research(rectification): DeepSeek Flash 抽 33% 对照现行分类器提示词
Independent Staging Quality Gate / validate (push) Successful in 10m16s
Independent Staging Quality Gate / publish (push) Successful in 3m57s

来源 B 仍为 0。Flash 套生产提示词,采集题相对门槛未过。结论仍不可接。
This commit is contained in:
jesse-ux
2026-09-19 09:45:29 +08:00
parent fde541c2ca
commit d6fc4fb8b3
7 changed files with 8610 additions and 527 deletions
+9
View File
@@ -87,6 +87,15 @@ class JevIntentCorpusTests(unittest.TestCase):
self.assertEqual(reviewed["intent"], "answer_current_focus")
self.assertEqual(reviewed["answer_class"], "no")
def test_current_instructions_match_production_classifier(self) -> None:
from scripts.research.jev_intent_current import CHOICE_INSTRUCTIONS, COLLECT_INSTRUCTIONS
src = (
ROOT / "frontend" / "src" / "lib" / "rectification-agentic" / "v9" / "turn-intent-classifier.ts"
).read_text(encoding="utf-8")
self.assertIn(CHOICE_INSTRUCTIONS, src)
self.assertIn(COLLECT_INSTRUCTIONS, src)
def test_simulated_has_no_holdout_names(self) -> None:
path = ROOT / "scripts" / "research" / "jev_intent_samples" / "simulated.jsonl"
if not path.is_file():