yilunjiang/AgentLab
1
0
Fork 0
mirror of https://github.com/ThearchyHelios/AgentLab.git synced 2026-11-15 05:31:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

可验证报告：查询快照只给哈希时照实说明原因，样本页和浏览器检查补「遮罩源上的汇总查询可核对」

Browse Source 
核对页对只给哈希的查询快照原来写「含遮罩列，未随文件附带」。现在没碰遮罩列的快照照常附带，只给哈希的是这条查询
用到或可能用到设了遮罩的列（条件里写到的、解析不了的也算），原文改成「这条查询用到或可能用到设了遮罩的列，快照未随
文件附带，只能核对到哈希」；口径卡的说法不变。核对逻辑不变，只是按工件种类挑说法（verifier.js 的 maskedQuery）；
内联脚本的 CSP 哈希由 render_html 按脚本现算，不用另改。顺手改正 verifier.js 开头一句过时的注释：口径卡现在会因遮罩
只给哈希，导出时不会出现的是报告文档标着遮罩。

tests/bundle_samples.py 加样本页 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
按地区汇总的查询和选出了号码的那份。check-bundle 断网打开它：汇总快照在 ③ 通过、引用它的两个数字在 ⑤ 通过、点开看得
到汇总的 SQL 和被引用的那一行；选出了号码的快照和引用它的数字无法核对并写明原因；总览「可核对的项全部通过」，页面里
找不到号码。另在这一页上篡改：汇总快照改一个字节 ③ 变红，改它的数字的引用值并重算全部哈希 ⑤ 变红。base 页上的原因
文案跟着改。test_bundle_build 守住样本页的形状。
This commit is contained in:
ThearchyHelios
2026-10-06 17:11:41 +08:00
parent faf21894a3
commit 02883dea7b
4 changed files with 102 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/tests/bundle_samples.py
+44 -17
View File
@@ -19,6 +19,8 @@
- 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：口径卡上一个指标的输入取自会员消费的号码列（设了遮罩），卡上记着号码原值：整张卡只给 id，引用它的
数字无法核对
- 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
"""
@@ -39,8 +41,8 @@ RUN = {"id": RUN_ID, "workflow_id": "wf-sample-weekly", "workflow_name": "门店
"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"),
("card", "metrics", "周报口径"), ("write", "report", "写周报"), ("monthly", "report", "写月报"),
("out", "output", "成果")]]}
("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],
@@ -48,6 +50,11 @@ STORES = [["青石店", 1280.5], ["白沙店", "960.00"], ["临川店", 732], ["
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"}]}
@@ -55,6 +62,9 @@ WEEKLY = ("## 门店周报\n\n本周销售额 [[m:gmv]]，*按发生周统计*
"**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]]"
#: 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]:
@@ -83,21 +93,29 @@ def masked_card(crm_id: str) -> dict[str, Any]:
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。"""
"""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）。"""
def __init__(self, *, nan: bool = False, masked: bool = False) -> None:
def __init__(self, *, nan: bool = False, masked: bool = False, regions: bool = False) -> None:
self.files: dict[str, bytes] = {}
self.shop_id = self.put(shop(nan))
self.crm_id = self.put(CRM)
self.card = masked_card(self.crm_id) if masked else CARD
self.card_id = self.put(self.card)
self.ledger = [
{"kind": "query", "node_id": "fetch", "exec": 1, "artifact": self.shop_id, "tool": "db_query__shop",
"source": "shop", "columns": ["store", "amount", "ratio"], "rows": len(STORES), "truncated": False},
{"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},
{"kind": "metric_set", "node_id": "card", "artifact": self.card_id},
]
self.entries = {
"fetch": {"kind": "query", "node_id": "fetch", "exec": 1, "artifact": self.shop_id,
"tool": "db_query__shop", "source": "shop", "columns": ["store", "amount", "ratio"],
"rows": len(STORES), "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)
def put(self, obj: Any) -> str:
@@ -131,12 +149,17 @@ class Sample:
"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.ledger[0]]})
"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.ledger[1]]})
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": {"kind": "metric_set"},
"evidence": [self.ledger[2]]})
"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})
@@ -167,12 +190,12 @@ class Sample:
def render(sample: Sample, events: list[tuple[int, str, str | None, Any]], bound: int, *, run: dict[str, Any] | None = None,
legacy: bool = False, drop: tuple[str, ...] = ()) -> str:
"""真实封存哈希的页面。drop：导出时服务端已没有文件的工件。"""
legacy: bool = False, drop: tuple[str, ...] = (), source_masks: dict[str, list[str]] | None = None) -> str:
"""真实封存哈希的页面。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}
bundle = 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={})
exported_at=EXPORTED_AT, legacy=legacy, graph=GRAPH, source_masks=source_masks or {})
return render_html(bundle)
@@ -215,6 +238,10 @@ def pages() -> dict[str, str]:
m = Sample(masked=True)
events, bound = m.events({"write": m.doc(WEEKLY, "write")})
out["masked-card"] = render(m, events, bound)
r = Sample(regions=True)
events, bound = r.events({"write": r.doc(MEMBERS, "write")})
out["masked-source"] = render(r, events, bound, source_masks={"crm": ["phone"]})
return out