Why: Real source-backed discoveries should reach the same task card before the slow channel completes. Evidence: SELF receipts record runtime and manager checkpoint red-green tests, scoped source/version checks, privacy filtering, quota corrections, and SQLite/PG regressions; fixed composition and live comparison follow. Impact: Adds a local material-only checkpoint sink with no summary model calls, uses version witnesses for source commits, and preserves existing reading and notification paths. Refs: fast-slow-u2-u3 Tasks 6 and 7; test-only live HTTP harness bounds shared provider requests without approving HITL
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。