admin/claw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

acceptance: stabilize zhihu hotlist excel flow

Browse Source
This commit is contained in:
zyl
2026-03-29 23:17:31 +08:00
parent e294fbb9b1
commit ef88487f4a
5 changed files with 287 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

75
tests/live_acceptance_score_test.py
View File

@@ -7,14 +7,14 @@ class LiveAcceptanceScoreTest(unittest.TestCase):
def test_score_acceptance_handles_preloaded_office_skill_without_read_skill_log(self):
result = {
"logs": [
{"message": "navigate https://www.zhihu.com/hot"},
{"message": "plan 读取知乎热榜并导出 Excel"},
{"message": "navigate https://www.zhihu.com/hot"},
{"message": "getText body"},
{"message": "call openxml_office"},
],
"final_task": {
"success": True,
"summary": "已导出 Excel",
"summary": "已导出 Excel /tmp/sgclaw/out.xlsx",
},
"stderr": [],
"exports": [],
@@ -25,6 +25,77 @@ class LiveAcceptanceScoreTest(unittest.TestCase):
self.assertEqual(score["skill_selection"], 30)
self.assertEqual(score["final_response_quality"], 5)
self.assertNotIn("planner output missing before tool execution", score["deductions"])
def test_score_acceptance_flags_missing_plan_repeated_summary_and_fake_export_path(self):
repeated = "第一段总结。\n\n第一段总结。"
result = {
"logs": [
{"message": "navigate https://www.zhihu.com/hot"},
{"message": "getText main"},
{"message": "call openxml_office"},
],
"final_task": {
"success": True,
"summary": f"{repeated}\n\n导出路径：/tmp/not-real.xlsx",
},
"stderr": [],
"exports": [],
}
items = [HotItem(rank=1, title="标题", heat="123万")]
score = score_acceptance(result, items)
self.assertIn("planner output missing before tool execution", score["deductions"])
self.assertIn("repeated assistant paragraphs detected", score["deductions"])
self.assertIn("export missing output path", score["deductions"])
self.assertEqual(score["final_response_quality"], 0)
def test_score_acceptance_flags_fake_rows_when_export_contains_no_live_hotlist_data(self):
result = {
"logs": [
{"message": "plan 读取知乎热榜并导出 Excel"},
{"message": "navigate https://www.zhihu.com/hot"},
{"message": "getText main"},
{"message": "call openxml_office"},
],
"final_task": {
"success": True,
"summary": "已导出 Excel /tmp/sgclaw/out.xlsx",
},
"stderr": [],
"exports": [],
}
items = [HotItem(rank=1, title="真实标题", heat="123万")]
score = score_acceptance(result, items)
self.assertIn("hotlist rows were not exported as structured live data", score["deductions"])
self.assertEqual(score["hotlist_data_correctness"], 0)
self.assertEqual(score["xlsx_export_success"], 0)
def test_score_acceptance_flags_structured_handoff_retry_noise(self):
result = {
"logs": [
{"message": "plan 读取知乎热榜并导出 Excel"},
{"message": "navigate https://www.zhihu.com/hot"},
{"message": "getText main"},
{"message": "call openxml_office"},
{"message": "unsupported columns: expected [rank, title, heat]"},
{"message": "call openxml_office"},
],
"final_task": {
"success": True,
"summary": "已导出 Excel /tmp/sgclaw/out.xlsx",
},
"stderr": [],
"exports": [],
}
items = [HotItem(rank=1, title="真实标题", heat="123万")]
score = score_acceptance(result, items)
self.assertIn("structured handoff required export retries", score["deductions"])
if __name__ == "__main__":