分析测试的「今天」按题集的时区取，不看本机时区：题集里的期次（上周、本周）按 suite.timezone 算，生成虚构库、判今天是不是周一也照它，本机在别的时区（或跨午夜那几个钟头）时两边不是同一天

- test_eval_analysis_runs.py：TZ 从题集读，新增 now()（datetime.now(ZoneInfo(TZ))），生成库用 now().date()，原来写死的 Asia/Shanghai 去掉
- test_eval_analysis_suite.py：从题集内容取时区算今天，判周一也按它
- test_evals_api.py：零售样例题集的「今天」同样从题集取时区

backend/tests/test_eval_analysis_runs.py

@@ -32,8 +32,9 @@ from app.eval.gold import Context
 from tests import eval_samples as es
 from tests.fixtures.acceptance import retail_trends
 
-TZ = "Asia/Shanghai"
 SUITE = json.loads((Path(__file__).parent / "fixtures" / "eval" / "analysis_suite.json").read_text(encoding="utf-8"))
+#: 题集的时区：题目里的期次（{{ schedule.* }}）按它算，生成库的「今天」也按它取，不看本机时区
+TZ = SUITE["suite"]["timezone"]
 #: 题集里的第 1 题（上周销售额下降主要来自华东）和第 3 题（订单数的常规波动）
 REGION = next(c for c in SUITE["cases"] if c["seq"] == 1)
 ORDERS = next(c for c in SUITE["cases"] if c["seq"] == 3)
@@ -53,7 +54,7 @@ async def engine_up(monkeypatch):
 
 @pytest.fixture
 async def source(tmp_path, scratch_source):
-    path = retail_trends.build(tmp_path / "trends.db", date.today())
+    path = retail_trends.build(tmp_path / "trends.db", now().date())
     sid = await scratch_source(retail_trends.SOURCE_NAME, path, schema=True)
     return {"id": sid, "name": retail_trends.SOURCE_NAME, "path": path}
 

backend/tests/test_eval_analysis_suite.py

@@ -4,9 +4,10 @@
 from __future__ import annotations
 
 import json
-from datetime import date
+from datetime import datetime
 from pathlib import Path
 from urllib.parse import quote
+from zoneinfo import ZoneInfo
 
 import pytest
 from httpx import ASGITransport, AsyncClient
@@ -33,9 +34,11 @@ async def engine_up():
 
 
 async def test_the_analysis_suite_imports_and_every_expectation_computes(tmp_path, scratch_source):
-    path = retail_trends.build(tmp_path / "trends.db", date.today())
-    sid = await scratch_source(retail_trends.SOURCE_NAME, path, schema=True)
     content = json.loads(SUITE_FILE.read_text(encoding="utf-8"))
+    # 「今天」按题集的时区取（题目里的期次按它算），不看本机时区：本机在别的时区时，跨日那几个钟头两边的今天不是同一天
+    today = datetime.now(ZoneInfo(content["suite"]["timezone"])).date()
+    path = retail_trends.build(tmp_path / "trends.db", today)
+    sid = await scratch_source(retail_trends.SOURCE_NAME, path, schema=True)
     assert {c["seq"] for c in content["cases"]} == set(WANTED)
     assert all(c["gold"]["datasource"] == retail_trends.SOURCE_NAME for c in content["cases"])
     async with AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as client:
@@ -44,7 +47,7 @@ async def test_the_analysis_suite_imports_and_every_expectation_computes(tmp_pat
         assert res.json()["imported"] == len(WANTED) and res.json()["skipped"] == []
         suite = res.json()["suite"]
         assert all(c["gold"]["datasource_id"] == sid for c in suite["cases"])
-        monday = date.today().weekday() == 0
+        monday = today.weekday() == 0
         for case in suite["cases"]:
             assert case["trial"]["status"] == "ok", (case["seq"], case["trial"])
             trial = (await client.post(f"/api/evals/suites/{suite['id']}/cases/{case['id']}/trial")).json()["trial"]

backend/tests/test_evals_api.py

@@ -386,7 +386,9 @@ async def test_export_then_import_matches_sources_by_name(client, source):
 
 async def test_the_retail_sample_suite_trials_on_the_retail_database(client, tmp_path):
     """仓库里附的零售样例题集：在虚构零售库上导入，每道题都试算通过，期望和直接查库一样，陷阱按口径算。"""
-    today = datetime.now(ZoneInfo("Asia/Shanghai")).date()
+    # 「今天」按题集的时区取（题目里的期次按它算），不看本机时区：本机在别的时区时，跨日那几个钟头两边的今天不是同一天
+    content = json.loads(SUITE_FILE.read_text(encoding="utf-8"))
+    today = datetime.now(ZoneInfo(content["suite"]["timezone"])).date()
     path = retail.build(tmp_path / "retail.db", today)
     await drop_source(name=retail.SOURCE_NAME)
     async with SessionLocal() as session:
@@ -398,7 +400,6 @@ async def test_the_retail_sample_suite_trials_on_the_retail_database(client, tmp
         await session.commit()
         sid = row.id
     try:
-        content = json.loads(SUITE_FILE.read_text(encoding="utf-8"))
         res = await client.post("/api/evals/suites/import", json={"content": content}, headers=ACTOR)
         assert res.status_code == 201, res.text
         assert res.json()["imported"] == 6 and res.json()["skipped"] == []