Files
cdsl-cad/backend/live-evals/20260831T214103Z/report.json
T
2026-09-01 14:10:23 +08:00

1110 lines
41 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": 3906
},
"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": 1652
},
"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": "2026-08-31T21:45:28.774315+00:00",
"finished_at": "2026-08-31T21:46:33.613688+00:00",
"duration_ms": 64839,
"terminal": {
"taskId": "cad_f33e5741666b",
"lifecycle": "failed",
"code": "RUNTIME_CONTRACT_INVALID",
"message": "RUNTIME_CONTRACT_INVALID: materialized fragment violates the engine CDSL schema: CDSL engine runtime preflight failed: no_solid_feature"
},
"projection": {
"schema_version": "3.0",
"task_id": "cad_f33e5741666b",
"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-v2-9bfc21fe46f3-cad_f33e5741666b_inv_9fc0d3ede67.json",
"requirements_review_path": "documents/requirements-review-95c3c7c2c161-cad_f33e5741666b_inv_d66f499f88e.json",
"requirements_contract_path": "documents/requirements-contract-81aacd221c20-cad_f33e5741666b_inv_d66f499f88e.json",
"action_ledger_summary": [
{
"sequence": 1,
"at": "2026-08-31 21:45:42",
"draft_path": "documents/requirements-draft-v1-52034a7a7fb3-cad_f33e5741666b_inv_1a52b9be8bf.json",
"draft_revision": 1,
"event": "requirements_draft_updated",
"invocation_id": "cad_f33e5741666b_inv_1a52b9be8bf06814",
"item_count": 1
},
{
"sequence": 2,
"at": "2026-08-31 21:45:45",
"draft_revision": 1,
"event": "requirements_review_requested",
"invocation_id": "cad_f33e5741666b_inv_e6181bb6e6737114"
},
{
"sequence": 3,
"at": "2026-08-31 21:45:52",
"event": "requirements_evaluation_oracle_revise",
"invocation_id": "cad_f33e5741666b_inv_13615cb45e024404",
"missing_claims": [
{
"claim_kind": "solid_count_equals",
"expected": {
"value": 1
}
},
{
"claim_kind": "bbox_rank_dimension_mm",
"expected": {
"rank": "minimum",
"value": 10
}
}
],
"oracle_path": "documents/evaluation-contract-oracle-02e8267c3c9f.json",
"review_path": "documents/requirements-review-95c3c7c2c161-cad_f33e5741666b_inv_13615cb45e0.json"
},
{
"sequence": 4,
"at": "2026-08-31 21:46:06",
"draft_path": "documents/requirements-draft-v2-9bfc21fe46f3-cad_f33e5741666b_inv_9fc0d3ede67.json",
"draft_revision": 2,
"event": "requirements_draft_patched",
"invocation_id": "cad_f33e5741666b_inv_9fc0d3ede67c4278",
"item_count": 1
},
{
"sequence": 5,
"at": "2026-08-31 21:46:09",
"draft_revision": 2,
"event": "requirements_review_requested",
"invocation_id": "cad_f33e5741666b_inv_bd28b1223823c81b"
},
{
"sequence": 6,
"at": "2026-08-31 21:46:14",
"contract_hash": "a678ddef79ff62c5acb4b4eb9f971bd99419b5ac1e2b99f978095f889885b7fa",
"contract_path": "documents/requirements-contract-81aacd221c20-cad_f33e5741666b_inv_d66f499f88e.json",
"event": "requirements_contract_frozen",
"invocation_id": "cad_f33e5741666b_inv_d66f499f88e1a877",
"requirement_count": 1,
"review_path": "documents/requirements-review-95c3c7c2c161-cad_f33e5741666b_inv_d66f499f88e.json"
},
{
"sequence": 7,
"at": "2026-08-31 21:46:25",
"action_id": "act_007",
"atomic_id": "reference_axis",
"contract_hash": "2ebeda16a1fc50aefb0fa923794f43e609aca07dbd5059968824dfcf97532aaa",
"event": "proposed",
"expected_change": "Create a construction axis aligned with the intended collinear centerline of the three bore centers to anchor the hole chain and symmetric outer profile placement.",
"intent": "Establish the governing line for the three-hole link so the subsequent solid and bore features can be aligned and validated against the collinearity and spacing requirements.",
"requirement_ids": [
"req_001"
],
"working_head": "cad_f33e5741666b:root:v6"
},
{
"sequence": 8,
"at": "2026-08-31 21:46:33",
"event": "runtime_contract_invalid",
"message": "RUNTIME_CONTRACT_INVALID: materialized fragment violates the engine CDSL schema: CDSL engine runtime preflight failed: no_solid_feature",
"tool": "submit_cdsl_fragment"
}
],
"revisions": []
},
"usage": {
"calls": 9,
"prompt_tokens": 51902,
"completion_tokens": 2470,
"context_chars": 28101,
"records": [
{
"cache_hit": false,
"completion_tokens": 649,
"context_chars": 943,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 6146,
"provider_id": "openai",
"raw_arguments_hash": "b19258e1dc7c21ad8600f909b119edae726d030422a770a970c950cb505d4d1d",
"retry_reason": "",
"tool": "submit_requirements_draft_batch",
"total_tokens": 6795,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 80,
"context_chars": 1890,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 5069,
"provider_id": "openai",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"retry_reason": "",
"tool": "finalize_requirements_draft",
"total_tokens": 5149,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 71,
"context_chars": 2675,
"model_id": "gpt-5.5",
"prompt_tokens": 5442,
"provider_id": "openai",
"raw_arguments_hash": "00996cae282886750e3169d668db3145d5aad3fa73c825b1b9d5d423613bdb52",
"retry_reason": "",
"role": "reviewer",
"tool": "review_requirements",
"total_tokens": 5513,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 705,
"context_chars": 3344,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 7019,
"provider_id": "openai",
"raw_arguments_hash": "0bec493a0900a421be36a5eafc048432e5269e18ce91cfbda2cc6cc92bf6ca91",
"retry_reason": "",
"tool": "patch_requirements_draft",
"total_tokens": 7724,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 67,
"context_chars": 2085,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 5122,
"provider_id": "openai",
"raw_arguments_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a",
"retry_reason": "",
"tool": "finalize_requirements_draft",
"total_tokens": 5189,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 71,
"context_chars": 2848,
"model_id": "gpt-5.5",
"prompt_tokens": 5495,
"provider_id": "openai",
"raw_arguments_hash": "00996cae282886750e3169d668db3145d5aad3fa73c825b1b9d5d423613bdb52",
"retry_reason": "",
"role": "reviewer",
"tool": "review_requirements",
"total_tokens": 5566,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 629,
"context_chars": 3484,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 5621,
"provider_id": "openai",
"raw_arguments_hash": "50d575f27e01a7d18e6e9da02780f925a8a02be74a4567de353d75e7d5201c1d",
"retry_reason": "",
"tool": "propose_next_action",
"total_tokens": 6250,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 39,
"context_chars": 4250,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 5667,
"provider_id": "openai",
"raw_arguments_hash": "da6ac94271d9307113e951d5504e2663bc25f269a3651e2ba9188008598c991d",
"retry_reason": "",
"tool": "get_cdsl_operation_contract",
"total_tokens": 5706,
"usage_available": true
},
{
"cache_hit": false,
"completion_tokens": 159,
"context_chars": 6582,
"model_id": "gpt-5.4-mini",
"prompt_tokens": 6321,
"provider_id": "openai",
"raw_arguments_hash": "5d765f7c73529ff5eb581f942d4c8d73d3f18d16bfe27d414a8bdb395c9917fa",
"retry_reason": "",
"tool": "submit_cdsl_fragment",
"total_tokens": 6480,
"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": [
"8708cfc7917d0ba75d5a",
"a5ef679a80e50dc49411",
"9ab89802bac5f790dc3c",
"9818d45d7a259e06f7dc",
"bcb545bbd790c6201392",
"59efa49cf2351ae2a589",
"7b19e057b103205004fb"
],
"tool_audits": [
{
"audit_id": 1,
"at": "2026-08-31 21:45:42",
"actor": "author",
"tool": "submit_requirements_draft_batch",
"raw_arguments_hash": "b19258e1dc7c21ad8600f909b119edae726d030422a770a970c950cb505d4d1d",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_f33e5741666b:root:v0",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_f33e5741666b: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 21:45:45",
"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_f33e5741666b:root:v1",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_f33e5741666b: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 21:45:52",
"actor": "reviewer",
"tool": "review_requirements",
"raw_arguments_hash": "00996cae282886750e3169d668db3145d5aad3fa73c825b1b9d5d423613bdb52",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_f33e5741666b:root:v2",
"phase": "REVIEWING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_f33e5741666b: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 21:46:06",
"actor": "author",
"tool": "patch_requirements_draft",
"raw_arguments_hash": "0bec493a0900a421be36a5eafc048432e5269e18ce91cfbda2cc6cc92bf6ca91",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_f33e5741666b:root:v3",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_f33e5741666b: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 21:46:09",
"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_f33e5741666b:root:v4",
"phase": "DRAFTING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_f33e5741666b: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 21:46:14",
"actor": "reviewer",
"tool": "review_requirements",
"raw_arguments_hash": "00996cae282886750e3169d668db3145d5aad3fa73c825b1b9d5d423613bdb52",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_f33e5741666b:root:v5",
"phase": "REVIEWING_REQUIREMENTS",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_f33e5741666b: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 21:46:25",
"actor": "author",
"tool": "propose_next_action",
"raw_arguments_hash": "50d575f27e01a7d18e6e9da02780f925a8a02be74a4567de353d75e7d5201c1d",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "",
"contract_hash_current": true,
"expected_working_head": "cad_f33e5741666b:root:v6",
"phase": "AWAITING_ACTION",
"selector_snapshot_id": "",
"supplied_working_head": "cad_f33e5741666b:root:v6",
"working_head": "cad_f33e5741666b: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 21:46:28",
"actor": "author",
"tool": "get_cdsl_operation_contract",
"raw_arguments_hash": "da6ac94271d9307113e951d5504e2663bc25f269a3651e2ba9188008598c991d",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "2ebeda16a1fc50aefb0fa923794f43e609aca07dbd5059968824dfcf97532aaa",
"contract_hash_current": true,
"expected_working_head": "cad_f33e5741666b:root:v7",
"phase": "ACTION_PENDING",
"selector_snapshot_id": "",
"supplied_working_head": "cad_f33e5741666b:root:v7",
"working_head": "cad_f33e5741666b: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 21:46:33",
"actor": "author",
"tool": "submit_cdsl_fragment",
"raw_arguments_hash": "5d765f7c73529ff5eb581f942d4c8d73d3f18d16bfe27d414a8bdb395c9917fa",
"canonical_schema_valid": true,
"field_errors": [],
"state_binding": {
"active_revision": "",
"binding_valid": true,
"contract_hash": "2ebeda16a1fc50aefb0fa923794f43e609aca07dbd5059968824dfcf97532aaa",
"contract_hash_current": true,
"expected_working_head": "cad_f33e5741666b:root:v7",
"phase": "ACTION_PENDING",
"selector_snapshot_id": "",
"supplied_working_head": "",
"working_head": "cad_f33e5741666b: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/20260831T214103Z/artifacts/cad_f33e5741666b",
"action_ledger_path": "/Users/lk/Projects/cdsl-cad/backend/live-evals/20260831T214103Z/artifacts/cad_f33e5741666b/actions/action-ledger.jsonl",
"artifact_manifest": {
"schema_version": "cad.live-eval-artifact-manifest.v1",
"artifact_root": "/Users/lk/Projects/cdsl-cad/backend/live-evals/20260831T214103Z/artifacts/cad_f33e5741666b",
"files": [
{
"path": "actions/action-ledger.jsonl",
"sha256": "377f7a8d6480c637b6f479e733f1953b8c3c84f82b02cf568d08335cda73a1e6"
},
{
"path": "completion.md",
"sha256": "565ab1afd91ffcb9d8718b0641f7dbd6a02e595bfb65a61518efeb6cfcc12805"
},
{
"path": "documents/requirements-contract-81aacd221c20-cad_f33e5741666b_inv_d66f499f88e.json",
"sha256": "0fd2292217ca92803479849d7b91581d100965be4ecba7d8db4e186e4c891c19"
},
{
"path": "documents/requirements-draft-v1-52034a7a7fb3-cad_f33e5741666b_inv_1a52b9be8bf.json",
"sha256": "b1cd25a734ff558e1b9c31564925d2b4c08ebd0b66d726c131bec3d8640ddc8a"
},
{
"path": "documents/requirements-draft-v2-9bfc21fe46f3-cad_f33e5741666b_inv_9fc0d3ede67.json",
"sha256": "7ed22e0b731678d8ff6e75aa295c7747a3f779b39142fae6af105c7c7899b8af"
},
{
"path": "documents/requirements-review-95c3c7c2c161-cad_f33e5741666b_inv_13615cb45e0.json",
"sha256": "674ff2208e459c4f4a86fa8e9edd0d6dbb98ffcad37ad7a2bff96bc7d0ec5423"
},
{
"path": "documents/requirements-review-95c3c7c2c161-cad_f33e5741666b_inv_d66f499f88e.json",
"sha256": "674ff2208e459c4f4a86fa8e9edd0d6dbb98ffcad37ad7a2bff96bc7d0ec5423"
},
{
"path": "requirements-contract.json",
"sha256": "0fd2292217ca92803479849d7b91581d100965be4ecba7d8db4e186e4c891c19"
},
{
"path": "requirements-index.json",
"sha256": "ef8a528abbba9fbeaa74d3072791ff609d674e629c2b398ba6cab5f373a1f310"
},
{
"path": "requirements.md",
"sha256": "26f23eb67e57f56c6f51b1c56e922f343338b12bc86caf596b3b87b76801dc28"
}
]
},
"ledger": [
{
"sequence": 1,
"at": "2026-08-31 21:45:42",
"draft_path": "documents/requirements-draft-v1-52034a7a7fb3-cad_f33e5741666b_inv_1a52b9be8bf.json",
"draft_revision": 1,
"event": "requirements_draft_updated",
"invocation_id": "cad_f33e5741666b_inv_1a52b9be8bf06814",
"item_count": 1
},
{
"sequence": 2,
"at": "2026-08-31 21:45:45",
"draft_revision": 1,
"event": "requirements_review_requested",
"invocation_id": "cad_f33e5741666b_inv_e6181bb6e6737114"
},
{
"sequence": 3,
"at": "2026-08-31 21:45:52",
"event": "requirements_evaluation_oracle_revise",
"invocation_id": "cad_f33e5741666b_inv_13615cb45e024404",
"missing_claims": [
{
"claim_kind": "solid_count_equals",
"expected": {
"value": 1
}
},
{
"claim_kind": "bbox_rank_dimension_mm",
"expected": {
"rank": "minimum",
"value": 10
}
}
],
"oracle_path": "documents/evaluation-contract-oracle-02e8267c3c9f.json",
"review_path": "documents/requirements-review-95c3c7c2c161-cad_f33e5741666b_inv_13615cb45e0.json"
},
{
"sequence": 4,
"at": "2026-08-31 21:46:06",
"draft_path": "documents/requirements-draft-v2-9bfc21fe46f3-cad_f33e5741666b_inv_9fc0d3ede67.json",
"draft_revision": 2,
"event": "requirements_draft_patched",
"invocation_id": "cad_f33e5741666b_inv_9fc0d3ede67c4278",
"item_count": 1
},
{
"sequence": 5,
"at": "2026-08-31 21:46:09",
"draft_revision": 2,
"event": "requirements_review_requested",
"invocation_id": "cad_f33e5741666b_inv_bd28b1223823c81b"
},
{
"sequence": 6,
"at": "2026-08-31 21:46:14",
"contract_hash": "a678ddef79ff62c5acb4b4eb9f971bd99419b5ac1e2b99f978095f889885b7fa",
"contract_path": "documents/requirements-contract-81aacd221c20-cad_f33e5741666b_inv_d66f499f88e.json",
"event": "requirements_contract_frozen",
"invocation_id": "cad_f33e5741666b_inv_d66f499f88e1a877",
"requirement_count": 1,
"review_path": "documents/requirements-review-95c3c7c2c161-cad_f33e5741666b_inv_d66f499f88e.json"
},
{
"sequence": 7,
"at": "2026-08-31 21:46:25",
"action_id": "act_007",
"atomic_id": "reference_axis",
"contract_hash": "2ebeda16a1fc50aefb0fa923794f43e609aca07dbd5059968824dfcf97532aaa",
"event": "proposed",
"expected_change": "Create a construction axis aligned with the intended collinear centerline of the three bore centers to anchor the hole chain and symmetric outer profile placement.",
"intent": "Establish the governing line for the three-hole link so the subsequent solid and bore features can be aligned and validated against the collinearity and spacing requirements.",
"requirement_ids": [
"req_001"
],
"working_head": "cad_f33e5741666b:root:v6"
},
{
"sequence": 8,
"at": "2026-08-31 21:46:33",
"event": "runtime_contract_invalid",
"message": "RUNTIME_CONTRACT_INVALID: materialized fragment violates the engine CDSL schema: CDSL engine runtime preflight failed: no_solid_feature",
"tool": "submit_cdsl_fragment"
}
],
"invocations": [
{
"invocation_id": "cad_f33e5741666b_inv_1a52b9be8bf06814",
"idempotency_key": "c9afd0b93a6f4da3d0672c5b9efdf27f184ec1d621de415554332d85e10753d2",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"draft_revision": 1,
"draft_ids": [
"draft_001"
]
}
},
"created_at": "2026-08-31 21:45:42",
"updated_at": "2026-08-31 21:45:42"
},
{
"invocation_id": "cad_f33e5741666b_inv_e6181bb6e6737114",
"idempotency_key": "68f980bd213694877c5680944f0ff6820fbdda6c8618e340e02554f78ec900a3",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "REVIEWING_REQUIREMENTS",
"draft_revision": 1
}
},
"created_at": "2026-08-31 21:45:45",
"updated_at": "2026-08-31 21:45:45"
},
{
"invocation_id": "cad_f33e5741666b_inv_13615cb45e024404",
"idempotency_key": "d0ac7b93ecb9ae064d4ed756b44826e343199cbf2cc725ba91794415f06ec1e0",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "DRAFTING_REQUIREMENTS",
"review": {
"schema_version": "cad.requirements-evaluation-oracle.v1",
"task_id": "cad_f33e5741666b",
"evaluation_only": true,
"verdict": "revise",
"draft_revision": 1,
"reviewer_verdict": "pass",
"reviewer_review_path": "documents/requirements-review-95c3c7c2c161-cad_f33e5741666b_inv_13615cb45e0.json",
"item_verdicts": [
{
"draft_id": "draft_001",
"verdict": "revise",
"reason_code": "evaluation_contract_oracle"
}
],
"issues": [
"The external live-evaluation contract oracle found missing executable acceptance claims."
],
"missing_claims": [
{
"claim_kind": "solid_count_equals",
"expected": {
"value": 1
}
},
{
"claim_kind": "bbox_rank_dimension_mm",
"expected": {
"rank": "minimum",
"value": 10
}
}
]
},
"reviewer_review_path": "documents/requirements-review-95c3c7c2c161-cad_f33e5741666b_inv_13615cb45e0.json",
"evaluation_oracle": {
"missing_claims": [
{
"claim_kind": "solid_count_equals",
"expected": {
"value": 1
}
},
{
"claim_kind": "bbox_rank_dimension_mm",
"expected": {
"rank": "minimum",
"value": 10
}
}
]
}
}
},
"created_at": "2026-08-31 21:45:52",
"updated_at": "2026-08-31 21:45:52"
},
{
"invocation_id": "cad_f33e5741666b_inv_9fc0d3ede67c4278",
"idempotency_key": "34a02f3f2b00f9672b9b16b67fe96373c4a0b2754aca68c3ee4d504efe2718b2",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"draft_revision": 2,
"item_count": 1
}
},
"created_at": "2026-08-31 21:46:06",
"updated_at": "2026-08-31 21:46:06"
},
{
"invocation_id": "cad_f33e5741666b_inv_bd28b1223823c81b",
"idempotency_key": "cb7f1a83bdb95da04f9d88f20ec0685dad5f141aa29870c2ee0cbdb6b9d9051e",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "REVIEWING_REQUIREMENTS",
"draft_revision": 2
}
},
"created_at": "2026-08-31 21:46:09",
"updated_at": "2026-08-31 21:46:09"
},
{
"invocation_id": "cad_f33e5741666b_inv_d66f499f88e1a877",
"idempotency_key": "0ef92b3031e37d20092e21bae8ef06fe67a36562e05787f8f0b2ef8192ff633e",
"status": "finished",
"result": {
"result_type": "accepted",
"payload": {
"phase": "AWAITING_ACTION",
"contract_hash": "a678ddef79ff62c5acb4b4eb9f971bd99419b5ac1e2b99f978095f889885b7fa"
}
},
"created_at": "2026-08-31 21:46:14",
"updated_at": "2026-08-31 21:46:14"
},
{
"invocation_id": "cad_f33e5741666b_inv_6c6ba112a19f2ecf",
"idempotency_key": "6045bee704541eef5cbfe2057a6fd79d8a2ffe2d447430166d1f2d3bd0fc1c9e",
"status": "finished",
"result": {
"action_id": "act_007",
"working_head": "cad_f33e5741666b:root:v6",
"atomic_id": "reference_axis",
"contract_hash": "2ebeda16a1fc50aefb0fa923794f43e609aca07dbd5059968824dfcf97532aaa"
},
"created_at": "2026-08-31 21:46:25",
"updated_at": "2026-08-31 21:46:25"
}
],
"event_audit": [
{
"name": "tool_call",
"tool": "submit_requirements_draft_batch",
"status": "success",
"code": "",
"raw_arguments_hash": "b19258e1dc7c21ad8600f909b119edae726d030422a770a970c950cb505d4d1d",
"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": "0bec493a0900a421be36a5eafc048432e5269e18ce91cfbda2cc6cc92bf6ca91",
"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": "50d575f27e01a7d18e6e9da02780f925a8a02be74a4567de353d75e7d5201c1d",
"field_errors": []
},
{
"name": "tool_call",
"tool": "get_cdsl_operation_contract",
"status": "success",
"code": "",
"raw_arguments_hash": "da6ac94271d9307113e951d5504e2663bc25f269a3651e2ba9188008598c991d",
"field_errors": []
},
{
"name": "candidate_result",
"tool": "submit_cdsl_fragment",
"status": "error",
"code": "RUNTIME_CONTRACT_INVALID",
"raw_arguments_hash": "5d765f7c73529ff5eb581f942d4c8d73d3f18d16bfe27d414a8bdb395c9917fa",
"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/20260831T214103Z"
}