feat(factor): challenger CLI+月度链 stage6 接线(影子失败不阻链;宽表源=stage4 截面盘,月度批 values 不含 12 源) [nas]

sanguo_factor/challenger_lgbm.py

@@ -203,3 +203,24 @@ def run_challenge(values_dir: str, vnpy_db: str, as_of: str, out_dir: str,
     with open(path, "w", encoding="utf-8") as f:
         json.dump(doc, f, ensure_ascii=False, indent=2)
     return path
+
+
+def main(argv: list[str] | None = None) -> int:
+    import argparse
+    ap = argparse.ArgumentParser(description="LGBM challenger 三路对拍(月度链 stage6)")
+    ap.add_argument("--values-dir", required=True,
+                    help="因子截面宽表目录(每因子一 parquet;NAS=stage4 截面盘"
+                         " /volume1/stock/factor_cross_section,月度批 values/ 只含"
+                         "注册表因子不含 quant12 12 源)")
+    ap.add_argument("--as-of", required=True)
+    ap.add_argument("--out-dir", required=True, help="报告根(factor_monthly)")
+    ap.add_argument("--vnpy-db", default=None)
+    ap.add_argument("--host", default="nas")
+    a = ap.parse_args(argv)
+    try:
+        path = run_challenge(a.values_dir, a.vnpy_db, a.as_of, a.out_dir, host=a.host)
+    except FileNotFoundError as e:
+        print(f"[challenger] skip: {e}")
+        return 0          # 无宽表=非错误(截面盘未建),不阻链
+    print(f"[challenger] 对拍件: {path}")
+    return 0

scripts/nas_sync/run_factor_monthly_standalone.sh

@@ -156,6 +156,25 @@ PY
   rc_replay=$?
   echo "=== $(date '+%F %T') stage5 verdict_replay exit=$rc_replay (派生件,不进 final) ==="
 
+  # stage6 challenger 三路对拍(影子实验,失败不阻月度链;产物落子目录
+  # 判定层端点只读根层零影响)。宽表源=stage4 截面盘(12 源主 parquet,
+  # daily_section 幂等 merge 累积)——月度批 values/ 只含注册表因子,
+  # 不含 quant12 12 源(2026-10-10 现场核实 NAS values/monthly_2026-09)。
+  "$DOCKER" run --rm --name sanguo-factor-chal --user "${UID_ADMIN}:${GID_ADMIN}" \
+    --group-add "${GID_ADMINS}" --no-healthcheck --entrypoint python \
+    -e HOME=/tmp -e MPLCONFIGDIR=/tmp/mpl \
+    -v /volume1/stock:/volume1/stock \
+    -v "$APP":/app:ro \
+    -w /app \
+    sanguo_vnpy_v2:lock-aligned \
+    -m sanguo_factor.challenger_lgbm \
+    --values-dir /volume1/stock/factor_cross_section \
+    --as-of "$AS_OF" --out-dir "$OUT_DIR" \
+    --vnpy-db /volume1/stock/sanguo_vnpy_v2/data_backup/quant_trading.db \
+    --host nas
+  rc_chal=$?
+  echo "=== $(date '+%F %T') stage6 challenger exit=$rc_chal (影子,不进 final) ==="
+
   # 真失败=②或③ rc=1(读件错);exit 2 是信号按 0 处理;④ 非零=真失败
   final=0
   [ "$rc_review" -eq 1 ] && final=1

tests/factor/test_challenger_lgbm.py

@@ -145,3 +145,22 @@ def test_run_challenge_end_to_end(tmp_path, monkeypatch):
     assert doc["pool"]["names"] == ["s0", "s1"]
     assert len(doc["feature_importance"]) == 2
     assert doc["split"]["oos_month"] == "2025-03"
+
+
+def test_cli_smoke(tmp_path, monkeypatch, capsys):
+    from sanguo_factor import challenger_lgbm as cl
+    idx = pd.date_range("2025-01-01", "2025-03-31", freq="B")
+    close = pd.DataFrame(100 + np.cumsum(np.random.default_rng(1).normal(0.4, size=(len(idx), 2)), axis=0),
+                         index=idx, columns=["a", "b"])
+    monkeypatch.setattr(cl, "_load_close_wide", lambda db, c, s, e: close)
+    monkeypatch.setattr(cl, "load_pool", lambda: {
+        "s0": {"direction": "+", "weight": 0.6},
+        "s1": {"direction": "-", "weight": 0.4}})
+    vdir = tmp_path / "vals"; vdir.mkdir()
+    for n in ("s0", "s1"):
+        pd.DataFrame(np.random.default_rng(2).normal(size=(len(idx), 2)),
+                     index=idx, columns=["a", "b"]).to_parquet(vdir / f"{n}.parquet")
+    rc = cl.main(["--values-dir", str(vdir), "--as-of", "2025-03-31",
+                  "--out-dir", str(tmp_path), "--vnpy-db", "fake.db"])
+    assert rc == 0
+    assert (tmp_path / "challenger_lgbm" / "nas_2025-03-31.json").exists()