Files
flynn/docs/plans/artifacts/pi_embedded_eval_window_a_2026-02-24.json

145 lines
3.2 KiB
JSON

{
"generated_at": "2026-02-24T06:37:06.279Z",
"event_count": 45,
"filters": {},
"options": {
"targetBackend": "pi_embedded",
"baselineBackend": "native",
"sessionIds": [
"telegram:8367012007"
]
},
"summary": {
"route_stats": {
"total": 10,
"by_backend": {
"native": 2,
"pi_embedded": 8
},
"by_source": {
"agent_override": 10
},
"forced_native_guards": {}
},
"target": {
"backend": "pi_embedded",
"routes": 8,
"completed_turns": 8,
"incomplete_turns": 0,
"completion_rate_pct": 100,
"e2e_latency_ms": {
"count": 8,
"avg_ms": 4615,
"p50_ms": 3240,
"p95_ms": 8776,
"min_ms": 1859,
"max_ms": 9381
}
},
"baseline": {
"backend": "native",
"routes": 2,
"completed_turns": 2,
"incomplete_turns": 0,
"completion_rate_pct": 100,
"e2e_latency_ms": {
"count": 2,
"avg_ms": 2981,
"p50_ms": 2981,
"p95_ms": 3081,
"min_ms": 2870,
"max_ms": 3092
}
},
"target_external_attempts": {
"attempts": 8,
"successes": 6,
"fallbacks": 2,
"unresolved_attempts": 0,
"success_rate_pct": 75,
"attempt_latency_ms": {
"count": 8,
"avg_ms": 3961,
"p50_ms": 2636,
"p95_ms": 8766,
"min_ms": 135,
"max_ms": 9371
}
},
"comparison": {
"completion_rate_delta_pp": 0,
"p50_latency_delta_ms": 259,
"p95_latency_delta_ms": 5695
},
"fallback_categories": [
{
"category": "empty_assistant_text",
"count": 1,
"pct": 50
},
{
"category": "pi_module_interface",
"count": 1,
"pct": 50
}
],
"fallback_top_reasons": [
{
"reason": "Loaded Pi module does not expose a supported session factory (expected one of: createAgentSession, createSession, createPiSession, createAge",
"count": 1
},
{
"reason": "Pi Agent runtime produced no assistant text",
"count": 1
}
]
},
"gate": {
"pass": false,
"criteria": [
{
"criterion": "Minimum target routes",
"pass": true,
"actual": "8",
"threshold": ">= 8"
},
{
"criterion": "Minimum baseline routes",
"pass": true,
"actual": "2",
"threshold": ">= 2"
},
{
"criterion": "Minimum target external attempts",
"pass": true,
"actual": "8",
"threshold": ">= 8"
},
{
"criterion": "Completion rate delta (target - baseline)",
"pass": true,
"actual": "0.00pp",
"threshold": ">= -2.00pp"
},
{
"criterion": "P50 latency delta (target - baseline)",
"pass": false,
"actual": "259ms",
"threshold": "<= 250ms"
},
{
"criterion": "P95 latency delta (target - baseline)",
"pass": false,
"actual": "5695ms",
"threshold": "<= 700ms"
},
{
"criterion": "Fallback rate (target external attempts)",
"pass": false,
"actual": "25.00%",
"threshold": "<= 5.00%"
}
]
}
}