test_confident_proceed_allows (test_judge_gate.J1_HappyPath.test_confident_proceed_allows) ... ok
test_noul_and_score_questions (test_judge_gate.J1_HappyPath.test_noul_and_score_questions) ... ok
test_exception_can_escalate_but_never_allow (test_judge_gate.J2_ErrorFailsClosed.test_exception_can_escalate_but_never_allow) ... ok
test_exception_denies (test_judge_gate.J2_ErrorFailsClosed.test_exception_denies) ... ok
test_slow_judge_denied (test_judge_gate.J3_TimeoutFailsClosed.test_slow_judge_denied) ... ok
test_each_malformed_response_denied (test_judge_gate.J4_MalformedFailsClosed.test_each_malformed_response_denied) ... ok
test_random_garbage_never_allows (test_judge_gate.J4_MalformedFailsClosed.test_random_garbage_never_allows) ... ok
test_below_threshold_escalates (test_judge_gate.J5_LowConfidence.test_below_threshold_escalates) ... ok
test_confident_block_denies_and_confident_escalate_escalates (test_judge_gate.J5_LowConfidence.test_confident_block_denies_and_confident_escalate_escalates) ... ok
test_small_margin_escalates_even_above_threshold (test_judge_gate.J5_LowConfidence.test_small_margin_escalates_even_above_threshold) ... ok
test_uncertain_can_deny (test_judge_gate.J5_LowConfidence.test_uncertain_can_deny) ... ok
test_documented_example_answers_parse (test_judge_gate.J6_ClefAdapterMatchesDocs.test_documented_example_answers_parse) ... ok
test_no_token_means_not_called_and_denied (test_judge_gate.J6_ClefAdapterMatchesDocs.test_no_token_means_not_called_and_denied) ... ok
test_pricing_constant_from_docs (test_judge_gate.J6_ClefAdapterMatchesDocs.test_pricing_constant_from_docs) ... ok
test_request_shape_url_and_auth (test_judge_gate.J6_ClefAdapterMatchesDocs.test_request_shape_url_and_auth) ... ok
test_rest_envelope_accepted_and_error_envelope_denied (test_judge_gate.J6_ClefAdapterMatchesDocs.test_rest_envelope_accepted_and_error_envelope_denied) ... ok
test_jev_cannot_be_primary (test_judge_gate.J7_JevBenchmarkOnly.test_jev_cannot_be_primary) ... ok
test_side_by_side_records_but_never_decides (test_judge_gate.J7_JevBenchmarkOnly.test_side_by_side_records_but_never_decides) ... ok
test_allow_still_requires_human_approval (test_judge_gate.J8_HarnessIntegration.test_allow_still_requires_human_approval) ... ok
test_block_rejects_before_approval (test_judge_gate.J8_HarnessIntegration.test_block_rejects_before_approval) ... ok
test_error_timeout_malformed_reject_run (test_judge_gate.J8_HarnessIntegration.test_error_timeout_malformed_reject_run) ... ok
test_low_confidence_escalates_flagged_for_human (test_judge_gate.J8_HarnessIntegration.test_low_confidence_escalates_flagged_for_human) ... ok

----------------------------------------------------------------------
Ran 22 tests in 0.241s

OK
