wip: hand off research artifact contract

README.md

@@ -25,6 +25,7 @@
 - `backtest` — weight-based 多日仿真（rebalance_table / compute_nav / compare_to_benchmark）
 - `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）
@@ -136,6 +137,28 @@ print(attribution.residual)  # 应接近 0；否则说明贡献未闭合到账
 # 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
+
+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="<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,
+)
+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(

docs/OPEN_SOURCE_REFERENCES.md

@@ -16,6 +16,17 @@
 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。
+
 ## hikyuu 的定位
 
 [hikyuu](https://github.com/fasiondog/hikyuu) 的 SG / MM / CN / PG 部件化思想、

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

@@ -0,0 +1,37 @@
+# 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；
+- reserved risk snapshot table；
+- 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 --cov=src --cov-report=term-missing`: 520 passed，9 个既有 SciPy warning；
+- total coverage 91%，`artifact.py` 91%；
+- `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。
+
+## Next action
+
+在 `research_results` 新建独立分支，实现只接受 `ResearchRunArtifact.table_frames()` 的
+ClickHouse / artifact-store adapter；先以 mock writer 做契约测试，不接触真实数据库。

src/quant_engine/artifact.py

@@ -0,0 +1,491 @@
+"""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
+
+RESEARCH_ARTIFACT_SCHEMA_VERSION = "1.0.0"
+
+RISK_COLUMNS = [
+    "run_id",
+    "trade_date",
+    "asset_id",
+    "weight",
+    "marginal_risk",
+    "component_risk",
+    "risk_contribution",
+    "covariance_snapshot_id",
+]
+
+__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["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 _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,
+) -> 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=pd.DataFrame(columns=RISK_COLUMNS),
+        _performance=_build_performance(result, normalized_run_id, benchmark_returns),
+    )

src/quant_engine/metrics.py

@@ -65,6 +65,20 @@ 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)
@@ -120,6 +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),

tests/test_artifact.py

@@ -0,0 +1,200 @@
+"""Stable research-run artifact contracts for downstream persistence."""
+
+from __future__ import annotations
+
+import json
+
+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
+
+
+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,
+) -> 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,
+    )
+
+
+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 {"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",
+    ]
+    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_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_metrics.py

@@ -14,6 +14,7 @@ from quant_engine.metrics import (
     calmar_ratio,
     max_drawdown,
     sharpe_ratio,
+    sortino_ratio,
     summary,
     win_rate,
 )
@@ -48,9 +49,22 @@ 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])
 
@@ -80,7 +94,15 @@ def test_summary_aliases_match_canonical_fields() -> None:
 
 @pytest.mark.parametrize(
     "metric",
-    [annualized_return, annualized_volatility, sharpe_ratio, max_drawdown, calmar_ratio, win_rate],
+    [
+        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"):