ai-kefu-admin/app/platform/stats.py

"""统计查询纯函数(Phase 2 Task 9,spec §7.6): 五表现有数据聚合——卡片/
漏斗/趋势/分布/推送健康,无新表。

数据形态: 单租户 collect_stats(该租户 session)+ 跨租户 merge_stats(应用层
合并)——**逐库查询、应用层合并,绝不用 SQLite ATTACH**(spec §7.6: ATTACH
默认上限 10 个附加库,租户一多就炸;本模块零 ATTACH 调用)。

指标口径(歧义处已定死,Phase 3 前端照此展示):
- 会话数: conversations 行数,**不要求有消息**——统计口径是"发生的会话",
  与数据视图列表"至少一条消息"(jc 列表语义)不同,两者有意并存。
- 线索数: 该会话的 customer_profiles.raw_info 含 phone/whatsapp/email
  (推送预检的"contact 三选一")任一**非 _ 前缀键**且值非空——wechat 不算
  (推送侧只认三选一);与 contact_pipeline.normalize_contacts 的归一化键
  同名(中英文别名入库前已归一)。
- 高意向数: evaluations.intent_level == "interested" 的会话数。
- 推送成功率: lead_push_logs 的 success/(success+failed);skipped(预检
  不满足必拒)与 pending(未终态)不进分母;分母 0 → None(前端展示"—")。
- 漏斗: 会话 → 留资 → 评估完成(有 evaluations 行)→ 推送成功(该会话有
  过 success 日志;日志自身不另受时间窗约束——会话本体已在窗内)。
- 趋势: 按日分组,**北京日界** date(created_at, '+8 hours')——created_at
  库内为 naive UTC(models 约定),容器部署 TZ=Asia/Shanghai,业务日界以
  北京为准(代码按 naive UTC 存储 + 固定 +8 偏移分组,不依赖进程本地时区,
  测试环境与生产同口径);无数据的日期不产出行(前端补零)。
- 分布: intent 三级 / source / site(client_info 的 site 键,JSON 取键,
  与 data_routes 的 site 筛选同一姿势;无 site 键的会话不计)/ country
  top10(IP 经 ip_service.resolve_country 逐行归国——iptocc 是内存库,
  逐行查 N 会话在几百量级毫秒级可接受,故不在 SQL 里做)。
- 推送健康: 四状态(pending/success/failed/skipped)计数 + duplicated
  (outcome 字段,200 但对方判重——不是错误)计数。

时间筛选: from_dt/to_dt 为 naive UTC 边界(由 stats_routes 经 data_routes
 的 _parse_dt 解析,日期-only 的 to 含当日全天,边界含)。会话锚定的指标滤
conversations.created_at;推送锚定的指标(成功率/推送健康)滤
lead_push_logs.created_at——两套锚点各自与本体表同窗。
"""
from collections import Counter, defaultdict

from sqlalchemy import ColumnElement, and_, func, or_, select

from app.engine.models import (
    Conversation,
    CustomerProfile,
    Evaluation,
    IntentLevel,
    LeadPushLog,
)
from app.engine.services.ip_service import resolve_country

# 线索判定的联系方式键(三选一;wechat 不算——与推送预检同口径)
CONTACT_KEYS = ("phone", "whatsapp", "email")
INTENT_KEYS = ("interested", "not_interested", "pending")
PUSH_STATUS_KEYS = ("pending", "success", "failed", "skipped")
COUNTRY_TOP_N = 10
# 北京日界偏移(SQLite date() 修饰符): 见模块 docstring"趋势"条
_TZ_BEIJING = "+8 hours"


def _empty_stats() -> dict:
    """零数据形态(无租户可查/空库)——与 collect_stats 输出同构。"""
    return {
        "cards": {
            "conversations": 0, "leads": 0, "high_intent": 0,
            "push_success_rate": None},
        "funnel": {
            "conversations": 0, "leads": 0, "evaluated": 0,
            "push_succeeded": 0},
        "trend": [],
        "distributions": {
            "intent": {k: 0 for k in INTENT_KEYS},
            "source": {},
            "site": {},
            "country": []},
        "push_health": {
            "pending": 0, "success": 0, "failed": 0, "skipped": 0,
            "duplicated": 0},
    }


def _contact_any() -> ColumnElement:
    """SQL 布尔: raw_info 三选一键任一非空(NULL/空白串都不算)。"""
    conds = []
    for key in CONTACT_KEYS:
        value = CustomerProfile.raw_info[key].as_string()
        conds.append(and_(value.is_not(None), func.trim(value) != ""))
    return or_(*conds)


def _range(column, from_dt, to_dt) -> list:
    """闭区间条件列表(边界含;None 边界不加条件)。"""
    conds = []
    if from_dt is not None:
        conds.append(column >= from_dt)
    if to_dt is not None:
        conds.append(column <= to_dt)
    return conds


def _push_rate(health: dict) -> float | None:
    """success/(success+failed);分母 0 → None。"""
    done = health["success"] + health["failed"]
    return health["success"] / done if done else None


def _sorted_counts(counter: dict) -> dict:
    """分布字典定序: 计数倒序、同数按 key 升序(JSON 对象保序,前端展示稳)。"""
    return dict(sorted(counter.items(), key=lambda kv: (-kv[1], kv[0])))


async def collect_stats(
        session, *, from_dt=None, to_dt=None) -> dict:
    """单租户统计: 在该租户库的 session 上跑全部聚合,输出指标 dict。

    只读不写;所有计数走 SQL 聚合(例外: country 逐行 IP 归国,见模块
    docstring)。"""
    conv_range = _range(Conversation.created_at, from_dt, to_dt)
    log_range = _range(LeadPushLog.created_at, from_dt, to_dt)

    # ---- 卡片 + 漏斗(会话锚定) ------------------------------------------------
    conversations = (await session.execute(
        select(func.count()).select_from(Conversation).where(*conv_range)
    )).scalar() or 0
    leads = (await session.execute(
        select(func.count())
        .select_from(Conversation)
        .join(CustomerProfile,
              CustomerProfile.conversation_id == Conversation.id)
        .where(*conv_range, _contact_any())
    )).scalar() or 0
    high_intent = (await session.execute(
        select(func.count())
        .select_from(Conversation)
        .join(Evaluation, Evaluation.conversation_id == Conversation.id)
        .where(*conv_range,
               Evaluation.intent_level == IntentLevel.interested)
    )).scalar() or 0
    evaluated = (await session.execute(
        select(func.count())
        .select_from(Conversation)
        .join(Evaluation, Evaluation.conversation_id == Conversation.id)
        .where(*conv_range)
    )).scalar() or 0
    push_succeeded = (await session.execute(
        select(func.count()).select_from(Conversation).where(
            *conv_range,
            Conversation.id.in_(
                select(LeadPushLog.conversation_id)
                .where(LeadPushLog.status == "success")))
    )).scalar() or 0

    # ---- 推送健康(日志锚定) --------------------------------------------------
    health = {k: 0 for k in PUSH_STATUS_KEYS}
    for status, count in (await session.execute(
            select(LeadPushLog.status, func.count())
            .where(*log_range).group_by(LeadPushLog.status))).all():
        if status in health:        # 未知状态不计(防御 imported/手改数据)
            health[status] = count
    health["duplicated"] = (await session.execute(
        select(func.count()).select_from(LeadPushLog).where(
            *log_range, LeadPushLog.outcome == "duplicated")
    )).scalar() or 0

    # ---- 趋势(北京日界) ------------------------------------------------------
    day = func.date(Conversation.created_at, _TZ_BEIJING)
    conv_per_day = dict((await session.execute(
        select(day, func.count()).where(*conv_range).group_by(day)
    )).all())
    lead_stmt = (
        select(day, func.count())
        .select_from(Conversation)
        .join(CustomerProfile,
              CustomerProfile.conversation_id == Conversation.id)
        .where(*conv_range, _contact_any())
        .group_by(day))
    lead_per_day = dict((await session.execute(lead_stmt)).all())
    trend = [
        {"date": d, "conversations": conv_per_day[d],
         "leads": lead_per_day.get(d, 0)}
        for d in sorted(set(conv_per_day) | set(lead_per_day))
    ]

    # ---- 分布 -----------------------------------------------------------------
    intent = {k: 0 for k in INTENT_KEYS}
    for level, count in (await session.execute(
            select(Evaluation.intent_level, func.count())
            .join(Conversation, Conversation.id == Evaluation.conversation_id)
            .where(*conv_range).group_by(Evaluation.intent_level))).all():
        intent[level.value if hasattr(level, "value") else str(level)] = count

    source = Counter()
    for src, count in (await session.execute(
            select(Conversation.source, func.count())
            .where(*conv_range).group_by(Conversation.source))).all():
        source[src.value if hasattr(src, "value") else str(src)] = count

    site_expr = Conversation.client_info["site"].as_string()
    site = Counter()
    for site_slug, count in (await session.execute(
            select(site_expr, func.count())
            .where(*conv_range, site_expr.is_not(None)).group_by(site_expr)
    )).all():
        site[site_slug] = count

    # country: 逐行 IP 归国(iptocc 内存库,几百会话毫秒级——见模块 docstring)
    country = Counter()
    for (ip,) in (await session.execute(
            select(Conversation.client_info["ip"].as_string())
            .where(*conv_range))).all():
        country[resolve_country(ip or "")] += 1

    return {
        "cards": {
            "conversations": conversations,
            "leads": leads,
            "high_intent": high_intent,
            "push_success_rate": _push_rate(health)},
        "funnel": {
            "conversations": conversations,
            "leads": leads,
            "evaluated": evaluated,
            "push_succeeded": push_succeeded},
        "trend": trend,
        "distributions": {
            "intent": intent,
            "source": _sorted_counts(source),
            "site": _sorted_counts(site),
            "country": [
                {"country": name, "count": count}
                for name, count in country.most_common(COUNTRY_TOP_N)]},
        "push_health": health,
    }


def merge_stats(parts: list[dict]) -> dict:
    """跨租户应用层合并(逐库结果求和;比率/排序合并后重算重排)。

    parts 为空 → 零数据形态。合并语义: 标量求和;趋势按日期键合并;
    intent/source/site 按 key 求和;country 计数合并后重取 top N。"""
    if not parts:
        return _empty_stats()
    out = _empty_stats()

    trend = defaultdict(lambda: {"conversations": 0, "leads": 0})
    intent = {k: 0 for k in INTENT_KEYS}
    source: Counter = Counter()
    site: Counter = Counter()
    country: Counter = Counter()

    for part in parts:
        for key in ("conversations", "leads", "high_intent"):
            out["cards"][key] += part["cards"][key]
        for key in ("conversations", "leads", "evaluated", "push_succeeded"):
            out["funnel"][key] += part["funnel"][key]
        for row in part["trend"]:
            trend[row["date"]]["conversations"] += row["conversations"]
            trend[row["date"]]["leads"] += row["leads"]
        for key, count in part["distributions"]["intent"].items():
            intent[key] = intent.get(key, 0) + count
        source.update(part["distributions"]["source"])
        site.update(part["distributions"]["site"])
        for item in part["distributions"]["country"]:
            country[item["country"]] += item["count"]
        for key in out["push_health"]:
            out["push_health"][key] += part["push_health"][key]

    out["cards"]["push_success_rate"] = _push_rate(out["push_health"])
    out["trend"] = [
        {"date": d, **counts} for d, counts in sorted(trend.items())]
    out["distributions"] = {
        "intent": intent,
        "source": _sorted_counts(source),
        "site": _sorted_counts(site),
        "country": [
            {"country": name, "count": count}
            for name, count in country.most_common(COUNTRY_TOP_N)]}
    return out