• Joined on 2026-06-26
solahqb closed issue solahqb/AgentEvalTool#26 2026-08-25 08:40:46 +00:00
实现用户体验指标(放弃率+流畅度)
solahqb pushed to main at solahqb/AgentEvalTool 2026-08-25 08:40:46 +00:00
e7e3716325 Merge pull request 'feat: 用户体验指标(放弃率+流畅度评估)' (#32) from feat/user-experience-metrics into main
21cc6ed407 feat: 用户体验指标(放弃率+流畅度评估)
Compare 2 commits »
solahqb merged pull request solahqb/AgentEvalTool#32 2026-08-25 08:40:45 +00:00
feat: 用户体验指标(放弃率+流畅度评估)
solahqb pushed to main at solahqb/AgentEvalTool 2026-08-25 08:40:29 +00:00
d27ed58999 Merge pull request 'feat: 成本效率跟踪基础设施' (#31) from feat/cost-tracking into main
56c56a7b4a feat: 成本效率跟踪基础设施
Compare 2 commits »
solahqb merged pull request solahqb/AgentEvalTool#31 2026-08-25 08:40:28 +00:00
feat: 成本效率跟踪基础设施
solahqb closed issue solahqb/AgentEvalTool#25 2026-08-25 08:40:28 +00:00
实现成本效率跟踪(对话级+任务级)
solahqb created pull request solahqb/AgentEvalTool#32 2026-08-25 08:37:30 +00:00
feat: 用户体验指标(放弃率+流畅度评估)
solahqb pushed to feat/user-experience-metrics at solahqb/AgentEvalTool 2026-08-25 08:37:10 +00:00
21cc6ed407 feat: 用户体验指标(放弃率+流畅度评估)
solahqb created branch feat/user-experience-metrics in solahqb/AgentEvalTool 2026-08-25 08:37:10 +00:00
solahqb created pull request solahqb/AgentEvalTool#31 2026-08-25 08:07:58 +00:00
feat: 成本效率跟踪基础设施
solahqb created branch feat/cost-tracking in solahqb/AgentEvalTool 2026-08-25 08:07:42 +00:00
solahqb pushed to feat/cost-tracking at solahqb/AgentEvalTool 2026-08-25 08:07:42 +00:00
56c56a7b4a feat: 成本效率跟踪基础设施
solahqb pushed to main at solahqb/AgentEvalTool 2026-08-25 08:02:07 +00:00
2c79abf1de Merge pull request 'feat(safety): 扩展规则覆盖幻觉、越权和合规检查' (#30) from feat/safety-extended into main
192fe0fc5f feat(safety): 扩展规则覆盖幻觉、越权和合规检查
Compare 2 commits »
solahqb closed issue solahqb/AgentEvalTool#22 2026-08-25 08:02:06 +00:00
扩展 safety 规则覆盖幻觉、越权和合规
solahqb merged pull request solahqb/AgentEvalTool#30 2026-08-25 08:02:06 +00:00
feat(safety): 扩展规则覆盖幻觉、越权和合规检查
solahqb pushed to main at solahqb/AgentEvalTool 2026-08-25 08:01:45 +00:00
eb615c6522 Merge pull request 'feat(response_time): 支持平均延迟和吞吐量指标' (#29) from feat/response-time-extended into main
737c9ab80e feat(response_time): 支持平均延迟和吞吐量指标
Compare 2 commits »
solahqb closed issue solahqb/AgentEvalTool#21 2026-08-25 08:01:44 +00:00
扩展 response_time 支持首字延迟和吞吐量
solahqb merged pull request solahqb/AgentEvalTool#29 2026-08-25 08:01:44 +00:00
feat(response_time): 支持平均延迟和吞吐量指标
solahqb commented on issue solahqb/AgentEvalTool#24 2026-08-25 07:58:34 +00:00
能力对比报告雷达图和排名调研

Resolution

调研完成,详见 research/compare-report-radar.md(分支…

solahqb closed issue solahqb/AgentEvalTool#24 2026-08-25 07:58:34 +00:00
能力对比报告雷达图和排名调研