feat(product): 取款主源切到 dim_style，平台编码与销量表按系列共享

产品生命进程建档（dim_style）成为款式身份唯一权威，采集端不再依赖 workflow_dynamic_styles + cmt_styles 双份维护： - workflow_config 运行时改读 dim_style（ERP 编码、四平台商品 ID、销量表、系列归属），cmt_styles 降级为 dim_style 不存在时的兜底；source_record_id 前缀由 cmt_style 改为 lifecycle_style - merge_lifecycle_style_records 把 series_name / is_series_anchor / sales_bitable_url 写进运行时记录，建档地址优先于动态配置 - StyleConfigLoader 新增 _apply_series_sharing：按系列标注各平台编码的承担款，子款继承主款销量表，但不复制平台商品编码，避免同一份访客/加购被同系列多款重复入账 - ERP 三道门（ERP 昨日采集、全店铺日报、月度销量表）只校验款式编码；平台编码缺失时提示「同系列某款已在采，本款只采 ERP 销量」 - CACHE_SCHEMA_VERSION 5 -> 6，旧缓存自动失效系（系列）级配置结果：ERP 门可采款数 33 -> 53，全店铺日报取款计划 42 -> 198。
2026-10-28 14:20:59 +08:00
1 parent 3cf7048140
commit ee6fd4170e
@@ -33,6 +33,25 @@ DEFAULT_SEED_PATH = (
    / "workflow-dynamic-config-seed.json"
 )

+DIM_STYLE_RUNTIME_SQL = """
+    SELECT s.id,
+           s.style_name AS name,
+           COALESCE(s.brand, '') AS brand,
+           COALESCE(s.erp_style_codes, '[]'::jsonb) AS erp_style_codes,
+           jsonb_build_object(
+               'tm', COALESCE(s.tm_spus, '[]'::jsonb),
+               'jd', COALESCE(s.jd_spus, '[]'::jsonb),
+               'dy', COALESCE(s.dy_spus, '[]'::jsonb),
+               'jd_self', COALESCE(s.jd_self_skus, '[]'::jsonb)
+           ) AS platform_product_ids,
+           COALESCE(s.bitable_weekly_url, '') AS sales_bitable_url,
+           COALESCE(s.series_name, '') AS series_name,
+           COALESCE(s.is_series_anchor, FALSE) AS is_series_anchor
+    FROM dim_style s
+    WHERE COALESCE(s.style_name, '') <> ''
+    ORDER BY s.style_name, s.id
+"""
+
 CONFIG_FIELDS = (
    "platform",
    "erp_codes",
@@ -298,8 +317,9 @@ def merge_lifecycle_style_records(
    """Overlay lifecycle product identity on legacy target configuration rows.

    ``workflow_dynamic_*`` still owns Feishu target URLs and persona targets, while
-    ``cmt_styles`` owns ERP codes and product IDs.  The result intentionally keeps
-    the old flat runtime contract so existing collectors need no per-workflow fork.
+    ``dim_style`` (产品生命进程建档) owns ERP codes, product IDs and the sales sheet.
+    The result intentionally keeps the old flat runtime contract so existing
+    collectors need no per-workflow fork.
    """

    dynamic_by_style: dict[str, list[Mapping[str, Any]]] = {}
@@ -311,7 +331,7 @@ def merge_lifecycle_style_records(
    lifecycle_by_style: dict[str, Mapping[str, Any]] = {}
    lifecycle_order: list[str] = []
    for row in lifecycle_rows:
-        style_name = " ".join(str(row.get("name") or "").split())
+        style_name = " ".join(str(row.get("name") or row.get("style_name") or "").split())
        if not style_name or style_name in lifecycle_by_style:
            continue
        lifecycle_by_style[style_name] = row
@@ -379,6 +399,19 @@ def merge_lifecycle_style_records(
                    if item_id not in dynamic_unknown_ids.setdefault(label, []):
                        dynamic_unknown_ids[label].append(item_id)

+        # 销量飞书表：生命进程建档的地址优先，动态配置只在建档为空时兜底。
+        sales_bitable_url = str(lifecycle.get("sales_bitable_url") or "").strip()
+        if not sales_bitable_url and legacy_rows:
+            sales_bitable_url = str(legacy_rows[0].get("sales_bitable_url") or "").strip()
+        series_name = str(lifecycle.get("series_name") or "").strip()
+        is_series_anchor = bool(lifecycle.get("is_series_anchor"))
+
+        # 生命进程建档是唯一权威：销量表与系列归属直接写进运行时记录，
+        # 子款即使没填平台编码/销量表，也能被下游按系列主款补齐。
+        template["sales_bitable_url"] = sales_bitable_url
+        template["series_name"] = series_name
+        template["is_series_anchor"] = is_series_anchor
+
        if managed:
            labels = []
            for label in LIFECYCLE_PLATFORM_LABELS.values():
@@ -413,7 +446,7 @@ def merge_lifecycle_style_records(
                else list(dynamic_ids.get(key, dynamic_unknown_ids.get(label, [])))
            )
            output["source_record_id"] = (
-                f"cmt_style:{lifecycle.get('id')}" if key and managed else output.get("source_record_id")
+                f"lifecycle_style:{lifecycle.get('id')}" if key and managed else output.get("source_record_id")
            )
            records.append(output)

@@ -1158,16 +1191,24 @@ class PostgresWorkflowConfigStore:
                    "WHERE s.enabled ORDER BY s.style_name, p.id"
                )
                rows = cursor.fetchall()
-                cursor.execute("SELECT to_regclass('public.cmt_styles') AS table_name")
-                cmt_table = cursor.fetchone() or {}
-                if cmt_table.get("table_name"):
-                    cursor.execute(
-                        "SELECT id, name, brand, erp_style_codes, platform_product_ids "
-                        "FROM cmt_styles ORDER BY name, id"
-                    )
+                cursor.execute("SELECT to_regclass('public.dim_style') AS table_name")
+                dim_table = cursor.fetchone() or {}
+                if dim_table.get("table_name"):
+                    # 产品生命进程（dim_style）是款式身份的唯一权威来源：
+                    # ERP 款式编码逐款填写，平台商品编码与销量表允许整系列只填主款。
+                    cursor.execute(DIM_STYLE_RUNTIME_SQL)
                    lifecycle_rows = cursor.fetchall()
                else:
-                    lifecycle_rows = []
+                    cursor.execute("SELECT to_regclass('public.cmt_styles') AS table_name")
+                    cmt_table = cursor.fetchone() or {}
+                    if cmt_table.get("table_name"):
+                        cursor.execute(
+                            "SELECT id, name, brand, erp_style_codes, platform_product_ids "
+                            "FROM cmt_styles ORDER BY name, id"
+                        )
+                        lifecycle_rows = cursor.fetchall()
+                    else:
+                        lifecycle_rows = []
        personas: dict[int, dict[str, str]] = {}
        for row in rows:
            if row.get("platform_enabled") is False:
@@ -18,7 +18,7 @@ from scrapling.fetchers import DynamicFetcher
 try:
    from . import collect_erp_yesterday_metrics as erp
    from .collect_retry_utils import retry_step
-    from .config.style_config_loader import StyleConfigLoader, has_complete_style_identity
+    from .config.style_config_loader import StyleConfigLoader
    from .db import (
        get_conn,
        init_schema,
@@ -35,7 +35,7 @@ try:
 except ImportError:  # Direct script execution from the module root.
    import collect_erp_yesterday_metrics as erp
    from collect_retry_utils import retry_step
-    from config.style_config_loader import StyleConfigLoader, has_complete_style_identity
+    from config.style_config_loader import StyleConfigLoader
    from db import get_conn, init_schema, upsert_erp_all_shop_style_daily_metrics
    from erp_login_product_analysis import (
        DEFAULT_CONFIG,
@@ -88,7 +88,7 @@ def build_style_plans(payload: Mapping[str, Any]) -> tuple[StylePlan, ...]:
                if str(code).strip()
            )
        )
-        if not style_name or not codes or not has_complete_style_identity(config):
+        if not style_name or not codes:
            continue
        for code in codes:
            previous = code_owners.setdefault(code, style_name)
@@ -32,7 +32,7 @@ except ImportError:  # Direct script execution from the module root.
    from runtime_paths import NORMALIZED_DATA_ROOT, STATE_ROOT, managed_data_path


-CACHE_SCHEMA_VERSION = 5
+CACHE_SCHEMA_VERSION = 6

 # 表格字段名（按实际表格设置，支持别名）
 FIELD_ALIASES = {
@@ -266,6 +266,8 @@ class StyleConfigLoader:
                        "style_analysis_bitable_url", ""
                    ),
                    "destinations": row.get("destinations", []),
+                    "series_name": row.get("series_name", ""),
+                    "is_series_anchor": bool(row.get("is_series_anchor", False)),
                }
            )
        return records
@@ -315,6 +317,9 @@ class StyleConfigLoader:
                "jd_persona_bitable": {},
                "style_analysis_bitable": {},
                "destinations": [],
+                "series_name": "",
+                "is_series_anchor": False,
+                "series": {},
            }

        # ── 第一遍:款式级字段 ──────────────────────────────────────
@@ -332,6 +337,13 @@ class StyleConfigLoader:
            if brand and not style["brand"]:
                style["brand"] = brand

+            # 系列归属（产品生命进程建档维护）：同系列可共享平台编码与销量表
+            series_name = str(record.get("series_name") or "").strip()
+            if series_name and not style["series_name"]:
+                style["series_name"] = series_name
+            if record.get("is_series_anchor"):
+                style["is_series_anchor"] = True
+
            destinations = record.get("destinations")
            if isinstance(destinations, list) and destinations and not style["destinations"]:
                style["destinations"] = [
@@ -427,6 +439,9 @@ class StyleConfigLoader:
            elif platform == "jd_self" and ids:
                style["jd_self"]["skus"] = ids

+        # ── 第三遍: 系列内共享（平台编码 / 销量表只要求主款填写）──────────
+        self._apply_series_sharing(styles)
+
        return {
            "styles": styles,
            "source": "database",
@@ -434,6 +449,46 @@ class StyleConfigLoader:
            "schema_version": CACHE_SCHEMA_VERSION,
        }

+    @staticmethod
+    def _apply_series_sharing(styles: dict[str, dict]) -> None:
+        """把同系列的平台编码归属与销量表摊到每个子款。
+
+        产品生命进程的录入约定：ERP 款式编码逐款必填，平台商品编码和
+        销量飞书表整系列只需要主款（锚点）填一次。这里只做「归属」标注
+        和销量表继承，不复制平台商品编码——同一个商品 ID 若被同系列多款
+        分别采集，会把同一份访客/加购重复写进每日指标。
+        """
+
+        by_series: dict[str, list[str]] = {}
+        for name, style in styles.items():
+            series = str(style.get("series_name") or "").strip()
+            if series:
+                by_series.setdefault(series, []).append(name)
+
+        for series, members in by_series.items():
+            # 锚点优先，其余按名称稳定排序，保证每次运行归属一致
+            members.sort(key=lambda n: (not styles[n].get("is_series_anchor"), n))
+            platform_owner: dict[str, str] = {}
+            for platform, ids_key in PRODUCT_ID_FIELDS.items():
+                for member in members:
+                    if styles[member].get(platform, {}).get(ids_key):
+                        platform_owner[platform] = member
+                        break
+            sales_owner = next(
+                (m for m in members if (styles[m].get("sales_bitable") or {}).get("base_token")),
+                "",
+            )
+            for member in members:
+                style = styles[member]
+                style["series"] = {
+                    "name": series,
+                    "is_anchor": bool(style.get("is_series_anchor")),
+                    "platform_owner": dict(platform_owner),
+                    "sales_owner": sales_owner,
+                }
+                if not style["sales_bitable"] and sales_owner:
+                    style["sales_bitable"] = dict(styles[sales_owner]["sales_bitable"])
+
    # ------------------------------------------------------------------
    # 缓存与回退
    # ------------------------------------------------------------------
@@ -656,10 +711,11 @@ class StyleConfigLoader:
        ]

    def get_erp_styles_input(self) -> list[dict]:
+        """ERP 编码清单：只要求款式编码，平台编码/销量表由系列主款承担。"""
        return [
            {"style_name": name, "erp_style_codes": cfg["erp_codes"]}
            for name, cfg in self.load()["styles"].items()
-            if self._has_complete_identity(cfg)
+            if cfg.get("erp_codes")
        ]

    def get_bitable_style_map(self) -> dict:
@@ -745,14 +801,17 @@ class StyleConfigLoader:
        payload = self.load()
        result = {p: {"collectable": [], "skipped": []} for p in ("tm", "jd", "dy")}
        for name, cfg in payload["styles"].items():
-            identity_missing = self._identity_missing(cfg)
+            # 平台编码在下面按平台逐项判定，这里不重复报「平台商品编码」
+            identity_missing = [
+                item for item in self._identity_missing(cfg) if item != "平台商品编码"
+            ]
            for plat in ("tm", "jd", "dy"):
                ids_key = "spus" if plat == "jd" else "item_ids"
                missing = list(identity_missing)
                if not self._cfg_has_sales_bitable(cfg):
                    missing.append("销量目标地址")
                if not cfg.get(plat, {}).get(ids_key):
-                    missing.append(f"{plat}商品编码")
+                    missing.append(self._platform_missing_label(cfg, plat))
                if missing:
                    result[plat]["skipped"].append(
                        {"style": name, "reason": "缺 " + "/".join(dict.fromkeys(missing))}
@@ -761,11 +820,25 @@ class StyleConfigLoader:
                    result[plat]["collectable"].append(name)
        return result

+    def _platform_missing_label(self, cfg: dict, platform: str) -> str:
+        """平台商品编码缺失的提示文案。
+
+        同系列其它款已填编码时，本款不采平台流量是预期行为（平台数据是
+        商品/系列级，重复采集会把同一份访客数写进多个款），因此文案指向
+        承担款而不是报了「缺配置」。
+        """
+
+        owner = (cfg.get("series") or {}).get("platform_owner", {}).get(platform, "")
+        if owner and owner != cfg.get("name"):
+            return f"{platform}商品编码（同系列「{owner}」已在采，本款只采 ERP 销量）"
+        return f"{platform}商品编码"
+
    def get_erp_daily_styles(self) -> dict:
-        """ERP daily 门：ERP 编码、至少一个平台商品编码和销量目标都要有。
+        """ERP daily 门：只要求 ERP 款式编码（有销量表写入需求时再校验表地址）。

        返回 {collectable, skipped, brand_map: {style: brand}}。
-        ERP 一次跑覆盖 jd/dy/tm 三个平台，平台商品编码只用于确认款式已完成商品身份配置。
+        ERP 销量按款式编码逐款查，平台商品编码与销量表都是系列级配置，
+        由同系列主款承担，子款不需要重复填写。
        brand_map 给 collect_erp_yesterday_metrics.py 按品牌选店铺
        (光影行星旗下店铺 vs ozko旗舰店)。
        """
@@ -774,7 +847,9 @@ class StyleConfigLoader:
        skipped: list[dict] = []
        brand_map: dict[str, str] = {}
        for name, cfg in payload["styles"].items():
-            missing = self._identity_missing(cfg)
+            missing: list[str] = []
+            if not cfg.get("erp_codes"):
+                missing.append("ERP款式编码")
            if not self._cfg_has_sales_bitable(cfg):
                missing.append("销量目标地址")
            if not missing:
@@ -23,10 +23,7 @@ try:
        collect_monthly_erp_metrics,
        monthly_report_interval,
    )
-    from .config.style_config_loader import (
-        StyleConfigLoader,
-        has_complete_style_identity,
-    )
+    from .config.style_config_loader import StyleConfigLoader
    from .lark_cli_runtime import run_lark_cli
 except ImportError:  # Direct script execution from the module root.
    from collect_erp_monthly_metrics import (
@@ -35,10 +32,7 @@ except ImportError:  # Direct script execution from the module root.
        collect_monthly_erp_metrics,
        monthly_report_interval,
    )
-    from config.style_config_loader import (
-        StyleConfigLoader,
-        has_complete_style_identity,
-    )
+    from config.style_config_loader import StyleConfigLoader
    from lark_cli_runtime import run_lark_cli

 _MARKDOWN_LINK = re.compile(r"^\s*\[([^]]+)]\([^)]*\)\s*$")
@@ -330,7 +324,7 @@ def plan_erp_styles(
                str(code).strip() for code in raw_codes if str(code).strip()
            )
        )
-        if not codes or not has_complete_style_identity(style_config):
+        if not codes:
            missing.append(target.product_name)
            continue
        key = normalized_name(style_name)