fix(api): codex review 修批——factors 列表 icFullT 从月报 factor_stats.tAll 接真(单次读取)+decompose similarity 仅建条落盘(已存在幂等重注册不重写) [vps]

2026-10-10 11:14:15 +08:00
parent eaac48a1db
commit 28e648b4fe
3 changed files with 91 additions and 9 deletions
@@ -437,6 +437,13 @@ def factors() -> dict:
    reg = vr.load_registry(ensure_runtime_registry(
        _factor_registry_path(), os.path.join("config", "factor_registry.yaml")))
    points, last_eval = _eval_latest_points()
+    # 全史 t(=全期合成 t)从最新月报 factor_stats 一次性接真(spec §4.2 承诺
+    # factors 端点升级;单次读取,勿循环内重读——codex review HIGH)
+    reports = _monthly_reports()
+    full_t: dict[str, Any] = (
+        {n: (s or {}).get("tAll")
+         for n, s in (reports[0][2].get("factor_stats") or {}).items()}
+        if reports else {})
    items: list[dict[str, Any]] = []
    for name, e in reg["factors"].items():
        if e.get("status") == "graveyard":
@@ -453,7 +460,7 @@ def factors() -> dict:
                      "hypothesis": e.get("hypothesis"),
                      "description": e.get("description") or "",
                      "icRecentT": t,   # 最近批(12M 滚动窗)即近窗 t
-                      "icFullT": None,  # eval_store 每批单窗 t,无全史批数据源,如实 null
+                      "icFullT": full_t.get(name),  # 全期合成 t(月报 factor_stats.tAll)
                      "promotedAtT": e.get("promotion_t") or None,
                      "similarity": e.get("similarity"),  # 疑似换皮提示(注册时落)
                      "decayMonths": 0,
@@ -1169,6 +1176,9 @@ async def _decompose_worker(hyp_id: str, config, job_id: str | None = None) -> d
            today = date.today().isoformat()
            for cand in result["passed"]:
                src = derive_source(cand["expression"])   # 已过门,必为 str
+                # 仅建条纪律(codex review):已存在条目(同名同假设幂等重注册)
+                # 不重写 similarity——与 description/origin 落盘纪律同款
+                is_new = cand["name"] not in reg["factors"]
                vr.upsert_factor(reg, cand["name"], hypothesis=hyp_id,
                                 status="incubating", origin="decomposer",
                                 description=cand.get("description"))
@@ -1180,14 +1190,15 @@ async def _decompose_worker(hyp_id: str, config, job_id: str | None = None) -> d
                # AST 防换皮提示(spec §4.2 2026-10-10):对既有池比对,≥0.6 存
                # entry.similarity——硬门(dup_subtree)外的部分同构仍可注册,
                # 提示非硬拒,判定人做.池=注册表条目当前表达式(versions[-1]).
-                from sanguo_factor import expression_match as em
-                _cands = {n: str(((v.get("versions") or [{}])[-1]
-                                  .get("params") or {}).get("expression") or "")
-                          for n, v in reg["factors"].items()
-                          if n != cand["name"]}
-                _sim = em.top_similar(str(cand["expression"]), _cands)
-                if _sim:
-                    reg["factors"][cand["name"]]["similarity"] = _sim
+                if is_new:
+                    from sanguo_factor import expression_match as em
+                    _cands = {n: str(((v.get("versions") or [{}])[-1]
+                                      .get("params") or {}).get("expression") or "")
+                              for n, v in reg["factors"].items()
+                              if n != cand["name"]}
+                    _sim = em.top_similar(str(cand["expression"]), _cands)
+                    if _sim:
+                        reg["factors"][cand["name"]]["similarity"] = _sim
                registered.append({"name": cand["name"], "source": src,
                                   "expression": cand["expression"],
                                   "description": cand.get("description", ""),
@@ -155,3 +155,34 @@ def test_factor_detail_ic_stats(client, tmp_path, monkeypatch):
    monkeypatch.setenv("SANGUO_FACTOR_MONTHLY_DIR", str(empty))
    r2 = client.get(f"/api/v1/pipeline/factors/{name}/detail")
    assert r2.status_code == 200 and r2.json()["factor"]["icStats"] is None
+
+
+def test_factors_list_ic_full_t_from_stats(client, tmp_path, monkeypatch):
+    """codex review:列表端点 icFullT 从最新报告 factor_stats.tAll 接真
+    (spec 承诺 factors 端点全史 t 升级);无报告仍如实 None."""
+    import json as _json
+    name, _ = _seed_factor_card(client, name="fa_x")
+    rep_dir = tmp_path / "reports" / "factor_monthly"
+    rep_dir.mkdir(parents=True)
+    doc = {"as_of": "2026-09-30",
+           "factor_stats": {"fa_x": {"icAll": 0.04, "tAll": 1.7321,
+                                     "positiveRatio": 1.0,
+                                     "byYear": {"2025": 0.05}}}}
+    (rep_dir / "nas_2026-09-30.json").write_text(_json.dumps(doc), "utf-8")
+    monkeypatch.setenv("SANGUO_FACTOR_MONTHLY_DIR", str(rep_dir))
+    items = client.get("/api/v1/pipeline/factors").json()["items"]
+    row = next(i for i in items if i["id"] == name)
+    assert row["icFullT"] == 1.7321
+    # tAll=None(样本不足)如实 null,不造数
+    doc["factor_stats"]["fa_x"]["tAll"] = None
+    (rep_dir / "nas_2026-09-30.json").write_text(_json.dumps(doc), "utf-8")
+    items = client.get("/api/v1/pipeline/factors").json()["items"]
+    row = next(i for i in items if i["id"] == name)
+    assert row["icFullT"] is None
+    # 无报告:零读不崩,如实 null
+    empty = tmp_path / "reports_empty"
+    empty.mkdir()
+    monkeypatch.setenv("SANGUO_FACTOR_MONTHLY_DIR", str(empty))
+    items = client.get("/api/v1/pipeline/factors").json()["items"]
+    row = next(i for i in items if i["id"] == name)
+    assert row["icFullT"] is None
@@ -295,6 +295,46 @@ class TestDecompose:
        from sanguo_api import routes_pipeline as rp
        assert isinstance(rp._DECOMPOSE_LOCK, type(threading.Lock()))
        assert isinstance(rp._GRADUATE_LOCK, type(threading.Lock()))
+    def test_decompose_similarity_only_on_new_entry(self, client, fake_llm,
+                                                     tmp_path, monkeypatch):
+        """codex review 仅建条纪律:条目已存在时 upsert 不重写 similarity
+        (强化形态——同名异假设 upsert 会拒,同名同假设幂等返回,此测后者)."""
+        import yaml
+        # 先建卡拿 hyp id,再预置 registry:fa_dup 绑同一假设(幂等重注册路径)
+        hyp = _seed_card(client)
+        reg_path = tmp_path / "r_sim2.yaml"
+        monkeypatch.setenv("SANGUO_FACTOR_REGISTRY", str(reg_path))
+        reg = {"factors": {
+            "fa_old": {"name": "fa_old", "hypothesis": "H-1",
+                       "status": "assessable",
+                       "versions": [{"v": 1, "commit": "x",
+                                     "params": {"expression":
+                                                "ts_mean(close, 5) * turnover"},
+                                     "effective_from": "2026-09-01"}]},
+            "fa_dup": {"name": "fa_dup", "hypothesis": hyp,
+                       "status": "incubating",
+                       "versions": [{"v": 1, "commit": "x",
+                                     "params": {"expression": "close + open"},
+                                     "effective_from": "2026-09-01"}]}}}
+        with open(reg_path, "w", encoding="utf-8") as f:
+            yaml.safe_dump(reg, f, allow_unicode=True)
+        # 绕开 LLM 与 name_taken 硬门,直接喂「已存在名」的 passed
+        import sanguo_api.routes_pipeline as rp
+
+        async def fake_run(client_, card, **k):
+            return {"passed": [{"name": "fa_dup",
+                                "expression": "ts_mean(close, 5) / volume",
+                                "description": "同窗均值除量",
+                                "justification": "j"}],
+                    "failed": [], "rounds": 1}
+
+        monkeypatch.setattr(rp, "_run_decompose", fake_run)
+        assert _wait_job(client, hyp)["status"] == "completed"
+        with open(reg_path, encoding="utf-8") as f:
+            reg2 = yaml.safe_load(f)
+        # 已存在条目:similarity 不写入(旧值 None 保持 None)
+        assert "similarity" not in reg2["factors"]["fa_dup"]
+
    def test_decompose_register_similarity_hint(self, client, fake_llm,
                                                tmp_path, monkeypatch):
        """AST 防换皮提示(spec §4.2 2026-10-10):新因子注册时对既有池比对,