liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
21 lines
869 B
Python
21 lines
869 B
Python
import unittest
|
|
|
|
from real_gaia_campaign import gaia_component_score, outcome_label
|
|
|
|
|
|
class RealGAIACampaignTest(unittest.TestCase):
|
|
def test_official_exact_and_partial_list_score_are_separate(self):
|
|
partial = gaia_component_score("Yoshida", "Yoshida, Uehara")
|
|
self.assertFalse(partial["official_exact"])
|
|
self.assertEqual(0.5, partial["component_score"])
|
|
self.assertEqual("partial", outcome_label(partial["component_score"]))
|
|
|
|
def test_numeric_and_formatted_answers_match_aworld_semantics(self):
|
|
self.assertTrue(gaia_component_score("5,876", "5876")["official_exact"])
|
|
self.assertTrue(gaia_component_score("Saint Petersburg", "Saint Petersburg")["official_exact"])
|
|
self.assertFalse(gaia_component_score("Petersburg", "Saint Petersburg")["official_exact"])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|