jesse-uxandClaude Code
aa46da1016
Add date-isolated caches and regression coverage, align scoring identity, and freeze full research reruns while preserving historical artifacts. Record unresolved cache/receipt identity and end-to-end acceptance gaps for branch review only. Co-Authored-By: Claude Code <noreply@anthropic.com>
90 lines
3.9 KiB
JSON
90 lines
3.9 KiB
JSON
{
|
|
"scope": "cross_midnight_regression_acceptance",
|
|
"baseline_commit": "03cba4780a220b132cf4f06d22e14608aaf9ad3c",
|
|
"baseline_test_tree": "932f2fffba820a47fa4e1a7b825d6b38c310a4d6",
|
|
"baseline_test_tree_reason": "The two later commits contain task documentation only; baseline executable sources are unchanged.",
|
|
"python_globs": ["test_rectification_*.py", "test_active_rectification_*.py", "test_minute_rectification_*.py"],
|
|
"baseline": {
|
|
"collected": 284,
|
|
"passed": 280,
|
|
"failed": 4,
|
|
"failure_ids": [
|
|
"tests/test_active_rectification_api.py::test_long_real_conversation_reaches_vedastro_after_local_range_is_narrow",
|
|
"tests/test_active_rectification_selector.py::test_selector_changes_do_not_change_legacy_or_v5_score_bytes",
|
|
"tests/test_minute_rectification_development.py::test_v3_development_result_stays_shadow_only",
|
|
"tests/test_minute_rectification_holdout_validator.py::test_frozen_implementation_hash_matches_manifest"
|
|
]
|
|
},
|
|
"current": {
|
|
"collected": 300,
|
|
"passed": 296,
|
|
"failed": 4,
|
|
"seconds": 609.52,
|
|
"exit_code": 1,
|
|
"failure_ids": [
|
|
"tests/test_active_rectification_api.py::test_long_real_conversation_reaches_vedastro_after_local_range_is_narrow",
|
|
"tests/test_active_rectification_selector.py::test_selector_changes_do_not_change_legacy_or_v5_score_bytes",
|
|
"tests/test_minute_rectification_development.py::test_v3_development_result_stays_shadow_only",
|
|
"tests/test_minute_rectification_holdout_validator.py::test_frozen_implementation_hash_matches_manifest"
|
|
],
|
|
"baseline_only_failures": [],
|
|
"current_only_failures": [],
|
|
"baseline_failure_assertion_values_unchanged": true,
|
|
"full_suite_passed": false,
|
|
"zero_new_failures": true
|
|
},
|
|
"metadata_alignment_independent_targeted": {
|
|
"passed": 25,
|
|
"failed": 0,
|
|
"seconds": 2.04
|
|
},
|
|
"pre_metadata_alignment_run": {
|
|
"collected": 300,
|
|
"passed": 294,
|
|
"failed": 6,
|
|
"baseline_failures_unchanged": true,
|
|
"new_failure_ids": [
|
|
"tests/test_rectification_engine_memoization.py::test_score_candidates_matches_baseline_golden",
|
|
"tests/test_rectification_relative_support.py::RelativeSupportScaleTest::test_holdout_gate_keeps_proportional_default"
|
|
],
|
|
"observed_new_failures": [
|
|
"decision_receipt.representative_candidate_id differs from the existing golden; root cause under verification",
|
|
"ALGORITHM_VERSION is rectification-v5-matrix-scoring-8; existing assertion expects rectification-v5-matrix-scoring-7"
|
|
]
|
|
},
|
|
"metadata_alignment": {
|
|
"reason": "Authorized algorithm identity bump from rectification-v5-matrix-scoring-7 to rectification-v5-matrix-scoring-8",
|
|
"golden_updated_paths": [
|
|
"decision_receipt.representative_candidate_id",
|
|
"candidate_feature_snapshot.algorithm_version"
|
|
],
|
|
"golden_source": "Two identity leaves extracted from the real engine after old/new identity A/B comparison",
|
|
"all_other_golden_leaves_equal_to_git_baseline": true,
|
|
"comparison_logic_unchanged": true,
|
|
"relative_support_and_policy_assertions_unchanged": true,
|
|
"version_literal_assertion_updated": true
|
|
},
|
|
"final_integrity_and_privacy_targeted": {
|
|
"passed": 86,
|
|
"failed": 0,
|
|
"seconds": 13.17
|
|
},
|
|
"independent_research_audit": {
|
|
"passed": true,
|
|
"scope": "Real source hashes, archived bytes, 900/20 coverage and arithmetic summaries, 45 Markdown cells and final report references; not a second scoring rerun or end-to-end deployment test"
|
|
},
|
|
"preflight": {
|
|
"remote_verified": true,
|
|
"fragment_scan_ok": true,
|
|
"external_engine_adapters_ok": true,
|
|
"passed": false,
|
|
"failed_test": "test_preflight_fragment_scan_reports_authority_layers_and_risk_buckets"
|
|
},
|
|
"quick": {
|
|
"baseline_passed": false,
|
|
"current_passed": false,
|
|
"same_blocker": "interpretation_source_inventory_gate.py: ModuleNotFoundError: No module named 'mcp'"
|
|
},
|
|
"deployment_verified": false
|
|
}
|