tzt
ce0f6170d3
- 入库历史遗漏源码/测试：router_system 9 模块（agent/executors/inference/knowledge/ memory/planner/skills/trace）、tests 11 个测试文件、config/knowledge 领域知识 - 入库根目录方案文档（v2/v3/可行性×2）、references 文献（arxiv 14-18/cnki_open/ 参考文献清单）、research 论文素材（routerarena/paper/中文文献 PDF） - 前端构建产物刷新（新 hash）；webapp 误写文档删除 - gitignore 增补：deepseek-harness、research/_refs、.mimosa/.zcode、网关日志/pid、 临时调试脚本、tests/e2e/node_modules、AI代理功能开发/prefix - 基线确认：318 passed
33 lines
836 B
JSON
33 lines
836 B
JSON
{
|
|
"router_name": "es-expert",
|
|
"n_queries": 90,
|
|
"routing_latency_ms_per_query": 21.243365556519066,
|
|
"domain_distribution": {
|
|
"code": 12,
|
|
"general": 40,
|
|
"math": 6,
|
|
"legal": 6,
|
|
"medical": 8,
|
|
"finance": 8,
|
|
"life": 4,
|
|
"education": 6
|
|
},
|
|
"routing_distribution": {
|
|
"gpt-4o-mini": 8,
|
|
"mistral-medium": 62,
|
|
"claude-3-haiku-20240307": 16,
|
|
"gemini-2.0-flash-001": 2,
|
|
"deepseek-chat": 2
|
|
},
|
|
"confidence": {
|
|
"min": 0.2592,
|
|
"max": 0.99,
|
|
"mean": 0.5881833333333334
|
|
},
|
|
"mock_accuracy": 0.7444444444444445,
|
|
"total_cost_usd": 0.04596006,
|
|
"cost_per_1k_usd": 0.5106673333333333,
|
|
"arena_score_mock": 0.7223003144396156,
|
|
"prediction_file": "research/routerarena/output\\es-expert.json",
|
|
"diagnostics_file": "research/routerarena/output\\es-expert_diagnostics.json"
|
|
} |