[ { "seed": 0, "note": "well-formed lookups, a fenced disposition after a bare brace, brace inside a string", "replies": [ "{\"action\":\"lookup\",\"what\":\"documents\"}", "I will check priors first. {\"action\":\"lookup\",\"what\":\"prior_alerts\"} and then decide.", "{\"action\":\"lookup\",\"what\":\"history\",\"month\":\"BADMONTH\"}", "Let me look at CP-1 {not json} ```json\n{\"action\":\"lookup\",\"what\":\"counterparty\",\"id\":\"CP-1\"}\n```", "{\"action\":\"close\",\"reason\":\"CONSISTENT_WITH_PROFILE\",\"cites\":[\"kyc.customer_type\",\"kyc.customer_type\",\"kyc.country\"],\"note\":\"braces {inside} a string \\\" and an escaped quote\"}" ] }, { "seed": 1, "note": "invalid first span then valid: rejected, no further scanning; lowercase enums; non-string cites", "replies": [ "{\"action\":\"lookup\",\"what\":\"documents\",} {\"action\":\"lookup\",\"what\":\"documents\"}", "{\"action\":\"close\",\"reason\":\"consistent_with_profile\",\"cites\":[\"kyc.country\"]}", "{\"action\":\"Lookup\",\"what\":\"documents\"}", "{\"action\":\"close\",\"reason\":\"CONSISTENT_WITH_PROFILE\",\"cites\":[1,2]}", "{\"action\":\"close\",\"reason\":\"CONSISTENT_WITH_PROFILE\",\"cites\":\"kyc.country\"}", "{\"action\":\"escalate\",\"typology\":\"structuring\",\"cites\":[\"kyc.country\"]}", "{\"action\":\"escalate\",\"typology\":\"STRUCTURING\",\"cites\":[],\"narrative\":\"x\"}", "{\"action\":\"escalate\",\"typology\":\"STRUCTURING\",\"cites\":[\"kyc.country\"],\"narrative\":42}" ] }, { "seed": 2, "note": "repeat lookups, nonexistent and unseen counterparties, out-of-window months, an unseen cite", "replies": [ "{\"action\":\"lookup\",\"what\":\"prior_alerts\"}", "{\"action\":\"lookup\",\"what\":\"prior_alerts\"}", "{\"action\":\"lookup\",\"what\":\"counterparty\",\"id\":\"CP-99\"}", "{\"action\":\"lookup\",\"what\":\"counterparty\",\"id\":\"cp-1\"}", "{\"action\":\"lookup\",\"what\":\"history\",\"month\":\"2024-01\"}", "{\"action\":\"lookup\",\"what\":\"history\",\"month\":\"2026-1\"}", "{\"action\":\"close\",\"reason\":\"DOCUMENTED_SOURCE_OF_FUNDS\",\"cites\":[\"doc.probate_letter\"]}", "{\"action\":\"close\",\"reason\":\"PREVIOUSLY_REVIEWED\",\"cites\":[\"kyc.prior_alerts\"]}" ] }, { "seed": 3, "note": "prose only, empty, null, NaN, a fenced array, nested objects, unbalanced braces; runs out the budget -> aborted", "replies": [ "I would like to think about this alert a little longer before acting.", "", null, "{\"action\":\"lookup\",\"what\":\"documents\",\"weight\":NaN}", "```json\n[{\"action\":\"lookup\",\"what\":\"documents\"}]\n```", "{\"outer\":{\"action\":\"lookup\",\"what\":\"documents\"}}", "{\"action\":\"lookup\",\"what\":\"documents\"", "{\"what\":\"documents\"}" ] }, { "seed": 4, "note": "a full investigation that itemises the two most recent months and escalates on the last turn", "replies": [ "{\"action\":\"lookup\",\"what\":\"documents\"}", "{\"action\":\"lookup\",\"what\":\"prior_alerts\"}", "{\"action\":\"lookup\",\"what\":\"counterparty\",\"id\":\"CP-2\"}", "{\"action\":\"lookup\",\"what\":\"counterparty\",\"id\":\"CP-3\"}", "{\"action\":\"lookup\",\"what\":\"history\",\"month\":\"2026-03\"}", "{\"action\":\"lookup\",\"what\":\"history\",\"month\":\"2026-04\"}", "{\"action\":\"lookup\",\"what\":\"history\",\"month\":\"2026-05\"}", "{\"action\":\"escalate\",\"typology\":\"UNKNOWN\",\"cites\":[\"kyc.country\",\"kyc.pep\"],\"narrative\":\"eighth turn\"}" ] }, { "seed": 5, "note": "a disposition citing every shown KYC field; extra keys ignored; the episode ends and later replies are not counted", "replies": [ "```json\n{\"action\": \"close\", \"reason\": \"RULE_ARTEFACT\", \"cites\": [\"kyc.customer_type\", \"kyc.country\", \"kyc.pep\", \"kyc.prior_alerts\", \"kyc.prior_sars\", \"kyc.stated_income\", \"kyc.expected_monthly_cash\", \"kyc.expected_activity\", \"kyc.account_opened\", \"kyc.kyc_refreshed\", \"kyc.remittance_declared\"], \"note\": \"\", \"confidence\": 0.9}\n```", "{\"action\":\"lookup\",\"what\":\"documents\"}" ] }, { "seed": 6, "note": "stops after three turns with no disposition: truncated, not aborted; an unknown lookup kind", "replies": [ "{\"action\":\"lookup\",\"what\":\"documents\"}", "thinking", "{\"action\":\"lookup\",\"what\":\"prior_alerts\"}", "{\"action\":\"lookup\",\"what\":\"emails\"}", "[{\"action\":\"lookup\",\"what\":\"counterparty\",\"id\":\"CP-1\"}] as a bare array: the inner object is the first balanced span" ] } ]