mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-15 22:42:01 +00:00
ThearchyHelios
2cf329648d
J1 给业务日期加了类型门槛（两边的时间列都在表结构里声明为日期 / 时间类型才写），而上传表格导入时日期一律按文字保存、表结构里总是 TEXT，上传源因此永远写不了业务日期。导入时配方里其实记着每一列的逻辑类型（导入确认时界面上标的「日期」）：列表块里类型为 DATE 的列、交叉表的日期轴。查过别处：构建回执里只有存储类型（列表的 DATE 列和文字列一样记 TEXT、role 都是 text），简单导入的回执只有 INTEGER / REAL / TEXT，所以只按配方认。
- dual_check_facts.recipe_dates：一份配方里逻辑类型是日期的列（{表: [列]}），表和列按 recipe_types.derive_tables 推，和建表同一份；日期轴写进它各分段的表，列表合计行另存的表不带日期列；类型按 _DATED_TYPE 认，只有时刻的不算
- dual_check_facts.upload_dates：只读，按数据源当前快照找配方（source_versions.snapshot_recipe_id，期 3 之前的快照取最后一期导入的），和 schema_cache 出自同一个版本；手工源、简单导入、快照或配方记录不在、配方解析不了一律给空
- 节点的 _source_info 带上 upload_dates，放进候选：审批卡的预告（preview / preview_joint）和裁决后的真写认的是发起审批时读的同一份，逐字一致；旧的 checkpoint 里没有这一项，照旧不写
- _dated_problem：上传源里按文字保存的列在 upload_dates 里的算日期列（按表结构认出的表名、列名去对，大小写不论）；不在的、读不出配方的照现在的原因说「来自上传的表格，表格里的日期一律按文字保存」；声明成别的类型的、只有时刻的照旧
测试：derive 一级补导入认作日期的写、只有一边是日期 / 读不出配方 / 记在别的表上的照旧说按文字保存、手工源不认 upload_dates、按表结构的名字对、preview_joint 同样认；新文件 test_dual_check_upload 经真实导入接口建上传源（暂存 → 改配方 → 试运行 → 提交、简单导入），配方里两列都是日期的审核人选盲算后业务日期记「支付日期」（人工确认、备注写运行），支付日期是文字的选哪边都不写、预告和跳过原因一字不差，配方记录改坏了的照旧不写；去掉认日期、去掉候选里的 upload_dates、去掉日期轴各做过一次，测试变红。
288 lines
16 KiB
Python
288 lines
16 KiB
Python
"""上传表格建的数据源上的双盲复算：业务日期按导入时配方里记的逻辑类型认日期列（engine/dual_check_facts.upload_dates）。
|
||
|
||
上传表格导入时日期一律按文字保存，表结构里总是 TEXT，以前这类数据源的业务日期永远写不了。导入时配方里其实记着每一列
|
||
的逻辑类型（导入确认时界面上标的「日期」）：
|
||
|
||
- 配方里是日期的两列（列表块里类型为 DATE 的列、交叉表的日期轴）：审核人选了哪一边，业务日期就记哪一列；审批卡的预告
|
||
和真写一字不差
|
||
- 配方里是文字的列不写；配方读不出来（简单导入没有配方、配方记录坏了）的照旧不写，原因都照实说是上传的表格按文字保存
|
||
- 只认数据源当前版本的配方：表结构出自同一个版本
|
||
|
||
数据源一律经真实的导入接口建（暂存 → 改配方 → 试运行 → 提交，或者简单导入），工作簿是现造的：表名、地区、金额都是
|
||
虚构的。盲算模型是 MockChatModel 剧本（tests/fixtures/dual_check_shop.Blind）。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import datetime as dt
|
||
import json
|
||
import uuid
|
||
from pathlib import Path
|
||
|
||
import pytest
|
||
from httpx import ASGITransport, AsyncClient
|
||
from openpyxl import Workbook
|
||
from sqlalchemy import delete, select
|
||
|
||
from app.data.recipe_types import Recipe
|
||
from app.db.base import SessionLocal
|
||
from app.db.models import DataSource, Setting, SourceSnapshot, TableRecipe
|
||
from app.engine import spend
|
||
from app.engine.dual_check_facts import recipe_dates, upload_dates
|
||
from app.engine.runner import run_manager
|
||
from app.main import app
|
||
from tests.fixtures.dual_check_shop import ROWS, Blind
|
||
from tests.fixtures.sources import drop_source
|
||
from tests.fixtures.xlsx import save
|
||
from tests.test_dual_check_node import decide, events, graph, logs, notes_of, pending, start
|
||
|
||
XLSX = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
|
||
API = "/api/datasources"
|
||
SHEET = "订单明细"
|
||
TABLE = "订单"
|
||
HEADER = ("订单号", "地区", "客户", "金额", "状态", "下单日期", "支付日期")
|
||
#: 同 dual_check_shop 的五笔单：退款行、下单日和支付日不在同一周的单，只是表名、列名、状态换成中文
|
||
STATUS = {"paid": "已支付", "refunded": "已退款"}
|
||
WEEK = "BETWEEN '2026-09-01' AND '2026-09-07'"
|
||
#: 口径说明要的写法：按支付日、排除退款（1、2、5 号单，330.0）
|
||
RIGHT = f"SELECT SUM(\"金额\") AS gmv FROM \"订单\" WHERE \"状态\" <> '已退款' AND \"支付日期\" {WEEK}"
|
||
#: 只错在时间列：按下单日（2、4、5 号单，310.0）
|
||
BY_ORDER_DATE = f"SELECT SUM(\"金额\") AS gmv FROM \"订单\" WHERE \"状态\" <> '已退款' AND \"下单日期\" {WEEK}"
|
||
DEFINITION = "已支付订单的金额合计：按支付日期归属到当周，不含退款"
|
||
#: 配方里不是日期、读不出配方时的原因：照旧说按文字保存
|
||
STORED_AS_TEXT = "来自上传的表格，表格里的日期一律按文字保存，无法确认存的是日期"
|
||
FLOW_RECIPE = json.loads((Path(__file__).parent / "fixtures" / "recipes" / "flow_recipe.json").read_text("utf-8"))
|
||
|
||
|
||
@pytest.fixture(autouse=True)
|
||
async def engine_up():
|
||
await run_manager.setup()
|
||
async with SessionLocal() as session:
|
||
await session.execute(delete(Setting).where(Setting.key.in_(["verify", spend.SPEND_KEY])))
|
||
await session.commit()
|
||
yield
|
||
await run_manager.shutdown()
|
||
|
||
|
||
@pytest.fixture
|
||
async def client():
|
||
async with AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as c:
|
||
yield c
|
||
|
||
|
||
def workbook() -> bytes:
|
||
"""订单明细：第 1 行表头，日期写成 Excel 的日期格（不是文字）。"""
|
||
wb = Workbook()
|
||
ws = wb.active
|
||
ws.title = SHEET
|
||
ws.append(list(HEADER))
|
||
for oid, region, customer, amount, status, ordered, paid, *_ in ROWS:
|
||
ws.append([oid, region, customer, amount, STATUS[status],
|
||
dt.date.fromisoformat(ordered), dt.date.fromisoformat(paid)])
|
||
return save(wb)
|
||
|
||
|
||
def list_recipe(*, ordered: str = "DATE", paid: str = "DATE") -> dict:
|
||
"""列表配方：两个日期列各按给定的类型导入（DATE 是界面上的「日期」，TEXT 是「文字」）。"""
|
||
types = {"订单号": "INTEGER", "地区": "TEXT", "客户": "INTEGER", "金额": "REAL", "状态": "TEXT",
|
||
"下单日期": ordered, "支付日期": paid}
|
||
return {"recipe_format": "agentlab-recipe/2",
|
||
"sheets": [{"id": "s1", "match": {"name": SHEET}, "blocks": [{
|
||
"id": "orders", "layout": "list", "table": TABLE,
|
||
"columns": [{"header": h, "name": h, "type": types[h]} for h in HEADER]}]}],
|
||
"tables": [{"name": TABLE, "grain": ["订单号"]}]}
|
||
|
||
|
||
async def recipe_import(client, recipe: dict) -> tuple[str, str]:
|
||
"""按配方导入：暂存 → 换成给定的配方 → 试运行 → 勾全部确认项提交。返回 (数据源名, id)。"""
|
||
name = f"dc_upload_{uuid.uuid4().hex[:8]}"
|
||
r = await client.post(f"{API}/imports/stage", files={"file": (f"{SHEET}_2026-09.xlsx", workbook(), XLSX)},
|
||
data={"name": name})
|
||
assert r.status_code == 201, r.text
|
||
staging = r.json()["id"]
|
||
r = await client.put(f"{API}/imports/{staging}/recipe", json={"recipe": recipe})
|
||
assert r.status_code == 200 and r.json()["recipe_problems"] == [], r.text
|
||
r = await client.post(f"{API}/imports/{staging}/trial", json={})
|
||
assert r.status_code == 200, r.text
|
||
trial = r.json()["trial"]
|
||
assert trial["status"] in ("passed", "needs_decision"), trial["problems"]
|
||
r = await client.post(f"{API}/imports/{staging}/commit", json={
|
||
"trial_id": trial["trial_id"], "confirmations": [i["id"] for i in trial.get("confirm_items") or []]})
|
||
assert r.status_code == 201, r.text
|
||
return name, r.json()["source"]["id"]
|
||
|
||
|
||
async def simple_import(client) -> tuple[str, str]:
|
||
"""期 1 的简单导入：按表头行导入，没有配方。"""
|
||
name = f"dc_simple_{uuid.uuid4().hex[:8]}"
|
||
r = await client.post(f"{API}/upload", files={"file": (f"{SHEET}.xlsx", workbook(), XLSX)}, data={"name": name})
|
||
assert r.status_code == 201, r.text
|
||
async with SessionLocal() as session:
|
||
source_id = (await session.execute(select(DataSource.id).where(DataSource.name == name))).scalar_one()
|
||
return name, source_id
|
||
|
||
|
||
async def dates_of(source_id: str) -> dict:
|
||
async with SessionLocal() as session:
|
||
return await upload_dates(session, await session.get(DataSource, source_id))
|
||
|
||
|
||
async def break_recipe(source_id: str) -> None:
|
||
"""把数据源当前版本的配方记录改坏（造「配方读不出来」）。"""
|
||
async with SessionLocal() as session:
|
||
row = await session.get(DataSource, source_id)
|
||
snap = await session.get(SourceSnapshot, row.current_snapshot_id)
|
||
record = await session.get(TableRecipe, snap.recipe_id)
|
||
record.recipe = {"recipe_format": "agentlab-recipe/0"}
|
||
await session.commit()
|
||
|
||
|
||
@pytest.fixture
|
||
async def dated(client):
|
||
"""两个日期列在配方里都是「日期」的上传源。"""
|
||
name, source_id = await recipe_import(client, list_recipe())
|
||
yield name, source_id
|
||
await drop_source(source_id)
|
||
|
||
|
||
@pytest.fixture
|
||
async def paid_as_text(client):
|
||
"""支付日期在配方里是「文字」、下单日期是「日期」的上传源。"""
|
||
name, source_id = await recipe_import(client, list_recipe(paid="TEXT"))
|
||
yield name, source_id
|
||
await drop_source(source_id)
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 配方里哪些列是日期
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
def test_the_date_columns_of_a_list_recipe_are_the_ones_typed_as_dates():
|
||
assert recipe_dates(Recipe.model_validate(list_recipe())) == {TABLE: ["下单日期", "支付日期"]}
|
||
assert recipe_dates(Recipe.model_validate(list_recipe(paid="TEXT"))) == {TABLE: ["下单日期"]}
|
||
assert recipe_dates(Recipe.model_validate(list_recipe(ordered="TEXT", paid="TEXT"))) == {}
|
||
|
||
|
||
def test_the_axis_of_a_crosstab_is_a_date_column_of_every_table_it_writes():
|
||
"""交叉表的日期轴（类型恒为日期）写进各分段的表：宽表、长表、表内合计另存的表都有这一列。"""
|
||
assert recipe_dates(Recipe.model_validate(FLOW_RECIPE)) == {
|
||
"日客流": ["日期"], "时段客流": ["日期"], "时段客流_表内合计": ["日期"]}
|
||
|
||
|
||
def test_a_list_total_kept_as_a_table_has_no_date_column():
|
||
"""列表的合计行另存成表时只有合计项和数字列：日期列不在里面。"""
|
||
recipe = list_recipe()
|
||
recipe["sheets"][0]["blocks"][0]["rows"] = {"total_row": {"label_column": "地区", "pick": "合计",
|
||
"keep_as": "订单合计"}}
|
||
recipe["tables"].append({"name": "订单合计", "kind": "reported_total"})
|
||
assert recipe_dates(Recipe.model_validate(recipe)) == {TABLE: ["下单日期", "支付日期"]}
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 读当前版本的配方
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
async def test_an_upload_source_reads_the_date_columns_from_its_current_recipe(client, dated, paid_as_text):
|
||
"""真实导入流程建的源：表结构里两列都是 TEXT，配方里是日期的那几列读得出来。"""
|
||
async with SessionLocal() as session:
|
||
schema = (await session.get(DataSource, dated[1])).schema_cache
|
||
types = {c["name"]: c["type"] for c in schema["tables"][TABLE]["columns"]}
|
||
assert (types["下单日期"], types["支付日期"]) == ("TEXT", "TEXT"), "背景：导入时日期一律按文字保存"
|
||
assert await dates_of(dated[1]) == {TABLE: ["下单日期", "支付日期"]}
|
||
assert await dates_of(paid_as_text[1]) == {TABLE: ["下单日期"]}
|
||
|
||
|
||
async def test_without_a_readable_recipe_no_column_is_taken_as_a_date(client, dated, tmp_path):
|
||
"""读不出配方的都不认：简单导入没有配方，配方记录坏了，手工登记的库，不存在的数据源。"""
|
||
name, source_id = await simple_import(client)
|
||
try:
|
||
async with SessionLocal() as session:
|
||
row = await session.get(DataSource, source_id)
|
||
assert row.origin == "upload" and row.current_recipe_id is None
|
||
assert await dates_of(source_id) == {}
|
||
finally:
|
||
await drop_source(source_id)
|
||
await break_recipe(dated[1])
|
||
assert await dates_of(dated[1]) == {}
|
||
async with SessionLocal() as session:
|
||
manual = DataSource(name=f"dc_manual_{uuid.uuid4().hex[:8]}", kind="sqlite", database=str(tmp_path / "x.db"))
|
||
assert await upload_dates(session, manual) == {}
|
||
assert await upload_dates(session, None) == {}
|
||
|
||
|
||
async def test_the_node_hands_the_import_dates_over_with_the_source(client, dated):
|
||
"""节点认数据源来历的那一步（_source_info）带上 upload_dates，候选据此交给 derive。"""
|
||
from app.engine.nodes.dual_check import _source_info, _Sources
|
||
|
||
info = await _source_info(_Sources(), dated[0])
|
||
assert info["uploaded"] is True and info["upload_dates"] == {TABLE: ["下单日期", "支付日期"]}
|
||
assert (await _source_info(_Sources(), "dc_no_such_source"))["upload_dates"] == {}
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 双盲复算：审批卡的预告、裁决后的真写
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
def upload_graph(name: str, sql: str) -> dict:
|
||
return graph(name, sql, dual={"definitions": {"gmv": DEFINITION}})
|
||
|
||
|
||
async def test_dates_the_import_took_as_dates_are_written_as_the_business_date(monkeypatch, client, dated):
|
||
"""两列在配方里都是「日期」：审批卡预告选哪边记哪一列，审核人选盲算，业务日期记「支付日期」，人工确认、备注写明出处。"""
|
||
name, source_id = dated
|
||
Blind(monkeypatch, name, {"销售额": (RIGHT, "gmv")})
|
||
run = await start(upload_graph(name, BY_ORDER_DATE))
|
||
assert run.status == "interrupted", run.error
|
||
[item] = (await pending(run.id)).payload["summary"]
|
||
assert len(item["diff"]) == 1 and "下单日期" in item["diff"][0] and "支付日期" in item["diff"][0]
|
||
where = {"source": name, "table": TABLE, "item": "business_date"}
|
||
assert item["catalog"] == {"a": {"write": True, **where, "value": {"column": "下单日期"}},
|
||
"b": {"write": True, **where, "value": {"column": "支付日期"}}}
|
||
done = await decide(client, run.id, {"gmv": "b"})
|
||
assert done.status == "succeeded", done.error
|
||
[wrote] = logs(await events(run.id), "dual_check_catalog")
|
||
assert wrote["written"] == [{**where, "value": {"column": "支付日期"}}] and wrote["skipped"] == []
|
||
entry = await notes_of(source_id, TABLE)
|
||
stored = entry.notes["business_date"]
|
||
assert stored["value"] == {"column": "支付日期"}
|
||
assert (stored["source"], stored["status"]) == ("human", "confirmed") and run.id in stored["note"]
|
||
|
||
|
||
async def test_a_column_the_recipe_kept_as_text_is_not_written(monkeypatch, client, paid_as_text):
|
||
"""支付日期在配方里是「文字」：选哪边都不记，原因照旧说按文字保存——被采纳的是它就说它，被采纳的下单日期是日期的，说
|
||
未被采纳的支付日期、另说清为什么也要看它。预告和裁决后跳过的原因一字不差，目录里什么都没写。"""
|
||
name, source_id = paid_as_text
|
||
Blind(monkeypatch, name, {"销售额": (RIGHT, "gmv")})
|
||
run = await start(upload_graph(name, BY_ORDER_DATE))
|
||
assert run.status == "interrupted", run.error
|
||
said = (await pending(run.id)).payload["summary"][0]["catalog"]
|
||
column = f"「{TABLE}.支付日期」{STORED_AS_TEXT}"
|
||
assert said["b"] == {"write": False, "reason": f"指标「销售额」被采纳的盲算按时间筛的列{column}，不写入数据目录"}
|
||
assert said["a"] == {"write": False, "reason": f"指标「销售额」未被采纳的盲算按时间筛的列{column}："
|
||
"两边都是日期列时，审核人选的才是业务日期按哪一列，不写入数据目录"}
|
||
done = await decide(client, run.id, {"gmv": "b"})
|
||
assert done.status == "succeeded", done.error
|
||
[wrote] = logs(await events(run.id), "dual_check_catalog")
|
||
assert wrote["written"] == [] and [s["reason"] for s in wrote["skipped"]] == [said["b"]["reason"]]
|
||
assert await notes_of(source_id, TABLE) is None
|
||
|
||
|
||
async def test_without_a_readable_recipe_nothing_is_written(monkeypatch, client, dated):
|
||
"""配方记录坏了、读不出来：两列都照旧说按文字保存，不写。"""
|
||
name, source_id = dated
|
||
await break_recipe(source_id)
|
||
Blind(monkeypatch, name, {"销售额": (RIGHT, "gmv")})
|
||
run = await start(upload_graph(name, BY_ORDER_DATE))
|
||
assert run.status == "interrupted", run.error
|
||
said = (await pending(run.id)).payload["summary"][0]["catalog"]
|
||
for side, label, column in (("a", "原流程", "下单日期"), ("b", "盲算", "支付日期")):
|
||
assert said[side] == {"write": False, "reason": f"指标「销售额」被采纳的{label}按时间筛的列「{TABLE}.{column}」"
|
||
f"{STORED_AS_TEXT}，不写入数据目录"}
|
||
done = await decide(client, run.id, {"gmv": "a"})
|
||
assert done.status == "succeeded", done.error
|
||
[wrote] = logs(await events(run.id), "dual_check_catalog")
|
||
assert wrote["written"] == [] and [s["reason"] for s in wrote["skipped"]] == [said["a"]["reason"]]
|
||
assert await notes_of(source_id, TABLE) is None
|