weichen
613fb27ba0
Why: No task-level measurement of real agent behavior existed, so the failure chain documented in the diagnosis was invisible to CI. The harness drives a configured backend over its public HTTP surface (upload, message, poll, HITL auto-resolve), computes per-turn metrics (tool failures, full regenerations, API-discovery calls, original-material reads, plan usage, gate checks) and outcome checks (unverified facts vs material text, final claims vs artifact headings), and writes a JSON + Markdown report. Evidence: SELF - built behind the live build tag (CI skips); vet passes with -tags live; drove the qa instance (remote main 1ebd46e) through the four golden tasks end to end; report referenced on the phase01 task card. Impact: New eval/live package (tasks.json + runner). Materials stay outside the repo per eval/README; runs are opt-in via AGENT_EVAL_BASE. Refs: Dev task feature/agent-quality-phase01; documents proposal 2026-10-09-agent-quality-improvement-plan.md §4 P0.
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。