5 Commits

Author	SHA1	Message	Date
Kevin	ac49bc7f23	feat(eval): memoir A/B chapter judging and eval-web parity with dialogue ... - 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.	2026-04-10 10:25:15 +08:00
Kevin	b0251e5b26	feat(eval): server-side replay/phase1 timing + memoir phase1 batch chunking ... - Replay and memoir-submit responses include started/finished UTC and elapsed_ms; Phase1 poll exposes Redis-backed submit time and elapsed_ms_since_submit. - Phase1 batch LLM splits segments by memoir_phase1_batch_llm_chunk_size with bisect fallback per chunk; Playground shows server timings. Made-with: Cursor	2026-04-09 13:39:04 +08:00
Kevin	309a051038	feat: 回忆录证据血缘与内部评测可追溯，顺带对齐本地评测台与 CI ... 数据库与模型：新增多版迁移（章节证据快照、对话血缘、记忆事实/时间线 lineage 等），把「成稿 ↔ 对话/记忆」的溯源信息落到表结构里。 业务链路：会话与 WS、回忆录/故事流水线、记忆写入与 enrichment 等跟着接上线索与快照；新增章节证据快照与评测侧 EvalTraceService 等模块，方便组评审用的证据包。 内部评测：自动化 run 与手工 memoir 评审共用可追溯证据；rubric/ judge 相关脚本与文档有配套调整。 app-eval-web：Memoir/实验详情里能展开看证据摘要与 evidence_trace（含对话轮次 id）；Vite 代理与 development.sh 注入的 API 端口与当前默认内部评测端口一致，避免改端口后页面连错服务。 工程杂项：GitHub Actions / 仓库说明有更新；各适配器与支付/配额/plan 等多处为小改动或跟随主改动的收尾；新增/扩充了?	2026-04-08 15:37:09 +08:00
Kevin	43d1689e9c	feat(api): 统一 LLM JSON 调用层 llm_json_call，按域 Schema 迁移 chat/memoir agents	2026-04-03 13:44:11 +08:00
Kevin	07c6478742	feat(api): 访谈路径轻量门控、Memoir Phase1 批处理与叙事/记忆管线加固 ... - 新增 utterance_substance：短时/应答/元话语可跳过记忆检索、阶段 LLM 与资料抽取 LLM；可配置 - 输入归一化：LLM 模式默认仅语音/ASR；配置项写入 .env.example - Memoir Phase1：可选 batch LLM 一次性抽取+分类（失败回退逐段）；Extraction 空槽位时阶段与 current_stage 对齐，prompt 约束收紧 - 叙事与忠实度：narrative_safety、证据重叠/场合锚点、标题 slots 与履历短语 grounded；fidelity 解析失败 fail-open 可配置 - 章节管线：锁 TTL 上调、锁竞争 Celery 重试、Phase2 immediate singleflight 等；story_pipeline_sync / chapter_compose / memoir_tasks 联动 - Memory：compaction / repo / summarizer / evidence 小修；事实 FTS 未命中是否回退最近事实可配置 - 新增 memoir_pipeline_trace；补充 memoir_reliability 文档与多项回归/门控测试	2026-04-03 10:12:59 +08:00