• Joined on 2026-06-26
solahqb created pull request solahqb/AgentEvalTool#34 2026-08-25 10:39:28 +00:00
feat(v1.3.1): Phase 2 成本/放弃率/Go-No-Go 基础设施生效
solahqb pushed to feat/v1.3.1-phase2-wiring at solahqb/AgentEvalTool 2026-08-25 10:39:28 +00:00
c956da7686 feat(v1.3.1): Phase 2 让成本/放弃率/Go-No-Go 基础设施真正生效
solahqb pushed to main at solahqb/AgentEvalTool 2026-08-25 10:22:54 +00:00
64ed534426 Merge pull request 'fix(rules): v1.3.1 Phase 1 修复规则层三处缺陷' (#33) from fix/v1.3.1-phase1-rule-bugfixes into main
c1a3cdbaa9 fix(rules): 修复代码审查发现的三处规则层缺陷
Compare 2 commits »
solahqb merged pull request solahqb/AgentEvalTool#33 2026-08-25 10:22:52 +00:00
fix(rules): v1.3.1 Phase 1 修复规则层三处缺陷
solahqb created pull request solahqb/AgentEvalTool#33 2026-08-25 10:20:01 +00:00
fix(rules): v1.3.1 Phase 1 修复规则层三处缺陷
solahqb created branch fix/v1.3.1-phase1-rule-bugfixes in solahqb/AgentEvalTool 2026-08-25 10:13:57 +00:00
solahqb pushed to fix/v1.3.1-phase1-rule-bugfixes at solahqb/AgentEvalTool 2026-08-25 10:13:57 +00:00
c1a3cdbaa9 fix(rules): 修复代码审查发现的三处规则层缺陷
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 created branch feat/user-experience-metrics in solahqb/AgentEvalTool 2026-08-25 08:37:10 +00:00
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 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 »