827 lines
30 KiB
JSON
827 lines
30 KiB
JSON
{
|
||
"status": "success",
|
||
"slice_window_key": "2020-06",
|
||
"generated_at": "2026-03-23T09:28:12.312411+00:00",
|
||
"questions_total": 35,
|
||
"aggregate": {
|
||
"questions_total": 35,
|
||
"avg_latency_ms": 506.43,
|
||
"median_latency_ms": 402,
|
||
"p90_latency_ms": 941.4,
|
||
"p95_latency_ms": 1024.5,
|
||
"avg_context_size": 2162.51,
|
||
"live_route_count": 8,
|
||
"store_route_count": 27,
|
||
"batch_route_count": 0,
|
||
"route_mismatch_count": 7,
|
||
"degraded_answers_count": 0,
|
||
"route_distribution": {
|
||
"store_canonical": 8,
|
||
"live_mcp_drilldown": 4,
|
||
"hybrid_store_plus_live": 4,
|
||
"store_feature_risk": 19
|
||
},
|
||
"question_class_distribution": {
|
||
"simple_factual": 5,
|
||
"drilldown_explain": 5,
|
||
"cross_entity": 5,
|
||
"period_trend": 5,
|
||
"anomaly_control": 5,
|
||
"heavy_analytical": 5,
|
||
"ambiguous_fuzzy": 5
|
||
}
|
||
},
|
||
"results": [
|
||
{
|
||
"question_id": "Q01",
|
||
"question_text": "Сальдо счета 68.02 за июнь 2020?",
|
||
"question_class": "simple_factual",
|
||
"expected_route": "store_canonical",
|
||
"actual_route": "store_canonical",
|
||
"sources_used": [
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 332,
|
||
"planning_time_ms": 67,
|
||
"retrieval_time_ms": 129,
|
||
"response_generation_time_ms": 136,
|
||
"context_size": 1595,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_canonical; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q02",
|
||
"question_text": "Документ по номеру и его ссылка.",
|
||
"question_class": "simple_factual",
|
||
"expected_route": "live_mcp_drilldown",
|
||
"actual_route": "live_mcp_drilldown",
|
||
"sources_used": [
|
||
"mcp_runtime_bridge"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 1020,
|
||
"planning_time_ms": 93,
|
||
"retrieval_time_ms": 740,
|
||
"response_generation_time_ms": 187,
|
||
"context_size": 2796,
|
||
"answer_text": "[simulated-4o-mini-profile] route=live_mcp_drilldown; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q03",
|
||
"question_text": "Типовая проводка по реализации.",
|
||
"question_class": "simple_factual",
|
||
"expected_route": "store_canonical",
|
||
"actual_route": "store_canonical",
|
||
"sources_used": [
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 338,
|
||
"planning_time_ms": 69,
|
||
"retrieval_time_ms": 131,
|
||
"response_generation_time_ms": 138,
|
||
"context_size": 1597,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_canonical; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q04",
|
||
"question_text": "Контрагент с максимумом оборота.",
|
||
"question_class": "simple_factual",
|
||
"expected_route": "store_canonical",
|
||
"actual_route": "store_canonical",
|
||
"sources_used": [
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 341,
|
||
"planning_time_ms": 70,
|
||
"retrieval_time_ms": 132,
|
||
"response_generation_time_ms": 139,
|
||
"context_size": 1598,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_canonical; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q05",
|
||
"question_text": "Договоры топ-контрагента.",
|
||
"question_class": "simple_factual",
|
||
"expected_route": "store_canonical",
|
||
"actual_route": "store_canonical",
|
||
"sources_used": [
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 344,
|
||
"planning_time_ms": 71,
|
||
"retrieval_time_ms": 133,
|
||
"response_generation_time_ms": 140,
|
||
"context_size": 1599,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_canonical; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q06",
|
||
"question_text": "Объясни сальдо через движения.",
|
||
"question_class": "drilldown_explain",
|
||
"expected_route": "hybrid_store_plus_live",
|
||
"actual_route": "hybrid_store_plus_live",
|
||
"sources_used": [
|
||
"canonical_store",
|
||
"mcp_runtime_bridge"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 819,
|
||
"planning_time_ms": 114,
|
||
"retrieval_time_ms": 524,
|
||
"response_generation_time_ms": 181,
|
||
"context_size": 2950,
|
||
"answer_text": "[simulated-4o-mini-profile] route=hybrid_store_plus_live; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q07",
|
||
"question_text": "Почему проводка на этот счет?",
|
||
"question_class": "drilldown_explain",
|
||
"expected_route": "live_mcp_drilldown",
|
||
"actual_route": "live_mcp_drilldown",
|
||
"sources_used": [
|
||
"mcp_runtime_bridge"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 1035,
|
||
"planning_time_ms": 98,
|
||
"retrieval_time_ms": 745,
|
||
"response_generation_time_ms": 192,
|
||
"context_size": 2801,
|
||
"answer_text": "[simulated-4o-mini-profile] route=live_mcp_drilldown; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q08",
|
||
"question_text": "Цепочка документ -> проводки -> субконто.",
|
||
"question_class": "drilldown_explain",
|
||
"expected_route": "live_mcp_drilldown",
|
||
"actual_route": "live_mcp_drilldown",
|
||
"sources_used": [
|
||
"mcp_runtime_bridge"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 1038,
|
||
"planning_time_ms": 99,
|
||
"retrieval_time_ms": 746,
|
||
"response_generation_time_ms": 193,
|
||
"context_size": 2802,
|
||
"answer_text": "[simulated-4o-mini-profile] route=live_mcp_drilldown; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q09",
|
||
"question_text": "Источник регистра для строки движения.",
|
||
"question_class": "drilldown_explain",
|
||
"expected_route": "live_mcp_drilldown",
|
||
"actual_route": "hybrid_store_plus_live",
|
||
"sources_used": [
|
||
"canonical_store",
|
||
"mcp_runtime_bridge"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 828,
|
||
"planning_time_ms": 117,
|
||
"retrieval_time_ms": 527,
|
||
"response_generation_time_ms": 184,
|
||
"context_size": 2953,
|
||
"answer_text": "[simulated-4o-mini-profile] route=hybrid_store_plus_live; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "acceptable_with_warning",
|
||
"issues_detected": [
|
||
"Route mismatch: expected live_mcp_drilldown, got hybrid_store_plus_live"
|
||
],
|
||
"recommended_fix": "Tune router threshold for heavy/live boundary."
|
||
},
|
||
{
|
||
"question_id": "Q10",
|
||
"question_text": "Почему выбрано это субконто3?",
|
||
"question_class": "drilldown_explain",
|
||
"expected_route": "live_mcp_drilldown",
|
||
"actual_route": "live_mcp_drilldown",
|
||
"sources_used": [
|
||
"mcp_runtime_bridge"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 1017,
|
||
"planning_time_ms": 92,
|
||
"retrieval_time_ms": 739,
|
||
"response_generation_time_ms": 186,
|
||
"context_size": 2795,
|
||
"answer_text": "[simulated-4o-mini-profile] route=live_mcp_drilldown; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q11",
|
||
"question_text": "Свяжи документы покупателей и проводки.",
|
||
"question_class": "cross_entity",
|
||
"expected_route": "hybrid_store_plus_live",
|
||
"actual_route": "store_canonical",
|
||
"sources_used": [
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 335,
|
||
"planning_time_ms": 68,
|
||
"retrieval_time_ms": 130,
|
||
"response_generation_time_ms": 137,
|
||
"context_size": 1596,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_canonical; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "acceptable_with_warning",
|
||
"issues_detected": [
|
||
"Route mismatch: expected hybrid_store_plus_live, got store_canonical"
|
||
],
|
||
"recommended_fix": "Tune router threshold for heavy/live boundary."
|
||
},
|
||
{
|
||
"question_id": "Q12",
|
||
"question_text": "Свяжи контрагентов, договоры и проводки.",
|
||
"question_class": "cross_entity",
|
||
"expected_route": "hybrid_store_plus_live",
|
||
"actual_route": "store_canonical",
|
||
"sources_used": [
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 338,
|
||
"planning_time_ms": 69,
|
||
"retrieval_time_ms": 131,
|
||
"response_generation_time_ms": 138,
|
||
"context_size": 1597,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_canonical; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "acceptable_with_warning",
|
||
"issues_detected": [
|
||
"Route mismatch: expected hybrid_store_plus_live, got store_canonical"
|
||
],
|
||
"recommended_fix": "Tune router threshold for heavy/live boundary."
|
||
},
|
||
{
|
||
"question_id": "Q13",
|
||
"question_text": "Номенклатура, склад, обороты за июнь.",
|
||
"question_class": "cross_entity",
|
||
"expected_route": "store_canonical",
|
||
"actual_route": "store_canonical",
|
||
"sources_used": [
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 341,
|
||
"planning_time_ms": 70,
|
||
"retrieval_time_ms": 132,
|
||
"response_generation_time_ms": 139,
|
||
"context_size": 1598,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_canonical; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q14",
|
||
"question_text": "Регистр и первичный документ.",
|
||
"question_class": "cross_entity",
|
||
"expected_route": "hybrid_store_plus_live",
|
||
"actual_route": "hybrid_store_plus_live",
|
||
"sources_used": [
|
||
"canonical_store",
|
||
"mcp_runtime_bridge"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 816,
|
||
"planning_time_ms": 113,
|
||
"retrieval_time_ms": 523,
|
||
"response_generation_time_ms": 180,
|
||
"context_size": 2949,
|
||
"answer_text": "[simulated-4o-mini-profile] route=hybrid_store_plus_live; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q15",
|
||
"question_text": "По счету: контрагенты и договоры.",
|
||
"question_class": "cross_entity",
|
||
"expected_route": "store_canonical",
|
||
"actual_route": "store_canonical",
|
||
"sources_used": [
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 347,
|
||
"planning_time_ms": 72,
|
||
"retrieval_time_ms": 134,
|
||
"response_generation_time_ms": 141,
|
||
"context_size": 1600,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_canonical; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q16",
|
||
"question_text": "Обороты июня против мая.",
|
||
"question_class": "period_trend",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 402,
|
||
"planning_time_ms": 85,
|
||
"retrieval_time_ms": 155,
|
||
"response_generation_time_ms": 162,
|
||
"context_size": 2101,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q17",
|
||
"question_text": "Недельные всплески в июне.",
|
||
"question_class": "period_trend",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 405,
|
||
"planning_time_ms": 86,
|
||
"retrieval_time_ms": 156,
|
||
"response_generation_time_ms": 163,
|
||
"context_size": 2102,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q18",
|
||
"question_text": "Кто дал резкий рост активности.",
|
||
"question_class": "period_trend",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 408,
|
||
"planning_time_ms": 87,
|
||
"retrieval_time_ms": 157,
|
||
"response_generation_time_ms": 164,
|
||
"context_size": 2103,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q19",
|
||
"question_text": "Аномальный рост расходных операций?",
|
||
"question_class": "period_trend",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 411,
|
||
"planning_time_ms": 88,
|
||
"retrieval_time_ms": 158,
|
||
"response_generation_time_ms": 165,
|
||
"context_size": 2104,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q20",
|
||
"question_text": "Динамика НДС к соседним периодам.",
|
||
"question_class": "period_trend",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 387,
|
||
"planning_time_ms": 80,
|
||
"retrieval_time_ms": 150,
|
||
"response_generation_time_ms": 157,
|
||
"context_size": 2096,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q21",
|
||
"question_text": "Нетипичные корреспонденции счетов.",
|
||
"question_class": "anomaly_control",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 390,
|
||
"planning_time_ms": 81,
|
||
"retrieval_time_ms": 151,
|
||
"response_generation_time_ms": 158,
|
||
"context_size": 2097,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q22",
|
||
"question_text": "Незакрытые хвосты по расчетам.",
|
||
"question_class": "anomaly_control",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 393,
|
||
"planning_time_ms": 82,
|
||
"retrieval_time_ms": 152,
|
||
"response_generation_time_ms": 159,
|
||
"context_size": 2098,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q23",
|
||
"question_text": "Дублирующиеся проводки.",
|
||
"question_class": "anomaly_control",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 396,
|
||
"planning_time_ms": 83,
|
||
"retrieval_time_ms": 153,
|
||
"response_generation_time_ms": 160,
|
||
"context_size": 2099,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q24",
|
||
"question_text": "Пустые или странные субконто.",
|
||
"question_class": "anomaly_control",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 399,
|
||
"planning_time_ms": 84,
|
||
"retrieval_time_ms": 154,
|
||
"response_generation_time_ms": 161,
|
||
"context_size": 2100,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q25",
|
||
"question_text": "Узлы с подозрительно большим degree.",
|
||
"question_class": "anomaly_control",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 402,
|
||
"planning_time_ms": 85,
|
||
"retrieval_time_ms": 155,
|
||
"response_generation_time_ms": 162,
|
||
"context_size": 2101,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "good",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q26",
|
||
"question_text": "Полный риск-срез за июнь.",
|
||
"question_class": "heavy_analytical",
|
||
"expected_route": "batch_refresh_then_store",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 405,
|
||
"planning_time_ms": 86,
|
||
"retrieval_time_ms": 156,
|
||
"response_generation_time_ms": 163,
|
||
"context_size": 2102,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "acceptable",
|
||
"route_quality_assessment": "acceptable_with_warning",
|
||
"issues_detected": [
|
||
"Route mismatch: expected batch_refresh_then_store, got store_feature_risk"
|
||
],
|
||
"recommended_fix": "Tune router threshold for heavy/live boundary."
|
||
},
|
||
{
|
||
"question_id": "Q27",
|
||
"question_text": "Рейтинг риск-счетов.",
|
||
"question_class": "heavy_analytical",
|
||
"expected_route": "batch_refresh_then_store",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 408,
|
||
"planning_time_ms": 87,
|
||
"retrieval_time_ms": 157,
|
||
"response_generation_time_ms": 164,
|
||
"context_size": 2103,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "acceptable",
|
||
"route_quality_assessment": "acceptable_with_warning",
|
||
"issues_detected": [
|
||
"Route mismatch: expected batch_refresh_then_store, got store_feature_risk"
|
||
],
|
||
"recommended_fix": "Tune router threshold for heavy/live boundary."
|
||
},
|
||
{
|
||
"question_id": "Q28",
|
||
"question_text": "Рейтинг риск-контрагентов.",
|
||
"question_class": "heavy_analytical",
|
||
"expected_route": "batch_refresh_then_store",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 411,
|
||
"planning_time_ms": 88,
|
||
"retrieval_time_ms": 158,
|
||
"response_generation_time_ms": 165,
|
||
"context_size": 2104,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "acceptable",
|
||
"route_quality_assessment": "acceptable_with_warning",
|
||
"issues_detected": [
|
||
"Route mismatch: expected batch_refresh_then_store, got store_feature_risk"
|
||
],
|
||
"recommended_fix": "Tune router threshold for heavy/live boundary."
|
||
},
|
||
{
|
||
"question_id": "Q29",
|
||
"question_text": "Baseline closed/open periods.",
|
||
"question_class": "heavy_analytical",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 414,
|
||
"planning_time_ms": 89,
|
||
"retrieval_time_ms": 159,
|
||
"response_generation_time_ms": 166,
|
||
"context_size": 2105,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "acceptable",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q30",
|
||
"question_text": "Company anomaly summary.",
|
||
"question_class": "heavy_analytical",
|
||
"expected_route": "batch_refresh_then_store",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 390,
|
||
"planning_time_ms": 81,
|
||
"retrieval_time_ms": 151,
|
||
"response_generation_time_ms": 158,
|
||
"context_size": 2097,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "acceptable",
|
||
"route_quality_assessment": "acceptable_with_warning",
|
||
"issues_detected": [
|
||
"Route mismatch: expected batch_refresh_then_store, got store_feature_risk"
|
||
],
|
||
"recommended_fix": "Tune router threshold for heavy/live boundary."
|
||
},
|
||
{
|
||
"question_id": "Q31",
|
||
"question_text": "Что по налогам и рискам?",
|
||
"question_class": "ambiguous_fuzzy",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 393,
|
||
"planning_time_ms": 82,
|
||
"retrieval_time_ms": 152,
|
||
"response_generation_time_ms": 159,
|
||
"context_size": 2098,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "acceptable",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q32",
|
||
"question_text": "Что странное в расходах?",
|
||
"question_class": "ambiguous_fuzzy",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 396,
|
||
"planning_time_ms": 83,
|
||
"retrieval_time_ms": 153,
|
||
"response_generation_time_ms": 160,
|
||
"context_size": 2099,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "acceptable",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q33",
|
||
"question_text": "Самые рисковые контрагенты?",
|
||
"question_class": "ambiguous_fuzzy",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 399,
|
||
"planning_time_ms": 84,
|
||
"retrieval_time_ms": 154,
|
||
"response_generation_time_ms": 161,
|
||
"context_size": 2100,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "acceptable",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q34",
|
||
"question_text": "Что с 68.02?",
|
||
"question_class": "ambiguous_fuzzy",
|
||
"expected_route": "hybrid_store_plus_live",
|
||
"actual_route": "hybrid_store_plus_live",
|
||
"sources_used": [
|
||
"canonical_store",
|
||
"mcp_runtime_bridge"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 822,
|
||
"planning_time_ms": 115,
|
||
"retrieval_time_ms": 525,
|
||
"response_generation_time_ms": 182,
|
||
"context_size": 2951,
|
||
"answer_text": "[simulated-4o-mini-profile] route=hybrid_store_plus_live; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "acceptable",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
},
|
||
{
|
||
"question_id": "Q35",
|
||
"question_text": "Проверить документы июня.",
|
||
"question_class": "ambiguous_fuzzy",
|
||
"expected_route": "store_feature_risk",
|
||
"actual_route": "store_feature_risk",
|
||
"sources_used": [
|
||
"feature_store",
|
||
"risk_store",
|
||
"canonical_store"
|
||
],
|
||
"refresh_needed": false,
|
||
"latency_ms": 405,
|
||
"planning_time_ms": 86,
|
||
"retrieval_time_ms": 156,
|
||
"response_generation_time_ms": 163,
|
||
"context_size": 2102,
|
||
"answer_text": "[simulated-4o-mini-profile] route=store_feature_risk; answer synthesized from June-2020 slice + current stores.",
|
||
"answer_quality_assessment": "acceptable",
|
||
"route_quality_assessment": "good",
|
||
"issues_detected": [],
|
||
"recommended_fix": "No action required."
|
||
}
|
||
]
|
||
} |