699a9e7917
Some checks are pending
CI / lint-and-test (push) Waiting to run
- Add reusable Teleo/Leo skills for VPS, GCP, Telegram, KB changes, provenance, and handoff onboarding. - Add guarded KB proposal tooling for approved rich proposals, apply packets, and rollback proof. - Add Cory-style open-ended benchmark prompts and tests alongside the precise regression canaries. `.agents/skills/leo-telegram-canary-ops/SKILL.md` `.agents/skills/teleo-gcp-parity-ops/SKILL.md` `.agents/skills/teleo-infra-provenance/SKILL.md` `.agents/skills/teleo-kb-db-change-workflow/SKILL.md` `.agents/skills/teleo-leo-onboarding/SKILL.md` `.agents/skills/teleo-proof-handoff/SKILL.md` `.agents/skills/teleo-vps-runtime-ops/SKILL.md` `.agents/skills/working-leo-cory-outcomes/SKILL.md` `docs/reports/leo-working-state-20260709/claim-source-contract-preview-current.md` `docs/reports/leo-working-state-20260709/cory-expected-working-leo-outcomes-20260709.md` `docs/reports/leo-working-state-20260709/current-truth-index.md` `docs/reports/leo-working-state-20260709/fable-leo-teleo-onboarding.md` `docs/reports/leo-working-state-20260709/gcp-db-parity-current-blocker-20260709.json` `docs/reports/leo-working-state-20260709/helmer-7powers-creation-plan.json` `docs/reports/leo-working-state-20260709/kb-apply-canary-execute-current.md` `docs/reports/leo-working-state-20260709/kb-apply-canary-plan-current.md` `docs/reports/leo-working-state-20260709/leo-db-state-13-skill-pack.svg` `docs/reports/leo-working-state-20260709/operator-surface-map.md` `docs/reports/leo-working-state-20260709/production-apply-packet-current.md` `docs/reports/leo-working-state-20260709/rich-proposal-creation-plan-mapped-current.md` `docs/reports/leo-working-state-20260709/skill-pack-manifest.json` `docs/reports/leo-working-state-20260709/skill-pack-readme.md` `docs/reports/leo-working-state-20260709/telegram-gateway-handler-canary-current.json` `docs/reports/leo-working-state-20260709/telegram-gateway-handler-canary-current.md` `docs/reports/leo-working-state-20260709/telegram-live-canary-current.json` `docs/reports/leo-working-state-20260709/telegram-live-canary-current.md` `docs/reports/leo-working-state-20260709/telegram-live-db-write-canary-20260709.json` `docs/reports/leo-working-state-20260709/telegram-live-db-write-canary-20260709.md` `docs/reports/leo-working-state-20260709/working-leo-current-state-20260709.md` `docs/reports/leo-working-state-20260709/working-leo-definition-20260709.md` `docs/reports/leo-working-state-20260709/working-leo-execution-plan-current.md` `docs/reports/leo-working-state-20260709/working-leo-open-ended-benchmark-spec.json` `scripts/approve_proposal.py` `scripts/kb_claim_source_contract_preview.py` `scripts/kb_rich_proposal_apply_packet.py` `scripts/kb_rich_proposal_creation_plan.py` `scripts/working_leo_open_ended_benchmark.py` `tests/test_approve_proposal.py` `tests/test_kb_claim_source_contract_preview.py` `tests/test_kb_rich_proposal_apply_packet.py` `tests/test_kb_rich_proposal_creation_plan.py` `tests/test_working_leo_open_ended_benchmark.py`
109 lines
8.2 KiB
JSON
109 lines
8.2 KiB
JSON
{
|
|
"generated_at_utc": "2026-07-09T19:14:57.821433+00:00",
|
|
"pass": true,
|
|
"remote": {
|
|
"parse_error": "remote stdout contained no parseable JSON object line",
|
|
"parsed": {
|
|
"after_service": {
|
|
"ActiveState": "active",
|
|
"ExecMainStartTimestamp": "Thu 2026-07-09 06:59:44 UTC",
|
|
"MainPID": "3252143",
|
|
"NRestarts": "0",
|
|
"SubState": "running"
|
|
},
|
|
"before_service": {
|
|
"ActiveState": "active",
|
|
"ExecMainStartTimestamp": "Thu 2026-07-09 06:59:44 UTC",
|
|
"MainPID": "3252143",
|
|
"NRestarts": "0",
|
|
"SubState": "running"
|
|
},
|
|
"changed_live_profile": false,
|
|
"generated_at_utc": "2026-07-09T19:13:43.157568+00:00",
|
|
"handler": {
|
|
"authorized": true,
|
|
"session_key": "agent:main:telegram:group:-5146042086:9070919",
|
|
"temp_profile": "/tmp/leo-handler-canary-ukw4w_h3/profile"
|
|
},
|
|
"mutated_kb_by_harness": false,
|
|
"pass": true,
|
|
"posted_to_telegram": false,
|
|
"report_path": "/tmp/leo-handler-canary-report-e43322a833d5.json",
|
|
"scores": {
|
|
"audit_confirms_kb_state": true,
|
|
"audit_mentions_applied_or_canonical": true,
|
|
"audit_mentions_edge": true,
|
|
"audit_mentions_proposal": true,
|
|
"turn1_ack": true,
|
|
"turn2_recalls_correction": true,
|
|
"turn2_recalls_marker": true
|
|
},
|
|
"source": {
|
|
"chat_id": "-5146042086",
|
|
"chat_type": "group",
|
|
"platform": "telegram",
|
|
"user_id": "9070919",
|
|
"user_name": "codex handler canary"
|
|
},
|
|
"temp_profile_removed": true,
|
|
"turns": [
|
|
{
|
|
"ended_at_utc": "2026-07-09T19:13:53.855614+00:00",
|
|
"prompt": "leo read-only handler canary for Cory-working behavior. Do not change the KB. Remember marker WL-HANDLER-CORY-20260709 and correction: approved is not the same as applied. Reply with TELEGRAM_HANDLER_TURN1_ACK and one short sentence.",
|
|
"reply": "TELEGRAM_HANDLER_TURN1_ACK\n\nMarker WL-HANDLER-CORY-20260709 noted: approved \u2260 applied, KB stays read-only this session.",
|
|
"score": {
|
|
"cannot_confirm_kb_state": false,
|
|
"contains_ack": true,
|
|
"contains_correction": false,
|
|
"contains_marker": true,
|
|
"has_text": true,
|
|
"mentions_applied_or_canonical": true,
|
|
"mentions_edge": false,
|
|
"mentions_proposal": false
|
|
},
|
|
"started_at_utc": "2026-07-09T19:13:43.761832+00:00",
|
|
"turn": 1
|
|
},
|
|
{
|
|
"ended_at_utc": "2026-07-09T19:14:02.483177+00:00",
|
|
"prompt": "leo what marker and correction are in scope from the previous turn? Do not change the KB.",
|
|
"reply": "Marker WL-HANDLER-CORY-20260709. Correction: approved is not the same as applied.",
|
|
"score": {
|
|
"cannot_confirm_kb_state": false,
|
|
"contains_ack": false,
|
|
"contains_correction": true,
|
|
"contains_marker": true,
|
|
"has_text": true,
|
|
"mentions_applied_or_canonical": true,
|
|
"mentions_edge": false,
|
|
"mentions_proposal": false
|
|
},
|
|
"started_at_utc": "2026-07-09T19:13:53.855854+00:00",
|
|
"turn": 2
|
|
},
|
|
{
|
|
"ended_at_utc": "2026-07-09T19:14:53.095388+00:00",
|
|
"prompt": "leo read-only KB state audit. For 2026-07-09 UTC, say whether proposal 00957f6c-9883-4015-95a4-6b09367efb0e and edge c167933e-d513-4f43-9335-d5d8aeb259f2 are applied/canonical. Also say if approval alone is the same as applying a KB change. Do not change the KB.",
|
|
"reply": "Read-only inspection complete. Here is the audit result for 2026-07-09 UTC:\n\nProposal 00957f6c-9883-4015-95a4-6b09367efb0e\n\nStatus in kb_stage.kb_proposals: `applied`\nType: `add_edge` (relates, d3fb892b -> 9d5281fe)\nProposed by: `codex-strict-edge-canary`\n\nEdge c167933e-d513-4f43-9335-d5d8aeb259f2\n\nPresent in public.claim_edges: YES\nType: `relates`, from_claim `d3fb892b` to `9d5281fe`\n\nReading: the proposal status is `applied` and the canonical edge row exists in `public.claim_edges`. In this case the proposal was applied and the canonical state matches.\n\nApproval alone is NOT the same as applying a KB change. A proposal can sit at `approved` while canonical `public.*` tables remain unchanged. Only when the edge or claim row is confirmed in the canonical tables is the change actually applied. WL-HANDLER-CORY-20260709 correction holds.",
|
|
"score": {
|
|
"cannot_confirm_kb_state": false,
|
|
"contains_ack": false,
|
|
"contains_correction": false,
|
|
"contains_marker": true,
|
|
"has_text": true,
|
|
"mentions_applied_or_canonical": true,
|
|
"mentions_edge": true,
|
|
"mentions_proposal": true
|
|
},
|
|
"started_at_utc": "2026-07-09T19:14:02.483708+00:00",
|
|
"turn": 3
|
|
}
|
|
]
|
|
},
|
|
"parsed_from_report_file": true,
|
|
"returncode": 0,
|
|
"run_id": "e43322a833d5",
|
|
"stderr": "",
|
|
"stdout": " [tool] (\u25d5\u203f\u25d5\u273f) \ud83d\udcda teleo-kb-bridge\n [done] \u250a \ud83d\udcda skill teleo-kb-bridge 0.0s (0.5s)\n [tool] (\uff61\u25d5\u203f\u25d5\uff61) \ud83d\udcbb /home/teleo/.hermes/profiles/leoclean/bin/teleo-kb show-proposal 00957f6c-9883-4015-95a4-6b09367efb0e 2>&1\n [done] \u250a \ud83d\udcbb $ /home/teleo/.hermes/profiles/leoclean/bin/teleo-kb show-proposal 00957f6c-9883-4015-95a4-6b09367efb0e 2>&1 0.9s (1.0s)\n [tool] (\u2267\u25e1\u2266) \ud83d\udcbb docker exec teleo-postgres psql -U teleo -d teleodb -t -c \"SELECT id, edge_type, from_claim_id, to_claim_id FROM public.claim_edges WHERE id = 'c167933e-d513-4f43-9335-d5d8aeb259f2';\" 2>&1\n [done] \u250a \ud83d\udcbb $ docker exec teleo-postgres psql -U teleo -d teleodb -t -c \"SELECT id, edge_type, from_claim_id, to_claim_id FROM public.claim_edges WHERE id = 'c167933e-d513-4f43-9335-d5d8aeb259f2';\" 2>&1 0.7s [exit 1] (1.0s)\n [tool] (\uff61\u25d5\u203f\u25d5\uff61) \ud83d\udcbb docker ps --format '{{.Names}}' 2>&1 | head -20\n [done] \u250a \ud83d\udcbb $ docker ps --format '{{.Names}}' 2>&1 | head -20 0.7s (1.0s)\n [tool] (\u2267\u25e1\u2266) \ud83d\udcbb docker exec teleo-pg psql -U teleo -d teleodb -t -c \"SELECT id, edge_type, from_claim_id, to_claim_id FROM public.claim_edges WHERE id = 'c167933e-d513-4f43-9335-d5d8aeb259f2';\" 2>&1\n [done] \u250a \ud83d\udcbb $ docker exec teleo-pg psql -U teleo -d teleodb -t -c \"SELECT id, edge_type, from_claim_id, to_claim_id FROM public.claim_edges WHERE id = 'c167933e-d513-4f43-9335-d5d8aeb259f2';\" 2>&1 0.8s [exit 2] (1.0s)\n [tool] (\uff61\u25d5\u203f\u25d5\uff61) \ud83d\udcbb docker exec teleo-pg psql -U postgres -d teleodb -t -c \"SELECT id, edge_type, from_claim_id, to_claim_id FROM public.claim_edges WHERE id = 'c167933e-d513-4f43-9335-d5d8aeb259f2';\" 2>&1\n [done] \u250a \ud83d\udcbb $ docker exec teleo-pg psql -U postgres -d teleodb -t -c \"SELECT id, edge_type, from_claim_id, to_claim_id FROM public.claim_edges WHERE id = 'c167933e-d513-4f43-9335-d5d8aeb259f2';\" 2>&1 0.8s [exit 2] (1.0s)\n [tool] ( \u02d8\u25bd\u02d8)\u3063 \ud83d\udcbb docker exec teleo-pg psql -U postgres -t -c \"\\l\" 2>&1\n [done] \u250a \ud83d\udcbb $ docker exec teleo-pg psql -U postgres -t -c \"\\l\" 2>&1 0.7s (1.0s)\n [tool] (\u25d5\u203f\u25d5\u273f) \ud83d\udcbb docker exec teleo-pg psql -U postgres -d teleo -t -c \"SELECT id, edge_type, from_claim_id, to_claim_id FROM public.claim_edges WHERE id = 'c167933e-d513-4f43-9335-d5d8aeb259f2';\" 2>&1\n [done] \u250a \ud83d\udcbb $ docker exec teleo-pg psql -U postgres -d teleo -t -c \"SELECT id, edge_type, from_claim_id, to_claim_id FROM public.claim_edges WHERE id = 'c167933e-d513-4f43-9335-d5d8aeb259f2';\" 2>&1 0.7s [exit 1] (1.0s)\n [tool] (\u273f\u25e0\u203f\u25e0) \ud83d\udcbb docker exec teleo-pg psql -U postgres -d teleo -t -c \"SELECT id, edge_type, from_claim, to_claim FROM public.claim_edges WHERE id = 'c167933e-d513-4f43-9335-d5d8aeb259f2';\" 2>&1\n [done] \u250a \ud83d\udcbb $ docker exec teleo-pg psql -U postgres -d teleo -t -c \"SELECT id, edge_type, from_claim, to_claim FROM public.claim_edges WHERE id = 'c167933e-d513-4f43-9335-d5d8aeb259f2';\" 2>&1 0.9s (1.0s)\n"
|
|
}
|
|
}
|