AgentLab/backend/tests/bundle_samples.py

"""可验证报告的虚构样本页：给 scripts/check-bundle.mjs 在浏览器里核对（pytest 不执行页面上的核对脚本）。

    python -m tests.bundle_samples <目录>

在目录里写下几份页面（<名字>.html）。每份都是 build_bundle + render_html 真实生成的，封存哈希按 runner 的算法
（artifact_store.manifest_hash）对事件真实算出，报告文档用 compose_doc 按证据目录真实组装（标题、段落、列表、
表格、粗体、斜体，数字和取值的引用都和真实运行一样）。check-bundle 断网打开它们，逐项断言核对结果和原因，再在
这几份上做篡改。这样遮罩快照、多份报告、早期运行、服务端缺文件这些分支，不论真数据里有没有，都有人在浏览器里核过。

数据全是虚构的：门店、会员、金额都是编的。

- base：一份报告，引用口径卡、门店流水（没有遮罩）、会员消费（有遮罩）各一处，一个没有出处的数，一张门店流水整表
  （数字列右对齐，数字与取值共 21 个，超过折叠的条数）；一条封存之后追加的按需裁判
- two-reports：另有一份月报，两份报告各自的引用链
- legacy：早期运行，封存范围按结束事件推算（运行结束事件在范围外，运行结果无法核对）
- failed：失败结束的运行（没有出具判定），封存说明多一句「继续运行会重新封存」
- continued：早期运行先失败、经继续运行跑到成功：范围里有那条运行失败，之后运行又继续了，成功结束的那条在范围外
- degraded：两条出具判定，先完整出具、后降档出具，认最后一条
- missing-doc / missing-card：导出时服务端已没有报告文档 / 口径卡的文件
- masked-card：口径卡上两个指标的输入取自会员消费的号码列（设了遮罩）：联系电话位数、首位会员手机号（值就是号码），卡上
  记着号码原值。整张卡只给 id，引用它的数字无法核对；卡的节点完成事件（预览里逐条写着「指标（名称）= 值」）只给哈希；
  报告文档按现在的报告撰写节点写，证据目录里这两个指标写「已遮罩」，照常随文件附带
- masked-old-doc：同一张卡，报告文档是之前的报告撰写节点写的，证据目录里这两个指标写着原值：整份文档只给哈希、不附带它
  引用的工件，报告的节点完成事件也只给哈希，页面照实说明原因
- masked-source：会员库设了号码遮罩（查询当时记下了，数据源现在也设着）。报告引用会员按地区汇总的查询（没碰遮罩列：
  快照随文件附带，数字核对得过）和选出了号码的那份会员消费（只给哈希）
- nan：运行开始事件和门店流水快照里有 json.dumps 写出的裸 NaN（快照里那一列报告没有引用）
- stray：报告自查记下的文档是另一次运行写的
- formats：经营月报，每种显示格式各引用一处：口径卡的千分位加货币单位、换算成万 / 亿、比率显示成百分数、负数、不分组、
  小数位与 |.N / |int、pct；流水快照里的文字取值（地区）、DECIMAL 落成的数字文本、负数、换算成万、超过 2^53 的订单号、
  ISO 日期时间（文档记下 2 版显示规则）。check-bundle 在它上面只改显示文字做伪造，tests/test_bundle_shown.py 在 node 里
  逐个格式核一遍
- formats-unit：同经营月报，销售额的单位带尾随空白（「元 」：单位输入框不去空白，指标节点照存），正文显示「74,613.65元 」，
  原样导出照样全部通过
"""
from __future__ import annotations

import json
import sys
from pathlib import Path
from typing import Any

from app.bundle.build import build_bundle, render_html
from app.core.artifact_store import canonical_json, content_hash, manifest_hash
from app.engine.evidence import build_catalog, compose_doc, withhold_metrics

RUN_ID = "5a3c0f4b9d2e4e1f8b7a6c5d4e3f2a1b"
RUN = {"id": RUN_ID, "workflow_id": "wf-sample-weekly", "workflow_name": "门店周报", "version": 3,
       "version_hash": "ab" * 32, "run_class": "formal", "status": "succeeded",
       "started_at": "2026-09-07T01:00:00+00:00", "finished_at": "2026-09-07T01:02:03+00:00"}
GRAPH = {"nodes": [{"id": n, "type": t, "data": {"label": label}} for n, t, label in [
    ("start", "input", "开始"), ("fetch", "tool", "门店流水"), ("members", "tool", "会员消费"),
    ("regions", "tool", "会员地区汇总"), ("card", "metrics", "周报口径"), ("write", "report", "写周报"),
    ("monthly", "report", "写月报"), ("out", "output", "成果")]]}
EXPORTED_AT = "2026-10-05T08:00:00+00:00"

STORES = [["青石店", 1280.5], ["白沙店", "960.00"], ["临川店", 732], ["望江店", 1105.25], ["枫桥店", 418],
          ["云岭店", 2210], ["石桥店", 655.5], ["柳湾店", 980]]
CRM = {"columns": ["name", "phone", "spend"], "column_types": {"name": "text", "phone": "text", "spend": "number"},
       "rows": [["林一", "000-0001", 320.0], ["周二", "000-0002", 188.5]], "source": "crm",
       "sql": "SELECT name, phone, spend FROM members ORDER BY id", "truncated": False, "mask_columns": ["phone"]}
#: 会员按地区汇总：同一个设了号码遮罩的会员库，SQL 没碰号码列
REGIONS = {"columns": ["region", "spend"], "column_types": {"region": "text", "spend": "number"},
           "rows": [["华东", 320.0], ["华南", 188.5]], "source": "crm",
           "sql": "SELECT region, SUM(spend) AS spend FROM members GROUP BY region ORDER BY region", "truncated": False,
           "mask_columns": ["phone"]}
CARD = {"kind": "metric_set", "caliber": "周报口径", "caliber_version": "v2",
        "metrics": [{"id": "gmv", "name": "销售额", "value": 8381.25, "unit": "元", "decimals": 2, "format": "thousands"}]}

WEEKLY = ("## 门店周报\n\n本周销售额 [[m:gmv]]，*按发生周统计*。青石店流水 [[v:Q1.r0.amount]]，白沙店 [[v:Q1.r1.amount]]，"
          "**会员消费** [[v:Q2.r0.spend]]，另有 42 笔退款待入账。[[see:Q1]]\n\n- 云岭店流水最高\n- 枫桥店流水最低\n\n"
          "[[table:Q1 cols=store,amount rows=0-7]]")
MONTHLY = "## 门店月报\n\n本月销售额 [[m:gmv]]，青石店流水 [[v:Q1.r0.amount]]。[[see:Q1]]"

#: 经营月报的口径卡：每个指标一种显示格式（千分位加货币单位、不分组、比率显示成百分数、负数、小数位、不写小数位）
FORMATS_CARD = {"kind": "metric_set", "caliber": "经营月报口径", "caliber_version": "v1", "metrics": [
    {"id": "gmv", "name": "销售额", "value": 74613.65, "unit": "元", "decimals": 2, "format": "thousands"},
    {"id": "annual", "name": "年度销售额", "value": 1234567890.5, "unit": "元", "decimals": 2, "format": "thousands"},
    {"id": "refund", "name": "退款", "value": -3120.5, "unit": "元", "decimals": 2, "format": "thousands"},
    {"id": "conv_rate", "name": "转化率", "value": 0.0235, "unit": "", "decimals": 4, "format": "percent_of_ratio"},
    {"id": "growth", "name": "环比", "value": -0.0815, "unit": "", "decimals": 3, "format": "percent_of_ratio"},
    {"id": "orders", "name": "订单数", "value": 12840, "unit": "单", "decimals": 0, "format": "plain"},
    {"id": "avg", "name": "客单价", "value": 5.8113, "unit": "元", "decimals": 2, "format": "thousands"},
    {"id": "share", "name": "线上占比", "value": 0.346, "unit": "", "decimals": None, "format": "thousands"},
    {"id": "export", "name": "出口额", "value": 15230.4, "unit": "美元", "decimals": 1, "format": "thousands"},
]}
#: 同上，销售额的单位带尾随空白：服务端照原样接在数后面
FORMATS_UNIT_CARD = {**FORMATS_CARD, "metrics": [{**FORMATS_CARD["metrics"][0], "unit": "元 "},
                                                 *FORMATS_CARD["metrics"][1:]]}
#: 经营流水：地区是文字，金额一格是 DECIMAL 落成的数字文本、一格是负数，订单号超过 2^53，付款时间是 ISO 日期时间
LEDGER = {"columns": ["region", "gmv", "order_no", "paid_at"],
          "column_types": {"region": "text", "gmv": "number", "order_no": "number", "paid_at": "datetime"},
          "rows": [["华南", "45678.50", 202609071234567890, "2026-09-07T08:21:39"],
                   ["华东", -1200.75, 202609071234567891, "2026-09-08T19:02:11"]],
          "source": "shop", "sql": "SELECT region, gmv, order_no, paid_at FROM ledger ORDER BY region DESC",
          "truncated": False}
FORMATS = ("## 经营月报\n\n本月销售额 [[m:gmv]]（约 [[m:gmv|万]]），年度累计 [[m:annual|亿]]，退款 [[m:refund]]。"
           "转化率 [[m:conv_rate]]，环比 [[m:growth]]，订单 [[m:orders]]。客单价 [[m:avg]]，精确些是 [[m:avg|.3]]，"
           "取整是 [[m:avg|int]]；线上占比 [[m:share|pct]]，出口额 [[m:export]]。\n\n"
           "[[v:Q1.r0.region]]流水 [[v:Q1.r0.gmv]]（约 [[v:Q1.r0.gmv|万]]），[[v:Q1.r1.region]]冲减 [[v:Q1.r1.gmv]]。"
           "最大一单的订单号 [[v:Q1.r0.order_no]]，付款时间 [[v:Q1.r0.paid_at]]。[[see:Q1]]")
#: 会员周报：Q3 是会员按地区汇总（没碰遮罩列），Q2 是选出了号码的会员消费
MEMBERS = ("## 会员周报\n\n华东会员消费 [[v:Q3.r0.spend]]，华南 [[v:Q3.r1.spend]]。[[see:Q3]]\n\n"
           "会员林一消费 [[v:Q2.r0.spend]]。")


def stored(obj: Any) -> tuple[str, bytes]:
    """照工件库的样子落一份：规范 JSON 的字节，id 是它的 sha256。"""
    raw = canonical_json(obj).encode()
    return content_hash(raw), raw


def shop(nan: bool = False) -> dict[str, Any]:
    """门店流水的查询快照。ratio 那一列报告不引用；nan=True 时第一行是浮点 NaN（json.dumps 写成裸的 NaN）。"""
    rows = [[name, amount, float("nan") if nan and i == 0 else round(0.05 * (i + 1), 2)]
            for i, (name, amount) in enumerate(STORES)]
    return {"columns": ["store", "amount", "ratio"],
            "column_types": {"store": "text", "amount": "number", "ratio": "number"}, "rows": rows, "source": "shop",
            "sql": "SELECT store, amount, ratio FROM orders ORDER BY id", "truncated": False}


#: 报告撰写节点把值取自遮罩格的指标写成的字（同 api/evidence.py 的 MASKED）
MASKED = "已遮罩"


def masked_card(crm_id: str) -> dict[str, Any]:
    """口径卡多两个指标：联系电话位数、首位会员手机号，输入都是会员消费第 0 行的号码（phone 设了遮罩），卡上记着号码原值
    和代入式；首位会员手机号的值就是号码。"""
    cell, phone = "cell(nodes.members, 0, 'phone')", CRM["rows"][0][1]
    read = {"path": cell, "value": phone, "node_id": "members", "via": "tool_cell", "artifact": crm_id,
            "locator": {"row": 0, "column": "phone"}, "status": "verified"}
    contact = {"id": "contact", "name": "联系电话位数", "value": 8, "unit": "位", "decimals": 0, "format": "thousands",
               "expression": f"len({cell})", "substituted": f"len('{phone}')", "inputs": [dict(read)]}
    first = {"id": "phone_raw", "name": "首位会员手机号", "value": phone, "unit": "", "decimals": None, "format": "plain",
             "expression": cell, "substituted": f"'{phone}'", "inputs": [dict(read)]}
    return {**CARD, "metrics": [*CARD["metrics"], contact, first]}


#: masked_card 上值不给的指标（和证据面板指标步骤的值同一个判断：输入取自遮罩格）
MASKED_METRICS = ("m:contact", "m:phone_raw")


def card_preview(card: dict[str, Any], artifact: str) -> dict[str, Any]:
    """口径卡节点完成事件的预览，照 metrics 节点产出的样子（compiler._preview）：text 里逐条写着「指标（名称）= 值」。"""
    lines = [f"- {m['id']}（{m['name']}）= {m['value']}{m.get('unit') or ''}" for m in card["metrics"]]
    return {"kind": "metric_set", "caliber": card["caliber"], "caliber_version": card["caliber_version"],
            "metrics": f"[{len(card['metrics'])} 项]",
            "text": f"指标清单（口径 {card['caliber']} @ {card['caliber_version']}）：\n" + "\n".join(lines),
            "artifact": artifact}


class Sample:
    """一次虚构的已封存运行：工件（原字节）、证据目录、报告文档、事件。masked=True 时口径卡带着取自遮罩列的输入；
    regions=True 时会员库另有一次按地区汇总的查询（目录里排在 Q3）。card、table 换掉口径卡和门店流水的快照（经营月报）；
    inputs 是运行输入（报告里写 [[i:字段]] 引用）。"""

    def __init__(self, *, nan: bool = False, masked: bool = False, regions: bool = False,
                 card: dict[str, Any] | None = None, table: dict[str, Any] | None = None,
                 inputs: dict[str, Any] | None = None) -> None:
        self.files: dict[str, bytes] = {}
        snapshot = table or shop(nan)
        self.shop_id = self.put(snapshot)
        self.crm_id = self.put(CRM)
        self.card = card or (masked_card(self.crm_id) if masked else CARD)
        self.card_id = self.put(self.card)
        self.entries = {
            "fetch": {"kind": "query", "node_id": "fetch", "exec": 1, "artifact": self.shop_id,
                      "tool": "db_query__shop", "source": "shop", "columns": snapshot["columns"],
                      "rows": len(snapshot["rows"]), "truncated": False},
            "members": {"kind": "query", "node_id": "members", "exec": 1, "artifact": self.crm_id,
                        "tool": "db_query__crm", "source": "crm", "columns": CRM["columns"], "rows": len(CRM["rows"]),
                        "truncated": False},
        }
        if regions:
            self.entries["regions"] = {"kind": "query", "node_id": "regions", "exec": 1,
                                       "artifact": self.put(REGIONS), "tool": "db_query__crm", "source": "crm",
                                       "columns": REGIONS["columns"], "rows": len(REGIONS["rows"]), "truncated": False}
        self.entries["card"] = {"kind": "metric_set", "node_id": "card", "artifact": self.card_id}
        self.ledger = list(self.entries.values())
        self.catalog = build_catalog(nodes={"card": self.card}, ledger=self.ledger, inputs=inputs)

    def put(self, obj: Any) -> str:
        artifact, raw = stored(obj)
        self.files[artifact] = raw
        return artifact

    def load(self, artifact: str) -> Any:
        raw = self.files.get(artifact)
        return json.loads(raw) if raw is not None else None

    def doc(self, text: str, node_id: str, run_id: str = RUN_ID, *, masked: tuple[str, ...] = ()) -> str:
        """组装一份报告文档。masked：值不给的指标，照现在的报告撰写节点写成「已遮罩」（withhold_metrics）；不给的是之前的
        报告撰写节点写的样子（目录里原样写着值）。"""
        catalog = withhold_metrics(self.catalog, masked, MASKED)
        return self.put(compose_doc(text, catalog, node_id=node_id, run_id=run_id, loader=self.load))

    def events(self, reports: dict[str, str], *, ending: str = "finished", tiers: tuple[str, ...] = ("formal",),
               nan: bool = False) -> tuple[list[tuple[int, str, str | None, Any]], int]:
        """(全部事件, 封存范围)。封存范围到结束事件为止，后面再追加一条按需裁判。"""
        rows: list[tuple[int, str, str | None, Any]] = []

        def add(etype: str, node_id: str | None, data: dict[str, Any]) -> None:
            rows.append((len(rows) + 1, etype, node_id, data))

        add("run.started", None, {"nodes": len(GRAPH["nodes"]), "resumed": False, "memory_scope": "default",
                                  "collection": "default", "approval_default": None, "tool_trust": "formal",
                                  "agent_limits": None, "data_versions": None, "replay_protocol": 2,
                                  **({"sample_rate": float("nan")} if nan else {})})
        add("node.started", "start", {"node_type": "input", "label": "开始"})
        add("node.finished", "start", {"duration_ms": 1, "attempt": 1, "preview": {"week": "2026-W37"}})
        add("node.started", "fetch", {"node_type": "tool", "label": "门店流水"})
        add("tool.end", "fetch", {"tool": "db_query__shop", "duration_ms": 12, "query_artifact": self.shop_id,
                                  "preview": json.dumps({"columns": ["store", "amount"], "rows": STORES[:2]},
                                                        ensure_ascii=False)})
        add("node.finished", "fetch", {"duration_ms": 14, "attempt": 1, "preview": "{\"rows\": …}",
                                       "evidence": [self.entries["fetch"]]})
        add("tool.end", "members", {"tool": "db_query__crm", "duration_ms": 9, "query_artifact": self.crm_id,
                                    "preview": json.dumps(CRM["rows"][:1], ensure_ascii=False)})
        add("node.finished", "members", {"duration_ms": 10, "attempt": 1, "evidence": [self.entries["members"]]})
        if "regions" in self.entries:
            add("tool.end", "regions", {"tool": "db_query__crm", "duration_ms": 7,
                                        "query_artifact": self.entries["regions"]["artifact"],
                                        "preview": json.dumps(REGIONS["rows"], ensure_ascii=False)})
            add("node.finished", "regions", {"duration_ms": 8, "attempt": 1, "evidence": [self.entries["regions"]]})
        add("node.finished", "card", {"duration_ms": 3, "attempt": 1, "preview": card_preview(self.card, self.card_id),
                                      "evidence": [self.entries["card"]]})
        for node_id, doc_id in reports.items():
            add("llm.end", node_id, {"model": "mock", "output": "（写作草稿）"})
            add("report.checked", node_id, {"doc_artifact": doc_id, "ok": True})
            add("node.finished", node_id, {"duration_ms": 20, "attempt": 1,
                                           "preview": {"text": "（报告正文）", "doc_artifact": doc_id}})
        if ending == "finished":
            for tier in tiers:
                add("issuance", "out", {"tier": tier, "mode": "citations"})
            add("node.finished", "out", {"duration_ms": 2, "attempt": 1, "preview": {"周报": "（报告正文）"}})
            add("run.finished", None, {"output": {"周报": "（报告正文）"}})
        elif ending == "continued":
            # 先失败，再从成果节点继续运行到成功（runner.continue_failed 记一条 run.resumed）
            add("node.failed", "out", {"error": "出口复核没有通过"})
            add("run.failed", None, {"error": "出口复核没有通过"})
            add("run.resumed", None, {"from": ["out"], "message": "从「成果」继续运行，保留前面 6 个节点的结果",
                                      "actor": "值班分析员"})
            for tier in tiers:
                add("issuance", "out", {"tier": tier, "mode": "citations"})
            add("node.finished", "out", {"duration_ms": 2, "attempt": 1, "preview": {"周报": "（报告正文）"}})
            add("run.finished", None, {"output": {"周报": "（报告正文）"}})
        else:
            add("node.failed", "out", {"error": "出口复核没有通过"})
            add("run.failed", None, {"error": "出口复核没有通过"})
        bound = len(rows)
        add("evidence.judged", next(iter(reports), None),
            {"verdicts": {"u1": {"verdict": "supported"}}, "model": "judge-x", "post_seal": True})
        return rows, bound


def build(sample: Sample, events: list[tuple[int, str, str | None, Any]], bound: int, *,
          run: dict[str, Any] | None = None, legacy: bool = False, drop: tuple[str, ...] = (),
          source_masks: dict[str, list[str]] | None = None) -> dict[str, Any]:
    """真实封存哈希的页面数据（bundle-data）。drop：导出时服务端已没有文件的工件；source_masks：数据源现在设的遮罩。"""
    sealed = [e for e in events if e[0] <= bound]
    files = {k: v for k, v in sample.files.items() if k not in drop}
    return build_bundle(run or RUN, events, manifest_seq=bound, manifest_hash=manifest_hash(sealed), read=files.get,
                        exported_at=EXPORTED_AT, legacy=legacy, graph=GRAPH, source_masks=source_masks or {})


def formats_bundle(*, card: dict[str, Any] = FORMATS_CARD, table: dict[str, Any] = LEDGER, text: str = FORMATS,
                   inputs: dict[str, Any] | None = None) -> dict[str, Any]:
    """经营月报（formats）的页面数据：每种显示格式各引用一处。tests/test_bundle_shown.py 换掉口径卡、流水、正文或者
    加上运行输入，组装别的写法。"""
    f = Sample(card=card, table=table, inputs=inputs)
    events, bound = f.events({"write": f.doc(text, "write")})
    return build(f, events, bound)


def bundles() -> dict[str, dict[str, Any]]:
    """{页面名: 页面数据}"""
    out: dict[str, dict[str, Any]] = {}
    s = Sample()
    weekly = s.doc(WEEKLY, "write")
    events, bound = s.events({"write": weekly})
    out["base"] = build(s, events, bound)
    out["missing-doc"] = build(s, events, bound, drop=(weekly,))
    out["missing-card"] = build(s, events, bound, drop=(s.card_id,))
    # 早期运行：运行结束事件落库之前封存，范围到它前一条为止（runner.verify_manifest 的老口径）
    finished = next(seq for seq, etype, _, _ in events if etype == "run.finished")
    out["legacy"] = build(s, events, finished - 1, legacy=True)

    monthly = s.doc(MONTHLY, "monthly")
    events, bound = s.events({"write": weekly, "monthly": monthly})
    out["two-reports"] = build(s, events, bound)

    events, bound = s.events({"write": weekly}, ending="failed")
    out["failed"] = build(s, events, bound, run={**RUN, "status": "failed"})

    # 早期运行先失败、经继续运行跑到成功：封存范围同样按结束事件推算，到成功结束的前一条为止
    events, _ = s.events({"write": weekly}, ending="continued")
    finished = next(seq for seq, etype, _, _ in events if etype == "run.finished")
    out["continued"] = build(s, events, finished - 1, legacy=True)

    events, bound = s.events({"write": weekly}, tiers=("formal", "degraded"))
    out["degraded"] = build(s, events, bound)

    stray = s.doc(WEEKLY, "write", run_id="another-run-0000")
    events, bound = s.events({"write": stray})
    out["stray"] = build(s, events, bound)

    n = Sample(nan=True)
    events, bound = n.events({"write": n.doc(WEEKLY, "write")}, nan=True)
    out["nan"] = build(n, events, bound)

    m = Sample(masked=True)
    events, bound = m.events({"write": m.doc(WEEKLY, "write", masked=MASKED_METRICS)})
    out["masked-card"] = build(m, events, bound)
    events, bound = m.events({"write": m.doc(WEEKLY, "write")})
    out["masked-old-doc"] = build(m, events, bound)

    r = Sample(regions=True)
    events, bound = r.events({"write": r.doc(MEMBERS, "write")})
    out["masked-source"] = build(r, events, bound, source_masks={"crm": ["phone"]})

    out["formats"] = formats_bundle()
    out["formats-unit"] = formats_bundle(card=FORMATS_UNIT_CARD)
    return out


def pages() -> dict[str, str]:
    """{页面名: HTML}"""
    return {name: render_html(bundle) for name, bundle in bundles().items()}


def main(argv: list[str]) -> int:
    if len(argv) != 2:
        print("用法：python -m tests.bundle_samples <目录>", file=sys.stderr)
        return 2
    target = Path(argv[1])
    target.mkdir(parents=True, exist_ok=True)
    for name, page in pages().items():
        (target / f"{name}.html").write_text(page, encoding="utf-8")
    return 0


if __name__ == "__main__":
    sys.exit(main(sys.argv))