
+    assert risk["component_risk"].sum() == pytest.approx((0.0004 * 252) ** 0.5)
+    assert risk["risk_contribution"].sum() == pytest.approx(1.0)
+
+
+def test_research_artifact_rejects_risk_from_a_different_data_snapshot() -> None:
+    result = _backtest_result()
+    trade_date = result.position_weights.index[-1].date()
+    covariance = pd.DataFrame(
+        [[0.0001, 0.0], [0.0, 0.0004]],
+        index=["A", "B"],
+        columns=["A", "B"],
+    )
+
+    with pytest.raises(ValueError, match="data lineage differs"):
+        _build(
+            result,
+            risk_snapshots={
+                trade_date: CovarianceSnapshot(
+                    snapshot_id="foreign-covariance",
+                    as_of_date="2026-01-07",
+                    covariance=covariance,
+                    return_frequency="1d",
+                    periods_per_year=252,
+                    data_snapshot_id="different-market-snapshot",
+                )
+            },
+        )
+
+
+def test_research_artifact_rejects_future_or_misaligned_risk_snapshots() -> None:
+    result = _backtest_result()
+    trade_date = result.position_weights.index[-1].date()
+    covariance = pd.DataFrame(
+        [[0.0001, 0.0], [0.0, 0.0004]],
+        index=["A", "B"],
+        columns=["A", "B"],
+    )
+
+    with pytest.raises(ValueError, match="must not be after trade date"):
+        _build(
+            result,
+            risk_snapshots={
+                trade_date: CovarianceSnapshot(
+                    snapshot_id="future-covariance",
+                    as_of_date="2026-01-09",
+                    covariance=covariance,
+                    return_frequency="1d",
+                    periods_per_year=252,
+                    data_snapshot_id="qtdb-pro-20260108-v1",
+                )
+            },
+        )
+
+    with pytest.raises(ValueError, match="same asset labels"):
+        _build(
+            result,
+            risk_snapshots={
+                trade_date: CovarianceSnapshot(
+                    snapshot_id="incomplete-universe",
+                    as_of_date="2026-01-07",
+                    covariance=covariance.loc[["B"], ["B"]],
+                    return_frequency="1d",
+                    periods_per_year=252,
+                    data_snapshot_id="qtdb-pro-20260108-v1",
+                )
+            },
+        )
+
+
+def test_research_artifact_serialization_and_hashes_are_deterministic() -> None:
+    result = _backtest_result()
+    first = _build(result, parameters={"top_k": 1, "lag_sessions": 1})
+    second = _build(result, parameters={"lag_sessions": 1, "top_k": 1})
+
+    assert first.run.loc[0, "config_hash"] == second.run.loc[0, "config_hash"]
+    assert first.content_sha256 == second.content_sha256
+    assert first.manifest() == second.manifest()
+    decoded = json.loads(first.canonical_json())
+    assert decoded["schema_version"] == RESEARCH_ARTIFACT_SCHEMA_VERSION
+    assert decoded["tables"]["nav"][0]["trade_date"] == "2026-01-05"
+
+    leaked_copy = first.nav
+    leaked_copy.loc[0, "nav"] = -999.0
+    assert first.nav.loc[0, "nav"] != -999.0
+    assert first.content_sha256 == second.content_sha256
+
+
+def test_research_artifact_requires_complete_reproducibility_identity() -> None:
+    result = _backtest_result()
+
+    with pytest.raises(ValueError, match="code_revision"):
+        build_research_run_artifact(
+            result,
+            run_id="run-1",
+            strategy_id="alpha-top1",
+            strategy_name="Alpha Top 1",
+            strategy_version="1.0.0",
+            engine_version="1.2.0",
+            code_revision="",
+            data_snapshot_id="snapshot-1",
+            calendar="CN-A",
+            timezone="Asia/Shanghai",
+            started_at="2026-01-08T10:00:00+08:00",
+            finished_at="2026-01-08T10:01:00+08:00",
+            parameters={},
+        )
+
+
+def test_research_artifact_requires_benchmark_identity_and_returns_together() -> None:
+    result = _backtest_result()
+
+    with pytest.raises(ValueError, match="benchmark_id and benchmark_returns"):
+        build_research_run_artifact(
+            result,
+            run_id="run-1",
+            strategy_id="alpha-top1",
+            strategy_name="Alpha Top 1",
+            strategy_version="1.0.0",
+            engine_version="1.2.0",
+            code_revision="3b1ad07",
+            data_snapshot_id="snapshot-1",
+            calendar="CN-A",
+            timezone="Asia/Shanghai",
+            started_at="2026-01-08T10:00:00+08:00",
+            finished_at="2026-01-08T10:01:00+08:00",
+            parameters={},
+            benchmark_id="000300.SH",
+        )

tests/test_attribution.py

@@ -0,0 +1,118 @@
+"""Post-execution return attribution contracts."""
+
+from __future__ import annotations
+
+import pandas as pd
+import pytest
+
+from quant_engine.attribution import DailyReturnAttribution
+from quant_engine.execution import ExecutionConfig
+from quant_engine.research_pipeline import run_factor_backtest_research
+
+
+def _zero_cost_config() -> ExecutionConfig:
+    return ExecutionConfig(
+        commission_bps=0,
+        stamp_tax_bps=0,
+        slippage_bps=0,
+        min_trade_amount=0,
+    )
+
+
+def test_daily_attribution_closes_across_rebalance_and_holding_days() -> None:
+    """开盘换仓时，隔夜和日内贡献必须来自实际换仓前后持仓。"""
+    dates = pd.date_range("2026-01-05", periods=4, freq="B")
+    scores = pd.DataFrame(
+        {"A": [2.0, 0.0], "B": [1.0, 3.0]},
+        index=dates[:2],
+    )
+    opens = pd.DataFrame(
+        {"A": [10.0, 10.0, 15.0, 15.0], "B": [20.0, 20.0, 20.0, 21.0]},
+        index=dates,
+    )
+    closes = pd.DataFrame(
+        {"A": [10.0, 12.0, 15.0, 15.0], "B": [20.0, 20.0, 18.0, 21.0]},
+        index=dates,
+    )
+    result = run_factor_backtest_research(
+        scores,
+        opens,
+        closes,
+        top_k=1,
+        execution_price_field="open",
+        valuation_price_field="close",
+        initial_cash=1_000.0,
+        config=_zero_cost_config(),
+    )
+
+    attribution = result.return_attribution()
+
+    assert isinstance(attribution, DailyReturnAttribution)
+    assert attribution.overnight.loc[dates[2], "A"] == pytest.approx(0.25)
+    assert attribution.intraday.loc[dates[2], "B"] == pytest.approx(-0.125)
+    assert attribution.asset_contributions.loc[dates[3], "B"] == pytest.approx(1 / 6)
+    pd.testing.assert_series_equal(
+        attribution.total_return,
+        result.returns.rename("total_return"),
+    )
+    pd.testing.assert_series_equal(
+        attribution.explained_return + attribution.residual,
+        attribution.total_return,
+        check_names=False,
+    )
+    assert attribution.residual.abs().max() < 1e-12
+
+
+def test_daily_attribution_reports_execution_cost_separately() -> None:
+    dates = pd.date_range("2026-01-05", periods=3, freq="B")
+    scores = pd.DataFrame({"A": [1.0]}, index=dates[:1])
+    prices = pd.DataFrame({"A": [10.0, 10.0, 10.0]}, index=dates)
+    config = ExecutionConfig(
+        commission_bps=10,
+        stamp_tax_bps=0,
+        slippage_bps=10,
+        min_trade_amount=0,
+    )
+    result = run_factor_backtest_research(
+        scores,
+        prices,
+        prices,
+        top_k=1,
+        gross_exposure=0.5,
+        execution_price_field="open",
+        valuation_price_field="close",
+        initial_cash=1_000.0,
+        config=config,
+    )
+
+    attribution = result.return_attribution()
+    execution = result.execution.daily_executions[1].executions[0]
+
+    assert attribution.asset_contributions.loc[dates[1], "A"] == 0.0
+    assert attribution.transaction_cost.loc[dates[1]] == pytest.approx(
+        -execution.total_cost / 1_000.0
+    )
+    assert attribution.total_return.loc[dates[1]] == pytest.approx(
+        attribution.transaction_cost.loc[dates[1]]
+    )
+    assert attribution.residual.loc[dates[1]] == pytest.approx(0.0, abs=1e-12)
+
+
+def test_return_attribution_is_empty_for_empty_research_result() -> None:
+    dates = pd.date_range("2026-01-05", periods=3, freq="B")
+    scores = pd.DataFrame(columns=["A"], index=pd.DatetimeIndex([]), dtype=float)
+    prices = pd.DataFrame({"A": [10.0, 10.0, 10.0]}, index=dates)
+    result = run_factor_backtest_research(
+        scores,
+        prices,
+        prices,
+        top_k=1,
+        execution_price_field="open",
+        valuation_price_field="close",
+    )
+
+    attribution = result.return_attribution()
+
+    assert attribution.overnight.empty
+    assert attribution.intraday.empty
+    assert attribution.total_return.empty

tests/test_backtest.py

@@ -0,0 +1,209 @@
+"""Backtest contract tests for weights, NAV, rebalancing, and benchmarks."""
+
+from __future__ import annotations
+
+import pandas as pd
+import pytest
+
+from quant_engine.backtest import (
+    BacktestResult,
+    compare_to_benchmark,
+    compute_nav_from_weights,
+    compute_returns_from_nav,
+    rebalance_periodic,
+    run_weight_backtest,
+    weights_to_long_short,
+)
+
+
+def test_compute_nav_from_weights_forward_fills_rebalance_weights() -> None:
+    dates = pd.date_range("2026-01-05", periods=3, freq="B")
+    weights = pd.DataFrame({"A": [0.5], "B": [0.5]}, index=dates[:1])
+    returns = pd.DataFrame({"A": [0.10, 0.00, -0.10], "B": [0.00, 0.10, 0.00]}, index=dates)
+
+    nav = compute_nav_from_weights(weights, returns, initial_capital=100.0)
+
+    expected = pd.Series([105.0, 110.25, 104.7375], index=dates)
+    pd.testing.assert_series_equal(nav, expected)
+
+
+def test_compute_nav_stays_in_cash_before_first_rebalance() -> None:
+    dates = pd.date_range("2026-01-05", periods=3, freq="B")
+    weights = pd.DataFrame({"A": [1.0]}, index=dates[1:2])
+    returns = pd.DataFrame({"A": [0.50, 0.10, 0.10]}, index=dates)
+
+    nav = compute_nav_from_weights(weights, returns)
+
+    pd.testing.assert_series_equal(nav, pd.Series([1.0, 1.1, 1.21], index=dates))
+
+
+def test_compute_nav_ignores_weight_columns_without_returns() -> None:
+    dates = pd.date_range("2026-01-05", periods=2, freq="B")
+    weights = pd.DataFrame({"A": [0.5], "MISSING": [0.5]}, index=dates[:1])
+    returns = pd.DataFrame({"A": [0.10, 0.10]}, index=dates)
+
+    nav = compute_nav_from_weights(weights, returns)
+
+    pd.testing.assert_series_equal(nav, pd.Series([1.05, 1.1025], index=dates))
+
+
+def test_compute_nav_charges_configured_turnover_cost() -> None:
+    dates = pd.date_range("2026-01-05", periods=2, freq="B")
+    weights = pd.DataFrame({"A": [1.0]}, index=dates[:1])
+    returns = pd.DataFrame({"A": [0.0, 0.0]}, index=dates)
+
+    nav = compute_nav_from_weights(weights, returns, tc_rate=0.01)
+
+    pd.testing.assert_series_equal(nav, pd.Series([0.995, 0.995], index=dates))
+
+
+def test_compute_returns_from_nav_preserves_index_and_sets_initial_zero() -> None:
+    nav = pd.Series([100.0, 110.0, 99.0], index=pd.date_range("2026-01-05", periods=3))
+
+    result = compute_returns_from_nav(nav)
+
+    pd.testing.assert_series_equal(result, pd.Series([0.0, 0.1, -0.1], index=nav.index))
+
+
+def test_rebalance_periodic_maps_weekend_to_previous_trading_day() -> None:
+    dates = pd.date_range("2026-01-05", periods=5, freq="B")
+    target = pd.Series({"A": 0.6, "B": 0.4})
+
+    result = rebalance_periodic(target, [pd.Timestamp("2026-01-10")], dates)
+
+    assert result.loc[pd.Timestamp("2026-01-08")].sum() == 0.0
+    pd.testing.assert_series_equal(
+        result.loc[pd.Timestamp("2026-01-09")], target, check_names=False
+    )
+
+
+def test_rebalance_periodic_accepts_empty_trading_calendar() -> None:
+    target = pd.Series({"A": 1.0})
+
+    result = rebalance_periodic(
+        target,
+        [pd.Timestamp("2026-01-05")],
+        pd.DatetimeIndex([]),
+    )
+
+    assert result.empty
+    assert result.columns.tolist() == ["A"]
+
+
+def test_weights_to_long_short_allocates_each_leg() -> None:
+    result = weights_to_long_short(["A", "B"], ["C"], long_weight=0.6, short_weight=0.4)
+
+    assert result["A"] == pytest.approx(0.3)
+    assert result["B"] == pytest.approx(0.3)
+    assert result["C"] == pytest.approx(-0.4)
+    assert result.sum() == pytest.approx(0.2)
+
+
+def test_weights_to_long_short_keeps_explicit_universe() -> None:
+    result = weights_to_long_short(["A"], [], all_tickers=["A", "B"])
+
+    pd.testing.assert_series_equal(result, pd.Series({"A": 0.5, "B": 0.0}))
+
+
+def test_compare_to_benchmark_returns_report_table() -> None:
+    dates = pd.date_range("2026-01-05", periods=4, freq="B")
+    strategy = pd.Series([1.0, 1.1, 1.0, 1.2], index=dates)
+    benchmark = pd.Series([1.0, 1.0, 1.05, 1.1], index=dates)
+
+    result = compare_to_benchmark(strategy, benchmark)
+
+    assert result.columns.tolist() == ["策略", "基准"]
+    assert result.loc["n_days", "策略"] == 4
+    assert result.loc["累计收益", "策略"] == pytest.approx(0.2)
+    assert result.loc["累计收益", "基准"] == pytest.approx(0.1)
+
+
+def test_compare_to_benchmark_rejects_non_overlapping_dates() -> None:
+    strategy = pd.Series([1.0], index=[pd.Timestamp("2026-01-05")])
+    benchmark = pd.Series([1.0], index=[pd.Timestamp("2026-02-05")])
+
+    with pytest.raises(ValueError, match="overlapping dates"):
+        compare_to_benchmark(strategy, benchmark)
+
+
+# ── 统一回测结果门面 ──────────────────────────────────────
+
+
+def test_run_weight_backtest_returns_nav_returns_and_input_snapshot() -> None:
+    dates = pd.date_range("2026-01-05", periods=3, freq="B")
+    weights = pd.DataFrame({"A": [1.0]}, index=dates[:1])
+    stock_returns = pd.DataFrame({"A": [0.10, -0.10, 0.20]}, index=dates)
+
+    result = run_weight_backtest(weights, stock_returns, initial_capital=100.0)
+
+    assert isinstance(result, BacktestResult)
+    pd.testing.assert_series_equal(
+        result.nav,
+        pd.Series([110.0, 99.0, 118.8], index=dates),
+    )
+    pd.testing.assert_series_equal(
+        result.returns,
+        pd.Series([0.0, -0.1, 0.2], index=dates),
+    )
+    pd.testing.assert_frame_equal(result.weights, weights)
+
+
+def test_backtest_result_stats_reuses_standard_metrics_contract() -> None:
+    dates = pd.date_range("2026-01-05", periods=3, freq="B")
+    result = run_weight_backtest(
+        pd.DataFrame({"A": [1.0]}, index=dates[:1]),
+        pd.DataFrame({"A": [0.10, -0.10, 0.20]}, index=dates),
+    )
+
+    stats = result.stats(rf=0.02)
+
+    assert stats["n_days"] == 3
+    assert stats["ann_return"] == pytest.approx(
+        (1.0 * 0.9 * 1.2) ** (252 / 3) - 1.0
+    )
+    assert "sharpe" in stats
+    assert stats["drawback"] == stats["max_drawdown"]
+
+
+def test_backtest_result_builds_benchmark_report() -> None:
+    dates = pd.date_range("2026-01-05", periods=3, freq="B")
+    benchmark = pd.Series([1.0, 1.05, 1.10], index=dates, name="benchmark")
+    result = run_weight_backtest(
+        pd.DataFrame({"A": [1.0]}, index=dates[:1]),
+        pd.DataFrame({"A": [0.10, -0.10, 0.20]}, index=dates),
+        benchmark_nav=benchmark,
+    )
+
+    report = result.benchmark_report()
+
+    assert report.columns.tolist() == ["策略", "基准"]
+    assert report.loc["累计收益", "基准"] == pytest.approx(0.10)
+
+
+def test_backtest_result_requires_benchmark_for_comparison() -> None:
+    dates = pd.date_range("2026-01-05", periods=2, freq="B")
+    result = run_weight_backtest(
+        pd.DataFrame({"A": [1.0]}, index=dates[:1]),
+        pd.DataFrame({"A": [0.0, 0.0]}, index=dates),
+    )
+
+    with pytest.raises(ValueError, match="benchmark_nav"):
+        result.benchmark_report()
+
+
+def test_backtest_result_isolated_from_mutated_caller_inputs() -> None:
+    dates = pd.date_range("2026-01-05", periods=2, freq="B")
+    weights = pd.DataFrame({"A": [1.0]}, index=dates[:1])
+    benchmark = pd.Series([1.0, 1.1], index=dates)
+    result = run_weight_backtest(
+        weights,
+        pd.DataFrame({"A": [0.0, 0.0]}, index=dates),
+        benchmark_nav=benchmark,
+    )
+
+    weights.iloc[0, 0] = 0.0
+    benchmark.iloc[1] = 99.0
+
+    assert result.weights.iloc[0, 0] == 1.0
+    assert result.benchmark_nav is not None
+    assert result.benchmark_nav.iloc[1] == 1.1

tests/test_data_adapter.py

@@ -7,10 +7,12 @@ import pandas as pd
 import pytest
 
 from quant_engine.data_adapter import (
+    AssetReturnSnapshot,
     add_vwap_proxy,
     apply_adj_factor,
     load_qtdb_daily,
     long_to_wide,
+    prepare_asset_return_snapshot,
     prepare_execution_inputs,
     prepare_stock_series,
     rename_tushare_columns,
@@ -266,6 +268,17 @@ def test_prepare_execution_inputs_basic(tushare_long: pd.DataFrame) -> None:
     assert volumes.iloc[0, 0] == pytest.approx(1000.0)
 
 
+def test_prepare_execution_inputs_can_select_next_session_open_price(
+    tushare_long: pd.DataFrame,
+) -> None:
+    """显式 price_col=open 时应生成开盘执行价矩阵。"""
+    renamed = rename_tushare_columns(tushare_long)
+
+    prices, _volumes = prepare_execution_inputs(renamed, price_col="open")
+
+    assert prices.iloc[0, 0] == pytest.approx(10.0)
+
+
 def test_prepare_execution_inputs_no_volume() -> None:
     """无 volume 列 → volumes 全 1.0。"""
     df = pd.DataFrame(
@@ -286,6 +299,177 @@ def test_prepare_execution_inputs_missing_close_raises() -> None:
         prepare_execution_inputs(df)
 
 
+def test_prepare_execution_inputs_missing_selected_price_raises() -> None:
+    df = pd.DataFrame({"stock_code": ["A"], "trade_date": ["2024-01-01"], "close": [10.0]})
+    with pytest.raises(ValueError, match="缺 open"):
+        prepare_execution_inputs(df, price_col="open")
+
+
+# ── prepare_asset_return_snapshot ────────────────────────────
+
+
+def _daily_prices() -> pd.DataFrame:
+    return pd.DataFrame(
+        {
+            "stock_code": ["B", "A", "B", "A", "B", "A"],
+            "trade_date": [
+                "2024-01-02",
+                "2024-01-01",
+                "2024-01-01",
+                "2024-01-03",
+                "2024-01-03",
+                "2024-01-02",
+            ],
+            "close": [18.0, 10.0, 20.0, 12.1, 19.8, 11.0],
+        }
+    )
+
+
+def test_prepare_asset_return_snapshot_is_stable_and_immutable_by_interface() -> None:
+    snapshot = prepare_asset_return_snapshot(
+        _daily_prices(),
+        source="qtdb_pro.hq_daily",
+        source_snapshot_id="hq-daily:2024-01-03:v1",
+        adjustment="qfq",
+    )
+
+    assert isinstance(snapshot, AssetReturnSnapshot)
+    assert snapshot.data_snapshot_id.startswith("asset-returns-v1:")
+    assert snapshot.source == "qtdb_pro.hq_daily"
+    assert snapshot.source_snapshot_id == "hq-daily:2024-01-03:v1"
+    assert snapshot.price_field == "close"
+    assert snapshot.adjustment == "qfq"
+    assert snapshot.return_method == "simple"
+    assert snapshot.start_date.isoformat() == "2024-01-01"
+    assert snapshot.end_date.isoformat() == "2024-01-03"
+    assert snapshot.sessions == 3
+    assert snapshot.assets == ("A", "B")
+
+    expected = pd.DataFrame(
+        {
+            "A": [np.nan, 0.1, 0.1],
+            "B": [np.nan, -0.1, 0.1],
+        },
+        index=pd.to_datetime(["2024-01-01", "2024-01-02", "2024-01-03"]),
+    )
+    expected.index.name = "trade_date"
+    expected.columns.name = "stock_code"
+    pd.testing.assert_frame_equal(snapshot.returns, expected)
+
+    exposed = snapshot.returns
+    exposed.iloc[1, 0] = 999.0
+    assert snapshot.returns.iloc[1, 0] == pytest.approx(0.1)
+
+
+def test_asset_return_snapshot_identity_is_order_independent_and_content_addressed() -> None:
+    kwargs = {
+        "source": "qtdb_pro.hq_daily",
+        "source_snapshot_id": "hq-daily:2024-01-03:v1",
+        "adjustment": "none",
+    }
+    baseline = prepare_asset_return_snapshot(_daily_prices(), **kwargs)
+    shuffled = prepare_asset_return_snapshot(
+        _daily_prices().sample(frac=1.0, random_state=7),
+        **kwargs,
+    )
+    changed_prices = _daily_prices().copy()
+    changed_prices.loc[changed_prices["close"] == 12.1, "close"] = 12.2
+    changed_content = prepare_asset_return_snapshot(changed_prices, **kwargs)
+    changed_source = prepare_asset_return_snapshot(
+        _daily_prices(),
+        source="qtdb_pro.hq_daily",
+        source_snapshot_id="hq-daily:2024-01-03:v2",
+        adjustment="none",
+    )
+
+    assert shuffled.data_snapshot_id == baseline.data_snapshot_id
+    assert changed_content.data_snapshot_id != baseline.data_snapshot_id
+    assert changed_source.data_snapshot_id != baseline.data_snapshot_id
+
+
+def test_prepare_asset_return_snapshot_does_not_fill_missing_prices() -> None:
+    prices = _daily_prices()
+    prices.loc[
+        (prices["stock_code"] == "A") & (prices["trade_date"] == "2024-01-02"),
+        "close",
+    ] = np.nan
+
+    snapshot = prepare_asset_return_snapshot(
+        prices,
+        source="qtdb_pro.hq_daily",
+        source_snapshot_id="hq-daily:missing-middle",
+    )
+
+    assert pd.isna(snapshot.returns.loc[pd.Timestamp("2024-01-02"), "A"])
+    assert pd.isna(snapshot.returns.loc[pd.Timestamp("2024-01-03"), "A"])
+
+
+def test_prepare_asset_return_snapshot_rejects_duplicate_sessions() -> None:
+    duplicate = pd.concat([_daily_prices(), _daily_prices().iloc[[0]]], ignore_index=True)
+
+    with pytest.raises(ValueError, match="duplicate"):
+        prepare_asset_return_snapshot(
+            duplicate,
+            source="qtdb_pro.hq_daily",
+            source_snapshot_id="hq-daily:duplicate",
+        )
+
+
+@pytest.mark.parametrize("invalid_price", [0.0, -1.0, np.inf])
+def test_prepare_asset_return_snapshot_rejects_invalid_prices(invalid_price: float) -> None:
+    prices = _daily_prices()
+    prices.loc[0, "close"] = invalid_price
+
+    with pytest.raises(ValueError, match="positive finite"):
+        prepare_asset_return_snapshot(
+            prices,
+            source="qtdb_pro.hq_daily",
+            source_snapshot_id="hq-daily:invalid-price",
+        )
+
+
+@pytest.mark.parametrize(
+    ("source", "source_snapshot_id", "adjustment"),
+    [
+        ("", "source-1", "none"),
+        ("qtdb_pro.hq_daily", "", "none"),
+        ("qtdb_pro.hq_daily", "source-1", ""),
+    ],
+)
+def test_prepare_asset_return_snapshot_requires_explicit_identity_semantics(
+    source: str,
+    source_snapshot_id: str,
+    adjustment: str,
+) -> None:
+    with pytest.raises(ValueError, match="must be non-empty"):
+        prepare_asset_return_snapshot(
+            _daily_prices(),
+            source=source,
+            source_snapshot_id=source_snapshot_id,
+            adjustment=adjustment,
+        )
+
+
+def test_asset_return_snapshot_feeds_reproducible_covariance_lineage() -> None:
+    from quant_engine.risk import estimate_covariance_snapshot
+
+    market_snapshot = prepare_asset_return_snapshot(
+        _daily_prices(),
+        source="qtdb_pro.hq_daily",
+        source_snapshot_id="hq-daily:2024-01-03:v1",
+    )
+    covariance_snapshot = estimate_covariance_snapshot(
+        market_snapshot.returns,
+        as_of_date=market_snapshot.end_date,
+        lookback_sessions=3,
+        min_observations=2,
+        data_snapshot_id=market_snapshot.data_snapshot_id,
+    )
+
+    assert covariance_snapshot.data_snapshot_id == market_snapshot.data_snapshot_id
+    assert covariance_snapshot.snapshot_id.startswith("sample-cov-v1:")
+
+
 # ── 端到端：长表 → 适配 → alpha158 + execution ──────────────
 
 

tests/test_execution.py

@@ -11,6 +11,7 @@ import pytest
 from quant_engine.execution import (
     ExecutionConfig,
     ExecutionResult,
+    ExecutionSimulationResult,
     apply_bid_ask_spread,
     apply_volume_constraint,
     check_price_limit,
@@ -19,7 +20,9 @@ from quant_engine.execution import (
     compute_realized_pnl,
     run_end_to_end_poc,
     simulate_execution,
+    simulate_daily_ledger_with_audit,
     simulate_multi_day,
+    simulate_multi_day_with_audit,
     simulate_with_daily_data,
     total_costs,
     total_turnover,
@@ -327,24 +330,26 @@ def test_simulate_multi_day_length_mismatch_raises():
 
 
 def test_simulate_multi_day_first_day_value_equals_initial():
-    """第一天 portfolio_value = initial_cash（无持仓）。"""
+    """零成本下第一天日末 NAV 等于初始资金。"""
     signals = [("d1", {"A": 1.0})]
     prices = [("d1", {"A": 10.0})]
-    positions = simulate_multi_day(signals, prices, 1_000_000.0)
+    config = ExecutionConfig(
-    # 第一天 NAV = 1_000_000（无持仓），第二天才是调仓后
+        commission_bps=0,
+        stamp_tax_bps=0,
+        slippage_bps=0,
+        min_trade_amount=0,
+    )
+    positions = simulate_multi_day(signals, prices, 1_000_000.0, config)
     assert positions[0].portfolio_value == 1_000_000.0
+    assert positions[0].holdings == {"A": 100_000.0}
 
 
 def test_simulate_multi_day_holdings_evolution():
-    """调仓后 holdings 演化。
+    """日末快照应反映当天调仓后的 holdings。"""
-
-    注意：positions[i] 是第 i 天 rebalance 之前的快照。
-    所以要看 d2 rebalance 后的 holdings，需要看 positions[2]（d3 的快照）。
-    """
     signals = [
         ("d1", {"A": 0.5, "B": 0.5}),
         ("d2", {"A": 1.0, "B": 0.0}),  # 全仓 A
-        ("d3", {"A": 1.0, "B": 0.0}),  # 第三天的快照才能看到 d2 rebalance 后的 holdings
+        ("d3", {"A": 1.0, "B": 0.0}),
     ]
     prices = [
         ("d1", {"A": 10.0, "B": 20.0}),
@@ -352,9 +357,288 @@ def test_simulate_multi_day_holdings_evolution():
         ("d3", {"A": 12.0, "B": 22.0}),
     ]
     positions = simulate_multi_day(signals, prices, 1_000_000.0)
-    # d3 的 PRE-trade snapshot 应该只有 A（B 在 d2 被平仓）
+    assert "B" not in positions[1].holdings
-    assert "B" not in positions[2].holdings
+    assert "A" in positions[1].holdings
-    assert "A" in positions[2].holdings
+
+
+def test_simulate_multi_day_with_audit_rebalances_target_weights_by_delta():
+    """相同目标权重不应在每个交易日重复买入。"""
+    config = ExecutionConfig(
+        commission_bps=0,
+        stamp_tax_bps=0,
+        slippage_bps=0,
+        min_trade_amount=0,
+    )
+    targets = [(date, {"A": 1.0}) for date in ("d1", "d2", "d3")]
+    prices = [(date, {"A": 10.0}) for date in ("d1", "d2", "d3")]
+
+    result = simulate_multi_day_with_audit(targets, prices, 1_000.0, config)
+
+    assert isinstance(result, ExecutionSimulationResult)
+    assert [len(day.executions) for day in result.daily_executions] == [1, 0, 0]
+    assert result.total_turnover == pytest.approx(1_000.0)
+    assert [position.cash for position in result.positions] == pytest.approx([0.0, 0.0, 0.0])
+    assert [position.holdings["A"] for position in result.positions] == pytest.approx(
+        [100.0, 100.0, 100.0]
+    )
+    assert [position.portfolio_value for position in result.positions] == pytest.approx(
+        [1_000.0, 1_000.0, 1_000.0]
+    )
+
+
+def test_simulate_multi_day_with_audit_records_costs_without_replay():
+    """成交成本与日末 NAV 应来自同一次状态推进。"""
+    targets = [("d1", {"A": 1.0}), ("d2", {"A": 1.0})]
+    prices = [("d1", {"A": 10.0}), ("d2", {"A": 10.0})]
+
+    result = simulate_multi_day_with_audit(targets, prices, 1_000.0)
+
+    first_day = result.daily_executions[0]
+    assert first_day.nav_before == pytest.approx(1_000.0)
+    assert first_day.nav_after == pytest.approx(result.positions[0].portfolio_value)
+    assert result.total_costs == pytest.approx(sum(r.total_cost for r in first_day.executions))
+    assert result.final_portfolio_value == pytest.approx(1_000.0 - result.total_costs)
+    assert result.daily_executions[1].executions == ()
+
+
+def test_simulate_multi_day_with_audit_never_spends_more_cash_than_available():
+    """满仓目标应按可用现金部分成交，不能用负现金隐式加杠杆。"""
+    result = simulate_multi_day_with_audit(
+        [("d1", {"A": 1.0})],
+        [("d1", {"A": 10.0})],
+        1_000.0,
+    )
+
+    execution = result.daily_executions[0].executions[0]
+    assert result.positions[0].cash >= -1e-9
+    assert 0 < execution.partial_fill_pct < 1
+    assert execution.blocked_reason == "insufficient_cash_partial_fill"
+    assert result.final_portfolio_value == pytest.approx(1_000.0 - result.total_costs)
+
+
+@pytest.mark.parametrize(
+    "targets",
+    [
+        {"A": -0.1},
+        {"A": 0.6, "B": 0.5},
+        {"A": float("nan")},
+    ],
+)
+def test_simulate_multi_day_with_audit_rejects_invalid_long_only_weights(targets):
+    """多日 A 股目标必须是有限、非负且合计不超过 100% 的权重。"""
+    with pytest.raises(ValueError, match="target weights"):
+        simulate_multi_day_with_audit(
+            [("d1", targets)],
+            [("d1", {"A": 10.0, "B": 10.0})],
+            1_000.0,
+        )
+
+
+def test_simulate_multi_day_with_audit_requires_price_for_existing_holding():
+    """已有持仓缺价时无法可信估值，必须失败而不是把市值记为零。"""
+    with pytest.raises(ValueError, match="missing price for held asset A"):
+        simulate_multi_day_with_audit(
+            [("d1", {"A": 1.0}), ("d2", {"A": 1.0})],
+            [("d1", {"A": 10.0}), ("d2", {})],
+            1_000.0,
+        )
+
+
+def test_simulate_multi_day_with_audit_records_unpriced_target_rejection():
+    """缺失价格的目标不能吞掉现金，且必须留下拒绝原因。"""
+    result = simulate_multi_day_with_audit(
+        [("d1", {"A": 1.0})],
+        [("d1", {"B": 10.0})],
+        1_000.0,
+    )
+
+    rejection = result.daily_executions[0].executions[0]
+    assert rejection.stock_code == "A"
+    assert rejection.executed_value == 0.0
+    assert rejection.partial_fill_pct == 0.0
+    assert rejection.blocked_reason == "missing_price"
+    assert result.positions[0].cash == 1_000.0
+    assert result.positions[0].holdings == {}
+
+
+def test_simulate_multi_day_with_audit_requires_matching_dates():
+    """权重与价格日期错位必须显式失败，不能按位置静默配对。"""
+    with pytest.raises(ValueError, match="dates must match"):
+        simulate_multi_day_with_audit(
+            [("d1", {"A": 1.0})],
+            [("d2", {"A": 10.0})],
+            1_000.0,
+        )
+
+
+# ── 逐交易日 Ledger：成交时点与估值时点分离 ─────────────────
+
+
+def test_daily_ledger_marks_every_session_after_sparse_open_execution() -> None:
+    """下一日开盘成交后，应按每日收盘价持续盯市，而非只记录调仓日。"""
+    config = ExecutionConfig(
+        commission_bps=0,
+        stamp_tax_bps=0,
+        slippage_bps=0,
+        min_trade_amount=0,
+    )
+
+    result = simulate_daily_ledger_with_audit(
+        target_weights_history=[("d1", {"A": 1.0})],
+        execution_price_history=[("d1", {"A": 10.0})],
+        valuation_price_history=[
+            ("d0", {"A": 9.0}),
+            ("d1", {"A": 11.0}),
+            ("d2", {"A": 12.0}),
+        ],
+        initial_cash=1_000.0,
+        config=config,
+    )
+
+    assert [position.date for position in result.positions] == ["d0", "d1", "d2"]
+    assert [position.portfolio_value for position in result.positions] == pytest.approx(
+        [1_000.0, 1_100.0, 1_200.0]
+    )
+    assert [len(day.executions) for day in result.daily_executions] == [0, 1, 0]
+    fill = result.daily_executions[1].executions[0]
+    assert fill.side == "buy"
+    assert fill.quantity == pytest.approx(100.0)
+    assert fill.price == pytest.approx(10.0)
+    pd.testing.assert_series_equal(
+        result.normalized_nav_series,
+        pd.Series([1.0, 1.1, 1.2], index=["d0", "d1", "d2"], dtype=float),
+    )
+    pd.testing.assert_series_equal(
+        result.daily_returns,
+        pd.Series([0.0, 0.1, 1.2 / 1.1 - 1.0], index=["d0", "d1", "d2"]),
+    )
+
+
+def test_daily_ledger_first_session_cost_reduces_first_return() -> None:
+    """首个估值日发生交易时，费用必须进入相对初始资金的首日收益。"""
+    result = simulate_daily_ledger_with_audit(
+        target_weights_history=[("d0", {"A": 1.0})],
+        execution_price_history=[("d0", {"A": 10.0})],
+        valuation_price_history=[("d0", {"A": 10.0})],
+        initial_cash=1_000.0,
+    )
+
+    assert result.total_costs > 0
+    assert result.daily_returns.iloc[0] == pytest.approx(
+        result.final_portfolio_value / result.initial_cash - 1.0
+    )
+    assert result.daily_returns.iloc[0] < 0
+
+
+def test_daily_ledger_nav_is_rebuildable_and_trades_are_projectable() -> None:
+    """Ledger 必须同时支持现金守恒校验和平台成交表投影。"""
+    config = ExecutionConfig(
+        commission_bps=0,
+        stamp_tax_bps=0,
+        slippage_bps=0,
+        min_trade_amount=0,
+    )
+    result = simulate_daily_ledger_with_audit(
+        target_weights_history=[
+            ("d1", {"A": 1.0, "B": 0.0}),
+            ("d2", {"A": 0.0, "B": 1.0}),
+        ],
+        execution_price_history=[
+            ("d1", {"A": 10.0, "B": 20.0}),
+            ("d2", {"A": 11.0, "B": 22.0}),
+        ],
+        valuation_price_history=[
+            ("d0", {"A": 9.0, "B": 19.0}),
+            ("d1", {"A": 10.5, "B": 21.0}),
+            ("d2", {"A": 12.0, "B": 24.0}),
+        ],
+        initial_cash=1_000.0,
+        config=config,
+    )
+
+    close_prices = {
+        "d0": {"A": 9.0, "B": 19.0},
+        "d1": {"A": 10.5, "B": 21.0},
+        "d2": {"A": 12.0, "B": 24.0},
+    }
+    for position in result.positions:
+        rebuilt = position.cash + sum(
+            shares * close_prices[position.date][asset]
+            for asset, shares in position.holdings.items()
+        )
+        assert position.portfolio_value == pytest.approx(rebuilt)
+
+    trades = result.trades_frame
+    assert trades.columns.tolist() == [
+        "trade_date",
+        "ts_code",
+        "side",
+        "qty",
+        "price",
+        "amount",
+        "fee",
+        "slippage",
+    ]
+    assert trades["side"].tolist() == ["buy", "sell", "buy"]
+    assert (trades["qty"] > 0).all()
+
+
+def test_daily_ledger_frame_matches_platform_projection_contract() -> None:
+    """核心层输出稳定日频投影，但不携带 run_id 或执行数据库写入。"""
+    config = ExecutionConfig(
+        commission_bps=0,
+        stamp_tax_bps=0,
+        slippage_bps=0,
+        min_trade_amount=0,
+    )
+    result = simulate_daily_ledger_with_audit(
+        target_weights_history=[("d1", {"A": 1.0})],
+        execution_price_history=[("d1", {"A": 10.0})],
+        valuation_price_history=[
+            ("d0", {"A": 9.0}),
+            ("d1", {"A": 11.0}),
+            ("d2", {"A": 12.0}),
+        ],
+        initial_cash=1_000.0,
+        config=config,
+    )
+
+    ledger = result.ledger_frame
+
+    assert ledger.columns.tolist() == [
+        "trade_date",
+        "portfolio_value",
+        "nav",
+        "pnl",
+        "pnl_pct",
+        "position_value",
+        "cash",
+        "turnover",
+    ]
+    assert ledger["trade_date"].tolist() == ["d0", "d1", "d2"]
+    assert ledger["nav"].tolist() == pytest.approx([1.0, 1.1, 1.2])
+    assert ledger["pnl"].tolist() == pytest.approx([0.0, 100.0, 100.0])
+    assert ledger["pnl_pct"].tolist() == pytest.approx([0.0, 0.1, 1.2 / 1.1 - 1.0])
+    assert ledger["position_value"].tolist() == pytest.approx([0.0, 1_100.0, 1_200.0])
+    assert ledger["cash"].tolist() == pytest.approx([1_000.0, 0.0, 0.0])
+    assert ledger["turnover"].tolist() == pytest.approx([0.0, 1.0, 0.0])
+
+
+def test_daily_ledger_rejects_missing_close_for_held_asset() -> None:
+    """已有持仓缺少收盘估值价时必须 fail closed。"""
+    with pytest.raises(ValueError, match="missing valuation price for held asset A"):
+        simulate_daily_ledger_with_audit(
+            target_weights_history=[("d0", {"A": 1.0})],
+            execution_price_history=[("d0", {"A": 10.0})],
+            valuation_price_history=[("d0", {"A": 10.0}), ("d1", {})],
+            initial_cash=1_000.0,
+        )
+
+
+def test_daily_ledger_requires_positive_initial_cash() -> None:
+    """可信收益曲线需要正初始资金作为归一化基准。"""
+    with pytest.raises(ValueError, match="initial_cash must be positive"):
+        simulate_daily_ledger_with_audit([], [], [], initial_cash=0.0)
 
 
 # ── v1.2.0 Phase 1：端到端 POC（run_end_to_end_poc） ─────
@@ -449,6 +733,15 @@ def test_run_end_to_end_poc_costs_recorded():
     result = run_end_to_end_poc(signals, prices, 1_000_000.0)
     assert result["total_costs"] > 0
     assert result["total_turnover"] > 0
+    executions = [
+        execution
+        for daily in result["daily_executions"]
+        for execution in daily.executions
+    ]
+    assert result["total_costs"] == pytest.approx(sum(item.total_cost for item in executions))
+    assert result["total_turnover"] == pytest.approx(
+        sum(item.executed_value for item in executions)
+    )
 
 
 # ── v1.2.0 Phase 2: T+1 / 涨跌停 / 部分成交 / 买卖价差 ─────
@@ -741,8 +1034,8 @@ def test_compute_realized_pnl_sell_realizes():
         target_weights_history=targets,
     )
     pnl_list = compute_realized_pnl(positions)
-    # 第三天（卖出兑现）应有 realized 正利润（cash 从 -800 → 2M = +2M）
+    # 第二天日末快照已包含当日卖出，现金流入应在当天反映。
-    assert pnl_list[2].realized_pnl > 0
+    assert pnl_list[1].realized_pnl > 0
 
 
 # ── O3: end-to-end 端到端测试（集成多个函数） ──────────────

tests/test_factor_library.py

@@ -0,0 +1,173 @@
+"""Contracts for reusable factor diagnostics and transformations."""
+
+from __future__ import annotations
+
+import numpy as np
+import pandas as pd
+import pytest
+
+from quant_engine.factor_library import (
+    annualized_sharpe,
+    apply_factor_direction,
+    cross_sectional_momentum,
+    cross_sectional_pct_rank,
+    cross_sectional_rank_with_direction,
+    ic_summary,
+    jb_test,
+    kurtosis,
+    ols_regress,
+    rolling_annual_vol,
+    rolling_zscore,
+    skewness,
+    spearman_ic,
+    time_series_momentum,
+    turnover,
+    winsorize,
+)
+
+
+def test_turnover_supports_one_way_and_round_trip_conventions() -> None:
+    weights = pd.DataFrame({"A": [1.0, 0.0], "B": [0.0, 1.0]})
+
+    pd.testing.assert_series_equal(turnover(weights), pd.Series([1.0], index=[1]))
+    pd.testing.assert_series_equal(
+        turnover(weights, divide_by_two=False), pd.Series([2.0], index=[1])
+    )
+    assert turnover(weights.iloc[:1]).empty
+
+
+def test_ic_functions_measure_monotonic_relationship() -> None:
+    factor = pd.Series([1.0, 2.0, 3.0, 4.0])
+    forward = pd.Series([10.0, 20.0, 30.0, 40.0])
+
+    assert spearman_ic(factor, forward) == pytest.approx(1.0)
+    result = ic_summary(factor, forward, periods=(1,), method="pearson")
+    assert result.loc[1, "ic_mean"] == pytest.approx(1.0)
+    assert result.loc[1, "n"] == 4
+
+
+def test_ic_summary_rejects_unknown_method() -> None:
+    with pytest.raises(ValueError, match="not supported"):
+        ic_summary(pd.Series([1, 2, 3]), pd.Series([1, 2, 3]), method="kendall")
+
+
+def test_winsorize_clips_tails_and_preserves_nan() -> None:
+    values = pd.Series([0.0, 1.0, 2.0, 100.0, np.nan])
+
+    result = winsorize(values, lower=0.25, upper=0.75)
+
+    assert result.iloc[0] == pytest.approx(0.75)
+    assert result.iloc[3] == pytest.approx(26.5)
+    assert pd.isna(result.iloc[4])
+
+
+def test_distribution_diagnostics_handle_short_samples() -> None:
+    assert np.isnan(skewness(pd.Series([1.0, 2.0])))
+    assert np.isnan(kurtosis(pd.Series([1.0, 2.0, 3.0])))
+    jb, p_value = jb_test(pd.Series(range(7), dtype=float))
+    assert np.isnan(jb)
+    assert np.isnan(p_value)
+
+
+def test_distribution_diagnostics_return_finite_values() -> None:
+    values = pd.Series([-2.0, -1.0, -0.5, 0.0, 0.25, 0.75, 1.0, 3.0])
+
+    assert np.isfinite(skewness(values))
+    assert np.isfinite(kurtosis(values))
+    jb, p_value = jb_test(values)
+    assert jb >= 0
+    assert 0 <= p_value <= 1
+
+
+def test_ols_recovers_linear_coefficients_and_residual_index() -> None:
+    index = pd.date_range("2026-01-01", periods=8)
+    factor = pd.Series(np.arange(8, dtype=float), index=index, name="factor")
+    target = 1.5 + 2.0 * factor
+
+    result = ols_regress(target, factor)
+
+    assert result.alpha == pytest.approx(1.5)
+    assert result.beta["factor"] == pytest.approx(2.0)
+    assert result.r_squared == pytest.approx(1.0)
+    assert result.n == 8
+    assert result.resid.index.equals(index)
+
+
+def test_ols_handles_collinear_factors_without_crashing() -> None:
+    x = pd.DataFrame({"a": np.arange(8, dtype=float), "b": np.arange(8, dtype=float)})
+    y = pd.Series(1.0 + x["a"])
+
+    result = ols_regress(y, x)
+
+    assert result.n == 8
+    assert np.isfinite(result.beta).all()
+    np.testing.assert_allclose(result.resid, 0.0, atol=1e-12)
+
+
+def test_ols_short_sample_returns_empty_estimate() -> None:
+    result = ols_regress(pd.Series([1.0, 2.0]), pd.Series([1.0, 2.0], name="x"))
+
+    assert np.isnan(result.alpha)
+    assert result.beta.empty
+    assert result.n == 2
+
+
+def test_momentum_and_rolling_transforms_match_manual_values() -> None:
+    prices = pd.DataFrame({"A": [100.0, 110.0, 121.0, 133.1]})
+    momentum = cross_sectional_momentum(prices, lookback=2, skip=0)
+    assert momentum.iloc[2, 0] == pytest.approx(0.21)
+
+    returns = pd.Series([0.1, 0.1, -0.5, -0.5])
+    pd.testing.assert_series_equal(
+        time_series_momentum(returns, lookback=2),
+        pd.Series([0, 1, -1, -1]),
+    )
+
+    values = pd.Series([1.0, 2.0, 3.0])
+    zscore = rolling_zscore(values, window=3)
+    assert zscore.iloc[-1] == pytest.approx(1.0)
+    annual_vol = rolling_annual_vol(returns, window=2, min_periods=2, trading_days=4)
+    assert annual_vol.iloc[1] == pytest.approx(0.0)
+
+
+def test_rank_helpers_support_global_and_grouped_ranking() -> None:
+    frame = pd.DataFrame(
+        {"factor": [3.0, 1.0, 2.0, 4.0], "industry": ["x", "x", "y", "y"]}
+    )
+
+    global_rank = cross_sectional_pct_rank(frame, "factor", ascending=True)
+    grouped_rank = cross_sectional_pct_rank(
+        frame, "factor", group_col="industry", ascending=True
+    )
+
+    assert global_rank.tolist() == [0.75, 0.25, 0.5, 1.0]
+    assert grouped_rank.tolist() == [1.0, 0.5, 0.5, 1.0]
+    assert cross_sectional_pct_rank(frame, "missing").empty
+
+
+def test_factor_direction_and_directional_rank() -> None:
+    pe = pd.Series([10.0, 20.0], name="pe_ttm")
+    pd.testing.assert_series_equal(apply_factor_direction(pe), -pe)
+
+    frame = pd.DataFrame({"pe_ttm": [10.0, 20.0], "roe": [0.1, 0.2]})
+    assert cross_sectional_rank_with_direction(frame, "pe_ttm").tolist() == [1.0, 0.5]
+    assert cross_sectional_rank_with_direction(frame, "roe").tolist() == [0.5, 1.0]
+
+
+@pytest.mark.parametrize("direction", ["sideways", "", "REVERSE"])
+def test_factor_direction_rejects_unknown_values(direction: str) -> None:
+    factor = pd.Series([1.0, 2.0], name="roe")
+
+    with pytest.raises(ValueError, match="direction"):
+        apply_factor_direction(factor, direction=direction)
+    with pytest.raises(ValueError, match="direction"):
+        cross_sectional_rank_with_direction(
+            pd.DataFrame({"roe": factor}), "roe", direction=direction
+        )
+
+
+def test_annualized_sharpe_handles_empty_and_nonzero_returns() -> None:
+    assert annualized_sharpe(pd.Series(dtype=float)) == 0.0
+    returns = pd.Series([0.01, -0.01, 0.02, 0.0])
+    expected = returns.mean() * 252 / (returns.std() * np.sqrt(252))
+    assert annualized_sharpe(returns) == pytest.approx(expected)

tests/test_metrics.py

@@ -0,0 +1,163 @@
+"""Mathematical contracts for the standard performance metrics."""
+
+from __future__ import annotations
+
+import numpy as np
+import pandas as pd
+import pytest
+
+from quant_engine.metrics import (
+    TRADING_DAYS_PER_YEAR,
+    annualized_return,
+    annualized_volatility,
+    benchmark_summary,
+    calmar_ratio,
+    max_drawdown,
+    sharpe_ratio,
+    sortino_ratio,
+    summary,
+    win_rate,
+)
+
+
+def test_annualized_return_uses_compounded_simple_returns() -> None:
+    returns = pd.Series([0.10, -0.10])
+    expected = 0.99 ** (TRADING_DAYS_PER_YEAR / 2) - 1.0
+
+    assert annualized_return(returns) == pytest.approx(expected)
+
+
+def test_annualized_volatility_uses_sample_standard_deviation() -> None:
+    returns = pd.Series([0.01, 0.03, 0.02])
+
+    assert annualized_volatility(returns) == pytest.approx(
+        returns.std() * np.sqrt(TRADING_DAYS_PER_YEAR)
+    )
+
+
+def test_sharpe_ratio_subtracts_annual_risk_free_rate() -> None:
+    returns = pd.Series([0.01, -0.005, 0.02, 0.0])
+
+    result = sharpe_ratio(returns, rf=0.02)
+
+    assert result == pytest.approx(
+        (annualized_return(returns) - 0.02) / annualized_volatility(returns)
+    )
+
+
+def test_zero_volatility_metrics_return_zero() -> None:
+    returns = pd.Series([0.0, 0.0, 0.0])
+
+    assert sharpe_ratio(returns) == 0.0
+    assert sortino_ratio(returns) == 0.0
+    assert calmar_ratio(returns) == 0.0
+
+
+def test_sortino_ratio_uses_all_sessions_for_downside_deviation() -> None:
+    returns = pd.Series([0.02, -0.01, 0.0, -0.03])
+    downside = np.minimum(returns.to_numpy(), 0.0)
+    downside_deviation = np.sqrt(np.mean(np.square(downside))) * np.sqrt(
+        TRADING_DAYS_PER_YEAR
+    )
+
+    assert sortino_ratio(returns) == pytest.approx(
+        annualized_return(returns) / downside_deviation
+    )
+
+
+def test_max_drawdown_includes_loss_from_initial_capital() -> None:
+    returns = pd.Series([-0.20, 0.0])
+
+    assert max_drawdown(returns) == pytest.approx(-0.20)
+
+
+def test_max_drawdown_tracks_peak_to_trough_loss() -> None:
+    returns = pd.Series([0.10, -0.20, 0.05])
+
+    assert max_drawdown(returns) == pytest.approx(-0.20)
+
+
+def test_metrics_clean_nan_and_infinite_values() -> None:
+    returns = pd.Series([0.10, np.nan, np.inf, -0.05, -np.inf])
+
+    assert win_rate(returns) == 0.5
+    assert summary(returns)["n_days"] == 2
+
+
+def test_summary_aliases_match_canonical_fields() -> None:
+    result = summary(pd.Series([0.01, -0.02, 0.03]))
+
+    assert result["annual_yield"] == result["ann_return"]
+    assert result["annual_sd"] == result["ann_volatility"]
+    assert result["drawback"] == result["max_drawdown"]
+
+
+@pytest.mark.parametrize(
+    "metric",
+    [
+        annualized_return,
+        annualized_volatility,
+        sharpe_ratio,
+        sortino_ratio,
+        max_drawdown,
+        calmar_ratio,
+        win_rate,
+    ],
+)
+def test_metrics_reject_non_series_input(metric) -> None:
+    with pytest.raises(TypeError, match=r"expected pd\.Series"):
+        metric([0.01, 0.02])
+
+
+def test_short_and_empty_series_return_zero() -> None:
+    assert annualized_return(pd.Series(dtype=float)) == 0.0
+    assert annualized_volatility(pd.Series([0.01])) == 0.0
+    assert max_drawdown(pd.Series([0.01])) == 0.0
+    assert win_rate(pd.Series(dtype=float)) == 0.0
+
+
+def test_benchmark_summary_uses_aligned_active_returns_and_regression() -> None:
+    dates = pd.date_range("2026-01-05", periods=4, freq="B")
+    benchmark = pd.Series([-0.01, 0.0, 0.01, 0.02], index=dates)
+    portfolio = 0.001 + 1.5 * benchmark
+    active = portfolio - benchmark
+
+    result = benchmark_summary(portfolio, benchmark)
+
+    assert result["n_observations"] == 4
+    assert result["tracking_error"] == pytest.approx(
+        active.std() * np.sqrt(TRADING_DAYS_PER_YEAR)
+    )
+    assert result["information_ratio"] == pytest.approx(
+        active.mean() / active.std() * np.sqrt(TRADING_DAYS_PER_YEAR)
+    )
+    assert result["beta"] == pytest.approx(1.5)
+    assert result["alpha"] == pytest.approx(1.001**TRADING_DAYS_PER_YEAR - 1.0)
+
+
+def test_benchmark_summary_rejects_silent_calendar_alignment() -> None:
+    portfolio = pd.Series([0.01, 0.02], index=pd.date_range("2026-01-05", periods=2))
+    benchmark = pd.Series([0.01, 0.02], index=pd.date_range("2026-01-06", periods=2))
+
+    with pytest.raises(ValueError, match="matching indexes"):
+        benchmark_summary(portfolio, benchmark)
+
+
+def test_benchmark_summary_rejects_missing_observations() -> None:
+    dates = pd.date_range("2026-01-05", periods=2)
+    portfolio = pd.Series([0.01, np.nan], index=dates)
+    benchmark = pd.Series([0.0, 0.01], index=dates)
+
+    with pytest.raises(ValueError, match="finite"):
+        benchmark_summary(portfolio, benchmark)
+
+
+def test_benchmark_summary_marks_constant_benchmark_regression_unestimable() -> None:
+    dates = pd.date_range("2026-01-05", periods=3)
+    portfolio = pd.Series([0.01, -0.01, 0.02], index=dates)
+    benchmark = pd.Series([0.0, 0.0, 0.0], index=dates)
+
+    result = benchmark_summary(portfolio, benchmark)
+
+    assert np.isnan(result["alpha"])
+    assert np.isnan(result["beta"])

tests/test_portfolio_construction.py

@@ -0,0 +1,157 @@
+"""Factor-score portfolio construction and backtest integration contracts."""
+
+from __future__ import annotations
+
+import numpy as np
+import pandas as pd
+import pytest
+
+from quant_engine.backtest import run_weight_backtest
+from quant_engine.portfolio_construction import (
+    equal_weight,
+    scores_to_target_weights,
+    scores_to_weight_table,
+    select_top_k,
+)
+
+
+def test_select_top_k_ignores_nan_and_breaks_ties_by_input_order() -> None:
+    scores = pd.Series([1.0, 1.0, np.nan, 0.5], index=["B", "A", "C", "D"])
+
+    selected = select_top_k(scores, top_k=2)
+
+    assert selected.tolist() == ["B", "A"]
+
+
+def test_select_top_k_can_select_lowest_scores() -> None:
+    scores = pd.Series([3.0, 1.0, 2.0], index=["A", "B", "C"])
+
+    selected = select_top_k(scores, top_k=2, largest=False)
+
+    assert selected.tolist() == ["B", "C"]
+
+
+def test_equal_weight_allocates_requested_gross_exposure() -> None:
+    result = equal_weight(pd.Index(["A", "B", "C"]), gross_exposure=0.9)
+
+    pd.testing.assert_series_equal(
+        result,
+        pd.Series([0.3, 0.3, 0.3], index=["A", "B", "C"], name="weight"),
+    )
+
+
+def test_equal_weight_returns_empty_float_series_for_no_assets() -> None:
+    result = equal_weight(pd.Index([], dtype=object))
+
+    assert result.empty
+    assert result.dtype == float
+    assert result.name == "weight"
+
+
+def test_scores_to_target_weights_keeps_full_universe_with_zero_for_unselected() -> None:
+    scores = pd.Series([0.2, 0.8, 0.5], index=["A", "B", "C"])
+
+    result = scores_to_target_weights(scores, top_k=2)
+
+    pd.testing.assert_series_equal(
+        result,
+        pd.Series([0.0, 0.5, 0.5], index=scores.index, name="weight"),
+    )
+
+
+def test_scores_to_target_weights_divides_exposure_over_available_scores() -> None:
+    scores = pd.Series([1.0, np.nan, 0.5], index=["A", "B", "C"])
+
+    result = scores_to_target_weights(scores, top_k=5, gross_exposure=0.8)
+
+    pd.testing.assert_series_equal(
+        result,
+        pd.Series([0.4, 0.0, 0.4], index=scores.index, name="weight"),
+    )
+
+
+def test_scores_to_weight_table_constructs_each_rebalance_independently() -> None:
+    dates = pd.to_datetime(["2026-01-05", "2026-01-07"])
+    scores = pd.DataFrame(
+        {"A": [3.0, 1.0], "B": [2.0, 3.0], "C": [1.0, 2.0]},
+        index=dates,
+    )
+
+    result = scores_to_weight_table(scores, top_k=2)
+
+    expected = pd.DataFrame(
+        {"A": [0.5, 0.0], "B": [0.5, 0.5], "C": [0.0, 0.5]},
+        index=dates,
+    )
+    pd.testing.assert_frame_equal(result, expected)
+
+    changed_future = scores.copy()
+    changed_future.iloc[1] = [100.0, -100.0, 0.0]
+    changed_result = scores_to_weight_table(changed_future, top_k=2)
+    pd.testing.assert_series_equal(result.iloc[0], changed_result.iloc[0])
+
+
+def test_effective_holding_weights_flow_into_weight_backtest() -> None:
+    dates = pd.date_range("2026-01-05", periods=3, freq="B")
+    effective_weights = pd.DataFrame(
+        {"A": [1.0, 0.0], "B": [0.0, 1.0]},
+        index=dates[[0, 2]],
+    )
+    stock_returns = pd.DataFrame(
+        {"A": [0.10, 0.0, 0.0], "B": [0.0, 0.0, 0.20]},
+        index=dates,
+    )
+
+    result = run_weight_backtest(effective_weights, stock_returns)
+
+    pd.testing.assert_series_equal(result.nav, pd.Series([1.1, 1.1, 1.32], index=dates))
+    pd.testing.assert_frame_equal(result.weights, effective_weights)
+
+
+@pytest.mark.parametrize("top_k", [0, -1])
+def test_portfolio_construction_rejects_non_positive_top_k(top_k: int) -> None:
+    scores = pd.Series([1.0], index=["A"])
+
+    with pytest.raises(ValueError, match="top_k must be positive"):
+        select_top_k(scores, top_k=top_k)
+
+
+@pytest.mark.parametrize("gross_exposure", [-0.1, np.inf, np.nan])
+def test_equal_weight_rejects_invalid_gross_exposure(gross_exposure: float) -> None:
+    with pytest.raises(ValueError, match="gross_exposure"):
+        equal_weight(pd.Index(["A"]), gross_exposure=gross_exposure)
+
+
+def test_portfolio_construction_rejects_duplicate_assets() -> None:
+    duplicate_scores = pd.Series([1.0, 2.0], index=["A", "A"])
+
+    with pytest.raises(ValueError, match="unique asset labels"):
+        scores_to_target_weights(duplicate_scores, top_k=1)
+
+
+def test_weight_table_rejects_duplicate_rebalance_dates() -> None:
+    duplicate_date = pd.Timestamp("2026-01-05")
+    scores = pd.DataFrame(
+        {"A": [1.0, 2.0]},
+        index=[duplicate_date, duplicate_date],
+    )
+
+    with pytest.raises(ValueError, match="unique rebalance dates"):
+        scores_to_weight_table(scores, top_k=1)
+
+
+def test_weight_table_rejects_unsorted_rebalance_dates() -> None:
+    scores = pd.DataFrame(
+        {"A": [1.0, 2.0]},
+        index=pd.to_datetime(["2026-01-07", "2026-01-05"]),
+    )
+
+    with pytest.raises(ValueError, match="chronological order"):
+        scores_to_weight_table(scores, top_k=1)
+
+
+def test_weight_table_rejects_non_numeric_scores() -> None:
+    scores = pd.DataFrame({"A": ["high"], "B": ["low"]})
+
+    with pytest.raises(TypeError, match="numeric"):
+        scores_to_weight_table(scores, top_k=1)

tests/test_research_pipeline.py

@@ -0,0 +1,336 @@
+"""No-lookahead factor-score to execution-audit integration contracts."""
+
+from __future__ import annotations
+
+import pandas as pd
+import pytest
+
+from quant_engine.execution import ExecutionConfig
+from quant_engine.research_pipeline import (
+    FactorBacktestResult,
+    FactorExecutionResult,
+    TargetWeightSchedule,
+    run_factor_backtest_research,
+    run_factor_execution_research,
+    schedule_target_weights,
+)
+
+
+def _calendar() -> pd.DatetimeIndex:
+    return pd.date_range("2026-01-05", periods=4, freq="B")
+
+
+def _factor_scores() -> pd.DataFrame:
+    dates = _calendar()
+    return pd.DataFrame(
+        {"A": [2.0, 0.0], "B": [1.0, 3.0]},
+        index=dates[:2],
+    )
+
+
+def _next_session_open_prices() -> pd.DataFrame:
+    dates = _calendar()
+    return pd.DataFrame(
+        {"A": [1.0, 10.0, 10.0, 10.0], "B": [1.0, 10.0, 20.0, 20.0]},
+        index=dates,
+    )
+
+
+def test_schedule_target_weights_maps_signal_to_next_trading_session() -> None:
+    dates = _calendar()
+    decision_weights = pd.DataFrame(
+        {"A": [1.0, 0.0], "B": [0.0, 1.0]},
+        index=dates[:2],
+    )
+
+    schedule = schedule_target_weights(decision_weights, dates, lag_sessions=1)
+
+    assert isinstance(schedule, TargetWeightSchedule)
+    assert schedule.lag_sessions == 1
+    pd.testing.assert_series_equal(
+        schedule.signal_to_execution,
+        pd.Series(dates[1:3], index=dates[:2], name="execution_date"),
+    )
+    expected = decision_weights.copy()
+    expected.index = dates[1:3]
+    expected.index.name = "execution_date"
+    pd.testing.assert_frame_equal(schedule.execution_weights, expected)
+    assert (schedule.execution_weights.index > schedule.signal_to_execution.index).all()
+
+
+def test_factor_execution_research_uses_next_session_prices() -> None:
+    config = ExecutionConfig(
+        commission_bps=0,
+        stamp_tax_bps=0,
+        slippage_bps=0,
+        min_trade_amount=0,
+    )
+
+    result = run_factor_execution_research(
+        _factor_scores(),
+        _next_session_open_prices(),
+        top_k=1,
+        execution_price_field="open",
+        initial_cash=1_000.0,
+        config=config,
+    )
+
+    assert isinstance(result, FactorExecutionResult)
+    assert result.execution_price_field == "open"
+    assert result.execution.daily_executions[0].date == str(_calendar()[1])
+    assert result.execution.positions[0].holdings == {"A": 100.0}
+    assert result.execution.positions[1].holdings == {"B": 50.0}
+    assert result.execution.final_portfolio_value == pytest.approx(1_000.0)
+
+
+def test_factor_execution_result_snapshots_research_inputs() -> None:
+    scores = _factor_scores()
+    prices = _next_session_open_prices()
+
+    result = run_factor_execution_research(
+        scores,
+        prices,
+        top_k=1,
+        execution_price_field="open",
+    )
+    scores.iloc[0, 0] = -999.0
+    prices.iloc[1, 0] = 999.0
+
+    assert result.factor_scores.iloc[0, 0] == 2.0
+    assert result.execution_prices.loc[_calendar()[1], "A"] == 10.0
+    assert result.execution.positions[0].holdings["A"] < 200_000.0
+
+
+@pytest.mark.parametrize("lag_sessions", [0, -1, True])
+def test_schedule_target_weights_requires_positive_integer_lag(lag_sessions: int) -> None:
+    with pytest.raises(ValueError, match="lag_sessions"):
+        schedule_target_weights(
+            pd.DataFrame({"A": [1.0]}, index=_calendar()[:1]),
+            _calendar(),
+            lag_sessions=lag_sessions,
+        )
+
+
+def test_schedule_target_weights_rejects_signal_outside_trading_calendar() -> None:
+    weekend = pd.Timestamp("2026-01-10")
+    with pytest.raises(ValueError, match="signal dates must be trading sessions"):
+        schedule_target_weights(
+            pd.DataFrame({"A": [1.0]}, index=[weekend]),
+            _calendar(),
+        )
+
+
+def test_schedule_target_weights_rejects_missing_future_execution_session() -> None:
+    dates = _calendar()
+    with pytest.raises(ValueError, match="future execution session"):
+        schedule_target_weights(
+            pd.DataFrame({"A": [1.0]}, index=dates[-1:]),
+            dates,
+        )
+
+
+def test_factor_execution_research_requires_explicit_price_field() -> None:
+    with pytest.raises(ValueError, match="execution_price_field"):
+        run_factor_execution_research(
+            _factor_scores(),
+            _next_session_open_prices(),
+            top_k=1,
+            execution_price_field="",
+        )
+
+
+def test_factor_execution_research_accepts_empty_scores() -> None:
+    scores = pd.DataFrame(columns=["A", "B"], index=pd.DatetimeIndex([]), dtype=float)
+
+    result = run_factor_execution_research(
+        scores,
+        _next_session_open_prices(),
+        top_k=1,
+        execution_price_field="open",
+    )
+
+    assert result.schedule.execution_weights.empty
+    assert result.execution.positions == ()
+
+
+def test_factor_backtest_research_runs_signal_to_daily_performance_without_lookahead() -> None:
+    """信号日保持现金，下一日开盘成交后才参与当日收盘收益。"""
+    dates = _calendar()
+    scores = pd.DataFrame({"A": [2.0], "B": [1.0]}, index=dates[:1])
+    opens = pd.DataFrame(
+        {"A": [1.0, 10.0, 10.0, 10.0], "B": [1.0, 20.0, 20.0, 20.0]},
+        index=dates,
+    )
+    closes = pd.DataFrame(
+        {"A": [500.0, 11.0, 12.0, 12.0], "B": [500.0, 20.0, 20.0, 20.0]},
+        index=dates,
+    )
+    config = ExecutionConfig(
+        commission_bps=0,
+        stamp_tax_bps=0,
+        slippage_bps=0,
+        min_trade_amount=0,
+    )
+
+    result = run_factor_backtest_research(
+        scores,
+        execution_prices=opens,
+        valuation_prices=closes,
+        top_k=1,
+        execution_price_field="open",
+        valuation_price_field="close",
+        initial_cash=1_000.0,
+        config=config,
+    )
+
+    assert isinstance(result, FactorBacktestResult)
+    assert result.execution_price_field == "open"
+    assert result.valuation_price_field == "close"
+    pd.testing.assert_series_equal(
+        result.nav,
+        pd.Series([1.0, 1.1, 1.2, 1.2], index=dates, name="nav"),
+    )
+    pd.testing.assert_series_equal(
+        result.returns,
+        pd.Series([0.0, 0.1, 1.2 / 1.1 - 1.0, 0.0], index=dates, name="returns"),
+    )
+    assert result.stats()["n_days"] == 4
+    assert result.execution.daily_executions[0].executions == ()
+    assert result.execution.daily_executions[1].executions[0].price == 10.0
+
+
+def test_factor_backtest_result_snapshots_both_price_semantics() -> None:
+    scores = pd.DataFrame({"A": [1.0]}, index=_calendar()[:1])
+    opens = pd.DataFrame({"A": [10.0, 10.0, 10.0, 10.0]}, index=_calendar())
+    closes = pd.DataFrame({"A": [10.0, 11.0, 12.0, 13.0]}, index=_calendar())
+
+    result = run_factor_backtest_research(
+        scores,
+        execution_prices=opens,
+        valuation_prices=closes,
+        top_k=1,
+        execution_price_field="open",
+        valuation_price_field="close",
+    )
+    opens.iloc[1, 0] = 999.0
+    closes.iloc[1, 0] = 999.0
+
+    assert result.execution_prices.iloc[1, 0] == 10.0
+    assert result.valuation_prices.iloc[1, 0] == 11.0
+
+
+def test_factor_backtest_research_requires_matching_daily_calendars() -> None:
+    scores = pd.DataFrame({"A": [1.0]}, index=_calendar()[:1])
+    opens = pd.DataFrame({"A": [10.0, 10.0, 10.0, 10.0]}, index=_calendar())
+    closes = pd.DataFrame({"A": [10.0, 11.0, 12.0]}, index=_calendar()[:3])
+
+    with pytest.raises(ValueError, match="matching trading calendars"):
+        run_factor_backtest_research(
+            scores,
+            execution_prices=opens,
+            valuation_prices=closes,
+            top_k=1,
+            execution_price_field="open",
+            valuation_price_field="close",
+        )
+
+
+def test_factor_backtest_starts_at_first_signal_instead_of_price_warmup() -> None:
+    """因子预热行情不能作为空仓日混入研究绩效区间。"""
+    dates = pd.date_range("2026-01-05", periods=5, freq="B")
+    scores = pd.DataFrame({"A": [1.0]}, index=dates[2:3])
+    opens = pd.DataFrame({"A": [1.0, 1.0, 1.0, 10.0, 10.0]}, index=dates)
+    closes = pd.DataFrame({"A": [100.0, 200.0, 300.0, 11.0, 12.0]}, index=dates)
+    config = ExecutionConfig(
+        commission_bps=0,
+        stamp_tax_bps=0,
+        slippage_bps=0,
+        min_trade_amount=0,
+    )
+
+    result = run_factor_backtest_research(
+        scores,
+        execution_prices=opens,
+        valuation_prices=closes,
+        top_k=1,
+        execution_price_field="open",
+        valuation_price_field="close",
+        initial_cash=1_000.0,
+        config=config,
+    )
+
+    assert result.nav.index.equals(dates[2:])
+    pd.testing.assert_series_equal(
+        result.nav,
+        pd.Series([1.0, 1.1, 1.2], index=dates[2:], name="nav"),
+    )
+    assert result.stats()["n_days"] == 3
+
+
+def test_factor_backtest_exposes_net_benchmark_metrics() -> None:
+    dates = _calendar()
+    scores = pd.DataFrame({"A": [1.0]}, index=dates[:1])
+    prices = pd.DataFrame({"A": [10.0, 10.0, 11.0, 11.0]}, index=dates)
+    result = run_factor_backtest_research(
+        scores,
+        prices,
+        prices,
+        top_k=1,
+        execution_price_field="open",
+        valuation_price_field="close",
+        config=ExecutionConfig(
+            commission_bps=0,
+            stamp_tax_bps=0,
+            slippage_bps=0,
+            min_trade_amount=0,
+        ),
+    )
+    benchmark = pd.Series([0.0, 0.01, -0.01, 0.0], index=dates)
+
+    relative = result.benchmark_stats(benchmark)
+
+    assert relative["n_observations"] == len(result.returns)
+    assert relative["tracking_error"] > 0
+
+
+def test_factor_backtest_projects_actual_close_weights_from_ledger() -> None:
+    dates = _calendar()
+    scores = pd.DataFrame({"A": [1.0], "B": [0.0]}, index=dates[:1])
+    opens = pd.DataFrame(
+        {"A": [10.0, 10.0, 10.0, 10.0], "B": [20.0, 20.0, 20.0, 20.0]},
+        index=dates,
+    )
+    closes = pd.DataFrame(
+        {"A": [10.0, 11.0, 12.0, 12.0], "B": [20.0, 20.0, 20.0, 20.0]},
+        index=dates,
+    )
+    result = run_factor_backtest_research(
+        scores,
+        opens,
+        closes,
+        top_k=1,
+        gross_exposure=0.5,
+        execution_price_field="open",
+        valuation_price_field="close",
+        initial_cash=1_000.0,
+        config=ExecutionConfig(
+            commission_bps=0,
+            stamp_tax_bps=0,
+            slippage_bps=0,
+            min_trade_amount=0,
+        ),
+    )
+
+    weights = result.position_weights
+    cash = result.cash_weights
+
+    assert weights.index.equals(result.nav.index)
+    assert weights.columns.tolist() == ["A", "B"]
+    assert weights.loc[dates[0]].sum() == 0.0
+    assert cash.loc[dates[0]] == 1.0
+    assert weights.loc[dates[1], "A"] == pytest.approx(550.0 / 1_050.0)
+    pd.testing.assert_series_equal(
+        weights.sum(axis=1) + cash,
+        pd.Series(1.0, index=dates),
+        check_names=False,
+    )

tests/test_risk.py

@@ -0,0 +1,270 @@
+"""Risk contribution contracts and validation tests."""
+
+from __future__ import annotations
+
+import numpy as np
+import pandas as pd
+import pytest
+
+from quant_engine.risk import (
+    ComponentRiskResult,
+    CovarianceSnapshot,
+    component_var,
+    estimate_covariance_snapshot,
+    labeled_component_risk,
+    marginal_risk_contribution,
+    risk_contribution,
+)
+
+
+def test_estimate_covariance_snapshot_is_complete_case_and_reproducible() -> None:
+    dates = pd.date_range("2026-01-05", periods=6, freq="B")
+    returns = pd.DataFrame(
+        {
+            "A": [0.01, 0.02, 0.03, 0.04, 0.05, 99.0],
+            "B": [0.02, 0.01, np.nan, 0.03, 0.04, -99.0],
+        },
+        index=dates,
+    )
+    as_of = dates[4]
+
+    snapshot = estimate_covariance_snapshot(
+        returns,
+        as_of_date=as_of,
+        lookback_sessions=4,
+        min_observations=3,
+        data_snapshot_id="market-returns-20260109-v1",
+        return_frequency="1d",
+        periods_per_year=252,
+    )
+
+    expected_window = returns.loc[:as_of].tail(4)
+    expected = expected_window.dropna(how="any").cov()
+    pd.testing.assert_frame_equal(snapshot.covariance, expected)
+    assert snapshot.snapshot_id.startswith("sample-cov-v1:")
+    assert snapshot.as_of_date == as_of.date()
+    assert snapshot.method == "sample"
+    assert snapshot.window_start_date == expected_window.index[0].date()
+    assert snapshot.window_end_date == as_of.date()
+    assert snapshot.observations == 3
+    assert snapshot.lookback_sessions == 4
+    assert snapshot.missing_policy == "complete_case"
+    assert snapshot.data_snapshot_id == "market-returns-20260109-v1"
+    assert len(snapshot.input_sha256) == 64
+
+    future_changed = returns.copy()
+    future_changed.loc[dates[-1], :] = [1_000_000.0, -1_000_000.0]
+    repeated = estimate_covariance_snapshot(
+        future_changed,
+        as_of_date=as_of,
+        lookback_sessions=4,
+        min_observations=3,
+        data_snapshot_id="market-returns-20260109-v1",
+        return_frequency="1d",
+        periods_per_year=252,
+    )
+    assert repeated.snapshot_id == snapshot.snapshot_id
+    pd.testing.assert_frame_equal(repeated.covariance, snapshot.covariance)
+
+
+def test_covariance_snapshot_identity_captures_data_and_estimator_contract() -> None:
+    dates = pd.date_range("2026-01-05", periods=4, freq="B")
+    returns = pd.DataFrame(
+        {"A": [0.01, 0.02, -0.01, 0.03], "B": [0.02, -0.01, 0.01, 0.04]},
+        index=dates,
+    )
+    base = estimate_covariance_snapshot(
+        returns,
+        as_of_date=dates[-1],
+        lookback_sessions=4,
+        min_observations=3,
+        data_snapshot_id="snapshot-a",
+    )
+    different_source = estimate_covariance_snapshot(
+        returns,
+        as_of_date=dates[-1],
+        lookback_sessions=4,
+        min_observations=3,
+        data_snapshot_id="snapshot-b",
+    )
+
+    assert base.snapshot_id != different_source.snapshot_id
+    assert base.covariance.equals(different_source.covariance)
+
+
+def test_estimate_covariance_snapshot_rejects_ambiguous_or_insufficient_history() -> None:
+    dates = pd.date_range("2026-01-05", periods=4, freq="B")
+    returns = pd.DataFrame(
+        {"A": [0.01, np.nan, 0.03, 0.04], "B": [0.02, 0.01, np.nan, 0.03]},
+        index=dates,
+    )
+
+    with pytest.raises(ValueError, match="complete observations"):
+        estimate_covariance_snapshot(
+            returns,
+            as_of_date=dates[-1],
+            lookback_sessions=4,
+            min_observations=3,
+            data_snapshot_id="snapshot-a",
+        )
+
+    with pytest.raises(ValueError, match="strictly increasing"):
+        estimate_covariance_snapshot(
+            returns.iloc[::-1],
+            as_of_date=dates[-1],
+            lookback_sessions=4,
+            min_observations=2,
+            data_snapshot_id="snapshot-a",
+        )
+
+
+def test_covariance_snapshot_is_validated_and_immutable_by_interface() -> None:
+    covariance = pd.DataFrame(
+        [[0.04, 0.01], [0.01, 0.09]],
+        index=["A", "B"],
+        columns=["A", "B"],
+    )
+    snapshot = CovarianceSnapshot(
+        snapshot_id="cov-20260107-v1",
+        as_of_date="2026-01-07",
+        covariance=covariance,
+        return_frequency="1d",
+        periods_per_year=252,
+    )
+
+    covariance.loc["A", "A"] = 999.0
+    leaked_copy = snapshot.covariance
+    leaked_copy.loc["B", "B"] = 999.0
+
+    assert snapshot.as_of_date == pd.Timestamp("2026-01-07").date()
+    assert snapshot.covariance.loc["A", "A"] == pytest.approx(0.04)
+    assert snapshot.covariance.loc["B", "B"] == pytest.approx(0.09)
+
+
+@pytest.mark.parametrize(
+    ("kwargs", "message"),
+    [
+        ({"snapshot_id": ""}, "snapshot_id"),
+        ({"return_frequency": ""}, "return_frequency"),
+        ({"periods_per_year": 0}, "periods_per_year"),
+    ],
+)
+def test_covariance_snapshot_rejects_incomplete_identity(
+    kwargs: dict[str, object],
+    message: str,
+) -> None:
+    values: dict[str, object] = {
+        "snapshot_id": "cov-20260107-v1",
+        "as_of_date": "2026-01-07",
+        "covariance": pd.DataFrame([[0.04]], index=["A"], columns=["A"]),
+        "return_frequency": "1d",
+        "periods_per_year": 252,
+    }
+    values.update(kwargs)
+
+    with pytest.raises((TypeError, ValueError), match=message):
+        CovarianceSnapshot(**values)
+
+
+def test_risk_contribution_sums_to_one_for_positive_portfolio_variance() -> None:
+    weights = np.array([0.5, 0.5])
+    covariance = np.diag([1.0, 4.0])
+
+    result = risk_contribution(weights, covariance)
+
+    np.testing.assert_allclose(result, [0.2, 0.8])
+    assert result.sum() == pytest.approx(1.0)
+
+
+def test_zero_variance_portfolio_falls_back_to_equal_contribution() -> None:
+    result = risk_contribution(np.array([0.2, 0.3, 0.5]), np.zeros((3, 3)))
+
+    np.testing.assert_allclose(result, np.full(3, 1 / 3))
+
+
+def test_marginal_and_component_risk_follow_matrix_identities() -> None:
+    weights = np.array([0.25, 0.75])
+    covariance = np.array([[0.04, 0.01], [0.01, 0.09]])
+
+    marginal = marginal_risk_contribution(weights, covariance)
+    component = component_var(weights, covariance)
+
+    np.testing.assert_allclose(marginal, covariance @ weights)
+    np.testing.assert_allclose(component, weights * marginal)
+    assert component.sum() == pytest.approx(weights @ covariance @ weights)
+
+
+@pytest.mark.parametrize(
+    "function",
+    [risk_contribution, marginal_risk_contribution, component_var],
+)
+def test_risk_functions_reject_covariance_shape_mismatch(function) -> None:
+    with pytest.raises(ValueError, match="does not match weights length"):
+        function(np.array([0.5, 0.5]), np.eye(3))
+
+
+@pytest.mark.parametrize(
+    "function",
+    [risk_contribution, marginal_risk_contribution, component_var],
+)
+def test_risk_functions_reject_empty_portfolio(function) -> None:
+    with pytest.raises(ValueError, match="at least one asset"):
+        function(np.array([]), np.empty((0, 0)))
+
+
+def test_labeled_component_risk_aligns_covariance_and_closes_to_volatility() -> None:
+    weights = pd.Series({"A": 0.25, "B": 0.75}, name="weight")
+    covariance = pd.DataFrame(
+        [[0.09, 0.01], [0.01, 0.04]],
+        index=["B", "A"],
+        columns=["B", "A"],
+    )
+
+    result = labeled_component_risk(weights, covariance)
+
+    aligned = covariance.reindex(index=weights.index, columns=weights.index)
+    expected_volatility = float(np.sqrt(weights @ aligned @ weights))
+    assert isinstance(result, ComponentRiskResult)
+    assert result.component.index.tolist() == ["A", "B"]
+    assert result.portfolio_volatility == pytest.approx(expected_volatility)
+    assert result.component.sum() == pytest.approx(expected_volatility)
+    assert result.percentage.sum() == pytest.approx(1.0)
+
+
+def test_component_risk_groups_actual_asset_contributions_by_label() -> None:
+    weights = pd.Series({"A": 0.2, "B": 0.3, "C": 0.5})
+    covariance = pd.DataFrame(np.diag([0.04, 0.09, 0.16]), index=weights.index, columns=weights.index)
+    groups = pd.Series({"C": "growth", "A": "value", "B": "value"})
+
+    result = labeled_component_risk(weights, covariance)
+    grouped = result.grouped_component(groups)
+
+    assert grouped.index.tolist() == ["growth", "value"]
+    assert grouped.loc["value"] == pytest.approx(
+        result.component.loc["A"] + result.component.loc["B"]
+    )
+    assert grouped.sum() == pytest.approx(result.portfolio_volatility)
+
+
+def test_labeled_component_risk_rejects_asset_label_mismatch() -> None:
+    weights = pd.Series({"A": 0.5, "B": 0.5})
+    covariance = pd.DataFrame(np.eye(2), index=["A", "C"], columns=["A", "C"])
+
+    with pytest.raises(ValueError, match="same asset labels"):
+        labeled_component_risk(weights, covariance)
+
+
+def test_labeled_component_risk_rejects_invalid_covariance() -> None:
+    weights = pd.Series({"A": 0.5, "B": 0.5})
+    asymmetric = pd.DataFrame([[1.0, 0.2], [0.1, 1.0]], index=weights.index, columns=weights.index)
+
+    with pytest.raises(ValueError, match="symmetric"):
+        labeled_component_risk(weights, asymmetric)
+
+
+def test_labeled_component_risk_rejects_zero_variance_portfolio() -> None:
+    weights = pd.Series({"A": 0.5, "B": 0.5})
+    covariance = pd.DataFrame(np.zeros((2, 2)), index=weights.index, columns=weights.index)
+
+    with pytest.raises(ValueError, match="positive portfolio variance"):
+        labeled_component_risk(weights, covariance)