OG T
fe7fd7a3e0
feat(tests): ADR-018 LLM 測試策略三層架構
問題: LLM 測試因模型波動導致 CI 失敗
解決方案: 三層測試策略
- Tier 1 (CI): Schema 驗證 + Golden Responses
- Tier 2 (Nightly): 屬性測試 + Live LLM
- Tier 3 (Weekly): 語意相似度測試
新增檔案:
- ADR-018-llm-testing-strategy.md
- tests/llm_testing/ 框架
- schema_validators.py: Pydantic Schema 驗證
- property_validators.py: kubectl/風險等級驗證
- golden_responses.py: 預錄回應管理
- tests/test_llm_tier1_schema.py: 35 個 Tier 1 測試
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-26 11:17:00 +08:00
..
2026-03-26 11:17:00 +08:00
2026-03-26 10:37:45 +08:00
2026-03-23 23:51:37 +08:00
2026-03-25 23:57:24 +08:00
2026-03-26 10:37:45 +08:00
2026-03-26 11:17:00 +08:00
2026-03-25 11:37:14 +08:00
2026-03-26 11:09:25 +08:00
2026-03-25 11:37:14 +08:00
2026-03-23 23:51:37 +08:00
2026-03-26 10:37:45 +08:00