Files
cdsl-cad/backend/live-evals/20260831T215036Z/report.json
T
2026-09-01 14:10:23 +08:00

1166 lines
43 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": 4153
},
"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": 1660
},
"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": "2db370891450194997b6862361e9cc5094ee037c710cdbae8a4b548897397dcd",
"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": "d3bf72f85ecafa742586ab42f596423359bb4c7e1d735957e62561066b9e007d",
"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": "3913357ee8a2db459dc8a4c642d79b37a39d3e39495032c3a54ee145a5715373",
"contract_version": "3.0",
"registry_revision": "1.3.1"
},
{
"atomic_id": "reference_plane",
"contract_hash": "fadd71be282d3e5233753f3de60f3d2e3c7c1e26691ede055376a363f28ade04",
"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": "57f511b35c2ef8b24ae376e7fd377d20f0448fc55d682aec6860754545fd4473",
"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": "2026-08-31T21:55:00.689499+00:00",
"finished_at": "2026-08-31T21:56:19.040096+00:00",
"duration_ms": 78351,
"terminal": {
"taskId": "cad_4284230fee59",
"lifecycle": "failed",
"code": "RUNTIME_CONTRACT_INVALID",
"message": "RUNTIME_CONTRACT_INVALID: materialized fragment violates the engine CDSL schema: CDSL engine runtime preflight failed: feature feature_001: profile_resolution_failed"
},
"projection": {
"schema_version": "3.0",
"task_id": "cad_4284230fee59",
"phase": "FAILED",
"lifecycle": "failed",
"state_version": 8,
"active_revision": "",
"current_revision": "",
"published_revision": "",
"pending_action": null,
"active_candidate_id": "",
"repair_required": false,
"last_error": "RUNTIME_CONTRACT_INVALID",
"retry_from_phase": "",
"requirements_draft_path": "documents/requirements-draft-v2-79ee12c071ab-cad_4284230fee59_inv_6057530b063.json",
"requirements_review_path": "documents/requirements-review-d49ae4f83418-cad_4284230fee59_inv_769c47f9bb7.json",
"requirements_contract_path": "documents/requirements-contract-37bbde8bf93d-cad_4284230fee59_inv_769c47f9bb7.json",
"action_ledger_summary": [
{
"sequence": 1,
"at": "2026-08-31 21:55:12",
"draft_path": "documents/requirements-draft-v1-ae7b227b2587-cad_4284230fee59_inv_49368ab55a0.json",
"draft_revision": 1,
"event": "requirements_draft_updated",
"invocation_id": "cad_4284230fee59_inv_49368ab55a040477",
"item_count": 2
},
{
"sequence": 2,
"at": "2026-08-31 21:55:16",
"draft_revision": 1,
"event": "requirements_review_requested",
"invocation_id": "cad_4284230fee59_inv_c7bfc663807afde8"
},
{
"sequence": 3,
"at": "2026-08-31 21:55:30",
"event": "requirements_evaluation_oracle_revise",
"invocation_id": "cad_4284230fee59_inv_ba8009288d5c09c7",
"missing_claims": [
{
"claim_kind": "bbox_rank_dimension_mm",
"expected": {
"rank": "minimum",
"value": 10
}
},
{
"claim_kind": "through_cylindrical_bore",
"expected": {
"count": 3,
"diameter_mm": 12
}
},
{
"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-da68344ae828.json",
"review_path": "documents/requirements-review-d49ae4f83418-cad_4284230fee59_inv_ba8009288d5.json"
},
{
"sequence": 4,
"at": "2026-08-31 21:55:43",
"draft_path": "documents/requirements-draft-v2-79ee12c071ab-cad_4284230fee59_inv_6057530b063.json",
"draft_revision": 2,
"event": "requirements_draft_patched",
"invocation_id": "cad_4284230fee59_inv_6057530b06311d2a",
"item_count": 2
},
{
"sequence": 5,
"at": "2026-08-31 21:55:48",
"draft_revision": 2,
"event": "requirements_review_requested",
"invocation_id": "cad_4284230fee59_inv_c4b3ddf49fa82110"
},
{
"sequence": 6,
"at": "2026-08-31 21:55:53",
"contract_hash": "1d9c54f6cfd3bfef2c61072ad4cc9581b6c2f75e934b2719453f871fb3e7dac8",
"contract_path": "documents/requirements-contract-37bbde8bf93d-cad_4284230fee59_inv_769c47f9bb7.json",
"event": "requirements_contract_frozen",
"invocation_id": "cad_4284230fee59_inv_769c47f9bb72733b",
"requirement_count": 2,
"review_path": "documents/requirements-review-d49ae4f83418-cad_4284230fee59_inv_769c47f9bb7.json"
},
{
"sequence": 7,
"at": "2026-08-31 21:56:02",
"action_id": "act_007",
"atomic_id": "extrude_add_blind",
"contract_hash": "fa9ffc9fd2141453fa18a389813dde2e2ef3fb4c7ef5d05e61d51d614309e95f",
"event": "proposed",
"expected_change": "Create a single solid link body 10 mm thick from a planar sketch that defines three collinear 12 mm through-holes with 60 mm and 80 mm center spacing, and an outer profile that blends smoothly around 32 mm diameter lobes at each hole center.",
"intent": "Establish the full connecting-rod body in one bounded solid operation so the hole chain, single-body condition, and thickness can be verified against the requirements.",
"requirement_ids": [
"req_001",
"req_002"
],
"working_head": "cad_4284230fee59:root:v6"
},
{
"sequence": 8,
"at": "2026-08-31 21:56:19",
"event": "runtime_contract_invalid",
"message": "RUNTIME_CONTRACT_INVALID: materialized fragment violates the engine CDSL schema: CDSL engine runtime preflight failed: feature feature_001: profile_resolution_failed",
"tool": "submit_cdsl_fragment"
}
],
"revisions": []
},
"usage": {
"calls": 9,
"prompt_tokens": 52948,
"completion_tokens": 3306,
"context_chars": 30590,
"records": [
{
"cache_hit": false,
"completion_tokens": 602,
"context_chars": 943,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 6146,
"provider_id": "openai",
"raw_arguments_hash": "ace991312f09042f4f2c0c1aee4a7ebf076d0d17ffa8c97b0944b07a7e2eeeba",
"retry_reason": "",
"tool": "submit_requirements_draft_batch",
"total_tokens": 6748,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 81,
"context_chars": 1822,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 5032,
"provider_id": "openai",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"retry_reason": "",
"tool": "finalize_requirements_draft",
"total_tokens": 5113,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 509,
"context_chars": 2611,
"model_id": "gpt-5.5",
"prompt_tokens": 5417,
"provider_id": "openai",
"raw_arguments_hash": "cdf2cf46e3297314cd1e4196d4b84eee95fc01a2bb6a3fca265fe1349ceabb1a",
"retry_reason": "",
"role": "reviewer",
"tool": "review_requirements",
"total_tokens": 5926,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 660,
"context_chars": 3557,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 7069,
"provider_id": "openai",
"raw_arguments_hash": "5c507d1ae4e866c6e0f8ebe7ff15eec0278c886789c25b6f7c324d00386b0b9b",
"retry_reason": "",
"tool": "patch_requirements_draft",
"total_tokens": 7729,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 106,
"context_chars": 1954,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 5073,
"provider_id": "openai",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"retry_reason": "",
"tool": "finalize_requirements_draft",
"total_tokens": 5179,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 96,
"context_chars": 2731,
"model_id": "gpt-5.5",
"prompt_tokens": 5458,
"provider_id": "openai",
"raw_arguments_hash": "cdf2cf46e3297314cd1e4196d4b84eee95fc01a2bb6a3fca265fe1349ceabb1a",
"retry_reason": "",
"role": "reviewer",
"tool": "review_requirements",
"total_tokens": 5554,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 473,
"context_chars": 3488,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 5618,
"provider_id": "openai",
"raw_arguments_hash": "7f9d2251573ccb8b78793f140fda3e7d5d5b969750f5a6bc1e45a2dd691265b7",
"retry_reason": "",
"tool": "propose_next_action",
"total_tokens": 6091,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 41,
"context_chars": 4252,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 5711,
"provider_id": "openai",
"raw_arguments_hash": "789c05347c7b26661cdfe08d08afcb36c2bbcc888e94adc149de9606c4e9c61b",
"retry_reason": "",
"tool": "get_cdsl_operation_contract",
"total_tokens": 5752,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 738,
"context_chars": 9232,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 7424,
"provider_id": "openai",
"raw_arguments_hash": "afb75b9056e8a7e149c5279332659fcd8f9b611b2b9965774ea8a23fb7420758",
"retry_reason": "",
"tool": "submit_cdsl_fragment",
"total_tokens": 8162,
"usage_available": true
}
]
},
"checks": {
"expected_terminal_phase": false,
"token_budget": true,
"call_budget": true,
"author_turn_budget": true,
"reviewer_turn_budget": true,
"required_claims": true,
"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": true
},
"acceptance_coverage": {
"required_claim_kinds": [
"bbox_rank_dimension_mm",
"collinear_through_bore_chain",
"solid_count_equals",
"through_cylindrical_bore",
"visual"
],
"covered_claim_kinds": [
"bbox_rank_dimension_mm",
"collinear_through_bore_chain",
"solid_count_equals",
"through_cylindrical_bore",
"visual"
],
"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": [],
"validation_capability_gaps": [
{
"id": "linkage_outer_circles",
"description": "32 mm outer circles with smoothly connected segments"
}
],
"complete": false
},
"failure_attribution": {
"layer": "v3_contract_or_verifier",
"reason_code": "RUNTIME_CONTRACT_INVALID",
"evidence_codes": [
"RUNTIME_CONTRACT_INVALID"
],
"failed_checks": [
"expected_terminal_phase",
"acceptance_contract_coverage",
"required_operations",
"required_operation_alternative",
"immutable_artifacts",
"required_artifact_evidence",
"deterministic_claims_pass"
]
},
"rejection_codes": [],
"schema_rejection_count": 0,
"retry_count": 1,
"rollback_count": 0,
"candidate_ids": [],
"revision_ids": [],
"final_claim_results": [],
"redacted_correlation_ids": [
"d8c6e4d6d195d272bb06",
"702878551930bb9369f3",
"82f2cae12e172f04d080",
"c76914aad4c379a6a708",
"54fe00cd6a37b385c9f7",
"797170dcfe531ebe140f",
"6b3e8be11549b43d0193"
],
"tool_audits": [
{
"audit_id": 1,
"at": "2026-08-31 21:55:12",
"actor": "author",
"tool": "submit_requirements_draft_batch",
"raw_arguments_hash": "ace991312f09042f4f2c0c1aee4a7ebf076d0d17ffa8c97b0944b07a7e2eeeba",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_4284230fee59:root:v0",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_4284230fee59: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 21:55:16",
"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_4284230fee59:root:v1",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_4284230fee59: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 21:55:30",
"actor": "reviewer",
"tool": "review_requirements",
"raw_arguments_hash": "cdf2cf46e3297314cd1e4196d4b84eee95fc01a2bb6a3fca265fe1349ceabb1a",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_4284230fee59:root:v2",
"phase": "REVIEWING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_4284230fee59: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 21:55:43",
"actor": "author",
"tool": "patch_requirements_draft",
"raw_arguments_hash": "5c507d1ae4e866c6e0f8ebe7ff15eec0278c886789c25b6f7c324d00386b0b9b",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_4284230fee59:root:v3",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_4284230fee59:root:v3",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "patch_requirements_draft",
"single_allowed_call": true
},
{
"audit_id": 5,
"at": "2026-08-31 21:55:48",
"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_4284230fee59:root:v4",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_4284230fee59:root:v4",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "finalize_requirements_draft",
"single_allowed_call": true
},
{
"audit_id": 6,
"at": "2026-08-31 21:55:53",
"actor": "reviewer",
"tool": "review_requirements",
"raw_arguments_hash": "cdf2cf46e3297314cd1e4196d4b84eee95fc01a2bb6a3fca265fe1349ceabb1a",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_4284230fee59:root:v5",
"phase": "REVIEWING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_4284230fee59:root:v5",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "review_requirements",
"single_allowed_call": true
},
{
"audit_id": 7,
"at": "2026-08-31 21:56:02",
"actor": "author",
"tool": "propose_next_action",
"raw_arguments_hash": "7f9d2251573ccb8b78793f140fda3e7d5d5b969750f5a6bc1e45a2dd691265b7",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_4284230fee59:root:v6",
"phase": "AWAITING_ACTION",
"selector_snapshot_id": "",
"supplied_working_head": "cad_4284230fee59:root:v6",
"working_head": "cad_4284230fee59:root:v6",
"working_head_binding_source": "schema_const",
"working_head_matches": true
},
"returned_tool": "propose_next_action",
"single_allowed_call": true
},
{
"audit_id": 8,
"at": "2026-08-31 21:56:05",
"actor": "author",
"tool": "get_cdsl_operation_contract",
"raw_arguments_hash": "789c05347c7b26661cdfe08d08afcb36c2bbcc888e94adc149de9606c4e9c61b",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "fa9ffc9fd2141453fa18a389813dde2e2ef3fb4c7ef5d05e61d51d614309e95f",
"contract_hash_current": true,
"expected_working_head": "cad_4284230fee59:root:v7",
"phase": "ACTION_PENDING",
"selector_snapshot_id": "",
"supplied_working_head": "cad_4284230fee59:root:v7",
"working_head": "cad_4284230fee59:root:v7",
"working_head_binding_source": "schema_const",
"working_head_matches": true
},
"returned_tool": "get_cdsl_operation_contract",
"single_allowed_call": true
},
{
"audit_id": 9,
"at": "2026-08-31 21:56:18",
"actor": "author",
"tool": "submit_cdsl_fragment",
"raw_arguments_hash": "afb75b9056e8a7e149c5279332659fcd8f9b611b2b9965774ea8a23fb7420758",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "fa9ffc9fd2141453fa18a389813dde2e2ef3fb4c7ef5d05e61d51d614309e95f",
"contract_hash_current": true,
"expected_working_head": "cad_4284230fee59:root:v7",
"phase": "ACTION_PENDING",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_4284230fee59:root:v7",
"working_head_binding_source": "current_state",
"working_head_matches": true
},
"returned_tool": "submit_cdsl_fragment",
"single_allowed_call": true
}
],
"artifact_root": "/Users/lk/Projects/cdsl-cad/backend/live-evals/20260831T215036Z/artifacts/cad_4284230fee59",
"action_ledger_path": "/Users/lk/Projects/cdsl-cad/backend/live-evals/20260831T215036Z/artifacts/cad_4284230fee59/actions/action-ledger.jsonl",
"artifact_manifest": {
"schema_version": "cad.live-eval-artifact-manifest.v1",
"artifact_root": "/Users/lk/Projects/cdsl-cad/backend/live-evals/20260831T215036Z/artifacts/cad_4284230fee59",
"files": [
{
"path": "actions/action-ledger.jsonl",
"sha256": "8c2086e69163eaeb2126af7feee710d183bcee5f4f5f4de1781f1c747bb2a245"
},
{
"path": "completion.md",
"sha256": "95c272b3303337e3be3ec760cc3029375ddb2a5c90480052d388b3993353e406"
},
{
"path": "documents/requirements-contract-37bbde8bf93d-cad_4284230fee59_inv_769c47f9bb7.json",
"sha256": "2f60d4c541ba8e92d8778697fb723237e813b7f08401d3064f8bb6c7a80e8eeb"
},
{
"path": "documents/requirements-draft-v1-ae7b227b2587-cad_4284230fee59_inv_49368ab55a0.json",
"sha256": "21a759f5d561f14fa14a40935af1a97c215157a952ec020ae379e1eff3471a4b"
},
{
"path": "documents/requirements-draft-v2-79ee12c071ab-cad_4284230fee59_inv_6057530b063.json",
"sha256": "b5aafb9498d1ea83b37b760339ec83244d56ed8fdc514069159993ade8b39851"
},
{
"path": "documents/requirements-review-d49ae4f83418-cad_4284230fee59_inv_769c47f9bb7.json",
"sha256": "ea3bf0b1a38681c9029c15c2db196d0e7cb307555a3793c989ace1d306d7050a"
},
{
"path": "documents/requirements-review-d49ae4f83418-cad_4284230fee59_inv_ba8009288d5.json",
"sha256": "ea3bf0b1a38681c9029c15c2db196d0e7cb307555a3793c989ace1d306d7050a"
},
{
"path": "requirements-contract.json",
"sha256": "2f60d4c541ba8e92d8778697fb723237e813b7f08401d3064f8bb6c7a80e8eeb"
},
{
"path": "requirements-index.json",
"sha256": "b2e0a31843bb33a82613ed9dccf9fa4b89ebb17f58db4d5a6094a5b52d9dd7b7"
},
{
"path": "requirements.md",
"sha256": "9549b41f99eee467e89ec3053e0a7070abc8d7727aa4acaa91c998763c70ec00"
}
]
},
"ledger": [
{
"sequence": 1,
"at": "2026-08-31 21:55:12",
"draft_path": "documents/requirements-draft-v1-ae7b227b2587-cad_4284230fee59_inv_49368ab55a0.json",
"draft_revision": 1,
"event": "requirements_draft_updated",
"invocation_id": "cad_4284230fee59_inv_49368ab55a040477",
"item_count": 2
},
{
"sequence": 2,
"at": "2026-08-31 21:55:16",
"draft_revision": 1,
"event": "requirements_review_requested",
"invocation_id": "cad_4284230fee59_inv_c7bfc663807afde8"
},
{
"sequence": 3,
"at": "2026-08-31 21:55:30",
"event": "requirements_evaluation_oracle_revise",
"invocation_id": "cad_4284230fee59_inv_ba8009288d5c09c7",
"missing_claims": [
{
"claim_kind": "bbox_rank_dimension_mm",
"expected": {
"rank": "minimum",
"value": 10
}
},
{
"claim_kind": "through_cylindrical_bore",
"expected": {
"count": 3,
"diameter_mm": 12
}
},
{
"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-da68344ae828.json",
"review_path": "documents/requirements-review-d49ae4f83418-cad_4284230fee59_inv_ba8009288d5.json"
},
{
"sequence": 4,
"at": "2026-08-31 21:55:43",
"draft_path": "documents/requirements-draft-v2-79ee12c071ab-cad_4284230fee59_inv_6057530b063.json",
"draft_revision": 2,
"event": "requirements_draft_patched",
"invocation_id": "cad_4284230fee59_inv_6057530b06311d2a",
"item_count": 2
},
{
"sequence": 5,
"at": "2026-08-31 21:55:48",
"draft_revision": 2,
"event": "requirements_review_requested",
"invocation_id": "cad_4284230fee59_inv_c4b3ddf49fa82110"
},
{
"sequence": 6,
"at": "2026-08-31 21:55:53",
"contract_hash": "1d9c54f6cfd3bfef2c61072ad4cc9581b6c2f75e934b2719453f871fb3e7dac8",
"contract_path": "documents/requirements-contract-37bbde8bf93d-cad_4284230fee59_inv_769c47f9bb7.json",
"event": "requirements_contract_frozen",
"invocation_id": "cad_4284230fee59_inv_769c47f9bb72733b",
"requirement_count": 2,
"review_path": "documents/requirements-review-d49ae4f83418-cad_4284230fee59_inv_769c47f9bb7.json"
},
{
"sequence": 7,
"at": "2026-08-31 21:56:02",
"action_id": "act_007",
"atomic_id": "extrude_add_blind",
"contract_hash": "fa9ffc9fd2141453fa18a389813dde2e2ef3fb4c7ef5d05e61d51d614309e95f",
"event": "proposed",
"expected_change": "Create a single solid link body 10 mm thick from a planar sketch that defines three collinear 12 mm through-holes with 60 mm and 80 mm center spacing, and an outer profile that blends smoothly around 32 mm diameter lobes at each hole center.",
"intent": "Establish the full connecting-rod body in one bounded solid operation so the hole chain, single-body condition, and thickness can be verified against the requirements.",
"requirement_ids": [
"req_001",
"req_002"
],
"working_head": "cad_4284230fee59:root:v6"
},
{
"sequence": 8,
"at": "2026-08-31 21:56:19",
"event": "runtime_contract_invalid",
"message": "RUNTIME_CONTRACT_INVALID: materialized fragment violates the engine CDSL schema: CDSL engine runtime preflight failed: feature feature_001: profile_resolution_failed",
"tool": "submit_cdsl_fragment"
}
],
"invocations": [
{
"invocation_id": "cad_4284230fee59_inv_49368ab55a040477",
"idempotency_key": "e69c85d995bcc6cdfc368d34a5a711248e9873cb04e9e8f2ad93f47011e4a395",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"draft_revision": 1,
"draft_ids": [
"draft_001",
"draft_002"
]
}
},
"created_at": "2026-08-31 21:55:12",
"updated_at": "2026-08-31 21:55:12"
},
{
"invocation_id": "cad_4284230fee59_inv_c7bfc663807afde8",
"idempotency_key": "2281fee265469c479beda9a35bc72405e2397678835c204945989e1b9cfa42dc",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "REVIEWING_REQUIREMENTS",
"draft_revision": 1
}
},
"created_at": "2026-08-31 21:55:16",
"updated_at": "2026-08-31 21:55:16"
},
{
"invocation_id": "cad_4284230fee59_inv_ba8009288d5c09c7",
"idempotency_key": "95332e640ed07773596ab524343e1c9117c4efa9ddb5a78f71d9ee035a9397db",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "DRAFTING_REQUIREMENTS",
"review": {
"schema_version": "cad.requirements-evaluation-oracle.v1",
"task_id": "cad_4284230fee59",
"evaluation_only": true,
"verdict": "revise",
"draft_revision": 1,
"reviewer_verdict": "pass",
"reviewer_review_path": "documents/requirements-review-d49ae4f83418-cad_4284230fee59_inv_ba8009288d5.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"
}
],
"issues": [
"The external live-evaluation contract oracle found missing executable acceptance claims."
],
"missing_claims": [
{
"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
}
}
]
},
"reviewer_review_path": "documents/requirements-review-d49ae4f83418-cad_4284230fee59_inv_ba8009288d5.json",
"evaluation_oracle": {
"missing_claims": [
{
"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
}
}
]
}
}
},
"created_at": "2026-08-31 21:55:30",
"updated_at": "2026-08-31 21:55:30"
},
{
"invocation_id": "cad_4284230fee59_inv_6057530b06311d2a",
"idempotency_key": "1df74443266e518717767fa286a13956fa2ed121aed94c1a8f5d6a85e0fa33e3",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"draft_revision": 2,
"item_count": 2
}
},
"created_at": "2026-08-31 21:55:43",
"updated_at": "2026-08-31 21:55:43"
},
{
"invocation_id": "cad_4284230fee59_inv_c4b3ddf49fa82110",
"idempotency_key": "26bae94ac8aa72a61518728cdd6b2de01bdafa4464375adccc07034ae189c661",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "REVIEWING_REQUIREMENTS",
"draft_revision": 2
}
},
"created_at": "2026-08-31 21:55:48",
"updated_at": "2026-08-31 21:55:48"
},
{
"invocation_id": "cad_4284230fee59_inv_769c47f9bb72733b",
"idempotency_key": "b54d40b40f09d4ea51f5e2cebe5d7795cfcf65781dded06d85c2e092c6ab326f",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "AWAITING_ACTION",
"contract_hash": "1d9c54f6cfd3bfef2c61072ad4cc9581b6c2f75e934b2719453f871fb3e7dac8"
}
},
"created_at": "2026-08-31 21:55:53",
"updated_at": "2026-08-31 21:55:53"
},
{
"invocation_id": "cad_4284230fee59_inv_82b606347e646bd1",
"idempotency_key": "0d1fa567c46a6f7fbb723950d989a47b0b009b97ff2aa08fec8e5162b7caf455",
"status": "finished",
"result": {
"action_id": "act_007",
"working_head": "cad_4284230fee59:root:v6",
"atomic_id": "extrude_add_blind",
"contract_hash": "fa9ffc9fd2141453fa18a389813dde2e2ef3fb4c7ef5d05e61d51d614309e95f"
},
"created_at": "2026-08-31 21:56:02",
"updated_at": "2026-08-31 21:56:02"
}
],
"event_audit": [
{
"name": "tool_call",
"tool": "submit_requirements_draft_batch",
"status": "success",
"code": "",
"raw_arguments_hash": "ace991312f09042f4f2c0c1aee4a7ebf076d0d17ffa8c97b0944b07a7e2eeeba",
"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": "5c507d1ae4e866c6e0f8ebe7ff15eec0278c886789c25b6f7c324d00386b0b9b",
"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": "action_selection",
"tool": "propose_next_action",
"status": "success",
"code": "",
"raw_arguments_hash": "7f9d2251573ccb8b78793f140fda3e7d5d5b969750f5a6bc1e45a2dd691265b7",
"field_errors": []
},
{
"name": "tool_call",
"tool": "get_cdsl_operation_contract",
"status": "success",
"code": "",
"raw_arguments_hash": "789c05347c7b26661cdfe08d08afcb36c2bbcc888e94adc149de9606c4e9c61b",
"field_errors": []
},
{
"name": "candidate_result",
"tool": "submit_cdsl_fragment",
"status": "error",
"code": "RUNTIME_CONTRACT_INVALID",
"raw_arguments_hash": "afb75b9056e8a7e149c5279332659fcd8f9b611b2b9965774ea8a23fb7420758",
"field_errors": []
},
{
"name": "task_terminal",
"tool": "",
"status": "",
"code": "RUNTIME_CONTRACT_INVALID",
"raw_arguments_hash": "",
"field_errors": []
}
]
}
],
"suite": "comprehensive",
"require_live": true,
"report_root": "/Users/lk/Projects/cdsl-cad/backend/live-evals/20260831T215036Z"
}