test_ambiguous_brand_does_not_invent_single_substance (test_agent_evaluation.AgentTests.test_ambiguous_brand_does_not_invent_single_substance) ... ok
test_failures_are_reported_not_scored_as_wrong (test_agent_evaluation.AgentTests.test_failures_are_reported_not_scored_as_wrong) ... ok
test_graph_budget_reserves_original_source_text (test_agent_evaluation.AgentTests.test_graph_budget_reserves_original_source_text) ... ok
test_judge_accepts_reasoning_prefix_without_scoring_it (test_agent_evaluation.AgentTests.test_judge_accepts_reasoning_prefix_without_scoring_it) ... ok
test_judge_rejects_more_supported_claims_than_claims (test_agent_evaluation.AgentTests.test_judge_rejects_more_supported_claims_than_claims) ... ok
test_missing_data_is_not_no_interaction (test_agent_evaluation.AgentTests.test_missing_data_is_not_no_interaction) ... ok
test_short_brand_and_full_name (test_agent_evaluation.AgentTests.test_short_brand_and_full_name) ... ok
test_slovak_inflection_and_brand (test_agent_evaluation.AgentTests.test_slovak_inflection_and_brand) ... ok
test_source_identity_accepts_pil_and_detail (test_agent_evaluation.AgentTests.test_source_identity_accepts_pil_and_detail) ... ok
test_unrelated_prefix_not_detected (test_agent_evaluation.AgentTests.test_unrelated_prefix_not_detected) ... ok

----------------------------------------------------------------------
Ran 10 tests in 0.003s

OK