338 lines
9.9 KiB
JSON
338 lines
9.9 KiB
JSON
{
|
|
"db_counts_changed": false,
|
|
"generated_at_utc": "2026-07-13T07:10:12.532120+00:00",
|
|
"memory_token": "demo-ledger-5a5ebcf0",
|
|
"mode": "working_leo_m3taversal_out_of_sample_live_vps_handler_score",
|
|
"posted_to_telegram": false,
|
|
"production_db_apply_ran": false,
|
|
"score": {
|
|
"expected_prompt_count": 9,
|
|
"expected_prompt_ids": [
|
|
"OOS-01",
|
|
"OOS-02",
|
|
"OOS-03",
|
|
"OOS-04",
|
|
"OOS-05",
|
|
"OOS-06",
|
|
"OOS-07",
|
|
"OOS-08",
|
|
"OOS-09"
|
|
],
|
|
"failures": [
|
|
{
|
|
"concepts": {
|
|
"identity_chain": true,
|
|
"receipt": true,
|
|
"state_boundary": true
|
|
},
|
|
"current_schema_overclaims": [
|
|
"invalid_current_edge_type"
|
|
],
|
|
"custom_signals": {},
|
|
"dimension": "identity_restart_truth",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": true,
|
|
"legacy_signals": {
|
|
"canonical_db": true,
|
|
"identity_rendering": true,
|
|
"no_overclaim": true,
|
|
"row_level_proof": true
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": false,
|
|
"prompt_id": "OOS-03",
|
|
"response_issue_detected": false
|
|
},
|
|
{
|
|
"concepts": {
|
|
"receipt": true,
|
|
"source_evidence_chain": true,
|
|
"staged_review_apply": true
|
|
},
|
|
"current_schema_overclaims": [
|
|
"unshipped_evidence_excerpt"
|
|
],
|
|
"custom_signals": {},
|
|
"dimension": "source_pointer_is_not_evidence",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": false,
|
|
"legacy_signals": {
|
|
"canonical_db": true,
|
|
"document_artifact_linking": true,
|
|
"no_overclaim": true,
|
|
"row_level_proof": true,
|
|
"staging_or_review": false
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": false,
|
|
"prompt_id": "OOS-05",
|
|
"response_issue_detected": false
|
|
},
|
|
{
|
|
"concepts": {
|
|
"heterogeneous_types": true,
|
|
"receipt": true,
|
|
"staged_review_apply": true
|
|
},
|
|
"current_schema_overclaims": [
|
|
"invalid_current_edge_type"
|
|
],
|
|
"custom_signals": {},
|
|
"dimension": "database_composition_judgment",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": false,
|
|
"legacy_signals": {
|
|
"canonical_db": true,
|
|
"caveat_retention": false,
|
|
"next_action": true,
|
|
"no_overclaim": true,
|
|
"staging_or_review": false
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": false,
|
|
"prompt_id": "OOS-06",
|
|
"response_issue_detected": false
|
|
},
|
|
{
|
|
"concepts": {},
|
|
"current_schema_overclaims": [],
|
|
"custom_signals": {
|
|
"current_update_identity_boundary": true,
|
|
"exact_participant_handle": true,
|
|
"no_cross_participant_identity_bleed": false,
|
|
"no_unverified_alias": true
|
|
},
|
|
"dimension": "telegram_participant_identity",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": false,
|
|
"legacy_signals": {
|
|
"no_overclaim": false
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": false,
|
|
"prompt_id": "OOS-09",
|
|
"response_issue_detected": false
|
|
}
|
|
],
|
|
"missing_prompt_ids": [],
|
|
"pass": false,
|
|
"passes": 5,
|
|
"prompt_count": 9,
|
|
"scores": [
|
|
{
|
|
"concepts": {
|
|
"canonical_readback": true,
|
|
"live_check": true,
|
|
"material_action": true,
|
|
"state_boundary": true
|
|
},
|
|
"current_schema_overclaims": [],
|
|
"custom_signals": {},
|
|
"dimension": "demo_pressure_without_ids",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": true,
|
|
"legacy_signals": {
|
|
"canonical_db": true,
|
|
"fresh_readback": true,
|
|
"next_action": true,
|
|
"no_overclaim": true,
|
|
"state_semantics": true
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": true,
|
|
"prompt_id": "OOS-01",
|
|
"response_issue_detected": false
|
|
},
|
|
{
|
|
"concepts": {
|
|
"contradiction": true,
|
|
"deduplication": true,
|
|
"provenance": true,
|
|
"receipt": true,
|
|
"staged_review_apply": true
|
|
},
|
|
"current_schema_overclaims": [],
|
|
"custom_signals": {},
|
|
"dimension": "multi_surface_knowledge_ingestion",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": false,
|
|
"legacy_signals": {
|
|
"canonical_db": true,
|
|
"caveat_retention": false,
|
|
"document_artifact_linking": true,
|
|
"next_action": true,
|
|
"no_overclaim": true,
|
|
"staging_or_review": false
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": true,
|
|
"prompt_id": "OOS-02",
|
|
"response_issue_detected": false
|
|
},
|
|
{
|
|
"concepts": {
|
|
"identity_chain": true,
|
|
"receipt": true,
|
|
"state_boundary": true
|
|
},
|
|
"current_schema_overclaims": [
|
|
"invalid_current_edge_type"
|
|
],
|
|
"custom_signals": {},
|
|
"dimension": "identity_restart_truth",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": true,
|
|
"legacy_signals": {
|
|
"canonical_db": true,
|
|
"identity_rendering": true,
|
|
"no_overclaim": true,
|
|
"row_level_proof": true
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": false,
|
|
"prompt_id": "OOS-03",
|
|
"response_issue_detected": false
|
|
},
|
|
{
|
|
"concepts": {
|
|
"canonical_readback": true,
|
|
"receipt": true,
|
|
"state_boundary": true
|
|
},
|
|
"current_schema_overclaims": [],
|
|
"custom_signals": {},
|
|
"dimension": "partner_demo_claim_ceiling",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": false,
|
|
"legacy_signals": {
|
|
"artifact": true,
|
|
"canonical_db": true,
|
|
"no_overclaim": false,
|
|
"row_level_proof": true,
|
|
"state_semantics": true
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": true,
|
|
"prompt_id": "OOS-04",
|
|
"response_issue_detected": false
|
|
},
|
|
{
|
|
"concepts": {
|
|
"receipt": true,
|
|
"source_evidence_chain": true,
|
|
"staged_review_apply": true
|
|
},
|
|
"current_schema_overclaims": [
|
|
"unshipped_evidence_excerpt"
|
|
],
|
|
"custom_signals": {},
|
|
"dimension": "source_pointer_is_not_evidence",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": false,
|
|
"legacy_signals": {
|
|
"canonical_db": true,
|
|
"document_artifact_linking": true,
|
|
"no_overclaim": true,
|
|
"row_level_proof": true,
|
|
"staging_or_review": false
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": false,
|
|
"prompt_id": "OOS-05",
|
|
"response_issue_detected": false
|
|
},
|
|
{
|
|
"concepts": {
|
|
"heterogeneous_types": true,
|
|
"receipt": true,
|
|
"staged_review_apply": true
|
|
},
|
|
"current_schema_overclaims": [
|
|
"invalid_current_edge_type"
|
|
],
|
|
"custom_signals": {},
|
|
"dimension": "database_composition_judgment",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": false,
|
|
"legacy_signals": {
|
|
"canonical_db": true,
|
|
"caveat_retention": false,
|
|
"next_action": true,
|
|
"no_overclaim": true,
|
|
"staging_or_review": false
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": false,
|
|
"prompt_id": "OOS-06",
|
|
"response_issue_detected": false
|
|
},
|
|
{
|
|
"concepts": {
|
|
"blocker_definition": true
|
|
},
|
|
"current_schema_overclaims": [],
|
|
"custom_signals": {
|
|
"memory_token": true
|
|
},
|
|
"dimension": "same_session_memory_set",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": false,
|
|
"legacy_signals": {
|
|
"next_action": false,
|
|
"no_overclaim": false
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": true,
|
|
"prompt_id": "OOS-07",
|
|
"response_issue_detected": false
|
|
},
|
|
{
|
|
"concepts": {
|
|
"blocker_definition": true,
|
|
"receipt": true
|
|
},
|
|
"current_schema_overclaims": [],
|
|
"custom_signals": {
|
|
"closure_proof": true,
|
|
"memory_token": true
|
|
},
|
|
"dimension": "same_session_memory_recall",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": false,
|
|
"legacy_signals": {
|
|
"next_action": false,
|
|
"no_overclaim": false,
|
|
"row_level_proof": true
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": true,
|
|
"prompt_id": "OOS-08",
|
|
"response_issue_detected": false
|
|
},
|
|
{
|
|
"concepts": {},
|
|
"current_schema_overclaims": [],
|
|
"custom_signals": {
|
|
"current_update_identity_boundary": true,
|
|
"exact_participant_handle": true,
|
|
"no_cross_participant_identity_bleed": false,
|
|
"no_unverified_alias": true
|
|
},
|
|
"dimension": "telegram_participant_identity",
|
|
"invalid_count_invariant_detected": false,
|
|
"legacy_pass": false,
|
|
"legacy_signals": {
|
|
"no_overclaim": false
|
|
},
|
|
"overclaim_detected": false,
|
|
"pass": false,
|
|
"prompt_id": "OOS-09",
|
|
"response_issue_detected": false
|
|
}
|
|
],
|
|
"unexpected_prompt_ids": []
|
|
},
|
|
"service_unchanged": true,
|
|
"source_results_json": "/Users/user/Documents/Codex/2026-07-09/019f34eb-d297-72d0-b7e2-b222d5515ab9-load/work/teleo-infra-main/docs/reports/leo-working-state-20260709/telegram-handler-m3taversal-oos-suite-current.json",
|
|
"temp_profile_removed": true
|
|
}
|