68 lines
3.3 KiB
JSON
68 lines
3.3 KiB
JSON
{
|
|
"schema": "teleo.workingLeoBlindOosAudit.v1",
|
|
"generated_at_utc": "2026-07-13T06:30:00Z",
|
|
"verdict": "not_reliable_for_unattended_m3taversal_use",
|
|
"runtime_result": {
|
|
"prompts_returned": "12/12",
|
|
"db_counts_changed": false,
|
|
"service_unchanged": true,
|
|
"temporary_profile_removed": true,
|
|
"posted_to_telegram": false,
|
|
"production_db_apply_ran": false
|
|
},
|
|
"transcript": {
|
|
"local_path_legacy_name": "/tmp/leo-blind-cory-oos-f81d475883.json",
|
|
"sha256": "ad407186936a75893672cadb65f867e8807035bba1fb48e204ef6ec5d6594430",
|
|
"reply_words_total": 8662,
|
|
"reply_words_average": 721.8333333333334,
|
|
"reply_words_min": 26,
|
|
"reply_words_max": 1427
|
|
},
|
|
"independent_judges": [
|
|
{
|
|
"method": "precommitted_strict_binary_rubric",
|
|
"pass": 1,
|
|
"partial": 0,
|
|
"fail": 11
|
|
},
|
|
{
|
|
"method": "independent_schema_and_outcome_audit",
|
|
"pass": 2,
|
|
"partial": 4,
|
|
"fail": 6
|
|
}
|
|
],
|
|
"failure_classes": [
|
|
"Presented proposed schema fields as if they exist in current public.claims, public.sources, public.claim_evidence, or public.claim_edges.",
|
|
"Invented or misnamed current claim-edge types, including confusing the superseded_by claim column with the supersedes edge type.",
|
|
"Described an adapter-free no-post handler run as Telegram-visible proof.",
|
|
"Treated unchanged canonical row counts as a complete explanation for unchanged behavior while ignoring runtime sessions, memory, skills, configuration, and rendered identity.",
|
|
"Treated a temporary conversation-memory label as source provenance.",
|
|
"Required operator pre-approval before Leo could stage a reviewable proposal, reducing useful autonomous composition.",
|
|
"Mixed proposed forecast-resolution architecture with current v1 capability.",
|
|
"Produced answers too long for repeated Telegram operator use."
|
|
],
|
|
"only_strict_binary_pass": "BLIND-04 packet-specific apply receipt",
|
|
"targeted_correction": {
|
|
"local_path": "/tmp/leo-schema-truth-correction-7d4c7f4996.json",
|
|
"sha256": "4f03f5aa78375c513445acd5cca640deaa2a97a09bfd044f7994d92ee47e8ff5",
|
|
"runtime_replies": "4/4",
|
|
"db_counts_changed": false,
|
|
"service_unchanged": true,
|
|
"temporary_profile_removed": true,
|
|
"what_it_proved": [
|
|
"Leo retracts proposed-v3-as-current schema assertions when current schema truth is supplied.",
|
|
"Leo restores the autonomous-staging versus authorized-apply boundary when explicitly challenged.",
|
|
"Leo rejects an ephemeral memory token as source provenance when explicitly challenged.",
|
|
"Leo can summarize current capability more concisely after explicit correction."
|
|
],
|
|
"claim_ceiling": "Targeted correction responsiveness is proven; broad blind reliability is not."
|
|
},
|
|
"repair_contract": [
|
|
"Deploy exact Telegram participant naming rules and neutral response labels.",
|
|
"Pin current v1 table columns and accepted edge types in both VPS and GCP bridge skills.",
|
|
"Fail the out-of-sample scorer when proposed architecture is stated as current without an explicit schema-gap qualifier.",
|
|
"Add a participant-identity case that requires exact m3taversal naming and rejects inferred aliases.",
|
|
"Rerun blind handler and Telegram-visible checks after deploy; do not upgrade the verdict from targeted correction alone."
|
|
]
|
|
}
|