mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-15 17:52:01 +00:00
ThearchyHelios
b080302e77
上一轮让被改过、解析不出的口径卡不再原样嵌入（号码不进文件），可这样一来它在页面上和正常的遮罩卡一模一样：「? 无法核对 含遮罩列，未随文件附带」，总结论从「有 1 项不通过」变成「可核对的项全部通过」，篡改的证据丢了；截断的卡服务端其实认不出输入，却被说成「含遮罩列」。现在 _Artifacts.add 对只给 id 的遮罩工件（口径卡、查询快照都算，带遮罩的快照被改过原来就有同样的问题）照实带上服务端看到的：store.intact 为假标 mismatch，解析不出对象标 unparsable。verifier.js 在遮罩分支认这两个标记：mismatch 判不通过，原因「导出时服务端的这份文件与工件 id（哈希）不一致，可能被改过；按含遮罩列处理，未随文件附带」；unparsable 是正常的无法核对，原因「导出时服务端的这份文件无法解析，认不出是否含遮罩列，按含遮罩列处理，未随文件附带」，引用它的数字跟着用这句。pytest 补被改过、截断、不是对象、哈希对得上却解析不出的卡和被改过的遮罩快照；check-bundle 在 masked-card 样本上补两条篡改检查。
556 lines
30 KiB
Python
556 lines
30 KiB
Python
"""可验证报告的构建：把一次已封存运行的报告、证据和运行记录打成一个自包含的 HTML 文件。
|
||
|
||
拿到文件的人不连服务、不装任何东西，在浏览器里就能核对（verifier.js）：
|
||
|
||
- 事件：封存范围内（seq ≤ manifest_seq）的每一条都带 {seq, type, node_id, data_sha256}，data_sha256 是
|
||
sha256(canonical_json(data))，和 runner 封存时算 manifest_hash 用的是同一个算法，浏览器按同样的拼法重算
|
||
清单哈希、和封存哈希比。白名单里的事件另带服务端算好的规范字符串 canonical（逐字等于 canonical_json(data)），
|
||
浏览器先核它的哈希，再从里面读出报告文档、口径卡、查询快照的 id。其余事件只给哈希：工具返回、节点产出的
|
||
预览里可能有遮罩列的原值和提示词。
|
||
- 工件：每份报告文档（各报告节点最后一次自查记下的 doc_artifact）、它引用到的口径卡和查询快照，按原字节
|
||
base64 嵌入，浏览器重算 sha256 和 id 比；带遮罩的快照不嵌内容、只给 id。口径卡上记着每个输入的值和代入式，
|
||
有输入取自遮罩列（cell() 的格、Agent 字段、按位置取的 vars.res.rows[0][2]）的整张卡同样只给 id，认法和证据
|
||
面板、推演同一个（recompute.input_origin）；服务端文件被改过的卡照样按卡上记的输入认，解析不出一张卡的整张只给
|
||
id。只给 id 的工件，服务端的文件和 id 对不上的另标 mismatch、解析不出来的另标 unparsable，核对页照实说（对不上的
|
||
判不通过）。没被报告引用的工件不嵌。
|
||
- 封存之后追加的事件（按需裁判、审批质询这类批注）单列：类型、序号、内容摘要，不进清单。
|
||
|
||
它只证明「内部一致」：数字、文档、运行记录彼此对得上，而且没被改过。真伪要拿页面上的封存哈希和系统里这次
|
||
运行的封存核对（GET /api/runs/{id}/verify）对照，页面上醒目地写着这一点。
|
||
|
||
主体是纯函数：不碰数据库，工件经 read 取原字节，数据源现在设的遮罩由调用方查好传进来（source_masks）。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import base64
|
||
import hashlib
|
||
import html
|
||
import json
|
||
import re
|
||
from collections.abc import Callable, Iterable, Mapping, Sequence
|
||
from datetime import datetime
|
||
from functools import lru_cache
|
||
from pathlib import Path
|
||
from typing import Any
|
||
from urllib.parse import quote
|
||
|
||
from app.core.artifact_store import canonical_json, content_hash
|
||
from app.core.events import EventType
|
||
from app.engine.evidence import iter_units, query_entry_fields
|
||
from app.engine.merge_query import MERGE_SOURCE
|
||
from app.engine.recompute import input_origin
|
||
from app.engine.schema import NodeType
|
||
from app.engine.toolcalls import QUERY_PREFIX
|
||
|
||
SCHEMA = "agentlab.bundle/1"
|
||
|
||
#: 不论哪个节点都带规范字符串的事件：运行开始（实际生效的运行参数）、报告自查（报告文档的 id）、
|
||
#: 口径卡升版处置、出具判定（档位）
|
||
_SHOWN_EVENTS = frozenset({EventType.RUN_STARTED, EventType.REPORT_CHECKED, EventType.CALIBER_UPGRADE,
|
||
EventType.ISSUANCE})
|
||
#: node.finished 带规范字符串的节点：报告（预览就是嵌进来的那份文档的正文）、口径卡（指标集的 id 记在台账里）
|
||
_SHOWN_NODES = frozenset({NodeType.REPORT, NodeType.METRICS})
|
||
#: 目录条目的种类 → 嵌进来的工件种类。运行输入、检索、表和字段的条目不嵌：前者没有工件，后几样不在核对范围里
|
||
_CITED_KINDS = {"metric": "metric_set", "query": "query"}
|
||
|
||
#: 没挂在工作流上的运行（画布、问数据当场搭的）：老数据叫「临时图」，新的叫「未保存的工作流」，也可能是空的。
|
||
#: 和前端 lib/terms.ts 的 runName 同一个规则
|
||
UNSAVED_NAME = "未保存的工作流"
|
||
_UNSAVED_NAMES = frozenset({"", "临时图", UNSAVED_NAME})
|
||
FILE_SUFFIX = "-可验证报告.html"
|
||
#: 文件名里不能出现的字（Windows 最严，按它来）和控制字符
|
||
_BAD_FILENAME = re.compile(r'[\\/:*?"<>|\x00-\x1f\x7f]')
|
||
_NAME_MAX = 80
|
||
|
||
Reader = Callable[[str], "bytes | None"]
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 工件：原字节、解析、遮罩
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
class _Store:
|
||
"""这一次构建里读过的工件：原字节、解析出来的内容、查询快照带不带遮罩。每份只读一次盘。"""
|
||
|
||
def __init__(self, read: Reader, source_masks: Mapping[str, Any]) -> None:
|
||
self._read = read
|
||
self._source_masks = source_masks
|
||
self._raw: dict[str, bytes | None] = {}
|
||
self._json: dict[str, Any] = {}
|
||
self._masked: dict[str, bool] = {}
|
||
|
||
def raw(self, artifact: str) -> bytes | None:
|
||
if artifact not in self._raw:
|
||
try:
|
||
data = self._read(artifact)
|
||
except (OSError, ValueError):
|
||
data = None
|
||
self._raw[artifact] = data if isinstance(data, (bytes, bytearray)) else None
|
||
return self._raw[artifact]
|
||
|
||
def content(self, artifact: str) -> Any:
|
||
"""解析出来的内容，读不出来、不是 JSON 的是 None。不看哈希：被改过的快照也要知道它记的遮罩。"""
|
||
if artifact not in self._json:
|
||
raw = self.raw(artifact)
|
||
try:
|
||
self._json[artifact] = json.loads(raw) if raw is not None else None
|
||
except ValueError:
|
||
self._json[artifact] = None
|
||
return self._json[artifact]
|
||
|
||
def intact(self, artifact: str) -> bool:
|
||
raw = self.raw(artifact)
|
||
return raw is not None and content_hash(bytes(raw)) == artifact
|
||
|
||
def masked(self, artifact: str) -> bool:
|
||
"""这份查询快照算不算带遮罩：查询当时记下了遮罩列（mask_columns），或者它的数据源现在设了遮罩
|
||
（合并查询看它合并的那几个数据源）。比证据面板粗：面板只遮那几列，这里整份不随文件附带——文件会
|
||
离开系统，遮罩只减少暴露，宁可多挡。读不出来的快照不知道带没带遮罩，按带遮罩算。"""
|
||
if artifact not in self._masked:
|
||
self._masked[artifact] = _snapshot_masked(self.content(artifact), self._source_masks)
|
||
return self._masked[artifact]
|
||
|
||
def card_masked(self, artifact: str, events: Sequence[tuple[int, str, str | None, Any]]) -> bool:
|
||
"""这张口径卡算不算带遮罩：卡上有一个输入取自遮罩列，或者遮没遮核对不了。卡上记着每个输入的值（cell() 取的格、
|
||
Agent 字段、按位置取的 vars.res.rows[0][2]）和代入式，整张卡不随文件附带——没法只拿掉几个值，拿掉了哈希就对不上。
|
||
|
||
认哪个输入取自哪份查询结果的哪几列，和证据面板、推演同一个认法（recompute.input_origin）；按位置取的一格顺着
|
||
取值链从写变量的节点在口径卡算这一次之前的产出起走。核对不了的宁可多挡：快照读不出来、取值链上的产出读不出来、
|
||
那份结果没存快照只带着数据源名、定位里没写列。认得出、可结果既没带快照的 id 也没带数据源名的（数据整形改过形状）
|
||
认不出出处，不算。
|
||
|
||
卡本身按解析出来的内容认，不看哈希（同 content）：服务端的文件被改过，嵌进页面的照样是这份原字节，卡上记着的号码
|
||
也照样在里面。读得出字节、解析不出一张卡的（截断的 JSON、不是对象）认不出有哪些输入，整张按带遮罩算，和读不出来的
|
||
快照按带遮罩算（_snapshot_masked）是同一个道理。字节都读不出来的卡本来就不嵌（只给 id、标缺失），这里不管。"""
|
||
key = f"card:{artifact}"
|
||
if key not in self._masked:
|
||
card = self.content(artifact)
|
||
if not isinstance(card, dict):
|
||
self._masked[key] = self.raw(artifact) is not None
|
||
return self._masked[key]
|
||
outputs = _card_outputs(events, artifact)
|
||
|
||
def output(node_id: Any) -> Any:
|
||
found = outputs.get(str(node_id or ""))
|
||
return self.content(found) if found and self.intact(found) else None
|
||
|
||
items = [item for metric in card.get("metrics") or [] if isinstance(metric, dict)
|
||
for item in metric.get("inputs") or [] if isinstance(item, dict)]
|
||
self._masked[key] = any(self._input_masked(item, output) for item in items)
|
||
return self._masked[key]
|
||
|
||
def _input_masked(self, item: dict[str, Any], output: Callable[[Any], Any]) -> bool:
|
||
origin = input_origin(item, output)
|
||
if origin is None:
|
||
return False
|
||
if origin.unverified is not None:
|
||
return True
|
||
if origin.artifact is None:
|
||
return origin.source is not None # 没存快照：查询当时记下的遮罩无从核对
|
||
content = self.content(origin.artifact)
|
||
if not self.intact(origin.artifact) or not isinstance(content, dict):
|
||
return True
|
||
if not origin.columns:
|
||
return self.masked(origin.artifact)
|
||
hidden = _snapshot_hidden(content, self._source_masks)
|
||
return any(c.lower() in hidden for c in origin.columns)
|
||
|
||
|
||
def _snapshot_masked(content: Any, source_masks: Mapping[str, Any]) -> bool:
|
||
if not isinstance(content, dict):
|
||
return True
|
||
recorded = content.get("mask_columns")
|
||
if isinstance(recorded, list) and any(isinstance(c, str) and c.strip() for c in recorded):
|
||
return True
|
||
sources = content.get("sources") if content.get("source") == MERGE_SOURCE else [content.get("source")]
|
||
return any(source_masks.get(str(name or "")) for name in sources or [])
|
||
|
||
|
||
def _snapshot_hidden(content: dict[str, Any], source_masks: Mapping[str, Any]) -> set[str]:
|
||
"""一份读得出来的快照要遮的列（小写）：查询当时记下的，加上它的数据源（合并查询看它合并的那几个）现在设的。"""
|
||
recorded = content.get("mask_columns")
|
||
hidden = {c.lower() for c in recorded if isinstance(c, str)} if isinstance(recorded, list) else set()
|
||
sources = content.get("sources") if content.get("source") == MERGE_SOURCE else [content.get("source")]
|
||
for name in sources if isinstance(sources, list) else []:
|
||
now = source_masks.get(str(name or ""))
|
||
hidden |= {str(c).lower() for c in now} if isinstance(now, (list, tuple, set, frozenset)) else set()
|
||
return hidden
|
||
|
||
|
||
def _card_outputs(events: Sequence[tuple[int, str, str | None, Any]], card: str) -> dict[str, str]:
|
||
"""算出这份指标集的那一次口径卡执行开始之前，每个节点最后一次的产出工件：卡上 vars.*、nodes.* 取到的就是它们
|
||
（和证据接口 api/evidence._card_outputs 同一个认法）。认不出是哪一次执行时取封存范围内每个节点最后一次的产出。"""
|
||
found = next(((seq, node_id) for seq, etype, node_id, data in events
|
||
if etype == EventType.NODE_FINISHED and isinstance(data, dict)
|
||
and any(isinstance(e, dict) and e.get("kind") == "metric_set" and e.get("artifact") == card
|
||
for e in data.get("evidence") or [])), None)
|
||
bound = None
|
||
if found is not None:
|
||
bound = max((seq for seq, etype, node_id, _ in events
|
||
if etype == EventType.NODE_STARTED and node_id == found[1] and seq < found[0]), default=found[0])
|
||
out: dict[str, str] = {}
|
||
for seq, etype, node_id, data in events:
|
||
if bound is not None and seq >= bound:
|
||
break
|
||
if etype == EventType.NODE_FINISHED and node_id and isinstance(data, dict) and data.get("artifact"):
|
||
out[node_id] = str(data["artifact"])
|
||
return out
|
||
|
||
|
||
def _query_artifacts(events: Iterable[tuple[int, str, str | None, Any]]) -> list[str]:
|
||
"""封存范围内交回过的查询快照：tool.end / merge.end 的 query_artifact，节点台账里的 query 条目。"""
|
||
out: list[str] = []
|
||
for _, etype, _, data in events:
|
||
if not isinstance(data, dict):
|
||
continue
|
||
if etype in (EventType.TOOL_END, EventType.MERGE_END) and isinstance(data.get("query_artifact"), str):
|
||
out.append(data["query_artifact"])
|
||
elif etype == EventType.NODE_FINISHED:
|
||
out += [str(e["artifact"]) for e in data.get("evidence") or []
|
||
if isinstance(e, dict) and e.get("kind") == "query" and e.get("artifact")]
|
||
return list(dict.fromkeys(a for a in out if a))
|
||
|
||
|
||
_UNSEEN = object()
|
||
|
||
|
||
def _query_returned(data: Mapping[str, Any], store: _Store) -> tuple[str, str | None]:
|
||
"""一次数据源查询（db_query__ 工具的 tool.end）交回了什么：("snapshot", 查询快照 id)；("none", None) 没交回数据
|
||
（查询失败、SQL 被拒的那句原话）；认不出来是 ("unknown", None)。
|
||
|
||
新运行在 query_artifact 里直接记了快照 id。没记的有三种：查询没成功；升级前的运行（证据台账之前，tool.end 只有
|
||
工具快照，查询快照的 id 嵌在工具快照记下的返回里，照证据接口 _legacy_pool 的办法认）；协作团队成员的查询（连工具
|
||
快照都不落，只能看事件里的预览，长一点的返回被截断，解析不了）。"""
|
||
artifact = data.get("query_artifact")
|
||
if isinstance(artifact, str) and artifact:
|
||
return "snapshot", artifact
|
||
returned: Any = _UNSEEN
|
||
snapshot = data.get("artifact")
|
||
# 工具快照要哈希对得上、记的是同一个工具：被改过的不能拿来说这次查询没有遮罩
|
||
if isinstance(snapshot, str) and snapshot and store.intact(snapshot):
|
||
content = store.content(snapshot)
|
||
if isinstance(content, dict) and content.get("tool") == data.get("tool") and "result" in content:
|
||
returned = content["result"]
|
||
if returned is _UNSEEN:
|
||
preview = data.get("preview")
|
||
if not isinstance(preview, str):
|
||
return "unknown", None
|
||
returned = preview
|
||
if preview.startswith('"'):
|
||
# 调用工具节点的预览是把返回值再 json.dumps 一遍（文本外面套了一层引号），截断了就剥不开
|
||
try:
|
||
returned = json.loads(preview)
|
||
except ValueError:
|
||
return "unknown", None
|
||
fields = query_entry_fields(returned)
|
||
if fields:
|
||
return "snapshot", str(fields["artifact"])
|
||
# 数据源工具成功时交回的是 JSON 对象；不是对象的是一句原话，对象里没有 rows 的是报错
|
||
if isinstance(returned, str) and not returned.lstrip().startswith("{"):
|
||
return "none", None
|
||
if isinstance(returned, dict) and "rows" not in returned:
|
||
return "none", None
|
||
return "unknown", None
|
||
|
||
|
||
def _masked_run(events: Sequence[tuple[int, str, str | None, Any]], store: _Store, cited: Iterable[str],
|
||
source_masks: Mapping[str, Any]) -> bool:
|
||
"""运行里有没有哪次查询的结果可能带着遮罩列。有的话，成果节点和运行结束事件的预览可能直接带出查询结果，只给哈希。
|
||
|
||
宁严勿宽：封存范围内每一次数据源查询都要对得上一份没有遮罩的查询快照，或者确实没交回数据，才算没有。数据源
|
||
现在设了遮罩的，按工具名就知道，不必去认快照；认不出查了什么的，按带遮罩算。"""
|
||
known = [*_query_artifacts(events), *cited]
|
||
for _, etype, _, data in events:
|
||
if etype != EventType.TOOL_END or not isinstance(data, dict):
|
||
continue
|
||
tool = str(data.get("tool") or "")
|
||
if not tool.startswith(QUERY_PREFIX):
|
||
continue
|
||
if source_masks.get(tool[len(QUERY_PREFIX):]):
|
||
return True
|
||
kind, artifact = _query_returned(data, store)
|
||
if kind == "unknown":
|
||
return True
|
||
if artifact:
|
||
known.append(artifact)
|
||
return any(store.masked(a) for a in dict.fromkeys(known))
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 报告文档和它引用到的工件
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
def _report_events(events: Iterable[tuple[int, str, str | None, Any]]) -> list[dict[str, Any]]:
|
||
"""每个报告节点最后一次自查记下的文档，按第一次出现的顺序。和证据接口（api/evidence._reports）同一个认法：
|
||
报告重写过的，认最后一次。"""
|
||
latest: dict[str, dict[str, Any]] = {}
|
||
for seq, etype, node_id, data in events:
|
||
if etype == EventType.REPORT_CHECKED and node_id and isinstance(data, dict) and data.get("doc_artifact"):
|
||
latest[node_id] = {"node_id": node_id, "doc_artifact": str(data["doc_artifact"]), "seq": seq}
|
||
return list(latest.values())
|
||
|
||
|
||
def _cited_artifacts(doc: dict[str, Any]) -> list[tuple[str, str, str | None]]:
|
||
"""报告正文引用到的口径卡和查询快照：(工件 id, 种类, 来源节点)，按正文顺序、去重。
|
||
|
||
看每个解析成功的引用（行内的数字、单元格，句末的 [[see:]]）在文档目录里指向的条目：指标条目指向口径卡，
|
||
查询条目指向快照。整表在组装时已经展开成每格一个单元格引用，不用另看。"""
|
||
catalog = doc.get("catalog") if isinstance(doc.get("catalog"), dict) else {}
|
||
out: list[tuple[str, str, str | None]] = []
|
||
for _, unit in iter_units(doc):
|
||
if not isinstance(unit, dict):
|
||
continue
|
||
cites = [s.get("cite") for s in unit.get("segments") or [] if isinstance(s, dict)]
|
||
for cite in [*cites, *(unit.get("see") or [])]:
|
||
if not isinstance(cite, dict) or cite.get("status") != "resolved":
|
||
continue
|
||
entry = catalog.get(cite.get("alias"))
|
||
kind = _CITED_KINDS.get(entry.get("kind")) if isinstance(entry, dict) else None
|
||
if kind and isinstance(entry.get("artifact"), str) and entry["artifact"]:
|
||
owner = entry.get("node_id")
|
||
out.append((entry["artifact"], kind, str(owner) if owner else None))
|
||
return list(dict.fromkeys(out))
|
||
|
||
|
||
class _Artifacts:
|
||
"""嵌进页面的工件清单，按先后：报告文档在前，接着是它引用到的。同一份只列一次。events 是封存范围内的事件
|
||
（认口径卡带不带遮罩时找写变量的节点当时的产出）。"""
|
||
|
||
def __init__(self, store: _Store, events: Sequence[tuple[int, str, str | None, Any]] = ()) -> None:
|
||
self.store = store
|
||
self.events = events
|
||
self.items: list[dict[str, Any]] = []
|
||
self._seen: set[str] = set()
|
||
|
||
def add(self, artifact: str, kind: str, node_id: str | None) -> None:
|
||
if artifact in self._seen:
|
||
return
|
||
self._seen.add(artifact)
|
||
item: dict[str, Any] = {"id": artifact, "kind": kind}
|
||
if node_id:
|
||
item["node_id"] = node_id
|
||
raw = self.store.raw(artifact)
|
||
if raw is None:
|
||
# 服务端的文件不在了：只给 id，浏览器照实说核对不了
|
||
item["missing"] = True
|
||
elif (kind == "query" and self.store.masked(artifact)) \
|
||
or (kind == "metric_set" and self.store.card_masked(artifact, self.events)):
|
||
item["masked"] = True
|
||
# 不嵌内容，浏览器就算不出这份文件对不对得上：服务端自己看到的照实带上，核对页据此判不通过、说清原因。
|
||
# 以前被改过的卡原样嵌进去，浏览器自己算出对不上；现在不嵌了，这个证据不能跟着丢
|
||
if not self.store.intact(artifact):
|
||
item["mismatch"] = True
|
||
if not isinstance(self.store.content(artifact), dict):
|
||
item["unparsable"] = True
|
||
else:
|
||
# 原样嵌入，不在这里复验哈希：被改过的文件照实交出去，浏览器自己算出对不上
|
||
item["b64"] = base64.b64encode(bytes(raw)).decode("ascii")
|
||
self.items.append(item)
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 事件
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
def _shows_content(etype: str, node_id: str | None, data: Any, node_types: Mapping[str, str], store: _Store,
|
||
masked_run: bool) -> bool:
|
||
"""这条封存范围内的事件带不带规范字符串（白名单）。"""
|
||
if etype in _SHOWN_EVENTS:
|
||
return True
|
||
if etype == EventType.RUN_FINISHED:
|
||
# 运行结束事件里是成果：字段可以直接引用查询结果，运行里有带遮罩的快照时只给哈希
|
||
return not masked_run
|
||
if etype == EventType.NODE_FINISHED:
|
||
kind = node_types.get(node_id or "")
|
||
return kind in _SHOWN_NODES or (kind == NodeType.OUTPUT and not masked_run)
|
||
if etype == EventType.TOOL_END:
|
||
# 查询类：把查询快照的 id 和运行记录连起来。预览里是查询结果的前一截，数据源带遮罩的只给哈希
|
||
artifact = data.get("query_artifact") if isinstance(data, dict) else None
|
||
return isinstance(artifact, str) and bool(artifact) and not store.masked(artifact)
|
||
return False
|
||
|
||
|
||
def _clip(text: Any, limit: int = 60) -> str:
|
||
flat = re.sub(r"\s+", " ", str(text or "")).strip()
|
||
return flat if len(flat) <= limit else flat[:limit] + "…"
|
||
|
||
|
||
def _summary(etype: str, data: Any) -> str:
|
||
"""封存之后追加的事件说一句是什么。只挑不会带出数据的字段：判了几句、问的是什么、日志那一句。"""
|
||
if not isinstance(data, dict):
|
||
return ""
|
||
if etype == EventType.EVIDENCE_JUDGED:
|
||
verdicts = data.get("verdicts")
|
||
count = len(verdicts) if isinstance(verdicts, dict) else 0
|
||
model = data.get("model")
|
||
return f"按需裁判 {count} 句结论" + (f"（模型 {_clip(model, 40)}）" if isinstance(model, str) and model else "")
|
||
if etype == EventType.APPROVAL_INQUIRY:
|
||
question = data.get("question")
|
||
return f"质询：{_clip(question)}" if isinstance(question, str) and question.strip() else "审批质询"
|
||
if etype == EventType.LOG and isinstance(data.get("message"), str):
|
||
return _clip(data["message"])
|
||
return ""
|
||
|
||
|
||
def _tier(events: Sequence[tuple[int, str, str | None, Any]]) -> dict[str, Any] | None:
|
||
"""出具档位：封存范围内最后一条出具判定事件里的 tier，带上序号（浏览器拿那条已核对的事件对照）。"""
|
||
for seq, etype, _, data in reversed(events):
|
||
if etype == EventType.ISSUANCE and isinstance(data, dict) and isinstance(data.get("tier"), str):
|
||
return {"value": data["tier"], "seq": seq}
|
||
return None
|
||
|
||
|
||
def _iso(value: Any) -> str | None:
|
||
if value is None:
|
||
return None
|
||
return value.isoformat() if isinstance(value, datetime) else str(value)
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 构建
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
def display_name(run: Mapping[str, Any]) -> str:
|
||
"""页面标题、附件名用的运行名：工作流名；没保存的工作流一律叫「未保存的工作流」。"""
|
||
name = str(run.get("workflow_name") or "").strip()
|
||
if not run.get("workflow_id") and name in _UNSAVED_NAMES:
|
||
return UNSAVED_NAME
|
||
return name or f"运行 {str(run.get('id') or '')[:8]}".strip()
|
||
|
||
|
||
def attachment_name(run: Mapping[str, Any]) -> str:
|
||
"""附件名「<运行名>-可验证报告.html」。文件名里不能有的字换成下划线。"""
|
||
name = _BAD_FILENAME.sub("_", display_name(run)).strip(" .")[:_NAME_MAX].strip(" .")
|
||
return f"{name or UNSAVED_NAME}{FILE_SUFFIX}"
|
||
|
||
|
||
def content_disposition(filename: str, *, run_id: str) -> str:
|
||
"""附件头：中文名按 RFC 5987 写在 filename* 里；filename 给不认 filename* 的老客户端一个纯 ASCII 的名字。"""
|
||
ascii_id = re.sub(r"[^A-Za-z0-9]", "", run_id)[:8]
|
||
return f"attachment; filename=\"agentlab-{ascii_id}-bundle.html\"; filename*=UTF-8''{quote(filename, safe='')}"
|
||
|
||
|
||
def build_bundle(
|
||
run: Mapping[str, Any],
|
||
events: Sequence[tuple[int, str, str | None, Any]],
|
||
*,
|
||
manifest_seq: int,
|
||
manifest_hash: str,
|
||
read: Reader,
|
||
exported_at: str,
|
||
legacy: bool = False,
|
||
graph: Mapping[str, Any] | None = None,
|
||
source_masks: Mapping[str, Any] | None = None,
|
||
) -> dict[str, Any]:
|
||
"""一次已封存运行 → 页面里的数据（bundle-data）。
|
||
|
||
- run：运行记录的几样（id、workflow_id、workflow_name、version、version_hash、run_class、status、
|
||
started_at、finished_at）
|
||
- events：这次运行的全部事件 (seq, type, node_id, data)，按数据库里 seq 的顺序。和封存核对
|
||
（runner.verify_manifest）读的是同一个顺序：seq 相同的几条，浏览器按这里的先后排，清单才算得一样
|
||
- manifest_seq / manifest_hash：封存范围（老运行是按结束事件推算的那个，legacy 为真）和封存哈希
|
||
- read：工件 id → 原字节（不复验哈希），没有就是 None
|
||
- source_masks：数据源名 → 它现在设的遮罩列（只列设了的）
|
||
"""
|
||
graph = graph if isinstance(graph, Mapping) else {}
|
||
node_types: dict[str, str] = {}
|
||
nodes: dict[str, dict[str, str]] = {}
|
||
for item in graph.get("nodes") or []:
|
||
if isinstance(item, Mapping) and item.get("id"):
|
||
nid = str(item["id"])
|
||
data = item.get("data") if isinstance(item.get("data"), Mapping) else {}
|
||
node_types[nid] = str(item.get("type") or "")
|
||
nodes[nid] = {"label": str(data.get("label") or nid), "type": node_types[nid]}
|
||
|
||
sealed = [e for e in events if e[0] <= manifest_seq]
|
||
later = [e for e in events if e[0] > manifest_seq]
|
||
store = _Store(read, source_masks or {})
|
||
|
||
artifacts = _Artifacts(store, sealed)
|
||
reports = _report_events(sealed)
|
||
cited_queries: list[str] = []
|
||
for report in reports:
|
||
doc_id, node_id = report["doc_artifact"], report["node_id"]
|
||
artifacts.add(doc_id, "report_doc", node_id)
|
||
doc = store.content(doc_id) if store.intact(doc_id) else None
|
||
# 文档要真是这次运行里这个节点写的：内容寻址只保证没被改，不保证没被张冠李戴。对不上的照实嵌进去让
|
||
# 浏览器标出来，但它的目录不可信，不顺着它去找别的工件
|
||
if not isinstance(doc, dict) or doc.get("run_id") != run.get("id") or doc.get("node_id") != node_id:
|
||
continue
|
||
for artifact, kind, owner in _cited_artifacts(doc):
|
||
artifacts.add(artifact, kind, owner)
|
||
if kind == "query":
|
||
cited_queries.append(artifact)
|
||
|
||
masked_run = _masked_run(sealed, store, cited_queries, source_masks or {})
|
||
shown_events = []
|
||
for seq, etype, node_id, data in sealed:
|
||
text = canonical_json(data)
|
||
item: dict[str, Any] = {"seq": seq, "type": etype, "node_id": node_id, "data_sha256": content_hash(text)}
|
||
if _shows_content(etype, node_id, data, node_types, store, masked_run):
|
||
item["canonical"] = text
|
||
shown_events.append(item)
|
||
|
||
return {
|
||
"schema": SCHEMA,
|
||
"meta": {
|
||
"run_id": run.get("id"), "workflow_id": run.get("workflow_id"), "workflow_name": display_name(run),
|
||
"version": run.get("version"), "version_hash": run.get("version_hash"),
|
||
"run_class": run.get("run_class"), "status": run.get("status"),
|
||
"started_at": _iso(run.get("started_at")), "finished_at": _iso(run.get("finished_at")),
|
||
"manifest_seq": manifest_seq, "manifest_hash": manifest_hash, "legacy": bool(legacy),
|
||
"tier": _tier(sealed), "exported_at": exported_at,
|
||
},
|
||
"nodes": nodes,
|
||
"events": shown_events,
|
||
"appended": [{"seq": seq, "type": etype, "node_id": node_id, "summary": _summary(etype, data)}
|
||
for seq, etype, node_id, data in later],
|
||
"reports": reports,
|
||
"artifacts": artifacts.items,
|
||
}
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 页面
|
||
# --------------------------------------------------------------------------
|
||
|
||
#: 数据放在 <script type="application/json"> 里：< > & 换成转义，正文里的 </script>、<!-- 截不断数据块；
|
||
#: U+2028 / U+2029 在老的 JS 解析器里是换行，一并转义。这几个字只会出现在 JSON 的字符串里，转义后 JSON 不变
|
||
_JSON_ESCAPES = str.maketrans({"<": "\\u003c", ">": "\\u003e", "&": "\\u0026",
|
||
"\u2028": "\\u2028", "\u2029": "\\u2029"})
|
||
_PLACEHOLDER = re.compile(r"__BUNDLE_(TITLE|NAME|SEAL|RUN|FAILED|CSP|DATA|SCRIPT)__")
|
||
|
||
|
||
@lru_cache(maxsize=1)
|
||
def _assets() -> tuple[str, str]:
|
||
here = Path(__file__).parent
|
||
return (here / "template.html").read_text(encoding="utf-8"), (here / "verifier.js").read_text(encoding="utf-8")
|
||
|
||
|
||
def bundle_json(bundle: Mapping[str, Any]) -> str:
|
||
"""页面数据块里的 JSON 文本。"""
|
||
return json.dumps(bundle, ensure_ascii=False, separators=(",", ":")).translate(_JSON_ESCAPES)
|
||
|
||
|
||
def render_html(bundle: Mapping[str, Any]) -> str:
|
||
"""把数据和核对脚本填进模板：样式、脚本都内联，零外链。
|
||
|
||
内容安全策略按哈希只放行这一段核对脚本，默认什么都不许连：页面打开后不会、也不能向任何地方发请求。
|
||
工作流名、封存哈希、运行 ID 直接写进页面：邮件、即时通讯的附件预览和系统的快速查看常常不执行脚本，也要看得到
|
||
该拿什么去系统里对照。脚本执行后拿数据里的封存哈希核对，再核一遍这里写出的和它一致。失败结束的运行另写一句：
|
||
之后在系统中继续运行会重新封存，这个文件就再也对不上了。
|
||
占位符一次替换完，填进去的内容不会再被当成占位符。"""
|
||
template, script = _assets()
|
||
digest = base64.b64encode(hashlib.sha256(script.encode("utf-8")).digest()).decode("ascii")
|
||
meta = bundle.get("meta") or {}
|
||
name = str(meta.get("workflow_name") or UNSAVED_NAME)
|
||
values = {"TITLE": html.escape(f"{name} · 可验证报告"), "NAME": html.escape(name),
|
||
"SEAL": html.escape(str(meta.get("manifest_hash") or "")), "RUN": html.escape(str(meta.get("run_id") or "")),
|
||
"FAILED": "" if meta.get("status") == "failed" else " hidden",
|
||
"CSP": f"'sha256-{digest}'", "DATA": bundle_json(bundle), "SCRIPT": script}
|
||
return _PLACEHOLDER.sub(lambda m: values[m.group(1)], template)
|