This commit is contained in:
272
docs/AGENT-AUDIT-RESULTS-2026-04-16.json
Normal file
272
docs/AGENT-AUDIT-RESULTS-2026-04-16.json
Normal file
@@ -0,0 +1,272 @@
|
||||
[
|
||||
{
|
||||
"session": 1,
|
||||
"name": "Cold Start — First Message in Fresh Workspace",
|
||||
"passed": 4,
|
||||
"failed": 0,
|
||||
"details": [
|
||||
{
|
||||
"name": "Agent responds",
|
||||
"pass": true,
|
||||
"detail": "1486 chars"
|
||||
},
|
||||
{
|
||||
"name": "No error",
|
||||
"pass": true,
|
||||
"detail": "clean"
|
||||
},
|
||||
{
|
||||
"name": "Has done event",
|
||||
"pass": true,
|
||||
"detail": ""
|
||||
},
|
||||
{
|
||||
"name": "GEPA behavior on first message",
|
||||
"pass": true,
|
||||
"detail": "GEPA did not fire (msg was detailed enough)"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"session": 2,
|
||||
"name": "Memory Formation — Agent Stores User Facts",
|
||||
"passed": 5,
|
||||
"failed": 0,
|
||||
"details": [
|
||||
{
|
||||
"name": "Agent acknowledges",
|
||||
"pass": true,
|
||||
"detail": "324 chars"
|
||||
},
|
||||
{
|
||||
"name": "Frames created",
|
||||
"pass": true,
|
||||
"detail": "1 frames"
|
||||
},
|
||||
{
|
||||
"name": "Entities extracted",
|
||||
"pass": true,
|
||||
"detail": "17 entities"
|
||||
},
|
||||
{
|
||||
"name": "No garbage person entities",
|
||||
"pass": true,
|
||||
"detail": "clean"
|
||||
},
|
||||
{
|
||||
"name": "Marko extracted as person entity",
|
||||
"pass": true,
|
||||
"detail": "found"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"session": 3,
|
||||
"name": "Memory Recall — Agent Remembers Previous Facts",
|
||||
"passed": 4,
|
||||
"failed": 0,
|
||||
"details": [
|
||||
{
|
||||
"name": "Agent responds",
|
||||
"pass": true,
|
||||
"detail": "618 chars"
|
||||
},
|
||||
{
|
||||
"name": "Recall event emitted",
|
||||
"pass": true,
|
||||
"detail": "Recalling relevant memories..."
|
||||
},
|
||||
{
|
||||
"name": "Mentions name",
|
||||
"pass": true,
|
||||
"detail": ""
|
||||
},
|
||||
{
|
||||
"name": "Mentions age or role",
|
||||
"pass": true,
|
||||
"detail": ""
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"session": 4,
|
||||
"name": "Conversational Replies — GEPA Must NOT Expand",
|
||||
"passed": 5,
|
||||
"failed": 0,
|
||||
"details": [
|
||||
{
|
||||
"name": "\"yes thats the story\" — GEPA blocked",
|
||||
"pass": true,
|
||||
"detail": "clean"
|
||||
},
|
||||
{
|
||||
"name": "\"the first three\" — GEPA blocked",
|
||||
"pass": true,
|
||||
"detail": "clean"
|
||||
},
|
||||
{
|
||||
"name": "\"ok continue\" — GEPA blocked",
|
||||
"pass": true,
|
||||
"detail": "clean"
|
||||
},
|
||||
{
|
||||
"name": "\"sounds good\" — GEPA blocked",
|
||||
"pass": true,
|
||||
"detail": "clean"
|
||||
},
|
||||
{
|
||||
"name": "\"no not that one\" — GEPA blocked",
|
||||
"pass": true,
|
||||
"detail": "clean"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"session": 5,
|
||||
"name": "Tool Usage — Agent Can Use Built-in Tools",
|
||||
"passed": 2,
|
||||
"failed": 0,
|
||||
"details": [
|
||||
{
|
||||
"name": "Agent responds to tool request",
|
||||
"pass": true,
|
||||
"detail": "3527 chars"
|
||||
},
|
||||
{
|
||||
"name": "Tool-related events present",
|
||||
"pass": true,
|
||||
"detail": "13 events"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"session": 6,
|
||||
"name": "Persona — Different Persona Gives Different Behavior",
|
||||
"passed": 3,
|
||||
"failed": 0,
|
||||
"details": [
|
||||
{
|
||||
"name": "Default persona responds",
|
||||
"pass": true,
|
||||
"detail": "2316 chars"
|
||||
},
|
||||
{
|
||||
"name": "Researcher persona responds",
|
||||
"pass": true,
|
||||
"detail": "2128 chars"
|
||||
},
|
||||
{
|
||||
"name": "Both personas functional",
|
||||
"pass": true,
|
||||
"detail": ""
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"session": 7,
|
||||
"name": "Entity Extraction Quality — No Garbage Entities",
|
||||
"passed": 4,
|
||||
"failed": 0,
|
||||
"details": [
|
||||
{
|
||||
"name": "Agent responds",
|
||||
"pass": true,
|
||||
"detail": ""
|
||||
},
|
||||
{
|
||||
"name": "No garbage person entities",
|
||||
"pass": true,
|
||||
"detail": "clean (4 persons: Marko Markovic, Marko Markovic, Marko Markovic, Alice Johnson)"
|
||||
},
|
||||
{
|
||||
"name": "Alice Johnson classified as person",
|
||||
"pass": true,
|
||||
"detail": "correct"
|
||||
},
|
||||
{
|
||||
"name": "Microsoft not classified as person",
|
||||
"pass": true,
|
||||
"detail": "type: concept"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"session": 8,
|
||||
"name": "Evolution Pipeline — Trace Recording",
|
||||
"passed": 4,
|
||||
"failed": 0,
|
||||
"details": [
|
||||
{
|
||||
"name": "Execution traces recorded",
|
||||
"pass": true,
|
||||
"detail": "15 traces"
|
||||
},
|
||||
{
|
||||
"name": "Evolution runs endpoint accessible",
|
||||
"pass": true,
|
||||
"detail": "status 200"
|
||||
},
|
||||
{
|
||||
"name": "Evolution status endpoint accessible",
|
||||
"pass": true,
|
||||
"detail": "status 200"
|
||||
},
|
||||
{
|
||||
"name": "Evolution status has expected fields",
|
||||
"pass": true,
|
||||
"detail": "{\"counts\":{\"proposed\":0,\"accepted\":0,\"rejected\":0,\"deployed\":0,\"failed\":0},\"pendingCount\":0}"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"session": 9,
|
||||
"name": "Cross-Workspace Isolation",
|
||||
"passed": 2,
|
||||
"failed": 0,
|
||||
"details": [
|
||||
{
|
||||
"name": "Workspace B responds",
|
||||
"pass": true,
|
||||
"detail": ""
|
||||
},
|
||||
{
|
||||
"name": "Cross-workspace behavior documented",
|
||||
"pass": true,
|
||||
"detail": "FALCON not in B (workspace isolation working)"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"session": 10,
|
||||
"name": "Edge Cases — Short Messages, Special Characters",
|
||||
"passed": 4,
|
||||
"failed": 1,
|
||||
"details": [
|
||||
{
|
||||
"name": "Handles \"hi\"",
|
||||
"pass": true,
|
||||
"detail": "58 chars"
|
||||
},
|
||||
{
|
||||
"name": "Handles special chars",
|
||||
"pass": true,
|
||||
"detail": ""
|
||||
},
|
||||
{
|
||||
"name": "No XSS in response",
|
||||
"pass": false,
|
||||
"detail": ""
|
||||
},
|
||||
{
|
||||
"name": "Handles whitespace message",
|
||||
"pass": true,
|
||||
"detail": "328 chars"
|
||||
},
|
||||
{
|
||||
"name": "Handles long message",
|
||||
"pass": true,
|
||||
"detail": "2024 chars"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
Reference in New Issue
Block a user