mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-15 08:41:59 +00:00
ThearchyHelios
9d8b41430e
- 完善口径编辑、只读试运行、统一质量验证与执行语义指纹 - 增加可执行指标约束、有预算的主动调查和过程评测 - 提取发布检查、证据读取与起草服务，支持任务停止、重试和检查点恢复 - 增加版本传递影响分析，修复并发覆盖、敏感值遮罩、异常评分及页面状态问题 - 修复 SQLite 复合查询追溯和 microVM 可选依赖缺失处理 - 纳入当前设计文档及部署配置调整 验证：相关主回归 3822 项通过，4 项跳过、8 项预期失败；补充回归通过。 前端构建、文案检查及 git diff --check 通过。 全量检查仍有环境权限、PostgreSQL 可选依赖和既有部署配置、SQLite 文件基线差异导致的未通过项。
254 lines
16 KiB
Python
254 lines
16 KiB
Python
"""分析结论在两份自包含页面里的渲染（第 1 波 W1-b）：报告导出（report_export/runtime.js）点开判定语、分析范围里的编号；
|
||
可验证报告（bundle/verifier.js）点开判定语看分析结论一节、正文后面的分析范围。
|
||
|
||
浏览器里的完整检查（check-report-export、check-bundle）第 2 波由编排者跑；这里在 node 里用一个最小的 DOM 替身把两份脚本
|
||
真正跑一遍，挡住渲染分析结论那几步时的脚本错误（引用了不存在的文案、函数），并核对面板里写出来的字。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
import re
|
||
import shutil
|
||
import subprocess
|
||
from pathlib import Path
|
||
from typing import Any
|
||
|
||
import pytest
|
||
from httpx import ASGITransport, AsyncClient
|
||
|
||
import app.bundle
|
||
import app.report_export
|
||
from app.main import app as asgi
|
||
from tests.test_analysis_bundle import bundle_of, card_bundle
|
||
from app.core import artifact_store
|
||
from tests.test_analysis_evidence import SNAPSHOT, analyzed
|
||
from tests.test_analysis_evidence_api import (
|
||
LAST_WEEK, SCOPE, TEXT, THIS_WEEK, comparability_card, ratio_run, sealed_run, seg_id,
|
||
)
|
||
|
||
NODE = shutil.which("node")
|
||
pytestmark = pytest.mark.skipif(NODE is None, reason="没有 node，无法执行页面上的脚本")
|
||
|
||
RUNTIME = Path(app.report_export.__file__).parent / "runtime.js"
|
||
VERIFIER = Path(app.bundle.__file__).parent / "verifier.js"
|
||
|
||
#: 最小的 DOM 替身：元素、文字、片段，getElementById 按 id 建元素；textContent 递归拼接
|
||
DOM = r"""
|
||
const camel = (s) => s.replace(/-([a-z])/g, (_, c) => c.toUpperCase())
|
||
class Node_ {
|
||
constructor() { this.children = []; this.parent = null }
|
||
append(...kids) {
|
||
for (const k of kids) {
|
||
const n = typeof k === 'string' ? new Text_(k) : k
|
||
if (n instanceof Frag_) { for (const c of n.children) { c.parent = this; this.children.push(c) } n.children = [] }
|
||
else { n.parent = this; this.children.push(n) }
|
||
}
|
||
}
|
||
replaceChildren(...kids) { this.children = []; this.append(...kids) }
|
||
get textContent() { return this.children.map((c) => c.textContent).join('') }
|
||
set textContent(v) { this.children = [new Text_(String(v))] }
|
||
walk(f) { f(this); for (const c of this.children) c.walk(f) }
|
||
}
|
||
class Text_ extends Node_ {
|
||
constructor(t) { super(); this.text = t }
|
||
get textContent() { return this.text }
|
||
set textContent(v) { this.text = String(v) }
|
||
}
|
||
class Frag_ extends Node_ {}
|
||
class El_ extends Node_ {
|
||
constructor(tag) {
|
||
super(); this.tag = tag; this.attrs = {}; this.dataset = {}; this.style = {}; this.hidden = false; this.listeners = {}
|
||
this.className = ''; const cls = new Set(); this.classList = { add: (c) => cls.add(c), remove: (c) => cls.delete(c), contains: (c) => cls.has(c) }
|
||
}
|
||
setAttribute(k, v) { this.attrs[k] = String(v); if (k.startsWith('data-')) this.dataset[camel(k.slice(5))] = String(v) }
|
||
getAttribute(k) { return this.attrs[k] ?? null }
|
||
removeAttribute(k) { delete this.attrs[k] }
|
||
addEventListener(t, f) { (this.listeners[t] ||= []).push(f) }
|
||
focus() {} scrollIntoView() {}
|
||
getBoundingClientRect() { return { top: 0, bottom: 0 } }
|
||
querySelector() { return new El_('span') }
|
||
closest() { return this }
|
||
}
|
||
globalThis.Node = Node_
|
||
const ids = {}
|
||
globalThis.window = { scrollBy() {} }
|
||
globalThis.document = {
|
||
readyState: 'complete', activeElement: null, documentElement: new El_('html'),
|
||
getElementById(id) { return ids[id] ||= new El_('div') },
|
||
createElement(tag) { return new El_(tag) }, createTextNode(t) { return new Text_(t) },
|
||
createDocumentFragment() { return new Frag_() }, addEventListener() {}, querySelectorAll() { return [] },
|
||
}
|
||
const fs = require('fs')
|
||
const input = JSON.parse(fs.readFileSync(0, 'utf8'))
|
||
const find = (root, pred) => { const out = []; root.walk((n) => { if (n instanceof El_ && pred(n)) out.push(n) }); return out }
|
||
"""
|
||
|
||
RUN_RUNTIME = DOM + r"""
|
||
document.getElementById('report-data').textContent = input.data
|
||
new Function(fs.readFileSync(process.argv[1], 'utf8'))()
|
||
const out = {}
|
||
for (const seg of input.segs) {
|
||
const el = new El_('button')
|
||
for (const [k, v] of Object.entries(seg)) el.setAttribute(`data-${k}`, v)
|
||
el.textContent = seg.text
|
||
for (const f of document.getElementById('report').listeners.click || []) f({ target: el })
|
||
out[seg.seg] = { title: document.getElementById('detail-title').textContent,
|
||
body: document.getElementById('detail-body').textContent,
|
||
steps: find(document.getElementById('detail-body'), (n) => n.attrs['data-step']).map((n) => n.attrs['data-step']) }
|
||
}
|
||
process.stdout.write(JSON.stringify(out))
|
||
"""
|
||
|
||
RUN_VERIFIER = DOM + r"""
|
||
document.getElementById('bundle-data').textContent = input.data
|
||
document.getElementById('seal-hash').textContent = input.seal
|
||
new Function(fs.readFileSync(process.argv[1], 'utf8'))()
|
||
setTimeout(() => {
|
||
const reports = document.getElementById('reports')
|
||
const out = { scope: find(reports, (n) => 'data-scope' in n.attrs).map((n) => n.textContent), opened: {} }
|
||
for (const btn of find(reports, (n) => n.attrs['data-num'])) {
|
||
for (const f of btn.listeners.click || []) f()
|
||
out.opened[btn.attrs['data-num']] = document.getElementById('detail-body').textContent
|
||
}
|
||
out.verified = document.documentElement.attrs['data-verified'] ?? null
|
||
process.stdout.write(JSON.stringify(out))
|
||
}, 200)
|
||
"""
|
||
|
||
|
||
def run_node(script: str, path: Path, payload: dict[str, Any]) -> Any:
|
||
done = subprocess.run([NODE, "-e", script, str(path)], input=json.dumps(payload), capture_output=True, text=True,
|
||
timeout=120)
|
||
assert done.returncode == 0, done.stderr[-3000:]
|
||
return json.loads(done.stdout)
|
||
|
||
|
||
async def test_the_export_page_opens_the_analysis_steps_and_the_scope_numbers():
|
||
made = await sealed_run(TEXT, doc_extra=SCOPE)
|
||
async with AsyncClient(transport=ASGITransport(app=asgi), base_url="http://test") as client:
|
||
html = (await client.get(f"/api/runs/{made['run']}/report.html")).text
|
||
data = re.search(r'<script type="application/json" id="report-data">(.*?)</script>', html, re.S).group(1)
|
||
phrase = seg_id(made["doc"], "a:A1")
|
||
cell = seg_id(made["doc"], "v:A1.r0.delta")
|
||
segs = [{"seg": phrase, "kind": "analysis", "state": "deterministic", "text": made["result"]["phrase"]},
|
||
{"seg": cell, "kind": "number", "state": "deterministic", "text": "-120"},
|
||
{"seg": "scope:A1", "kind": "analysis", "state": "deterministic", "text": "A1"}]
|
||
# 现查结果的三种写法：按运行当天现算的界、一列一个值都没有、表的范围（结论里的 probes 原样交给页面）
|
||
parsed = json.loads(data)
|
||
method = next(s for s in parsed["chains"][parsed["refs"][phrase]] if s["step"] == "analysis_method")
|
||
method["probes"] = [
|
||
{"source": "shop", "expr": "date('now', '-7 days')", "value": "2026-10-14", "basis": "live",
|
||
"at": "2026-10-21T09:00:00"},
|
||
{"source": "shop", "table": "orders", "column": "refund_date", "min": None, "max": None, "basis": "live",
|
||
"at": "2026-10-21T09:00:00"},
|
||
{"source": "shop", "table": "orders", "column": "order_date", "min": "2025-01-01", "max": "2026-10-20",
|
||
"basis": "profile", "at": "2026-10-21T09:00:00"}]
|
||
out = run_node(RUN_RUNTIME, RUNTIME, {"data": json.dumps(parsed, ensure_ascii=False), "segs": segs})
|
||
opened = out[phrase]
|
||
assert opened["steps"] == ["analysis", "analysis_method", "analysis_calc", "analysis_input", "query",
|
||
"analysis_recompute", "analysis_seal"]
|
||
assert opened["title"].startswith("判定「销售额下降")
|
||
body = opened["body"]
|
||
# 分析卡做的结论（台账条目带 item）：那一句是模板作者写的，照实写「分析卡上写的『在验证什么』」，不标成 Agent 写的假设
|
||
for text in ("判定标准一段占总变化的一半以上算主要来源", "分析卡上写的『在验证什么』华东拖累", "实际用的阈值", "「主要来源」的占比",
|
||
"华东的占比 = 华东的变化 ÷ 总变化 = -120 ÷ （-194） = 61.9%", "结果表（列出 4 行，共 4 行）",
|
||
"复算一致：按封存的输入重新计算，结论逐项相同", "封存范围内的台账记过这份分析结论",
|
||
"按运行当天现算的界 date('now', '-7 days') = 2026-10-14（现查 · 2026-10-21T09:00:00）",
|
||
"orders.refund_date：这一列一个值都没有（现查", "orders.order_date：2025-01-01 至 2026-10-20（剖析"):
|
||
assert text in body, text
|
||
# 结果表的格写结果表记的列名（labels 的「变化」），不把列 id 当叫法
|
||
assert "结果表第 1 行「变化」" in out[cell]["body"]
|
||
assert out["scope:A1"]["steps"] == opened["steps"]
|
||
|
||
|
||
async def test_the_export_page_speaks_of_the_overall_ratio_for_a_ratio_decomposition():
|
||
"""比率拆解的总数那一格是整体比率：导出页写「整体比率那一格」「整体比率 x 与各段分子之和 ÷ 分母之和 y 闭合」，不说
|
||
「各段之和」。比率按结论记的格式写成百分数（3.5%，不是 0.035），两格一致。可加拆解照旧（上一个用例的页面里没有
|
||
「整体比率」）。"""
|
||
made = await ratio_run()
|
||
async with AsyncClient(transport=ASGITransport(app=asgi), base_url="http://test") as client:
|
||
html = (await client.get(f"/api/runs/{made['run']}/report.html")).text
|
||
data = re.search(r'<script type="application/json" id="report-data">(.*?)</script>', html, re.S).group(1)
|
||
phrase = seg_id(made["doc"], "a:A1")
|
||
out = run_node(RUN_RUNTIME, RUNTIME, {"data": data, "segs": [
|
||
{"seg": phrase, "kind": "analysis", "state": "deterministic", "text": made["result"]["phrase"]}]})
|
||
body = out[phrase]["body"]
|
||
for text in ("基期整体比率", "整体比率那一格", "自身效应", "结构效应",
|
||
"整体比率 3.5% 与各段分子之和 ÷ 分母之和 3.5% 闭合",
|
||
"整体比率 5.3% 与各段分子之和 ÷ 分母之和 5.3% 闭合"):
|
||
assert text in body, text
|
||
assert "各段之和 0.0" not in body
|
||
|
||
|
||
async def test_the_export_page_writes_the_headline_cell_the_way_the_server_rendered_it():
|
||
"""总数那一格的值由服务端渲染（render_cell：千分位），页面照原样显示：以前照原值写「2220」，同一节里闭合核对写
|
||
「2,220」，一处引用里两个写法并排。"""
|
||
totals = {"columns": ["gmv_base", "gmv"], "column_types": {"gmv_base": "number", "gmv": "number"},
|
||
"rows": [[2220, 2026]], "sql": "SELECT 2220 AS gmv_base, 2026 AS gmv", "source": "shop",
|
||
"truncated": False}
|
||
t = artifact_store.content_hash(artifact_store.canonical_json(totals))
|
||
q = artifact_store.content_hash(artifact_store.canonical_json(SNAPSHOT))
|
||
result = await analyzed({"Q2": (SNAPSHOT, q), "Q5": (totals, t)}, headline=["Q5.r0.gmv_base", "Q5.r0.gmv"])
|
||
made = await sealed_run("[[a:A1]]。", result=result, queries=[totals])
|
||
async with AsyncClient(transport=ASGITransport(app=asgi), base_url="http://test") as client:
|
||
html = (await client.get(f"/api/runs/{made['run']}/report.html")).text
|
||
data = re.search(r'<script type="application/json" id="report-data">(.*?)</script>', html, re.S).group(1)
|
||
phrase = seg_id(made["doc"], "a:A1")
|
||
out = run_node(RUN_RUNTIME, RUNTIME, {"data": data, "segs": [
|
||
{"seg": phrase, "kind": "analysis", "state": "deterministic", "text": made["result"]["phrase"]}]})
|
||
body = out[phrase]["body"]
|
||
for text in ("总数那一格第 1 行「gmv_base」 = 2,220", "总数那一格第 1 行「gmv」 = 2,026",
|
||
"总数 2,220 与各段之和 2,220 闭合"):
|
||
assert text in body, text
|
||
assert "= 2220" not in body and "= 2026" not in body
|
||
|
||
|
||
async def test_the_bundle_page_shows_the_analysis_detail_and_the_scope():
|
||
bundle, _, _ = bundle_of(doc_extra=SCOPE)
|
||
out = run_node(RUN_VERIFIER, VERIFIER, {"data": json.dumps(bundle), "seal": bundle["meta"]["manifest_hash"]})
|
||
assert out["verified"] == ""
|
||
[scope] = out["scope"]
|
||
assert scope.startswith("分析范围") and "现象A1：销售额下降" in scope and "拆过A1（按地区）：主要来自华东" in scope
|
||
assert "没拆渠道" in scope and "这次做了 2 次差异检验，几次检验之间没有按次数校正" in scope
|
||
phrase = next(text for text in out["opened"].values() if "出处分析结论 A1 的判定语" in text)
|
||
assert "核对结果✓ 通过" in phrase and "分析结论里的值「销售额下降 194（-8.7%）" in phrase
|
||
# 方法写服务端带来的叫法和 id（和导出页同一个写法），不只写 id
|
||
assert "判定语销售额下降 194（-8.7%）" in phrase and "方法与版本变化拆解（可加） · decompose.additive@2" in phrase
|
||
assert "输入数据 · Q1" in phrase # 输入的角色写叫法，不写 data
|
||
# 这份结论是分析卡做的（台账条目带 item）：那一句「在验证什么」写「分析卡上写的『在验证什么』」，不标成 Agent 写的假设
|
||
assert "分析卡上写的『在验证什么』" in phrase and "Agent 写的假设" not in phrase
|
||
assert "复算一致：按封存的输入重新计算，结论逐项相同（导出时服务端按封存的输入复算的结论；本页只核哈希" in phrase
|
||
value = next(text for text in out["opened"].values() if "具名的数「top_share」" in text)
|
||
assert "引用的值0.618556701031" in value and "正文显示61.9%（与按显示规则渲染的结果一致）" in value
|
||
scope_item = next(text for key, text in out["opened"].items() if key.endswith("|scope:A1"))
|
||
assert "核对结果✓ 通过" in scope_item and "正文显示" not in scope_item
|
||
|
||
|
||
async def test_the_export_page_opens_the_comparability_on_a_metric():
|
||
"""口径卡指标上的可比性：指标那一步里写判定，点得开那份可比性结论（同分析结论的几步，收在一个可展开的块里）。"""
|
||
card, result = await comparability_card()
|
||
made = await sealed_run("环比 [[m:wow]]。", card=card, queries=[LAST_WEEK, THIS_WEEK])
|
||
async with AsyncClient(transport=ASGITransport(app=asgi), base_url="http://test") as client:
|
||
html = (await client.get(f"/api/runs/{made['run']}/report.html")).text
|
||
data = re.search(r'<script type="application/json" id="report-data">(.*?)</script>', html, re.S).group(1)
|
||
wow = seg_id(made["doc"], "m:wow")
|
||
out = run_node(RUN_RUNTIME, RUNTIME, {"data": data, "segs": [
|
||
{"seg": wow, "kind": "number", "state": "deterministic", "text": "-0.0874"}]})
|
||
opened = out[wow]
|
||
assert opened["steps"][:1] == ["metric"]
|
||
assert opened["steps"][opened["steps"].index("analysis"):] [:3] == ["analysis", "analysis_method", "analysis_calc"]
|
||
for text in ("两期可比性", "展开这份可比性结论", "可比性检查", "口径卡执行时自动做的可比性检查", result["phrase"],
|
||
"同口径", "复算一致：按封存的输入重新计算，结论逐项相同", "记在口径卡的指标集里，随卡封存（不进台账）"):
|
||
assert text in opened["body"], text
|
||
|
||
|
||
def test_the_bundle_page_shows_the_comparability_in_the_metric_detail():
|
||
bundle, _, _, _ = card_bundle()
|
||
out = run_node(RUN_VERIFIER, VERIFIER, {"data": json.dumps(bundle), "seal": bundle["meta"]["manifest_hash"]})
|
||
assert out["verified"] == ""
|
||
[detail] = out["opened"].values()
|
||
for text in ("两期可比性", "判定两期有条件可比", "判定标准只差日期", "方法与版本可比性检查 · comparable@2", "各项检查", "同口径",
|
||
"复算一致：按封存的输入重新计算，结论逐项相同（导出时服务端按封存的输入复算的结论"):
|
||
assert text in detail, text
|
||
|