Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/NVIDIA/SkillEvaluator
/ functions
Functions
24,741 in github.com/NVIDIA/SkillEvaluator
⨍
Functions
24,741
◇
Types & classes
1,292
↳
Endpoints
703
Function
test_behavior_inventory_keeps_all_expectations_after_judge_error
(module, monkeypatch)
tests/tier3/test_judge_result_semantics.py:72
Function
test_behavior_inventory_preserves_original_requirements_and_missing_verdicts
(module, monkeypatch)
tests/tier3/test_judge_result_semantics.py:55
Function
test_behavior_inventory_survives_unexpected_provider_exceptions
(module, exception, monkeypatch)
tests/tier3/test_judge_result_semantics.py:85
Function
test_behavior_judge_can_abstain_without_calling_missing_evidence_a_violation
(module, monkeypatch)
tests/tier3/test_judge_result_semantics.py:116
Function
test_behavior_judge_empty_reasoning_burn_yields_scoreless_error
(monkeypatch)
tests/tier3/test_judge_parse_robustness.py:353
Function
test_behavior_judge_keeps_explicit_max_tokens_override
(monkeypatch)
tests/tier3/test_judge_parse_robustness.py:327
Function
test_behavior_judge_refuses_to_cut_accounted_evidence_a_second_time
(judge_module, monkeypatch)
tests/tier3/test_judge_contracts.py:485
Function
test_behavior_judge_requests_reasoning_safe_max_tokens
(monkeypatch)
tests/tier3/test_judge_parse_robustness.py:318
Function
test_behavior_judge_retries_once_with_minified_json_reminder
(monkeypatch)
tests/tier3/test_judge_parse_robustness.py:336
Function
test_behavior_judge_salvage_scores_against_expected_behavior_count
(monkeypatch)
tests/tier3/test_judge_parse_robustness.py:392
Function
test_behavior_judge_salvages_truncated_results_after_retry
(monkeypatch)
tests/tier3/test_judge_parse_robustness.py:373
Function
test_behavior_judge_success_path_unchanged
(monkeypatch)
tests/tier3/test_judge_parse_robustness.py:412
Function
test_behavior_judge_treats_list_payload_as_unparseable
(monkeypatch)
tests/tier3/test_judge_parse_robustness.py:264
Function
test_behavior_keeps_middle_evidence_under_new_budget
(monkeypatch)
tests/tier3/test_judge_uses_evidence.py:70
Function
test_behavior_pool
()
tests/tier3/test_grader_validation.py:305
Function
test_behavior_prompt_example_is_a_valid_reply_for_any_number_of_behaviors
( judge_module, monkeypatch, behavior_count: int )
tests/tier3/test_judge_contracts.py:135
Function
test_behavior_reply_must_judge_each_step_exactly_once
( judge_module, monkeypatch, results: list[dict[str, Any]], problem: str )
tests/tier3/test_judge_contracts.py:359
Function
test_behavior_retries_ambiguous_multiple_documents_then_errors
(judge_module, monkeypatch)
tests/tier3/test_judge_result_semantics.py:1188
Function
test_behavior_retries_malformed_or_invalid_shapes_once_then_errors
( judge_module, monkeypatch, content: str, )
tests/tier3/test_judge_result_semantics.py:991
Function
test_behavior_retries_nonstandard_constant_in_metadata_then_errors
( judge_module, monkeypatch, )
tests/tier3/test_judge_result_semantics.py:1068
Function
test_behavior_retries_overflowed_numeric_metadata_once_and_recovers
(judge_module, monkeypatch)
tests/tier3/test_judge_result_semantics.py:941
Function
test_behavior_retry_transport_failure_salvages_only_complete_first_entries
(judge_module, monkeypatch)
tests/tier3/test_judge_result_semantics.py:1087
Function
test_behavior_retry_transport_failure_without_salvage_is_redacted_error
(judge_module, monkeypatch)
tests/tier3/test_judge_result_semantics.py:1104
Function
test_behavior_salvage_accepts_append_only_completable_current_entry
( judge_module, monkeypatch, unfinished_entry: str, )
tests/tier3/test_judge_result_semantics.py:1168
Function
test_behavior_salvage_keeps_finite_top_level_score_prefix
(judge_module, monkeypatch)
tests/tier3/test_judge_result_semantics.py:1377
Function
test_behavior_salvage_rejects_excessive_nesting
( judge_module, monkeypatch, malformed: str, )
tests/tier3/test_judge_result_semantics.py:1249
Function
test_behavior_salvage_rejects_invalid_top_level_prefixes
( judge_module, monkeypatch, malformed: str, )
tests/tier3/test_judge_result_semantics.py:1358
Function
test_behavior_salvage_rejects_noncompletable_current_entry
( judge_module, monkeypatch, unfinished_entry: str, )
tests/tier3/test_judge_result_semantics.py:1140
Function
test_behavior_salvage_rejects_nonstandard_constants
( judge_module, monkeypatch, malformed: str, )
tests/tier3/test_judge_result_semantics.py:1285
Function
test_behavior_salvage_rejects_repeated_steps
(judge_module, monkeypatch)
tests/tier3/test_judge_contracts.py:375
Function
test_behavior_salvage_tolerates_non_structural_wrappers
(judge_module, monkeypatch, prefix: str)
tests/tier3/test_judge_result_semantics.py:1395
Function
test_benchmark_allows_explicit_optional_skipped_tier2
()
tests/golden/test_benchmark_card.py:644
Function
test_benchmark_allows_explicit_persisted_optional_tier2_policy
()
tests/golden/test_benchmark_card.py:507
Function
test_benchmark_allows_explicit_persisted_optional_tier3_policy
()
tests/golden/test_benchmark_card.py:943
Function
test_benchmark_allows_tier1_only_when_both_later_tiers_are_optional
()
tests/golden/test_benchmark_card.py:545
Function
test_benchmark_baseline_without_the_skill_can_pass
(tmp_path: Path)
tests/golden/test_benchmark_card.py:1253
Function
test_benchmark_baseline_without_the_skill_still_needs_matching_evidence
( tmp_path: Path, changes: dict[str, dict[str, object]], )
tests/golden/test_benchmark_card.py:1300
Method
test_benchmark_blocks_publication_on_incomplete_evidence
(self)
tests/reporting/test_incomplete_scans.py:112
Function
test_benchmark_cannot_publish_tier3_evidence_from_another_skill
(tmp_path: Path)
tests/reporting/test_advisory_skip_verdict.py:3261
Function
test_benchmark_capability_alone_keeps_default_output_byte_identical
(repository, benchmark_release, tmp_path)
tests/test_ci_onboarding_model_routing.py:274
Function
test_benchmark_classifies_similarity_check_as_tier2
()
tests/golden/test_benchmark_card.py:810
Function
test_benchmark_discloses_partial_required_tier1_skip
()
tests/golden/test_benchmark_card.py:624
Function
test_benchmark_discloses_partial_tier2_skips
( tier2_required: bool, skip_optional: bool, overall_status: str, tier_status: str, )
tests/golden/test_benchmark_card.py:666
Function
test_benchmark_does_not_blame_missing_signals_for_custom_failed_or_legacy_agents
()
tests/reporting/test_dimension_explanations.py:379
Function
test_benchmark_escapes_block_markdown_in_agent_labels
(display_name: str, escaped: str)
tests/golden/test_benchmark_card.py:1750
Function
test_benchmark_escapes_block_markdown_in_static_test_messages
()
tests/golden/test_benchmark_card.py:1761
Function
test_benchmark_escapes_exact_block_marker_before_model
(display_name: str)
tests/golden/test_benchmark_card.py:1775
Function
test_benchmark_explains_a_failed_with_skill_arm_below_the_table
()
tests/reporting/test_tier3_incomplete_arms.py:381
Function
test_benchmark_fail_card_matches_golden
()
tests/golden/test_benchmark_card.py:1146
Function
test_benchmark_handles_huge_tier3_metadata_without_crashing
(malformed_field: str)
tests/golden/test_benchmark_card.py:1072
Function
test_benchmark_handles_malformed_tier3_shapes_without_crashing
( malformed_field: str, expected_status: str, )
tests/golden/test_benchmark_card.py:1041
Function
test_benchmark_headline_matches_completed_agent_row
(peer_failed, quality_failed)
tests/reporting/test_tier3_scoped_reports.py:80
Function
test_benchmark_headline_without_completed_agent_names_missing_evidence
(run_verdict)
tests/reporting/test_tier3_scoped_reports.py:99
Function
test_benchmark_hides_absolute_finding_paths
(file_path: str, private_prefix: str)
tests/golden/test_benchmark_card.py:1571
Function
test_benchmark_infers_expected_skill_name_from_publication_target
()
tests/golden/test_benchmark_card.py:562
Function
test_benchmark_invalid_tier2_policy_fails_closed
()
tests/golden/test_benchmark_card.py:745
Function
test_benchmark_is_incomplete_when_required_tier2_is_missing
()
tests/golden/test_benchmark_card.py:484
Function
test_benchmark_is_incomplete_when_tier1_is_missing
()
tests/golden/test_benchmark_card.py:496
Function
test_benchmark_keeps_never_activated_wording_over_an_incomplete_baseline
()
tests/reporting/test_tier3_incomplete_arms.py:404
Function
test_benchmark_keeps_the_recorded_tier3_evaluator_version
()
tests/golden/test_benchmark_card.py:456
Function
test_benchmark_links_reject_unsafe_foreign_or_contradictory_entries
(change)
tests/ci/test_benchmark_report_links.py:73
Function
test_benchmark_lists_gate_before_findings
(with_findings: bool)
tests/reporting/test_quality_gate_reports.py:68
Function
test_benchmark_live_results_are_decision_first_and_unambiguous
()
tests/golden/test_benchmark_card.py:298
Function
test_benchmark_local_mode_does_not_claim_sandboxing
()
tests/golden/test_benchmark_card.py:1463
Function
test_benchmark_md_generated_for_skill
(tmp_path: Path)
tests/golden/test_policy_behavior.py:136
Function
test_benchmark_methodology_explains_meaning_evidence_and_baseline
(tmp_path: Path)
tests/reporting/test_dimension_explanations.py:106
Function
test_benchmark_methodology_states_when_no_baseline_ran
()
tests/reporting/test_dimension_explanations.py:126
Function
test_benchmark_missing_dimension_requires_a_successful_active_signal
()
tests/reporting/test_dimension_explanations.py:367
Function
test_benchmark_mixed_agents_keep_inconclusive_missing_baseline_and_measured_lift_distinct
()
tests/reporting/test_activation_benchmark_html_regressions.py:98
Function
test_benchmark_never_activated_scores_do_not_reconstruct_uplift
(baseline: bool, score: float)
tests/reporting/test_activation_benchmark_html_regressions.py:72
Function
test_benchmark_no_baseline_never_fabricates_uplift
()
tests/golden/test_benchmark_card.py:1154
Function
test_benchmark_normalizes_invalid_attempt_metadata_and_scans_cleanly
( tmp_path: Path, max_attempts: object, )
tests/golden/test_benchmark_card.py:1098
Function
test_benchmark_normalizes_retired_identity_in_relative_paths_and_non_label_text
(tmp_path: Path)
tests/golden/test_benchmark_card.py:1801
Function
test_benchmark_omits_internal_validation_profile
()
tests/golden/test_benchmark_card.py:1544
Function
test_benchmark_omits_missing_or_malformed_quality_config
(config: dict | None)
tests/reporting/test_quality_config_reporting.py:76
Function
test_benchmark_omits_missing_or_malformed_quality_min_score
(min_score: object)
tests/reporting/test_quality_config_reporting.py:87
Function
test_benchmark_pass_card_matches_golden
()
tests/golden/test_benchmark_card.py:1136
Function
test_benchmark_policy_resolves_each_key_across_source_precedence
()
tests/golden/test_benchmark_card.py:770
Function
test_benchmark_pr_adds_only_a_pinned_job_to_existing_feedback_file
(repository, benchmark_release, monkeypatch)
tests/test_ci_onboarding_model_routing.py:235
Function
test_benchmark_pr_refuses_gitlab_without_writing
(repository, benchmark_release)
tests/test_ci_onboarding_model_routing.py:262
Function
test_benchmark_pr_requires_its_own_capability
(repository, routing_release)
tests/test_ci_onboarding_model_routing.py:255
Function
test_benchmark_preserves_non_sandbox_skill_name
()
tests/golden/test_benchmark_card.py:1481
Function
test_benchmark_prioritizes_gates_within_blocking_findings_limit
()
tests/reporting/test_quality_gate_reports.py:82
Function
test_benchmark_publisher_is_separate_from_read_only_pr_feedback
()
tests/ci/test_gateway_benchmark_workflows.py:123
Function
test_benchmark_rebrands_retired_product_name_from_payload
(retired_name: str)
tests/golden/test_benchmark_card.py:1512
Function
test_benchmark_records_quality_config
(config: dict, expected: str)
tests/reporting/test_quality_config_reporting.py:64
Function
test_benchmark_records_quality_min_score
()
tests/reporting/test_quality_config_reporting.py:80
Function
test_benchmark_records_the_writer_version_when_no_tier3_version_is_recorded
()
tests/golden/test_benchmark_card.py:444
Function
test_benchmark_redacts_absolute_paths_from_dynamic_text
()
tests/golden/test_benchmark_card.py:1826
Function
test_benchmark_redacts_advisory_skip_path
()
tests/reporting/test_advisory_skip_verdict.py:3776
Function
test_benchmark_redacts_embedded_private_environment_labels
(metric_label: str)
tests/golden/test_benchmark_card.py:1889
Function
test_benchmark_redacts_file_uri_authorities
(tmp_path: Path, file_uri: str)
tests/golden/test_benchmark_card.py:1909
Function
test_benchmark_redacts_unicode_dash_private_identities
( separator: str, identity: str, )
tests/golden/test_benchmark_card.py:1523
Function
test_benchmark_rejects_invalid_markdown_skill_name
()
tests/golden/test_benchmark_card.py:1936
Function
test_benchmark_renders_dataset_size
(sufficiency)
tests/reporting/test_dataset_sufficiency_rendering.py:71
Function
test_benchmark_renders_recorded_negative_count_when_unclassified_cases_remain
()
tests/reporting/test_dataset_sufficiency_rendering.py:88
Function
test_benchmark_reports_correct_answers_under_overall
()
tests/test_tier3_attempt_verdict.py:412
Function
test_benchmark_required_skipped_tier2_is_incomplete
()
tests/golden/test_benchmark_card.py:582
Function
test_benchmark_requires_tier3_by_default
()
tests/golden/test_benchmark_card.py:430
Function
test_benchmark_sanitizes_agent_and_model_labels
()
tests/golden/test_benchmark_card.py:1635
← previous
next →
13,201–13,300 of 24,741, ranked by callers