Commit Graph

17 Commits

Author SHA1 Message Date
Sully
53e0065e3e refactor(api): TOML 配置 SSOT、统一错误契约、Auth/事务加固与可观测性 (#33)
配置 SSOT(TOML + .env)
统一错误契约
Auth 与事务边界
Redis / Celery 可靠性:业务 Redis(DB/0)与 Celery broker/backend(DB/1)显式拆分;连接池、sync client
可观测性(OpenTelemetry + LGTM)
2026-05-22 13:44:50 +08:00
Sully
f09ae248f9 feat: OpenTelemetry LGTM observability, dev tooling, and memoir UX fixes (#31) (#32)
* add staging ios app build script

* feat(api): add OpenTelemetry LGTM stack for local observability

Wire OTel traces, metrics, and logs through a collector to Tempo,
Prometheus, and Loki, with custom LLM instrumentation, dev compose overlay,
Grafana provisioning, env templates, and development.sh auto-start.



* feat: expand observability, harden dev tooling, and fix expo staging UX

Add business and LLM Prometheus metrics with Grafana dashboards, alerting,
and a metrics verification script. Wire telemetry through adapters and core
LLM paths, and document the local LGTM workflow.

Fix development.sh for macOS bash 3.2, open Grafana and eval-web in Chrome,
and repair eval-web auto-open (unbound EVAL_WEB_BROWSER_SCHEDULED). Merge
internal-eval into the main dev script with improved compose handling.

Require EXPO_PUBLIC_* at build time, improve iOS HTTP ATS for staging IPs,
show memoir empty state instead of load errors when no chapters exist, and
add jest env setup plus chapter list response normalization.



* chore: enable Grafana Assistant Cursor plugin



* fix: memoir empty state and repair withdrawn 0020_chapters_book_id stamp

Show empty memoir UI when the chapter list succeeds with no items; treat auth/404 as non-fatal. Extend alembic revision repair so local dev DBs stamped with the removed 0020_chapters_book_id migration can roll back and upgrade to 0019.



---------

Co-authored-by: Kevin <kevin@brighteng.org>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-20 15:14:13 +08:00
Kevin
3d01085442 fix(conversation): 修复实时会话 TTS/回复被离屏 WS 抢占
- 列表预热仅预取消息缓存,避免后台 WebSocket 覆盖服务端连接
- RealtimeSession UI 回调按 owner 独占,防止 offscreen 覆盖聊天页
- 列表页聚焦时再 prewarm,会话页 TTS 入队优先 base64
- 管线下发 TTS 同时带 audio_base64 与 audio_url;协议说明同步
- 移除 TTS 排查用前后端调试日志,保留错误/告警
- 补充 WS / RealtimeSession / entry-warmup / 播放器相关单测

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-12 10:42:44 +08:00
Kevin
93be60f74c fix(tts): gate auto reply by ENABLE_TTS; allow on-demand and manual playback
- Pipeline: skip _send_tts_audio only for non-manual when ENABLE_TTS=false;
  remove enable_tts early return from handle_tts_request_on_demand.
- Tencent TTS: PrimaryLanguage/chunking follow user language preference only.
- Expo: let manual tts_audio bypass late-segment playback gate after interrupt.
- Docs: clarify ENABLE_TTS vs tts_request in api/.env.example and TTSProvider port.
- Tests: add manual bypass cases; adjust pipeline language tests for en+Chinese text.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-11 17:15:02 +08:00
Kevin
ccdc4e4277 feat(i18n): persist language preference and thread through chat, memoir, TTS
- Add users.language_preference (Alembic 0018, default zh); capture at signup/SMS
  only; expose on auth and profile APIs
- Lite English prompts for chat and memoir; localized stage labels and agent
  names (Life Echo / 岁月知己)
- Tencent TTS: language-aware synthesis, ModelType=1 for 501004, English chunking
- WebSocket pipeline: emit all AGENT_RESPONSE segments when TTS cancels; INFO logs
  for tts_this_turn and TTS decisions; on-demand TTS logging
- Expo: device language on auth, i18n tiers/agent name, [SPLIT] streaming UX fixes
- Tests for migration, prompts, pipeline, router tts_this_turn, reply segments

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-11 16:16:49 +08:00
Kevin
ac436b87a2 feat(api): 收敛对话与记忆流程边界,引入 LLM 网关与专用服务
- MemoryService 异步路径委托 MemoryIngestService / MemoryRetrievalService;富化派发经 MemoryEnrichmentScheduler
- WebSocket pipeline 经 ChatTurnService 与显式 DTO 编排单轮对话;回忆录片段入队由 MemoirIngestScheduler 封装
- 新增 LlmGateway(LlmUseCase),各 agent、任务与适配器对齐 ports
- 补充 memory 提示适配、runtime 类型、memory-retrieval 文档、ai-touchpoints 说明与扫描脚本及配套测试

Made-with: Cursor
2026-04-30 09:17:01 +08:00
Kevin
80833f7033 feat(api): DeepSeek V4 Flash 默认、HTTP 错讯与多供应商分层
- 主链路默认 deepseek-v4-flash,DEEPSEEK_THINKING_ENABLED 对齐旧非思考 chat
- 评测台评审装配迁入 adapters/llm(deepseek_eval_judge、zhipu_eval_judge)与 eval_judge_spec
- 拆分 llm_http_openai_chat_errors 与 llm_errors(DeepSeek/智谱品牌与文档链),llm_call 支持 http_error_vendor
- EvalJudgeService 按 spec.provider 传入 allm_json_call;评测台前端文案改为 V4 Flash
- 更新 .env 示例与 staging/production 的 DEEPSEEK_MODEL;补充 openai/供应商错讯测试

Made-with: Cursor
2026-04-27 14:34:30 +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
41518bda11 聊天和回忆录证据检索都走 pgvector,去掉 Postgres FTS/content_tsv,新迁移删掉 content_tsv 列(部署要先 alembic upgrade)。
Embedding 端口增加 is_available(),聊天和回忆录日志用统一方式表示向量是否真能调用。

记忆整理(compaction)支持 Beat 定期扫用户;

事实抽取提示与 subject 归一化,减少同一人多种称呼;
2026-04-03 11:43:16 +08:00
Kevin
42ae2a5e91 feat(api): 接入智谱 embedding-3(1024 维)并迁移 memory_chunks 向量列 2026-03-30 13:54:35 +08:00
Kevin
aac484463d feat(api): 拆分章节物化与 Story 后处理,并加固 Redis 锁与腾讯 ASR
回忆录 Story 流水线(同步)
- 同步路径仅写入 Story 与章节关联,改为 mark_chapter_dirty_sync,不再内联 compose
- 物化由 Celery recompose_chapter 异步完成;compose 不变量与异常时保留 dirty 的语义在 repo 中补充说明
- Evidence:大批次时降低 top_k;路由候选 story 携带 char_count/version_count;append 超长/版本过多时强制新开 story
- 叙事 prompt:relevant_chunks 去重,减少重复证据噪声
- 叙事回退与忠实度 gate:返回 fallback 类型并记录结构化日志(含耗时、JSON 有效性等)

Post-commit 与任务编排
- 新增 post_commit.enqueue_story_post_commit_effects:统一派发 generate_story_image(Redis 去重)、延迟 recompose_chapter、可选 memory compaction
- memoir_tasks / story_service / story_image_tasks 改为调用 post-commit 入口;主图回填后按关联章节重算并调度物化与 compacs(锁委托、Redis 单例、ASR to_thread)
- 更新 test_narrative_pipeline 以适配 _apply_narrative_fallbacks 返回值
2026-03-30 11:53:04 +08:00
Kevin
e4bf0710c7 feat(memory,conversation): 记忆富化/证据包、时间线幂等字段与对话分段全链路
数据库
- 新增迁移 0003:timeline_events.memory_source_id 外键 → memory_sources,便于按 ingest 源做时间线幂等

后端 - 记忆
- 新增 ingest 后 LLM 富化(摘要/事实/时间线),可配置开关与最大字符数
- 新增证据包组装:合并 chunk、摘要、事实、时间线、故事等检索结果;支持空 query 时是否仍带 rolling 等开关
- repo/retriever/service/router/schemas/summarizer/timeline/extractor 等扩展;文档 memory-retrieval.md 更新

后端 - 对话 WS
- 增加 PING/PONG;分段 ASR 日志与空音频处理;转写失败与「无助手回复」错误提示更明确
- 助手多段回复持久化使用统一分隔符,与分段逻辑一致

后端 - Agent
- reply_limits:按 [SPLIT] 与段落拆段,并保证非空 fallback,供 WS 与 TTS 多段下发

后端 - 回忆录任务
- transcript ingest 记录 source_id;任务成功结?
2026-03-27 16:24:43 +08:00
Kevin
a3f61fcc0f feat(api+app): 对话阶段化、回忆录流水线与客户端会话体验
- DB: segments 用户输入文本(Alembic 0002)
- Chat: 阶段检测/阶段提示/回复限制,编排与访谈/画像 prompts 调整
- Memoir: 忠实度检查 agent,叙事与分类等链路更新
- Core: agent 日志、Alembic 启动、LangChain/日志/配置等
- Story: time_hints;Memory 检索与相关测试
- Expo: 助手头像、会话页与消息拆分、实时会话与文案/i18n
- Docs/scripts/tests: 迁移脚本、LLM JSON/记忆检索文档、新增单测
2026-03-26 12:13:36 +08:00
Kevin
7317bf10cd fix/various fixes 2026-03-20 15:15:35 +08:00
Kevin
c6e07ce5ca chore/ 删除无用文件 2026-03-19 14:36:40 +08:00
Sully
92b7848c48 feat/tts (#15)
Co-authored-by: Kevin <kevin@brighteng.org>
2026-03-19 09:11:25 +08:00
yangshilin
48b70e1350 Merge branch 'refactor/backend-architecture' into development 2026-03-18 17:18:23 +08:00