weichen
51d7c6ab87
ci / vet-and-test (pull_request) Successful in 51s
Why: A 250ms card poll missed a checkpoint saved about one millisecond before failure. Evidence: The persistence regression failed before the fix, passed afterward, and independent read-only replay isolated the current conversation and running state. Impact: Evaluation reads committed card events without changing model output or re-running the paid sample; U3 quality remains failed. Refs: Agent-System-Backend#193; Agent-System-Dev#512
交付物评测
仓内 testdata/ 是脱敏短样例，用来确认评分卡能区分“结论先行”和“栏目式笔记”。
真实会议材料不要放进仓库。放到 ~/.agent-system/eval/，或设置 EVAL_DIR。其中的 .md 会在 go test ./eval/ 里被打分并打印，缺失该目录时测试跳过。
cd modules/backend && go test ./eval/ ./internal/quality/ -count=1
两种入口的切换由 DecideSwitch 判断：squad 分数不低于 direct，并且直通路径多出来的首字延迟 P50 不超过 3 秒。没有同一评测集上的实测分数时，结果是不切换，runtime.entry 默认保持 direct。