test_clustered_boolq_preserves_duplicate_passages (test_analyze.AnalysisTests.test_clustered_boolq_preserves_duplicate_passages) ... ok
test_duplicate_quality_rows_rejected (test_analyze.AnalysisTests.test_duplicate_quality_rows_rejected) ... ok
test_failed_pairs_affect_accuracy_not_probability_scores (test_analyze.AnalysisTests.test_failed_pairs_affect_accuracy_not_probability_scores) ... ok
test_integration_separates_bulk_latency_and_billing (test_analyze.AnalysisTests.test_integration_separates_bulk_latency_and_billing) ... ok
test_invalid_denominators_and_balanced_accuracy (test_analyze.AnalysisTests.test_invalid_denominators_and_balanced_accuracy) ... ok
test_nonfinite_predictions_and_empty_groups (test_analyze.AnalysisTests.test_nonfinite_predictions_and_empty_groups) ... ok
test_probability_truth_and_missing_bill (test_analyze.AnalysisTests.test_probability_truth_and_missing_bill) ... ok
test_timing_medians_cluster_repeats_and_exclude_incomplete (test_analyze.AnalysisTests.test_timing_medians_cluster_repeats_and_exclude_incomplete) ... ok
test_wilson_does_not_make_perfect_small_sample_certain (test_analyze.AnalysisTests.test_wilson_does_not_make_perfect_small_sample_certain) ... ok
test_clustered_statistics_preserve_fixed_counterfactual_comparisons (test_cache_analysis.CacheAnalysisTests.test_clustered_statistics_preserve_fixed_counterfactual_comparisons) ... ok
test_incomplete_duplicate_or_mismatched_pairing_rejected (test_cache_analysis.CacheAnalysisTests.test_incomplete_duplicate_or_mismatched_pairing_rejected) ... ok
test_missing_cost_rejected (test_cache_analysis.CacheAnalysisTests.test_missing_cost_rejected) ... ok
test_budget_stop_and_partial_block_resume_refusal (test_cache_study.CacheStudyTests.test_budget_stop_and_partial_block_resume_refusal) ... ok
test_cache_and_control_same_content_and_unique_prefixes (test_cache_study.CacheStudyTests.test_cache_and_control_same_content_and_unique_prefixes) ... ok
test_complete_run_has_four_cold_primes_and_288_measured (test_cache_study.CacheStudyTests.test_complete_run_has_four_cold_primes_and_288_measured) ... ok
test_exact_labels_counterfactual_pairs_and_block_balance (test_cache_study.CacheStudyTests.test_exact_labels_counterfactual_pairs_and_block_balance) ... ok
test_missing_bill_stops_and_never_becomes_zero_total (test_cache_study.CacheStudyTests.test_missing_bill_stops_and_never_becomes_zero_total) ... ok
test_warm_prime_and_missing_cache_counters_not_verified (test_cache_study.CacheStudyTests.test_warm_prime_and_missing_cache_counters_not_verified) ... ok
test_all_9570_attempts_counted_complete_with_original_invalid_retained (test_continue_quality.ContinuationTests.test_all_9570_attempts_counted_complete_with_original_invalid_retained) ... ok
test_failed_attempt_retained_no_retry_prefix_and_metadata_hash_preserved (test_continue_quality.ContinuationTests.test_failed_attempt_retained_no_retry_prefix_and_metadata_hash_preserved) ... ok
test_five_consecutive_invalid_stops_before_sixth_new_attempt (test_continue_quality.ContinuationTests.test_five_consecutive_invalid_stops_before_sixth_new_attempt) ... ok
test_global_failure_rate_reuses_initial_records (test_continue_quality.ContinuationTests.test_global_failure_rate_reuses_initial_records) ... ok
test_pending_and_unknown_allocations_both_constrain_reservations (test_continue_quality.ContinuationTests.test_pending_and_unknown_allocations_both_constrain_reservations) ... ok
test_all_probability_targets_by_outcome_enumeration (test_expanded_datasets.ExpandedDataTests.test_all_probability_targets_by_outcome_enumeration) ... ok
test_balanced_policy_oracle_and_meaningful_contrasts (test_expanded_datasets.ExpandedDataTests.test_balanced_policy_oracle_and_meaningful_contrasts) ... ok
test_complete_counts_schema_and_hashes (test_expanded_datasets.ExpandedDataTests.test_complete_counts_schema_and_hashes) ... ok
test_exact_public_label_mappings (test_expanded_datasets.ExpandedDataTests.test_exact_public_label_mappings) ... ok
test_overlap_and_source_label_error_preserved (test_expanded_datasets.ExpandedDataTests.test_overlap_and_source_label_error_preserved) ... ok
test_public_source_rows_and_wic_offsets (test_expanded_datasets.ExpandedDataTests.test_public_source_rows_and_wic_offsets) ... ok
test_synthetic_generation_reproduces_frozen_inputs (test_expanded_datasets.ExpandedDataTests.test_synthetic_generation_reproduces_frozen_inputs) ... ok
test_case_and_both_native_request_formats (test_publication.PublicationTests.test_case_and_both_native_request_formats) ... ok
test_export_manifest_and_zip (test_publication.PublicationTests.test_export_manifest_and_zip) ... ok
test_nested_json_and_html_examples (test_publication.PublicationTests.test_nested_json_and_html_examples) ... ok
test_non_rte_json_is_byte_identical (test_publication.PublicationTests.test_non_rte_json_is_byte_identical) ... ok
test_budget_rejects_invalid_limit_and_tracks_pending_reservations (test_run_study.RunStudyTests.test_budget_rejects_invalid_limit_and_tracks_pending_reservations) ... ok
test_final_call_overspend_is_logged_and_stopped (test_run_study.RunStudyTests.test_final_call_overspend_is_logged_and_stopped) ... ok
test_five_invalid_circuit_breaker_stops_before_sixth_serial_call (test_run_study.RunStudyTests.test_five_invalid_circuit_breaker_stops_before_sixth_serial_call) ... ok
test_missing_bill_is_unknown_even_for_rejected_http_status (test_run_study.RunStudyTests.test_missing_bill_is_unknown_even_for_rejected_http_status) ... ok
test_quality_plan_pair_order_and_jsonl_thread_integrity (test_run_study.RunStudyTests.test_quality_plan_pair_order_and_jsonl_thread_integrity) ... ok
test_quality_records_unknown_billing_before_stopping (test_run_study.RunStudyTests.test_quality_records_unknown_billing_before_stopping) ... ok
test_threaded_reservations_cannot_overallocate (test_run_study.RunStudyTests.test_threaded_reservations_cannot_overallocate) ... ok
test_timing_blocks_are_serial_and_warmups_distinct_from_measurements (test_run_study.RunStudyTests.test_timing_blocks_are_serial_and_warmups_distinct_from_measurements) ... ok
test_timing_unknown_bill_is_retained_and_stops_immediately (test_run_study.RunStudyTests.test_timing_unknown_bill_is_retained_and_stops_immediately) ... ok
test_unexpected_client_exception_is_retained_and_secret_redacted (test_run_study.RunStudyTests.test_unexpected_client_exception_is_retained_and_secret_redacted) ... ok
test_amendment_prefix_and_snapshot_verified (test_verify_expanded.VerifyTests.test_amendment_prefix_and_snapshot_verified) ... ok
test_complete_quality_reconciles_exact_requests (test_verify_expanded.VerifyTests.test_complete_quality_reconciles_exact_requests) ... ok
test_duplicate_attempt_not_silently_selected (test_verify_expanded.VerifyTests.test_duplicate_attempt_not_silently_selected) ... ok
test_failed_attempt_and_unknown_bill_are_retained (test_verify_expanded.VerifyTests.test_failed_attempt_and_unknown_bill_are_retained) ... ok
test_payload_tamper_is_detected (test_verify_expanded.VerifyTests.test_payload_tamper_is_detected) ... ok

----------------------------------------------------------------------
Ran 49 tests in 0.899s

OK