Files
cdsl-cad/backend/live-evals/20260831T212855Z/report.json
T
2026-09-01 14:10:23 +08:00

1432 lines
50 KiB
JSON

{
"status": "failed",
"author": {
"provider": "openai",
"model": "gpt-5.4-mini"
},
"author_request_identity": {
"provider": "openai",
"model": "gpt-5.4-mini",
"api_style": "responses",
"reasoning_effort": "medium",
"sampling": {
"temperature": null
}
},
"reviewer": {
"provider": "openai",
"model": "gpt-5.5"
},
"author_capability": {
"schema_hash": "3935c6f40d3b8b9bb7c5672cdea37049a3cd9eb57c9f722b738397a45d77490c",
"tool_count": 28,
"supported": true,
"failures": [],
"usage": {
"prompt_tokens": 133729,
"completion_tokens": 3822
},
"mode": "openai_compatible_tool_calling",
"probe_unavailable": false
},
"reviewer_capability": {
"schema_hash": "3935c6f40d3b8b9bb7c5672cdea37049a3cd9eb57c9f722b738397a45d77490c",
"tool_count": 28,
"supported": true,
"failures": [],
"usage": {
"prompt_tokens": 133729,
"completion_tokens": 1667
},
"mode": "openai_compatible_tool_calling",
"probe_unavailable": false
},
"structured_output_mode": {
"author": "openai_compatible_tool_calling",
"reviewer": "openai_compatible_tool_calling"
},
"git_revision": "7533b298f1a23ed5d4c8a63982b2984258426b52",
"protocol_version": "3.0",
"runtime_profile_sha256": "bc2e2110a49929d96ad1e0d1996b2579ff1b56c80fd822423107bee7e560187e",
"operation_contracts": [
{
"atomic_id": "chamfer",
"contract_hash": "eb5d3b87d055edf18fd8d7398cd104f5edf2bb9ae6994fc5eb870a3ab685d678",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "extrude_add_blind",
"contract_hash": "fa9ffc9fd2141453fa18a389813dde2e2ef3fb4c7ef5d05e61d51d614309e95f",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "extrude_add_two_sided",
"contract_hash": "35de3efa8ec4d4a1a37904f0c34084bb3fd2da07fa479a2b6d35e4837b210e9d",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "extrude_cut_blind",
"contract_hash": "fe00ac225362469afe00cd4aee9b48259e8ceb74aa11d9a54ff038c6d12f0d50",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "fillet",
"contract_hash": "db31dd9c749707cc9453fc248d7ca86ef4faaaf15376a40bd659c325b037c878",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "hole_blind",
"contract_hash": "f62e12603feeca6d7e83acdab651fcb023e08a46c39fd1509e9dcb81d4f0c721",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "hole_counterbore",
"contract_hash": "15a56094125780177ad75040d160430cc9f0a97928214bd0553acddfbff9aa16",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "hole_countersink",
"contract_hash": "84b98d26d2a836105cf383bdfb1e733ea16bfa41935a08a48cf5c4d6c71ad49f",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "hole_wizard",
"contract_hash": "35d56dd42ee933e0fe59f9cfc33391b25844bd270a8909703af7855ad6bd25f2",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "pattern_linear",
"contract_hash": "ecf393713de82ac30ca326719774ed8315030d9d980d1370c95003505ce28471",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "pattern_mirror",
"contract_hash": "ec014e6c1639d98e2a50a26c88256ad0a9ad0fd8a027cd57b710c07d8bf3ecb8",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "reference_axis",
"contract_hash": "2ebeda16a1fc50aefb0fa923794f43e609aca07dbd5059968824dfcf97532aaa",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "reference_plane",
"contract_hash": "86968365856f972fdacef1a739be379458a563be5763c97d4f18e6b93d14ef55",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "revolve_add",
"contract_hash": "8c0c5e842fb868cad4dc37f5d195d0d8971878bc5c23a7eb9017d829ea36c6db",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "revolve_cut",
"contract_hash": "101c9d285c46cf8c6d3bba516cde2bf9002eee0e9cc62d66cade676c3a71db56",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "sphere_add",
"contract_hash": "ef855cadd1f295b16ebbf11538557efaf790ff0c44262c9ae61e769242844c95",
"contract_version": "3.0",
"registry_revision": "1.3.1"
}
],
"verifier_registry_version": "cad.verifier-registry.v1",
"verifier_schema_hash": "7a05abe600903feabb57bc8c77e26042c28ca13fe5d5caeb94f37351ce8adf97",
"token_comparison": {
"schema_version": "cad.token-comparison.v1",
"status": "not_required"
},
"baseline_report": "",
"results": [
{
"scenario": "three_hole_linkage",
"repetition": 1,
"success": false,
"outcome": "failed",
"started_at": "2026-08-31T21:33:15.791574+00:00",
"finished_at": "2026-08-31T21:35:04.607001+00:00",
"duration_ms": 108815,
"terminal": {
"taskId": "cad_61118b0b03ba",
"lifecycle": "waiting_for_user",
"code": "WAITING_FOR_USER",
"message": "Requirements review limit reached; a user decision is required."
},
"projection": {
"schema_version": "3.0",
"task_id": "cad_61118b0b03ba",
"phase": "WAITING_FOR_USER",
"lifecycle": "waiting_for_user",
"state_version": 10,
"active_revision": "",
"current_revision": "",
"published_revision": "",
"pending_action": null,
"active_candidate_id": "",
"repair_required": false,
"last_error": "WAITING_FOR_USER",
"retry_from_phase": "",
"requirements_draft_path": "documents/requirements-draft-v3-1e78fc5e001e-cad_61118b0b03ba_inv_c4f29c79aef.json",
"requirements_review_path": "documents/requirements-review-95eef23b7115-cad_61118b0b03ba_inv_ba791c6e359.json",
"requirements_contract_path": "",
"action_ledger_summary": [
{
"sequence": 1,
"at": "2026-08-31 21:33:29",
"draft_path": "documents/requirements-draft-v1-9569137a152d-cad_61118b0b03ba_inv_cbe0d9057fa.json",
"draft_revision": 1,
"event": "requirements_draft_updated",
"invocation_id": "cad_61118b0b03ba_inv_cbe0d9057fa9c392",
"item_count": 7
},
{
"sequence": 2,
"at": "2026-08-31 21:33:34",
"draft_revision": 1,
"event": "requirements_review_requested",
"invocation_id": "cad_61118b0b03ba_inv_06bbea193838a2fc"
},
{
"sequence": 3,
"at": "2026-08-31 21:33:57",
"event": "requirements_review_revise",
"invocation_id": "cad_61118b0b03ba_inv_e2c8d7369fe13f8e",
"review_path": "documents/requirements-review-ad5c325ac148-cad_61118b0b03ba_inv_e2c8d7369fe.json"
},
{
"sequence": 4,
"at": "2026-08-31 21:34:09",
"draft_path": "documents/requirements-draft-v2-61b42ee7c0c5-cad_61118b0b03ba_inv_d94f7195643.json",
"draft_revision": 2,
"event": "requirements_draft_patched",
"invocation_id": "cad_61118b0b03ba_inv_d94f71956434ed71",
"item_count": 7
},
{
"sequence": 5,
"at": "2026-08-31 21:34:12",
"draft_revision": 2,
"event": "requirements_review_requested",
"invocation_id": "cad_61118b0b03ba_inv_c7caf81afa71f667"
},
{
"sequence": 6,
"at": "2026-08-31 21:34:19",
"event": "requirements_evaluation_oracle_revise",
"invocation_id": "cad_61118b0b03ba_inv_576f30faa568cb0c",
"missing_claims": [
{
"claim_kind": "collinear_through_bore_chain",
"expected": {
"adjacent_distances_mm": [
60,
80
],
"diameter_mm": 12,
"tolerance_mm": 0.1
}
}
],
"oracle_path": "documents/evaluation-contract-oracle-e9f00ebbf0e1.json",
"review_path": "documents/requirements-review-83c51572391b-cad_61118b0b03ba_inv_576f30faa56.json"
},
{
"sequence": 7,
"at": "2026-08-31 21:34:36",
"draft_path": "documents/requirements-draft-v3-1e78fc5e001e-cad_61118b0b03ba_inv_c4f29c79aef.json",
"draft_revision": 3,
"event": "requirements_draft_patched",
"invocation_id": "cad_61118b0b03ba_inv_c4f29c79aef5c797",
"item_count": 7
},
{
"sequence": 8,
"at": "2026-08-31 21:34:40",
"draft_revision": 3,
"event": "requirements_review_requested",
"invocation_id": "cad_61118b0b03ba_inv_2443bcac857a1442"
},
{
"sequence": 9,
"at": "2026-08-31 21:35:04",
"event": "requirements_review_revise",
"invocation_id": "cad_61118b0b03ba_inv_ba791c6e359e7a0c",
"review_path": "documents/requirements-review-95eef23b7115-cad_61118b0b03ba_inv_ba791c6e359.json"
},
{
"sequence": 10,
"at": "2026-08-31 21:35:04",
"draft_revision": 3,
"event": "requirements_review_limit_reached"
}
],
"revisions": []
},
"usage": {
"calls": 11,
"prompt_tokens": 68755,
"completion_tokens": 4585,
"context_chars": 52489,
"records": [
{
"cache_hit": false,
"completion_tokens": 774,
"context_chars": 738,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 6103,
"provider_id": "openai",
"raw_arguments_hash": "8fbb73db04f9d70dd7e37dc17b29a9769f032e019356f8854d89eb0e9e82323c",
"retry_reason": "",
"tool": "submit_requirements_draft_batch",
"total_tokens": 6877,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 120,
"context_chars": 4428,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 5614,
"provider_id": "openai",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"retry_reason": "",
"tool": "finalize_requirements_draft",
"total_tokens": 5734,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 258,
"context_chars": 5106,
"model_id": "gpt-5.5",
"prompt_tokens": 6079,
"provider_id": "openai",
"raw_arguments_hash": "cf6c2f9e01e7bd94362e092964f28710a1b5c3434fbafad5751029456d8b80e6",
"retry_reason": "",
"role": "reviewer",
"tool": "review_requirements",
"total_tokens": 6337,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 663,
"context_chars": 5545,
"model_id": "gpt-5.5",
"prompt_tokens": 6175,
"provider_id": "openai",
"raw_arguments_hash": "a435608eaedeadc4928fde0cc5dda4c2a3ce9b87de7eea978531fdeadef44c67",
"retry_reason": "",
"role": "reviewer",
"tool": "review_requirements",
"total_tokens": 6838,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 640,
"context_chars": 6624,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 7782,
"provider_id": "openai",
"raw_arguments_hash": "6193c963abbf512fa5e35a8341c03519eaac38c4625873d564d2bc296267c724",
"retry_reason": "",
"tool": "patch_requirements_draft",
"total_tokens": 8422,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 18,
"context_chars": 4281,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 5566,
"provider_id": "openai",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"retry_reason": "",
"tool": "finalize_requirements_draft",
"total_tokens": 5584,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 221,
"context_chars": 4973,
"model_id": "gpt-5.5",
"prompt_tokens": 6031,
"provider_id": "openai",
"raw_arguments_hash": "7b225d8587ad1f268c063230c59fdac1a294758f12328af9d0315046acb5b2a1",
"retry_reason": "",
"role": "reviewer",
"tool": "review_requirements",
"total_tokens": 6252,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 922,
"context_chars": 6143,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 7681,
"provider_id": "openai",
"raw_arguments_hash": "8d1b6e26d94c397559dc1df3462b2d3ae1c3bee2849bde8deee99e0617c14301",
"retry_reason": "",
"tool": "patch_requirements_draft",
"total_tokens": 8603,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 82,
"context_chars": 4276,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 5566,
"provider_id": "openai",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"retry_reason": "",
"tool": "finalize_requirements_draft",
"total_tokens": 5648,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 262,
"context_chars": 4968,
"model_id": "gpt-5.5",
"prompt_tokens": 6031,
"provider_id": "openai",
"raw_arguments_hash": "8f9388eb00532e29c7ea722eb4b27a5f65c1b2b9d72948c2b153e4f473a74f31",
"retry_reason": "",
"role": "reviewer",
"tool": "review_requirements",
"total_tokens": 6293,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 625,
"context_chars": 5407,
"model_id": "gpt-5.5",
"prompt_tokens": 6127,
"provider_id": "openai",
"raw_arguments_hash": "df0a30724f7a0e8f6bfaa7d05655b84aa6a59864fb03ef0352fd434f3332c19e",
"retry_reason": "",
"role": "reviewer",
"tool": "review_requirements",
"total_tokens": 6752,
"usage_available": true
}
]
},
"checks": {
"expected_terminal_phase": false,
"token_budget": true,
"call_budget": true,
"author_turn_budget": true,
"reviewer_turn_budget": true,
"required_claims": false,
"acceptance_contract_coverage": false,
"required_operations": false,
"required_operation_alternative": false,
"immutable_artifacts": false,
"required_artifact_evidence": false,
"artifact_manifest": true,
"action_ledger": true,
"unique_revisions": true,
"deterministic_claims_pass": false,
"raw_argument_audit": true,
"no_schema_or_decision_rejections": false
},
"acceptance_coverage": {
"required_claim_kinds": [
"bbox_rank_dimension_mm",
"collinear_through_bore_chain",
"solid_count_equals",
"through_cylindrical_bore",
"visual"
],
"covered_claim_kinds": [],
"required_claims": [
{
"claim_kind": "solid_count_equals",
"expected": {
"value": 1
}
},
{
"claim_kind": "bbox_rank_dimension_mm",
"expected": {
"rank": "minimum",
"value": 10
}
},
{
"claim_kind": "through_cylindrical_bore",
"expected": {
"diameter_mm": 12,
"count": 3
}
},
{
"claim_kind": "collinear_through_bore_chain",
"expected": {
"diameter_mm": 12,
"adjacent_distances_mm": [
60,
80
],
"tolerance_mm": 0.1
}
},
{
"claim_kind": "visual",
"expected": {}
}
],
"missing_claims": [
{
"claim_kind": "solid_count_equals",
"expected": {
"value": 1
}
},
{
"claim_kind": "bbox_rank_dimension_mm",
"expected": {
"rank": "minimum",
"value": 10
}
},
{
"claim_kind": "through_cylindrical_bore",
"expected": {
"diameter_mm": 12,
"count": 3
}
},
{
"claim_kind": "collinear_through_bore_chain",
"expected": {
"diameter_mm": 12,
"adjacent_distances_mm": [
60,
80
],
"tolerance_mm": 0.1
}
},
{
"claim_kind": "visual",
"expected": {}
}
],
"validation_capability_gaps": [
{
"id": "linkage_outer_circles",
"description": "32 mm outer circles with smoothly connected segments"
}
],
"complete": false
},
"failure_attribution": {
"layer": "model_format_or_decision",
"reason_code": "AUTHOR_FORMAT_INVALID",
"evidence_codes": [
"AUTHOR_FORMAT_INVALID",
"WAITING_FOR_USER"
],
"failed_checks": [
"expected_terminal_phase",
"required_claims",
"acceptance_contract_coverage",
"required_operations",
"required_operation_alternative",
"immutable_artifacts",
"required_artifact_evidence",
"deterministic_claims_pass",
"no_schema_or_decision_rejections"
]
},
"rejection_codes": [
"AUTHOR_FORMAT_INVALID",
"AUTHOR_FORMAT_INVALID"
],
"schema_rejection_count": 2,
"retry_count": 2,
"rollback_count": 0,
"candidate_ids": [],
"revision_ids": [],
"final_claim_results": [],
"redacted_correlation_ids": [
"36c10a2456241ab335db",
"471b5dc2e6d8f6fe3f09",
"91c9bb6407a468a4a83b",
"0a01e51e65bc8c10cd4c",
"ee3ecfd2549b57452a56",
"9aad4de9aeb8e2f4211f",
"e64a2c2e1177a13c338b",
"4c3eb8a266c1dfe574ff",
"ffd7ab6fe688f66e6408"
],
"tool_audits": [
{
"audit_id": 1,
"at": "2026-08-31 21:33:29",
"actor": "author",
"tool": "submit_requirements_draft_batch",
"raw_arguments_hash": "8fbb73db04f9d70dd7e37dc17b29a9769f032e019356f8854d89eb0e9e82323c",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_61118b0b03ba:root:v0",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_61118b0b03ba:root:v0",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "submit_requirements_draft_batch",
"single_allowed_call": true
},
{
"audit_id": 2,
"at": "2026-08-31 21:33:34",
"actor": "author",
"tool": "finalize_requirements_draft",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_61118b0b03ba:root:v1",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_61118b0b03ba:root:v1",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "finalize_requirements_draft",
"single_allowed_call": true
},
{
"audit_id": 3,
"at": "2026-08-31 21:33:42",
"actor": "reviewer",
"tool": "review_requirements",
"raw_arguments_hash": "cf6c2f9e01e7bd94362e092964f28710a1b5c3434fbafad5751029456d8b80e6",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_61118b0b03ba:root:v2",
"phase": "REVIEWING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_61118b0b03ba:root:v2",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "review_requirements",
"single_allowed_call": true
},
{
"audit_id": 4,
"at": "2026-08-31 21:33:57",
"actor": "reviewer",
"tool": "review_requirements",
"raw_arguments_hash": "a435608eaedeadc4928fde0cc5dda4c2a3ce9b87de7eea978531fdeadef44c67",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_61118b0b03ba:root:v2",
"phase": "REVIEWING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_61118b0b03ba:root:v2",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "review_requirements",
"single_allowed_call": true
},
{
"audit_id": 5,
"at": "2026-08-31 21:34:09",
"actor": "author",
"tool": "patch_requirements_draft",
"raw_arguments_hash": "6193c963abbf512fa5e35a8341c03519eaac38c4625873d564d2bc296267c724",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_61118b0b03ba:root:v3",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_61118b0b03ba:root:v3",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "patch_requirements_draft",
"single_allowed_call": true
},
{
"audit_id": 6,
"at": "2026-08-31 21:34:11",
"actor": "author",
"tool": "finalize_requirements_draft",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_61118b0b03ba:root:v4",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_61118b0b03ba:root:v4",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "finalize_requirements_draft",
"single_allowed_call": true
},
{
"audit_id": 7,
"at": "2026-08-31 21:34:19",
"actor": "reviewer",
"tool": "review_requirements",
"raw_arguments_hash": "7b225d8587ad1f268c063230c59fdac1a294758f12328af9d0315046acb5b2a1",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_61118b0b03ba:root:v5",
"phase": "REVIEWING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_61118b0b03ba:root:v5",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "review_requirements",
"single_allowed_call": true
},
{
"audit_id": 8,
"at": "2026-08-31 21:34:36",
"actor": "author",
"tool": "patch_requirements_draft",
"raw_arguments_hash": "8d1b6e26d94c397559dc1df3462b2d3ae1c3bee2849bde8deee99e0617c14301",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_61118b0b03ba:root:v6",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_61118b0b03ba:root:v6",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "patch_requirements_draft",
"single_allowed_call": true
},
{
"audit_id": 9,
"at": "2026-08-31 21:34:40",
"actor": "author",
"tool": "finalize_requirements_draft",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_61118b0b03ba:root:v7",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_61118b0b03ba:root:v7",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "finalize_requirements_draft",
"single_allowed_call": true
},
{
"audit_id": 10,
"at": "2026-08-31 21:34:47",
"actor": "reviewer",
"tool": "review_requirements",
"raw_arguments_hash": "8f9388eb00532e29c7ea722eb4b27a5f65c1b2b9d72948c2b153e4f473a74f31",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_61118b0b03ba:root:v8",
"phase": "REVIEWING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_61118b0b03ba:root:v8",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "review_requirements",
"single_allowed_call": true
},
{
"audit_id": 11,
"at": "2026-08-31 21:35:04",
"actor": "reviewer",
"tool": "review_requirements",
"raw_arguments_hash": "df0a30724f7a0e8f6bfaa7d05655b84aa6a59864fb03ef0352fd434f3332c19e",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_61118b0b03ba:root:v8",
"phase": "REVIEWING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_61118b0b03ba:root:v8",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "review_requirements",
"single_allowed_call": true
}
],
"artifact_root": "/Users/lk/Projects/cdsl-cad/backend/live-evals/20260831T212855Z/artifacts/cad_61118b0b03ba",
"action_ledger_path": "/Users/lk/Projects/cdsl-cad/backend/live-evals/20260831T212855Z/artifacts/cad_61118b0b03ba/actions/action-ledger.jsonl",
"artifact_manifest": {
"schema_version": "cad.live-eval-artifact-manifest.v1",
"artifact_root": "/Users/lk/Projects/cdsl-cad/backend/live-evals/20260831T212855Z/artifacts/cad_61118b0b03ba",
"files": [
{
"path": "actions/action-ledger.jsonl",
"sha256": "c1c99d4e2f54d9958889c3e5fd4deb7f4af3bcda799d8800d1b5eebecfd14a9e"
},
{
"path": "documents/requirements-draft-v1-9569137a152d-cad_61118b0b03ba_inv_cbe0d9057fa.json",
"sha256": "d82a1140cda227024f98bbcbf637ca8ebd505afad1404fc31d49075ae0fd645d"
},
{
"path": "documents/requirements-draft-v2-61b42ee7c0c5-cad_61118b0b03ba_inv_d94f7195643.json",
"sha256": "13d99d23d666778ec80d2641d5c40dab90efd70820138ed509bf28c9403165a4"
},
{
"path": "documents/requirements-draft-v3-1e78fc5e001e-cad_61118b0b03ba_inv_c4f29c79aef.json",
"sha256": "3eee160a4e523da910d889436b98fa0de98b29273b25bd62f5e2c455a05d9b7d"
},
{
"path": "documents/requirements-review-83c51572391b-cad_61118b0b03ba_inv_576f30faa56.json",
"sha256": "992d1e9318e9703f0ae4f1433f42ba6010d6996dcf08620d2cbd61cce9605bc4"
},
{
"path": "documents/requirements-review-95eef23b7115-cad_61118b0b03ba_inv_ba791c6e359.json",
"sha256": "f8dc0671dcdaf0bd9932e6181105fae271cf07c3ee811b36f04722fe6b1c877c"
},
{
"path": "documents/requirements-review-ad5c325ac148-cad_61118b0b03ba_inv_e2c8d7369fe.json",
"sha256": "5c2cfdcea313a64f38d4dbc29eb51f35bcbb9b0442befd55c2515d33b52085b0"
}
]
},
"ledger": [
{
"sequence": 1,
"at": "2026-08-31 21:33:29",
"draft_path": "documents/requirements-draft-v1-9569137a152d-cad_61118b0b03ba_inv_cbe0d9057fa.json",
"draft_revision": 1,
"event": "requirements_draft_updated",
"invocation_id": "cad_61118b0b03ba_inv_cbe0d9057fa9c392",
"item_count": 7
},
{
"sequence": 2,
"at": "2026-08-31 21:33:34",
"draft_revision": 1,
"event": "requirements_review_requested",
"invocation_id": "cad_61118b0b03ba_inv_06bbea193838a2fc"
},
{
"sequence": 3,
"at": "2026-08-31 21:33:57",
"event": "requirements_review_revise",
"invocation_id": "cad_61118b0b03ba_inv_e2c8d7369fe13f8e",
"review_path": "documents/requirements-review-ad5c325ac148-cad_61118b0b03ba_inv_e2c8d7369fe.json"
},
{
"sequence": 4,
"at": "2026-08-31 21:34:09",
"draft_path": "documents/requirements-draft-v2-61b42ee7c0c5-cad_61118b0b03ba_inv_d94f7195643.json",
"draft_revision": 2,
"event": "requirements_draft_patched",
"invocation_id": "cad_61118b0b03ba_inv_d94f71956434ed71",
"item_count": 7
},
{
"sequence": 5,
"at": "2026-08-31 21:34:12",
"draft_revision": 2,
"event": "requirements_review_requested",
"invocation_id": "cad_61118b0b03ba_inv_c7caf81afa71f667"
},
{
"sequence": 6,
"at": "2026-08-31 21:34:19",
"event": "requirements_evaluation_oracle_revise",
"invocation_id": "cad_61118b0b03ba_inv_576f30faa568cb0c",
"missing_claims": [
{
"claim_kind": "collinear_through_bore_chain",
"expected": {
"adjacent_distances_mm": [
60,
80
],
"diameter_mm": 12,
"tolerance_mm": 0.1
}
}
],
"oracle_path": "documents/evaluation-contract-oracle-e9f00ebbf0e1.json",
"review_path": "documents/requirements-review-83c51572391b-cad_61118b0b03ba_inv_576f30faa56.json"
},
{
"sequence": 7,
"at": "2026-08-31 21:34:36",
"draft_path": "documents/requirements-draft-v3-1e78fc5e001e-cad_61118b0b03ba_inv_c4f29c79aef.json",
"draft_revision": 3,
"event": "requirements_draft_patched",
"invocation_id": "cad_61118b0b03ba_inv_c4f29c79aef5c797",
"item_count": 7
},
{
"sequence": 8,
"at": "2026-08-31 21:34:40",
"draft_revision": 3,
"event": "requirements_review_requested",
"invocation_id": "cad_61118b0b03ba_inv_2443bcac857a1442"
},
{
"sequence": 9,
"at": "2026-08-31 21:35:04",
"event": "requirements_review_revise",
"invocation_id": "cad_61118b0b03ba_inv_ba791c6e359e7a0c",
"review_path": "documents/requirements-review-95eef23b7115-cad_61118b0b03ba_inv_ba791c6e359.json"
},
{
"sequence": 10,
"at": "2026-08-31 21:35:04",
"draft_revision": 3,
"event": "requirements_review_limit_reached"
}
],
"invocations": [
{
"invocation_id": "cad_61118b0b03ba_inv_cbe0d9057fa9c392",
"idempotency_key": "3877c33a9dbd2ad4976f8fe4ea308e8107f9bf3124b8a9e9c18392b72a076f26",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"draft_revision": 1,
"draft_ids": [
"draft_001",
"draft_002",
"draft_003",
"draft_004",
"draft_005",
"draft_006",
"draft_007"
]
}
},
"created_at": "2026-08-31 21:33:29",
"updated_at": "2026-08-31 21:33:29"
},
{
"invocation_id": "cad_61118b0b03ba_inv_06bbea193838a2fc",
"idempotency_key": "a1e1a18a87923a110048a5fae5831964103010bcea0cf527d75643216682b042",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "REVIEWING_REQUIREMENTS",
"draft_revision": 1
}
},
"created_at": "2026-08-31 21:33:34",
"updated_at": "2026-08-31 21:33:34"
},
{
"invocation_id": "cad_61118b0b03ba_inv_e2c8d7369fe13f8e",
"idempotency_key": "345fc76130f8145f19339cc33947555e1a2e8b1438a6538d66262e29ca397085",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "DRAFTING_REQUIREMENTS",
"review": {
"verdict": "revise",
"coverage": [
{
"source_id": "src_001",
"requirement_ids": [
"req_001",
"req_002",
"req_003",
"req_004",
"req_005",
"req_006",
"req_007"
]
}
],
"item_verdicts": [
{
"draft_id": "draft_001",
"verdict": "pass",
"reason_code": "none",
"question": null
},
{
"draft_id": "draft_002",
"verdict": "pass",
"reason_code": "none",
"question": null
},
{
"draft_id": "draft_003",
"verdict": "pass",
"reason_code": "none",
"question": null
},
{
"draft_id": "draft_004",
"verdict": "pass",
"reason_code": "none",
"question": null
},
{
"draft_id": "draft_005",
"verdict": "pass",
"reason_code": "none",
"question": null
},
{
"draft_id": "draft_006",
"verdict": "revise",
"reason_code": "claim_unverifiable",
"question": null
},
{
"draft_id": "draft_007",
"verdict": "pass",
"reason_code": "none",
"question": null
}
],
"issues": [
"The 32 mm outer lobe diameter and smooth outer contour are represented by scoped visual claims, but the deterministic verifier has a known capability gap for validating these outer-circle/blend requirements; draft_006 also includes an unavailable executable outer_cylindrical_surface claim for that gap."
]
}
}
},
"created_at": "2026-08-31 21:33:57",
"updated_at": "2026-08-31 21:33:57"
},
{
"invocation_id": "cad_61118b0b03ba_inv_d94f71956434ed71",
"idempotency_key": "f981d2a32d680102e21e350fd1ffe82a4829e9c59b99538c15d2be72cd9629c1",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"draft_revision": 2,
"item_count": 7
}
},
"created_at": "2026-08-31 21:34:09",
"updated_at": "2026-08-31 21:34:09"
},
{
"invocation_id": "cad_61118b0b03ba_inv_c7caf81afa71f667",
"idempotency_key": "610c505fca1dd1a4afe5585e6dfad5e029d0e781041d167db0154a46121052eb",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "REVIEWING_REQUIREMENTS",
"draft_revision": 2
}
},
"created_at": "2026-08-31 21:34:12",
"updated_at": "2026-08-31 21:34:12"
},
{
"invocation_id": "cad_61118b0b03ba_inv_576f30faa568cb0c",
"idempotency_key": "b6bb4084c9d5c29a410d9d95a589f71cabb39a8cfdad871a2e086047eb1e5a27",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "DRAFTING_REQUIREMENTS",
"review": {
"schema_version": "cad.requirements-evaluation-oracle.v1",
"task_id": "cad_61118b0b03ba",
"evaluation_only": true,
"verdict": "revise",
"draft_revision": 2,
"reviewer_verdict": "pass",
"reviewer_review_path": "documents/requirements-review-83c51572391b-cad_61118b0b03ba_inv_576f30faa56.json",
"item_verdicts": [
{
"draft_id": "draft_001",
"verdict": "revise",
"reason_code": "evaluation_contract_oracle"
},
{
"draft_id": "draft_002",
"verdict": "revise",
"reason_code": "evaluation_contract_oracle"
},
{
"draft_id": "draft_003",
"verdict": "revise",
"reason_code": "evaluation_contract_oracle"
},
{
"draft_id": "draft_004",
"verdict": "revise",
"reason_code": "evaluation_contract_oracle"
},
{
"draft_id": "draft_005",
"verdict": "revise",
"reason_code": "evaluation_contract_oracle"
},
{
"draft_id": "draft_006",
"verdict": "revise",
"reason_code": "evaluation_contract_oracle"
},
{
"draft_id": "draft_007",
"verdict": "revise",
"reason_code": "evaluation_contract_oracle"
}
],
"issues": [
"The external live-evaluation contract oracle found missing executable acceptance claims."
],
"missing_claims": [
{
"claim_kind": "collinear_through_bore_chain",
"expected": {
"diameter_mm": 12,
"adjacent_distances_mm": [
60,
80
],
"tolerance_mm": 0.1
}
}
]
},
"reviewer_review_path": "documents/requirements-review-83c51572391b-cad_61118b0b03ba_inv_576f30faa56.json",
"evaluation_oracle": {
"missing_claims": [
{
"claim_kind": "collinear_through_bore_chain",
"expected": {
"diameter_mm": 12,
"adjacent_distances_mm": [
60,
80
],
"tolerance_mm": 0.1
}
}
]
}
}
},
"created_at": "2026-08-31 21:34:19",
"updated_at": "2026-08-31 21:34:19"
},
{
"invocation_id": "cad_61118b0b03ba_inv_c4f29c79aef5c797",
"idempotency_key": "2d00902c522d478617eb26e505c20d2178546e0a45397340ba94c35d477544d5",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"draft_revision": 3,
"item_count": 7
}
},
"created_at": "2026-08-31 21:34:36",
"updated_at": "2026-08-31 21:34:36"
},
{
"invocation_id": "cad_61118b0b03ba_inv_2443bcac857a1442",
"idempotency_key": "ff489a45f8a239834a465e9e28efce6a105f831359dbd295be81110327e9cb4e",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "REVIEWING_REQUIREMENTS",
"draft_revision": 3
}
},
"created_at": "2026-08-31 21:34:40",
"updated_at": "2026-08-31 21:34:40"
},
{
"invocation_id": "cad_61118b0b03ba_inv_ba791c6e359e7a0c",
"idempotency_key": "3a9f1710d14c5146405b94c39ca44e8b3db4ab55676e2cbddcd5ae943d0db5d4",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "DRAFTING_REQUIREMENTS",
"review": {
"verdict": "revise",
"coverage": [
{
"source_id": "src_001",
"requirement_ids": [
"req_001",
"req_002",
"req_003",
"req_004",
"req_005",
"req_006",
"req_007"
]
}
],
"item_verdicts": [
{
"draft_id": "draft_001",
"verdict": "pass",
"reason_code": "none",
"question": null
},
{
"draft_id": "draft_002",
"verdict": "pass",
"reason_code": "none",
"question": null
},
{
"draft_id": "draft_003",
"verdict": "pass",
"reason_code": "none",
"question": null
},
{
"draft_id": "draft_004",
"verdict": "pass",
"reason_code": "none",
"question": null
},
{
"draft_id": "draft_005",
"verdict": "pass",
"reason_code": "none",
"question": null
},
{
"draft_id": "draft_006",
"verdict": "revise",
"reason_code": "claim_unverifiable",
"question": null
},
{
"draft_id": "draft_007",
"verdict": "revise",
"reason_code": "claim_unverifiable",
"question": null
}
],
"issues": [
"Known validation capability gap: the 32 mm outer lobe diameter and smooth outer contour are represented by scoped visual claims only because deterministic executable validation for linkage outer circles/blended segments is unavailable in the current registry."
]
}
}
},
"created_at": "2026-08-31 21:35:04",
"updated_at": "2026-08-31 21:35:04"
}
],
"event_audit": [
{
"name": "tool_call",
"tool": "submit_requirements_draft_batch",
"status": "success",
"code": "",
"raw_arguments_hash": "8fbb73db04f9d70dd7e37dc17b29a9769f032e019356f8854d89eb0e9e82323c",
"field_errors": []
},
{
"name": "tool_call",
"tool": "finalize_requirements_draft",
"status": "success",
"code": "",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"field_errors": []
},
{
"name": "requirements_review",
"tool": "",
"status": "error",
"code": "AUTHOR_FORMAT_INVALID",
"raw_arguments_hash": "",
"field_errors": [
{
"path": "/",
"message": "Value error, pass requires every draft item to pass and forbids unresolved issues"
}
]
},
{
"name": "requirements_review",
"tool": "",
"status": "success",
"code": "",
"raw_arguments_hash": "",
"field_errors": []
},
{
"name": "tool_call",
"tool": "patch_requirements_draft",
"status": "success",
"code": "",
"raw_arguments_hash": "6193c963abbf512fa5e35a8341c03519eaac38c4625873d564d2bc296267c724",
"field_errors": []
},
{
"name": "tool_call",
"tool": "finalize_requirements_draft",
"status": "success",
"code": "",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"field_errors": []
},
{
"name": "requirements_review",
"tool": "",
"status": "success",
"code": "",
"raw_arguments_hash": "",
"field_errors": []
},
{
"name": "tool_call",
"tool": "patch_requirements_draft",
"status": "success",
"code": "",
"raw_arguments_hash": "8d1b6e26d94c397559dc1df3462b2d3ae1c3bee2849bde8deee99e0617c14301",
"field_errors": []
},
{
"name": "tool_call",
"tool": "finalize_requirements_draft",
"status": "success",
"code": "",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"field_errors": []
},
{
"name": "requirements_review",
"tool": "",
"status": "error",
"code": "AUTHOR_FORMAT_INVALID",
"raw_arguments_hash": "",
"field_errors": [
{
"path": "/",
"message": "Value error, pass requires every draft item to pass and forbids unresolved issues"
}
]
},
{
"name": "requirements_review",
"tool": "",
"status": "success",
"code": "",
"raw_arguments_hash": "",
"field_errors": []
},
{
"name": "task_terminal",
"tool": "",
"status": "",
"code": "WAITING_FOR_USER",
"raw_arguments_hash": "",
"field_errors": []
}
]
}
],
"suite": "comprehensive",
"require_live": true,
"report_root": "/Users/lk/Projects/cdsl-cad/backend/live-evals/20260831T212855Z"
}