- Judge baseline excerpt and library chapter separately; build_memoir_compare_summary for gate, nine-dim and leaf deltas. - Memoir SSE chapter payload: baseline_judge, compare_summary, baseline_judge_error. - MemoirJudgeOutput: loose score coercion and post-validate clamp; memoir judge prompt caps from settings. - app-eval-web: two-column MemoirScoreCard layout, MemoirCompareSummary, chapter blocks and CSS. - Add memoir_compare_summary, log_events, celery_log_context, memoir_pipeline_progress; tests and migration 0014. - Misc: memory/evidence and enrichment paths, task/orchestrator updates, internal-eval docs, env examples.
内部评测 Web(Life Echo)
独立 Vite + React 控制台,对接 app.internal_main:internal_app。路由仅 Playground(分步测评)、Memoir、Memoir · Stories:先对话重放(skip_memoir)→ memoir-submit → 查看成稿。
环境变量
VITE_EVAL_API_BASE— 内部 API 根,如http://127.0.0.1:8001VITE_EVAL_API_KEY— 与后端INTERNAL_EVAL_API_KEY相同
开发
npm install
VITE_EVAL_API_BASE=http://127.0.0.1:8001 VITE_EVAL_API_KEY=your-secret npm run dev
浏览器打开提示的端口(默认 5174)。
构建
npm run build
产物在 dist/,可挂任意静态服务器。对话流式评审使用带 X-Internal-Eval-Key 的 fetch(见 api/docs/internal-eval.md)。