4 Commits
Author SHA1 Message Date
linshen 083275e03e fix(test): align preview toolbar imports and evaluation fixtures 2026-04-02 23:04:33 +08:00
linshen f49edee170 feat(core): add structured compare evaluation pipeline 2026-03-21 14:36:17 +08:00
linshen 2f0df2bb8c refactor(core): redesign evaluation protocol and template builders
- replace original/optimized semantics with analysis, result, and compare request types
- centralize evaluation prompt construction in shared builders
- tighten rendered sample and evidence behavior tests for core evaluation service
2026-03-18 09:35:43 +08:00
linshen 63ab9e66cd feat(test): 建立完整的测试基础设施和集成测试
- 建立 VCR 测试基础设施,支持 LLM API 回放
- 添加错误门禁和冒烟测试
- 添加 LLM 服务集成测试(P0)
- 记录测试进展并更新任务计划
2026-01-03 21:08:00 +08:00