176 lines
7.4 KiB
JSON
176 lines
7.4 KiB
JSON
{
|
|
"before_service": {
|
|
"ActiveState": "active",
|
|
"ExecMainStartTimestamp": "Tue 2026-07-14 00:25:49 UTC",
|
|
"MainPID": "366950",
|
|
"NRestarts": "0",
|
|
"SubState": "running"
|
|
},
|
|
"changed_live_profile": false,
|
|
"database_context_all_ok": true,
|
|
"database_context_injection_count": 1,
|
|
"database_context_trace": [
|
|
{
|
|
"compiled_response_available": true,
|
|
"contract_ids": [
|
|
"reply_budget",
|
|
"proposal_state_readback"
|
|
],
|
|
"contract_sha256": "e7c0b07ae30ff5cd38e62e5de3ebd7efaa05830448fb11c8e588c143fa33f873",
|
|
"event": "pre_llm_call",
|
|
"generated_at_utc": "2026-07-14T00:27:26.227305+00:00",
|
|
"injected": true,
|
|
"query_sha256": "4de6976f5e757d40e5f97a4f98c52ffcdc9261e412d23d5ab35efddceb19785d",
|
|
"source": "kb_tool.py --local context",
|
|
"status": "ok"
|
|
},
|
|
{
|
|
"compiled_response_enforced": true,
|
|
"compiled_response_issues": [],
|
|
"contract_ids": [
|
|
"proposal_state_readback",
|
|
"reply_budget"
|
|
],
|
|
"delivered_response_sha256": "0c501444d51851cdf706ca64c6646d9183841fc322d9b80f54d2dca9c371f9af",
|
|
"event": "post_llm_call",
|
|
"fail_closed": false,
|
|
"generated_at_utc": "2026-07-14T00:27:38.562438+00:00",
|
|
"issues": [
|
|
"missing_live_count_readback:proposal_state_readback",
|
|
"missing_live_proposal_state:applied",
|
|
"missing_live_proposal_state:approved",
|
|
"missing_live_proposal_state:canceled",
|
|
"missing_live_proposal_state:pending_review",
|
|
"missing_matching_proposal_readback",
|
|
"missing_proof_changing_followup",
|
|
"missing_proposal_apply_boundary"
|
|
],
|
|
"query_sha256": "4de6976f5e757d40e5f97a4f98c52ffcdc9261e412d23d5ab35efddceb19785d",
|
|
"response_sha256": "a82929d36f5767f370587c068964cb29c0cbeed25e6dadeccf507bf1ed646d03",
|
|
"status": "ok",
|
|
"transformed": true,
|
|
"validated": true
|
|
}
|
|
],
|
|
"database_response_transform_count": 1,
|
|
"database_response_validation_all_ok": true,
|
|
"database_response_validation_count": 1,
|
|
"db_counts_after": {
|
|
"kb_stage.kb_proposals": 29,
|
|
"public.claim_edges": 4916,
|
|
"public.claim_evidence": 4670,
|
|
"public.claims": 1837,
|
|
"public.sources": 4145
|
|
},
|
|
"db_counts_before": {
|
|
"kb_stage.kb_proposals": 29,
|
|
"public.claim_edges": 4916,
|
|
"public.claim_evidence": 4670,
|
|
"public.claims": 1837,
|
|
"public.sources": 4145
|
|
},
|
|
"db_counts_changed": false,
|
|
"generated_at_utc": "2026-07-14T00:27:23.161266+00:00",
|
|
"handler": {
|
|
"authorized": true,
|
|
"session_key": "agent:main:telegram:group:-5146042086:9070919",
|
|
"temp_profile": "/tmp/leo-direct-claim-handler-wxc88297/profile"
|
|
},
|
|
"harness_notes": [
|
|
"One broad no-context post-restart state-semantics probe; no Telegram post and no DB mutation.",
|
|
"The harness uses a temporary copy of the leoclean profile and does not post to Telegram.",
|
|
"This proves handler-level live VPS GatewayRunner behavior, not human-visible Telegram delivery."
|
|
],
|
|
"mode": "live_vps_gatewayrunner_temp_profile_v3_post_restart",
|
|
"mutates_kb_by_harness": false,
|
|
"pass_runtime": true,
|
|
"posted_to_telegram": false,
|
|
"remote_report_path": "/tmp/leo-v3-post-restart-88c0cf0dfef1.json",
|
|
"remote_returncode": 0,
|
|
"remote_run_id": "88c0cf0dfef1",
|
|
"results": [
|
|
{
|
|
"claim_ceiling": "Live VPS GatewayRunner reply from temp leoclean profile; no Telegram post; no production DB apply authorized.",
|
|
"database_context_trace": [
|
|
{
|
|
"compiled_response_available": true,
|
|
"contract_ids": [
|
|
"reply_budget",
|
|
"proposal_state_readback"
|
|
],
|
|
"contract_sha256": "e7c0b07ae30ff5cd38e62e5de3ebd7efaa05830448fb11c8e588c143fa33f873",
|
|
"event": "pre_llm_call",
|
|
"generated_at_utc": "2026-07-14T00:27:26.227305+00:00",
|
|
"injected": true,
|
|
"query_sha256": "4de6976f5e757d40e5f97a4f98c52ffcdc9261e412d23d5ab35efddceb19785d",
|
|
"source": "kb_tool.py --local context",
|
|
"status": "ok"
|
|
},
|
|
{
|
|
"compiled_response_enforced": true,
|
|
"compiled_response_issues": [],
|
|
"contract_ids": [
|
|
"proposal_state_readback",
|
|
"reply_budget"
|
|
],
|
|
"delivered_response_sha256": "0c501444d51851cdf706ca64c6646d9183841fc322d9b80f54d2dca9c371f9af",
|
|
"event": "post_llm_call",
|
|
"fail_closed": false,
|
|
"generated_at_utc": "2026-07-14T00:27:38.562438+00:00",
|
|
"issues": [
|
|
"missing_live_count_readback:proposal_state_readback",
|
|
"missing_live_proposal_state:applied",
|
|
"missing_live_proposal_state:approved",
|
|
"missing_live_proposal_state:canceled",
|
|
"missing_live_proposal_state:pending_review",
|
|
"missing_matching_proposal_readback",
|
|
"missing_proof_changing_followup",
|
|
"missing_proposal_apply_boundary"
|
|
],
|
|
"query_sha256": "4de6976f5e757d40e5f97a4f98c52ffcdc9261e412d23d5ab35efddceb19785d",
|
|
"response_sha256": "a82929d36f5767f370587c068964cb29c0cbeed25e6dadeccf507bf1ed646d03",
|
|
"status": "ok",
|
|
"transformed": true,
|
|
"validated": true
|
|
}
|
|
],
|
|
"dimension": "pending_document_is_not_canonical",
|
|
"ended_at_utc": "2026-07-14T00:27:38.671539+00:00",
|
|
"evidence_tier": "live_vps_gatewayrunner_temp_profile",
|
|
"mutates_kb": false,
|
|
"ok": true,
|
|
"prompt": "Someone says the V3 architecture document is already part of Leo's live knowledge because a proposal exists. What is actually true right now, what would you inspect, and what must happen before those claims are canonical? Do not mutate anything.",
|
|
"prompt_id": "V3-POST-RESTART-01",
|
|
"reply": "No.\nFresh live readback.\nDB readback: claims: 1837; sources: 4145; claim_edges: 4916; claim_evidence: 4670; kb_proposals: 29.\nDB readback: proposal: 10bc0719-1c2b-5f42-a41e-86e6478692cb; status: pending_review; applied_at: none; source_ref: normalized:12e38cb0-b72b-557c-95e5-ffc789a29f62:72895c9b58b79d41; readiness: needs_human_review.\nProposal states are applied: 2, approved: 3, pending_review: 16, canceled: 8. Approved is not applied. The matching proposal remains pending_review and applied_at is empty, so it has not reached canonical apply. A proposal row is not canonical knowledge without the guarded apply receipt and row-level public.* postflight.\n\nNext proof-changing follow-up: inspect the matching proposal payload and exact source binding, complete human review, obtain explicit guarded-apply authorization, then return non-null applied_at plus the created public.* row IDs and hashes.",
|
|
"started_at_utc": "2026-07-14T00:27:23.632357+00:00",
|
|
"turn": 1
|
|
}
|
|
],
|
|
"service_before_after": {
|
|
"after": {
|
|
"ActiveState": "active",
|
|
"ExecMainStartTimestamp": "Tue 2026-07-14 00:25:49 UTC",
|
|
"MainPID": "366950",
|
|
"NRestarts": "0",
|
|
"SubState": "running"
|
|
},
|
|
"before": {
|
|
"ActiveState": "active",
|
|
"ExecMainStartTimestamp": "Tue 2026-07-14 00:25:49 UTC",
|
|
"MainPID": "366950",
|
|
"NRestarts": "0",
|
|
"SubState": "running"
|
|
},
|
|
"unchanged_from_preexisting_live_readback": true
|
|
},
|
|
"source": {
|
|
"chat_id": "-5146042086",
|
|
"chat_name": "Leo",
|
|
"chat_type": "group",
|
|
"platform": "telegram",
|
|
"user_id": "9070919",
|
|
"user_name": "codex handler direct claim"
|
|
},
|
|
"source_report_path": "/tmp/leo-v3-post-restart-handler.json",
|
|
"temp_profile_removed": true
|
|
}
|