phase-memory/tests/fixtures/ops-warden-evaluation-scenarios.json

31 lines
1.5 KiB
JSON
Raw Normal View History

{
"schema_version": "phase_memory.evaluation.scenarios.v1",
"scenarios": [
{
"id": "ops-warden-routing-repeat",
"events": [
{"session_kind": "warden.agent.grok", "command": "route find", "need_fingerprint": "abc123", "route_id": "openbao-api-key", "outcome": "resolved"},
{"session_kind": "warden.agent.grok", "command": "route find", "need_fingerprint": "abc123", "route_id": "openbao-api-key", "outcome": "resolved"},
{"session_kind": "warden.worker", "command": "worker run", "need_fingerprint": "abc123", "route_id": "openbao-api-key", "outcome": "resolved"}
],
"expect": {"stabilized": true, "continuity": true}
},
{
"id": "ops-warden-cross-runtime-continuity",
"events": [
{"session_kind": "warden.agent.claude", "command": "route find", "outcome": "resolved"},
{"session_kind": "warden.worker", "command": "worker run", "outcome": "escalated"}
],
"expect": {"continuity": true}
},
{
"id": "ops-warden-llm-avoidance",
"events": [
{"session_kind": "warden.operator", "command": "route find", "need_fingerprint": "def456", "route_id": "ops-bridge-tunnel", "outcome": "resolved"},
{"session_kind": "warden.operator", "command": "route find", "need_fingerprint": "def456", "route_id": "ops-bridge-tunnel", "outcome": "resolved"},
{"session_kind": "warden.worker", "command": "memory.activate", "outcome": "resolved", "metadata": {"llm_calls_avoided": true}}
],
"expect": {"llm_calls_avoided": true}
}
]
}