mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-15 04:41:57 +00:00
ThearchyHelios
59f1868dac
早期运行先失败、经继续运行跑到成功的，封存范围里留着中途那条运行失败，成功结束的那条在范围外（run.finished 落库之前封存）。 以前 checkMeta 拿范围内最后一条结束类事件去对，把运行结果改成「已失败」也标「已核对」。现在只认范围内最后一条、且是结束类 事件的那一条；没有这样一条时，早期运行成功结束照旧说无法核对，别的说法写明那条失败之后运行又继续了、没有事件印证，判不通过， 页面顶上显示「—」而不是把文件里写的当成核对出来的。 样本页加一份 continued（先失败、继续运行到成功的早期运行），check-bundle 断言它原样时无法核对、运行结果改成已失败或已取消时不通过。
217 lines
13 KiB
Python
217 lines
13 KiB
Python
"""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
|
||
- 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
|
||
"""
|
||
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
|
||
|
||
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"),
|
||
("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"]}
|
||
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]]"
|
||
|
||
|
||
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}
|
||
|
||
|
||
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。"""
|
||
|
||
def __init__(self, *, nan: bool = False) -> None:
|
||
self.files: dict[str, bytes] = {}
|
||
self.shop_id = self.put(shop(nan))
|
||
self.crm_id = self.put(CRM)
|
||
self.card_id = self.put(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.catalog = build_catalog(nodes={"card": CARD}, ledger=self.ledger)
|
||
|
||
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) -> str:
|
||
return self.put(compose_doc(text, self.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.ledger[0]]})
|
||
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", "card", {"duration_ms": 3, "attempt": 1, "preview": {"kind": "metric_set"},
|
||
"evidence": [self.ledger[2]]})
|
||
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 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。"""
|
||
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={})
|
||
return render_html(bundle)
|
||
|
||
|
||
def pages() -> dict[str, str]:
|
||
"""{页面名: HTML}"""
|
||
out: dict[str, str] = {}
|
||
s = Sample()
|
||
weekly = s.doc(WEEKLY, "write")
|
||
events, bound = s.events({"write": weekly})
|
||
out["base"] = render(s, events, bound)
|
||
out["missing-doc"] = render(s, events, bound, drop=(weekly,))
|
||
out["missing-card"] = render(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"] = render(s, events, finished - 1, legacy=True)
|
||
|
||
monthly = s.doc(MONTHLY, "monthly")
|
||
events, bound = s.events({"write": weekly, "monthly": monthly})
|
||
out["two-reports"] = render(s, events, bound)
|
||
|
||
events, bound = s.events({"write": weekly}, ending="failed")
|
||
out["failed"] = render(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"] = render(s, events, finished - 1, legacy=True)
|
||
|
||
events, bound = s.events({"write": weekly}, tiers=("formal", "degraded"))
|
||
out["degraded"] = render(s, events, bound)
|
||
|
||
stray = s.doc(WEEKLY, "write", run_id="another-run-0000")
|
||
events, bound = s.events({"write": stray})
|
||
out["stray"] = render(s, events, bound)
|
||
|
||
n = Sample(nan=True)
|
||
events, bound = n.events({"write": n.doc(WEEKLY, "write")}, nan=True)
|
||
out["nan"] = render(n, events, bound)
|
||
return out
|
||
|
||
|
||
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))
|