140 lines
5.2 KiB
JSON
140 lines
5.2 KiB
JSON
{
|
|
"artifact": "leo_post_deploy_direct_claim_repeat_proof",
|
|
"generated_at_utc": "2026-07-13T00:43:12Z",
|
|
"deployed_commit": "0183a5c805fa3b51d638267afd20f67a1bc3777f",
|
|
"deployed_skill_sha256": "0af66196c20a25370dac88365e4df4ae5e634bc81140675379cf899404b249ba",
|
|
"trial_count": 3,
|
|
"total_replies": 18,
|
|
"all_runtime_pass": true,
|
|
"all_scores_pass": true,
|
|
"all_db_counts_unchanged": true,
|
|
"all_service_identity_unchanged": true,
|
|
"all_temp_profiles_removed": true,
|
|
"telegram_messages_sent": false,
|
|
"live_profile_changed": false,
|
|
"production_apply_executed": false,
|
|
"orphan_temp_directories_after_trials": [],
|
|
"trials": [
|
|
{
|
|
"trial": 1,
|
|
"run_id": "bdefcfe98ba2",
|
|
"generated_at_utc": "2026-07-13T00:35:11.035868+00:00",
|
|
"runtime_pass": true,
|
|
"score_pass": true,
|
|
"passes": 6,
|
|
"expected_prompt_count": 6,
|
|
"failures": [],
|
|
"responses": 6,
|
|
"db_counts_before": {
|
|
"kb_stage.kb_proposals": 26,
|
|
"public.claim_edges": 4916,
|
|
"public.claim_evidence": 4670,
|
|
"public.claims": 1837,
|
|
"public.sources": 4145
|
|
},
|
|
"db_counts_after": {
|
|
"kb_stage.kb_proposals": 26,
|
|
"public.claim_edges": 4916,
|
|
"public.claim_evidence": 4670,
|
|
"public.claims": 1837,
|
|
"public.sources": 4145
|
|
},
|
|
"db_counts_changed": false,
|
|
"posted_to_telegram": false,
|
|
"changed_live_profile": false,
|
|
"mutates_kb_by_harness": false,
|
|
"service_unchanged": true,
|
|
"service_after": {
|
|
"ActiveState": "active",
|
|
"ExecMainStartTimestamp": "Sun 2026-07-12 09:14:10 UTC",
|
|
"MainPID": "2403328",
|
|
"NRestarts": "0",
|
|
"SubState": "running"
|
|
},
|
|
"temp_profile_removed": true,
|
|
"handler_path": "/Users/user/Documents/Codex/2026-07-09/019f34eb-d297-72d0-b7e2-b222d5515ab9-load/outputs/leo-post-deploy-direct-claim-repeat-20260713/trial-1-handler.json",
|
|
"score_path": "/Users/user/Documents/Codex/2026-07-09/019f34eb-d297-72d0-b7e2-b222d5515ab9-load/outputs/leo-post-deploy-direct-claim-repeat-20260713/trial-1-score.json"
|
|
},
|
|
{
|
|
"trial": 2,
|
|
"run_id": "f68219fcbca7",
|
|
"generated_at_utc": "2026-07-13T00:37:25.661024+00:00",
|
|
"runtime_pass": true,
|
|
"score_pass": true,
|
|
"passes": 6,
|
|
"expected_prompt_count": 6,
|
|
"failures": [],
|
|
"responses": 6,
|
|
"db_counts_before": {
|
|
"kb_stage.kb_proposals": 26,
|
|
"public.claim_edges": 4916,
|
|
"public.claim_evidence": 4670,
|
|
"public.claims": 1837,
|
|
"public.sources": 4145
|
|
},
|
|
"db_counts_after": {
|
|
"kb_stage.kb_proposals": 26,
|
|
"public.claim_edges": 4916,
|
|
"public.claim_evidence": 4670,
|
|
"public.claims": 1837,
|
|
"public.sources": 4145
|
|
},
|
|
"db_counts_changed": false,
|
|
"posted_to_telegram": false,
|
|
"changed_live_profile": false,
|
|
"mutates_kb_by_harness": false,
|
|
"service_unchanged": true,
|
|
"service_after": {
|
|
"ActiveState": "active",
|
|
"ExecMainStartTimestamp": "Sun 2026-07-12 09:14:10 UTC",
|
|
"MainPID": "2403328",
|
|
"NRestarts": "0",
|
|
"SubState": "running"
|
|
},
|
|
"temp_profile_removed": true,
|
|
"handler_path": "/Users/user/Documents/Codex/2026-07-09/019f34eb-d297-72d0-b7e2-b222d5515ab9-load/outputs/leo-post-deploy-direct-claim-repeat-20260713/trial-2-handler.json",
|
|
"score_path": "/Users/user/Documents/Codex/2026-07-09/019f34eb-d297-72d0-b7e2-b222d5515ab9-load/outputs/leo-post-deploy-direct-claim-repeat-20260713/trial-2-score.json"
|
|
},
|
|
{
|
|
"trial": 3,
|
|
"run_id": "05810612557f",
|
|
"generated_at_utc": "2026-07-13T00:39:30.991053+00:00",
|
|
"runtime_pass": true,
|
|
"score_pass": true,
|
|
"passes": 6,
|
|
"expected_prompt_count": 6,
|
|
"failures": [],
|
|
"responses": 6,
|
|
"db_counts_before": {
|
|
"kb_stage.kb_proposals": 26,
|
|
"public.claim_edges": 4916,
|
|
"public.claim_evidence": 4670,
|
|
"public.claims": 1837,
|
|
"public.sources": 4145
|
|
},
|
|
"db_counts_after": {
|
|
"kb_stage.kb_proposals": 26,
|
|
"public.claim_edges": 4916,
|
|
"public.claim_evidence": 4670,
|
|
"public.claims": 1837,
|
|
"public.sources": 4145
|
|
},
|
|
"db_counts_changed": false,
|
|
"posted_to_telegram": false,
|
|
"changed_live_profile": false,
|
|
"mutates_kb_by_harness": false,
|
|
"service_unchanged": true,
|
|
"service_after": {
|
|
"ActiveState": "active",
|
|
"ExecMainStartTimestamp": "Sun 2026-07-12 09:14:10 UTC",
|
|
"MainPID": "2403328",
|
|
"NRestarts": "0",
|
|
"SubState": "running"
|
|
},
|
|
"temp_profile_removed": true,
|
|
"handler_path": "/Users/user/Documents/Codex/2026-07-09/019f34eb-d297-72d0-b7e2-b222d5515ab9-load/outputs/leo-post-deploy-direct-claim-repeat-20260713/trial-3-handler.json",
|
|
"score_path": "/Users/user/Documents/Codex/2026-07-09/019f34eb-d297-72d0-b7e2-b222d5515ab9-load/outputs/leo-post-deploy-direct-claim-repeat-20260713/trial-3-score.json"
|
|
}
|
|
],
|
|
"claim_ceiling": "Three repeated post-deploy no-post GatewayRunner trials strict-scored 6/6 with unchanged production DB counts and gateway identity. This proves repeated handler behavior, not a corrected Telegram-visible reply or production KB mutation."
|
|
}
|