-- ============================================================================
-- 载体判定与人工块量化（只读量化 + 回填草案）
-- ----------------------------------------------------------------------------
-- 状态：草案（DRAFT）。**未接入** apps/backend/src/db/migrations。
--       当前已使用迁移至 106；接入时按当前最大迁移号顺延，并先跑 `npm run check:sql`。
-- 基线：main @ 7542d547；数据来源 = 本地只读克隆（生产快照，orders 316,597，数据截至 2026-10-14 14:52）
-- 金额单位：分（BIGINT）。orders.total_amount / work_orders.reward_amount / source_order_amount_fen 均为分。
-- 口径基准：§1 所有查询以「已支付订单项」为单位；人工块 = 既无 fulfillment_tasks 也无 work_orders。
-- 用途：§1 是可重复执行的只读量化；§2–§4 是载体判定/回填草案，不作为现行迁移。
-- 设计依据：docs/成本中心与三块履约模型.md、docs/README.md 第 2 条口径。
-- ============================================================================


-- ============================================================================
-- §0 只读安全（对生产库执行 §1 时先设置；只跑 SELECT）
-- ============================================================================
-- SET default_transaction_read_only = on;
-- SET statement_timeout = '60s';
-- 所有查询里的“截止时间”统一由 CTE w 取 max(paid_at)，避免写死日期导致窗口漂移。


-- ============================================================================
-- §1 量化查询（只读，可直接对生产/克隆执行）
-- ============================================================================

-- Q1 载体分布：按来源统计「自动发货 / 工单 / 人工 / 双载体冲突」
-- 实测（快照，近 30 天）：91 人工 38,451（34.2%，¥485.3 万）；PDD 人工 2,066（55.6%，¥36.1 万）；
--                          抖音 人工 2/4；双载体冲突 = 0（三载体互斥在数据上成立）。
WITH w AS (
  SELECT max(paid_at) AS hi FROM orders WHERE pay_status = 'paid' AND paid_at IS NOT NULL
),
base AS (
  SELECT oi.id AS item_id,
         o.provider,
         o.shop_id,
         o.total_amount,
         EXISTS (SELECT 1 FROM fulfillment_tasks ft
                  WHERE ft.order_item_id = oi.id AND ft.executor_key = 'affiliate_dash') AS has_auto,
         EXISTS (SELECT 1 FROM fulfillment_tasks ft WHERE ft.order_item_id = oi.id)      AS has_task,
         EXISTS (SELECT 1 FROM work_orders wo WHERE wo.order_item_id = oi.id)            AS has_wo
  FROM order_items oi
  JOIN orders o ON o.id = oi.order_id, w
  WHERE o.pay_status = 'paid'
    AND o.paid_at >= w.hi - interval '30 days'
)
SELECT provider,
       count(*)                                              AS paid_items,
       count(*) FILTER (WHERE has_auto)                       AS auto_items,
       count(*) FILTER (WHERE has_wo)                         AS work_order_items,
       count(*) FILTER (WHERE NOT has_task AND NOT has_wo)     AS manual_items,
       count(*) FILTER (WHERE has_task AND has_wo)             AS conflict_items,
       round(sum(total_amount) FILTER (WHERE NOT has_task AND NOT has_wo) / 100.0) AS manual_yuan,
       round(100.0 * count(*) FILTER (WHERE NOT has_task AND NOT has_wo) / count(*), 1) AS manual_pct
FROM base
GROUP BY provider
ORDER BY manual_items DESC;

-- Q1b 非 affiliate_dash 的任务执行器（识别历史执行器，避免把“历史自动”误判成人工）
-- 实测：affiliate_dash 30,902 项；kuaishou_ct_assisted 262 项（= KUAISHOU_CLOUD，已下线，见 executors/registry.ts）
WITH w AS (
  SELECT max(paid_at) AS hi FROM orders WHERE pay_status = 'paid' AND paid_at IS NOT NULL
),
base AS (
  SELECT oi.id AS item_id
  FROM order_items oi JOIN orders o ON o.id = oi.order_id, w
  WHERE o.pay_status = 'paid' AND o.paid_at >= w.hi - interval '30 days'
)
SELECT ft.executor_key, count(DISTINCT b.item_id) AS items, count(*) AS tasks
FROM base b JOIN fulfillment_tasks ft ON ft.order_item_id = b.item_id
GROUP BY 1 ORDER BY 2 DESC;

-- Q2 人工块：店铺集中度 + 金额分位（用于判断监管收益与人工成本量级）
-- 实测：91 只有 8 个店铺，avg ¥126.22 / p50 ¥53 / p90 ¥288；≥¥100 有 13,229 项，≥¥500 有 2,708 项。
WITH w AS (
  SELECT max(paid_at) AS hi FROM orders WHERE pay_status = 'paid' AND paid_at IS NOT NULL
),
base AS (
  SELECT o.provider, o.shop_id, o.shop_name, o.total_amount
  FROM order_items oi JOIN orders o ON o.id = oi.order_id, w
  WHERE o.pay_status = 'paid' AND o.paid_at >= w.hi - interval '30 days'
    AND NOT EXISTS (SELECT 1 FROM fulfillment_tasks ft WHERE ft.order_item_id = oi.id)
    AND NOT EXISTS (SELECT 1 FROM work_orders wo WHERE wo.order_item_id = oi.id)
)
SELECT provider,
       count(DISTINCT shop_id)                                          AS shops,
       count(*)                                                         AS items,
       round(avg(total_amount) / 100.0, 2)                              AS avg_yuan,
       round(percentile_disc(0.5) WITHIN GROUP (ORDER BY total_amount) / 100.0, 2) AS p50_yuan,
       round(percentile_disc(0.9) WITHIN GROUP (ORDER BY total_amount) / 100.0, 2) AS p90_yuan,
       count(*) FILTER (WHERE total_amount >= 10000)                    AS ge_100y,
       count(*) FILTER (WHERE total_amount >= 50000)                    AS ge_500y
FROM base GROUP BY provider ORDER BY items DESC;

-- Q3 人工块是否存在任何“完成信号”
-- 实测：40,519 项全部 order_status='paid' AND pay_status='paid' AND claim_status='active' —— 零完成信号。
WITH w AS (
  SELECT max(paid_at) AS hi FROM orders WHERE pay_status = 'paid' AND paid_at IS NOT NULL
)
SELECT o.order_status, o.pay_status, o.claim_status, count(*) AS items,
       round(sum(o.total_amount) / 100.0) AS yuan
FROM order_items oi JOIN orders o ON o.id = oi.order_id, w
WHERE o.pay_status = 'paid' AND o.paid_at >= w.hi - interval '30 days'
  AND NOT EXISTS (SELECT 1 FROM fulfillment_tasks ft WHERE ft.order_item_id = oi.id)
  AND NOT EXISTS (SELECT 1 FROM work_orders wo WHERE wo.order_item_id = oi.id)
GROUP BY 1, 2, 3 ORDER BY items DESC;

-- Q4 月度趋势：确认人工块不是历史遗留
-- 实测：2026-08 人工 46,337 / 已支付 142,969；2026-09 39,148 / 103,010；2026-10（部分月）17,469 / 55,647。
SELECT to_char(o.paid_at, 'YYYY-MM') AS mon,
       count(*) AS paid_items,
       count(*) FILTER (
         WHERE NOT EXISTS (SELECT 1 FROM fulfillment_tasks ft WHERE ft.order_item_id = oi.id)
           AND NOT EXISTS (SELECT 1 FROM work_orders wo WHERE wo.order_item_id = oi.id)
       ) AS manual_items
FROM order_items oi JOIN orders o ON o.id = oi.order_id
WHERE o.pay_status = 'paid' AND o.paid_at >= '2026-08-01'
GROUP BY 1 ORDER BY 1;

-- Q5 数量口径：quantity 不可用于“卖了多少件”
-- 实测（全量已支付 316,585 项）：quantity=1 的有 316,578 项；quantity>1 仅 7 项；
--   其中 104,710 项的名称里带「N个」；sum(quantity)=316,593，而按名称解析 sum=2,316,222 —— 相差 7.3 倍。
SELECT count(*)                                                              AS items,
       count(*) FILTER (WHERE quantity = 1)                                   AS qty_eq_1,
       count(*) FILTER (WHERE quantity = 1 AND sku_name ~ '[0-9]+[ ]*个')      AS qty1_name_has_num,
       count(*) FILTER (WHERE quantity > 1)                                   AS qty_gt_1,
       sum(quantity)                                                          AS sum_quantity,
       sum(coalesce((regexp_match(sku_name, '([0-9]+)[ ]*个'))[1]::int, quantity)) AS sum_name_quantity
FROM order_items oi JOIN orders o ON o.id = oi.order_id
WHERE o.pay_status = 'paid';

-- Q6 SKU 多码一名：同一商品名对应多个 sku_code（必须先做映射再统计）
-- 实测（全量已支付）：苏尔南钻石100颗 47 个码 / 3,319 项；指挥官密钥1个 42 个码 / 26,748 项；
--                     指挥官密钥5个 41 个码；指挥官密钥10个 37 个码；苏尔南钻石50颗 35 个码。
SELECT sku_name, count(DISTINCT sku_code) AS distinct_sku, count(*) AS items
FROM order_items oi JOIN orders o ON o.id = oi.order_id
WHERE o.pay_status = 'paid'
GROUP BY 1
HAVING count(DISTINCT sku_code) > 5
ORDER BY 2 DESC
LIMIT 20;


-- ============================================================================
-- §2 判定规则（唯一口径，代码与回填必须一致）
-- ----------------------------------------------------------------------------
-- 执行载体 carrier_type ∈ { affiliate_dash, work_order, legacy, manual }
--   ※ 与文档三分类的差异：数据中存在已下线执行器（kuaishou_ct_assisted / kuaishou_feifei /
--     kuaishou-industry）的存量任务，单列 legacy，不并入 affiliate_dash，也不并入 manual。
--     近 30 天 legacy = 262 项。需业务确认其归属（建议只读展示、不计入自动发货口径）。
--
-- 判定优先级（严格顺序，命中即停）：
--   1. 存在 fulfillment_tasks 且 executor_key IN ('affiliate_dash')            -> affiliate_dash
--   2. 存在 fulfillment_tasks 且 executor_key IN ('kuaishou_ct_assisted',
--        'kuaishou_feifei', 'kuaishou-industry')                               -> legacy
--   3. 存在 work_orders（任意状态，含已取消）                                    -> work_order
--   4. 以上都无                                                               -> manual
--   命中 1/2 且 3 同时成立 = 冲突，写入异常队列，不静默取其一（当前实测 0 条）。
--
-- carrier_status ∈ { pending, active, completed, failed, cancelled }
--   终态判定：affiliate_dash 取 task_status IN ('redeemed','closed')；work_order 取 status='accepted'；
--             manual 只能由人工 case 完成时写入（当前无表，见 docs/成本中心与三块履约模型.md §6）。
-- 宽限期：paid_at 之后 N 小时（建议 24h）内允许 carrier_type 为空（判定未跑完）；
--         超过宽限期仍无载体 -> 强制置 manual 并建 case，禁止长期为空。
--
-- 重要：本判定是**派生列**，不是事实来源。事实来源仍是 fulfillment_tasks / work_orders 存在性；
--       派生列只用于报表、监管与成本挂载，必须提供重算作业（见 §4）。
-- ============================================================================


-- ============================================================================
-- §3 回填草案（接入时拆成 100_order_item_carrier.sql；分三步，可回滚）
-- ============================================================================

-- 3.1 加列（ADD COLUMN + 常量 DEFAULT 在 PG11+ 为 metadata-only，不重写 31 万行）
ALTER TABLE order_items
  ADD COLUMN IF NOT EXISTS carrier_type TEXT,
  ADD COLUMN IF NOT EXISTS carrier_status TEXT,
  ADD COLUMN IF NOT EXISTS carrier_decided_at TIMESTAMPTZ,
  ADD COLUMN IF NOT EXISTS carrier_reason TEXT NOT NULL DEFAULT '';

DO $$
BEGIN
  IF NOT EXISTS (SELECT 1 FROM pg_constraint WHERE conname = 'chk_order_items_carrier_type') THEN
    ALTER TABLE order_items
      ADD CONSTRAINT chk_order_items_carrier_type
      CHECK (carrier_type IS NULL OR carrier_type IN ('affiliate_dash', 'work_order', 'legacy', 'manual'));
  END IF;
  IF NOT EXISTS (SELECT 1 FROM pg_constraint WHERE conname = 'chk_order_items_carrier_status') THEN
    ALTER TABLE order_items
      ADD CONSTRAINT chk_order_items_carrier_status
      CHECK (carrier_status IS NULL OR carrier_status IN ('pending', 'active', 'completed', 'failed', 'cancelled'));
  END IF;
END $$;

COMMENT ON COLUMN order_items.carrier_type IS '执行载体(派生): affiliate_dash(自动发货)/work_order(接单工单)/legacy(已下线执行器存量)/manual(人工客服)';
COMMENT ON COLUMN order_items.carrier_status IS '载体状态: pending/active/completed/failed/cancelled';
COMMENT ON COLUMN order_items.carrier_decided_at IS '载体判定时间（重算作业会更新）';
COMMENT ON COLUMN order_items.carrier_reason IS '载体判定原因或人工改派说明';

-- 3.2 回填（只填 NULL，可反复执行；建议按 10 万行分批，避免长事务）
-- 注意：不要在 UPDATE 里直接 JOIN 多张一对多表，统一用 EXISTS，避免行放大。
UPDATE order_items oi
SET carrier_type = CASE
      WHEN EXISTS (SELECT 1 FROM fulfillment_tasks ft
                    WHERE ft.order_item_id = oi.id AND ft.executor_key = 'affiliate_dash')
        THEN 'affiliate_dash'
      WHEN EXISTS (SELECT 1 FROM fulfillment_tasks ft
                    WHERE ft.order_item_id = oi.id
                      AND ft.executor_key IN ('kuaishou_ct_assisted', 'kuaishou_feifei', 'kuaishou-industry'))
        THEN 'legacy'
      WHEN EXISTS (SELECT 1 FROM work_orders wo WHERE wo.order_item_id = oi.id)
        THEN 'work_order'
      ELSE 'manual'
    END,
    carrier_decided_at = now(),
    carrier_reason = 'backfill:2026-10-17'
WHERE oi.carrier_type IS NULL
  AND oi.id IN (
    SELECT oi2.id
    FROM order_items oi2 JOIN orders o ON o.id = oi2.order_id
    WHERE o.pay_status = 'paid' AND o.paid_at < now() - interval '24 hours'
    LIMIT 100000
  );

-- 3.3 索引（CONCURRENTLY 不能放在事务里，需单独执行；生产执行前确认无长事务）
-- CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_order_items_carrier_type
--   ON order_items (carrier_type);
-- CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_fulfillment_tasks_order_item_executor
--   ON fulfillment_tasks (order_item_id, executor_key);
-- CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_work_orders_order_item
--   ON work_orders (order_item_id);

-- 3.4 回滚
-- ALTER TABLE order_items DROP CONSTRAINT IF EXISTS chk_order_items_carrier_type;
-- ALTER TABLE order_items DROP CONSTRAINT IF EXISTS chk_order_items_carrier_status;
-- ALTER TABLE order_items
--   DROP COLUMN IF EXISTS carrier_type,
--   DROP COLUMN IF EXISTS carrier_status,
--   DROP COLUMN IF EXISTS carrier_decided_at,
--   DROP COLUMN IF EXISTS carrier_reason;


-- ============================================================================
-- §4 校验（每次重算后必须跑；差异不为 0 说明派生列与事实不一致）
-- ============================================================================

-- Q7 守恒校验：三类 + legacy 必须等于已支付订单项总数
WITH w AS (
  SELECT max(paid_at) AS hi FROM orders WHERE pay_status = 'paid' AND paid_at IS NOT NULL
),
paid AS (
  SELECT oi.id AS item_id
  FROM order_items oi JOIN orders o ON o.id = oi.order_id, w
  WHERE o.pay_status = 'paid' AND o.paid_at >= w.hi - interval '30 days'
)
SELECT count(*) AS paid_items,
       count(*) FILTER (WHERE oi.carrier_type = 'affiliate_dash') AS auto_items,
       count(*) FILTER (WHERE oi.carrier_type = 'work_order')     AS work_order_items,
       count(*) FILTER (WHERE oi.carrier_type = 'legacy')         AS legacy_items,
       count(*) FILTER (WHERE oi.carrier_type = 'manual')         AS manual_items,
       count(*) FILTER (WHERE oi.carrier_type IS NULL)            AS still_null,
       count(*) FILTER (WHERE oi.carrier_type = 'manual'
                          AND EXISTS (SELECT 1 FROM fulfillment_tasks ft WHERE ft.order_item_id = oi.id)
                       OR oi.carrier_type <> 'manual'
                          AND NOT EXISTS (SELECT 1 FROM fulfillment_tasks ft WHERE ft.order_item_id = oi.id)
                          AND NOT EXISTS (SELECT 1 FROM work_orders wo WHERE wo.order_item_id = oi.id)
       ) AS mismatched
FROM paid p JOIN order_items oi ON oi.id = p.item_id;

-- Q8 冲突与长期无载体（应进异常队列，不进报表）
SELECT oi.id, oi.order_id, oi.carrier_type,
       EXISTS (SELECT 1 FROM fulfillment_tasks ft WHERE ft.order_item_id = oi.id) AS has_task,
       EXISTS (SELECT 1 FROM work_orders wo WHERE wo.order_item_id = oi.id)       AS has_wo
FROM order_items oi
WHERE oi.carrier_type IN ('affiliate_dash', 'legacy')
  AND EXISTS (SELECT 1 FROM work_orders wo WHERE wo.order_item_id = oi.id)
LIMIT 100;


-- ============================================================================
-- §5 人工成本区间（按单成本 × 人工块件数）
-- ----------------------------------------------------------------------------
-- 人工块实测：40,519 项 / 30 天（91 38,451 + PDD 2,066 + 抖音 2），涉及金额 ¥5,214,708。
-- 单均人工成本 X 元时的月度人工成本：
--   X=3  -> ¥121,557      X=5  -> ¥202,595      X=8  -> ¥324,152      X=15 -> ¥607,785
-- 说明：这是“人工履约投入”的量级估算，不含商品/货源成本；商品成本走 cost_versions。
--       建议先按单固定成本落地，同时记录 started_at/completed_at 以备后续按工时核算。
-- ============================================================================