# ============================================================
# M3 知识与偏好黄金测试（moduleId: golden-m3, 发版门禁 §14.3）
# 固化不变式：
#   K1 检索必带出处（assetId/title/version）且未命中返回空（诚实原则 §8.1）
#   K2 报告数字全部可溯源到快照字段（§9.10 硬规则 1）
#   K3 偏好个性化：采用权重 > 试排权重；无信号回退默认（§8.3）
#   K4 知识资产同名重复入库版本递增（§8.1 版本化）
# ============================================================
from __future__ import annotations                    # 前向类型引用

import re                                              # 报告数字抽取

from server.knowledge.assets import KnowledgeStore     # 资产库（临时路径实例化）
from server.knowledge.preferences import PreferenceStore  # 偏好仓
from server.knowledge.retrieval import search          # 混合检索
from server.aps_domain.reports import build_daily_report, build_version_diff_report  # 报告
from server.state.seed import seed_world               # 种子世界
from server.engines import get_engine                  # 引擎（造版本用）
from server.engines.base import EngineParams           # 引擎入参
from server.timeutil import add_minutes, fmt_date, today0  # 日期工具


def _make_version(world, strategy="DELIVERY_FIRST"):
    """在世界里真实跑一版排产（报告测试的前置数据）。"""
    counters = {}                                      # 独立发号器
    def next_id(kind):
        counters[kind] = counters.get(kind, 0) + 1
        return counters[kind] + 1000
    params = EngineParams(orderIds=[], engineType="RULE", strategyTemplate=strategy,
                          planningHorizonDays=14, startDate=fmt_date(add_minutes(today0(), 24 * 60)))
    return get_engine("RULE").solve(world, params, next_id)


# ---------------- K1：检索带出处 + 诚实未命中 ----------------
def test_search_returns_provenance(tmp_path):
    """命中必带 assetId/title/version；无关问题返回空列表（不编造）。"""
    kb = KnowledgeStore(path=str(tmp_path / "kn.json"))  # 临时库（自动播种）
    hits = search(kb.assets, "换线有什么规定")           # SOP 问题
    assert hits, "种子 SOP 应能命中"                    # 有命中
    top = hits[0]                                      # 最相关
    assert top["title"] == "换线标准SOP"                # 命中正确资产
    for key in ("assetId", "title", "version", "snippet"):  # 出处字段齐全
        assert top[key], f"命中缺出处字段 {key}"
    miss = search(kb.assets, "quantum blockchain xyzzy")  # 无关问题（无重叠词）
    assert miss == [], "无关问题必须诚实返回空"          # 未命中为空


# ---------------- K2：报告数字可溯源 ----------------
def test_daily_report_numbers_from_snapshot():
    """日报正文中的核心数字必须与冻结快照字段一致。"""
    world = seed_world()                               # 种子世界
    _make_version(world)                               # 真实排一版
    report = build_daily_report(world)                 # 生成日报
    snap = report["snapshot"]                          # 冻结快照
    assert snap is not None                            # 有快照
    md = report["markdown"]                            # 报告正文
    assert f"**{snap['poCount']}** 个" in md            # 订单数可溯源
    assert f"**{snap['woCount']}** 个" in md            # 工单数可溯源
    assert f"**{snap['conflictCount']}** 项" in md      # 冲突数可溯源
    assert snap["versionNo"] in md                     # 版本号出现在出处行


def test_version_diff_report_needs_two_versions():
    """不足两版时诚实拒绝；两版后 KPI 表出现新旧版本号。"""
    world = seed_world()                               # 种子世界
    r0 = build_version_diff_report(world)              # 无版本
    assert r0["reportId"] is None                      # 拒绝生成
    _make_version(world, "DELIVERY_FIRST")             # 第一版
    _make_version(world, "CAPACITY_BALANCE")           # 第二版
    r = build_version_diff_report(world)               # 生成对比
    assert r["reportId"]                               # 成功
    assert r["snapshot"]["new"]["versionNo"] in r["markdown"]   # 新版号在正文
    assert r["snapshot"]["old"]["versionNo"] in r["markdown"]   # 旧版号在正文


# ---------------- K3：偏好个性化 ----------------
def test_preference_weighting(tmp_path):
    """采用（2分）> 试排（1分）；无信号回退系统默认。"""
    ps = PreferenceStore(path=str(tmp_path / "pref.json"))  # 临时仓
    default, scores = ps.preferred_strategy()          # 无样本
    assert default == "COMPREHENSIVE" and scores == {}  # 回退默认
    ps.record("DELIVERY_FIRST", source="schedule.run")   # 试排交期 ×2 = 2分
    ps.record("DELIVERY_FIRST", source="schedule.run")
    ps.record("CAPACITY_BALANCE", source="scenario.apply")  # 采用均衡 ×1 = 2分…
    ps.record("CAPACITY_BALANCE", source="scenario.apply")  # ×2 = 4分（采用权重更高）
    best, scores = ps.preferred_strategy()             # 求偏好
    assert best == "CAPACITY_BALANCE", f"采用权重应更高，got {scores}"  # 采用胜出
    assert scores["DELIVERY_FIRST"] == 2 and scores["CAPACITY_BALANCE"] == 4  # 得分可解释


# ---------------- K4：资产版本化 ----------------
def test_asset_versioning(tmp_path):
    """同名资产重复入库版本号递增（v1 → v2）。"""
    kb = KnowledgeStore(path=str(tmp_path / "kn.json"))  # 临时库
    a1 = kb.add("sop", "测试SOP", "第一版内容")          # 首次入库
    assert a1["version"] == "v1"                       # v1
    a2 = kb.add("sop", "测试SOP", "第二版内容")          # 同名再入
    assert a2["version"] == "v2"                       # 版本递增
    assert kb.find_by_title("测试SOP") is not None      # 标题可检索


def test_hybrid_search_units_with_chunks(tmp_path):
    """带 chunks 的资产按单元检索，仍强制出处。"""
    kb = KnowledgeStore(path=str(tmp_path / "kn.json"))
    kb.assets = []
    kb._write()
    kb.add_with_chunks(
        kind="sop", title="夜班换线禁令", content="摘要",
        chunks=[{"chunkId": "c0", "text": "每日十六点后禁止跨产品族换线作业。", "seq": 0}],
        tags=["换线", "夜班"], approved=True,
    )
    hits = search(kb.assets, "夜班换线")
    # search() 走整篇；再用 hybrid on units
    from server.knowledge.retrieval import hybrid_search
    units = kb.iter_search_units()
    hits2 = hybrid_search(units, "禁止跨产品族换线", top_k=2)
    assert hits2
    for key in ("assetId", "title", "version", "snippet"):
        assert hits2[0][key]
    assert hits2[0].get("chunkId") == "c0"