MCPcopy Create free account

hub / github.com/NVIDIA/SkillEvaluator / functions

Functions24,741 in github.com/NVIDIA/SkillEvaluator

Functiontest_paired_pass_comparison_bounds_unpaired_case_id_diagnostics
()
tests/test_harbor_metrics_truth.py:1292
Functiontest_paired_pass_comparison_does_not_issue_exact_test_for_partial_pairing
()
tests/test_harbor_metrics_truth.py:1275
Functiontest_paired_pass_comparison_preserves_case_direction_and_exact_test
()
tests/test_harbor_metrics_truth.py:1087
Functiontest_paired_report_mode_is_both
(tmp_path: Path, skill: Path)
tests/tier3/test_skip_with_skill.py:529
Functiontest_paired_run_rejects_normalized_skill_owned_setup_before_environment_preflight
( monkeypatch: pytest.MonkeyPatch, tmp_path: Path, setup_key: str, )
tests/test_harbor_runner_environment.py:2057
Functiontest_paired_runner_still_suffixes_both_arms
(skill: Path, monkeypatch: pytest.MonkeyPatch)
tests/tier3/test_skip_with_skill.py:335
Functiontest_pairing_covers_same_cases_and_excludes_judge_mismatch_per_metric
()
tests/tier3/test_metric_applicability_producer.py:90
Functiontest_pairing_requires_same_attempt_not_just_same_case
(payload)
tests/tier3/test_external_metrics.py:196
Methodtest_pairwise_comparison_limit_fails_before_comparing
(self, monkeypatch)
tests/embedding/test_registry.py:487
Functiontest_pairwise_judges_do_not_inherit_another_arms_fallback
()
tests/tier3/test_private_comparison_contracts.py:234
Methodtest_pairwise_match_limit_fails_closed
(self, monkeypatch)
tests/embedding/test_registry.py:501
Functiontest_pairwise_policy_exclusion_bounds_count_every_withheld_entry
()
tests/reporting/test_private_runtime_projection.py:384
Functiontest_pairwise_policy_exclusions_survive_without_a_loose_parts_ladder
(member_skills)
tests/reporting/test_private_runtime_projection.py:334
Methodtest_pairwise_scan_normalizes_each_vector_once
(self, monkeypatch)
tests/embedding/test_registry.py:473
Functiontest_parallel_catalog_applies_the_registry_id_conflict
(tmp_path: Path)
tests/golden/test_policy_behavior.py:217
Functiontest_parallel_scan_matches_sequential_rows_logs_annotations_and_reports
(tmp_path, capsys)
tests/ci/test_run_tier1.py:1278
Functiontest_parallel_subagents_are_credited_by_their_agent_id
The plugin agent and a general-purpose agent start together; the plugin agent writes the artifact.
tests/tier3/test_f90_signals_handoff.py:265
Functiontest_parallel_timestamp_tools_use_longest_wall_time
()
tests/tier3/test_trajectory_timing.py:204
Functiontest_parallel_tool_choice_is_preserved_for_responses_and_anthropic_requests
()
tests/test_nvidia_build_bridge.py:2727
Functiontest_parent_agent_component_cannot_escape_run_directory
(tmp_path: Path)
tests/test_tier3_case_summary.py:1922
Functiontest_parent_directory_swap_cannot_redirect_staging_or_write
(repository, monkeypatch, tmp_path)
tests/test_ci_onboarding_writes.py:145
Functiontest_parent_segment_after_a_symlink_does_not_lose_the_root
(tmp_path: Path)
tests/harness/test_overlay.py:186
Functiontest_parent_segment_after_a_symlink_goes_to_the_real_parent
(tmp_path: Path, monkeypatch: pytest.MonkeyPatch)
tests/harness/test_overlay.py:171
Functiontest_parent_segments_do_not_make_a_false_root
(tmp_path: Path)
tests/harness/test_overlay.py:153
Methodtest_parent_workflow_mismatch_warning
Test warning when parent_workflow doesn't match workflow name.
tests/validators/test_workflows_schema.py:468
Functiontest_parity_read_budget_rejects_before_an_extra_secure_read
(tmp_path, monkeypatch, limit, value)
tests/tier3/test_private_comparison_staging.py:224
Functiontest_parity_rejects_symlink_content_even_when_all_arms_match
(tmp_path)
tests/tier3/test_private_comparison_staging.py:181
Methodtest_parse_checks_a_list_of_known_case_ids_in_bounded_time
(self)
tests/evaluation/test_judges.py:1369
Methodtest_parse_does_not_trust_direct_or_custom_spoofed_invocation_booleans
( self, source: str | None, )
tests/evaluation/test_judges.py:724
Methodtest_parse_does_not_use_explicit_custom_metric_as_legacy_routing_grounding
(self)
tests/evaluation/test_judges.py:757
Functiontest_parse_environment_kwargs_empty_key
Reject arguments with an empty key.
tests/test_harbor_gke_mode.py:651
Functiontest_parse_environment_kwargs_missing_equals
Reject arguments missing the equals separator.
tests/test_harbor_gke_mode.py:645
Functiontest_parse_environment_kwargs_permits_benign_token_keys
Verify parse_environment_kwargs permits benign token count, rate, and tokenizer keys.
tests/test_harbor_gke_mode.py:845
Functiontest_parse_environment_kwargs_rejects_credential_keys
Verify parse_environment_kwargs rejects sensitive credential keys with ValueError.
tests/test_harbor_gke_mode.py:821
Functiontest_parse_environment_kwargs_valid
Parse valid --ek key=value arguments with whitespace trimming and JSON coercion.
tests/test_harbor_gke_mode.py:634
Functiontest_parse_jsonl_and_wrapper
()
tests/test_trace_import.py:54
Methodtest_parse_limit_row_on_the_manifest_stays_incomplete
SkillSpector 2.13.4 reads a hook "timeout" key as a shell wrapper and records a parse limit. The scan is recorded as incomplete, and the Crit
tests/validators/test_skillspector_hook_surface.py:897
Functiontest_parse_name_status_z_rejects_malformed_records
(payload: bytes)
tests/test_ci_change_classifier.py:181
Functiontest_parse_name_status_z_returns_every_changed_path
(payload: bytes, expected: list[bytes])
tests/test_ci_change_classifier.py:167
Methodtest_parse_negative_control_uses_strict_evidence_before_legacy_numeric_fallback
( self, trial: dict, accepted: bool, )
tests/evaluation/test_judges.py:646
Methodtest_parse_preserves_negative_control_warning_with_failed_routing_evidence
(self)
tests/evaluation/test_judges.py:341
Methodtest_parse_preserves_ordered_grounding_for_positive_general_claim
(self)
tests/evaluation/test_judges.py:817
Methodtest_parse_preserves_unrelated_insights_and_nonremoval_test_improvements
(self)
tests/evaluation/test_judges.py:474
Methodtest_parse_rejects_case_ids_hidden_beyond_the_grounding_text_bound
(self)
tests/evaluation/test_judges.py:576
Methodtest_parse_rejects_general_claim_with_negative_control_semantics
( self, title: str, message: str, )
tests/evaluation/test_judges.py:548
Methodtest_parse_rejects_original_general_claim_with_empty_evidence_ids
(self)
tests/evaluation/test_judges.py:516
Methodtest_parse_rejects_special_claim_without_grounding
( self, evidence_case_ids: list[str], )
tests/evaluation/test_judges.py:381
Methodtest_parse_rejects_unintended_skill_use_paraphrase_without_routing_evidence
( self, claim_type: str, )
tests/evaluation/test_judges.py:412
Methodtest_parse_rejects_unrelated_case_removal_paraphrase_without_routing_evidence
( self, claim_type: str, )
tests/evaluation/test_judges.py:443
Methodtest_parse_requires_every_cited_negative_control_to_have_failure_evidence
(self)
tests/evaluation/test_judges.py:687
Methodtest_parse_requires_exact_unique_known_case_ids_named_in_prose
( self, evidence_case_ids: list[str], message: str, )
tests/evaluation/test_judges.py:608
Methodtest_parse_response_valid
(self)
tests/validators/test_rubric_eval.py:130
Functiontest_parse_retry_after_http_date_future
Verify parse_retry_after handles RFC-7231 HTTP dates in UTC.
tests/test_retry.py:81
Functiontest_parse_retry_after_http_date_past
Verify parse_retry_after clamps past dates to 0.0.
tests/test_retry.py:90
Functiontest_parse_retry_after_naive_date
Verify parse_retry_after correctly handles offset-naive parsed datetimes without raising.
tests/test_retry.py:99
Functiontest_parse_retry_after_numeric_and_fallback
Verify parse_retry_after handles numeric strings, negatives, and fallbacks.
tests/test_retry.py:72
Methodtest_parse_rules_manifest
Test parse_rules_manifest utility function.
tests/validators/test_rules_schema.py:216
Methodtest_parse_rules_manifest_invalid
Test parse_rules_manifest returns None for invalid file.
tests/validators/test_rules_schema.py:224
Functiontest_parse_skill_does_not_truncate_multiline_quoted_description
A quoted scalar spanning lines was silently cut at the first line.
tests/tier3/test_generate_dataset_results.py:583
Functiontest_parse_skill_falls_back_to_defaults_on_malformed_frontmatter
Unparseable YAML must degrade to the directory name and an empty description.
tests/tier3/test_generate_dataset_results.py:589
Functiontest_parse_skill_folds_block_scalar_description
``description: >-`` must fold, not be captured as the literal indicator.
tests/tier3/test_generate_dataset_results.py:568
Functiontest_parse_skill_includes_tools_dir_scripts
(tmp_path)
tests/tier3/test_generate_dataset_results.py:672
Functiontest_parse_skill_keeps_literal_block_scalar_newlines
(tmp_path)
tests/tier3/test_generate_dataset_results.py:578
Functiontest_parse_tool_list_respects_parentheses_and_separators
()
tests/validators/test_plugin_component_risk.py:67
Functiontest_parse_tool_list_returns_every_entry
()
tests/validators/test_plugin_hook_risk_bounds.py:289
Methodtest_parse_treats_overflowing_legacy_numeric_evidence_as_unknown
(self)
tests/evaluation/test_judges.py:790
Functiontest_parse_vertex_openapi_metadata
Verify extraction of project and location from Vertex OpenAPI base URL.
tests/test_harbor_runtime_preflight.py:4359
Methodtest_parse_workflows_manifest
Test parse_workflows_manifest utility function.
tests/validators/test_workflows_schema.py:323
Methodtest_parses_plain_json
(self, monkeypatch: pytest.MonkeyPatch)
tests/inference/test_llm_client.py:810
Functiontest_partial_agent_eval_result_carries_engine_errors
(monkeypatch, tmp_path)
tests/test_commands.py:2771
Functiontest_partial_agent_eval_result_rejects_stale_results
(monkeypatch, tmp_path)
tests/test_commands.py:2808
Functiontest_partial_and_unknown_evidence_does_not_claim_complete_or_zero
()
tests/reporting/test_evidence_views.py:57
Functiontest_partial_arm_retains_scored_evidence_without_enabling_quality
( tmp_path: Path, partial_variant: str, score: float )
tests/test_harbor_collector_runtime_failures.py:885
Functiontest_partial_atomic_publication_preserves_signed_output_and_reruns
( tmp_path: Path, monkeypatch: pytest.MonkeyPatch, force_fallback: bool, )
tests/test_harbor_output_provenance.py:518
Functiontest_partial_baseline_only_or_contradictory_execution_remains_incomplete
(mutate)
tests/ci/test_tier3_execution_complete.py:128
Functiontest_partial_budget_run_collects_real_harbor_results
(monkeypatch, tmp_path, denial_mode)
tests/tier3/test_run_budget.py:327
Functiontest_partial_case_selection_cannot_certify_publication
(tmp_path: Path)
tests/reporting/test_advisory_skip_verdict.py:2855
Functiontest_partial_composition_shows_only_supplied_fields_and_reason
()
tests/reporting/test_native_evidence.py:78
Functiontest_partial_coverage_sums_only_measured_attempts_and_never_estimates
()
tests/tier3/test_token_usage.py:246
Functiontest_partial_credit_requires_the_script_to_be_named
A walk that cannot resolve a command which never names the script has learned nothing about that script. A bare ``cd`` loses track of the dire
tests/tier3/test_script_invocation_evidence.py:744
Functiontest_partial_error_prose_is_not_misidentified_as_a_complete_legacy_blob
()
tests/reporting/test_insights_view.py:263
Functiontest_partial_evidence_is_retained_without_turning_it_into_a_pass
(monkeypatch, terminal)
tests/validators/test_skillspector_diagnostics.py:47
Functiontest_partial_execution_failure_reports_coverage_without_quality_claims
(tmp_path: Path)
tests/test_harbor_html_report_failures.py:263
Functiontest_partial_expected_attempt_counts_remain_visible
()
tests/reporting/test_final_render_context.py:227
Functiontest_partial_extra_case_count_without_expected_ids_clears_scores
(tmp_path: Path, variant: str)
tests/test_harbor_collector_runtime_failures.py:3006
Functiontest_partial_failed_case_requires_all_attempts
( tmp_path: Path, variant: str, case_detail_cap: int, monkeypatch: pytest.MonkeyPatch )
tests/test_harbor_collector_runtime_failures.py:2980
Functiontest_partial_failed_run_still_exposes_known_configuration_change
(tmp_path)
tests/test_tier3_history.py:375
Functiontest_partial_headers_time_out_without_exceeding_the_worker_bound
( bridge_services: _BridgeServices, monkeypatch: pytest.MonkeyPatch )
tests/test_nvidia_build_bridge.py:1671
Functiontest_partial_integrity_failure_clears_scores
(tmp_path: Path, variant: str, corruption: str)
tests/test_harbor_collector_runtime_failures.py:2946
Methodtest_partial_llm_failure_preserves_valid_duplicate_finding
( self, mock_embed, _mock_llm, mock_analyze, tmp_path: Path )
tests/deduplication/intra_skill/test_intra_skill_validator.py:1209
Methodtest_partial_llm_verdicts_are_reported_as_partial
A verifier response covering only some findings must not claim full confirmation.
tests/validators/test_security.py:6011
Functiontest_partial_load_does_not_trust_lift_without_recorded_exclusions
( tmp_path: Path, monkeypatch: pytest.MonkeyPatch, recorded_mixed: dict | None )
tests/test_judge_lift_integrity.py:306
Functiontest_partial_missing_metrics_never_become_zero_or_partial_total
()
tests/reporting/test_dashboard_data.py:107
Functiontest_partial_native_agent_llm_does_not_report_subtotal
()
tests/tier3/test_trajectory_timing.py:129
Functiontest_partial_native_tool_timing_does_not_report_subtotal
()
tests/tier3/test_trajectory_timing.py:143
Functiontest_partial_or_invalid_step_counters_do_not_become_totals
(tmp_path)
tests/tier3/test_private_usage_recovery_review2.py:88
Functiontest_partial_or_mismatched_cases_do_not_get_timing_deltas
(baseline, complete)
tests/tier3/test_resource_usage.py:163
Functiontest_partial_or_untyped_attempt_outcomes_do_not_invent_a_pass_count
(attempts)
tests/reporting/test_report_readability.py:107
Functiontest_partial_pass_at_k_case_without_attempts_skipped_still_renders
(tmp_path: Path)
tests/reporting/test_unified_tier3_report.py:3222
Functiontest_partial_reports_do_not_rank_agents_scored_on_different_metrics
()
tests/reporting/test_unified_tier3_report.py:1326
← previousnext →19,901–20,000 of 24,741, ranked by callers