Compare commits

...
504 Commits
Author SHA1 Message Date
吉鑫升 ca2696b23f Merge branch 'master' into master-zl 2026-08-31 18:06:54 +08:00
吉鑫升 90e94994f5 Merge remote-tracking branch 'origin/master' into master 2026-08-31 18:06:10 +08:00
吉鑫升 2718915d34 Merge branch 'master' into master-zl 2026-08-31 18:02:26 +08:00
吉鑫升 8e0d755b57 fix: preserve knowledge base references 2026-08-31 18:02:05 +08:00
吉鑫升 ee83258b70 Merge branch 'master' into master-zl
# Conflicts:
#	frontend-web/src/components/workspace/input-box.tsx
#	offline-backend-20260512/backend/CLAUDE.md
#	offline-backend-20260512/backend/packages/harness/deerflow/agents/lead_agent/prompt.py
#	offline-backend-20260512/backend/tests/test_es_query_routing_prompt.py
2026-08-31 17:55:11 +08:00
吉鑫升 40542db400 feat: add configurable chat display modes 2026-08-31 17:49:48 +08:00
董宏凯andCursor f18994fd38 fix: show generated HTML charts on Win7 Chrome
Rewrite oklch/color-mix and space-separated rgb before iframe preview so pie and bar fills are not dropped on Chrome 109.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-30 09:25:09 +08:00
董宏凯andCursor 7c15ca6710 fix: show sandbox flowcharts on Win7 Chrome and repair common Mermaid syntax
Disable HTML labels so nodes use native SVG text, and rewrite bare edge labels plus invalid class statements before render.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-30 09:05:29 +08:00
董宏凯 31cfa93408 feat: 智能体列表页引导改为手动触发,完成/跳过不再跳转创建页
- AgentGuide 新增 autoStart 属性(默认 true),列表页挂载传 false:进智能体列表页不再自动弹引导,仅由头部「使用引导」按钮手动触发
- 去掉 list 段与创建页的联动:finish 不再 router.push,最后一步按钮恢复默认「完成」,跳过/走完都就地结束并写记忆
- AGENTS.md 同步更新智能体引导条目
2026-08-30 08:53:34 +08:00
董宏凯andCursor b164e70541 fix: unlock send immediately after SSE close
Normal Q&A no longer waits on GET /runs before the next message. Probe run status only on 409 or dropped streams.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-30 08:48:53 +08:00
吉鑫升 3715af3138 chore: move offline release assets to standalone repository 2026-08-27 23:35:57 +08:00
吉鑫升 973500a0f0 fix: preserve LF in offline deployment assets 2026-08-27 22:35:57 +08:00
吉鑫升 d9a94245fc feat: standardize DeerFlow offline deployment 2026-08-27 22:06:43 +08:00
董宏凯 1764d0d5f2 Merge branch 'master-nj' into 'master'
fix: 8BF 无 taskId 开全新会话,公共链条发布联动席位智能体

See merge request knowledge-base-bj/deerflow-code!35
2026-08-27 13:48:17 +00:00
董宏凯andCursor 84370e2072 fix: 8BF 无 taskId 开全新会话,公共链条发布联动席位智能体
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-27 21:47:31 +08:00
董宏凯 0289a76fce Merge branch 'master-nj' into 'master'
feat: 新增 agentfx 任务深链与研判报告入库流程

See merge request knowledge-base-bj/deerflow-code!34
2026-08-27 10:39:04 +00:00
董宏凯andCursor 32e509b2b3 fix: 岗位会商 handoff 将上游产物镜像到当前席位沙箱
席位线程隔离导致下游 read_file 找不到上游路径;镜像到 workspace/upstream 并改写 handoff 引用,附带安全路径校验与 SQL 回退测试。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-27 18:35:17 +08:00
董宏凯 440b490b0d Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-nj 2026-08-27 16:33:33 +08:00
董宏凯andCursor 52b9cbf707 feat: 新增 agentfx 任务深链与研判报告入库流程
支持 goPath=agentfx 的 iframe 嵌入问答、内置研判助手种子与报告导入协助卡,并完善深度研究流式报告能力。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-27 16:32:22 +08:00
吉鑫升 87505feac4 feat: improve skill uploads and agent runtime stability 2026-08-27 11:15:25 +08:00
吉鑫升 11326eeb1c feat: improve skill uploads and agent runtime stability 2026-08-27 11:14:23 +08:00
吉鑫升 485a8fa9d9 feat: standardize Word export and Office conversion 2026-08-27 00:09:53 +08:00
吉鑫升 c5eefe60f0 feat: standardize Word export and Office conversion 2026-08-27 00:09:08 +08:00
董宏凯 4ce2f3a502 Merge branch 'master-nj' into 'master'
feat: 智能体问答页右侧面板受控折叠,收起整列归零并在 header 提供展开入口

See merge request knowledge-base-bj/deerflow-code!33
2026-08-26 10:25:11 +00:00
董宏凯andCursor 6e9e89a6cb fix: 流式自动开沙箱分阶段收起侧栏,避免同帧布局卡顿
新增 preOpen 两阶段标记,先错开收起左右侧栏再展开沙箱;智能体详情面板据此提前收起,减少与沙箱展开同帧叠加造成的卡顿。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-26 18:24:06 +08:00
董宏凯 5be21f2c3d Merge branch 'master-nj' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl
# Conflicts:
#	frontend-web/src/components/workspace/agents/agent-card.tsx
#	frontend-web/src/components/workspace/custom-prompt-menu.tsx
2026-08-26 17:45:39 +08:00
董宏凯andCursor 90d29ed232 feat: 智能体问答页右侧面板受控折叠,收起整列归零并在 header 提供展开入口
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-26 17:37:23 +08:00
董宏凯 d9de41dd67 代码修改 2026-08-26 17:15:04 +08:00
董宏凯 f1245da3e4 Merge branch 'master-nj' into 'master'
feat: 舆情分析智能体改为经 Gateway 转发外部 AG-UI 网关

See merge request knowledge-base-bj/deerflow-code!32
2026-08-26 09:00:55 +00:00
董宏凯 38c3de39f0 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-nj
# Conflicts:
#	AGENTS.md
#	frontend-web/src/pages/AgentChatPage.tsx
2026-08-26 16:37:41 +08:00
董宏凯andCursor 33639e5b89 fix: 修复嵌套 iframe 污染 embed 会话与协助卡后流式显示异常
顶层窗口通过 topOwned 标记自愈老版嵌套页写脏的 embed.session;协助卡提交后避免冻结 checkpoint 覆盖实时 SSE,并仅在服务端回显新 human 消息时清除乐观气泡。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-26 16:28:10 +08:00
吉鑫升 d488e65e49 Merge branch 'master' into master-zl 2026-08-26 16:09:06 +08:00
吉鑫升 676b00afb6 Merge branch 'ji' into master 2026-08-26 16:07:37 +08:00
吉鑫升 0980eea975 feat: unify formal Word export 2026-08-26 16:02:23 +08:00
董宏凯 eba3008482 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-nj 2026-08-26 15:48:23 +08:00
吉鑫升 9b904ac3dd Merge branch 'ji' into master
# Conflicts:
#	offline-backend-20260512/backend/CLAUDE.md
#	offline-backend-20260512/backend/README.md
#	offline-backend-20260512/backend/app/gateway/routers/llmwiki.py
#	offline-backend-20260512/backend/config.yaml
#	offline-backend-20260512/backend/packages/harness/deerflow/config/llmwiki_config.py
#	offline-backend-20260512/backend/tests/test_llmwiki_weknora.py
2026-08-26 15:46:58 +08:00
董宏凯 704438b3d2 bug修改 2026-08-26 15:46:49 +08:00
吉鑫升 d35d075669 feat: add compact toolbox and public wiki vector search 2026-08-26 14:40:57 +08:00
董宏凯 910cee9e67 用户引导沙箱优化 2026-08-26 14:14:26 +08:00
fengxiangdebaozi dcc3e0799d Merge branch 'master-zl' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl 2026-08-26 12:31:48 +08:00
董宏凯 21f3787b8b 代码修改 2026-08-26 11:30:39 +08:00
董宏凯 33b719d460 用户引导 2026-08-26 11:09:43 +08:00
董宏凯 c6fcf51e0c 用户引导 2026-08-26 09:41:53 +08:00
董宏凯andCursor 62a3faa7c8 feat: 舆情分析智能体改为经 Gateway 转发外部 AG-UI 网关
前端不再直连上游 SSE,改为 POST /api/sentiment-agent/stream 由后台代理转发,支持关闭 TLS 校验并回传完整错误信息。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-25 18:26:48 +08:00
fengxiangdebaozi 7cc6aca398 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl 2026-08-25 17:36:14 +08:00
董宏凯 d87dfec2de Merge branch 'master-nj' into 'master'
feat: 业务链条发布审核流程 + 编辑器去除岗位职责输入框

See merge request knowledge-base-bj/deerflow-code!31
2026-08-25 09:35:16 +00:00
董宏凯 5c0864bf0a Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-nj 2026-08-25 17:33:40 +08:00
董宏凯andCursor 8ce3a62826 fix: 岗位会商历史按用户隔离,并为 write-file 预览启用 AI 写作视图
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-25 17:32:56 +08:00
董宏凯 8c3d6a02fc feat: 业务链条发布审核流程 + 编辑器去除岗位职责输入框
- 发布改为可选「确认审核 / 直接发布」:链条编辑页与圆桌「业务链条」弹窗行为一致;审核中可撤回
- 管理员在业务链条列表新增「待审核」筛选,审核发布后进入公共库
- 后端 roundtable_chains 新增 pending_review 字段(启动期自动补列)与 scope=pending 筛选;新增审核流程测试
- 编辑器席位去掉「岗位职责」输入框(保存时存量值原样保留)
2026-08-25 17:30:29 +08:00
fengxiangdebaozi dd1064b3cb Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl 2026-08-25 17:07:09 +08:00
吉鑫升 be9a490923 fix: harden wiki delivery and leaderboard performance 2026-08-25 16:58:58 +08:00
吉鑫升 e053b36b6e fix: harden wiki delivery and leaderboard performance 2026-08-25 16:58:13 +08:00
吉鑫升 9f29ecae9e fix: harden wiki delivery and leaderboard performance 2026-08-25 16:57:42 +08:00
fengxiangdebaozi 2ea331f9ec Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl 2026-08-25 14:53:57 +08:00
fengxiangdebaozi 296974e9e5 Merge branch 'master-zl' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl 2026-08-25 14:28:45 +08:00
吉鑫升 ed5b550ead fix: restore embedded wiki images and optimize vector sync 2026-08-25 11:27:02 +08:00
吉鑫升 4b86106a24 fix: restore embedded wiki images and optimize vector sync 2026-08-25 11:26:27 +08:00
fengxiangdebaozi 7f2c51957b Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl 2026-08-25 11:26:24 +08:00
董宏凯 043b0900d5 Merge branch 'master-nj' into 'master'
Master nj

See merge request knowledge-base-bj/deerflow-code!30
2026-08-25 03:26:03 +00:00
吉鑫升 0c5e2e8cb0 fix: restore embedded wiki images and optimize vector sync 2026-08-25 11:24:01 +08:00
董宏凯 40d06b781a 接口调整 2026-08-25 11:23:53 +08:00
董宏凯 c5328e6a35 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-nj 2026-08-24 20:47:55 +08:00
董宏凯 babc5e95c6 代码提交 2026-08-24 20:47:31 +08:00
吉鑫升 644cabd23d feat: complete public wiki and embedded previews 2026-08-24 20:42:39 +08:00
吉鑫升 1736227723 feat: complete public wiki and embedded previews 2026-08-24 20:41:24 +08:00
吉鑫升 30943159bf feat: complete public wiki and embedded previews 2026-08-24 20:40:44 +08:00
fengxiangdebaozi c4d61288b4 Merge branch 'master-zl' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl
# Conflicts:
#	frontend-web/src/components/workspace/input-box.tsx
2026-08-24 17:18:39 +08:00
fengxiangdebaozi 389df2ace5 Merge branch 'master-nj' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl
# Conflicts:
#	frontend-web/src/components/workspace/input-box.tsx
#	frontend-web/src/components/workspace/skill-display-sources.tsx
2026-08-24 17:14:46 +08:00
董宏凯 007ed5a7de Merge branch 'master-nj' into 'master'
Master nj

See merge request knowledge-base-bj/deerflow-code!29
2026-08-24 09:08:51 +00:00
董宏凯 ebc727e4fd 代码提交 2026-08-24 17:08:22 +08:00
吉鑫升 32dbdca480 Merge branch 'ji' into master-zl 2026-08-24 16:27:53 +08:00
吉鑫升 bc49df4561 feat: add public wiki embeds and ES query routing 2026-08-24 15:21:28 +08:00
fengxiangdebaozi 28eb8f86a7 Merge branch 'master-nj' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl 2026-08-24 14:45:45 +08:00
董宏凯 cdb8aa5f81 弹窗样式修改 2026-08-24 14:45:25 +08:00
吉鑫升 e818c24769 Merge remote-tracking branch 'origin/master' into ji
# Conflicts:
#	.gitignore
#	frontend-web/src/components/workspace/artifacts/context.tsx
#	frontend-web/src/components/workspace/messages/message-group.tsx
#	offline-backend-20260512/backend/CLAUDE.md
#	offline-backend-20260512/backend/README.md
#	offline-backend-20260512/backend/app/gateway/app.py
#	offline-backend-20260512/backend/app/gateway/deps.py
#	offline-backend-20260512/backend/app/gateway/routers/llmwiki.py
2026-08-24 14:21:19 +08:00
吉鑫升 49babb6d25 feat: improve wiki document and artifact views 2026-08-24 14:01:10 +08:00
fengxiangdebaozi b3aa9f4bac Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl 2026-08-24 09:10:20 +08:00
Administrator 3785345353 feat: add local LLMWiki wiki vector index 2026-08-24 00:49:31 +08:00
董宏凯 daaa0eab26 Merge branch 'master-nj' into 'master'
feat: 深度研究支持独立新报告与原文改写,并完善沙箱、模型管理与全文改写

See merge request knowledge-base-bj/deerflow-code!28
2026-08-23 14:30:21 +00:00
董宏凯andCursor 541bc3280f fix: 岗位会商本轮只允许 present_files 一次,避免重复产物卡
弱模型写完报告后仍会再调用一次 present_files,前端会画出两张相同卡片。上限同时覆盖呈现,已呈现则只催收尾。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-23 21:26:57 +08:00
董宏凯andCursor b81d200eca fix: 协助卡停轮与提交防 409,隐藏配置向导会话,并限制岗位会商产物重复写入
澄清中间件改为 ToolMessage + after_model 停轮,前端提交前取消残留 run;系统/向导 thread_type 从对话列表排除;岗位总结席位加 write_file 上限。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-23 20:29:59 +08:00
董宏凯andCursor 51afebb394 feat: 报告结构支持检索方向/来源与智能新增,并修复协助卡停轮与宿主跳转
为深度研究报告结构增加检索方向与技能来源、对话式智能新增页与详情排版;澄清中间件在 after_model 可靠结束本轮,避免弱模型出卡后继续生成;任务按钮补充 host 跳转与相关深链能力。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-22 17:46:06 +08:00
fengxiangdebaozi 1c0e4e9723 Merge branch 'master-nj' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl 2026-08-21 21:48:29 +08:00
董宏凯andCursor a5a9c952e8 feat: 深度研究支持独立新报告与原文改写,并完善沙箱、模型管理与全文改写
新报告不再覆盖当前文件卡片,写入时打开沙箱;步骤条仅在改写原文时位于卡片上方。同时补齐改写本地回退、模型管理与会商第三步相关改动。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-21 21:46:04 +08:00
吉鑫升 4c9f75f31e feat: add fixed questions and improve authentication 2026-08-21 17:58:39 +08:00
fengxiangdebaozi d19d6ced66 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl 2026-08-20 17:05:41 +08:00
董宏凯 7c34e18ad6 Merge branch 'master-nj' into 'master'
fix: 单轮 RAG 步骤条思考内容支持可点击参考序号

See merge request knowledge-base-bj/deerflow-code!27
2026-08-20 09:04:49 +00:00
董宏凯andCursor 11f928bc95 feat: 新增独立企业深度研究工作台,并接入工作流报告结构与 8BF 深色锁定
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-20 16:43:03 +08:00
董宏凯andCursor e881c242fe feat: 岗位职责迁至业务链席位,并支持 WeKnora 嵌入页知识库切换
将岗位职责从智能体配置迁移到业务链席位 JSON,会商面板只读展示;WeKnora 嵌入 iframe 支持在授权可见范围内切换知识库并重新签发会话。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-19 22:26:40 +08:00
fengxiangdebaozi 8e77e2da1e Merge branch 'master-nj' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl 2026-08-19 21:24:58 +08:00
董宏凯andCursor e860357563 fix: 单轮 RAG 步骤条思考内容支持可点击参考序号
把思考区的 `[n]` 按正文同一套引用规则渲染,并去掉回答气泡里重复的 Thought for a few seconds。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-19 21:21:22 +08:00
fengxiangdebaozi bc49ef6027 merge: integrate master-nj RAG updates 2026-08-19 20:46:37 +08:00
fengxiangdebaozi 288ba64923 代码提交 2026-08-19 20:39:06 +08:00
董宏凯 c69fde22bd Merge branch 'master-nj' into 'master'
feat: 支持会商 Markdown 产物提交到任务过程,并补充 Angular 对接文档

See merge request knowledge-base-bj/deerflow-code!26
2026-08-19 12:38:26 +00:00
董宏凯andCursor 0ce060693b feat: 会商链条启停与深度研究报告结构,并完善问答展示与 8BF 返回。
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-19 20:37:34 +08:00
fengxiangdebaozi db5b6ba574 fix(rag): restore single-round source streaming 2026-08-19 20:29:00 +08:00
董宏凯 be4851555d 代码提交 2026-08-19 17:11:36 +08:00
董宏凯andCursor 3afa76894f feat: 完善会商产物提交匹配与流式写文件预览
席位流程图按已提交 Markdown 对齐;流式未命名产物不再误请求 artifacts API,并兼容临时文件名路径。同时补强会话流中断识别与 8BF/岗位会商展示。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-19 17:08:52 +08:00
董宏凯andCursor acf538ac01 feat: 简介模式菜单按类型 A/B 分套,兼容未配置的旧部署
两套网页可通过 runtime-config.js 的 VITE_COMPACT_MENU_TYPE 加载各自左侧菜单;缺省或旧页面不传参数时仍读取原来的类型 A 数据。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-19 16:59:34 +08:00
董宏凯andCursor 5e1765d889 feat: 完善 8BF 会商第一步产物与智能体列表,第二步对话区对齐第一步样式
抽出共用分析成果卡片,第一步展示第二、三步 Markdown 产物;智能体列表对齐岗位会商选择样式。第二步对话面板改为深蓝顶栏,第一步保留可配置返回按钮。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-19 12:12:35 +08:00
董宏凯andCursor 30799f17be fix: 节流会商流式写文件预览,避免 Maximum update depth
write_file 的 content 在每个 SSE chunk 中持续增长,原先会反复触发 React 状态更新并打断整页;现改为按身份入参去重、节流发布 stub,并收口第 3 步为 Markdown 报告工作台。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-18 23:23:46 +08:00
董宏凯andCursor dcfaa199bf feat: 支持会商 Markdown 产物提交到任务过程,并补充 Angular 对接文档
8BF/会商工作区可将 Markdown 产物一键提交到任务过程报告,后端记录提交状态以便跨用户与刷新后保持已提交;同时为 Angular 智能体对话对接文档补上前后端参考代码索引。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-18 20:08:51 +08:00
fengxiangdebaozi 1f961ee1df fix: bundle workspace branding assets 2026-08-18 19:43:35 +08:00
董宏凯 33b0af333c Merge branch 'master-nj' into 'master'
增强 Deep Research 可靠性,并接入 8BF 任务卡片与会商上下文。

See merge request knowledge-base-bj/deerflow-code!25
2026-08-18 09:55:17 +00:00
董宏凯 172250e6b5 代码提交 2026-08-18 17:54:07 +08:00
董宏凯andCursor 15a46b903a 增强文档改写配图与深度研究流式稳定性,并完善 8BF/会商工作区。
全文改写支持可选配图与思考过程展示,深度研究接入 DashScope 原生出图并剥离内联 think 标签;8BF 会商补齐第一步工作区与任务卡回退,同时限制热重载扫描范围。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-18 17:46:11 +08:00
fengxiangdebaozi 6ff04ea4e3 fix: restore skill list styling 2026-08-18 16:50:27 +08:00
fengxiangdebaozi 0f667261be Merge branch 'master-zl' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl
# Conflicts:
#	frontend-web/src/components/workspace/skill-display-sources.tsx
2026-08-18 16:43:48 +08:00
fengxiangdebaozi e412d7db3f 代码合并 2026-08-18 16:39:56 +08:00
吉鑫升 6de3026f8f fix: adapt WeKnora source preview on master-zl 2026-08-18 15:48:58 +08:00
吉鑫升 64067ea478 Merge branch 'ji' into master-zl 2026-08-18 15:38:17 +08:00
吉鑫升 8af4fed89d feat: update knowledge workspace and menu configuration 2026-08-18 15:23:14 +08:00
fengxiangdebaozi e0b6e1cd19 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-zl
# Conflicts:
#	frontend-web/src/App.tsx
#	frontend-web/src/components/workspace/agents/agent-detail-panel.tsx
#	frontend-web/src/components/workspace/agents/agent-gallery.tsx
#	frontend-web/src/components/workspace/appearance-controls.tsx
#	frontend-web/src/components/workspace/compact-welcome.tsx
#	frontend-web/src/components/workspace/input-box.tsx
#	frontend-web/src/components/workspace/settings/appearance-settings-page.tsx
#	frontend-web/src/components/workspace/settings/skill-settings-page.tsx
#	frontend-web/src/components/workspace/skill-display-sources.tsx
#	frontend-web/src/components/workspace/workspace-sidebar.tsx
#	frontend-web/src/contexts/ThemeContext.tsx
#	frontend-web/src/core/embed/embed-session.ts
#	frontend-web/src/core/i18n/locales/en-US.ts
#	frontend-web/src/core/i18n/locales/types.ts
#	frontend-web/src/core/i18n/locales/zh-CN.ts
#	frontend-web/src/core/system-settings/api.ts
#	frontend-web/src/env.ts
#	frontend-web/src/pages/ChatPage.tsx
#	frontend-web/src/pages/LightAppIframeView.tsx
#	frontend-web/src/pages/LightAppListPage.tsx
#	frontend-web/src/pages/LightAppNoteQAPage.tsx
#	frontend-web/src/pages/NotebookAIWritingPage.tsx
#	frontend-web/src/pages/PageRoutes.tsx
#	frontend-web/src/pages/WorkspaceRoutes.tsx
#	frontend-web/src/pages/light-app-management.css
#	frontend-web/src/pages/light-app-pages.css
#	frontend-web/src/strategy-components/lib/light-app.ts
#	frontend-web/src/styles/globals.css
#	offline-backend-20260512/backend/CLAUDE.md
#	offline-backend-20260512/backend/README.md
#	offline-backend-20260512/backend/app/gateway/routers/system_settings.py
#	offline-backend-20260512/backend/packages/harness/deerflow/config/system_settings.py
2026-08-18 10:06:34 +08:00
Administrator 64a5305bbf feat: add markdown word editor for knowledge workspace 2026-08-18 00:44:29 +08:00
董宏凯 819e537aa3 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-nj 2026-08-17 19:30:37 +08:00
吉鑫升 68c4896088 fix: stabilize auth sync and stream recovery for ji 2026-08-17 19:27:39 +08:00
董宏凯andCursor 771957429a 增强 Deep Research 可靠性,并接入 8BF 任务卡片与会商上下文。
修复 MySQL 读写分离下的持久化与 SSE 重连问题,报告完成前先落库;8BF 嵌入页支持 taskId 任务卡与独立意图 metadata;前端统一 createClientId 并更新 runtime 配置。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-17 18:16:05 +08:00
吉鑫升 5bf08c83a6 Merge remote-tracking branch 'origin/master' into ji 2026-08-17 15:53:36 +08:00
吉鑫升 3ab2c9b282 feat: improve WeKnora source preview and wiki management 2026-08-17 15:53:19 +08:00
吉鑫升 94cf37a2ae fix: normalize system messages before model calls 2026-08-17 10:12:43 +08:00
董宏凯 47faa9bcdf 代码提交 2026-08-16 21:48:38 +08:00
董宏凯 5901246030 Merge branch 'master-nj' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-nj 2026-08-16 20:43:43 +08:00
董宏凯 44e0b7596b Merge branch 'master-baogao' into 'master'
Master baogao

See merge request knowledge-base-bj/deerflow-code!24
2026-08-16 11:21:33 +00:00
董宏凯 178572bc7f 代码提交 2026-08-16 19:17:45 +08:00
董宏凯 70da7c5649 代码提交 2026-08-15 12:51:58 +08:00
fengxiangdebaozi 5c586652af daimhebing1 2026-08-14 21:25:29 +08:00
fengxiangdebaozi 067f602732 代码提交 2026-08-14 19:31:15 +08:00
董宏凯 96bfdacee5 Merge branch 'master-nj' into 'master'
Master nj

See merge request knowledge-base-bj/deerflow-code!23
2026-08-14 05:01:17 +00:00
董宏凯 500dab29ab Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-nj 2026-08-14 12:57:04 +08:00
董宏凯 4d688ddbd8 代码提交 2026-08-14 12:56:55 +08:00
Administrator 8193cc53d5 fix: stabilize embedded WeKnora detail page 2026-08-14 11:32:33 +08:00
Administrator a28ad2140e fix: stabilize embedded WeKnora detail page 2026-08-14 11:29:58 +08:00
董宏凯 7b37415604 Merge branch 'master-nj' into 'master'
feat: 岗位会商命令幂等与圆桌后台作业租约调度

See merge request knowledge-base-bj/deerflow-code!22
2026-08-14 03:17:53 +00:00
董宏凯 c4d244881f Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-nj 2026-08-14 11:15:37 +08:00
董宏凯andCursor 75963c9ad9 feat: 岗位会商命令幂等与圆桌后台作业租约调度
岗位会商写操作引入 command_id 幂等与版本锁,前端支持同键重试;圆桌后台作业改为 DB 租约 dispatcher、去重与草稿 outbox 补偿,并持久化 intent turns。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-14 11:08:12 +08:00
Administrator 11e54550ed fix: harden WeKnora proxy and configurable search 2026-08-13 23:44:47 +08:00
fengxiangdebaozi 4f536d9b39 feat(frontend): add workspace single and multi round rag 2026-08-13 21:05:31 +08:00
Administrator b527bc94bb fix: stabilize WeKnora embed session cookie 2026-08-13 20:42:24 +08:00
Administrator 54fd0e7316 fix: route WeKnora embed through backend prefix 2026-08-13 20:22:50 +08:00
Administrator 6dbaf40f99 fix: preserve WeKnora embed proxy prefix 2026-08-13 19:17:01 +08:00
Administrator 3aeb6ac5ce fix: authenticate WeKnora API client 2026-08-13 17:41:30 +08:00
董宏凯 5a4881053d Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-nj 2026-08-13 16:44:47 +08:00
董宏凯 cebc44ff82 代码提交 2026-08-13 16:43:31 +08:00
Administrator 56044d9cb7 fix: improve llmwiki search integration 2026-08-13 16:03:08 +08:00
吉鑫升 4809ee7db3 fix: update offline backend llmwiki support 2026-08-13 11:17:11 +08:00
Administrator a4a1e73b8e chore: configure VS Code launch tasks 2026-08-13 10:36:06 +08:00
Administrator 5123b7bdd7 chore: configure WeKnora admin password 2026-08-13 10:29:08 +08:00
Administrator e189349eeb fix: sync llmwiki embed theme 2026-08-13 10:25:49 +08:00
董宏凯 f2e81d8875 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-nj 2026-08-12 16:00:35 +08:00
董宏凯 e5e0f3a7c3 代码提交 2026-08-12 16:00:26 +08:00
吉鑫升 c4fd9dd7da Merge remote-tracking branch 'origin/master' into ji
# Conflicts:
#	.gitignore
#	frontend-web/src/components/workspace/input-box.tsx
#	frontend-web/src/core/threads/types.ts
#	frontend-web/src/pages/ChatPage.tsx
2026-08-12 15:55:51 +08:00
吉鑫升 b4d076a2d4 fix: harden WeKnora knowledge permissions and details 2026-08-12 15:45:28 +08:00
董宏凯 bc82072710 Merge branch 'master-nj' into 'master'
feat: 管理员可删除内置技能并管理技能内文件

See merge request knowledge-base-bj/deerflow-code!21
2026-08-12 07:08:19 +00:00
董宏凯andCursor bf023d746a feat: 管理员可删除内置技能并管理技能内文件
新增内置技能删除与技能文件删除 API,允许管理员编辑/删除内置技能文件;技能设置页与文件预览弹窗同步支持删除操作。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-12 15:05:29 +08:00
董宏凯 fb5024ea82 Merge branch 'master-nj' into 'master'
feat: 模型配置支持删除,岗位行动规划对接任务系统字典与批量新增 Skill

See merge request knowledge-base-bj/deerflow-code!20
2026-08-12 06:48:24 +00:00
董宏凯andCursor c9c2dc7ea8 feat: 模型配置支持删除,岗位行动规划对接任务系统字典与批量新增 Skill
模型管理新增 DELETE 接口与前端删除能力(支持含斜杠的模型名);行动规划改为 9 字段 JSON,prepare 传入 taskId/字典并绑定 position-roundtable-action-create Skill。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-12 14:47:14 +08:00
董宏凯 2a869f4ff6 Merge branch 'master-nj' into 'master'
feat: 添加管理员模型配置页面与 config.yaml 模型管理 API

See merge request knowledge-base-bj/deerflow-code!19
2026-08-12 06:44:18 +00:00
fengxiangdebaozi af509eb670 Merge branch 'master-nj' of http://192.168.0.200/knowledge-base-bj/deerflow-code into master-nj 2026-08-12 14:32:57 +08:00
fengxiangdebaozi 783e698b6e 代码提交 2026-08-12 14:32:47 +08:00
董宏凯andCursor ba912acf72 feat: 添加管理员模型配置页面与 config.yaml 模型管理 API
新增 /api/admin/models 路由(读写 config.yaml models 段、连接测试、写前备份),以及工作区「模型配置」管理页与侧栏入口。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-11 21:45:56 +08:00
吉鑫升 e0c09f6704 feat: integrate WeKnora llmwiki knowledge flow 2026-08-11 18:13:30 +08:00
董宏凯 17a12bb7b6 Merge branch 'master-nj' into 'master'
feat: 岗位会商独立意图智能体与四项意图 schema

See merge request knowledge-base-bj/deerflow-code!18
2026-08-11 05:00:55 +00:00
董宏凯andCursor f8757d1a43 feat: 岗位会商独立意图智能体与四项意图 schema
岗位会商 Step 1 改用 position-roundtable-intent 智能体,输出 coreGoals/riskWarnings/keyPoints/strategicSignificance 四项数组;支持单轮多张协助卡、按轮次计澄清上限,并兼容旧会话 objective/constraints 映射。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-11 13:00:16 +08:00
董宏凯 69b95f0d6d Merge branch 'master-nj' into 'master'
feat(frontend): 岗位会商页面布局与意图理解交互优化

See merge request knowledge-base-bj/deerflow-code!17
2026-08-11 04:59:37 +00:00
董宏凯 ca32a22c0d 代码提交 2026-08-10 15:11:47 +08:00
董宏凯 3eb307c5c5 代码提交 2026-08-10 14:26:49 +08:00
董宏凯 49af497085 代码修改 2026-08-05 21:15:36 +08:00
董宏凯andCursor 8b732b43ee fix(frontend): 同路径二次 write_file 时重挂岗位会商沙箱
按 tool-call 身份区分预览,避免同路径重写复用旧 previewKey 导致沙箱不刷新。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-04 00:54:15 +08:00
董宏凯andCursor 69e455274a fix(frontend): 岗位会商沙箱在 write_file 流式阶段实时打开并刷新
content 先于 path 到达时用临时文件名开沙箱,流式快照改走外部 store 避免整页重渲染卡顿。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-04 00:51:38 +08:00
董宏凯andCursor e939dc4548 feat(frontend): 岗位会商页面布局与意图理解交互优化
完善 PositionRoundtable 样式与输入组件,补充 SVG 资源,并同步 Step1 意图相关逻辑。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-02 21:52:54 +08:00
董宏凯 1ffead7ee2 岗位会商样式修改 2026-08-02 15:33:26 +08:00
董宏凯 a0a75a9964 Merge branch 'dhk-1' into 'master'
fix: avoid MySQL thread_meta refresh races and harden roundtable bootstrap

See merge request knowledge-base-bj/deerflow-code!16
2026-07-31 13:11:29 +00:00
董宏凯 37964d1f95 代码修改 2026-07-31 21:09:54 +08:00
董宏凯andCursor a9d66536c3 fix: avoid MySQL thread_meta refresh races and harden roundtable bootstrap
Skip post-commit ORM refresh on threads_meta creates so concurrent MySQL
read/write-split deployments no longer fail with Could not refresh instance;
clean up partial roundtable threads on checkpoint failure, and ship related
position-roundtable/frontend build fixes.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-31 21:00:56 +08:00
董宏凯 a968c3b5cd Merge branch 'dhk-1' into 'master'
代码修改

See merge request knowledge-base-bj/deerflow-code!15
2026-07-29 14:27:46 +00:00
董宏凯 e52261fc3d fix: preserve full chat embed mode navigation 2026-07-29 22:25:42 +08:00
董宏凯 4450f342d8 页面嵌套修改 2026-07-29 21:53:32 +08:00
董宏凯 213dd841b5 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into dhk-1 2026-07-28 19:18:52 +08:00
董宏凯 816c46d447 代码提交 2026-07-28 19:17:40 +08:00
g zy db857ddd4d Merge branch 'gzy_dev_new' into 'master'
fix: fix iframe agent selector width

See merge request knowledge-base-bj/deerflow-code!14
2026-07-28 03:30:12 +00:00
Rocky Kwok 9be0c6555f fix: fix iframe agent selector width 2026-07-28 11:27:47 +08:00
g zy e475c37f1d Merge branch 'gzy_dev_new' into 'master'
Gzy dev new

See merge request knowledge-base-bj/deerflow-code!13
2026-07-28 03:14:47 +00:00
Rocky Kwok d86c9d48a6 fix: remove iframe general chat entry 2026-07-28 11:12:00 +08:00
Rocky Kwok 008c9ede6e fix: preserve iframe plugin chat mode 2026-07-28 11:03:28 +08:00
董宏凯 151ecceb85 feat: 更新主题配置与系统设置 2026-07-27 21:31:09 +08:00
董宏凯 1555d5344b feat: 优化8BF业务链流程图与深色配置弹窗 2026-07-27 21:30:57 +08:00
董宏凯 bd8ec41914 Merge branch 'dhk-1' into 'master'
Dhk 1

See merge request knowledge-base-bj/deerflow-code!12
2026-07-27 11:25:40 +00:00
董宏凯 1e21e559fb merge: 合并远端 dhk-1 最新改动 2026-07-27 19:22:59 +08:00
董宏凯 e496221dc3 Merge remote-tracking branch 'origin/master' into HEAD 2026-07-27 19:19:01 +08:00
董宏凯 5bf3955b26 代码提交 2026-07-27 19:16:12 +08:00
董宏凯 1ab3329f6d feat: 新增8BF多智能体会商页面 2026-07-27 19:00:14 +08:00
董宏凯 e70bb4aa6f feat: 新增8BF多智能体会商页面 2026-07-27 18:59:42 +08:00
g zy b22d0200c3 Merge branch 'gzy_dev_new' into 'master'
fix(frontend): preserve iframe theme across login

See merge request knowledge-base-bj/deerflow-code!11
2026-07-27 02:16:32 +00:00
Rocky Kwok fb73ae0471 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into gzy_dev_new 2026-07-27 10:06:33 +08:00
Rocky Kwok 75aad4eef6 fix(frontend): preserve iframe theme across login
The iframe login used a fixed queryless redirect and called setTheme, which both dropped the iframe theme and persisted it into the normal site's shared theme storage.
2026-07-27 09:54:22 +08:00
董宏凯 cec2996861 Merge branch 'dhk-1' into 'master'
feat(沙箱): md 产物支持 AI 写作编辑与划词改写

See merge request knowledge-base-bj/deerflow-code!9
2026-07-26 13:20:20 +00:00
fengxiangdebaozi 239b798c5d Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into dhk-1
# Conflicts:
#	frontend-web/src/components/workspace/workspace-nav-menu.tsx
#	offline-backend-20260512/backend/app/gateway/routers/multi_agent.py
2026-07-26 20:55:50 +08:00
董宏凯 f1e53ef5c0 功能:完善自定义主题与独立登录会话 2026-07-26 18:19:50 +08:00
g zy a368037e81 Merge branch 'gzy_dev_new' into 'master'
fix:iframe切换颜色

See merge request knowledge-base-bj/deerflow-code!8
2026-07-26 09:10:27 +00:00
Rocky Kwok 59f2f56124 fix:iframe切换颜色 2026-07-26 17:01:09 +08:00
董宏凯 3779bb69ef fix: load model keys from environment 2026-07-26 13:08:09 +08:00
董宏凯 25153dbd84 代码修改 2026-07-24 14:12:42 +08:00
董宏凯 91ba47bf47 代码提交 2026-07-24 11:24:11 +08:00
董宏凯 28bf1ac7b2 Merge branch 'dhk-1' of http://192.168.0.200/knowledge-base-bj/deerflow-code into dhk-1
# Conflicts:
#	frontend-web/src/position-roundtable/components/PositionBuiltinAgentChat.tsx
#	frontend-web/src/position-roundtable/components/PositionNodeChat.tsx
2026-07-24 10:41:38 +08:00
董宏凯 45df500a9c 代码提交 2026-07-24 10:33:28 +08:00
fengxiangdebaozi f32de510fe 代码泰囧 2026-07-23 16:27:35 +08:00
fengxiangdebaozi 21722b9f5a 代码提交 2026-07-23 16:03:34 +08:00
董宏凯 f49def09ea 代码修改 2026-07-23 16:00:39 +08:00
董宏凯 4948a80c56 代码提交 2026-07-23 15:53:43 +08:00
董宏凯 7d249a81ce Merge branch 'dhk-1' of http://192.168.0.200/knowledge-base-bj/deerflow-code into dhk-1
# Conflicts:
#	frontend-web/src/position-roundtable/components/PositionBuiltinAgentChat.tsx
#	frontend-web/src/position-roundtable/components/PositionNodeChat.tsx
2026-07-23 15:11:43 +08:00
董宏凯 1d07025f74 代码修改 2026-07-23 15:08:00 +08:00
fengxiangdebaozi 91c5d43c48 代码提交 2026-07-23 15:07:23 +08:00
董宏凯 b60d9ed09e 代码修改 2026-07-23 14:29:12 +08:00
董宏凯 56740ecf56 Merge branch 'dhk-1' of http://192.168.0.200/knowledge-base-bj/deerflow-code into dhk-1 2026-07-23 12:38:52 +08:00
董宏凯 9f788e37de 样式修改 2026-07-23 12:38:48 +08:00
fengxiangdebaozi 0634337858 feat: 支持登录隐藏壳层和路由跳转参数 2026-07-23 11:16:11 +08:00
董宏凯 08ce3dda73 merge: integrate dhk-dev into dhk-1 2026-07-23 10:38:48 +08:00
董宏凯 c8f69781e4 样式修改 2026-07-23 10:10:47 +08:00
董宏凯 13bfa719ee feat: refine position roundtable workflow 2026-07-22 22:22:38 +08:00
董宏凯 359bd28f2c fix: polish position roundtable artifact preview 2026-07-22 18:41:46 +08:00
fengxiangdebaozi 7bd032ec77 feat: 支持岗位会商任务和意图编辑 2026-07-22 17:44:34 +08:00
董宏凯 790267ac43 Merge branch 'dhk-1' of http://192.168.0.200/knowledge-base-bj/deerflow-code into dhk-1
# Conflicts:
#	frontend-web/src/position-roundtable/pages/PositionRoundtablePage.tsx
2026-07-22 17:02:07 +08:00
董宏凯 d9844e0180 打开沙箱错误修改 2026-07-22 16:53:56 +08:00
fengxiangdebaozi 6ade3b69b9 feat: refine position roundtable workflow 2026-07-22 16:53:10 +08:00
董宏凯 ae184f434d Merge branch 'dhk-1' of http://192.168.0.200/knowledge-base-bj/deerflow-code into dhk-1 2026-07-22 15:43:13 +08:00
董宏凯 055523bf33 代码修改 2026-07-22 15:43:06 +08:00
fengxiangdebaozi 866bc0f8d8 样式修改 2026-07-22 15:42:29 +08:00
fengxiangdebaozi 1bc203b5cd 岗位会商 2026-07-22 15:40:00 +08:00
董宏凯 e2041c0b07 feat(frontend): add theme variants and compact navigation config 2026-07-22 14:55:42 +08:00
fengxiangdebaozi 1cd99a5a90 feat(position-roundtable): add delivery rejection workflow 2026-07-21 20:16:52 +08:00
fengxiangdebaozi 2ca8a23102 feat(position-roundtable): add delivery workflow scaffolding 2026-07-21 19:48:39 +08:00
fengxiangdebaozi 97ce19973d docs(position-roundtable): plan delivery workflow 2026-07-21 19:31:08 +08:00
fengxiangdebaozi 783774d3f3 fix(position-roundtable): align header controls 2026-07-21 19:30:55 +08:00
fengxiangdebaozi 85e119db08 feat(position-roundtable): add standalone position collaboration 2026-07-21 17:50:24 +08:00
吉鑫升 5436719bfb Merge branch 'master-dev' into 'master' 2026-07-21 14:47:46 +08:00
吉鑫升 e571caaf2c fix: keep offline start script minimal 2026-07-21 14:46:58 +08:00
吉鑫升 5d2997b6a0 fix: preserve offline deployment LF files 2026-07-21 14:39:57 +08:00
吉鑫升 f8cb7be18c chore: add offline backend wheelhouse deployment 2026-07-21 14:35:06 +08:00
董宏凯 b93b82fcaf Merge branch 'dhk-1' of http://192.168.0.200/knowledge-base-bj/deerflow-code into dhk-1 2026-07-21 11:00:19 +08:00
董宏凯 d0b4832ed7 代码提交 2026-07-21 10:58:56 +08:00
fengxiangdebaozi 4ffd5a3c94 feat(frontend): add position roundtable workspace 2026-07-20 20:41:37 +08:00
董宏凯 2d6992d656 feat(frontend): adapt TDesign themes 2026-07-20 20:10:22 +08:00
董宏凯 2fa7000ff7 feat(workspace): add red theme assets and adapt workspace styles 2026-07-19 17:30:38 +08:00
董宏凯 bb7291a97c Merge branch 'dhk-1' into 'master'
feat: 支持深色主题顶栏 Logo 位置配置

See merge request knowledge-base-bj/deerflow-code!5
2026-07-17 13:08:45 +00:00
fengxiangdebaozi a699545c4c feat: 支持深色主题顶栏 Logo 位置配置 2026-07-17 21:07:48 +08:00
董宏凯 2c331aa744 Merge branch 'dhk-1' into 'master'
Dhk 1

See merge request knowledge-base-bj/deerflow-code!4
2026-07-16 14:45:42 +00:00
fengxiangdebaozi 82dd9fb08f feat: 支持主题系统Logo与欢迎页开关 2026-07-16 22:31:22 +08:00
fengxiangdebaozi b97aa77adc fix: 会商界面适配字号设置 2026-07-16 16:26:43 +08:00
fengxiangdebaozi d7d101814f fix: 修复深色导航与会商悬浮样式 2026-07-16 11:21:52 +08:00
董宏凯 871d98e6f2 Merge branch 'dhk-1' into 'master'
Dhk 1

See merge request knowledge-base-bj/deerflow-code!3
2026-07-16 01:57:37 +00:00
fengxiangdebaozi 3cd093a8a2 地址修改 2026-07-16 09:56:54 +08:00
fengxiangdebaozi 4a59da7ff0 fix: 优化侧栏并接入品牌脱敏 2026-07-16 09:48:40 +08:00
董宏凯 760b88d6f1 feat: refresh workspace UI and agent visuals 2026-07-16 00:06:40 +08:00
董宏凯 d7ad0624b7 代码提交 2026-07-15 16:13:03 +08:00
董宏凯 27e6b0b23e Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-code into dhk-dev
# Conflicts:
#	frontend-web/src/open-canvas/components/ai-writing/AIWritingForm.tsx
2026-07-11 19:01:10 +08:00
董宏凯 55b5c2cc9f 代码部署说明 2026-07-11 18:58:16 +08:00
董宏凯 d5d5199f6d Merge branch 'dhk-1' into 'master'
代码合并

See merge request knowledge-base-bj/deerflow-code!2
2026-07-11 10:16:38 +00:00
fengxiangdebaozi 0bd0ac41cd 代码合并 2026-07-11 18:16:08 +08:00
董宏凯 b1c396717b Merge branch 'dhk-1' into 'master'
feat(message-token-usage): 速度条下方常驻颜色含义图例

See merge request knowledge-base-bj/deerflow-code!1
2026-07-11 10:12:52 +00:00
fengxiangdebaozi 388a9133fc fix: adapt frontend for legacy Chrome and runtime config 2026-07-11 16:55:08 +08:00
董宏凯 221e947488 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-dev
# Conflicts:
#	frontend-web/src/open-canvas/components/ai-writing/AIWritingForm.tsx
#	frontend-web/src/open-canvas/components/ai-writing/AIWritingPanel.tsx
#	offline-backend-20260512/backend/CLAUDE.md
#	offline-backend-20260512/backend/app/gateway/services.py
#	offline-backend-20260512/backend/tests/test_ai_writing_knowledge_base.py
2026-07-03 22:28:21 +08:00
董宏凯 a1c63a1fe5 代码提交 2026-07-03 22:11:50 +08:00
吉鑫升 db2f21191c fix(frontend): handle clipboard fallback and markdown word export 2026-07-03 16:54:16 +08:00
董宏凯 195ef3ee40 Merge branch 'dhk-1' into 'master'
Dhk 1

See merge request knowledge-base-bj/deerflow-server!169
2026-07-03 08:37:06 +00:00
fengxiangdebaozi f3511e5cd0 样式修改 2026-07-03 16:35:52 +08:00
fengxiangdebaozi 96947d7636 Merge branch 'dhk-1' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-07-03 14:56:49 +08:00
fengxiangdebaozi 034a379ecd 技能提交 2026-07-03 14:56:35 +08:00
董宏凯 da856f2b58 fix: improve ai writing chat streaming and intent handling 2026-07-02 17:43:23 +08:00
董宏凯 845c87e3ee feat: add AI writing chat workspace 2026-07-02 13:56:46 +08:00
董宏凯 7d9c0894f8 fix: limit roundtable chain rail height 2026-07-02 11:17:52 +08:00
吉鑫升 ae30a20739 Merge remote-tracking branch 'origin/master' into ji 2026-07-02 11:15:06 +08:00
吉鑫升 7e7d3c9846 fix: truncate rwfx 3q context 2026-07-02 11:05:12 +08:00
吉鑫升 daff70c34f fix: include rwfx 3q status in context 2026-07-02 10:43:16 +08:00
董宏凯 94188db9ea Merge branch 'dhk-1' into 'master'
Dhk 1

See merge request knowledge-base-bj/deerflow-server!168
2026-07-02 02:15:43 +00:00
董宏凯 b12497898a fix: polish roundtable chain rail toggle 2026-07-02 10:14:40 +08:00
董宏凯 3e51208024 feat: add roundtable chain rail scroll 2026-07-02 10:06:24 +08:00
吉鑫升 36a3851233 feat: inject 3q context into rwfx chat 2026-07-02 10:03:34 +08:00
董宏凯 54190d7a83 提交代码 2026-07-01 19:24:23 +08:00
fengxiangdebaozi 2215ec3c49 feat: add user-assisted xdfx skill flow 2026-07-01 19:21:18 +08:00
董宏凯 d21dbeb214 feat: refine ai writing search flow 2026-07-01 18:00:14 +08:00
董宏凯 ba0c32dcee Merge branch 'dhk-1' into 'master'
代码修改

See merge request knowledge-base-bj/deerflow-server!167
2026-07-01 09:51:15 +00:00
fengxiangdebaozi f5efe9b041 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-07-01 17:50:33 +08:00
fengxiangdebaozi a4a44e1154 Merge branch 'dhk-1' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-07-01 17:50:06 +08:00
fengxiangdebaozi cef08638af 技能修改 2026-07-01 17:49:51 +08:00
董宏凯 025e43f4c5 feat: improve ai writing imitation flow 2026-07-01 17:16:12 +08:00
董宏凯 fa04ab8b5a fix: filter position-granted agent favorites 2026-07-01 14:51:14 +08:00
董宏凯 f3e5a3bb35 fix: prevent notebook writing redirect to agent chat 2026-07-01 14:48:40 +08:00
董宏凯 0547fb1715 提交 2026-07-01 11:22:26 +08:00
董宏凯 bb6b9bd84b feat: add ai writing imitation mode 2026-07-01 11:21:41 +08:00
g zy f485d4fff3 Merge branch 'gzy' into 'master-dev'
fix: 注释插件管理

See merge request knowledge-base-bj/deerflow-server!166
2026-07-01 02:25:19 +00:00
董宏凯 4bfaeb728b fix: disable ssl verification for intranet ai writing search 2026-07-01 10:21:52 +08:00
Rocky Kwok 2b0ba2a68b fix: 注释插件管理 2026-07-01 10:08:46 +08:00
董宏凯 c8cdd1d0b2 Merge branch 'dhk-1' into 'master'
统一外部 access_token 存储与轻应用 URL 拼接,修复嵌入会话鉴权隔离。

See merge request knowledge-base-bj/deerflow-server!165
2026-06-30 11:21:42 +00:00
董宏凯 8fbfd35296 Add scheduled HTML templates no19-no27 2026-06-30 19:18:48 +08:00
董宏凯 dfb745a5e4 代码提交 2026-06-30 16:04:51 +08:00
吉鑫升 c23350f17b fix: isolate user concurrency from internal agent runs 2026-06-30 14:56:29 +08:00
吉鑫升 124eb04a6b Merge remote-tracking branch 'origin/master-dev' into ji-dev 2026-06-30 11:34:45 +08:00
吉鑫升 b4206d6421 Add Redis-backed concurrency gate 2026-06-30 11:25:44 +08:00
董宏凯andCursor 537e2e4d06 fix(登录): token 登录补全 userInfo + 全方式打印路由参数
- 把「拉外部用户信息(yUserId→consumer)」与登录鉴权方式解耦:只要 URL 带
  yUserId 就填充 userInfo(含 token 登录,consumer 失败非致命),修复 token
  登录后 userInfo 残缺、iframe/轻应用拿不到 yUserId/userName/gateDepartName/
  typeName/accessToken 的问题。
- token 登录用 auth.username 写入正确用户名(不覆盖 consumer 已落的 userName)。
- 保留 yUserId 优先级(onlineTicket/toolToken 仅在无 yUserId 时启用)。
- 新增登录路由参数 + 落地结果日志(令牌脱敏),方便排查各登录方式取值问题。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-29 23:36:33 +08:00
董宏凯andCursor 9268c73776 feat(沙箱): md 产物支持 AI 写作编辑与划词改写
- 新增 MarkdownAiEditor,复用 AI 写作的 TipTap 编辑器与 AI 改写流程

- 沙箱 md 增加 AI 写作视图切换,默认仍为预览;单文件隐藏文件名避免工具栏错位

- 单智能体聊天页开启 allowVirtualMarkdownEdit,生成完成后可编辑

- 会商总结页续看时自动收起研讨原料侧栏

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-29 23:08:55 +08:00
fengxiangdebaozi 6378cd33bd 统一外部 access_token 存储与轻应用 URL 拼接,修复嵌入会话鉴权隔离。
将 access_token 纳入 scoped storage 迁移,yUserId 登录优先并独立持久化 token;轻应用/按钮管理默认改用 access_token 参数名,支持 hash 路由占位符替换与自动追加。
2026-06-29 23:00:31 +08:00
fengxiangdebaozi 8c6d08d6bf Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-29 18:08:37 +08:00
fengxiangdebaozi 29082b349d 技能修改 2026-06-29 18:08:09 +08:00
Administrator 7d8656bfde fix xdfx task start context recovery 2026-06-29 17:45:46 +08:00
fengxiangdebaozi 45ce14e15a Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-29 17:39:52 +08:00
g zy 8947223255 Merge branch 'gzy' into 'master-dev'
fix: iframe底部选择智能体

See merge request knowledge-base-bj/deerflow-server!164
2026-06-29 09:36:11 +00:00
Rocky Kwok 5a420189b1 fix: iframe底部选择智能体 2026-06-29 17:35:36 +08:00
g zy 17650afe96 Merge branch 'revert-f22a6a99' into 'master'
Revert "Merge branch 'revert-d8af6c8f' into 'master'"

See merge request knowledge-base-bj/deerflow-server!163
2026-06-29 09:19:24 +00:00
g zy 80fce34c1a Revert "Merge branch 'revert-d8af6c8f' into 'master'"
This reverts merge request !158
2026-06-29 09:19:17 +00:00
g zy ae31c50424 Merge branch 'gzy' into 'master-dev'
Gzy

See merge request knowledge-base-bj/deerflow-server!162
2026-06-29 09:14:43 +00:00
Rocky Kwok 794aab1007 fix: recode 2026-06-29 17:14:01 +08:00
Rocky Kwok be06cac223 fix: reset code 2026-06-29 17:12:18 +08:00
Administrator b0db8cc3d8 feat: 优化定时任务 Markdown 阅读页 2026-06-29 17:08:38 +08:00
g zy 0dab5a8121 Merge branch 'gzy' into 'master-dev'
fix: chore

See merge request knowledge-base-bj/deerflow-server!161
2026-06-29 09:05:30 +00:00
Rocky Kwok c012146c18 fix: chore 2026-06-29 17:04:50 +08:00
fengxiangdebaozi 6851c96a45 技能提交 2026-06-29 16:59:23 +08:00
g zy f75f4f9db1 Merge branch 'gzy' into 'master-dev'
feat: iframe增加智能体显示

See merge request knowledge-base-bj/deerflow-server!159
2026-06-29 08:47:03 +00:00
g zy f22a6a9957 Merge branch 'revert-d8af6c8f' into 'master'
Revert "Merge branch 'gzy' into 'master'"

See merge request knowledge-base-bj/deerflow-server!158
2026-06-29 08:45:40 +00:00
fengxiangdebaozi 210cb5117f fix: polish compact workspace controls 2026-06-29 16:44:13 +08:00
Administrator 0c663f5f7c Merge remote-tracking branch 'origin/master' into ji-dev 2026-06-29 16:43:45 +08:00
g zy 75e8a90ac7 Revert "Merge branch 'gzy' into 'master'"
This reverts merge request !157
2026-06-29 08:43:19 +00:00
g zy d8af6c8f48 Merge branch 'gzy' into 'master'
feat: iframe增加智能体显示

See merge request knowledge-base-bj/deerflow-server!157
2026-06-29 08:43:11 +00:00
Rocky Kwok 1ab4216ccb feat: iframe增加智能体显示 2026-06-29 16:42:38 +08:00
Administrator d39b58255d 并发版 2026-06-29 16:09:51 +08:00
Administrator cd2ca406a5 Merge branch 'master-dev' into ji-dev 2026-06-29 15:12:24 +08:00
Administrator 637be00946 feat: improve agent skill selection 2026-06-29 15:09:27 +08:00
Administrator 0dd93421c4 feat: enhance public task markdown preview 2026-06-29 14:42:47 +08:00
Administrator e27321cb23 feat: enhance public task markdown preview 2026-06-29 14:40:26 +08:00
g zy 6157b42f5a Merge branch 'gzy' into 'master'
Gzy

See merge request knowledge-base-bj/deerflow-server!156
2026-06-29 06:33:12 +00:00
Rocky Kwok be4b180d92 fix: 智能体对应 2026-06-29 14:31:55 +08:00
Rocky Kwok e9e4c181b9 feat: 插件管理及域名和智能体对应 2026-06-29 14:31:40 +08:00
fengxiangdebaozi eb61b332a2 Add XDFX skill data artifacts 2026-06-29 10:25:36 +08:00
fengxiangdebaozi 4fce6f9104 Add intranet retrieval diagnostics for AI writing 2026-06-29 10:21:10 +08:00
fengxiangdebaozi bcd656fb49 代码提交 2026-06-28 18:50:59 +08:00
Administrator 2d3033434b Fix async thread title generation flow 2026-06-28 18:09:48 +08:00
Administrator d522498cc9 ji 2026-06-28 00:23:01 +08:00
fengxiangdebaozi 65449ffd71 merge dhk-1 yuser login cache 2026-06-27 19:58:57 +08:00
fengxiangdebaozi 006c5bc4c1 fix: cache yuser login info by user id 2026-06-27 19:57:06 +08:00
Administrator a046d19ce1 fix: improve model concurrency limiting 2026-06-27 18:57:01 +08:00
Administrator aca089e8ef feat: add per-model concurrency limits 2026-06-27 18:57:01 +08:00
董宏凯 24eb629773 Merge branch 'dhk-1' into 'master'
feat(ai写作): 历史记录可继续未完成的会话(从checkpoint续跑)

See merge request knowledge-base-bj/deerflow-server!155
2026-06-27 09:31:57 +00:00
fengxiangdebaozi 1847eb9d6a fix(auth): normalize external accessToken and preserve on empty yUser login 2026-06-27 17:29:52 +08:00
董宏凯 44d7304f8e Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-27 16:00:47 +08:00
董宏凯andCursor 5de74e90dc feat(ai写作): 左栏智能体 Tab 内嵌问答并优化模块侧栏
AI 写作页默认展示智能体 Tab,在页内复用 ai-writing 模块配置与 AgentChatPage;确认类型后侧栏扁平展示类型名并支持整块收起动画。同步历史回看、流式续跑、改写菜单与 researcher 检索相关改动。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-27 15:53:51 +08:00
Administrator 6fdca41a1d Merge branch 'ji' into master 2026-06-27 15:13:45 +08:00
Administrator c978a25b7f Fix 3qfx task context fallback 2026-06-27 15:12:28 +08:00
董宏凯andClaude Opus 4.8 c11307aa67 feat(ai写作): 历史记录可继续未完成的会话(从checkpoint续跑)
历史列表里 in_progress/draft_ready/review_ready 记录加绿色▶️「继续未完成」按钮
(点标题亦可);done/error/background 不可继续。多 worker 安全——与4个确认卡同机制,
全基于共享 checkpoint(gateway GET /threads/{id}/state + /history 读,任意 worker)。

链路:continueWriting(sessionId) → closeHistory + 设活跃 sessionId → useStream
fetchStateHistory 拉该 thread checkpoint 进 stream.values → host rehydrate effect
(continueTargetRef 守卫,每 thread 一次)用 buildRehydrateSnapshot 重建已完成阶段;
status=awaiting_* → 显示确认卡等用户操作,否则 submit({command:{}}) 从 checkpoint
续跑当前阶段。重新加回 buildRehydrateSnapshot + rehydrate action。

入口在侧栏 WritingHistoryItem。刷新=重置不受影响(这是显式点击,非自动重连)。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-27 13:12:47 +08:00
吉鑫升 199269712f Merge branch 'ji' into master
账号级登录口令(白名单管理页设明文口令,凭 /login/<用户名>?password= 直登)。
2026-06-27 11:19:58 +08:00
吉鑫升andClaude Opus 4.8 9572b66ecb feat(白名单): 账号级登录口令——管理员设明文口令,用户凭 /login/<用户名>?password= 直登
白名单管理页可给单个账号设明文登录口令(users.login_password,可空):
设置后该账号用户名直登(/login/username)须带匹配 ?password=,且优先于全局共享口令门;
未设口令的账号行为不变。前端登录 URL 已支持透传 ?password=,无需改登录页。

- 后端:UserRow/User 新增 login_password + 仓储映射;/login/username 账号级口令闸门
  (_lookup_user_by_username 仅查不建);新管理员接口 PUT /users/{id}/login-password;
  UserListItem 暴露明文(仅 admin 列表);migration 20260625_04 + 幂等补列 SQL。
- 前端:白名单页新增「登录口令」列(设置/修改/清除 + 复制登录链接);
  core/auth api+hooks 增 setUserLoginPassword/useSetUserLoginPassword(含 Y-Log)。
- 文档:根 + 后端 CLAUDE.md 同步。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-27 11:03:39 +08:00
董宏凯 45315f18d2 Merge branch 'dhk-1' into 'master'
fix(ai写作): 恢复内网直连检索(知识库检索)空地址回退默认端点

See merge request knowledge-base-bj/deerflow-server!154
2026-06-26 16:02:52 +00:00
董宏凯andClaude Opus 4.8 e889cc25cf fix(ai写作): 历史记录 in_progress 不再误显示「进行中」转圈
刷新=重置后,开始过但没跑完的会话 DB status 永远停在 in_progress、且无任何活进程,
历史列表却转圈显示「进行中」,误导用户以为还在运行。改为中性、不转圈的「未完成」
(text-slate-400)。真正在跑的 background(后台挂起,有 executor 驱动)保留「挂起中」转圈。
改 WRITING_STATUS_PILL(侧栏列表) + STATUS_LABELS(下拉)。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-27 00:01:32 +08:00
董宏凯andClaude Opus 4.8 8385d1913a fix(ai写作): 继续从checkpoint续跑(修resume_is_map) + 刷新=重置不重连
后端 worker(runtime/runs/worker.py): 空 command(无 resume/update/goto)不再构造
Command()(会因无挂起 interrupt 抛 'resume_is_map' 未绑定错误),改为 astream(None)
让 Pregel 续跑 checkpoint 里挂起的当前阶段节点。有 resume/update/goto 时(4个干预卡)
仍走 Command,行为不变。前端"继续"发空 command:{} 即从当前阶段续跑、不回 intent。

按用户要求把"断网/刷新自动重连续跑"整套移除(刷新=重置即可):
- 删 sessionStorage 持久化 + reconnectTargetRef + 恢复/持久化 effect + host rehydrate
- 删 buildRehydrateSnapshot/rehydrate action(保留 clear_streaming)
- 提交去掉 onDisconnect:'continue'/streamResumable;reconnectOnMount 改 false
- 卸载不再自动后台挂起;刷新断 SSE 后端默认 cancel 取消 run,页面回 idle

手动暂停/继续保留:暂停=stream.stop(),继续=clear_streaming+空command 从checkpoint续。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 23:44:37 +08:00
董宏凯andClaude Opus 4.8 9f462beec5 fix(ai写作): 继续(暂停后)从checkpoint续跑而非从头重跑意图
根因:resumeWriting 的 stream.submit(undefined) 没带 command。后端 worker
(runtime/runs/worker.py:283) 只有收到 command 才翻成 Command() 让 Pregel 从最近
checkpoint 恢复;不带 command 时按 graph_input 起新一轮=从图入口 intent_parser
重跑,于是"规划大纲/检索素材时暂停后继续又从识别意图开始"。

修复:继续时带空 command:{},走 Command 恢复路径(与4个干预卡续跑同机制),
Pregel 从 checkpoint 续跑当前未完成阶段(已完成阶段不丢),不再重跑 intent。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 23:31:48 +08:00
董宏凯andClaude Opus 4.8 4f0c75e76e feat(ai写作): 暂停/继续 + 断网刷新后自动重连续跑
需求:写作任一活跃阶段(素材搜集/大纲/写作/审核中)断网也能继续。

断网续跑(纯前端,后端无需改):
- 所有 stream.submit 加 onDisconnect:'continue'(断开后端不取消 run,继续跑到
  下一个确认点等待);不开 streamResumable(避免与 rehydrate 重复累积时间线)
- 活跃 sessionId 存 sessionStorage,刷新后渲染期同步恢复 → threadId 首帧即交给
  useStream(reconnectOnMount) 重连该 run
- 重连后用 graph values 快照 buildRehydrateSnapshot 重建 reducer(rehydrate
  action),素材/大纲/草稿/审核/时间线立刻回显;currentPause 由 interrupt effect 设
- 去掉卸载时"自动后台挂起跑完"(会自动替用户确认),改为自然续跑等待;显式后台挂起按钮保留

手动暂停/继续:
- ENABLE_PAUSE_RESUME_UI 开启;暂停=stream.stop()(已完成阶段已落 checkpoint),
  继续=clear_streaming 后从 checkpoint 重新 submit 续跑(重跑当前阶段,已完成不丢)
- 按钮"停止"→"暂停"(Pause 图标)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 23:20:48 +08:00
董宏凯andClaude Opus 4.8 2097587b42 feat(ai写作): 左侧研究栏加历史记录列表(参考会商样式)+侧栏可收起
- ResearchSidebar 底部新增「历史记录」列表,跟随侧栏自然滚动;样式对齐
  多智能体会商 HistoryDropdown(圆角卡片+divide-y+状态药丸+打开/改名/删除)
- 点历史记录在右侧区域显示历史回看,左侧栏保留(showSidebar 含历史态)
- 侧栏顶部加「收起」按钮,收起为细窄展开条(页面承载 sidebarCollapsed)
- 「挂起中」记录点击经 window 事件 ai-writing:show-progress 打开进度流程图弹窗

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 22:54:10 +08:00
董宏凯 53af352ce8 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-26 22:14:31 +08:00
董宏凯andClaude Opus 4.8 0089af94d3 fix(ai写作): 恢复内网直连检索(知识库检索)空地址回退默认端点
knowledge_base 检索类型遇到空 intranet_search_url 会短路报「未配置」、返回 0
素材,导致「内网直连检索不能用」。旧版 get_search_provider(search_provider=
intranet) 在空地址时由 IntranetSearchProvider 回退内置默认内网端点,所以不配
地址也能直连。本次去掉该短路,空地址原样下传由 provider 回退默认端点,恢复旧逻辑。

- researcher.py: knowledge_base 分支无条件构造 IntranetSearchProvider
- test_ai_writing_knowledge_base.py: 空地址用例改为断言回退默认端点仍出素材
- backend CLAUDE.md: 检索类型段说明更新

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 22:13:19 +08:00
吉鑫升 26ab6f663c Merge branch 'ji' into master
完善并发监控图表(整数刻度Y轴 + 图例 + 说明)
2026-06-26 21:23:40 +08:00
吉鑫升andClaude Opus 4.8 bce0abba6e fix(监控): 完善并发监控图表——整数刻度Y轴 + 图例 + 说明
- 修复并发量图左轴出现「0 0 0 1 1」重复刻度:值很小时改用整数刻度(nice
  ticks,0/1/2…无重复),并修正按 axisMax 归一
- 每张图加图例(带当前读数)+ 一句中文说明,讲清每条线含义:
  并发量=峰值(红)/平均(橙);出字速度=平均(蓝)/最慢(紫)
- 修复两张图共用同一个 SVG 渐变 id 导致的颜色串用(改 useId 唯一化)
- 空数据态更友好(虚线占位 + 引导开启采样)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 21:23:08 +08:00
董宏凯 c732fd75e4 Merge branch 'dhk-1' into 'master'
feat(定时任务): 新增 9 个 HTML 模板,下拉补齐为 no.1~no.18(只展示)

See merge request knowledge-base-bj/deerflow-server!153
2026-06-26 12:51:31 +00:00
董宏凯 89232d7521 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-26 20:50:47 +08:00
吉鑫升 9ef8b1990e Merge branch 'ji' into master
实时并发监控 + 真正停止对话 + 409 中文化(管理员排行榜)
2026-06-26 20:40:56 +08:00
吉鑫升andClaude Opus 4.8 26f8010a57 feat(监控): 管理员排行榜实时并发监控 + 真正停止对话 + 409 中文化
- 排行榜页顶部新增「实时并发监控」面板(admin-only):当前并发大模型调用数 +
  调用列表(用户/智能体/类型/已运行时长),每行「停止」+「全部停止」经
  RunManager.cancel 真正中断 LLM 流式调用,减轻大模型压力
- 并发量折线图(峰值/均值,按分钟/小时):新增轻量后台采样器写入新表
  concurrency_samples(create_all 自动建表),可按分/时聚合
- 大模型出字速度折线图(tokens/秒,按分钟/小时):复用 llm_call_metrics 聚合,
  便于定位是模型/供应商慢
- 后台采样可开关、默认关闭(opt-in)、运行时切换免重启、对线上零影响
  (单条极小 INSERT、保留期清理、查询有上限、全程 best-effort)
- 409 中文化:上一轮未结束又发新问题时返回中文提示,前端 onError 友好映射

后端:runtime/runs/manager.py(list_active)、persistence/concurrency(新模块)、
config/system_settings(ConcurrencyMonitorSettings)、gateway/routers/admin_active_runs、
app.py(采样后台任务)、services.py(409)。前端:core/admin/{active-runs,hooks}、
components/workspace/admin/concurrency-monitor、AdminUserLeaderboardPage、threads/hooks。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 20:29:26 +08:00
董宏凯andClaude Opus 4.8 abf97cdc78 feat(大屏绘制): 战情大屏隐藏顶部标题区,只保留导航 Tab
DashboardApp 顶部 Header(标题+副标题+生成时间)在 usingPages 模式下整块隐藏,
dashboard-agent 战情大屏直接从导航 Tab 起;会商 Step3 大屏行为不变。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 14:36:29 +08:00
fengxiangdebaozi 4d10590511 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-26 11:04:19 +08:00
fengxiangdebaoziandClaude Opus 4.8 3d60651491 feat(ai-writing): 检索类型加回「知识库检索」(直连内网 ES 接口)
弱模型常识别不了配置技能(deepseek-chat 等),恢复旧的"不用技能"检索路径
作为独立检索类型 knowledge_base:绕过技能编排,直接调
ai_writing.intranet_search_url 内网知识库 ES 接口(IntranetSearchProvider)
对检索词并发检索;未配地址 → 无素材 + skill_error 告警。

- researcher.py: material_source 归一保留 knowledge_base + 新增直连内网分支
- state.py: material_source 三值注释
- 前端 AIWritingForm/WritingFormContext/types: 下拉新增「知识库检索」
- tests/test_ai_writing_knowledge_base.py: 直连/未配/不编排技能 3 用例
- backend CLAUDE.md: 检索类型段更新为三值

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 10:04:57 +08:00
董宏凯andClaude Opus 4.8 a400989f64 feat(定时任务): 新增 9 个 HTML 模板,下拉补齐为 no.1~no.18(只展示)
- 从 zt-0625 加入 no.8/no.9/no.10/no.11/no.14/no.15/no.16/no.17/no.18
- 新 no.8/no.9 的 id 用 no8b/no9b(no8/no9 已被显示名 no.12/no.13 的模板占用)
- 重排 TEMPLATES 使下拉按显示名升序 no.1→no.18;均 convertible=False 只展示
- 测试覆盖全部 id 存在、显示名覆盖 1~18、各模板文件可读为完整 HTML

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 09:55:34 +08:00
董宏凯 2a1f50f726 Merge branch 'ji' into 'master'
fix(ai写作): 弱模型也能真正执行技能脚本(执行优先的强提示)

See merge request knowledge-base-bj/deerflow-server!152
2026-06-25 15:00:57 +00:00
fengxiangdebaoziandClaude Opus 4.8 158d157af4 feat(ai写作): 内网检索接口执行诊断写入 material_package.intranet_debug(排查用)
- material_package 新增 intranet_debug:是否配置/端点/知识库/超时/每个检索词命中数与
  报错/原始响应片段/总命中数/是否被采用为兜底/status(not_configured|pending|ran|
  cancelled|crashed)。随 values 事件回前端,前端忽略该字段,仅供 devtools 排查。
- 新增 config ai_writing.intranet_search_debug(默认 false):开启后即使技能成功也跑完
  内网并记录完整结果,用于验证内网接口是否真能通。
- 前端不改动。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 22:55:27 +08:00
fengxiangdebaoziandClaude Opus 4.8 1ed004fbb1 fix(ai写作): 弱模型也能真正执行技能脚本(执行优先的强提示)
弱模型在 lead agent 能执行 py 脚本、在 ai写作子智能体却不能:根因是子智能体的
_MATERIAL_OUTPUT_CONTRACT 过度强调"只输出 JSON",弱模型据此跳过工具执行直接吐空 JSON。
对齐 lead agent 的 skill_system 强框架,把契约改成"执行优先":

- 第一步强制先用 bash 实际运行技能脚本(给出 cd 技能目录 && python3 scripts/..py 的命令形态),
  严禁不调用工具就直接输出 JSON/凭记忆编造
- JSON 输出降级为第二步"检索完成后再整理"
- task 末尾追加"现在立刻开始执行检索"的强指令,进一步推动弱模型先动手

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 22:50:10 +08:00
吉鑫升 38f98cdf5c Merge branch 'ji' into master
# Conflicts:
#	offline-backend-20260512/backend/scripts/sql/column_additions_mysql.sql
2026-06-25 21:49:12 +08:00
吉鑫升andClaude Opus 4.8 a417124c21 feat(auth): 登录白名单细化为黑名单模式(approved 默认放行)+ 同步构建产物
- approved 放行标记默认 True:新账号首次登录即放行,登录白名单开关打开时只拦截
  被管理员显式「取消放行」(approved=False) 的用户;enforce_user_approved 放在
  各登录端点拿到 user 后、签发 JWT 前调用,admin 永远放行。
- 同步调整 LoginWhitelistPage / local_provider / models / system_settings /
  迁移 20260625_02 / user model / column_additions_mysql.sql 与 CLAUDE.md。
- 更新 backend/backend.zip 构建产物。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 21:41:15 +08:00
吉鑫升andClaude Opus 4.8 f3f11461de fix(open-3qfx): 免登录建会话补 default 用户上下文,修复 thread_meta 不落库
开放接口 /api/open/3qfx/ask 免登录、无 user context,start_run 写 thread_meta
前先 thread_store.get() 默认 user_id=AUTO,resolve_user_id(AUTO) 在无 context 时
抛 RuntimeError 被 start_run 的 try/except 当「非致命」吞掉,thread_meta 行从未
创建,前端按 metadata.taskId 怎么也搜不到这条会话(run 却已建)。

- 调 start_run 前显式 set_current_user 为 default 用户桶(后台 run_agent task
  在 create_task 时快照此 context,故后台运行也归属 default,符合任务深链对话
  全局共享、按创建者解析文件的语义),thread_meta 正常落库。
- 把 cop_task_detail_* 配置补到实际加载的 offline-backend-20260512/config.yaml
  (此前只加在不生效的 backend/config.yaml)。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 21:40:57 +08:00
董宏凯 2e79cee24a Merge branch 'dhk-1' into 'master'
Dhk 1

See merge request knowledge-base-bj/deerflow-server!151
2026-06-25 13:30:25 +00:00
fengxiangdebaozi 1fd997303e Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-25 21:29:14 +08:00
吉鑫升 cc017a22c7 Merge branch 'ji' into master 2026-06-25 20:38:33 +08:00
AdministratorandClaude Opus 4.8 5f01e8dd03 feat(message-token-usage): 速度条图例按当前速度只显示对应颜色
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 20:29:26 +08:00
fengxiangdebaozi ce69905950 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-25 19:54:58 +08:00
fengxiangdebaozi 71e7b9dd63 代码提交 2026-06-25 19:54:37 +08:00
吉鑫升andClaude Opus 4.8 58357547c9 Merge branch 'ji' into master
按钮管理「登录参数」两套实现冲突解决——两分支各自独立给跳转按钮加了登录态追加能力,
二者正交、保留两套,互不影响:
- master: login_params (JSON 列 login_params_json,从 userInfo 解析,类似轻应用登录参数)
- ji: append_auth + auth_token_param + auth_name_param (token 登录时追加 token1+用户名)

迁移 revision 碰撞修复(两分支都用了 20260625_01):重编号为线性链
  20260620_02 → 20260625_01 (login_params) → 20260625_02 (auth_params) → 20260625_03 (users_approved)
并同步 column_additions_mysql.sql 注释里的 migration 编号。

前后端 task_buttons(model/sql/memory/router/前端 type·api·admin 页)均保留两套字段;
两份 CLAUDE.md 文档合并为同时记录两种机制。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 19:36:43 +08:00
AdministratorandClaude Opus 4.8 fe7c6cb8f7 feat(open-3qfx): 开放接口按 taskId 直接发起 3qfx 第一次问答
新增 POST /api/open/3qfx/ask(无需登录,/api/open/ 白名单 + CSRF 豁免):
只传一个 taskId,后端解析 3Q 业务配置的智能体 + 按 id 拉取 cop-task-detail
拼出与前端一致的开场白,新建带 metadata.{taskId,agent_id} 的真实会话并后台
启动持久化运行,立即返回 thread_id(随后在 3qfx 任务工作区对话列表观看)。

- start_run() 增加 keyword-only enforce_access(默认 True);开放接口传 False
  绕过按当前(无)登录用户的智能体可见性校验
- task_deeplink 配置新增 cop_task_detail_url / _authorization / _test + mock
- tests/test_open_3qfx.py(10 项,tests/ 被 .gitignore 故未入库)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 19:19:17 +08:00
fengxiangdebaoziandClaude Opus 4.8 dc5b83e8cd Merge branch 'dhk-3': 会商第一步分析记录按业务链筛选
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 18:09:37 +08:00
fengxiangdebaoziandClaude Opus 4.8 27fffbec61 feat(会商第一步): 分析记录按业务链筛选(漏斗下拉, 选项从草稿chainTitle去重)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 18:08:36 +08:00
AdministratorandClaude Opus 4.8 d35d121261 feat(auth): 登录白名单也拦「接口问答」(已登录的 run 接口按用户放行)
开关开启时,未放行用户(非 admin)即便持旧 token,直接调发起问答的 run 接口
(/api/threads/{id}/runs[/stream|/wait]、/api/runs/{stream|wait})也返回 403,
不止拦登录。在 AuthMiddleware 解析出 user 后仅对问答 run 请求复用
enforce_user_approved;GET 列表/join/cancel/feedback 及普通浏览不受影响;
内部/渠道调用与无鉴权 /api/open/chat 不在此范围。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 17:37:47 +08:00
fengxiangdebaozi 368673c3b4 Merge branch 'dhk-1': ai写作技能检索稳定接收数据 + 内网兜底优化 2026-06-25 17:06:01 +08:00
fengxiangdebaoziandClaude Opus 4.8 854de9b43c fix(ai写作): 技能检索稳定接收数据(复用参考文献提取+截断抢救+上限早停)
- 复用主智能体「参考文献」模式的提取逻辑(deerflow.runtime.references)解析技能JSON,字段并集兼容
- bash输出中间截断时逐条抢救完整记录对象,不再因大JSON解析失败而全丢
- 所有退出路径(超时/递归上限/异常)都从tool输出收割,不依赖模型最终汇总
- 达到max_materials上限即停止驱动模型,修复步骤条爆100+条/素材超额
- 步骤条实时显示每次检索获得多少条数据
- 内网兜底:与技能并行预跑、响应解析兼容两套接口字段、0结果换简单检索词重试、超时放宽到10分钟

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 17:05:09 +08:00
Administrator 0aa55eb333 Merge branch 'ji' of http://192.168.0.200/knowledge-base-bj/deerflow-server into ji 2026-06-25 16:09:51 +08:00
AdministratorandClaude Opus 4.8 1d1ab384ef feat(auth): 登录白名单(注册后管理员审批放行 + 全局开关)
用户仍可自助注册,普通账号默认 approved=False(待审批),admin 建号即 True;
存量用户迁移回填 True 避免锁死。系统设置 login_whitelist.enabled 总开关:关=
所有人可登录,开=仅已放行用户(或 admin)可登录。三登录端点建号后、发 token 前
经 enforce_user_approved 拦截,未放行返回 403 PENDING_APPROVAL。管理员在「白名单
管理」页(设置下拉入口)切总开关 + 逐用户放行。取消放行只拦下次登录。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 16:09:38 +08:00
吉鑫升andClaude Opus 4.8 864224e07c feat(message-token-usage): 速度条下方常驻颜色含义图例
生成结束后在速度条下方展示一行图例(SpeedLegend),把进度条配色归并为用户视角的
延迟正常/微长/长 + 无响应四类说明,帮助用户理解速度条颜色代表的模型生成延迟状态。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 16:07:54 +08:00
吉鑫升andClaude Opus 4.8 04b38a4a25 fix(task-buttons): append_auth 显式 server_default 修复旧库 /api/task-buttons 报 500
旧库已存在 task_buttons 表时,启动期自动补列 _ensure_orm_columns_sync 会跳过
「NOT NULL 且无 server_default」的列,导致 2026-06-25 新增的 append_auth 永远补不上,
GET /api/task-buttons 查询报 Unknown column → 500。给该列加 server_default="0" 后,
重启即自动 ALTER TABLE 补列,与迁移 20260625_01 保持一致。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 15:57:26 +08:00
吉鑫升andClaude Opus 4.8 f8b40353ef feat(task-buttons): 跳转按钮可追加登录态 token+username + token 登录离线测试映射
rwfx/3qfx/xdfx 任务工作区的可配置跳转按钮(按钮管理)新增「追加登录态」开关:
url 类型按钮可在外链后拼 ?token=<token1>&username=<登录名>(参数名可配,默认
token/username),供跳转目标外部系统识别当前登录用户。

- 仅 token 登录(login/token)生效: token1 = ?authToken=,username = 后端用
  token 调 getTokenInfo 解析出的原始登录名(非邮箱前缀/非解 JWT)。二者登录时
  经 persistLoginCredentials 存入 login.token1/login.username(scoped-storage
  自动隔离嵌入/独立会话);非 token 登录读不到 token1 则跳过追加。
- 后端 UsernameLoginResponse 回传 username(原始名,规避邮箱归一化有损);
  token_login 加 mock_tokens 离线测试映射(123ewq->admin),命中即跳过外网
  getTokenInfo,便于本地全链路联调。
- task_buttons 加列 append_auth/auth_token_param/auth_name_param
  (migration 20260625_01 + 幂等 SQL)。

Tests: test_task_buttons.py, test_auth_login_modes.py(mock token/username 回传)。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 14:52:07 +08:00
fengxiangdebaoziandClaude Opus 4.8 893f1e6933 fix(会商第三步): 流程图入库限 rwfx-A + 修复跳过报告生成流程图出现双调度中卡片
- 入库功能仅 rwfx-A(businessCode 6BF)深链会商模式提供,其它业务深链生成流程图不再出现入库按钮/询问
- 流程图抽取串行化:auto 自动出图与用户「跳过报告直接生成流程图」手动出图竞态时,先中止上一轮、复用/移除被取代气泡,保证任意时刻只有一张流程图卡片

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 12:29:45 +08:00
fengxiangdebaoziandClaude Opus 4.8 04e6d0aa00 fix(ai写作): 前端实时接收技能步骤(此前被白名单丢弃,只在快照里一次性显示)
根因在前端:后端 _emit_skill_step 以 writer({"type":"skill_search_step", **step})
发出,**step 里的 type(invoke_skill/list_skills/skill_result/select_skills/
match_skills/skill_error/fallback/stop_early)会覆盖外层 "skill_search_step",
所以 custom 事件实际 type 是这些内层值。customToProgressEvent 的白名单没有它们,
直接 return null 丢弃——后端逐条实时发(SSE id 时间戳已证实分散在 0~76s),前端却
全扔了,技能步骤只能等节点结束的素材包快照一次性出现(前端一直 loading)。

修复:customToProgressEvent 按内层 step 类型识别,实时归一成 skill_search_step
事件(与快照里的 step 同格式),让技能调用过程一步步实时进时间线。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 01:20:21 +08:00
fengxiangdebaoziandClaude Opus 4.8 1d6659f9e7 fix(ai写作): 技能步骤从节点协程 emit,custom 事件真正实时刷给前端
前端/SDK 都是实时的(onCustomEvent 逐条即触发,draft_chunk 同链路就实时)。
问题在后端:技能步骤原来在节点内的嵌套 agent.astream 里直接 emit,custom 事件
被攒到整段跑完才一次性吐到 SSE(后端在跑、前端一直 loading)。

改为:嵌套 astream 跑后台任务,只把工具调用塞进 asyncio.Queue;真正的 writer
由 researcher 节点**自身协程**从队列取出来调(与 draft_chunk 同一上下文),
custom 事件即被 LangGraph 实时刷给前端。撤掉上一版无效的 sleep(0)。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 01:04:49 +08:00
fengxiangdebaoziandClaude Opus 4.8 a4a67c1a00 fix(ai写作): 技能流式每步主动让出事件循环,custom 事件实时刷给前端
前端 skill_search_step 已是 pushImmediate(实时渲染),但事件在节点内的嵌套
agent.astream 里发出后没及时让出事件循环,被攒到整段跑完才一次性吐到 SSE,
前端看着像卡死。每个 chunk 处理完 await asyncio.sleep(0) 主动让出,促使刚 emit
的 custom 事件实时刷给前端(对齐 draft_chunk 的实时行为)。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 00:48:57 +08:00
fengxiangdebaoziandClaude Opus 4.8 8f773d3f1b fix(ai写作): 技能调用实时流式显示 + 去掉大纲拼检索词/复用检索词
- 技能调用过程改为实时流式:run_skill_via_real_agent 不再 to_thread 阻塞跑
  executor.execute(),而是复用其 agent/state 构建后在图事件循环里 astream,
  每个工具调用(读 SKILL.md / bash / 检索)实时推一条步骤到时间线——内网慢时
  用户能看到技能在执行,不会以为卡死。整段 asyncio.wait_for 卡 5 分钟超时。
- 回退检索词相关改动(实测无用、且结合大纲后检索词变长不利按词匹配):
  - intent_parser 不再顺便生成 keywords,删 precomputed_keywords 状态字段;
  - researcher 不再复用,每次自己现生成检索词(回到原行为);
  - 检索词提示词去掉「结合大纲/{outline_section}」,删 keyword_outline_section。
  保留:关思考、技能真实运行时、技能目录修复、内网兜底。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 00:33:57 +08:00
fengxiangdebaoziandClaude Opus 4.8 c0305c9269 fix(ai写作): 修复内网技能检不出东西(技能目录路径 + 模型 + 兜底 + 开关)
对比主智能体与 AI 写作两份调用日志定位到根因:真实 agent 路径只注入了
SKILL.md 内容、没告诉模型技能在容器内的目录,模型用相对路径跑脚本
(python3 scripts/search)→ No such file。主智能体则 cd 进技能绝对目录再跑。

- _skill_agent:注入 skill.get_container_path() 的绝对目录,要求先 cd 再执行
  脚本/用绝对路径(对齐主智能体 skill_view 拿 location 后的行为)。
- researcher:跑技能的 agent 改用用户选定的写作主模型(model_name_fallback=None),
  不再用常配成外网的 keyword_model,避免技能 agent 连不上自己的模型。
- researcher:所有技能都 0 条时,最终兜底直连内网 ES 接口(IntranetSearchProvider),
  受 ai_writing.intranet_search_url 控制。
- config.yaml:开 researcher_skill_agent=true(内网技能必须走真实运行时),
  新增 intranet_search_url / intranet_knowledge_base 兜底配置项。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 23:52:32 +08:00
吉鑫升andClaude Opus 4.8 6989dd45f1 fix(chat): 问答回答时间戳不再漂移到当前电脑时间
AI 回答无自身时间戳,原先在首次渲染时用 new Date() 兜底,导致
未在原会话完成、或从历史重新加载的回答显示加载时刻而非真实时间。
改为让 AI 回答继承同轮提问的可靠 client_ts(turnTime),并停止给
AI 消息打 now 戳;显示层优先用提问时间,可自愈历史错误时间。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 22:57:21 +08:00
fengxiangdebaoziandClaude Opus 4.8 d8b43e7579 fix(ai写作): 技能检索超时硬编码 5 分钟(内网慢检索不被过早切断)
内网检索很慢,原 120s 在三个真正生效的层把检索切断。统一硬编码 300s,
不依赖环境变量(部署方不一定会配):
- researcher._SKILL_SEARCH_TIMEOUT_SECONDS:120(env) → 300(写死),删掉 _env_int;
  作用于直连/定向技能检索的 wait_for,也传给真实智能体路径。
- IntranetSearchProvider 默认 httpx 超时:120 → 300(直连内网 ES 的真正瓶颈)。
- run_skill_via_real_agent 整段运行上限:max(timeout_s, 300),至少 5 分钟。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 22:54:42 +08:00
fengxiangdebaozi 4f68235c94 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-24 22:45:42 +08:00
吉鑫升 c1143564ef Merge branch 'ji' of http://192.168.0.200/knowledge-base-bj/deerflow-server into ji 2026-06-24 22:42:21 +08:00
吉鑫升andClaude Opus 4.8 ea2ea9783e feat(task-deeplink): xdfx 开场信息追加行动标题与行动内容
xdfx(行动分析)深链开场信息原先只附行动id(action_id),现额外
拼上行动标题(actionName)与行动内容(narration)。优先读登录时
缓存的行动详情(readActionDetail),无缓存再 fetchActionDetail,避免
重复请求。buildOpeningText 第三参数由 actionId 改为 ActionOpeningInfo。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 22:34:25 +08:00
吉鑫升andClaude Opus 4.8 e3e93712b6 feat(task-deeplink): xdfx 开场信息追加行动标题与行动内容
xdfx(行动分析)深链开场信息原先只附行动id(action_id),现额外
拼上行动标题(actionName)与行动内容(narration)。优先读登录时
缓存的行动详情(readActionDetail),无缓存再 fetchActionDetail,避免
重复请求。buildOpeningText 第三参数由 actionId 改为 ActionOpeningInfo。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 22:33:09 +08:00
fengxiangdebaoziandClaude Opus 4.8 afb78a6943 feat(ai写作): 素材收集专家按真实智能体运行时跑技能 + 步骤条对齐
- 新增 run_skill_via_real_agent:复用 SubagentExecutor(与 lead agent / 子智能体
  同一套运行时),加载技能 SKILL.md + 全套工具 + 懒加载沙箱,让技能的真实检索逻辑
  (读文件 / 调内网接口 / MCP)真正执行,再按 JSON 契约收割结构化素材;researcher 的
  _execute_skill 在 researcher_skill_agent 开启时切到它,失败/空结果回退直连检索。
  解决内网技能(在别的智能体里好使)在 AI 写作里检不出东西的问题。
- 步骤条轻量对齐别的智能体:技能调用拆成「读取 SKILL.md → 执行检索 → 检索到 N 条」
  三段(前两段新增,结果段沿用 skill_result);前端 SkillStepsCard 零改动。
- 含 roundtable-planning(业务链选择 / Step2 编排)的进行中改动。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 22:19:30 +08:00
董宏凯andClaude Opus 4.8 1a127ef602 chore(定时任务): 替换 no.3 模板内容为 no.3-1.html(仍只展示)
- templates/no3/no3.html 覆盖为新版(73KB,const DATA = {…} 内联)
- id/name/注册不变,仍为 convertible=False 只展示

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 22:17:24 +08:00
AdministratorandClaude Opus 4.8 acc29c8121 fix(middlewares): 标题模型推理不再泄漏到 UI 流 + open/ephemeral 会话避免无谓 DB 访问
- title: 标题模型用隔离 config(不继承父级 streaming callbacks),force_disable_thinking,<think> 块清洗,避免推理 token 进入实时流/运行日志
- uploads: 无文件的普通对话轮次直接跳过,不再解析线程归属(避免命中 DB)
- thread_data: ephemeral 会话用当前登录用户解析数据目录
- thread_paths: open-/__skill-review__ 等合成线程视为 local-only,直接用当前用户
- frontend: 新增 build:test 构建脚本

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 21:20:12 +08:00
董宏凯andClaude Opus 4.8 ca31490241 chore(定时任务): no.9 模板显示名称改为 no.13(id 仍为 no9)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 21:11:33 +08:00
董宏凯andClaude Opus 4.8 6c42f86e30 chore(定时任务): no.8 模板显示名称改为 no.12(id 仍为 no8)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 21:09:56 +08:00
董宏凯 5b818836d7 Merge branch 'dhk-1' into 'master'
fix(登录): redirect 透传登录 URL 其余 query 到目标页

See merge request knowledge-base-bj/deerflow-server!150
2026-06-24 11:49:00 +00:00
fengxiangdebaozi 3ea8e73389 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-24 19:48:15 +08:00
fengxiangdebaoziandClaude Opus 4.8 c117e296cb feat(ai写作): 草稿局部修改只改命中章节,支持改章节标题,修改时右侧流式重写
用户在草稿确认填修改意见(user_revise)时,按章节定位只重写命中章节、
其余字节级保留;新增范围识别区分「改标题」与「改正文」,改标题同步回写
outline 使其持久生效(修复改章节标题不生效);整体性/结构性意见自动回退
整篇重写。前端新增 isRevising:修改时右侧先恢复初始占位(清空旧稿),
重写流到达后实时展示被改章节的流式重写。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 19:45:00 +08:00
fengxiangdebaoziandClaude Opus 4.8 42f55251f2 feat(ai写作): 历史回看右侧成稿可编辑并保存回历史记录
- 后端新增 PUT /api/ai-writing/sessions/{id}/draft(属主校验,draft_title 可选)
- 前端历史模式放开只读,工具栏新增「保存」按钮持久化修改
- 实时写作完成态保持原样(仅导出,不落库)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 18:32:11 +08:00
fengxiangdebaoziandClaude Opus 4.8 304e1b637a feat(ai写作): 意图解析顺便生成检索词 + 修复快捷模式
- 意图解析(intent_parser)与意图理解共用同一次 LLM 调用顺便生成检索词
  (结合意图 + 大纲覆盖各章节主题),存入 state.precomputed_keywords;
  researcher 首轮直接复用,省掉素材收集阶段单独的「生成检索词」LLM 往返。
  解析失败/为空时回退到 researcher 自己生成(优雅降级);re_search 仍重新生成。
  keyword_outline_section 提到 _utils 供两处共用。
- 修复快捷模式:之前被「大纲先行确认」改动拖累,先误成「问一堆问题」,再被我
  过度修正成「不生成大纲」。现修正为——快捷模式 = 用默认选项、不逐项澄清提问
  (make_lead_agent 在快捷模式下直接不挂 ask_clarification 工具,物理上问不了),
  但**仍生成并确认大纲**再提交;普通模式不变。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 18:32:10 +08:00
fengxiangdebaoziandClaude Opus 4.8 49173d9c28 feat(ai写作): 大纲整理可见化 + 检索词结合大纲 + 素材/大纲阶段关思考
- 草稿确认卡:「给出修改意见」「让编辑继续审核」移到「确认定稿」上方。
- 大纲整理阶段文案:用户自带大纲时显示「整理你的大纲」而非「规划大纲」
  (OutlineStreamingView / 骨架屏 / 状态栏,按 request.userOutline 切换)。
- 素材收集专家:用户自带大纲时把大纲原文带入检索词生成,让关键词结合写作
  意图覆盖各章节主题(_keyword_outline_section,agent + legacy 两路)。
- 素材收集(检索词/排序)与大纲整理/生成阶段强制关闭思考
  (create_chat_model force_disable_thinking:GLM thinking.disabled +
  Qwen/vLLM enable_thinking=false),关不掉的模型仍由 ThinkTagParser 把
  <think> 分流到思考框正常展示。disable_thinking 串入
  _utils.get_model/llm_json 与 _agent_runner.stream/run_writing_agent。
- 含草稿「局部修改」WIP(writer_draft 只重写命中章节)及外观控件改动。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 18:32:10 +08:00
董宏凯andClaude Opus 4.8 8678ceb422 feat(定时任务): 新增第九个 HTML 模板 no.9(只展示)
- no.9.html(160KB)复制进 templates/no9/;数据用 `const DATA = {…}`(= 前有空格,同 no.6),
  当前引擎正则要求 const DATA=,不匹配,故先注册为 convertible=False 只展示
- 前端下拉/参考列表自动出现 no.9
- 测试覆盖 no.9 存在/只展示/文件可读

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 18:17:56 +08:00
董宏凯andClaude Opus 4.8 31cd19aabb feat(定时任务): 新增第八个 HTML 模板 no.8(只展示)
- no.8.html(77KB)复制进 templates/no8/;数据存于 <script id="DATA"
  type="application/json"> 元素(同 no.4/no.7 元素注入),当前引擎只支持 const VAR= 行注入,
  故先注册为 convertible=False 只展示
- 前端下拉/参考列表自动出现 no.8
- 测试覆盖 no.8 存在/只展示/文件可读

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 18:16:34 +08:00
董宏凯andClaude Opus 4.8 60029ae3dc feat(定时任务): 新增第七个 HTML 模板 no.7(只展示)
- no.7.html(605KB)复制进 templates/no7/;数据存于 <script id="PAGE_DATA"
  type="application/json"> 元素(同 no.4 类元素注入),当前引擎只支持 const VAR= 行注入,
  故先注册为 convertible=False 只展示
- 前端下拉/参考列表自动出现 no.7
- 测试覆盖 no.7 存在/只展示/文件可读

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 18:13:38 +08:00
董宏凯andClaude Opus 4.8 4f62703477 feat(定时任务): 新增第六个 HTML 模板 no.6(只展示)
- no.6.html(266KB)复制进 templates/no6/;数据用 `const DATA = {…}`(= 前有空格),
  当前引擎正则要求 const DATA=,不匹配,故先注册为 convertible=False 只展示
- 前端下拉/参考列表自动出现 no.6
- 测试覆盖 no.6 存在/只展示/文件可读

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 18:09:47 +08:00
董宏凯andClaude Opus 4.8 c0af23aefe feat(定时任务): 新增第五个 HTML 模板 no.5(只展示)
- no.5.html(174KB)复制进 templates/no5/;数据用 `let DATA = {…}`(let+空格,非
  const DATA= 行),当前引擎行注入正则不匹配,故先注册为 convertible=False 只展示
- 前端下拉/参考列表自动出现 no.5
- 测试覆盖 no.5 存在/只展示/文件可读

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 17:51:12 +08:00
董宏凯andClaude Opus 4.8 6a6195f883 feat(定时任务): 新增第四个 HTML 模板 no.4(只展示)
- no.4.html(3.9MB)复制进 templates/no4/;数据存于 <script id="app-data"
  type="application/json"> 元素(非 const DATA= 行),当前引擎只支持 const VAR= 行注入,
  故先注册为 convertible=False 只展示,转换后续接(需扩展元素注入)
- 前端下拉/参考列表从 API 拉取,no.4 自动出现
- 测试覆盖 no.4 存在/只展示/文件可读

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 17:45:40 +08:00
吉鑫升 1a87077642 Merge branch 'ji' into master
并入: loop 跨事件循环 DB 访问修复(asyncmy attached to a different loop)、y-log 前缀、全角参考文献角标识别

# Conflicts:
#	CLAUDE.md
2026-06-24 17:13:45 +08:00
fengxiangdebaoziandClaude Opus 4.8 e9c8d1cea2 feat(ai写作): 自带大纲/会商及研究模板等前后端改动
提交工作区中 AI 写作(表单/时间线/历史/上下文/流式 hook/类型)、
研究模板配置页、lead_agent、researcher/graph/state 及 gateway/config
的进行中改动。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 16:15:39 +08:00
fengxiangdebaoziandClaude Opus 4.8 d2c76100f2 perf(ai写作): 用户自带大纲整理提速并流式化
用户自带大纲时「整理大纲」原有两个阻塞式非流式 LLM 调用,内网模型
<think> 关不掉导致用户长时间干等:

- 素材关联(每次都调)改为确定性词重叠 _assign_materials_heuristic,
  零 LLM、瞬时;有编号/标题/缩进的大纲整理几乎零等待。
- 散文化大纲的 LLM 归一改为流式 _stream_normalize_user_outline:
  ThinkTagParser 把思考推思考框、正文实时打字机展示并累积解析;
  并在 OUTLINE_NORMALIZE_USER 末尾追加 /no_think。
- researcher 路径只做确定性解析,解析不出返回 None,交给 writer_outline
  流式归一(outline_chunk 在该阶段天然映射大纲思考框)。
- 移除废弃的 OUTLINE_MATERIAL_ASSIGN_* 提示词与 llm_json 死引用。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 16:15:39 +08:00
吉鑫升andClaude Opus 4.8 6aff165d09 fix(db): 路由跨 loop 的 DB 访问回引擎主 loop,消除 asyncmy "attached to a different loop"
会商/定时任务/沙箱工具等在 worker 线程的临时 loop 上用 asyncio.run 跑全局引擎连接池的
DB 操作,连接被绑定到随即关闭的临时 loop;池子回收/释放该连接时 asyncmy
_terminate_graceful_close 在错误的 loop 上触发 future,持续刷
"got Future attached to a different loop"。

- engine.py: 新增 run_db_blocking(fire_and_forget_db_write 的带返回值版本)。离开主 loop
  时用 run_coroutine_threadsafe 把协程送回主 loop 执行、阻塞调用线程拿结果;仅在无主 loop
  或正同步处于主 loop 内(送回会死锁)时退回临时 loop。
- thread_paths / prompt / skill_tools: 三处同步→异步阻塞读桥(任务owner解析/常驻技能/
  技能可见性)改走 run_db_blocking,删除各自重复的 _run_coro_blocking。
- llm/tool metrics 中间件: fire-and-forget 写改走 fire_and_forget_db_write。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 15:57:04 +08:00
吉鑫升andClaude Opus 4.8 5ecf28e60c feat(y-log/knowledge): 日志前缀改 CM助手-全量 + 入库 nodeName 按标题去时间戳保持一致
1. Y-Log 上报 optDetail 前缀 B1-CM助手 → CM助手-全量(全量替换 44 个前端文件 + 文档)
2. 知识库入库 nodeName 改为只取 md5(标题).md(去掉时间戳),同一篇 md 每次入库一致,避免重复记录

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 15:46:51 +08:00
g zy fb103b6ad9 Merge branch 'gzy' into 'master'
Gzy

See merge request knowledge-base-bj/deerflow-server!149
2026-06-24 07:42:20 +00:00
Rocky Kwok 71a865dc0c Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into gzy 2026-06-24 15:41:25 +08:00
Rocky Kwok 8ed54448c2 feat: 打开 browser_act 2026-06-24 15:40:56 +08:00
董宏凯andClaude Opus 4.8 5a2441cc9f feat(定时任务): 新增第三个 HTML 模板 no.3(只展示)
- no.3.html(3.8MB)复制进 templates/no3/,无 const DATA= 注入点 → 注册为
  convertible=False 只展示模板(同 no.2,后续接转换再开)
- 前端下拉/参考列表从 API 拉取,no.3 自动出现,无需前端改动
- 测试覆盖 no.3 存在/只展示/文件可读

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 14:38:49 +08:00
董宏凯andClaude Opus 4.8 089d3e171f fix(定时任务): 抽取开关只控制模板HTML数据,不再影响Markdown等正常操作
- 之前关闭抽取会整段跳过 gather/agent,连带把 Markdown 生成也跳过了
- 改为:抽取开关只决定 HTML 用「抽取数据」还是「模板默认数据」;require_markdown 独立——
  需要时照常跑 gather 产出 .md 并校验/带出,与开关无关
- gather 仅在 do_extract(开关开+有描述+可转换) 或 require_markdown 时跑一次,两者复用同一次
- 只展示模板恒不抽取,但仍尊重 require_markdown;_finalize_template_html 支持 extra_files 带出 .md
- 测试:关闭抽取+必须Markdown → 仍产出.md/不转换/HTML用默认数据

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 14:23:45 +08:00
xu hd ed71df1b60 Merge branch 'xuhd' into 'master'
fix(notebook): 来源搜索导入后立刻显示占位卡并刷新来源列表

See merge request knowledge-base-bj/deerflow-server!148
2026-06-24 05:15:19 +00:00
xuhdandClaude Sonnet 4.6 85cd2c888e fix(notebook): 来源搜索导入后立刻显示占位卡并刷新来源列表
- handleImport 成功后调用 onUploadComplete 通知父组件(原先缺失)并关闭弹窗
- 新增 pendingImportTitles state,同步导入后立刻渲染 PendingSourceCard
- sources 刷新后按标题匹配移除占位卡并自动选中新来源

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-24 13:14:36 +08:00
董宏凯andClaude Opus 4.8 6673121f3f feat(定时任务): 选内置模板时加「执行数据抽取」开关,关闭则直接用默认数据
- html_config.template_extract(默认关,仅参考选 tpl:<id> 时显示开关):
  关闭→跳过检索/转换,直接用模板默认数据填充;开启→才执行检索+转换抽取
- 后端 _run_html_template_reference 在只展示分支后先判开关
- 前端 ScheduledTasksPage:参考选内置模板时显示 Switch,存进 html_config.template_extract,编辑回显
- 测试覆盖 开/关 两条路径

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 13:09:16 +08:00
董宏凯andClaude Opus 4.8 4898ea0a85 build(harness): 显式把 no.1/no.2 HTML 模板纳入打包,保证新机器内置可见
- harness pyproject [tool.hatch.build] artifacts 显式包含 templates/**/*.html,
  任何构建方式(wheel/sdist)都带上模板(已验证 wheel 内含 no1/no2)
- 模板文件本就 git 跟踪、源码安装直读、内置 agent 启动自动 seed —— 新机器 clone
  装好即可直接看到
- 加自检测试 test_all_registered_template_files_exist

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 13:05:43 +08:00
董宏凯andClaude Opus 4.8 7d9a0637ca fix(定时任务): 模板子页面空内容回退原数据,避免子页面显示不全
- 引擎 merge_with_reference:按顶层键(=子页面)逐一合并,转换结果里没抽到有效内容的
  子页面/字段回退模板原有数据(_has_content/_merge_fill 递归,列表/标量整体保留,
  字典逐键回退空分支);整体为空等价于返回模板默认数据
- _run_html_template_reference:描述与任务prompt都为空→直接用原数据不检索;转换成功后
  对结果做 merge_with_reference 补空子页面
- _run_template_fill_attempt 同样套用 merge,空子页面一致回退
- 测试覆盖 _has_content/merge 各场景 + 端到端空子页面回退/空描述用原数据

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 12:20:12 +08:00
董宏凯andClaude Opus 4.8 ba885ca201 fix(定时任务): require_html 选内置模板时用真实模板出页,保留全部子页面
- 模板是 JS 驱动多页 SPA,子页面靠脚本从 DATA 渲染;之前用 style_reference 抽 CSS 摘要
  让模型自由渲染,结果只剩主页、子页面全丢
- 改为:_run_html_page_attempt 见 tpl:<id> 参考即提前分支到 _run_html_template_reference,
  用真实模板文件出页——可转换模板=检索数据→转换→fill_template;只展示模板=原样输出;
  转换失败兜底默认数据,保证页面与子页面始终可用
- 抽出 _convert_to_template_data / _finalize_template_html 复用,删除已废弃的 style_reference
- 测试覆盖:真模板保留 const DATA/script/id=tabs;只展示原样;转换失败回退

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 11:47:16 +08:00
董宏凯andClaude Opus 4.8 ec60b77a71 feat(定时任务): 必须生成HTML的「参考收藏页面」加入 no.1/no.2 模板作为风格参考
- 引擎 template_fill.style_reference:抽取模板 <style> CSS + 去脚本结构骨架(~13-28KB),
  剥掉巨大数据常量,供 require_html 渲染模型模仿风格;reference_template_id 解析 tpl:<id>
- 调度器 _run_html_page_attempt:参考来源为 tpl:<id> 时用模板风格参考,否则走收藏 store
- 前端 ScheduledTasksPage:require_html 模式下「参考收藏页面」列表加入「模板:no.1/no.2」,
  值存 tpl:<id>;htmlTemplates 在 require_html 时也拉取
- 文档同步

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 11:09:48 +08:00
董宏凯andClaude Opus 4.8 ae3788a87d feat(定时任务): 模板数据转换器对话页加「页面模板+渲染预览」调试入口
- 后端 POST /api/scheduled-tasks/template-fill/render:不调模型,抽取回复里的 JSON
  → 校验 → 填充,返回完整 HTML + 校验错误/缺失字段(非法也照样填充便于看效果),
  只展示模板原样返回
- 前端仅 template-json-builder 智能体的 AgentChatPage:顶部加页面模板下拉 +「渲染预览」
  按钮,取最近一条 AI 回复填进所选模板,弹窗用 sandbox=allow-scripts iframe 预览 +
  校验状态;严格按 agent id 门控,不影响其他智能体对话页
- 文档同步

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 10:00:18 +08:00
吉鑫升andClaude Opus 4.8 3e68260afa fix(citations): 识别全角参考文献角标(全角数字/合并/区间)
正文里的引用角标识别此前全角括号只支持单个半角数字 【1】,
导致 【1】(全角数字)、【1,2】/【1,2】/【1、2】(合并)、
【1-3】/【2~5】(区间) 等中文常见写法无法识别成参考文献。

补齐全角括号的「全角数字 / 合并 / 区间」三种形态,转成半角后交给
原有半角逻辑统一处理;仍保留 isValidIndex 闸门,避免把正文里的
【3】(越界)、【附录】(非数字) 误判为引用。新增 inline-citations.test.ts。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 22:14:52 +08:00
fengxiangdebaoziandClaude Opus 4.8 f551c7af9b fix(登录): redirect 透传登录 URL 其余 query 到目标页
?redirect=/page/strategy/dashboard-agent&taskId=3334 时把 taskId 等非登录消费参数
透传到目标页 query(目标自带同名参数优先),鉴权类参数不透传以防泄漏到地址栏。
修复跳转后目标页「缺少 taskId」。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 22:10:40 +08:00
董宏凯 b1ef4ccb1a Merge branch 'dhk-1' into 'master'
feat(定时任务): 模板转换支持纯文本/含JSON文本/纯JSON三种源输入

See merge request knowledge-base-bj/deerflow-server!147
2026-06-23 13:53:18 +00:00
fengxiangdebaozi e3631a9fd6 Merge branch 'dhk-1' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-23 21:52:27 +08:00
fengxiangdebaoziandClaude Opus 4.8 8241f8dd6b feat(登录): 新增 ?redirect= 参数,登录后跳转指定站内页面
支持 ?redirect=page/strategy/dashboard-agent(可不带前导斜杠、可自带 query),
优先级高于 taskId/goPath 深链与默认首页;仅接受站内相对路径,拒绝绝对/协议相对
URL 与反斜杠以防开放式跳转。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 21:51:59 +08:00
董宏凯andClaude Opus 4.8 3d2cc9e5cd fix(深链会商): Step2 文件产物虚拟预览仅在有内容时用,否则回退 HTTP 按创建者解析(修复跨账号看不到)
- useStep2Orchestration.openArtifactPreview: stub 无内容(str_replace/跨账号草稿恢复)时不再短路,
  回退到 artifacts HTTP 接口,并优先用子席位 thread(roundtable 线程→后端按对话创建者解析+放行跨账号)
- findSeatArtifactSource 一并返回 stub 捕获的 content 供判断
- 附:模板数据转换器「源数据抽取」手工测试清单文档

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 21:47:46 +08:00
fengxiangdebaozi e263d86fc3 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-23 21:22:02 +08:00
fengxiangdebaozi 151384b26d 代码修改 2026-06-23 21:21:49 +08:00
fengxiangdebaozi 030ede6887 Merge branch 'ji' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-23 21:07:05 +08:00
fengxiangdebaozi e6ca2bf64f Merge branch 'dhk-1' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-23 21:06:19 +08:00
fengxiangdebaozi 47cff9e2f9 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-23 21:06:09 +08:00
fengxiangdebaozi 6742346eb4 代码提交 2026-06-23 21:05:58 +08:00
吉鑫升 b5e682cfd2 Merge branch 'ji' of http://192.168.0.200/knowledge-base-bj/deerflow-server into ji 2026-06-23 21:01:05 +08:00
吉鑫升 2193c4484b Merge remote-tracking branch 'origin/master' into ji 2026-06-23 20:58:41 +08:00
Administrator 4fc3d7dae2 Merge remote-tracking branch 'origin/master' into ji 2026-06-23 20:57:01 +08:00
Administrator 6f0f9fb1fc Merge branch 'ji' of http://192.168.0.200/knowledge-base-bj/deerflow-server into ji
# Conflicts:
#	CLAUDE.md
2026-06-23 20:52:39 +08:00
AdministratorandClaude Opus 4.8 df9c59e21c feat(y-log): 问答按 LLM 调用各记一条 + 全量补齐各 API 操作埋点
- 问答日志从「每轮 onFinish 一条」改为 useThreadStream onLangChainEvent
  监听 on_chat_model_end,每次大模型调用结束各上报一条(含子代理)
- 广覆盖各 API client 成功路径:查看(view)/查询(search)/新增(create)/
  编辑(edit)/删除(delete)/启停(enabled·disabled)/导入导出,补齐此前
  整模块零埋点与漏掉的单条详情 GET;跳过高频 typeahead/轮询/bootstrap

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 20:42:54 +08:00
AdministratorandClaude Opus 4.8 6131eda219 feat(y-log): 问答按 LLM 调用各记一条 + 全量补齐各 API 操作埋点
- 问答日志从「每轮 onFinish 一条」改为 useThreadStream onLangChainEvent
  监听 on_chat_model_end,每次大模型调用结束各上报一条(含子代理)
- 广覆盖各 API client 成功路径:查看(view)/查询(search)/新增(create)/
  编辑(edit)/删除(delete)/启停(enabled·disabled)/导入导出,补齐此前
  整模块零埋点与漏掉的单条详情 GET;跳过高频 typeahead/轮询/bootstrap

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 20:41:07 +08:00
吉鑫升andClaude Opus 4.8 14082b3e7b fix(深链): 删除接口空响应体也判成功
dropSixOrSevenData 成功时返回空响应体,原 success: obj.success === true
永远为 false,导致删除已成功却总弹「清除失败/无法覆盖」。改为
success: obj.success !== false:请求未抛错即算成功,仅显式 {success:false} 才失败。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 20:28:18 +08:00
董宏凯andClaude Opus 4.8 00181ebde8 feat(定时任务): 模板转换支持纯文本/含JSON文本/纯JSON三种源输入
- template_fill.extract_embedded_json:字符串感知平衡扫描,从含 JSON 的文本里抠出
  内嵌 {…}/[…](纯文本返回 None)
- 调度器转换 prompt 预识别内嵌 JSON,单独标注「识别到的结构化数据」并保留原文;
  纯文本则让模型按语义理解;conversion prompt 重写覆盖三种形态
- 内置 agent SOUL 说明三种源数据形态
- 文档同步

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 20:28:05 +08:00
董宏凯 320f2ef814 Merge branch 'dhk-1' into 'master'
feat(深链会商): rwfx-A/3qfx-A 首条消息附带 taskId,xdfx-A 附带 taskId+actionId

See merge request knowledge-base-bj/deerflow-server!146
2026-06-23 12:09:45 +00:00
fengxiangdebaoziandClaude Opus 4.8 8b022bffc5 feat(深链会商): rwfx-A/3qfx-A 首条消息附带 taskId,xdfx-A 附带 taskId+actionId
会商 Step1 自动发送的「任务信息」现追加任务/行动 id,与单智能体路径口径一致,
id 标签统一用驼峰(taskId / actionId)。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 20:08:33 +08:00
董宏凯 5fddb08e04 Merge branch 'dhk-1' into 'master'
fix(roundtable): xdfx-A 深链会商聊天记录按行动id隔离存储

See merge request knowledge-base-bj/deerflow-server!145
2026-06-23 11:48:10 +00:00
fengxiangdebaozi 0fedb6ffd8 Merge branch 'dhk-1' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-23 19:47:54 +08:00
董宏凯andClaude Opus 4.8 498e3c6a84 fix(深链): 「上一步」进大屏绘制页强制显示全局导航栏+侧边栏
- PageLayout 对 /strategy/dashboard-agent 路由强制 pageSidebarAllowed(不受界面模式/
  会话级 sidebar 标志影响;仍尊重 embed=1 嵌入态隐藏),避免从去 chrome 的深链工作区进来后整页无顶栏/侧栏
- 「上一步」按钮 openMode 改回 self(同窗导航;forceChrome 后同窗/新窗都能带回 chrome)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 19:47:02 +08:00
fengxiangdebaozi 85aa242fd5 Merge branch 'master' into dhk-1 2026-06-23 19:45:41 +08:00
fengxiangdebaoziandClaude Opus 4.8 6f94a40303 fix(ai-writing): 写作分栏拖拽条不再压住左侧滚动条
隐形拖拽热区只向右(草稿区留白)延伸 + 抓手微右移,避免鼠标抓左侧时间线滚动条时
误触左右 resize 导致滑不动;不留任何视觉间隙。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 19:37:30 +08:00
董宏凯andClaude Opus 4.8 34893007a7 feat(深链会商): rwfx-A 复用单智能体 3q 预检闸门,未完成引导前往三情会商(3qfx-A)
- 抽出共用组件 RwfxSqReportGate(单/多智能体共用),targetGoPath 参数化「前往」目标
- 单智能体 TaskFxWorkspace 改为 import 共用组件(默认 3qfx),清理因抽离失效的 import
- 多智能体会商 RoundtablePlanningPage 深链 rwfx-A 挂同一闸门,目标 3qfx-A(三情会商)
- 改一处两处都生效,避免双份逻辑漂移

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 19:26:00 +08:00
Administrator 053d3e300e Merge branch 'ji' into master (操作日志 Y-Log 上报)
# Conflicts:
#	CLAUDE.md
2026-06-23 19:22:53 +08:00
吉鑫升andClaude Opus 4.8 a1fbfaf864 feat(xdfx): 行动历史查询与删除(与 rwfx 共用 dropSixOrSevenData 删除接口)
- 删除接口统一为 dropSixOrSevenData:rwfx 传 ?taskId=、xdfx 传 ?actionId=,另一参数直接不出现在 URL
- xdfx 工作区新增「清除记录」按钮(按行动id 删除),删除前预检「行动历史是否存在」
- action_history_url 配置位(地址待提供,留空则不查询/不阻断删除)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 19:14:16 +08:00
fengxiangdebaoziandClaude Opus 4.8 b8c78ba06e feat(ai-writing): 大纲先行确认 + 新文章类型识别 + 参考文献 + 编辑器修复
- 写作配置 Q&A 改为「先流式生成大纲并多轮确认 → 再确认意图」,放宽轮数上限
- 意图识别出列表外的新文章类型时带上类型名+简介(仅本次写作临时使用)
- 成稿支持参考文献:正文 [n] 角标 + 文末按出现顺序的「参考文献」列表(表单开关,默认开)
- 流式接取未闭合 <think> 思考内容,首 token 前加「正在整理…」占位
- 修复右侧编辑器输入空格只出一次、光标跳字(避免自激回灌 setContent 重置光标)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 19:07:03 +08:00
董宏凯andClaude Opus 4.8 cd33aaeded feat(定时任务): 内置「模板数据转换器」按 HTML 模板填充 JSON 生成大屏
- 模板填充引擎 template_fill.py:模板注册表 + schema 骨架 + 结构校验 + 行级安全填充;
  模板自带 DATA 即 schema 来源。no.1 可转换填充(含 MANIFEST 更新时间刷新),
  no.2 暂为「只展示」(convertible=False) 原样输出已有数据
- 内置 agent template-json-builder(seed + SOUL),随 lifespan 注入,自动出现在
  定时任务「执行智能体」下拉
- 调度器新增模板填充执行分支 _run_template_fill_attempt:源 JSON→大模型转换→
  结构校验→失败回喂重试;空源/只展示模板直接用模板默认数据,绝不失败
- API:GET /api/scheduled-tasks/html-templates
- 前端:选中该 agent 后条件渲染「HTML模板」下拉 + .json 上传,只展示型模板隐藏 JSON 输入
- 文档同步(前后端 CLAUDE.md)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 18:00:00 +08:00
吉鑫升andClaude Opus 4.8 5aa66fc07d chore(backend): 放宽递归与循环检测阈值
- build_run_config recursion_limit 100 -> 250
- LoopDetectionMiddleware 默认阈值放宽(warn/hard/window/tool-freq)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 17:48:23 +08:00
吉鑫升andClaude Opus 4.8 23d170cde1 fix(rwfx): 3q 无数据时不默认发送问题,仅「不去3q分析」才发送
问题:rwfx 进入时的 3q 预检弹框与「目的树为空自动发送第一次问题」相互独立,
导致 3q 无数据时弹框出现的同时问题已被自动发出。

修复:新增 rwfx 专用 3q 门控(rwfx-sq-gate.tsx,RwfxSqGateProvider + useRwfxSqGate),
把自动发送交给门控——
- 3q 完成/无法判定 → 立即发送;
- 3q 未完成 → 弹「前往 3qfx」框并挂起发送,仅当用户「暂不(不去3q分析)」或关闭弹框才发送;
  点「前往 3qfx」则跳转并丢弃发送。
TaskPurposePanel 自动开始改调 gateStart(onStart);手动「开始问答」/覆盖确认不受影响。
替换原独立的 RwfxSqReportGate(它弹同一个框但没门控自动发送)。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 17:48:23 +08:00
AdministratorandClaude Opus 4.8 d2be3b206d feat(y-log): 操作日志上报(前端直连 + 后端公开只读下发地址)
- 后端新增 y_log 公开只读配置:YLogConfig + AppConfig.y_log +
  GET /api/public/config/y-log,地址写在 config.yaml(mtime 热重载)
- 前端核心 src/core/log/:writeYLog(双门控/异步即发即忘/永不抛错/
  去ip-host/对象序列化裁剪/optResult恒0)+ 配置加载 + token1 隔离存取
- 登录(token)持久化 token1 并报登录、登出先报后清;启动预热配置
- 各 API client 成功路径埋点:敏感词/菜单/按钮/技能地址/轻应用、
  会商草稿+任务草稿+后台任务、智能体/定时任务/知识库、Word导出,
  以及问答完成钩子(ChatPage/AgentChatPage onFinish)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 17:46:08 +08:00
董宏凯andClaude Opus 4.8 1a2ef0a537 feat(大屏绘制): 战情大屏样式优化与脱敏全覆盖
- 去掉顶栏与「生成于」时间标签;无数据时仅显示「暂无数据」、隐藏导航与标题
- 战情各页 + 导航 Tab 文本全部脱敏(响应式取后台敏感词,避免 replaceDesensitizeMap 时序竞态)
- 全页最小字号 16px,调整行高/对齐;表格加横向滚动防溢出
- 关键事件改时间线样式(灰色虚线 + 浅红空心圆圈节点),敌情三块改单行全宽
- 应对方案渲染 Markdown;处置建议由 7 列大表改为单条卡片(字段标签改 #222222)
- 通用过滤引用角标([[1]] / 资料[[1]] / (资料[[1]]) 等,解析末尾整树清洗)
- safelist + 本页兜底 CSS 修复 border 语义色回退成灰色(时间线圆圈/FooterNote 强调条)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 12:36:36 +08:00
xu hd ce3a5b6bf9 Merge branch 'xuhd' into 'master'
feat(frontend): 来源弹窗加loading + 笔记页暗色适配 + 主题透传

See merge request knowledge-base-bj/deerflow-server!144
2026-06-23 03:28:12 +00:00
xuhdandClaude Sonnet 4.6 91a6183757 feat(notebook): 来源上传优化 + 工作室问答停止回答功能
- 上传来源后显示处理中占位卡,轮询成功后自动选中该来源
- 失败时不选中,占位卡去重(已在真实列表中则不显示)
- 输入框三态:空→无按钮,有内容→发送箭头,streaming→停止按钮

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-23 11:27:40 +08:00
g zy 076cdc746e Merge branch 'gzy' into 'master'
Gzy

See merge request knowledge-base-bj/deerflow-server!143
2026-06-23 02:57:41 +00:00
Rocky Kwok 1c2e524b28 fix: iframe页面子智能体不跳出,增加按钮 2026-06-23 10:56:51 +08:00
xuhdandClaude Sonnet 4.6 42ce20b4df feat(frontend): 来源弹窗加loading + 笔记页暗色适配 + 主题透传
- 来源上传弹窗 A系统基因库 tab 搜索时显示 loading spinner
- NetworkActor 组件初始加载时显示 loading spinner(初始状态设为 true)
- StudioNotebooksPage 笔记卡片支持暗色主题样式
- StudioNotebookDetailPage / NotebookAIWritingPage 跳转时透传 themekey 参数

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-23 10:07:13 +08:00
Rocky Kwok 1cbc0e2dd6 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into gzy 2026-06-23 09:21:01 +08:00
董宏凯andClaude Opus 4.8 fc632f26e9 feat(大屏绘制): 战情七页版式 + 对接 selectSqReport 真实数据
- 新增 dashboard-agent 独占战情多页(总览/敌情/我情/战场环境/情况判断/决心建议/处置建议),
  经 DashboardApp 的可选 pages 插槽注入,会商 Step3 大屏多页样式零影响
- 总览由六类数据聚合;六个详情页对接 selectSqReport(防御式解析,容错不抛错,
  接口为空显示「暂无数据」)
- 展示层 desensitizeDeep 脱敏 + 请求加载框;去掉所有「更多」按钮

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 22:47:43 +08:00
fengxiangdebaozi adabfa2fe3 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-22 21:03:19 +08:00
吉鑫升 ec56fa671b Merge branch 'ji'
# Conflicts:
#	CLAUDE.md
2026-06-22 21:02:35 +08:00
fengxiangdebaoziandClaude Opus 4.8 f144a59c97 fix(roundtable): xdfx-A 深链会商聊天记录按行动id隔离存储
xdfx 深链 URL ?taskId= 原始值即 actionId(登录时解析成真实任务id)。
一个任务可派生多个行动,各行动会商需互相独立,故聊天记录/后台作业
按 actionId 存取,而非解析出的真实 taskId。

新增 recordTaskIdOf(prefill)=actionId??taskId,应用到草稿 CRUD/回显
(useDraftPersistence/useRoundtableDrafts/loadLatestByTask) 与后台作业
(startJob/getJobByDraft/cancelJob/startJobKeepalive)。目的树/入库/任务
详情/底部快捷跳转栏仍用真实 taskId。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 21:01:34 +08:00
吉鑫升andClaude Opus 4.8 dd942cdd60 feat(xdfx): 行动分析聊天记录按行动id划分 + 首问追加 action_id
xdfx 单智能体问答不再按 task_id 划分聊天记录,改按「行动id(action_id)」划分:
- TaskContext 增加 partitionByAction 标记 + taskThreadMetadata 统一产出线程标签
- xdfx 新建线程额外打 metadata.actionId,对话列表按 actionId(+agent_id) 过滤
- 仍保留 metadata.taskId 以维持后端「任务深链对话全局共享」语义
- 首次提问开场信息追加「行动id(action_id)为…」
- useTaskThreads 增加 actionId 过滤参数;useChatsBase 从上下文派生
rwfx / 3qfx 行为不变。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 21:00:22 +08:00
吉鑫升andClaude Opus 4.8 fbec222eb4 Merge branch 'ji' into master
合并 ji 的功能:开放问答接口(/api/open/chat[/stream] 回传生成文件 + 临时不留存)、
技能地址管理、智能体详情「最近对话」等。
冲突 frontend StrategyRoutes.tsx 已解决:同时保留 admin/roundtable-diagnostics(master)
与 admin/skill-addresses(ji) 两个管理员路由。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 19:39:35 +08:00
吉鑫升andClaude Opus 4.8 7c55a577ad feat(open-chat): 开放问答接口回传生成文件 + 临时不留存
- /api/open/chat[/stream] 新增 include_files(默认开),把智能体在 outputs 目录
  生成的文件(name/virtual_path/encoding(text|base64)/content)随结果回传,
  解决"报告写进文件、answer 只回一段总结"导致拿不到完整内容的问题;
  既无 answer 也无文件时返回 502。
- 无状态运行标记 ephemeral:lead agent 跳过记忆与知识库中间件(不召回/不留存/
  不自动沉淀),取完文件后清理临时线程目录,做到"通过本接口的聊天记录不存储"。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 19:36:30 +08:00
董宏凯 57ffe1a706 Merge branch 'dhk-1' into 'master'
feat(layout): 简洁模式右上角加换肤 + 界面模式下拉切换

See merge request knowledge-base-bj/deerflow-server!142
2026-06-22 11:17:40 +00:00
吉鑫升andClaude Opus 4.8 06b169d7a1 feat(skill-addresses): 新增技能地址修改记录,支持单次记录回退
后端:
- 每次「应用」写一份 {id}.manifest.json(记录本次 from→to 替换明细/文件数/处数),
  放在备份目录的同级,避免被回退误恢复或计入文件数
- GET /backups 返回每条记录的 replaced_total + replacements;POST /rollback/{id} 回退单条

前端:
- 把「撤销上次」升级为「修改记录」面板:每条显示时间/改了哪些地址/文件数,
  带「回退此次」(二次确认);应用后自动展开
- BackupEntry 类型扩展 replacedTotal + replacements

同步更新前后端 CLAUDE.md。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 18:05:05 +08:00
吉鑫升andClaude Opus 4.8 7487395e44 feat(skill-addresses): 地址检索升级为多关键词匹配
- 空格分隔多个关键词,全部命中(地址或技能名任一包含)才显示,便于在大量地址中收窄
- 搜索框加清除按钮 + 更清晰的占位提示
- 过滤时列表头显示「命中 / 总数」

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 17:55:44 +08:00
吉鑫升andClaude Opus 4.8 26557b30a0 feat(skill-addresses): 将「技能地址管理」并入管理员「技能管理」页的标签页
- SkillAddressesPage 主体抽成可复用的 SkillAddressesPanel(默认导出保留旧路由作直链回退)
- AdminSkillsPage 顶部加 Tabs:技能列表 + 技能地址管理(嵌入 panel)
- 移除 page-sidebar 左下角设置下拉里两处独立的「技能地址管理」入口
- 同步更新前后端 CLAUDE.md 文档

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 17:35:42 +08:00
吉鑫升andClaude Opus 4.8 f8228847ab fix(skill-addresses): 补提交被 gitignore 漏掉的 address_scan 引擎模块
skills/ 忽略规则误伤了 packages/harness/deerflow/skills/address_scan.py,
导致部署环境缺模块、启动报 ModuleNotFoundError: deerflow.skills.address_scan。
强制纳入跟踪。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 17:29:10 +08:00
吉鑫升andClaude Opus 4.8 6b480fdbe9 feat: 新增技能地址管理与开放问答接口,完善任务工作区
- 新增「技能地址管理」页面与 /api/skill-addresses 路由(扫描/预览/批量替换技能内地址)
- 完善 /api/open/chat 开放问答接口与模型工厂、网关配置
- 调整任务工作区、侧边栏与路由
- 将本地 0622/ 临时目录与 __pycache__/ 加入忽略,不提交

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 17:17:54 +08:00
fengxiangdebaoziandClaude Opus 4.8 0a456e9146 feat(ai-writing): 后台挂起改为即时返回,乐观标记历史「挂起中」
点击「转后台」后立刻 reset 回初始页,挂起请求 fire-and-forget;
历史下拉靠 markBackground/clearBackground 乐观标记马上显示「挂起中」,
不等后端确认,与「多智能体会商」交互一致。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 17:07:53 +08:00
fengxiangdebaoziandClaude Opus 4.8 b59cbd51d9 feat(ai-writing): 各阶段模型调用自动容错,失败时换下一个模型继续
参考多智能体会商的容错思路:意图解析/大纲/正文/审核四个 LLM
环节失败时,按 config.yaml models 顺序换下一个模型重跑该环节,
并通过 model_switch 事件在前端时间线提示「『X』模型<原因>,
已自动切换到『Y』继续」。正文逐章节、审核逐维度独立切换,
已生成的章节/维度保留;意图解析成功的模型还会写回 state
供下游阶段沿用,避免每阶段重复经历同一次失败。

- nodes/_model_fallback.py: 候选模型链 + 异常分类 + model_switch
  事件构造(沿用 ROUNDTABLE_MODEL_FALLBACK[_MAX] env 开关)
- intent_parser/writer_outline/writer_draft/editor: 失败循环换模型
- 前端 types/reducer/timeline: 新增 model_switch 事件类型,按
  stage 复位对应流式缓冲并以 amber 系统提示渲染

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 17:07:53 +08:00
fengxiangdebaoziandClaude Opus 4.8 23743ee193 chore: 精简 AI 写作示例文案
ai-writing 表单/检索/欢迎页的占位与示例改为通用文案。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 17:07:53 +08:00
董宏凯andClaude Opus 4.8 7748661963 feat(roundtable): 历史卡片显示所用业务链(自由模式) + 诊断只收报错日志
- 历史「分析记录」卡片/侧边栏列表:把「第X步」改为本次会商所用业务链名,
  无链条显示「自由模式」。后端 list 轻量 meta 从 step2 正则抽取 chain_title
  (不整体解析大块 JSON),个人草稿 + task 草稿两个 store 都覆盖。
- 会商诊断改为只收集报错日志:record_diagnostic 写库前丢弃 level==info
  运行日志(begin/consensus/gather/job_started),只留 warning/error。
  单点收口覆盖前台/后台/recorder 全部写路径;诊断页标题改「会商报错日志」。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 16:36:31 +08:00
fengxiangdebaoziandClaude Opus 4.8 e28277b21b feat(layout): 全量模式右上角也加界面模式切换
复用 appearance-controls 的 LayoutModeSwitcher,Header 操作区在换肤旁
补上界面模式下拉,与简洁模式右上角保持一致。LayoutModeSwitcher 新增
fallback 属性指明 mode 未设置时的兜底界面(Header 传 full,ChatPage 传 compact)。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 15:43:55 +08:00
吉鑫升andClaude Opus 4.8 32476c7ad4 feat: 智能体详情新增「最近对话」列表,完善推荐问题与任务深链配置
- 新增 AgentRecentChats 组件,在智能体详情面板底部按 agent_id 展示最近对话
- 调整问答/智能体侧边栏与最近对话列表展示逻辑
- 补充 dashboard-input、task-deeplink 相关配置与线程工具方法
- 后端推荐问题接口标签处理及 position_sync 微调,新增相关测试

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 14:47:43 +08:00
吉鑫升andClaude Opus 4.8 16ba5deb0e feat(agents): 智能体归属/发布操作前增加「账号已切换」提醒
- 新增 useLiveAccount 钩子:跟踪「实时」登录账号(随 storage/focus 刷新),
  并与组件挂载时捕获的账号对比;token 存 localStorage 会被同浏览器其他标签页
  共享,另一标签页登录会静默替换本页 API 所用账号
- agent-card / agent-detail-panel / publish-square-picker-dialog / NewAgentPage
  接入该钩子,切换账号后对归属/发布类操作做提醒,避免误归属

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 11:30:15 +08:00
吉鑫升andClaude Opus 4.8 2b6424b3ff feat(open-chat): 新增 /api/open/chat 开放问答接口
- 无需登录(/api/open/ 加入 auth 白名单 + CSRF 豁免),供外部系统直接调用本项目智能体做问答
- 可指定模型(model_name)与智能体(agent_name 中文名称,扫描 agents/*/config.yaml 解析为运行 id);GET /api/open/agents 列出可选名称
- 只返回最终结果(answer = 最后一段 markdown),不含中间过程/工具调用
- 可靠关闭思考:thinking_enabled=false 时下发 thinking_force_disabled,经 create_chat_model(force_disable_thinking=True) 强制注入 enable_thinking=false(及 GLM thinking.type=disabled),覆盖只声明 supports_thinking 的内网 vLLM/Qwen 模型(与生成标题关思考一致)
- 一次性问答设 is_scheduled_run 跳过自动起标题

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 11:21:56 +08:00
fengxiangdebaoziandClaude Opus 4.8 79f1a004a0 feat(layout): 简洁模式右上角加换肤 + 界面模式下拉切换
抽出共享 appearance-controls(ThemeSwitcher 按 tone 适配 banner/content
配色,新增图标+下拉的 LayoutModeSwitcher);Header 复用换肤组件,简洁模式
ChatPage 顶栏右上角补上换肤与界面模式切换,与全量模式保持一致。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 11:02:51 +08:00
fengxiangdebaozi 548cfd1719 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-06-22 10:47:15 +08:00
fengxiangdebaozi 7d32b41e90 加载框样式 2026-06-22 10:46:57 +08:00
1860 changed files with 250000 additions and 153038 deletions

No files matched your search

+20
View File
@@ -0,0 +1,20 @@
import os
import paramiko
client = paramiko.SSHClient()
client.set_missing_host_key_policy(paramiko.AutoAddPolicy())
client.connect(
"119.254.86.251",
port=22322,
username="root",
password=os.environ["TARGET_SSH_PASSWORD"],
timeout=15,
auth_timeout=15,
banner_timeout=15,
)
_, stdout, stderr = client.exec_command(os.environ["TARGET_SSH_COMMAND"], timeout=30)
print(stdout.read().decode(errors="replace"), end="")
print(stderr.read().decode(errors="replace"), end="")
client.close()
+35
View File
@@ -0,0 +1,35 @@
# Never send source-control history, local dependencies, runtime state, or
# credentials to the Docker daemon. The offline images are built from the
# repository root by deploy/1panel-offline/Dockerfile.*.
.git
.runtime
.history
tmp
dist
# Credentials and environment-specific configuration are supplied at runtime
# through the offline delivery package, never copied into an image layer.
**/.env
**/.env.*
offline-backend-20260512/backend/.deer-flow
offline-backend-20260512/backend/logs
offline-backend-20260512/backend/docker-data
offline-backend-20260512/backend/dist
offline-backend-20260512/backend/wheelhouse
offline-backend-20260512/backend/offline-wheels
offline-backend-20260512/backend/.venv
offline-backend-20260512/backend/.pytest_cache
offline-backend-20260512/backend/.ruff_cache
# Reproducibly install frontend dependencies inside the image instead.
frontend-web/node_modules
frontend-web/dist
frontend-web/.vite
frontend-web/.offline-pack-build
frontend-web/.offline-extract-test
frontend-web/node_modules-offline-*.tar.gz
# Editor and operating-system metadata.
**/__pycache__
**/*.py[cod]
**/.DS_Store
+58 -4
View File
@@ -1,5 +1,9 @@
# Workspace/editor
.vscode/
.vscode/*
!.vscode/launch.json
!.vscode/tasks.json
!.vscode/extensions.json
!.vscode/settings.json
frontend-web/.vscode/
node_modules/
# Claude Code local-only settings (per-user permissions, not shared)
@@ -53,6 +57,7 @@ offline-backend-20260505/bundle/stop_backend.sh
# offline-backend-20260512 runtime artifacts (large files, local config, data)
offline-backend-20260512/.env.example
offline-backend-20260512/.env
offline-backend-20260512/DEPLOY_BACKEND_OFFLINE_ZH.md
offline-backend-20260512/SHA256SUMS
offline-backend-20260512/config.yaml.example
@@ -64,6 +69,8 @@ offline-backend-20260512/wheelhouse/
offline-backend-20260512/backend/.deer-flow/data/*.db
offline-backend-20260512/backend/.deer-flow/data/*.db-*
offline-backend-20260512/backend/.deer-flow/*
offline-backend-20260512/backend/.env
offline-backend-20260512/backend/.env.local
offline-backend-20260512/start_backend.sh
offline-backend-20260512/stop_backend.sh
offline-backend-20260512/check_backend.sh
@@ -80,8 +87,39 @@ offline-backend-20260512/backend/skill_evolution.json
skills/
hermes-agent-main/
.gitignore
offline-backend-20260512/backend/tests/*
deploy
offline-backend-20260512/backend/tests/*
!offline-backend-20260512/backend/tests/test_llmwiki_weknora.py
!offline-backend-20260512/backend/tests/test_health_auth_bypass.py
# Keep formal Word OOXML and embedded-font regression coverage versioned.
!offline-backend-20260512/backend/tests/test_word_export.py
# Keep the model configuration regression coverage versioned even though
# this deployment repository otherwise ignores newly added backend tests.
!offline-backend-20260512/backend/tests/test_model_management.py
# Keep the forced-research agent runtime gate and sandbox-policy regressions versioned.
!offline-backend-20260512/backend/tests/test_forced_research_agent.py
# Keep fixed-question exact-match and streaming regression coverage versioned.
!offline-backend-20260512/backend/tests/test_fixed_questions.py
# Keep configurable es_query system-prompt routing regression coverage versioned.
!offline-backend-20260512/backend/tests/test_es_query_routing_prompt.py
# Keep the local LLMWiki vector-index and external API regression coverage versioned.
!offline-backend-20260512/backend/tests/test_llmwiki_local_index_repository.py
!offline-backend-20260512/backend/tests/test_llmwiki_vector_search.py
!offline-backend-20260512/backend/tests/test_llmwiki_wiki_sync.py
!offline-backend-20260512/backend/tests/test_external_llmwiki_search.py
!offline-backend-20260512/backend/tests/test_llmwiki_wiki_retrieval.py
!offline-backend-20260512/backend/tests/test_public_llmwiki_embed.py
# Deep-research reliability regression coverage.
!offline-backend-20260512/backend/tests/test_deep_research_persistence.py
!offline-backend-20260512/backend/tests/test_deep_research_event_sink.py
!offline-backend-20260512/backend/tests/test_deep_research_executor_reliability.py
!offline-backend-20260512/backend/tests/test_deep_research_start_job.py
!offline-backend-20260512/backend/tests/test_summarization_human_message.py
!offline-backend-20260512/backend/tests/test_compact_menu_overrides.py
# Independent enterprise-research persistence, HTTP and race regressions.
!offline-backend-20260512/backend/tests/test_enterprise_research_tasks.py
# Position-roundtable per-turn write/present cap (weak-model duplicate artifacts).
!offline-backend-20260512/backend/tests/test_position_artifact_cap.py
deploy
.history
# Cloned third-party repos (local only)
@@ -93,6 +131,16 @@ git-clone/
# Frontend offline pack working directories
frontend-web/.offline-pack-build/
frontend-web/.offline-extract-test/
frontend-web-node_modules-offline-*.tar.gz
# Local dependency caches and backend scratch archives
/.pnpm-store/
/offline-backend-20260512/backend/backend*.zip
# Local offline bundles and scratch tooling
/*.tar.gz
/offline-backend-20260512/*.zip
/tmp/
.codegraph
codegraph.mdc
@@ -105,5 +153,11 @@ docs/backups
# uv lockfile (not tracked per project preference)
offline-backend-20260512/backend/uv.lock
# Local-only scratch directory (not committed)
0622/
# Python bytecode cache
__pycache__/
# misc
.DS_Store
.DS_Store
+6
View File
@@ -0,0 +1,6 @@
{
"recommendations": [
"ms-python.python",
"ms-python.debugpy"
]
}
+66
View File
@@ -0,0 +1,66 @@
{
"version": "0.2.0",
"configurations": [
{
"name": "DeerFlow: Backend FastAPI (8001)",
"type": "debugpy",
"request": "launch",
"module": "uvicorn",
"args": [
"app.gateway.app:app",
"--host",
"0.0.0.0",
"--port",
"8001"
],
"cwd": "${workspaceFolder}/offline-backend-20260512/backend",
"python": "${workspaceFolder}/offline-backend-20260512/backend/.venv/Scripts/python.exe",
"envFile": "${workspaceFolder}/offline-backend-20260512/.env",
"env": {
"PYTHONPATH": "${workspaceFolder}/offline-backend-20260512/backend;${workspaceFolder}/offline-backend-20260512/backend/.deer-flow/python-vendor",
"GATEWAY_CORS_ORIGINS": "http://localhost:5174,http://127.0.0.1:5174,http://localhost:8080,http://127.0.0.1:8080",
"UV_LINK_MODE": "copy",
"WEKNORA_ADMIN_PASSWORD": "1qaz@WSX"
},
"console": "integratedTerminal",
"redirectOutput": true,
"justMyCode": false,
"subProcess": true
},
{
"name": "DeerFlow: Frontend Vite (5174)",
"type": "node-terminal",
"request": "launch",
"command": "npm.cmd run dev -- --host 0.0.0.0 --port 5174",
"cwd": "${workspaceFolder}/frontend-web",
"env": {
"VITE_BACKEND_BASE_URL": "http://127.0.0.1:8001",
"VITE_LANGGRAPH_BASE_URL": "http://127.0.0.1:8001/api"
},
"serverReadyAction": {
"pattern": "Local:\\s+(https?://[^\\s]+)",
"uriFormat": "%s",
"action": "openExternally"
}
},
{
"name": "DeerFlow: Open Frontend in Chrome",
"type": "node-terminal",
"request": "launch",
"preLaunchTask": "DeerFlow: VS Code Start",
"command": "powershell.exe -NoProfile -ExecutionPolicy Bypass -Command \"Start-Process 'http://127.0.0.1:5174/'\"",
"cwd": "${workspaceFolder}"
}
],
"compounds": [
{
"name": "DeerFlow: Full Stack (Backend + Frontend)",
"preLaunchTask": "DeerFlow: Stop Full Stack",
"configurations": [
"DeerFlow: Backend FastAPI (8001)",
"DeerFlow: Frontend Vite (5174)"
],
"stopAll": true
}
]
}
+6
View File
@@ -0,0 +1,6 @@
{
"python.defaultInterpreterPath": "${workspaceFolder}/offline-backend-20260512/backend/.venv/Scripts/python.exe",
"python.terminal.activateEnvironment": true,
"typescript.tsdk": "frontend-web/node_modules/typescript/lib",
"npm.packageManager": "npm"
}
+175
View File
@@ -0,0 +1,175 @@
{
"version": "2.0.0",
"tasks": [
{
"label": "DeerFlow: VS Code Start",
"type": "process",
"command": "powershell.exe",
"args": [
"-NoProfile",
"-ExecutionPolicy",
"Bypass",
"-File",
"${workspaceFolder}/scripts/vscode-start.ps1",
"-OpenBrowser"
],
"group": {
"kind": "build",
"isDefault": true
},
"presentation": {
"reveal": "always",
"panel": "dedicated",
"clear": true
},
"problemMatcher": []
},
{
"label": "DeerFlow: Start Full Stack and Wait",
"type": "process",
"command": "powershell.exe",
"args": [
"-NoProfile",
"-ExecutionPolicy",
"Bypass",
"-File",
"${workspaceFolder}/scripts/start-all-and-wait-frontend.ps1"
],
"problemMatcher": []
},
{
"label": "DeerFlow: Start Full Stack",
"type": "process",
"command": "powershell.exe",
"args": [
"-NoProfile",
"-ExecutionPolicy",
"Bypass",
"-File",
"${workspaceFolder}/scripts/start-all.ps1"
],
"problemMatcher": []
},
{
"label": "DeerFlow: Stop Full Stack",
"type": "process",
"command": "powershell.exe",
"args": [
"-NoProfile",
"-ExecutionPolicy",
"Bypass",
"-File",
"${workspaceFolder}/scripts/stop-all.ps1"
],
"problemMatcher": []
},
{
"label": "DeerFlow: Status",
"type": "process",
"command": "powershell.exe",
"args": [
"-NoProfile",
"-ExecutionPolicy",
"Bypass",
"-File",
"${workspaceFolder}/scripts/status.ps1"
],
"problemMatcher": []
},
{
"label": "DeerFlow: Check Local Dev Environment",
"type": "shell",
"command": "$backendPython = '${workspaceFolder}\\offline-backend-20260512\\backend\\.venv\\Scripts\\python.exe'; if (-not (Test-Path -LiteralPath $backendPython)) { throw 'Backend virtual environment is missing. Run uv sync in offline-backend-20260512/backend first.' }; & $backendPython -c \"import uvicorn; print('Backend Python OK')\"; npm --prefix '${workspaceFolder}\\frontend-web' exec vite -- --version",
"options": {
"shell": {
"executable": "powershell.exe",
"args": [
"-NoProfile",
"-ExecutionPolicy",
"Bypass",
"-Command"
]
}
},
"problemMatcher": []
},
{
"label": "DeerFlow: Install Frontend Dependencies",
"type": "process",
"command": "npm",
"args": [
"ci",
"--no-audit",
"--no-fund"
],
"options": {
"cwd": "${workspaceFolder}/frontend-web"
},
"problemMatcher": []
},
{
"label": "DeerFlow: Frontend Typecheck",
"type": "process",
"command": "npm",
"args": [
"run",
"typecheck"
],
"options": {
"cwd": "${workspaceFolder}/frontend-web"
},
"problemMatcher": "$tsc"
},
{
"label": "DeerFlow: Frontend Build",
"type": "process",
"command": "npm",
"args": [
"run",
"build"
],
"options": {
"cwd": "${workspaceFolder}/frontend-web"
},
"problemMatcher": []
},
{
"label": "DeerFlow: Backend Tests",
"type": "process",
"command": "${workspaceFolder}/offline-backend-20260512/backend/.venv/Scripts/python.exe",
"args": [
"-m",
"pytest",
"tests/",
"-v"
],
"options": {
"cwd": "${workspaceFolder}/offline-backend-20260512/backend",
"env": {
"PYTHONPATH": ".",
"WEKNORA_ADMIN_PASSWORD": "1qaz@WSX"
}
},
"problemMatcher": []
},
{
"label": "DeerFlow: WeKnora Backend Tests",
"type": "process",
"command": "${workspaceFolder}/offline-backend-20260512/backend/.venv/Scripts/python.exe",
"args": [
"-m",
"pytest",
"tests/test_llmwiki_weknora.py",
"-v"
],
"options": {
"cwd": "${workspaceFolder}/offline-backend-20260512/backend",
"env": {
"PYTHONPATH": ".",
"WEKNORA_ADMIN_PASSWORD": "1qaz@WSX"
}
},
"problemMatcher": []
}
]
}
@@ -0,0 +1,61 @@
# 深度研究第三轮:检索稳定性修复 + 参考文献确定性 + 页面对齐 AI 写作改造
## A. 两个 bug 的排查结论与修复
### A1. 第二次检索「网络波动」——确认是真问题(DDG 限流 + 错误语义混淆 + 零重试)
**排查结论**(用户判断"确实是网络波动"基本正确,但代码层面放大了它):
- 「网络波动」文案不存在于任何代码中——是收集员 LLM 看到 `{"error": "No results found"}` 信封后自己编的解释
- 真实根因:DDG html 端点对同 IP 快速连续请求限流(403/429 挑战页)→ `DDGSException` → `ddg_search/tools.py::_search_text` 把异常吞成 `[]` → 上层把「被限流」和「真没结果」混成同一个错误信封;工具层完全没有重试
**修复**(`packages/harness/deerflow/community/ddg_search/tools.py`):
1. `_search_text` 对异常加 2 次重试 + 指数退避(约 1.5s / 3s + 抖动)
2. 错误信封区分场景:真无结果 → `no results`;多次尝试仍失败 → `web search failed after N attempts (rate limited or network), 换一组检索词稍后重试`——让模型不再瞎猜「网络波动」
3. 收集员 SOUL.md 行为准则加一条(同步改种子资产 + 已安装副本 `.deer-flow/agents/deep-research-collector/`):搜索返回 error 信封时先换检索词重试一轮,而不是直接告知用户网络异常
### A2. 参考文献缺失——代码确有隐患(当前是模型自发行为,时有时无)
**排查结论**:后端没有任何「参考来源」追加逻辑;四个 runner 的报告 prompt 只要求内联 `[N]` 引用。出现过的参考列表是模型看到上下文头 `[N] 标题(URL)` 后**自发**补写的——弱模型下不可靠,与"信息够不够"无必然关系。
**修复**(prompt 指示 + 确定性兜底双保险):
1. 四个 runner(basic / detailed / deep / multi_agent)的报告 prompt 各加一条:报告最后附「## 参考来源」,按 `[N] 标题. URL` 列出正文实际引用过的来源
2. `basic.py` 新增共享函数 `ensure_reference_section(report, context_list, materials)`:报告缺少参考小节时,解析正文引用的 `[N]` 编号,按压缩上下文顺序生成编号列表追加(无编号时列全部来源,封顶 20 条;已有参考小节则不重复追加)。在各 runner 最终 `write_text("report.md", ...)` 前调用(约 7 个调用点,跳过零材料 fallback)
3. 新增测试 `tests/test_deep_research_references.py`:helper 单测(正常追加/编号映射/不重复追加/无 URL 来源)+ runner 集成断言
## B. 页面改造(核心需求):左列复用 AI 写作对话形态,右列改真沙箱
### B1. 左列 = AI 写作式对话收集面板(仿 WritingSetupChat)
- **空状态欢迎屏**(无消息时隐藏头部,展示欢迎卡片,WritingWelcome 式)+ 有消息后 `MessageList`(沿用现有绑 collector 线程的接线)+ 首 token 前「正在整理…」占位条
- **输入框换成白卡片 PromptInput 套件**(与 AI 写作完全同款组件):卡片内一行「当前对话模型」Select(沿用 ModelNameSelect)+ 高级配置入口;下方 PromptInputTextarea + PromptInputFooter + PromptInputSubmit(`status` ready/streaming,流式中变停止按钮)。经典模式入口保留在高级配置对话框
- **配置卡片进对话流**(对标 AI 写作「识别出意图后出现表单」):
- `message-list.tsx` 最小扩展(约 15 行):新增分组 `assistant:research-approval`(识别 `additional_kwargs.setup_research_approval`)+ 可选 prop `researchApprovalSlot?: ReactNode`;不传 slot 或无该载荷时零行为变化——普通对话/AI 写作完全不受影响
- workbench:收集回合结束(awaiting_report,即"意图识别完成")时向 `displayThread` 尾部注入一条虚拟 ai 消息(WritingSetupChat 的 displayThread 同款手法),slot 传现有 `ReportConfigCard` → 卡片作为助手下一轮出现在对话流里
- 写作进度卡、完成卡、摘要气泡、追问列表保留在列表下方卡片区(报告正文移到右侧沙箱)
### B2. 右列 = 工作区真沙箱(Step2SandboxLayout 的 stub 线程模式)
- 新建 `deep-research/ResearchSandboxPanel.tsx`(约 100 行,含关闭/重开)+ `useReportSandbox.ts` hook(仿 `useStep3Report` 的 stub 机制):
- threadStub:`messages = [{type:'ai', tool_calls:[{name:'write_file', args:{path:'/mnt/user-data/outputs/report.md', content: <流式报告>}}]}]`,`isLoading = job 运行中 && phase !== 'summarizing'`
- `report_delta` 首帧 → `openArtifact(write-file: 虚拟URL)` 自动展开右栏;`run.report` 每帧 upsert stub(带防抹空守卫);刷新/切换会话用 `session.reportMarkdown` 重建
- `ArtifactFileDetail` 自带能力全部免费获得:**流式期 code 视图自动滚底 → 报告写完 isLoading 翻 false 自动切 preview + 脉冲提示**(正是「生成完直接切预览」)、Streamdown 渲染的 Markdown(比现在的好看)、另存 Word/复制/下载、默认走展示层脱敏
- 布局:ResizablePanelGroup chat 60 / sandbox 40(对齐 ChatBox/圆桌),沙箱可关闭、头部按钮重开
- **删除自定义 `ResearchSandbox` 组件**;legacy 会话与经典模式共用同一右栏(`run.report` 数据源相同,行为一致)
- 已知小限制(可接受):报告配图模式下沙箱内图片可能无法经 artifacts API 解析(配图默认关闭;真需要时后续把产物落 thread artifacts)
### B3. 验证
- 后端:`PYTHONPATH=. uv run --no-sync pytest tests/ -k deep_research -q --ignore=tests/test_notification_templates.py` 全绿 + ruff;改完配置/SOUL 后 touch 触发 dev 服务重载
- 前端:`pnpm typecheck` 零新增错误(基线 51)
- 手动走查:连续两次检索不再误报、弱模型报告末尾必带参考来源、页面全流程(欢迎屏 → 对话收集 → 流内配置卡 → 沙箱流式 → 自动预览 → 摘要/追问)
## 涉及文件
**后端**:`community/ddg_search/tools.py`、`deep_research/runners/{basic,detailed,deep,multi_agent}.py`、收集员 SOUL.md(种子 + 已安装副本)、`tests/test_deep_research_references.py`(新)
**前端**:`components/workspace/messages/message-list.tsx`(可选 slot 分组)、`pages/deep-research/DeepResearchWorkbench.tsx`(大改)、`pages/deep-research/ResearchSandboxPanel.tsx`(新)、`pages/deep-research/useReportSandbox.ts`(新)
## 明确不动
- AI 写作 / 普通对话现有组件行为(message-list.tsx 仅加可选分组,缺省零变化)
- 报告写作管线的写作逻辑本身(prompt 加一条要求 + 末尾确定性追加参考小节,均为附加式)
- 深度研究后端会话/任务/事件模型(本轮不动)
+114
View File
@@ -0,0 +1,114 @@
# AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
## Project Overview
This is a customized offline deployment of **DeerFlow** — a LangGraph-based AI super agent platform. The repo contains two sub-projects:
- `offline-backend-20260512/backend/` — Python backend (FastAPI Gateway + LangGraph agent runtime)
- `frontend-web/` — Vite + React 19 frontend (TypeScript, pnpm)
Managed together via shell scripts in `scripts/`.
## Offline Release Repository
Linux AMD64 离线发版脚本、wheelhouse、`deploy.env` 模板和部署文档统一维护在
`knowledge-base-bj/deerflow-offline-deployment`,不要把离线镜像或发版资产提交到
本业务源码仓库。正式发版从该仓库执行 `scripts/build-latest-master.sh`,脚本会读取
本仓库最新 `master` 的干净源码快照。
## Commands
### Full Application (from repo root)
```bash
./scripts/start-all.sh # Start backend + frontend as background daemons
./scripts/stop-all.sh # Stop both
./scripts/restart-all.sh # Restart both
./scripts/status.sh # Check running status
```
Logs and PID files are written to `.runtime/logs/` and `.runtime/pids/`.
### Backend Only (from `offline-backend-20260512/backend/`)
```bash
make install # Install Python dependencies (uv)
make dev # Run Gateway API with hot-reload on port 8001
make gateway # Run Gateway API without reload
make test # Run all tests: PYTHONPATH=. uv run pytest tests/ -v
make lint # Lint with ruff
make format # Format with ruff
```
Run a single test file:
```bash
PYTHONPATH=. uv run pytest tests/test_<feature>.py -v
```
### Frontend Only (from `frontend-web/`)
```bash
pnpm install # Install dependencies
pnpm dev # Start Vite dev server on port 5174
pnpm build # Production build
pnpm typecheck # TypeScript type checking (tsc --noEmit)
```
## Service Ports
| Service | Port | Notes |
|---------|------|-------|
| Backend (Gateway API) | 8001 | FastAPI + LangGraph runtime |
| Frontend (Vite) | 5174 | React SPA |
Frontend connects to backend via env vars `VITE_BACKEND_BASE_URL` and `VITE_LANGGRAPH_BASE_URL` (injected by `scripts/start-frontend.sh`).
## Architecture
### Backend
The backend (`offline-backend-20260512/backend/`) is split into two layers:
- **`packages/harness/deerflow/`** — publishable agent framework (`deerflow.*` imports): LangGraph lead agent, middleware chain, sandbox, tools, MCP, memory, models, skills. **Never imports from `app.*`.**
- **`app/`** — application layer (`app.*` imports): FastAPI Gateway routers, IM channel integrations (Feishu, Slack, Telegram, DingTalk).
The **Lead Agent** (`deerflow/agents/lead_agent/`) is the single LangGraph graph entry point. It wraps a middleware chain (~18 middlewares assembled in strict order) around LLM calls, handling: thread isolation, sandbox lifecycle, uploads, memory, plan mode, vision, subagent delegation, and loop detection.
**Middleware order matters** — middlewares are appended in a fixed sequence; `ClarificationMiddleware` must always be last. See `offline-backend-20260512/backend/AGENTS.md` for the full ordered list.
**Harness → App import firewall** is enforced by `tests/test_harness_boundary.py` (runs in CI).
### Frontend
The frontend (`frontend-web/`) is a React 19 + Vite SPA:
- **Routing**: React Router v7; top-level routes in `src/pages/PageRoutes.tsx`, workspace sub-routes in `src/pages/WorkspaceRoutes.tsx`
- **Pages**: `ChatPage` (thread chat), `AgentChatPage` (custom agent chat), `AgentsPage`/`NewAgentPage` (agent management), `ScheduledTasksPage`/`ScheduledTaskRunDetailPage` (scheduled tasks), `LightAppManagementPage`/`LightAppListPage`/`LightAppIframeView` (轻应用中心 — register/list/embed mini-apps)
- **AI 写作·对话版(对话驱动写作台)**: a **parallel new entry** beside the classic AI-writing page (classic page/routes untouched) — route `/page/canvas/ai-writing-chat`, sidebar 「问答管理 → 课题研究(对话版)」. Page `open-canvas/pages/AIWritingChatPage.tsx` reuses the engine (`AIWritingContext` + `useStream` + `AIWritingDraftPanel`); **idle keeps the classic setup layout** (`WritingSetupChat` + collapsible form) and switches to the chat workbench once writing starts; left panel `components/ai-writing-chat/WritingChatPanel.tsx` = **unified chronological feed** (`ChatFlowTimeline.tsx`, chat bubbles anchor-interleaved into the progress timeline so triggered events render below the user's message) + button-only intervention cards (`ChatInterventionCards.tsx`, inline textareas removed) + bottom unified smart composer. Intent resolution: frontend fast path + `POST /api/ai-writing/sessions/{id}/intent` → `deerflow/agents/ai_writing/intent_router.py` (per-pause action whitelist, high-cost confidence gates, payload cleaning); supports QA bypass, clarify follow-ups, control intents, and material-stage auto re-search + pending-intent resume. Tests `tests/test_ai_writing_intent.py`; plan doc `frontend-web/docs/ai-writing-对话驱动写作台-实现方案.md`.
- **轻应用中心 (Light App Center)**: a sibling of 任务管理 in the sidebar with two pages — 应用管理 (admin registers `window_open` or `iframe` mini-apps with a route-param builder: login params resolved from `localStorage.userInfo`, theme params literal) and 应用列表 (card grid of `window_open` apps, `window.open` launch). `iframe` apps are mounted under a chosen parent menu (XK/PG/TY/综合管理) and **dynamically injected into the sidebar** by `core/page-layout/use-sidebar-menu.ts` (`useSidebarMenuItems`), opening in the `LightAppIframeView` host. Client + React Query hooks in `strategy-components/api/light-apps.ts`; URL builder/constants in `strategy-components/lib/light-app.ts`. Backend: `/api/light-apps` (global/shared, admin-gated writes).
- **菜单管理 (Menu Management, admin-only)**: an **overlay** over the static sidebar menu — `MenuManagementPage` (`pages/MenuManagementPage.tsx`, route `/page/strategy/admin/menu-management`, opened from the admin-only 「菜单管理」 item in the **bottom-left settings dropdown** of `components/page-sidebar.tsx`). Admins rename / 停用·启用 / reorder (↑↓ or @dnd-kit drag) / re-parent (horizontal drag **or** the edit dialog's 「移动到」parent selector) any node across 一级/二级/三级, **including injected iframe light-app nodes** (`light-app-<appId>`). The static tree (`core/page-layout/sidebar-menu.ts`) stays the source of icons/routes; only per-node deltas (`label`/`disabled`/`parentId`/`sortOrder`) persist to the backend. Merge logic in `core/page-layout/menu-overrides.ts` (`applyMenuOverrides`, applied in `use-sidebar-menu.ts` after light-app injection, before role filter; disabling a node hides its whole subtree) — strict **3-level cap** (`wouldExceedDepth`). Client `strategy-components/api/menu-overrides.ts`. Backend: `/api/menu-overrides` (global/shared; open read, admin atomic replace-all). **简介模式** uses a separate overlay: every compact workspace menu item can be placed in `sidebar`(左侧菜单)、`settings`(设置和更多)or `toolbox`(右侧工具箱); `CompactToolbox` (`components/workspace/compact-toolbox.tsx`, mounted by `PageRoutes.tsx`) opens only when the square right-edge trigger is clicked, then slides a compact, content-height right-side drawer over a backdrop above global dropdowns; configured items render top-to-bottom as centered square cards with a large icon above the label while the effective layout is compact. `/api/compact-menu-overrides` stores two independent sets (type `A` / `B`); each website picks one via `runtime-config.js` `VITE_COMPACT_MENU_TYPE`.
- **舆情分析智能体(前端虚拟智能体)**: 智能体管理页新增「舆情分析」类型 tab,固定一张虚拟智能体卡片(名称/简介可编辑,存 localStorage)。对话页 `pages/SentimentAgentChatPage.tsx`(路由 `agents/sentiment-analysis/chats/:thread_id`)复用普通问答布局 + `MessageList`,**输入框只有发送按钮**;问答经 Gateway `POST /api/sentiment-agent/stream` 转发外部 AG-UI 网关(不经过 LangGraph),会话仅存 sessionStorage。接口地址 + Basic Auth 在 `runtime-config.js` 配置(`VITE_SENTIMENT_AGENT_API_URL` / `_AUTH_USERNAME` / `_AUTH_PASSWORD`)并随请求传给后台;后台按传入地址转发、关闭 TLS 校验,失败时把完整错误回传。核心模块 `src/core/sentiment-agent/`。
- **简洁模式用户引导 (Compact-mode onboarding tour)**: 简洁模式(外观设置的「全量/简洁」= compact,无全局导航栏 + 页面侧边栏)新增 TDesign React `Guide` 组件驱动的分步引导。组件 `components/workspace/compact-mode-guide.tsx`(挂在 `ChatPage`):9 步 —— 欢迎弹窗(dialog 模式)→ 左侧功能导航 → 聊天记录 → 设置和更多 → 换肤 → 界面模式(切回全量)→ 常用提示词栏 → 提示词管理弹窗 → 输入框;高亮目标由各组件上的 `data-compact-guide` 标记定位(`workspace-nav-chat-list` / `recent-chat-list` / `workspace-nav-menu` / `appearance-controls` / `custom-prompt-menu.tsx` 的 `CustomPromptBar`(提示词栏,仅新对话落地态渲染)与其 `ManagePromptsDialog`(`prompt-dialog` 锚点)/ ChatPage 输入框容器),**启动时按目标是否存在过滤步骤**(如新用户无聊天记录、侧栏收起时自动剔除该步 —— Guide 对缺失元素会抛错,不能盲传)。**提示词管理弹窗步骤是动态目标**:弹窗平时不渲染,引导切到该步前先广播 `PROMPT_DIALOG_GUIDE_EVENT`(`custom-prompt-menu.tsx` 导出)让 `CustomPromptBar` 打开 `ManagePromptsDialog` 并**接管**(`owner: true` 期间 ESC/点遮罩不关闭,防止高亮目标消失导致 Guide 报错),轮询锚点真正挂载后才切步;离开该步 / 跳过 / 完成 / 中途卸载时以 `owner: false` 收回弹窗,4 秒打不开则跳过该步防卡死。**TDesign Guide × Radix 模态互操作**:Radix 模态弹窗打开时会把 `body` 置 `pointer-events:none`(滚动锁定),Guide 直接挂在 body 下的遮罩/高亮/弹层会一并继承失活(引导按钮点不动),`styles/tdesign-theme.css` 末尾对 `.t-guide__overlay/__highlight/__popup/__wrapper` 显式 `pointer-events:auto` 兜底。触发:① 自动 —— 简洁模式新对话落地页自动演示,直到用户显式点「完成」或「跳过」才写 localStorage `deerflow.compact-guide-finished` 记忆(浏览器级);**中途刷新/离开不记忆,下次进入还会再演示**。② 手动 —— 「设置和更多」下拉新增「界面使用引导」(该下拉仅存在于简洁模式工作区侧栏 footer):已在问答页时广播 `compact-guide:start` 窗口事件直接启动,否则写 sessionStorage 请求并导航 `/chats/new` 由挂载的引导消费(消费在定时器真正启动时才执行,规避 StrictMode effect 双跑吞请求)。`eligible` 排除 embed=1 / hideChrome=1 / chats_iframe / FORCE_COLLAPSED_SIDEBAR(无界)等同样无全局 chrome 的特殊环境;启动延迟 800ms 等侧栏宽度过渡稳定后再测量高亮框。
- **智能体使用引导 (Agent onboarding tour, 三段式)**: 智能体「浏览管理 → 创建与配置 → 发起问答」全流程分步引导,组件 `components/workspace/agents/agent-guide.tsx`(同一 TDesign `Guide` 封装模式,与简洁模式引导共享记忆语义:**仅显式点「完成/跳过」才写 localStorage** `deerflow.agent-guide.<stage>.finished`,中途刷新/离开不记忆)。**自动演示仅 create / chat 两段**(进智能体列表页不弹引导,点「创建智能体」进入新建页时才自动演示;list 段的 `AgentGuide` 传 `autoStart={false}`,只能由头部「使用引导」按钮手动触发)。三段各自挂载、各自记忆:① `list`(`agent-gallery.tsx`,/page/workspace/agents)——分区 Tabs、搜索排序、智能体卡片操作、右上「创建智能体」按钮;**完成/跳过就地结束(不跳转创建页,与 create 段无联动)**,最后一步仅提示进入创建页后会有配置引导;② `create`(`NewAgentPage.tsx`,/page/workspace/agents/new)——左侧对话式创建输入区、基本信息、运行模型+入库模板名、知识空间、SOUL.md、技能穿梭框、保存按钮(9 步);③ `chat`(`AgentChatPage.tsx`,agents/:id/chats)——左栏切换与历史、常用问题 chips、输入框(落地态/会话态两个挂点同一 `chat-input` 标记)、右侧详情面板;`eligible` 限定普通智能体对话页(`showAgentList && !isEmbedded && !taskCtxOn`,即排除通用问答原地嵌入与任务深链工作区),三段共用 `isAgentGuideEnvironment()` 排除 embed/hideChrome/无界环境。高亮锚点 `data-agent-guide`:列表页 `tabs`/`search`/`agent-card`(卡片+列表两种布局的根元素)/`new-agent-btn`,创建页 `create-chat-input`/`create-basic`/`create-model`/`create-knowledge`/`create-soul`/`create-skills`/`create-save-btn`,对话页 `chat-sidebar`/`chat-questions`/`chat-input`/`chat-detail`;同样**启动时按目标存在性过滤步骤**(新用户无卡片/无预设问题时自动剔除)。手动重放:三个页面头部各有「使用引导」按钮(列表页创建按钮左侧、创建页 header 右侧、对话页 header),广播 `agent-guide:start:<stage>` 窗口事件强制重放(忽略已看过记忆)。
- **敏感词管理 (Sensitive Word Management)**: configures the **展示层脱敏映射** (原始词 → 替换词). **Gated on the username `lqq`** (not the admin role) — `getAccountDisplayName().toLowerCase() === "lqq"` (username = email `@` prefix, else `user_id`, same as the profile page); the dropdown entry, the route guard, and the page-level guard all use this check. `src/lib/desensitize.ts` ships a frozen seed map `SEED_DESENSITIZE_MAP` (the deployment seed) plus a live mutable `DESENSITIZE_MAP` (initialized from the seed so `desensitize()` works before any fetch). `DesensitizeWordsLoader` (mounted in `App.tsx` `AppProviders`) fetches `/api/sensitive-words` on startup and, if non-empty, calls `replaceDesensitizeMap(...)` to make the backend config the source of truth (empty/failed → keep seed). Page `SensitiveWordsPage.tsx` (route `/page/strategy/admin/sensitive-words`, opened from the 「敏感词管理」 item in the **bottom-left settings dropdown** of `components/page-sidebar.tsx`, present in **both** full + collapsed sidebar modes) lists/adds/edits/启停/deletes words and saves the **whole set atomically** (replace-all); a 「导入种子词」 button merges any missing `SEED_DESENSITIZE_MAP` entries into the editor. Client + hooks in `strategy-components/api/sensitive-words.ts` (`wordsToMap` folds enabled rows into the runtime map). Backend: `/api/sensitive-words` (global/shared; open read, write allowed for admin **or** the `lqq` account), mirroring 菜单管理's store shape. **侧边栏 + 导航栏 menu labels are desensitized** at the data source: `useSidebarMenuItems`/`useActiveThirdLevel` (`core/page-layout/use-sidebar-menu.ts`) map every node's `label` through a desensitizer built **directly from the `/api/sensitive-words` query** (`makeDesensitizer(wordsToMap(words))`, falling back to the global seed `desensitize` while empty) — this sidesteps the `replaceDesensitizeMap` effect-timing race. Only `label` is rewritten; `path`/`id`/`icon` are untouched so routing/highlight are unaffected. All nav surfaces (`page-sidebar.tsx`, `page-sidebar-dark.tsx`, `page-sidebar-v1.tsx`, `strategy-components/Header.tsx`, `PageRoutes.tsx`) consume this hook and are covered; `MenuManagementPage` uses the raw tree so admins still edit real labels.
- **技能地址管理 (Skill Address Management, admin-only)**: 扫描运行中的技能(`skills/{public,custom}` 下所有 `.md`/`.py`)里的 **http(s) URL 与 IP/IP:端口**,按唯一地址聚合全部出现位置(跨 .md/.py),支持**批量替换**(如把 UAT 地址一次性改成生产)。主体抽成可复用组件 `SkillAddressesPanel`(`pages/SkillAddressesPage.tsx` 导出,默认导出 `SkillAddressesPage` 仍保留旧路由 `/page/strategy/admin/skill-addresses` 作直链回退),**作为「技能地址管理」标签页嵌入管理员「技能管理」页 `pages/AdminSkillsPage.tsx`**(该页加 Tabs:「技能列表」+「技能地址管理」;入口在「设置和更多」下拉的「技能管理」`workspace-nav-menu.tsx` → `/page/workspace/admin/skills`,不再单列于 `components/page-sidebar.tsx` 左下角设置下拉):打开自动扫描并带**进度条**(扫描逐技能 / 应用逐文件 X/N,应对 150+ 技能),URL/IP 类型过滤 + 搜索 + 「片段批量套用」(如所有 `uat.4.cn` → `prod.4.cn`)、每地址「替换为」输入框(可展开看 `file:line` 片段)、内联**预览**、**应用**、**多关键词检索**(空格分隔全部命中),以及**修改记录**面板——每次应用生成一条记录(显示时间/改了哪些地址 from→to/文件数/处数),可**针对单次记录回退**(二次确认)。client + NDJSON 流式解析在 `strategy-components/api/skill-addresses.ts`。后端 `/api/skill-addresses`(**仅管理员**):所有文件 IO 走 `asyncio.to_thread` 不阻塞事件循环;`GET /scan`(+`/scan/stream`)、`POST /preview`、`POST /apply`(+`/apply/stream`)、`GET /backups`、`POST /rollback/{id}`;**子串安全替换**(基于 token span,不会误伤子串)、`expected_total` 乐观锁(409)、写前自动磁盘备份到 `{skills_root}/.address-edits/`(同时写一份 `{id}.manifest.json` 记录本次替换明细,供修改记录展示)、应用后刷新技能系统提示缓存。纯引擎 `deerflow/skills/address_scan.py`,router `app/gateway/routers/skill_addresses.py`,tests `tests/test_skill_addresses.py`。范围仅运行中技能,不动 `deploy/minimal/skills/`。
- **按钮管理 (Task Button Management, admin-only)**: configures the **可配置跳转按钮** rendered in the left task panel of the task deep-link workspaces (rwfx / 3qfx / xdfx, see `TaskFxWorkspace`). Each button = `{business, label, linkType, target, appendTaskId, idParam, idKind, enabled, sortOrder}`; `linkType` is `url` (外链 `window.open`, optional append of `?{idParam}={id}` — **`idParam` is the editable query-param name**, e.g. `id`/`task_id`), `business` (内部切换到另一业务, reuses `resolveTaskDeeplinkTarget`, always task id), or `purpose` (弹出当前任务的「任务目的」表格 via the shared `TaskPurposeDialog`, no target — configurable for any page incl. xdfx). **`host`(宿主路由)** asks the embedding parent to navigate: `runTaskButton` sends `window.parent.postMessage({ type:'HOST_NAVIGATE', path, queryParams:{ [idParam]: Number(taskId) } }, hostOrigin)` — `target` is the host route, `appendTaskId`/`idParam` become numeric `queryParams` (task id only), origin from `runtime-config.js` `VITE_HOST_NAVIGATE_ORIGIN` (else ancestorOrigins/referrer; never `*`). **`idKind` (`task`/`action`) only matters for xdfx**: its deep-link `?taskId=` is an 行动id and the 任务id is resolved at login (`fetchTaskIdFromAction`) — `TaskContext` now also stashes the raw `actionId`, so a url button can append either (default `task`). Page `TaskButtonsPage.tsx` (route `/page/strategy/admin/task-buttons`, **admin-gated**, entry「按钮管理」in the bottom-left settings dropdown of `components/page-sidebar.tsx`, both full + collapsed modes) has per-business tabs, edits name/type/target/启停/排序/增删, saves the **whole set atomically** (replace-all), plus 「导入默认」 to merge code-seed defaults. **Seed/fallback** (like 敏感词管理): only when the whole table is empty (fresh deploy, never saved) do the workspace + page fall back to `defaultTaskButtons(cfg)` — rwfx's url buttons (编辑/下一步/3q详情) built from the **live** `/api/public/config/task-deeplink` plus cross-business switch buttons for **all three** businesses (each switches to the other two — rwfx→三情/行动, 3qfx→任务/行动, xdfx→任务/三情). Once saved, the store is the sole source of truth. The old hardcoded jump buttons were migrated out: `TaskFxWorkspace` no longer hardcodes 切换到三情分析, `TaskActionsPanel` keeps only the non-jump 清除记录, and `TaskPurposePanel` dropped its 3q详情 button (now configurable) **and defaults the 目的树 table to collapsed** (chevron toggle). Helpers `core/auth/task-buttons.ts` (`TaskButton`, `defaultTaskButtons`, `resolveTaskButtons`, `buttonsForBusiness`, `runTaskButton`), client+hooks `strategy-components/api/task-buttons.ts`. Backend: `/api/task-buttons` (global/shared; open read, admin replace-all), store `deerflow.persistence.task_buttons` (table `task_buttons`, auto-created by `create_all`), wired `app.state.task_button_store`. Tests: `tests/test_task_buttons.py`.
- **State**: TanStack Query for server state, context providers (`SubtasksProvider`, `ArtifactsProvider`, `PromptInputProvider`) scoped to `WorkspaceRoutes`
- **LLM streaming**: `@langchain/langgraph-sdk` streams messages from the backend via SSE
- **UI**: Radix UI primitives + TailwindCSS v4 + shadcn-style components in `src/components/ui/`
- **Shims**: `src/shims/` provides `next/link` and `next/navigation` polyfills (original code was Next.js)
- **Login URL params** (`LoginPage.tsx`, frontend-only — the backend never sees these): besides the auth params (`ticket`/`userId`/`env`/`theme`/`yUserId`/`token`/`access_token`/`authToken`/`password`), the page supports a **task deep-link** via `?taskId=&goPath=`. After login it calls the consumer API `GET {VITE_AIPI_CONSUMER_URL}/taskAnalyseSearch/cop-task-detail?taskId=` (header `Authorization: Bearer admin`, auto-injected by `utils/request.ts`), stashes the full `data` (`id/overview/taskDirection/taskName/taskContent`) into `sessionStorage["login.copTaskDetail"]`, then routes by `goPath`: base codes `3qfx`/`rwfx`/`xdfx` → that business's configured **single agent** Q&A inside a **任务工作区** (resolved via `/api/business-mapping`; `resolveTaskDeeplinkTarget` calls `persistTaskContext({taskId, agentId, openingText})` and navigates to the `…/chats` **index**, which opens the latest task conversation or 新建 — a 1:N task↔对话 workspace, NOT `pendingAgentMessage`); the `-A` suffix (`3qfx-A`/…) → **multi-agent roundtable** with `roundtablePrefill.businessCode` so the page auto-selects the configured 业务链条. **xdfx's deep-link `?taskId=` is actually an 行动id, not a 任务id** — `resolveDeeplinkTaskId(goPath, rawId)` (called in `LoginPage` before everything) detects `xdfx`/`xdfx-A` and resolves it via `GET {action_detail_url}/{actionId}` → `data.taskId` (`fetchTaskIdFromAction`; `action_test`+`mock.action_detail` for offline testing); the resolved 任务id then drives `cop-task-detail`, the purpose tree, and the 1:N binding (other businesses pass the id through unchanged). **xdfx additionally partitions its chat records by 行动id (action_id), NOT by task_id**: `resolveTaskDeeplinkTarget` sets `partitionByAction:true` + keeps the raw action_id as `TaskContext.actionId`, so new threads are tagged `metadata.{taskId,actionId}` (taskId kept only to preserve the backend「任务深链对话全局共享」semantics, which keys off `metadata.taskId`) and the conversation list filters by `actionId` (+`agent_id`) — different actions of the same task get separate lists. xdfx's first-question opening text also appends `行动id(action_id)为…` (see `buildOpeningText` / `taskThreadMetadata`). goPath→businessCode: `3qfx`→`3Q`, `rwfx`→`6BF`, `xdfx`→`7BF`. The roundtable target also threads the URL `taskId` into `roundtablePrefill.taskId` (`resolveTaskDeeplinkTarget(goPath, detail, taskId)`), which turns on two taskId-scoped behaviors: (1) **separate, unpartitioned per-task storage** — taskId 会商聊天记录 live in their **own** store/table (`roundtable_task_drafts`), keyed **only by `task_id`** (one taskId = many records, shared across users, **no user 分权** at all; `created_by` is audit-only), kept entirely out of the per-user personal store (`roundtable_drafts`, now strictly per-user) so the two never mix. Backend router `/api/roundtable-task-drafts` (`GET /by-task/{id}` + `/by-task/{id}/latest`, `POST`, `GET/PUT/DELETE /{id}` — all user-agnostic); frontend client `roundtable-planning/api/task-drafts.ts`, and `useDraftPersistence`/`useRoundtableDrafts` route **all** CRUD to it when a `taskId` is present (else the personal `drafts.ts`). The matching **background jobs** are shared by task too: `roundtable_jobs.task_id` marks a task job; reads/dedup/stream/resume/cancel pass `?task_id=` so any user opening the task sees the same running 研讨 (progress/flowchart), and the executor writes the final report back to the task-draft store. Existing rows are moved over by `scripts/migrate_roundtable_task_drafts.py` (migration `20260618_01`). The history dropdown filters to the task and 新建 keeps the binding; (2) **Step-3 auto structured output** — after the `roundtable-summary` agent writes the Markdown report it automatically runs a second round emitting a `flow-json` flowchart (`useStep3Summary` `autoFlow`+`chainLevels`), whose hierarchy follows the business chain's stage goals (任务 → 目的 → 行为体 → …; coordinatorPrompt-specified hierarchy wins) and whose nodes never carry 阶段编号/阶段名 (the prior bug). **Both targets render embedded under the 任务管理 layout** — nested routes under `task-management/<business-path>/{roundtable,agent/:agent_id/chats}` in `StrategyRoutes.tsx` (`<business-path>` = `plan-task-sentiment` / `plan-task/plan-task-fx` / `plan-task/plan-task-action`, matching the COH中任务 menu paths in `sidebar-menu.ts`) so the global sidebar keeps 任务管理 → COH中任务 → the matching business highlighted. **All three single-agent businesses share `TaskFxWorkspace`** (`task-components/TaskFxWorkspace.tsx`): left = a「当前任务」card (`readCopTaskDetail()` 任务名称 + 简介, desensitized, 留存 above 新建对话) + per-task 1:N conversation list (`useTaskThreads(taskId, agentId, actionId?)` — filtered by **both** `metadata.taskId` AND `metadata.agent_id` so the three businesses' conversations staLine truncated
- **agentfx 任务深链(新系统 iframe 嵌入的智能体问答,3qfx 单智能体 lite 模式的独立复制)**: goPath=`agentfx`(`${loginBase}?password=…&taskId=…&goPath=agentfx&embed=1&hideJump=1&theme=dark-blue`)。与 3qfx 的差异:①任务详情不走外部 consumer,改调**本系统 Gateway** `GET {backend}/taskAnalyseSearch/cop-task-detail?taskId=`(`apiFetch` 带刚登录的 DeerFlow 态;任务数据来自 TaskCOP 任务表,与任务列表/报告导入同一份);②**固定使用内置智能体** `agentfx-analyst`(不走业务映射);③路由 `task-management/plan-task-agentfx/agent/:agent_id/chats`,页面为独立复制的 `AgentFxWorkspace.tsx`(`AgentFxWorkspace`/`AgentFxIndexResolver`/`AgentFxChat` —— 左「当前任务」卡 + 1:N 对话列表 + 新建对话,`AgentChatPage taskBind` 自动发开场白;无 TaskJumpBar/清除记录/闸门/xdfx 行动卡)。模块 `core/auth/agentfx-deeplink.ts`(`isAgentfxGoPath`/`fetchAgentfxTaskDetail`/`resolveAgentfxDeeplinkTarget`);任务详情整包仍存共享键 `login.copTaskDetail`(按标签页隔离),`AgentChatPage` 的 taskBind 自恢复对 agentfx 生效。`LoginPage` 在既有深链分支前用 `isAgentfxGoPath` 分流。**内置「任务研判报告助手」**:后端 seeder `app/gateway/routers/_agentfx_seed.py` + `_agentfx_seed_assets/`(config.yaml + SOUL.md,目录存在不覆盖;app.py lifespan 在 `_sync_legacy_agents` 之前调用,自动进 agents 表 user_id IS NULL)——SOUL 规定工作流「搜集信息(`web_search`,**首步不可跳过**)→ `write_file` 生成 `/mnt/user-data/outputs/report.md` + `task-reports.json`(14 个 categoryType 的 `{contentJson, categoryType}` 数组,contentJson 为 JSON 字符串)→ 聊天总结 → 引导入库」,硬性约束:categoryType 逐字用 14 个全称(禁缩写自造如「DQ关键事件」)、JSON 直接写汉字禁 `\uXXXX` 转义、每类必须有实质内容不许空数组/纯占位、文件一律用 `/mnt/user-data/...` 虚拟路径(防宿主路径泄漏进 tool args)。**检索依赖 `config.yaml tools.web_search`(DDG,enabled 已开;内网需换 configurable_search 时改回并填 endpoint)**。任务工作区输入框在 `taskCtxOn` 时隐藏「写作/记忆/参考文献」(InputBox `hideContextTools` prop)与「知识空间」(不传 knowledgeSelector);消息流里 write_file 文件卡片只显示文件名(`artifactDisplayName` 收敛宿主/虚拟路径)。**入库两条路径**:(a) **前端协助卡** —— `AgentChatPage`(taskBind 且非 taskGate)检测线程 artifacts 出现 `task-reports.json`(按文件名后缀匹配,兼容本地沙箱记录的宿主路径)且流式结束时,向 displayThread 尾部注入 `additional_kwargs.task_report_import_approval` 虚拟 ai 消息(`core/messages/utils.ts` 分组 `assistant:task-report-import` + `MessageList` 的 `taskReportImportSlot` 插槽渲染 `TaskReportImportCard`),点「开始入库」前端校验(`strategy-components/lib/agentfx-report-schema.ts`,14 类 + contentJson 合法 JSON + **\u 转义归一化还原为汉字**,与技能脚本同规则)后 `importTaskReport`(`strategy-components/api/task-reports.ts`)POST 导入接口整体替换;任务已有详情**不抑制**卡片(入库即整体替换,卡片文案说明覆盖语义),导入成功按 thread 记 sessionStorage(刷新不重复询问)、「暂不入库」为会话内记忆;(b) **入库技能** `task-report-import`(seeder 一并复制到 `skills/public/`,public 类技能 extensions_config 缺省即启用)—— 用户聊天里说「入库」时智能体按 SKILL.md 用 bash 跑 `scripts/task_report_import.py`(纯标准库:同样的校验规则 + 转义归一化;**默认关闭 SSL 证书校验** `ssl._create_unverified_context` + 忽略代理,适配内网自签证书;鉴权 `--token`/env `AGENTFX_IMPORT_TOKEN`→`DEERFLOW_AUTH_TOKEN`→`TOOLS_TOKEN` 优先,缺省经公共端点 `POST /api/parallel-agents/auth/token` 以 `agentfx-import` 用户现签 token——内网既有鉴权旁路;gateway 地址 env `AGENTFX_GATEWAY_URL` 或 `http://127.0.0.1:{DEER_FLOW_GATEWAY_PORT}`);`--strict` 可要求 14 类齐全,默认允许部分导入并在 stdout JSON 的 `missing_categories` 里列缺。入库成功后任务 TaskCOP 状态自动置 25(已完成分析)。**入库成功通知宿主**(iframe 嵌入场景):两条路径成功后都会 `window.top.postMessage({source: "magent-web", type: "task-report:saved", taskId: String(taskId)}, "*")`(`notifyTaskReportSaved`,`agentfx-report-schema.ts`)——卡片路径在 `TaskReportImportCard` 导入成功回调里直发;技能路径由 `AgentChatPage` 从消息流检测 `task_report_import.py` 的成功 stdout(`"success": true` + `task_id`)代发——**仅在回合结束后检测**(`!thread.isLoading` 才扫描;流式过程中 messages Line truncated
- **iframe 嵌入模式 (外部系统用 iframe 套用深链问答/会商)** — 三个**按标签页**开关,全部由深链 URL 参数开启、存进同一份 `sessionStorage` 会话(`embed.session`,键名常量在 `core/embed/embed-session.ts`),跨登录跳转/刷新/页内导航存活,**绝不跨标签污染**同浏览器另开的正常系统页。核心隔离手法:用 `sessionStorage`(按标签页/浏览上下文隔离,iframe 即便同源也有独立一份)而非 `localStorage`(跨标签共享)。开关:(1) **`?embed=1`(可带 `&theme=`)** — 去全局 chrome(`PageLayout` 的 `pageSidebarAllowed && !isEmbedActive()` → 隐藏 Header + PageSidebar)+ 按外部主题色**强制**明/暗:走 next-themes 的 `forcedTheme`(`App.tsx` `AppProviders` 调 `resolveForcedEmbedTheme`,**不写** localStorage `strategy-theme`),离散映射 `dark-blue`/`dark`→深、其余→浅;嵌入侧**绝不**调 `setTheme`/`persistSidebarEnabled`(那俩落 localStorage 跨标签污染,`LoginPage` 据 `readEmbedParam` 跳过)。(2) **`?hideJump=1`** — 隐藏深链底部「快捷跳转」栏 `TaskJumpBar` 的两部分(底部「下一步」等按钮 + 右侧垂直居中悬浮菜单),单智能体问答 + 会商共用该栏,`isJumpBarHidden()` 为真时整条 `return null`。(3) **登录用户隔离** — 嵌入态下鉴权/身份键(`deerflow.auth` token、`userInfo`、`login.*`、`tools_token`、maxkey/userDetail token)全部经 `core/auth/scoped-storage.ts` 的 `authStorage()`(嵌入→sessionStorage / 正常→localStorage)读写,使 iframe 里登录的用户与正常登录用户**完全隔离**、互不覆盖;所有 token 读取都过 `getStoredAuth()`/`getAuthorizationHeaderValue()`(API 客户端 `core/api/*` 全走这俩),改中心函数即让全体调用方自动隔离;跨标签账号变更监听 `AuthSyncWatcher`(`core/auth/sync.tsx`)在嵌入态禁用。嵌入会话在 `main.tsx` 渲染前 `syncEmbedSessionFromCurrentUrl()` 同步启用(早于任何鉴权写入,避免首帧 effect 顺序漏写 localStorage);`AppProviders` 的 effect 再按 SPA 导航同步。`embed=0`/`hideJump=0` 可显式关闭。正常(非嵌入)标签页所有 `isXxx()` 恒 false,行为**零变化**。第三个开关 `?isolate=1`(**独立登录会话**)把同一套**登录用户隔离**单独提供给**普通(带 chrome)标签页**——只切换鉴权存储、不去 chrome / 不强制主题 / 不动跳转栏:`authStorage()` 的条件从「仅嵌入」放宽为 `isEmbedActive() || isIsolatedSession()`,`AuthSyncWatcher` 的跨标签监听对嵌入态**或**独立态都即时忽略(handler 内实时判,运行时开关也即刻生效)。除 URL 参数外,**设置 → 外观 →「登录会话」** 有一个 Switch「独立登录会话(本标签页)」运行时切换(`setIsolatedSession`,`appearance-settings-page.tsx`):**开启时先 `migrateAuthToSession()`**(`scoped-storage.ts`,把 localStorage 的受保护键 `deerflow.auth`/`userInfo`/`userId`/`tools_token` + `login.*` 前缀快照搬进 sessionStorage)再翻标志,故无感不登出;此后本标签页登录态独立——别处登录/换号影响不到它,它换号也影响不到别人,但关掉该标签即结束(需重登)。开启给 toast 提示。
### Configuration
Backend config lives in `offline-backend-20260512/backend/config.yaml`. Values starting with `$` resolve as environment variables (e.g., `$OPENAI_API_KEY`). MCP servers and skills are configured in `extensions_config.json` in the same directory.
## Detailed Backend Reference
The backend has its own comprehensive documentation at:
- `offline-backend-20260512/backend/AGENTS.md` — architecture, middleware chain, all API routes, config schema, sandbox/memory/subagent systems
- `offline-backend-20260512/backend/README.md` — setup guide, technology stack
+11 -4
View File
@@ -79,16 +79,23 @@ The frontend (`frontend-web/`) is a React 19 + Vite SPA:
- **Routing**: React Router v7; top-level routes in `src/pages/PageRoutes.tsx`, workspace sub-routes in `src/pages/WorkspaceRoutes.tsx`
- **Pages**: `ChatPage` (thread chat), `AgentChatPage` (custom agent chat), `AgentsPage`/`NewAgentPage` (agent management), `ScheduledTasksPage`/`ScheduledTaskRunDetailPage` (scheduled tasks), `LightAppManagementPage`/`LightAppListPage`/`LightAppIframeView` (轻应用中心 — register/list/embed mini-apps)
- **定时任务「JSON → HTML 模板填充」(模板数据转换器)**: a third scheduled-task execution mode. In the create/edit dialog (`ScheduledTasksPage.tsx`), selecting the built-in agent **「模板数据转换器」** (`execution_agent_name === "template-json-builder"`, `TEMPLATE_BUILDER_AGENT_ID`) reveals a 「HTML模板」 select (`useHtmlTemplates` → `GET /api/scheduled-tasks/html-templates`) + a **.json 上传** button (reads the file's text into the prompt box) and **hides** the 必须生成 HTML/Markdown switches (this mode always outputs HTML). The chosen template persists as `execution_context.template_config.template_id` (`TemplateFillConfig` in `core/scheduled-tasks/types.ts`). At run time the backend converts the source JSON (the task prompt) into that template's `DATA` structure, validates (retry-on-fail), fills the template, and stores an HTML page previewable via the existing run-detail HTML preview. The source can be **pure JSON, plain text, or text-with-embedded-JSON** — the backend pre-extracts any embedded JSON and the agent's `SOUL.md` maps it (or the plain text's semantics) to the template's schema skeleton. **Chat-page debug entry (only this agent's `AgentChatPage`)**: when `agent_id === "template-json-builder"`, the chat header shows a 「页面模板」 select + a 「渲染预览」 button — after a normal Q&A run, the button takes the **latest AI reply**, POSTs it to `POST /api/scheduled-tasks/template-fill/render` (`renderTemplateFill`), and pops a dialog rendering the filled HTML in a `sandbox="allow-scripts"` iframe plus the structure-validation status/errors/gaps — for debugging the agent's conversion effect without creating a scheduled task. Gated strictly on the agent id, so other agents' chat pages are untouched. See the backend CLAUDE.md「Template-fill mode」for the engine (`deerflow/runtime/scheduler/template_fill.py`), agent seed, dispatch, and the render API.
- **AI 写作·对话版(对话驱动写作台)**: a **parallel new entry** beside the classic AI-writing page (classic page/routes untouched) — route `/page/canvas/ai-writing-chat` (`OpenCanvasRoutes.tsx`), sidebar 「问答管理 → 课题研究(对话版)」. Page `open-canvas/pages/AIWritingChatPage.tsx` fully **reuses the engine** (`AIWritingContext` state machine + LangGraph `useStream`, `AIWritingHistoryProvider`, right-side `AIWritingDraftPanel`) but replaces the presentation: left = `components/ai-writing-chat/WritingChatPanel.tsx` (timeline + **button-only intervention cards** `ChatInterventionCards.tsx` — the five pause cards copied from `InterventionCard.tsx` with all inline textareas removed, confirm/action buttons kept — plus a bottom **unified smart composer**). Free text goes through two-level intent resolution (`open-canvas/api/ai-writing-intent.ts`): deterministic short-phrase fast path (确认/继续/重新搜索/重写大纲…; high-cost actions never fast-pathed) then `POST /api/ai-writing/sessions/{id}/intent` — the backend reads the graph checkpoint (authoritative pause point from the pending interrupt) and routes via `deerflow/agents/ai_writing/intent_router.py` (LLM + strict per-pause action whitelist aligned to the graph's real resume actions, confidence gates: finalize/force_finalize/覆盖式 re_search need ≥0.85 else clarify, payload key-whitelist cleaning). Results map to `submitIntervention`/control (暂停/继续/后台挂起)/QA bypass (`answer` rendered as a chat bubble, never touches graph state)/clarify (amber follow-up bubble with multi-turn context). **Two-state layout**: idle (未开始写作) renders the **classic setup experience unchanged** — `WritingSetupChat` + collapsible `AIWritingPanel` form under `WritingFormProvider` (same as `AIWritingPage`'s idle branch); once writing starts (or history view opens) it switches to the chat workbench. **Unified chronological feed** (`ChatFlowTimeline.tsx`): intent-layer chat bubbles are interleaved INTO the progress-event timeline by anchor (= `progressEvents.length` at message creation), so events triggered by a user message render **below** it (Google-AI-Studio-style single stream, not timeline-above/chat-below); composer-driven interventions suppress the duplicate 「我的要求」card (`suppressedRequirementIndices`). **素材不足自动续跑** only at `material_confirm` (the only pause the graph supports re-search from): needResearch caches the payload as a pending intent, submits `re_search + userQuery`, and auto-submits the pending intent when the new material-confirm pause arrives (cancellable pill). Stage chips + per-stage placeholder + 「当前交互对象」status badge. Backend tests `tests/test_ai_writing_intent.py`. Plan doc: `frontend-web/docs/ai-writing-对话驱动写作台-实现方案.md`.
- **轻应用中心 (Light App Center)**: a sibling of 任务管理 in the sidebar with two pages — 应用管理 (admin registers `window_open` or `iframe` mini-apps with a route-param builder: login params resolved from `localStorage.userInfo`, theme params literal) and 应用列表 (card grid of `window_open` apps, `window.open` launch). `iframe` apps are mounted under a chosen parent menu (XK/PG/TY/综合管理) and **dynamically injected into the sidebar** by `core/page-layout/use-sidebar-menu.ts` (`useSidebarMenuItems`), opening in the `LightAppIframeView` host. Client + React Query hooks in `strategy-components/api/light-apps.ts`; URL builder/constants in `strategy-components/lib/light-app.ts`. Backend: `/api/light-apps` (global/shared, admin-gated writes).
- **菜单管理 (Menu Management, admin-only)**: an **overlay** over the static sidebar menu — `MenuManagementPage` (`pages/MenuManagementPage.tsx`, route `/page/strategy/admin/menu-management`, opened from the admin-only 「菜单管理」 item in the **bottom-left settings dropdown** of `components/page-sidebar.tsx`). Admins rename / 停用·启用 / reorder (↑↓ or @dnd-kit drag) / re-parent (horizontal drag **or** the edit dialog's 「移动到」parent selector) any node across 一级/二级/三级, **including injected iframe light-app nodes** (`light-app-<appId>`). The static tree (`core/page-layout/sidebar-menu.ts`) stays the source of icons/routes; only per-node deltas (`label`/`disabled`/`parentId`/`sortOrder`) persist to the backend. Merge logic in `core/page-layout/menu-overrides.ts` (`applyMenuOverrides`, applied in `use-sidebar-menu.ts` after light-app injection, before role filter; disabling a node hides its whole subtree) — strict **3-level cap** (`wouldExceedDepth`). Client `strategy-components/api/menu-overrides.ts`. Backend: `/api/menu-overrides` (global/shared; open read, admin atomic replace-all).
- **菜单管理 (Menu Management, admin-only)**: an **overlay** over the static sidebar menu — `MenuManagementPage` (`pages/MenuManagementPage.tsx`, route `/page/strategy/admin/menu-management`, opened from the admin-only 「菜单管理」 item in the **bottom-left settings dropdown** of `components/page-sidebar.tsx`). Admins rename / 停用·启用 / reorder (↑↓ or @dnd-kit drag) / re-parent (horizontal drag **or** the edit dialog's 「移动到」parent selector) any node across 一级/二级/三级, **including injected iframe light-app nodes** (`light-app-<appId>`). The static tree (`core/page-layout/sidebar-menu.ts`) stays the source of icons/routes; only per-node deltas (`label`/`disabled`/`parentId`/`sortOrder`) persist to the backend. Merge logic in `core/page-layout/menu-overrides.ts` (`applyMenuOverrides`, applied in `use-sidebar-menu.ts` after light-app injection, before role filter; disabling a node hides its whole subtree) — strict **3-level cap** (`wouldExceedDepth`). Client `strategy-components/api/menu-overrides.ts`. Backend: `/api/menu-overrides` (global/shared; open read, admin atomic replace-all). **简介模式** left-nav is a separate overlay: `/api/compact-menu-overrides` stores two independent sets (type `A` / `B`); each website picks one via `runtime-config.js` `VITE_COMPACT_MENU_TYPE`.
- **白名单管理 (Login Whitelist, admin-only)**: gates **who may log in**, run as a **blocklist (黑名单模式)**. Two pieces: a global master switch (`system_settings.json → login_whitelist.enabled`, surfaced by **admin-only** `GET|PUT /api/system-settings/login-whitelist`) + a per-user **放行** flag (`users.approved` column, migration `20260625_02`). Users **self-register** as usual and **every new account defaults to `approved=True`** — so a user who has never logged into this system before is allowed straight through; the switch only blocks users an admin has explicitly **取消放行** (`approved=False`). (`create_user`/`User`/`UserRow` all default `approved=True`; admins are always approved; existing rows are backfilled `True`.) Login interception is the single helper `enforce_user_approved(user)` in `app/gateway/routers/auth.py`, called in all three login endpoints (`/login/{local,username,token}`) **after** the account is resolved/created and **before** the JWT is issued: switch off → everyone passes; `system_role=="admin"` → always passes (anti-lockout); else `approved=False` (admin-revoked) → 403 `{code:"PENDING_APPROVAL"}` (the frontend's `extractErrorMessage` surfaces the message and login throws before writing any auth state, so no half-login). Admin approves on `pages/LoginWhitelistPage.tsx` (route `/page/strategy/admin/login-whitelist`, entry「白名单管理」in the bottom-left settings dropdown of `components/page-sidebar.tsx`, both sidebar modes): a top master-switch + a list of all registered users (`GET /api/v1/auth/users`, now carrying `approved`) with a per-row 放行 Switch (`PUT /api/v1/auth/users/{id}/approval`, admin-only; revoking only blocks the **next** login — `token_version` is left untouched, existing sessions are not force-killed). Client/hooks: switch in `strategy-components/api/login-whitelist.ts`, user list + approval in `core/auth/{api,hooks}.ts` (`useSetUserApproval`). Backend tests: `tests/test_login_approval.py`. **账号级「登录口令」(per-account password — 临时开通)**: the same page also lets an admin assign one specific account an individual **plaintext** password (`users.login_password` column, migration `20260625_04`, nullable; auto-added on startup by `_ensure_orm_columns_sync`). Once set, **that account's** username login (`POST /api/v1/auth/login/username`) **requires** `?password=` to exactly match it and that personal password **takes precedence over** the global shared-password gate (`username_login.require_password`); accounts without one keep today's shared-gate / passwordless behavior. The user then logs in via the **existing** frontend URL `#/login/<用户名>?password=xxxx` (LoginPage already forwards `?password=`; `<用户名>` = the account's email `@`-prefix). **Plaintext is intentional** — the password rides in the URL query anyway, so storing it readably lets the admin re-copy the full login link from the page; it is exposed only on the **admin-only** `GET /api/v1/auth/users` (`UserListItem.login_password`) and the new admin-only `PUT /api/v1/auth/users/{id}/login-password` (set non-empty / clear with null·empty; doesn't touch `token_version`). The whitelist page renders a per-user 「登录口令」 column with a set/修改 editor + a live 「复制登录链接」 button (`useSetUserLoginPassword` in `core/auth/hooks.ts`, `setUserLoginPassword` in `core/auth/api.ts`). Backend gate helper `_lookup_user_by_username` (lookup-only, no auto-register) in `routers/auth.py`; tests `tests/test_login_personal_password.py`.
- **敏感词管理 (Sensitive Word Management)**: configures the **展示层脱敏映射** (原始词 → 替换词). **Gated on the username `lqq`** (not the admin role) — `getAccountDisplayName().toLowerCase() === "lqq"` (username = email `@` prefix, else `user_id`, same as the profile page); the dropdown entry, the route guard, and the page-level guard all use this check. `src/lib/desensitize.ts` ships a frozen seed map `SEED_DESENSITIZE_MAP` (the deployment seed) plus a live mutable `DESENSITIZE_MAP` (initialized from the seed so `desensitize()` works before any fetch). `DesensitizeWordsLoader` (mounted in `App.tsx` `AppProviders`) fetches `/api/sensitive-words` on startup and, if non-empty, calls `replaceDesensitizeMap(...)` to make the backend config the source of truth (empty/failed → keep seed). Page `SensitiveWordsPage.tsx` (route `/page/strategy/admin/sensitive-words`, opened from the 「敏感词管理」 item in the **bottom-left settings dropdown** of `components/page-sidebar.tsx`, present in **both** full + collapsed sidebar modes) lists/adds/edits/启停/deletes words and saves the **whole set atomically** (replace-all); a 「导入种子词」 button merges any missing `SEED_DESENSITIZE_MAP` entries into the editor. Client + hooks in `strategy-components/api/sensitive-words.ts` (`wordsToMap` folds enabled rows into the runtime map). Backend: `/api/sensitive-words` (global/shared; open read, write allowed for admin **or** the `lqq` account), mirroring 菜单管理's store shape. **侧边栏 + 导航栏 menu labels are desensitized** at the data source: `useSidebarMenuItems`/`useActiveThirdLevel` (`core/page-layout/use-sidebar-menu.ts`) map every node's `label` through a desensitizer built **directly from the `/api/sensitive-words` query** (`makeDesensitizer(wordsToMap(words))`, falling back to the global seed `desensitize` while empty) — this sidesteps the `replaceDesensitizeMap` effect-timing race. Only `label` is rewritten; `path`/`id`/`icon` are untouched so routing/highlight are unaffected. All nav surfaces (`page-sidebar.tsx`, `page-sidebar-dark.tsx`, `page-sidebar-v1.tsx`, `strategy-components/Header.tsx`, `PageRoutes.tsx`) consume this hook and are covered; `MenuManagementPage` uses the raw tree so admins still edit real labels.
- **按钮管理 (Task Button Management, admin-only)**: configures the **可配置跳转按钮** rendered in the left task panel of the task deep-link workspaces (rwfx / 3qfx / xdfx, see `TaskFxWorkspace`). Each button = `{business, label, linkType, target, appendTaskId, idParam, idKind, enabled, sortOrder}`; `linkType` is `url` (外链 `window.open`, optional append of `?{idParam}={id}` — **`idParam` is the editable query-param name**, e.g. `id`/`task_id`), `business` (内部切换到另一业务, reuses `resolveTaskDeeplinkTarget`, always task id), or `purpose` (弹出当前任务的「任务目的」表格 via the shared `TaskPurposeDialog`, no target — configurable for any page incl. xdfx). **`idKind` (`task`/`action`) only matters for xdfx**: its deep-link `?taskId=` is an 行动id and the 任务id is resolved at login (`fetchTaskIdFromAction`) — `TaskContext` now also stashes the raw `actionId`, so a url button can append either (default `task`). Page `TaskButtonsPage.tsx` (route `/page/strategy/admin/task-buttons`, **admin-gated**, entry「按钮管理」in the bottom-left settings dropdown of `components/page-sidebar.tsx`, both full + collapsed modes) has per-business tabs, edits name/type/target/启停/排序/增删, saves the **whole set atomically** (replace-all), plus 「导入默认」 to merge code-seed defaults. **Seed/fallback** (like 敏感词管理): only when the whole table is empty (fresh deploy, never saved) do the workspace + page fall back to `defaultTaskButtons(cfg)` — rwfx's url buttons (编辑/下一步/3q详情) built from the **live** `/api/public/config/task-deeplink` plus cross-business switch buttons for **all three** businesses (each switches to the other two — rwfx→三情/行动, 3qfx→任务/行动, xdfx→任务/三情). Once saved, the store is the sole source of truth. The old hardcoded jump buttons were migrated out: `TaskFxWorkspace` no longer hardcodes 切换到三情分析, `TaskActionsPanel` keeps only the non-jump 清除记录, and `TaskPurposePanel` dropped its 3q详情 button (now configurable) **and defaults the 目的树 table to collapsed** (chevron toggle). Helpers `core/auth/task-buttons.ts` (`TaskButton`, `defaultTaskButtons`, `resolveTaskButtons`, `buttonsForBusiness`, `runTaskButton`), client+hooks `strategy-components/api/task-buttons.ts`. Backend: `/api/task-buttons` (global/shared; open read, admin replace-all), store `deerflow.persistence.task_buttons` (table `task_buttons`, auto-created by `create_all`), wired `app.state.task_button_store`. Tests: `tests/test_task_buttons.py`.
- **技能地址管理 (Skill Address Management, admin-only)**: 扫描运行中的技能(`skills/{public,custom}` 下所有 `.md`/`.py`)里的 **http(s) URL 与 IP/IP:端口**,按唯一地址聚合全部出现位置(跨 .md/.py),支持**批量替换**(如把 UAT 地址一次性改成生产)。主体抽成可复用组件 `SkillAddressesPanel`(`pages/SkillAddressesPage.tsx` 导出,默认导出 `SkillAddressesPage` 仍保留旧路由 `/page/strategy/admin/skill-addresses` 作直链回退),**作为「技能地址管理」标签页嵌入管理员「技能管理」页 `pages/AdminSkillsPage.tsx`**(该页加 Tabs:「技能列表」+「技能地址管理」;入口在「设置和更多」下拉的「技能管理」`workspace-nav-menu.tsx` → `/page/workspace/admin/skills`,不再单列于 `components/page-sidebar.tsx` 左下角设置下拉):打开自动扫描并带**进度条**(扫描逐技能 / 应用逐文件 X/N,应对 150+ 技能),URL/IP 类型过滤 + 搜索 + 「片段批量套用」(如所有 `uat.4.cn` → `prod.4.cn`)、每地址「替换为」输入框(可展开看 `file:line` 片段)、内联**预览**、**应用**、**多关键词检索**(空格分隔全部命中),以及**修改记录**面板——每次应用生成一条记录(显示时间/改了哪些地址 from→to/文件数/处数),可**针对单次记录回退**(二次确认)。client + NDJSON 流式解析在 `strategy-components/api/skill-addresses.ts`。后端 `/api/skill-addresses`(**仅管理员**):所有文件 IO 走 `asyncio.to_thread` 不阻塞事件循环;`GET /scan`(+`/scan/stream`)、`POST /preview`、`POST /apply`(+`/apply/stream`)、`GET /backups`、`POST /rollback/{id}`;**子串安全替换**(基于 token span,不会误伤子串)、`expected_total` 乐观锁(409)、写前自动磁盘备份到 `{skills_root}/.address-edits/`(同时写一份 `{id}.manifest.json` 记录本次替换明细,供修改记录展示)、应用后刷新技能系统提示缓存。纯引擎 `deerflow/skills/address_scan.py`,router `app/gateway/routers/skill_addresses.py`,tests `tests/test_skill_addresses.py`。范围仅运行中技能,不动 `deploy/minimal/skills/`。
- **按钮管理 (Task Button Management, admin-only)**: configures the **可配置跳转按钮** rendered in the left task panel of the task deep-link workspaces (rwfx / 3qfx / xdfx, see `TaskFxWorkspace`). Each button = `{business, label, linkType, target, appendTaskId, idParam, idKind, openMode, loginParams, appendAuth, authTokenParam, authNameParam, enabled, sortOrder}`; `linkType` is `url` (外链 `window.open`, optional append of `?{idParam}={id}` — **`idParam` is the editable query-param name**, e.g. `id`/`task_id`), `business` (内部切换到另一业务, reuses `resolveTaskDeeplinkTarget`, always task id), or `purpose` (弹出当前任务的「任务目的」表格 via the shared `TaskPurposeDialog`, no target — configurable for any page incl. xdfx). **`host`(宿主路由)** asks the embedding parent to navigate: `runTaskButton` sends `window.parent.postMessage({ type:'HOST_NAVIGATE', path, queryParams:{ [idParam]: Number(taskId) } }, hostOrigin)` — `target` is the host route (e.g. `/task/item-aiceh/step-analysis-audience`), `appendTaskId`/`idParam` become numeric `queryParams` (task id only), origin from `runtime-config.js` `VITE_HOST_NAVIGATE_ORIGIN` (else ancestorOrigins/referrer; never `*`). Independent-tab clicks toast and do nothing. **`url` buttons support two independent, coexisting login-append mechanisms**: (1) **`loginParams` (追加登录参数, like 应用管理/Light App Center)** — a list of `{key, source, customValue}` resolved at click time: `runTaskButton` reads `userInfo` (via `readUserInfo` from `strategy-components/lib/light-app`, embed-isolated through `authStorage`) and appends `?{key}={value}` for each (`source` = a userInfo field such as `accessToken`/`yUserId`, or `other` → literal `customValue`); empty list = nothing appended. Reuses `LOGIN_SOURCE_OPTIONS` from light-app; stored as JSON column `task_buttons.login_params_json` (`PortableJSON`, migration `20260625_01`). (2) **`appendAuth` (追加登录态)** — appends `?{authTokenParam}={token1}&{authNameParam}={username}` (default param names `token`/`username`) so the跳转目标外部系统 can identify the current user — e.g. `…/action/sentiment?token=<JWT>&username=lizhaoxing`. **Gated on token login**: `token1` = the `?authToken=` used by token-exchange login; `username` = the raw login name the backend resolved from `getTokenInfo`. Both are stashed at login by `persistLoginCredentials` into `login.token1`/`login.username` (`core/auth/login-credentials.ts`, scoped via [[scoped-storage]] so嵌入/独立会话隔离 + 随独立会话迁移). Only token login writes them → a non-token-login session has no `token1`, so `runTaskButton` silently skips the auth append (the jump still works, just without those two params). The frontend reads `username` straight from the new `UsernameLoginResponse.username` field (the stored email local-part is lossy — lowercased/normalized — so not used), **not** by decoding the JWT. Stored as columns `task_buttons.{append_auth, auth_token_param, auth_name_param}` (migration `20260625_02`). The admin page renders both editors for `url` buttons (loginParams 虚线框 + 追加登录态 switch). **`idKind` (`task`/`action`) only matters for xdfx**: its deep-link `?taskId=` is an 行动id and the 任务id is resolved at login (`fetchTaskIdFromAction`) — `TaskContext` now also stashes the raw `actionId`, so a url button can append either (default `task`). Page `TaskButtonsPage.tsx` (route `/page/strategy/admin/task-buttons`, **admin-gated**, entry「按钮管理」in the bottom-left settings dropdown of `components/page-sidebar.tsx`, both full + collapsed modes) has per-business tabs, edits name/type/target/启停/排序/增删, saves the **whole set atomically** (replace-all), plus 「导入默认」 to merge code-seed defaults. **Seed/fallback** (like 敏感词管理): only when the whole table is empty (fresh deploy, never saved) do the workspace + page fall back to `defaultTaskButtons(cfg)` — rwfx's url buttons (编辑/上一步/下一步/3q详情) built from the **live** `/api/public/config/task-deeplink` plus cross-business switch buttons for **all three** businesses (each switches to the other two — rwfx→三情/行动, 3qfx→任务/行动, xdfx→任务/三情). Once saved, the store is the sole source of truth. **Bottom 快捷跳转 bar groups by prev/next**: `TaskJumpBar` renders only「上一步/下一步」-type buttons in the bottom bar — a `prev` group (id 含 `prev` 或文案「上一步」, 描边次要样式 + ←图标) rendered **左侧**, then a `next` group (id 含 `next` 或文案「下一步」, 实心主色) on the **右侧** (container `justify-end`); everything else goes to the right-edge floating menu. The default 上一步 button (`rwfx-prev`, `url`, target = `DASHBOARD_AGENT_ROUTE` `/page/strategy/dashboard-agent`, `appendTaskId` + `idParam=taskId` → `?taskId=任务id`, `openMode=self`) 默认指向**应用内**「大屏绘制」Line truncated
- **实时并发监控 (Concurrency / System-Pressure Monitor, admin-only)**: a live panel mounted at the **top of the admin 排行榜 page** (`components/workspace/admin/concurrency-monitor.tsx` `ConcurrencyMonitorPanel`, rendered in `pages/AdminUserLeaderboardPage.tsx`) showing **当前并发的大模型调用数 + 列表(用户/智能体/类型/已运行时长)**, each row with a 「停止」button (and a 「全部停止」) that **truly aborts** that run's in-flight model stream via `RunManager.cancel` (`POST /api/admin/active-runs/{run_id}/cancel`) — to relieve pressure when 使用人数过多. Two line charts (minute/hour toggle): **并发量折线图** (peak/avg, `GET /api/admin/active-runs/concurrency`, fed by a lightweight background sampler into `concurrency_samples`) and **大模型出字速度折线图** (tokens/sec, `GET /api/admin/active-runs/token-speed`, aggregated from `llm_call_metrics`) so a dip pinpoints where the bottleneck is. A **「后台采样」Switch** (`system_settings.json → concurrency_monitor.enabled`, **default off / opt-in**, `GET|PUT /api/admin/active-runs/settings`) turns the background sampling on/off **at runtime, no restart** (the live concurrency count + 「停止」 work even while sampling is off — only the 并发量 history chart needs it on); everything is designed to **never impact production** (one tiny INSERT/15s, retention-purged, best-effort). Client/hooks: `core/admin/active-runs.ts` + `core/admin/hooks.ts` (`useActiveRuns`/`useConcurrencySeries`/`useTokenSpeedSeries`/`useCancel*`/`useMonitorSettings`). See the backend CLAUDE.md「Admin Concurrency Monitor」.
- **会话冲突 409 中文化**: when a user submits a new question while the previous turn is still streaming, the backend's `RunManager.create_or_reject` rejects with HTTP 409 (`services.py` now returns a **Chinese** detail「当前对话还在生成回答…」). `core/threads/hooks.ts` `onError` detects the conflict (`isActiveRunConflictError`: 409 / "already has an active run" / the Chinese text). A premature SSE close (SDK treats it as success and restores the send button while the backend run is still occupying the thread) is recovered by `confirmOrRejoin`: hold the stop button, `joinStream` the live run, and on 409 auto-reconnect instead of a fake AI bubble. `sse_consumer` no longer ends a resumable (`on_disconnect=continue`) stream on a false-positive `is_disconnected()`.
- **State**: TanStack Query for server state, context providers (`SubtasksProvider`, `ArtifactsProvider`, `PromptInputProvider`) scoped to `WorkspaceRoutes`
- **LLM streaming**: `@langchain/langgraph-sdk` streams messages from the backend via SSE
- **UI**: Radix UI primitives + TailwindCSS v4 + shadcn-style components in `src/components/ui/`
- **Shims**: `src/shims/` provides `next/link` and `next/navigation` polyfills (original code was Next.js)
- **Login URL params** (`LoginPage.tsx`, frontend-only — the backend never sees these): besides the auth params (`ticket`/`userId`/`env`/`theme`/`yUserId`/`token`/`access_token`/`authToken`/`password`), the page supports a **task deep-link** via `?taskId=&goPath=`. After login it calls the consumer API `GET {VITE_AIPI_CONSUMER_URL}/taskAnalyseSearch/cop-task-detail?taskId=` (header `Authorization: Bearer admin`, auto-injected by `utils/request.ts`), stashes the full `data` (`id/overview/taskDirection/taskName/taskContent`) into `sessionStorage["login.copTaskDetail"]`, then routes by `goPath`: base codes `3qfx`/`rwfx`/`xdfx` → that business's configured **single agent** Q&A inside a **任务工作区** (resolved via `/api/business-mapping`; `resolveTaskDeeplinkTarget` calls `persistTaskContext({taskId, agentId, openingText})` and navigates to the `…/chats` **index**, which opens the latest task conversation or 新建 — a 1:N task↔对话 workspace, NOT `pendingAgentMessage`); the `-A` suffix (`3qfx-A`/…) → **multi-agent roundtable** with `roundtablePrefill.businessCode` so the page auto-selects the configured 业务链条. **xdfx's deep-link `?taskId=` is actually an 行动id, not a 任务id** — `resolveDeeplinkTaskId(goPath, rawId)` (called in `LoginPage` before everything) detects `xdfx`/`xdfx-A` and resolves it via `GET {action_detail_url}/{actionId}` → `data.taskId` (`fetchTaskIdFromAction`; `action_test`+`mock.action_detail` for offline testing); the resolved 任务id then drives `cop-task-detail`, the purpose tree, and the 1:N binding (other businesses pass the id through unchanged). goPath→businessCode: `3qfx`→`3Q`, `rwfx`→`6BF`, `xdfx`→`7BF`. The roundtable target also threads the URL `taskId` into `roundtablePrefill.taskId` (`resolveTaskDeeplinkTarget(goPath, detail, taskId)`), which turns on two taskId-scoped behaviors: (1) **separate, unpartitioned per-task storage** — taskId 会商聊天记录 live in their **own** store/table (`roundtable_task_drafts`), keyed **only by `task_id`** (one taskId = many records, shared across users, **no user 分权** at all; `created_by` is audit-only), kept entirely out of the per-user personal store (`roundtable_drafts`, now strictly per-user) so the two never mix. Backend router `/api/roundtable-task-drafts` (`GET /by-task/{id}` + `/by-task/{id}/latest`, `POST`, `GET/PUT/DELETE /{id}` — all user-agnostic); frontend client `roundtable-planning/api/task-drafts.ts`, and `useDraftPersistence`/`useRoundtableDrafts` route **all** CRUD to it when a `taskId` is present (else the personal `drafts.ts`). The matching **background jobs** are shared by task too: `roundtable_jobs.task_id` marks a task job; reads/dedup/stream/resume/cancel pass `?task_id=` so any user opening the task sees the same running 研讨 (progress/flowchart), and the executor writes the final report back to the task-draft store. Existing rows are moved over by `scripts/migrate_roundtable_task_drafts.py` (migration `20260618_01`). The history dropdown filters to the task and 新建 keeps the binding; (2) **Step-3 auto structured output** — after the `roundtable-summary` agent writes the Markdown report it automatically runs a second round emitting a `flow-json` flowchart (`useStep3Summary` `autoFlow`+`chainLevels`), whose hierarchy follows the business chain's stage goals (任务 → 目的 → 行为体 → …; coordinatorPrompt-specified hierarchy wins) and whose nodes never carry 阶段编号/阶段名 (the prior bug). **Both targets render embedded under the 任务管理 layout** — nested routes under `task-management/<business-path>/{roundtable,agent/:agent_id/chats}` in `StrategyRoutes.tsx` (`<business-path>` = `plan-task-sentiment` / `plan-task/plan-task-fx` / `plan-task/plan-task-action`, matching the COH中任务 menu paths in `sidebar-menu.ts`) so the global sidebar keeps 任务管理 → COH中任务 → the matching business highlighted. **All three single-agent businesses share `TaskFxWorkspace`** (`task-components/TaskFxWorkspace.tsx`): left = a「当前任务」card (`readCopTaskDetail()` 任务名称 + 简介, desensitized, 留存 above 新建对话) + per-task 1:N conversation list (`useTaskThreads(taskId, agentId)` — filtered by **both** `metadata.taskId` AND `metadata.agent_id` so the three businesses' conversations stay isolated even though they share one taskId) + 新建对话; the `…/chats` index (`TaskFxIndexResolver`) opens the latest task thread or 新建. The right `:thread_id` host differs by business: **rwfx** → `TaskFxChat` (`AgentChatPage taskGate`) = full workspace (non-`lite`): 目的树闸门 panel + 清除记录 (placed under 新建对话); **xdfx** → also `TaskFxChat` (same 目的树闸门 query+display, same `purpose_detail_url`) but workspace passed `lite`; **3qfx** → `TaskBindChat` (`AgentChatPage taskBind`, `lite`) = 1:N list only, no gate, and 新建对话 **auto-sends** the task opening text (`taskAutoSendText`; gate Line truncated
- **iframe 嵌入模式 (外部系统用 iframe 套用深链问答/会商)** — 三个**按标签页**开关,全部由深链 URL 参数开启、存进同一份 `sessionStorage` 会话(`embed.session`,键名常量在 `core/embed/embed-session.ts`),跨登录跳转/刷新/页内导航存活,**绝不跨标签污染**同浏览器另开的正常系统页。核心隔离手法:用 `sessionStorage`(按标签页/浏览上下文隔离,iframe 即便同源也有独立一份)而非 `localStorage`(跨标签共享)。开关:(1) **`?embed=1`(可带 `&theme=`)** — 去全局 chrome(`PageLayout` 的 `pageSidebarAllowed && !isEmbedActive()` → 隐藏 Header + PageSidebar)+ 按外部主题色**强制**明/暗:走 next-themes 的 `forcedTheme`(`App.tsx` `AppProviders` 调 `resolveForcedEmbedTheme`,**不写** localStorage `strategy-theme`),离散映射 `dark-blue`/`dark`→深、其余→浅;嵌入侧**绝不**调 `setTheme`/`persistSidebarEnabled`(那俩落 localStorage 跨标签污染,`LoginPage` 据 `readEmbedParam` 跳过)。(2) **`?hideJump=1`** — 隐藏深链底部「快捷跳转」栏 `TaskJumpBar` 的两部分(底部「下一步」等按钮 + 右侧垂直居中悬浮菜单),单智能体问答 + 会商共用该栏,`isJumpBarHidden()` 为真时整条 `return null`。(3) **登录用户隔离** — 嵌入态下鉴权/身份键(`deerflow.auth` token、`userInfo`、`login.*`、`tools_token`、maxkey/userDetail token)全部经 `core/auth/scoped-storage.ts` 的 `authStorage()`(嵌入→sessionStorage / 正常→localStorage)读写,使 iframe 里登录的用户与正常登录用户**完全隔离**、互不覆盖;所有 token 读取都过 `getStoredAuth()`/`getAuthorizationHeaderValue()`(API 客户端 `core/api/*` 全走这俩),改中心函数即让全体调用方自动隔离;跨标签账号变更监听 `AuthSyncWatcher`(`core/auth/sync.tsx`)在嵌入态禁用。嵌入会话在 `main.tsx` 渲染前 `syncEmbedSessionFromCurrentUrl()` 同步启用(早于任何鉴权写入,避免首帧 effect 顺序漏写 localStorage);`AppProviders` 的 effect 再按 SPA 导航同步。`embed=0`/`hideJump=0` 可显式关闭。正常(非嵌入)标签页所有 `isXxx()` 恒 false,行为**零变化**。第三个开关 `?isolate=1`(**独立登录会话**)把同一套**登录用户隔离**单独提供给**普通(带 chrome)标签页**——只切换鉴权存储、不去 chrome / 不强制主题 / 不动跳转栏:`authStorage()` 的条件从「仅嵌入」放宽为 `isEmbedActive() || isIsolatedSession()`,`AuthSyncWatcher` 的跨标签监听对嵌入态**或**独立态都即时忽略(handler 内实时判,运行时开关也即刻生效)。除 URL 参数外,**设置 → 外观 →「登录会话」** 有一个 Switch「独立登录会话(本标签页)」运行时切换(`setIsolatedSession`,`appearance-settings-page.tsx`):**开启时先 `migrateAuthToSession()`**(`scoped-storage.ts`,把 localStorage 的受保护键 `deerflow.auth`/`userInfo`/`userId`/`tools_token` + `login.*` 前缀快照搬进 sessionStorage)再翻标志,故无感不登出;此后本标签页登录态独立——别处登录/换号影响不到它,它换号也影响不到别人,但关掉该标签即结束(需重登)。开启给 toast 提示。
- **Login URL params** (`LoginPage.tsx`, frontend-only — the backend never sees these): besides the auth params (`ticket`/`userId`/`env`/`theme`/`yUserId`/`token`/`access_token`/`authToken`/`password`), the page supports a **task deep-link** via `?taskId=&goPath=`. After login it calls the consumer API `GET {VITE_AIPI_CONSUMER_URL}/taskAnalyseSearch/cop-task-detail?taskId=` (header `Authorization: Bearer admin`, auto-injected by `utils/request.ts`), stashes the full `data` (`id/overview/taskDirection/taskName/taskContent`) into `sessionStorage["login.copTaskDetail"]`, then routes by `goPath`: base codes `3qfx`/`rwfx`/`xdfx` → that business's configured **single agent** Q&A inside a **任务工作区** (resolved via `/api/business-mapping`; `resolveTaskDeeplinkTarget` calls `persistTaskContext({taskId, agentId, openingText})` and navigates to the `…/chats` **index**, which opens the latest task conversation or 新建 — a 1:N task↔对话 workspace, NOT `pendingAgentMessage`); the `-A` suffix (`3qfx-A`/…) → **multi-agent roundtable** with `roundtablePrefill.businessCode` so the page auto-selects the configured 业务链条. **xdfx's deep-link `?taskId=` is actually an 行动id, not a 任务id** — `resolveDeeplinkTaskId(goPath, rawId)` (called in `LoginPage` before everything) detects `xdfx`/`xdfx-A` and resolves it via `GET {action_detail_url}/{actionId}` → `data.taskId` (`fetchTaskIdFromAction`; `action_test`+`mock.action_detail` for offline testing); the resolved 任务id then drives `cop-task-detail`, the purpose tree, and the 1:N binding (other businesses pass the id through unchanged). **xdfx additionally partitions its chat records by 行动id (action_id), NOT by task_id**: `resolveTaskDeeplinkTarget` sets `partitionByAction:true` + keeps the raw action_id as `TaskContext.actionId`, so new threads are tagged `metadata.{taskId,actionId}` (taskId kept only to preserve the backend「任务深链对话全局共享」semantics, which keys off `metadata.taskId`) and the conversation list filters by `actionId` (+`agent_id`) — different actions of the same task get separate lists. xdfx's first-question opening text also appends `行动id(action_id)为…` (see `buildOpeningText` / `taskThreadMetadata`). goPath→businessCode: `3qfx`→`3Q`, `rwfx`→`6BF`, `xdfx`→`7BF`. The roundtable target also threads the URL `taskId` into `roundtablePrefill.taskId` (`resolveTaskDeeplinkTarget(goPath, detail, taskId)`), which turns on two taskId-scoped behaviors: (1) **separate, unpartitioned per-task storage** — taskId 会商聊天记录 live in their **own** store/table (`roundtable_task_drafts`), keyed **only by `task_id`** (one taskId = many records, shared across users, **no user 分权** at all; `created_by` is audit-only), kept entirely out of the per-user personal store (`roundtable_drafts`, now strictly per-user) so the two never mix. Backend router `/api/roundtable-task-drafts` (`GET /by-task/{id}` + `/by-task/{id}/latest`, `POST`, `GET/PUT/DELETE /{id}` — all user-agnostic); frontend client `roundtable-planning/api/task-drafts.ts`, and `useDraftPersistence`/`useRoundtableDrafts` route **all** CRUD to it when a `taskId` is present (else the personal `drafts.ts`). The matching **background jobs** are shared by task too: `roundtable_jobs.task_id` marks a task job; reads/dedup/stream/resume/cancel pass `?task_id=` so any user opening the task sees the same running 研讨 (progress/flowchart), and the executor writes the final report back to the task-draft store. Existing rows are moved over by `scripts/migrate_roundtable_task_drafts.py` (migration `20260618_01`). The history dropdown filters to the task and 新建 keeps the binding; (2) **Step-3 auto structured output** — after the `roundtable-summary` agent writes the Markdown report it automatically runs a second round emitting a `flow-json` flowchart (`useStep3Summary` `autoFlow`+`chainLevels`), whose hierarchy follows the business chain's stage goals (任务 → 目的 → 行为体 → …; coordinatorPrompt-specified hierarchy wins) and whose nodes never carry 阶段编号/阶段名 (the prior bug). **Both targets render embedded under the 任务管理 layout** — nested routes under `task-management/<business-path>/{roundtable,agent/:agent_id/chats}` in `StrategyRoutes.tsx` (`<business-path>` = `plan-task-sentiment` / `plan-task/plan-task-fx` / `plan-task/plan-task-action`, matching the COH中任务 menu paths in `sidebar-menu.ts`) so the global sidebar keeps 任务管理 → COH中任务 → the matching business highlighted. **All three single-agent businesses share `TaskFxWorkspace`** (`task-components/TaskFxWorkspace.tsx`): left = a「当前任务」card (`readCopTaskDetail()` 任务名称 + 简介, desensitized, 留存 above 新建对话) + per-task 1:N conversation list (`useTaskThreads(taskId, agentId, actionId?)` — filtered by **both** `metadata.taskId` AND `metadata.agent_id` so the three businesses' conversations staLine truncated
- **iframe 嵌入模式 (外部系统用 iframe 套用深链问答/会商)** — 三个**按标签页**开关,全部由深链 URL 参数开启、存进同一份 `sessionStorage` 会话(`embed.session`,键名常量在 `core/embed/embed-session.ts`),跨登录跳转/刷新/页内导航存活,**绝不跨标签污染**同浏览器另开的正常系统页。核心隔离手法:用 `sessionStorage`(按标签页/浏览上下文隔离,iframe 即便同源也有独立一份)而非 `localStorage`(跨标签共享)。开关:(1) **`?embed=1`(可带 `&theme=`)** — 去全局 chrome(`PageLayout` 的 `pageSidebarAllowed && !isEmbedActive()` → 隐藏 Header + PageSidebar)+ 按外部主题色**强制**明/暗:走 next-themes 的 `forcedTheme`(`App.tsx` `AppProviders` 调 `resolveForcedEmbedTheme`,**不写** localStorage `strategy-theme`),离散映射 `dark-blue`/`dark`→深、其余→浅;嵌入侧**绝不**调 `setTheme`/`persistSidebarEnabled`(那俩落 localStorage 跨标签污染,`LoginPage` 据 `readEmbedParam` 跳过)。(2) **`?hideJump=1`** — 隐藏深链底部「快捷跳转」栏 `TaskJumpBar` 的两部分(底部「下一步」等按钮 + 右侧垂直居中悬浮菜单),单智能体问答 + 会商共用该栏,`isJumpBarHidden()` 为真时整条 `return null`。(2.5) **`?hideChrome=1`** — **仅**去全局 chrome(Header 导航栏 + PageSidebar 侧边栏),**不**强制主题、**不**隔离鉴权(区别于 `embed`:只想要一个干净全屏页面,如「大屏绘制」`/page/strategy/dashboard-agent?taskId=…&hideChrome=1`)。新增 `EmbedSession.hideChrome` 字段 + `readHideChromeParam()` + `isChromeHidden()`(取 `embed || hideChrome` 之并),与 `hideJump` 完全对称;`PageRoutes.tsx` 的 `PageLayout` 把 `chromeHidden`(`isChromeHidden() || readHideChromeParam(location.search)==="on"`)并入 `pageSidebarAllowed`,且其**优先级高于** dashboard-agent 路由原本的强制全局 chrome(`forceChromeForDashboardAgent`)。`hideChrome=0` 可显式关闭。(3) **登录用户隔离** — 嵌入态下鉴权/身份键(`deerflow.auth` token、`userInfo`、`login.*`、`tools_token`、maxkey/userDetail token)全部经 `core/auth/scoped-storage.ts` 的 `authStorage()`(嵌入→sessionStorage / 正常→localStorage)读写,使 iframe 里登录的用户与正常登录用户**完全隔离**、互不覆盖;所有 token 读取都过 `getStoredAuth()`/`getAuthorizationHeaderValue()`(API 客户端 `core/api/*` 全走这俩),改中心函数即让全体调用方自动隔离;跨标签账号变更监听 `AuthSyncWatcher`(`core/auth/sync.tsx`)在嵌入态禁用。嵌入会话在 `main.tsx` 渲染前 `syncEmbedSessionFromCurrentUrl()` 同步启用(早于任何鉴权写入,避免首帧 effect 顺序漏写 localStorage);`AppProviders` 的 effect 再按 SPA 导航同步。`embed=0`/`hideJump=0` 可显式关闭。正常(非嵌入)标签页所有 `isXxx()` 恒 false,行为**零变化**。第三个开关 `?isolate=1`(**独立登录会话**)把同一套**登录用户隔离**单独提供给**普通(带 chrome)标签页**——只切换鉴权存储、不去 chrome / 不强制主题 / 不动跳转栏:`authStorage()` 的条件从「仅嵌入」放宽为 `isEmbedActive() || isIsolatedSession()`,`AuthSyncWatcher` 的跨标签监听对嵌入态**或**独立态都即时忽略(handler 内实时判,运行时开关也即刻生效)。除 URL 参数外,**设置 → 外观 →「登录会话」** 有一个 Switch「独立登录会话(本标签页)」运行时切换(`setIsolatedSession`,`appearance-settings-page.tsx`):**开启时先 `migrateAuthToSession()`**(`scoped-storage.ts`,把 localStorage 的受保护键 `deerflow.auth`/`userInfo`/`userId`/`tools_token` + `login.*` 前缀快照搬进 sessionStorage)再翻标志,故无感不登出;此后本标签页登录态独立——别处登录/换号影响不到它,它换号也影响不到别人,但关掉该标签即结束(需重登)。开启给 toast 提示。
- **操作日志(Y-Log)上报** — 用户的关键操作(登录登出/查询/查看/增删改/启停/导入导出/问答等)成功后,**前端直连**外部接口 `POST {write_url}`(默认 `https://ch1.b.uat.4.cn/api/y-log/write`)记一条审计日志。核心模块 `src/core/log/`:`y-log.ts`(`writeYLog(params)` + `OptType` 枚举 0/1/3..12;**异步即发即忘、永不 await、永不抛错、失败静默**,自动把完整 url 转相对路径去 ip/host、对象入参/返回自动 `JSON.stringify` + 50k 裁剪、`optResult` 恒 0 只报成功),`y-log-config.ts`(从公开只读 `GET /api/public/config/y-log` 拉 `{enabled, writeUrl}`,模块级缓存 + 去重 + 默认兜底;`App.tsx` `AppProviders` 启动预热 `fetchYLogConfig()`),`y-log-token.ts`(token1 = token 登录的 `?authToken=`,经 [[scoped-storage]] 的 `authStorage*` 存取,嵌入态自动隔离)。**双门控**:仅当①存在 token1(即用 token 登录,`LoginPage` 成功后 `persistYLogToken(authToken)`,登出 `account-settings-page.tsx` 先报后清 token1)且②配置 `enabled && writeUrl` 才上报;否则一律不发。`optDetail` 统一「CM助手-全量-…」(**禁内部框架名**)。埋点**广覆盖**各 API client 的成功路径——原则是「一个用户操作(查看/查询/新增/编辑/删除/启停/导入导出)= 一条日志」,每个 API client 的**单条详情 GET(查看→view 4)/ 列表查询 GET(search 3)/ 新增 POST(create 9)/ 改 PUT·PATCH(edit 5)/ 删 DELETE(delete 6)/ 启停(enabled 11 / disabled 10)/ 导入导出(import 7 / export 8)**都各落一条,仅跳过高频 typeahead/状态轮询/纯 bootstrap config 读。覆盖文件:`strategy-components/api/{sensitive-words,menu-overrides,task-buttons,skill-addresses,light-apps,business-mapping}.ts`、`roundtable-planning/api/{drafts,task-drafts,roundtable-jobs,recommend,chains,multi-agent,dashboard-sessions}.ts`、`core/{agents,scheduled-tasks,knowledge,positions,tags,studio,system-settings,memory,mcp,models,custom-prompts,user-preferences,notifications,recommended-questions,user-qa,curator,admin,thread-shares,roundtable-draft-shares,tool-metrics,llm-metrics,note,artifacts}/api.ts`、`core/api/markdown-docx-export.ts`。**问答(Q&A)改为「一次大模型调用 = 一条日志」**:在共享的 `core/threads/hooks.ts` `useThreadStream` 的 `onLangChainEvent` 里监听 `on_chat_model_end`,每次模型调用结束就上报一条(optType 12,`reqParam` 取本次 input 的最后一条 user 文本 + 模型名,`returnParam` 取本次输出文本)——一个问答轮次里 lead agent / 子代理的**每次** LLM 调用都各记一条,覆盖所有走 `useThreadStream` 的页面(`ChatPage`/`AgentChatPage`/创建智能体/iframe/会商等);`ChatPage`/`AgentChatPage` 的 `onFinish` 仍额外保留一条轮次汇总。后端仅新增公开只读配置:`deerflow/config/y_log_config.py`(`YLogConfig{enabled,write_url}`)挂到 `AppConfig.y_log`,`app/gateway/routers/public_config.py` 加 `GET /api/public/config/y-log`,地址写在 `config.yaml` 的 `y_log` 段(mtime 热重载,前端无需重建);**不做后端代理**。Tests:`tests/test_y_log_config.py`。
### Configuration
File diff suppressed because it is too large. Load diff
+1 -1
View File
@@ -8,7 +8,7 @@ VITE_USE_REAL_DATA=true
VITE_MOCK_COP_TASK_DETAIL=true
# 研判情报报告(大屏绘制智能体深链 selectSqReport)数据源:true 走本地样例假数据(真实接口未就绪时调试用);联调通过后置 false。
VITE_MOCK_SQ_REPORT=true
VITE_MOCK_SQ_REPORT=false
# 深链任务详情(cop-task-detail:任务名称/描述)数据源:true 走本地假数据(真实接口未就绪时调试用);联调通过后置 false。
VITE_MOCK_COP_TASK_DETAIL=true
+9
View File
@@ -37,6 +37,10 @@
# 默认真实接口(未设/false);改成 true 时该接口走本地假数据(consumer 外网不可达时调试用)。
# 与 VITE_USE_REAL_DATA 独立。改后需重启 dev / 重新打包生效。
# VITE_MOCK_COP_TASK_DETAIL=false
# VITE_POSITION_ROUNDTABLE_DEMO_MODE=false
# true=免登录直达岗位分析,完全使用前端 JSON,不请求任何后台接口。
# 仅限离线演示环境;生产环境请保持 false。
# VITE_POSITION_ROUNDTABLE_STANDALONE_MODE=false
# MaxKey 鉴权根地址(无界 onlineTicket 换 token)
# VITE_AUTH_BASE_URL=https://auth.y.sit.4.cn
@@ -50,4 +54,9 @@
# 可选
# VITE_CANVAS_LANGGRAPH_BASE_URL=
# VITE_STATIC_WEBSITE_ONLY=
# 部署级紧凑导航:true 时固定收起工作台左侧栏,并隐藏换肤与全量/简洁模式切换。
# VITE_FORCE_COLLAPSED_SIDEBAR=false
# 简介模式左侧菜单类型:与菜单管理页「简介模式」的类型 A / B 对应。两套网页分别填 A 或 B。
# 不填或留空时按类型 A,继续使用原来的简介菜单数据。
# VITE_COMPACT_MENU_TYPE=A
# VITE_GITHUB_OAUTH_TOKEN=
+3 -3
View File
@@ -14,8 +14,8 @@ VITE_MOCK_SQ_REPORT=false
VITE_MOCK_COP_TASK_DETAIL=false
# Gateway / DeerFlow API
VITE_BACKEND_BASE_URL=http://47.88.25.99:7001
VITE_LANGGRAPH_BASE_URL=http://47.88.25.99:7001/api
VITE_BACKEND_BASE_URL=http://10.19.200.5:2026
VITE_LANGGRAPH_BASE_URL=http://10.19.200.5:2026/api
# 轻应用「新建笔记」系列接口
VITE_NOTE_API_BASE_URL=http://47.88.25.99:8000
@@ -42,7 +42,7 @@ VITE_AIPI_BACKENP_URL=http://47.88.25.99:8000
# VITE_AIPI_FRONTEND_URL=https://knowledgetoolserver.b.uat.4.cn
VITE_NOTEBOOK_API_BASE_URL=http://47.88.25.99:8000
VITE_AIPI_FRONTEND_URL=http://47.88.25.99:3000
VITE_AIPI_CONSUMER_URL=https://ch1.b.uat.4.cn/consumer
VITE_AIPI_CONSUMER_URL=http://10.19.200.5:8002/consumer
# A 系统跳转地址(人物/组织/事件等列表项打开链接)
VITE_AIPI_PRESENT_URL=http://present.a.uat.4.cn/present/domain
# B 系统知识库 iframe 根地址
+46
View File
@@ -0,0 +1,46 @@
**Comparison target**
- Source visual truth (dark intelligent-agent list): `C:/Users/董宏凯/AppData/Local/Temp/codex-clipboard-75f6ce1c-cd70-4b8c-a80a-a3d100105c69.png`
- Additional source references: `C:/Users/董宏凯/AppData/Local/Temp/codex-clipboard-00567484-ba8a-4595-b386-52e1467ae9cf.png` (segmented switch), `C:/Users/董宏凯/AppData/Local/Temp/codex-clipboard-02808803-05ba-4f2c-be50-c72b484a9f06.png` (business-chain node card), `C:/Users/董宏凯/AppData/Local/Temp/codex-clipboard-adf38fec-7baf-4d01-9c73-bdbae94b774e.png` (business-chain selector)
- Implementation screenshots: `C:/Users/董宏凯/AppData/Local/Temp/position-roundtable-revised-light.png`, `C:/Users/董宏凯/AppData/Local/Temp/position-roundtable-revised-dark.png`
- Full-view comparison evidence: `C:/Users/董宏凯/AppData/Local/Temp/position-roundtable-revised-comparison.png`
- Viewport: 1280 × 720. Light route: `#/page/strategy/qa/position-roundtable`; dark embedded route: `#/page/strategy/qa/position-roundtable?embed=1&theme=dark`.
- State: local browser has no authenticated API session. The original intent API is invoked and reports `Authentication required`; business-chain and agent endpoints return no usable data.
**Findings**
- [P1] Populated agent and business-chain states cannot be compared yet.
Location: right agent list and non-planning-role chain diagram.
Evidence: reference images show populated cards and nodes; the implementation has `0 个` agents and no available business chain in the unauthenticated preview.
Impact: card density, selected-card indicator, chain node flow, and agent-detail transition cannot be truthfully verified against live data.
Fix: verify the route in an authenticated session with at least one public chain and tagged agents.
**Open Questions**
- The final business-chain stage arrangement is still pending product confirmation. The compact graph maps whatever stage configuration is returned, while intentionally omitting dependency-label text as requested.
**Implementation Checklist**
1. Left task panel is now display-only and retains its independent position-roundtable task adapter.
2. Business-chain selection uses the original roundtable card/radio/relationship-entry pattern.
3. Every position uses the original `useStep1Intent` interface and `Step1Panel` message list/input panel; only the position header changes.
4. The right switch now uses the exact `课题研究 / ai写作` segmented-control treatment (light gray track, white active state; dark blue glass equivalent).
5. The embedded layout widens the left panel to 360px and applies the deep-blue right-panel tokens used by the reference.
6. Other roles render a taller top-to-bottom card-node flow without dependency labels. The canvas supports mouse-drag panning, and each node retains only a name plus a single-line description.
**Follow-up Polish**
- [P3] If live content is unusually long, tune the compact flow node width or horizontal scrolling after seeing the production chain data.
**Comparison history**
- Iteration 1: task fields were editable and the right TDesign card tabs looked unlike the reference. Replaced the task form with display-only information and replaced the tabs with the existing `课题研究 / ai写作` segmented switch.
- Iteration 2: business-chain selection was a dropdown and the flow was vertical avatar chips. Replaced it with original-roundtable selection cards and compact business-chain configuration-style node cards with link lines but no dependency labels.
- Iteration 3: dark right-panel background differed from the supplied deep-blue reference. Applied the `#032650` / `#042b59` / `#2b8ffe` token family and captured the revised embedded dark state in the full-view comparison.
- Iteration 4: removed the custom disabled input from non-planning positions and reused the original roundtable input panel. Enlarged the left flow viewport, retained its connection lines, and removed node level/seat/status metadata.
- Iteration 5: converted the compact flow from left-to-right to top-to-bottom. Added mouse-drag panning and single-line description truncation; populated-chain visual QA remains blocked by the unauthenticated preview.
- Iteration 6: constrained the flow canvas to its card viewport, narrowed nodes from 190px to 158px, and realigned branch gaps plus connector anchors to prevent clipping and offset lines.
**Final result**
blocked
@@ -0,0 +1,507 @@
# AI 写作「对话驱动写作台」实现方案(可落地版)
> 需求:**复制**现有 AI 写作代码,新增一个独立页面(**原页面/原路由零改动**)。在新页面里
> **大改交互流程**——去掉「素材收集 / 大纲规划 / 作家写作 / 编辑审核」四个阶段干预卡里的**输入框**,
> 只**保留原来的确认按钮**;在页面**底部新增一个统一的多行智能输入框**,具备**强意图理解**能力:
> 重新搜索、新增检索词、添加检索素材、重新规划大纲、按要求改大纲、提修改意见、审核意见、
> 素材不足继续搜集、对写作内容提问……**覆盖现有全部交互甚至更多**。
>
> 交互节奏不变:**一步一确认**——进行到某个专家阶段时,交互就针对该专家(阶段作用域);
> 用户可以**点原来的确认按钮**,也可以**在底部输入框里发「继续下一步」的意图**推进。
> 意图**拿不准时**主动向用户**发起协助/澄清**,绝不盲目触发高代价动作(定稿 / 重搜等)。
本文是**实现指引**,落地时按第 9 节路线图分阶段推进。文中所有文件路径、符号名均对齐当前代码。
---
## 1. 现状梳理(改造地基)
现有 AI 写作是一套**独立 LangGraph 子系统**(不是 lead_agent),前后端都已成型、可复用。
### 1.1 后端 `ai_writing` graph
- 图工厂:`offline-backend-20260512/backend/packages/harness/deerflow/agents/ai_writing/graph.py`
(`make_ai_writing_graph`,registered as `assistant_id="ai_writing"`)
- 状态:`.../ai_writing/state.py`(`AIWritingState`)
- 四个「阶段大脑」节点:
| 阶段 | 节点 | 文件 |
|------|------|------|
| 素材收集 | `researcher` | `nodes/researcher.py` |
| 大纲规划 | `writer_outline` | `nodes/writer_outline.py` |
| 作家写作 | `writer_draft` | `nodes/writer_draft.py` |
| 编辑审核 | `editor` | `nodes/editor.py` |
- **五个暂停点**(`interrupt()`,`Command(resume=payload)` 续跑)——这是对话改造的核心可复用资产:
| pause_point | 语义 | 现有 action |
|-------------|------|-------------|
| `material_confirm` | 素材确认 | `confirm` / `re_search` / `enable_skill_search` |
| `outline_confirm` | 大纲确认 | `confirm` / `re_outline` |
| `draft_confirm` | 草稿确认 | `to_editor` / `finalize` / `user_revise` |
| `review_confirm` | 编辑打回确认 | `accept_review` / `force_finalize` |
| `section_help` | 素材不足求助 | `section_help`(+`sectionDecisions`) |
- resume 载荷(`UserInterventionPayload`,`types/ai-writing.ts`)字段:`action`、`approvedMaterialIds`、
`userQuery`(自然语言补充检索)、`editedOutline`、`outlineFeedback`、`userRevisionNotes`、
`overrideVerdict`、`selectedIssueIndices`、`sectionDecisions`。
**协议已同时支持「自然语言 + 结构化 action」**——这是对话层能复用的关键。
> 结论:**状态机 / 流式 / 暂停·续跑协议 / 持久化都可复用**,无需重写引擎。改造本质是
> 「把分散在干预卡里的输入框,换成一个底部智能输入框 + 意图路由层」,再把意图翻译回**现有
> `action + payload`**;仅少量新意图(对内容提问、素材不足自动回退重搜、追加审核意见)需新增能力。
### 1.2 前端 `open-canvas` 子系统
- 主页面:`frontend-web/src/open-canvas/pages/AIWritingPage.tsx`
- 路由注册:`open-canvas/routes/OpenCanvasRoutes.tsx`(`/page/canvas/ai-writing/*`)、
`pages/WorkspaceRoutes.tsx`(`/page/workspace/ai-writing/*`)、`pages/NotebookAIWritingPage.tsx`
- 状态机 + 流式:`contexts/AIWritingContext.tsx`(`useReducer` + LangGraph `useStream`,`assistantId:'ai_writing'`)
- 事件翻译 / reducer:`hooks/useAIWritingStream.ts`
- 类型:`types/ai-writing.ts`
- **左栏面板**:`components/ai-writing/AIWritingPanel.tsx`(时间线 + 干预卡 + 状态栏;idle 时挂启动表单)
- **要改造的输入 UI**(本次重点):
- 干预卡 `components/ai-writing/InterventionCard.tsx`:内含
`MaterialConfirmCard`(素材:有 `MaterialsToolbar` 输入框)、
`OutlineConfirmCard`(大纲:有 feedback textarea)、
`DraftConfirmCard`(草稿:有「修改意见」textarea)、
`ReviewConfirmCard`(审核:有「补充修改指令」textarea)、
`SectionHelpCard`(素材不足:按钮组)。
**每张卡里都既有输入框又有确认/动作按钮**——本次要**去掉输入框、保留按钮**。
- 启动表单 `components/ai-writing/AIWritingForm.tsx`(idle 阶段的配置表单)——本次由底部输入框接管启动。
- **已存在的对话原型**(可借鉴):`components/ai-writing/WritingSetupChat.tsx`
(`useThreadStream` 起 lead_agent 线程 + `setup_writing` 审批卡回填表单;仅管启动前配置,不直接复用)。
- 底部输入框可直接复用 UI 组件:`@/components/ai-elements/prompt-input`
(`PromptInput` / `PromptInputTextarea` / `PromptInputSubmit` / `PromptInputFooter`,见 `WritingSetupChat`)。
---
## 2. 目标与范围
### 2.1 必须满足
1. **复制式新增**:新目录 / 新路由 / 新侧边栏入口,**旧页面、旧路由、旧组件零改动**(「初始的不用动」)。
2. 页面**底部单一多行智能输入框**接管全流程交互;四个阶段干预卡里的**输入框全部移除**。
3. **保留确认按钮**:每个阶段到达暂停点时,消息流里仍渲染**产物卡 + 原来的确认/动作按钮**
(素材「确认素材」、大纲「确认大纲」、草稿「让编辑审核 / 确认定稿」、审核「按编辑意见修改 / 强制定稿」、
素材不足的三选一按钮)。用户**点按钮**或**在底部输入框发自然语言意图**二选一均可推进。
4. **强意图理解**:把用户自由文本准确路由到正确动作,**覆盖现有全部交互 + 更多**(见 3.2)。
5. **阶段作用域**:意图解析必须知道「当前停在哪个专家阶段」,把同一句话按当前阶段翻译成对应 action。
6. **素材不足自动回退重搜**:修改意见需要的信息现有素材没有时,先重搜补素材、补完自动继续原意图。
7. **拿不准就协助**:低置信意图**不猜着执行**,走澄清追问(clarify)或用户协助。
8. 保留右侧草稿实时预览(可编辑)与时间线 / 进度展示。
### 2.2 明确不做(本期)
- 不改旧 `AIWritingPage` 及其 `AIWritingForm` / `InterventionCard`(这两个是要在**副本**里改的)。
- 不替换 `ai_writing` graph 四个阶段大脑逻辑,不动五个暂停点 / checkpoint / 持久化。
- 不引新状态管理库(继续 `useReducer` + `useStream`)。
### 2.3 复制策略(关键决策)
「复制一份」= **复制会被大改的表现层组件**(页面 + 干预卡 + 面板),**复用不改的引擎层**:
| 复制(新建副本,大改) | 复用(原样,不改;仅对 `types` 做**追加式**扩展) |
|------------------------|--------------------------------------------------|
| 新页面 `AIWritingChatPage.tsx` | `contexts/AIWritingContext.tsx`(状态机 + 流式) |
| 新面板 `WritingChatPanel.tsx`(消息流 + 底部输入框) | `hooks/useAIWritingStream.ts`(事件 → state) |
| 新消息卡 `chat-cards/*`(产物卡+确认按钮,**无输入框**) | `components/ai-writing/AIWritingDraftPanel.tsx`(右侧草稿预览) |
| 新意图客户端 `api/ai-writing-intent.ts` | 各流式展示子组件(`MaterialsCard`/`OutlineCard`/`ReviewCard`/`SkillStepsCard`…) |
| (可选)新 `contexts/WritingChatContext.tsx` 包一层「pending 意图 / 澄清态」 | `types/ai-writing.ts`(**只加字段不改旧字段**,保证旧页面不受影响) |
> **不复用、也不改** 的三个「输入框组件」:`AIWritingForm` / `InterventionCard` / `WritingFormContext`——
> 旧页面继续用它们,新页面完全不引用它们。这样「初始的不用动」得到硬保证。
>
> 为什么复用 `AIWritingContext` 而不复制它?它**不含任何输入框 UI**,只是「状态机 + 与后端 graph 的
> 流式桥」,复用它**不会改动旧页面的任何呈现**(旧页面照常在自己的 Provider 实例里跑)。复用能显著
> 降低维护成本、避免两套引擎漂移。若要绝对物理隔离,也可整目录复制 `AIWritingContext` +
> `useAIWritingStream` 到新目录——**推荐先复用**,仅当后续需要给对话态加大量图内新协议时再分叉。
---
## 3. 核心设计
### 3.1 三层结构
```
┌──────────────────────────────────────────────────────────────┐
│ 对话 UI 层(新) WritingChatPanel │
│ - 消息流:用户消息 + AI 阶段产物卡(含【保留的确认按钮】)+ 进度 │
│ - 底部:统一多行智能输入框(唯一自由输入入口) │
│ - 右侧:草稿实时预览(复用 AIWritingDraftPanel) │
└───────────────┬──────────────────────────────────────────────┘
│ 用户自然语言(+ 当前 status/pausePoint 上下文)
▼
┌──────────────────────────────────────────────────────────────┐
│ 意图解析层(新,核心) POST /api/ai-writing/sessions/{id}/intent │
│ 输出:{ intent, pausePoint, action, payload, │
│ needResearch, researchQuery, answer, confidence, clarify }│
└───────────────┬──────────────────────────────────────────────┘
│ 结构化 action + payload
▼
┌──────────────────────────────────────────────────────────────┐
│ 执行层(复用现有 AIWritingContext) │
│ idle → startWriting(AIWritingRequest) │
│ 暂停 → submitIntervention(UserInterventionPayload) │
│ 问答 → 旁路回答(不改写作状态) │
│ 素材不足 → 先重搜、缓存 pending、补完自动续跑 │
└──────────────────────────────────────────────────────────────┘
```
**设计原则**:意图解析层是「翻译官」——把自由文本翻译成**执行层已经懂的指令**。能复用
`action + payload` 的绝不新造协议;确认按钮点击**直接走执行层**(不经意图层,零延迟、零误判)。
### 3.2 意图分类体系(覆盖全流程 + 更多)
按「意图 → 触发时机(当前 status/pausePoint)→ 映射执行」组织,即意图解析引擎的目标 schema。
**「甚至更多」** = G(问答)、H(控制)、以及 B/C/D/E 里的「素材不足自动回退重搜」。
#### A. 启动类(status = `idle`)
| 意图 | 用户说法示例 | 映射 |
|------|-------------|------|
| `start_writing` | 「写一篇关于新能源出口的深度分析,2000 字」 | 解析成 `AIWritingRequest` → `startWriting()` |
| `start_with_outline` | 「按这个大纲写:…」 | `AIWritingRequest.userOutline` |
| `start_imitate` | 「仿照这篇样文写…」 | `writingModeType='imitate'` + `sampleText` |
#### B. 素材类(pausePoint = `material_confirm`)
| 意图 | 示例 | 映射 |
|------|------|------|
| `confirm_materials` | 「素材可以,继续 / 下一步」 | `{action:'confirm', approvedMaterialIds}` |
| `research_again` | 「重新搜索素材」 | `{action:'re_search'}`(无 userQuery=覆盖式重检) |
| `add_material`/`add_keyword` | 「再补点关于 X 的素材」「加个关键词 Y」 | `{action:'re_search', userQuery:'X/Y'}`(追加) |
| `select_materials` | 「只用第 1、3 条」 | `{action:'confirm', approvedMaterialIds:[…]}` |
| `drop_materials` | 「去掉第 2 条」 | 同上(反选后的子集) |
#### C. 大纲类(pausePoint = `outline_confirm`)
| 意图 | 示例 | 映射 |
|------|------|------|
| `confirm_outline` | 「大纲 OK,开始写」 | `{action:'confirm'}` |
| `reoutline` | 「重写大纲」 | `{action:'re_outline'}`(feedback 可空) |
| `revise_outline` | 「第二章拆成两节」「调整顺序」 | `{action:'re_outline', outlineFeedback:自然语言}` |
#### D. 写作 / 草稿类(pausePoint = `draft_confirm`)
| 意图 | 示例 | 映射 |
|------|------|------|
| `to_editor` | 「交给编辑审核」 | `{action:'to_editor'}` |
| `finalize` | 「就这样定稿」 | `{action:'finalize'}` **(高代价:低置信必澄清)** |
| `revise_draft` | 「第三段太啰嗦,精简」「补个 2024 案例」 | `{action:'user_revise', userRevisionNotes:意见}` |
| `rewrite_section` | 「重写第二章」 | `user_revise` + 章节定位写进 notes |
| `change_tone/style` | 「更口语一点 / 更正式」 | `user_revise` + notes |
| `apply_review`(若已有审核结果) | 「按编辑意见改」「只接受第 1、2 条」 | `{action:'user_revise', selectedIssueIndices:[…]}` |
#### E. 编辑审核类(pausePoint = `review_confirm`)
| 意图 | 示例 | 映射 |
|------|------|------|
| `accept_review` | 「按编辑意见改」 | `{action:'accept_review', selectedIssueIndices}` |
| `partial_accept_review` | 「只接受第 1、2 条」 | `accept_review` + `selectedIssueIndices` 子集 |
| `add_review_opinion` | 「再补一条:核查数据准确性」 | `accept_review` + `userRevisionNotes`(并入补充指令,现协议已支持) |
| `force_finalize` | 「不改了,强制定稿」 | `{action:'force_finalize', overrideVerdict:true}` **(高代价:必澄清)** |
#### F. 素材不足求助类(pausePoint = `section_help`)
| 意图 | 映射 |
|------|------|
| `section_supplement` | `{action:'section_help', sectionDecisions:[…'supplement']}` |
| `section_loose` | `sectionDecisions:[…'loose']` |
| `section_delete` | `sectionDecisions:[…'delete']` |
#### G. 问答类(**新**;任意 status;旁路,不改写作状态)
| 意图 | 示例 | 映射 |
|------|------|------|
| `ask_about_content` | 「第二章讲了啥?」「为什么用这个论点?」 | 意图节点直接带回 `answer`,对话流渲染(见 5.4) |
| `ask_meta` | 「现在到哪步了?」「用了哪些素材?」 | 读当前 state 直接回答,不走图 |
#### H. 控制类(**新 / 半新**)
| 意图 | 映射 |
|------|------|
| `next_step`(通用「继续/下一步」) | 按**当前 pausePoint** 映射到该阶段的默认确认(material/outline→`confirm`,draft→`to_editor`…;等价点确认按钮) |
| `restart_stage` | 重跑当前阶段(复用 `resumeWriting()` 空 command 续跑) |
| `run_background` | 转后台自动跑:`suspendAIWritingToBackground()` |
| `cancel` | `pauseWriting()`(`stream.stop()`) |
| `unknown/clarify` | 无法判定 → 反问澄清 / 用户协助(**防误触发硬指标**) |
### 3.3 「素材不足自动重搜」判定与回退(用户强调点)
触发:用户在**大纲/草稿/审核**阶段提出修改意见,但意见需要的信息现有素材里没有。
判定来源(组合):
1. **意图节点直接判**:把「素材摘要(keywords + 每条 title/source)」喂给意图 prompt,让它判断
「这条意见能否用现有素材满足」;不能 → `needResearch=true` + `researchQuery`。
2. **执行阶段兜底**:`writer_draft` 严格模式已有 `blocked_sections` → `section_help` 暂停点,
对话层把它翻译成「素材不足,是否重搜?」的追问。
回退动作(**首期纯前端实现,不动后端协议**):`needResearch=true` 时,前端把用户的修改
`payload` 缓存为 `pendingIntent`,先 `submitIntervention({action:'re_search', userQuery:researchQuery})`
补素材;监听到新一轮 `material_confirm`(素材追加完成)后,**自动提交** `pendingIntent`。
需处理「重搜期间用户又改主意」→ 允许覆盖 pending。
---
## 4. 意图解析引擎:方案与契约
**采用方案 A:后端 LLM 意图节点(独立 REST)**,叠加高频短句**规则快路径**优化。
理由:`needResearch` 判定需要**完整写作上下文**(素材/大纲/草稿),后端天然持有 checkpoint state;
与 `setup_writing` 一脉相承,离线模型选择策略统一;输出 schema 稳定、前端只消费。
### 4.1 后端入口
`app/gateway/routers/ai_writing.py` 新增:
```
POST /api/ai-writing/sessions/{session_id}/intent
Body: { text: string, status: string, pausePoint?: string }
Resp: IntentResult(见 4.3)
```
实现:读该 session 的 checkpoint state(素材摘要 / 大纲纲要 / 草稿字数·章节 / 审核意见)→
用 `ai_writing` 配置模型(复用 `intent_parser.py` 同套 `create_chat_model` + `parse_json` +
模型容错 `_model_fallback`)解析 → 返回结构化契约。**不改图拓扑**。
新增 prompt:`agents/ai_writing/prompts/intent_router_prompts.py`
- 输入:用户文本、`current_status`/`pause_point`、素材摘要、大纲纲要、草稿字数+章节标题、审核意见列表。
- 输出:严格 JSON(4.3 契约)。硬要求:**只在证据充分时给高 confidence,否则给 `clarify`**;
`finalize`/`force_finalize`/`re_search` 等高代价意图**必须**高置信才不澄清。
### 4.2 前端快路径(先跑规则,未命中再调后端)
`api/ai-writing-intent.ts` 里对**当前 pausePoint** 做少量确定性短语命中,直接产出 payload,省一次往返:
- 「继续/下一步/确认/可以/ok/好的」→ 当前阶段默认 `confirm`(draft 阶段=`to_editor`)。
- 「重新搜索/重搜」(material)→ `re_search`。「重写大纲」(outline)→ `re_outline`。
- 「定稿/强制定稿」→ **不进快路径**(高代价,一律走后端 + 可能澄清)。
- 命中即执行;未命中 → 调后端 `intent` 接口。
### 4.3 意图解析输出契约
```jsonc
{
"intent": "revise_draft", // 见 3.2 分类
"pausePoint": "draft_confirm", // 需要 resume 时;否则 null
"action": "user_revise", // 映射到现有 action
"payload": { // 直接可喂 submitIntervention 的字段(camelCase)
"userRevisionNotes": "第三段精简,并补一个 2024 年的案例"
},
"needResearch": true, // 素材是否不足
"researchQuery": "2024 行业案例", // needResearch 时的检索意图
"answer": null, // 问答类意图的直接回答(旁路)
"confidence": 0.86,
"clarify": null // 低置信时的反问话术(非空则不执行、只追问)
}
```
前端消费顺序:
1. `answer` 非空 → 对话流渲染回答(问答旁路,不动写作状态)。
2. `clarify` 非空 **或** `confidence < 阈值(建议 0.6)` → 渲染反问气泡,等用户澄清(**防误触发**)。
3. `needResearch=true` → 缓存 `pendingIntent=payload`,先重搜,收到新素材后自动提交。
4. 否则 → `idle` 走 `startWriting(...)`;暂停态走 `submitIntervention({action, ...payload})`。
---
## 5. 前端改造方案
### 5.1 新页面与路由(复制式)
- 新页面:`open-canvas/pages/AIWritingChatPage.tsx`
(骨架照抄 `AIWritingPage.tsx` 的 Provider 包裹与左右分栏;左栏换成 `WritingChatPanel`,右栏仍
`AIWritingDraftPanel`;idle 不再挂 `AIWritingForm`,改由底部输入框启动)。
- 路由注册(**新增,不动旧行**):
- `open-canvas/routes/OpenCanvasRoutes.tsx` 加 `path="ai-writing-chat/*"`。
- 侧边栏 `core/page-layout/sidebar-menu.ts`:在 `qa-research` 旁新增
`{ id:"qa-research-chat", label:"AI写作(对话版)", icon:FileText, path:"/page/canvas/ai-writing-chat" }`。
(或先不加、内部灰度直链验证。)
### 5.2 新面板 `WritingChatPanel.tsx`(左栏主体)
职责 = 消息流容器 + 底部输入框,替代 `AIWritingPanel` 里的「时间线 + InterventionCard + 状态栏」。
复用 `useAIWriting()` 读 state / 调 `startWriting` / `submitIntervention` / `pauseWriting` /
`suspendAIWritingToBackground`。
消息流渲染(把 `ProgressEvent` / 阶段产物适配成消息卡,复用现有展示子组件):
- 运行中:`research_progress`/`outline_chunk`/`draft_chunk`/`review_chunk` → 进度 / 流式卡
(复用 `SkillStepsCard`/`OutlineStreamingView`/`DraftGeneratingView`/`ReviewStreamingView` 的展示部分)。
- 到达暂停点:渲染 **产物卡 + 保留的确认按钮**(见 5.3),不再有输入框。
- 用户消息、AI 澄清追问、问答回答:普通气泡。
底部输入框:直接复用 `@/components/ai-elements/prompt-input`(`PromptInput`+`PromptInputTextarea`+
`PromptInputSubmit`),Enter 发送、Shift+Enter 换行;发送时读当前 `state.status`/`currentPause?.pausePoint`
交给意图路由(见 5.5)。运行中(非暂停点)可禁用发送或转「排队/提示当前在生成」。
### 5.3 新消息卡 `chat-cards/*`(**保留按钮、去掉输入框**)
把 `InterventionCard.tsx` 的五张卡各复制一份到 `open-canvas/components/ai-writing-chat/chat-cards/`,
**删掉其中的 textarea / MaterialsToolbar 输入部分,保留产物展示 + 确认/动作按钮**:
| 新卡 | 展示(复用) | 保留的按钮 | 删除的输入 |
|------|-------------|-----------|-----------|
| `MaterialConfirmChatCard` | `MaterialsCard`(勾选保留)+ `SkillStepsCard` | 「确认素材,规划大纲」「重新搜索」 | `MaterialsToolbar` 的 userQuery 输入框 |
| `OutlineConfirmChatCard` | `OutlineCard`(可点标题微调保留) | 「确认大纲,开始写作」 | feedback textarea + 发送 |
| `DraftConfirmChatCard` | `ReviewCard`(若有审核,勾选保留) | 「按编辑审核意见修改」「让编辑继续审核」「确认定稿」 | 「修改意见」textarea |
| `ReviewConfirmChatCard` | `ReviewCard`(勾选保留) | 「按编辑意见修改」「强制定稿」 | 「补充修改指令」textarea |
| `SectionHelpChatCard` | 章节 + 三选一按钮组 | 三选一 + 「提交并继续」 | (本就无自由输入,原样保留) |
> 勾选态(素材/审核意见)**保留**——它是「点按钮」路径的一部分,不算自由输入框。用户想用自然语言
> 「只用第 1、3 条」也能走底部输入框(意图层产出 `approvedMaterialIds`/`selectedIssueIndices`)。
> 按钮点击 **直接调 `submitIntervention`**,与旧卡完全一致,零改动风险。
### 5.4 问答旁路(新能力)
「对写作内容提问」不改写作 state。首期**轻量实现**:意图节点检出 `ask_*` 时读 state 直接带回 `answer`,
前端在消息流渲染为普通 AI 气泡即可(一次调用出答案)。完整版(后续)可另起只读 lead_agent 线程注入
草稿/大纲作背景,类似 `WritingSetupChat` 的 `useThreadStream`。
### 5.5 交互流程(对话版)串起来
1. **空闲**:底部输入「写一篇关于 X 的深度分析,2000 字」→ 意图 `start_writing` → 组 `AIWritingRequest`
→ `startWriting()`。(缺关键字段时先 `clarify` 追问字数/读者/类型。)
2. **运行中**:进度/流式卡渲染。
3. **到暂停点**:渲染产物卡 + 按钮 + 一句提示「你可以点上面的按钮,或直接说:确认继续 / 补充素材 / 改大纲…」。
- **点按钮** → 直接 `submitIntervention`(旧逻辑)。
- **发文字** → `resolveIntent(text, status, pausePoint)`(先快路径、后后端)→ 按 4.3 消费。
4. **问答**:任意时刻提问 → 旁路 `answer`,不打断写作。
5. **素材不足**:`needResearch` 或 `section_help` → 追问/执行「重搜 → 自动续跑 pending 意图」。
6. **拿不准**:`clarify`/低置信 → 反问气泡,不执行。
### 5.6 pending 意图 & 澄清态(新增本地状态)
在 `WritingChatPanel`(或新 `WritingChatContext`)维护:
- `pendingIntent: UserInterventionPayload | null` —— 素材不足重搜完成后自动提交。
- `awaitingClarify: { originalText: string } | null` —— 澄清态,用户下一句与上一句拼接再解析。
- pending 生命周期:设置 → 提交 `re_search` → 监听 reducer 里新一轮 `awaiting_material_confirm`
(`state.status` 从 `researching` 回到 `awaiting_material_confirm`)→ 自动 `submitIntervention(pending)` → 清空。
---
## 6. 后端改造方案
### 6.1 意图解析入口(新增,唯一后端改动主体)
- `app/gateway/routers/ai_writing.py`:新增 `POST /sessions/{id}/intent`(见 4.1)。
读 checkpoint state 用 `app.state.checkpointer` + `make_ai_writing_graph().aget_state(...)`
(参照 `ai_writing_job_executor.py` 的读法)取素材/大纲/草稿/审核摘要。
- `agents/ai_writing/prompts/intent_router_prompts.py`:新增意图 prompt(见 4.1)。
- 复用 `nodes/intent_parser.py` 的模型创建 / `parse_json` / `_model_fallback` 容错。
### 6.2 不需要改的部分
- 四个阶段大脑节点、五个暂停点、checkpoint、StreamBridge、持久化、sessions/transcript REST——**全不动**。
- 「素材不足自动续跑」「问答旁路」首期都在**前端 / 意图节点**实现,**不扩 resume 协议**。
### 6.3 可选增强(阶段 3,按需)
- `add_review_opinion` 完整版:`review_confirm` resume 增字段 `extra_review_notes`(首期已用现有
`userRevisionNotes` 降级承载,够用)。
- `resume_intent` 后端化(把「重搜完自动续跑」搬到后端,减少前端状态机复杂度)。
- undo / 回退到上一暂停点(依赖 checkpoint 回滚)。
---
## 7. 数据流时序(改稿 + 素材不足自动重搜)
```
用户(draft_confirm 暂停): "第三段补个2024年的行业案例"
│ 底部输入框 → resolveIntent(text, status='awaiting_draft_confirm', pausePoint='draft_confirm')
▼ POST /api/ai-writing/sessions/{id}/intent { text, status, pausePoint }
后端: 读 state(素材摘要) + LLM 解析
│ 返回 { intent:revise_draft, action:user_revise,
│ payload:{userRevisionNotes:"第三段…补2024案例"},
│ needResearch:true, researchQuery:"2024 行业案例", confidence:0.9 }
▼
前端: needResearch=true → pendingIntent = payload
│ submitIntervention({action:'re_search', userQuery:"2024 行业案例"})
▼ LangGraph resume → researcher 追加素材 → status 回到 awaiting_material_confirm
前端: 监听到新一轮素材确认 → 自动提交 pendingIntent
│ submitIntervention({action:'user_revise', userRevisionNotes:"第三段…补2024案例"})
▼ writer_draft 用新素材改稿 → draft_chunk… → draft_ready → draft_confirm
前端: 消息流展示新草稿卡 + "已按你的意见改写并补充了 2024 案例"
```
---
## 8. 关键实现细节与坑
1. **阶段作用域**:`resolveIntent` 必须带 `state.currentPause?.pausePoint` + `state.status`——
同一句「重新来」在 material 是重搜、在 outline 是重写大纲。`AIWritingContext` 已有这两个字段,直接读。
2. **确认按钮零改动**:新卡的按钮 `onClick` 原样调 `submitIntervention(payload)`,与旧卡逐字一致,
风险最低;**只删输入框**。
3. **防误触发**:低置信(<0.6)或 `clarify` 非空一律追问;`finalize`/`force_finalize`/`re_search`
即使命中也要求高置信,否则澄清。绝不盲目定稿/覆盖重搜。
4. **pending 意图队列**:素材不足是「先插重搜、再回原意图」,用 5.6 的小状态机;重搜完成前允许覆盖 pending。
5. **问答不污染 transcript**:问答/澄清消息在前端标记 `kind:'qa'|'clarify'`,与写作进度事件区分(
`AIWritingContext` 的 transcript 只存 progressEvents/completedInterventions,问答气泡是纯前端消息,
默认不入 transcript,避免历史回看错乱)。
6. **流式产物→消息卡**:复用 `OutlineStreamingView`/`DraftGeneratingView`/`ReviewStreamingView`/
`SkillStepsCard` 的**展示部分**,套进消息容器,不重写渲染。
7. **右侧草稿预览**:`AIWritingDraftPanel` + `DraftSync` 原样复用(`DraftSync` 依据 status/markdown
同步右侧画布)。
8. **离线内网**:意图模型走 `config.yaml → ai_writing` 配置模型;检索仍走技能/内网 ES,不联网。
9. **模型选择透传**:`submitIntervention` 的 resume 已把 `state.request?.modelName` 一并回传(见
`AIWritingContext`),新页面沿用即可。
10. **旧页面隔离验证**:改完后回归旧 `/page/canvas/ai-writing` 与 `/page/workspace/ai-writing`、
笔记本嵌入页,确认零变化(新代码不 import 旧的 `AIWritingForm`/`InterventionCard`/`WritingFormContext`)。
---
## 9. 分阶段实施路线图
**阶段 0 — 骨架(不含意图)**
- 复制 `AIWritingChatPage` + 注册新路由 + 侧边栏入口;复用 `AIWritingContext`/`useStream`/`DraftPanel`。
- 复制五张 `chat-cards`(删输入框、留按钮);底部输入框先只做 idle 直发 `start_writing`
(文本原样当 `userIntent`,其余字段取默认)+ 暂停点靠按钮推进。端到端跑通。
**阶段 1 — 意图解析(核心)**
- 后端 `POST /sessions/{id}/intent` + `intent_router_prompts.py`,返回 4.3 契约。
- 前端 `api/ai-writing-intent.ts`(快路径 + 后端)接入 `WritingChatPanel`,覆盖 A~F 类意图。
- 低置信 `clarify` 澄清态(5.6)。
**阶段 2 — 问答旁路 + 素材不足自动重搜**
- G 类问答(意图节点直接带 `answer`)。
- `needResearch` + pending 意图机制(前端实现重搜后自动续跑,5.6)。
**阶段 3 — 增强(按需)**
- `add_review_opinion` 扩协议、`resume_intent` 后端化、undo/回退、完整问答只读线程。
**阶段 4 — 打磨**
- 消息卡视觉、历史回看(transcript)、后台挂起入口、灰度到侧边栏。
---
## 10. 关键文件清单(落地对照)
### 新增(前端)
- `open-canvas/pages/AIWritingChatPage.tsx` — 新页面(复制 `AIWritingPage` 骨架改造)
- `open-canvas/components/ai-writing-chat/WritingChatPanel.tsx` — 消息流 + 底部输入框
- `open-canvas/components/ai-writing-chat/chat-cards/{MaterialConfirmChatCard,OutlineConfirmChatCard,DraftConfirmChatCard,ReviewConfirmChatCard,SectionHelpChatCard}.tsx` — 保留按钮、去掉输入框
- `open-canvas/components/ai-writing-chat/progressToMessage.ts` — `ProgressEvent` → 消息卡适配
- `open-canvas/api/ai-writing-intent.ts` — 意图解析客户端(快路径 + `POST …/intent`)
- (可选)`open-canvas/contexts/WritingChatContext.tsx` — pending 意图 / 澄清态
### 修改(前端,仅追加,不动旧逻辑)
- `open-canvas/routes/OpenCanvasRoutes.tsx` — 加一条 `ai-writing-chat/*` 路由
- `core/page-layout/sidebar-menu.ts` — 加一个侧边栏入口(可选)
- `open-canvas/types/ai-writing.ts` — **仅追加** `IntentResult` 等新类型,不改旧字段
### 新增(后端)
- `app/gateway/routers/ai_writing.py` — 加 `POST /sessions/{id}/intent`
- `agents/ai_writing/prompts/intent_router_prompts.py` — 意图 prompt
- `tests/test_ai_writing_intent.py` — 意图接口单测(TDD 强制)
### 复用(不改)
- `open-canvas/contexts/AIWritingContext.tsx`、`hooks/useAIWritingStream.ts`
- `open-canvas/components/ai-writing/{AIWritingDraftPanel,DraftSync,MaterialsCard,OutlineCard,ReviewCard,SkillStepsCard,OutlineStreamingView,DraftGeneratingView,ReviewStreamingView}.tsx`
- `agents/ai_writing/graph.py`、四个阶段节点、五个暂停点、`nodes/intent_parser.py`
### 绝不动(保证「初始的不用动」)
- `open-canvas/pages/AIWritingPage.tsx` 及其引用的
`components/ai-writing/{AIWritingForm,InterventionCard}.tsx`、`contexts/WritingFormContext.tsx`
- 旧路由 `/page/canvas/ai-writing`、`/page/workspace/ai-writing`、笔记本嵌入页
---
## 11. 待确认(默认取值已给出,可直接推进)
1. 意图引擎:**后端 LLM 节点(方案 A)+ 前端短句快路径** —— 默认采用。
2. `AIWritingContext` / `useAIWritingStream`:**复用**(不物理复制)——默认采用;需绝对隔离可改为复制。
3. 新页面入口:**侧边栏新增「AI写作(对话版)」** —— 默认加;若要先灰度可只留直链。
4. 「素材不足自动重搜」:**首期前端 pending 续跑**(不动后端 resume 协议)——默认采用。
5. 问答旁路:**首期意图节点直接带 `answer`** —— 默认采用。
> 以上默认按「A + 复用引擎 + 侧边栏入口 + 前端 pending + 意图节点带答案」推进,如需调整请指出。
@@ -0,0 +1,454 @@
# AI 写作「对话驱动 + 意图解析」改造方案
> 目标:在**不动现有 AI 写作页面**的前提下,新建一个「对话驱动」的写作工作台。
> 去掉素材收集 / 大纲规划 / 作家写作 / 编辑审核各阶段**分散的输入框/表单**,
> 用**底部一个统一的智能输入框**接管全流程交互;该输入框具备**强意图解析**能力,
> 能准确识别用户意图(重新搜索、加素材、加关键词、重写大纲、按要求改大纲、改写作、
> 改编辑、提编辑意见、对写作内容提问……),并在**素材不足**时自动回退去重新检索素材。
本文只做**方案与实现指引**,不含代码改动。落地时按第 9 节的路线图分阶段推进。
---
## 1. 现状梳理(改造的地基)
现有 AI 写作是一套**独立的 LangGraph 子系统**(不是 lead_agent),前后端都已成型。
### 1.1 后端:`ai_writing` graph
- 图工厂:`offline-backend-20260512/backend/packages/harness/deerflow/agents/ai_writing/graph.py`
- 状态:`.../agents/ai_writing/state.py`(`AIWritingState` + `UserInterventionPayload`)
- 注册:`offline-backend-20260512/backend/langgraph.json` → `assistant_id = "ai_writing"`
- 执行:与 lead agent **共用** RunManager + StreamBridge + checkpointer(`app/gateway/services.py` 里 `assistant_id=="ai_writing"` 分发到 `make_ai_writing_graph`)
节点拓扑(实际):
```
sample_analyzer → intent_parser → researcher
→ [cond] pause_material | writer_draft
→ writer_outline → pause_outline
→ writer_draft → [cond] pause_section_help | pause_draft | END
→ editor → [cond] pause_draft | pause_review
→ pause_review → END | writer_draft
```
四个「阶段大脑」节点:
| 阶段 | 节点 | 文件 |
|------|------|------|
| 素材收集 | `researcher` | `nodes/researcher.py` |
| 大纲规划 | `writer_outline` | `nodes/writer_outline.py` |
| 作家写作 | `writer_draft` | `nodes/writer_draft.py` |
| 编辑审核 | `editor` | `nodes/editor.py` |
五个**暂停点**(`interrupt()`,靠 `Command(resume=payload)` 续跑):
| pause_point | 语义 | 可用 action(现有) |
|-------------|------|---------------------|
| `material_confirm` | 素材确认 | `confirm` / `re_search` / `supplement_search` / `enable_skill_search` |
| `outline_confirm` | 大纲确认 | `confirm` / `re_outline` |
| `draft_confirm` | 草稿确认 | `to_editor` / `finalize` / `user_revise` / `custom_revise` |
| `review_confirm` | 编辑打回确认 | `accept_review` / `force_finalize` |
| `section_help` | 素材不足求助 | `supplement` / `loose` / `delete` |
> resume 载荷字段(`UserInterventionPayload`):`action`、`approved_material_ids`、
> `extra_keywords`、`user_query`(自然语言补充检索)、`edited_outline`、`outline_feedback`、
> `user_revision_notes`、`override_verdict`、`selected_issue_indices`、`section_decisions`。
> **关键点**:现有协议已经支持「自然语言 + 结构化 action」,这是对话改造的核心可复用资产。
REST(业务元数据,非图执行):`app/gateway/routers/ai_writing.py`,前缀 `/api/ai-writing`
(sessions CRUD、transcript 保存、article-types、后台挂起 `/background` + `/progress` 等)。
持久化:`ai_writing_sessions` 表(`transcript` 为 `PortableLongText`)
+ `ai_writing_article_types`(`deerflow/persistence/...`)。
配置:`config.yaml → ai_writing`(`keyword_model`、`rank_model`、`max_materials`、
`use_builtin_agents.{researcher,outliner,writer,editor}` 等)。
### 1.2 前端:`open-canvas` 子系统
- 主页面:`frontend-web/src/open-canvas/pages/AIWritingPage.tsx`
- 路由:`/page/canvas/ai-writing`、`/page/workspace/ai-writing`
- 状态机:`contexts/AIWritingContext.tsx`(`useReducer` + LangGraph `useStream`)
- 事件翻译/reducer:`hooks/useAIWritingStream.ts`
- 类型:`types/ai-writing.ts`(`WritingStatus`、`ProgressEvent`、`UserInterventionPayload`、`AIWritingRequest`…)
- 流式:LangGraph `useStream`,`assistantId: 'ai_writing'`,`streamMode: ['values','updates','custom','messages-tuple']`
- **要去掉的输入 UI**(改造重点):
- 启动表单 `components/ai-writing/AIWritingForm.tsx` + `WritingFormContext`
- 阶段暂停输入 `components/ai-writing/InterventionCard.tsx`(素材/大纲/草稿/审核四套内嵌表单)
- **已存在的对话原型**:`components/ai-writing/WritingSetupChat.tsx`
(用 `useThreadStream` 起一条 lead_agent 线程 + `setup_writing` 工具审批卡回填表单)——
这是「对话 → 结构化配置」的现成范式,可借鉴但**不直接复用**(它只管启动前配置)。
### 1.3 结论
- **状态机、流式、暂停/续跑协议、持久化都可复用**,无需重写引擎。
- 改造本质 = **把「分散表单」换成「一个对话输入框 + 意图路由层」**,
再把意图映射回**现有的 `action + payload`**(大部分场景),
少量新意图(如「对内容提问」「素材不足自动重搜」)需要**新增协议/节点**。
---
## 2. 目标与范围
### 2.1 必须满足
1. 新页面/新路由,**旧页面零改动**(用户要求「初始的不用动」)。
2. 底部**单一对话输入框**控制所有阶段交互,移除各阶段独立输入框。
3. **强意图解析**:准确识别用户自然语言意图并路由到正确动作,覆盖全流程 + 更多。
4. 用户给修改意见后,**若现有素材不足以满足要求 → 自动/建议重新检索素材**再继续。
5. 保留右侧草稿实时预览(可编辑)与时间线/进度展示。
### 2.2 明确不做(本期)
- 不改旧 `AIWritingPage` 及其表单/干预卡组件。
- 不替换底层 `ai_writing` graph 的四个阶段大脑逻辑(只加意图层与少量新协议)。
- 不引入新的状态管理库(继续 `useReducer` + `useStream`)。
---
## 3. 核心设计
### 3.1 总体思路:三层结构
```
┌─────────────────────────────────────────────────────────┐
│ 对话 UI 层(新) │
│ - 左:消息流(用户消息 + AI 阶段产物卡片 + 进度) │
│ - 底:统一智能输入框(唯一交互入口) │
│ - 右:草稿实时预览(复用 AIWritingDraftPanel) │
└───────────────┬─────────────────────────────────────────┘
│ 用户自然语言
▼
┌─────────────────────────────────────────────────────────┐
│ 意图解析层(新,核心) │
│ - 输入:用户文本 + 当前 WritingStatus + 上下文快照 │
│ - 输出:{ intent, action, payload, needResearch, ... } │
└───────────────┬─────────────────────────────────────────┘
│ 结构化 action + payload
▼
┌─────────────────────────────────────────────────────────┐
│ 执行层(复用现有) │
│ - 空闲态:startWriting(AIWritingRequest) │
│ - 暂停态:submitIntervention(UserInterventionPayload) │
│ - 运行中:stream.stop() → 续跑 / 新命令 │
│ - 提问态:旁路问答(不改写作状态) │
└─────────────────────────────────────────────────────────┘
```
**设计原则**:意图解析层是「翻译官」——把自由文本翻译成**现有执行层已经懂的指令**。
能复用 `action + payload` 的绝不新造协议;只有现有协议表达不了的才扩展。
### 3.2 意图分类体系(覆盖用户全流程 + 更多)
按「意图类别 → 触发时机(当前 status)→ 映射到的执行」组织。这是**意图解析引擎的目标 schema**。
#### A. 启动类(status = idle)
| 意图 | 说明 | 映射 |
|------|------|------|
| `start_writing` | 用户描述要写什么 | 解析成 `AIWritingRequest` → `startWriting()` |
| `start_with_outline` | 用户自带大纲 | `AIWritingRequest.userOutline` |
| `start_imitate` | 样文仿写 | `writingModeType=imitate` + 样文 |
#### B. 素材类(status ≈ awaiting_material_confirm / 运行中)
| 意图 | 用户说法示例 | 映射 |
|------|-------------|------|
| `confirm_materials` | 「素材可以,继续」 | `material_confirm` + `confirm`(可带勾选 ids) |
| `research_again` | 「重新搜索素材」 | `material_confirm` + `re_search` |
| `add_material` / `add_keyword` | 「补充关于 X 的素材」「加个关键词 Y」 | `material_confirm` + `supplement_search`,`user_query`=X/Y |
| `use_skill_search` | 「用 XX 技能查」 | `material_confirm` + `enable_skill_search`,`user_query`=技能/来源 |
| `select_materials` | 「只用第 1、3 条」 | `confirm` + `approved_material_ids` 子集 |
| `drop_materials` | 「去掉第 2 条」 | 同上,反选后 `approved_material_ids` |
#### C. 大纲类(status ≈ awaiting_outline_confirm)
| 意图 | 示例 | 映射 |
|------|------|------|
| `confirm_outline` | 「大纲 OK」 | `outline_confirm` + `confirm` |
| `reoutline` | 「重写大纲」 | `outline_confirm` + `re_outline`(`outline_feedback` 可空) |
| `revise_outline` | 「第二章拆成两节」「调整顺序」 | `re_outline` + `outline_feedback`=自然语言 |
| `edit_outline_manually` | 用户直接给出新大纲文本 | 解析成 `edited_outline` |
#### D. 写作/草稿类(status ≈ awaiting_draft_confirm / writing_draft)
| 意图 | 示例 | 映射 |
|------|------|------|
| `to_editor` | 「交给编辑审核」 | `draft_confirm` + `to_editor` |
| `finalize` | 「就这样定稿」 | `draft_confirm` + `finalize` |
| `revise_draft` | 「第三段太啰嗦,精简」「补个案例」 | `draft_confirm` + `user_revise`,`user_revision_notes`=意见 |
| `rewrite_section` | 「重写第二章」 | `user_revise` + 定位信息(章节)写进 notes |
| `change_tone/style` | 「更口语一点」 | `user_revise` + notes |
#### E. 编辑审核类(status ≈ awaiting_review_confirm)
| 意图 | 示例 | 映射 |
|------|------|------|
| `accept_review` | 「按编辑意见改」 | `review_confirm` + `accept_review`(可带 `selected_issue_indices`) |
| `partial_accept_review` | 「只接受第 1、2 条意见」 | `accept_review` + `selected_issue_indices` |
| `force_finalize` | 「不改了,强制定稿」 | `review_confirm` + `force_finalize` |
| `add_review_opinion` | 「你再补一条:检查数据准确性」 | 追加自定义审核意见(见 5.3 扩展) |
#### F. 素材不足求助类(status = awaiting_section_help)
| 意图 | 映射 |
|------|------|
| `section_supplement` | `section_help` + `supplement`(去重搜) |
| `section_loose` | `section_help` + `loose`(放宽续写) |
| `section_delete` | `section_help` + `delete` |
#### G. 问答类(**新**,任意 status,旁路,不改写作状态)
| 意图 | 示例 | 映射 |
|------|------|------|
| `ask_about_content` | 「第二章讲了啥?」「为什么用这个论点?」 | 旁路问答(见 5.4) |
| `ask_meta` | 「现在进行到哪一步?」「用了哪些素材?」 | 读当前 state 直接回答,不走图 |
#### H. 控制类(**新/半新**)
| 意图 | 映射 |
|------|------|
| `undo/back` | 回退到上一暂停点(依赖 checkpoint 回滚,见 8.4) |
| `restart_stage` | 重跑当前阶段 |
| `run_background` | 挂起后台自动跑 → `POST /sessions/{id}/background` |
| `cancel` | `stream.stop()` |
| `unknown/clarify` | 无法判定 → 反问澄清(对话追问,不误触发) |
> **覆盖「甚至更多」**:G(问答)、H(控制)、以及 D/E 里「素材不足自动回退重搜」都是超出原表单能力的新增。
### 3.3 「素材不足自动重搜」的判定与回退(用户强调的重点)
触发场景:用户在**大纲/草稿/审核**阶段提出修改意见,但意见需要的**信息现有素材里没有**。
判定放在**意图解析层**输出一个 `needResearch: boolean` + `researchQuery`,判定来源二选一(推荐组合):
1. **意图解析 LLM 直接判断**:把「当前素材摘要(keywords + 每条 title/来源)」喂给意图解析
prompt,让它判断「用户这条意见能否用现有素材满足」。不能 → `needResearch=true` 并给出检索词。
2. **执行阶段兜底**:`writer_draft` 严格模式本就有 `blocked_sections` → `pause_section_help`,
这是**已有的**素材不足闸门;对话层把它翻译成「素材不足,是否重新检索?」的对话追问。
回退动作:`needResearch=true` 时,先走 `material_confirm + supplement_search`(或新的
「带目标的重搜」协议,见 8.3)补素材,**补完自动继续**用户原本的修改意图(需要在对话层
记住「pending 修改意图」,重搜结束后再提交)。
---
## 4. 意图解析引擎:方案对比与推荐
| 方案 | 做法 | 优点 | 缺点 |
|------|------|------|------|
| **A. 后端 LLM 意图节点**(推荐) | 新增 `/api/ai-writing/intent/parse`(或图内新节点),后端用 LLM 把 `{text, status, contextSnapshot}` → 结构化意图 JSON | 能吃到完整 state(素材/大纲/草稿);可判 `needResearch`;prompt/模型集中可控;离线内网可用配置模型 | 多一次网络往返(可接受,交互本就等待) |
| B. 前端调模型接口分类 | 前端直接调现有 `/api/models` 聊天做分类 | 少一层后端改动 | 前端难拿全后端 state 快照;prompt 分散;鉴权/模型选择复杂 |
| C. 规则 + LLM 混合 | 常见短句走关键词规则快路径,兜底 LLM | 快、省 token | 规则易漏、维护成本高;中文表达多样命中率低 |
**推荐 A(后端 LLM 意图节点)**,并在其上**叠加 C 的快路径**做优化(如「确认/继续/定稿」等
高频短句先走轻量规则,未命中再调 LLM)。理由:
- 意图判定需要**当前写作上下文**(尤其 `needResearch` 判定),后端天然持有 state/checkpoint。
- 与现有「配置助手 `setup_writing`」一脉相承,模型选择/离线部署策略统一。
- 输出 schema 稳定,前端只消费结构化结果,UI 简单。
### 4.1 意图解析输出契约(建议)
```jsonc
{
"intent": "revise_draft", // 见第 3.2 分类
"pausePoint": "draft_confirm", // 若需 resume;否则 null
"action": "user_revise", // 映射到现有 action;新意图可为新值
"payload": { // 直接可喂 submitIntervention 的字段
"userRevisionNotes": "第三段精简,并补一个 2024 年的案例"
},
"needResearch": true, // 素材是否不足
"researchQuery": "2024 行业案例", // needResearch 时的检索意图
"answer": null, // 问答类意图的直接回答(旁路)
"confidence": 0.86,
"clarify": null // 低置信时的反问话术
}
```
前端拿到后:
- `answer` 非空 → 直接在对话流渲染回答(问答旁路,不动写作状态)。
- `clarify` 非空或 `confidence` 低 → 渲染反问,等用户澄清(**防误触发**)。
- `needResearch=true` → 先重搜,缓存 `payload` 为 pending,重搜完再提交。
- 否则 → `submitIntervention({action, ...payload})` 或 `startWriting(...)`。
---
## 5. 前端改造方案
### 5.1 新页面与路由
- 新目录:`frontend-web/src/open-canvas/pages/AIWritingChatPage.tsx`(或 `conversational/` 子目录)。
- 新路由:`/page/canvas/ai-writing-chat`(在 `OpenCanvasRoutes.tsx` 注册;旧路由保留)。
- 侧边栏:`sidebar-menu.ts` 加一个入口(如「AI 写作(对话版)」),或先不加、内部灰度。
### 5.2 复用 vs 新建
| 复用(尽量不改) | 新建 |
|------------------|------|
| `AIWritingContext` / `useAIWritingStream`(状态机 + 流式) | 统一对话输入框组件 `WritingChatComposer` |
| `AIWritingDraftPanel`(右侧草稿预览) | 消息流容器 `WritingChatThread`(渲染阶段产物为消息卡片) |
| `types/ai-writing.ts`(按需扩展) | 意图解析客户端 `api/ai-writing-intent.ts` |
| `ProgressEvent` 事件模型 | 阶段产物 → 消息卡片的适配器 `progressToMessage.ts` |
| 会话持久化 REST | 「pending 意图」暂存逻辑(重搜后续跑) |
**不复用**:`AIWritingForm` / `WritingFormContext` / `InterventionCard`(这三个就是要去掉的表单)。
### 5.3 交互流程(对话版)
1. 空闲:用户在底部输入「写一篇关于 X 的深度分析,2000 字」→ 意图解析 `start_writing`
→ 组装 `AIWritingRequest` → `startWriting()`。
2. 运行中:`ProgressEvent`(`research_progress`/`outline_chunk`/`draft_chunk`…)
→ 适配成消息流里的**进度卡片/流式卡片**(复用现有流式视图组件的展示部分)。
3. 到达暂停点:不再弹 `InterventionCard`,而是在消息流里展示**阶段产物卡片**
(素材列表 / 大纲 / 草稿 / 审核结果)+ 一句提示「你可以说:确认继续 / 补充素材 / 改大纲…」。
用户下一句自然语言 → 意图解析 → `submitIntervention`。
4. 问答:任意时刻用户提问 → 旁路回答,不打断写作状态。
5. 素材不足:意图解析 `needResearch` 或后端 `section_help` → 对话追问「素材不足,帮你重搜?」
→ 确认后重搜 → 自动续跑 pending 意图。
### 5.4 问答旁路(新能力)
「对写作内容提问」不应改写作 state。两种实现:
- **轻量(推荐先做)**:意图解析节点直接带回 `answer`(后端能读 state,一次调用出答案)。
- **完整**:新起一条**只读**问答线程(lead_agent,context 注入当前草稿/大纲作为背景),
类似 `WritingSetupChat` 的 `useThreadStream` 模式,但只读不回填。
---
## 6. 后端改造方案
### 6.1 意图解析入口(二选一)
- **方案 A1(推荐,独立 REST)**:`app/gateway/routers/ai_writing.py` 新增
`POST /api/ai-writing/sessions/{id}/intent`,入参 `{text}`,后端读该 session 的
checkpoint state(素材/大纲/草稿摘要)+ 用 `ai_writing` 配置模型解析,返回第 4.1 的契约。
- 好处:不改图拓扑;前端拿到结果后再决定调 `startWriting`/`submitIntervention`。
- 方案 A2(图内节点):在图里加 `conversation_router` 节点。改动大、状态耦合高,**不推荐**首期。
### 6.2 意图解析 prompt
新增 `agents/ai_writing/prompts/intent_router_prompts.py`(或复用/扩展 `intent_parser.py`):
- 输入:用户文本、`current_status`、素材摘要(keywords + 每条 title/source)、大纲纲要、
草稿字数/章节标题、审核意见列表。
- 输出:严格 JSON(第 4.1 契约)。要求模型**只在证据充分时给高 confidence**,
否则给 `clarify`(防误触发是硬指标)。
### 6.3 「带目标的重搜」协议扩展(可选增强)
现有 `supplement_search` 用 `user_query` 追加检索。为支持「改稿意见 → 缺素材 → 重搜 → 自动续跑」,
建议在 `material_confirm` 的 resume 里新增可选字段 `resume_intent`(重搜完成后要自动执行的原始意图)。
- 前端也可**纯前端**实现(重搜完成事件回来后再自动提交缓存的 pending payload),**首期优先前端实现**,避免动后端协议。
### 6.4 追加自定义审核意见(`add_review_opinion`)
`editor`/`pause_review` 目前只接受「接受/强制定稿」。要支持「你再补一条审核意见」,
需在 `review_confirm` resume 里接受 `extra_review_notes`,`editor` 或 `writer_draft`
修订时并入。首期可先降级为 `user_revise` + notes(把用户的审核诉求当作改稿意见),
**完整版**再扩协议。
### 6.5 不需要改的部分
- 四个阶段大脑节点(researcher/writer_outline/writer_draft/editor)逻辑不动。
- 五个暂停点、checkpoint、StreamBridge、持久化不动。
---
## 7. 数据流时序(改稿 + 素材不足自动重搜)
```
用户: "第三段补个2024年的行业案例"
│
▼ POST /api/ai-writing/sessions/{id}/intent { text }
后端: 读 state(素材摘要) + LLM 解析
│ 返回 { intent:revise_draft, action:user_revise,
│ payload:{userRevisionNotes:...},
│ needResearch:true, researchQuery:"2024 行业案例" }
▼
前端: needResearch=true → 缓存 pending=payload
│ 对话追问/直接执行: submitIntervention(material_confirm, supplement_search, user_query="2024 行业案例")
▼ LangGraph resume → researcher 补素材 → materials_ready
前端: 收到新素材 → 自动提交 pending
│ submitIntervention(draft_confirm, user_revise, userRevisionNotes=...)
▼ writer_draft 用新素材改稿 → draft_chunk... → draft_ready → pause_draft
前端: 消息流展示新草稿 + "已按你的意见改写并补充了案例"
```
---
## 8. 关键实现细节与坑
1. **暂停态识别**:对话层必须知道「现在停在哪个 pause_point」才能正确映射 action。
`AIWritingContext` 已有 `currentPause`/`status`,直接读。
2. **防误触发**:低置信意图一律走 `clarify` 反问,绝不猜着执行(尤其 `finalize`/`re_search` 这种代价大的)。
3. **pending 意图队列**:素材不足重搜是「先插一段、再回原意图」,需要一个小状态机记住 pending,
并处理「重搜后用户又改主意」的情况(重搜完成前允许覆盖 pending)。
4. **回退/undo(H 类)**:依赖 checkpoint 回滚,`runtime/runs/worker.py` 有 `rollback` 概念,
首期可**不做**或只做「重跑当前阶段」。
5. **问答旁路不污染 transcript**:问答消息可标记 `kind:'qa'`,与写作进度事件区分持久化。
6. **流式产物→消息卡片**:复用现有 `OutlineStreamingView`/`DraftStreamingPreview` 等的**展示部分**,
套进消息气泡即可,不必重写渲染。
7. **离线内网**:意图解析模型走 `config.yaml → ai_writing` 里的配置模型;检索仍走技能/内网 ES,
不联网(与现有并行席位「禁 web_search」的离线策略一致)。
---
## 9. 分阶段实施路线图
**阶段 0 — 骨架(不含意图)**
- 新路由 + 新页面 `AIWritingChatPage`,复用 `AIWritingContext`/`useStream`/`DraftPanel`。
- 底部对话框先只做「空闲 `start_writing` + 暂停点固定按钮」跑通端到端(相当于把干预卡换成消息)。
**阶段 1 — 意图解析(核心)**
- 后端 `POST /sessions/{id}/intent` + intent prompt,返回第 4.1 契约。
- 前端接入:自然语言 → 意图 → `startWriting`/`submitIntervention`,覆盖 A~F 类意图。
- 加高频短句规则快路径 + 低置信 `clarify` 反问。
**阶段 2 — 问答旁路 + 素材不足自动重搜**
- G 类问答(先用 intent 节点直接带 `answer`)。
- `needResearch` + pending 意图机制(前端实现重搜后自动续跑)。
**阶段 3 — 增强协议(按需)**
- `add_review_opinion` 扩 `review_confirm` 协议、`resume_intent` 后端化、undo/回退。
**阶段 4 — 打磨**
- 消息卡片视觉、历史回看(复用 transcript)、后台挂起入口、灰度到侧边栏。
---
## 10. 关键文件清单(落地时对照)
### 新增(前端)
- `open-canvas/pages/AIWritingChatPage.tsx` — 新页面
- `open-canvas/components/ai-writing-chat/WritingChatComposer.tsx` — 统一输入框
- `open-canvas/components/ai-writing-chat/WritingChatThread.tsx` — 消息流
- `open-canvas/components/ai-writing-chat/progressToMessage.ts` — 事件→消息适配
- `open-canvas/api/ai-writing-intent.ts` — 意图解析客户端
- 路由注册:`open-canvas/OpenCanvasRoutes.tsx`(+ 可选 `sidebar-menu.ts`)
### 新增(后端)
- `app/gateway/routers/ai_writing.py` — 加 `POST /sessions/{id}/intent`
- `agents/ai_writing/prompts/intent_router_prompts.py` — 意图 prompt
- (阶段 3)`state.py` / `nodes/*` — 扩 `review_confirm`、`resume_intent`
### 复用(尽量不改)
- `open-canvas/contexts/AIWritingContext.tsx`、`hooks/useAIWritingStream.ts`
- `open-canvas/components/ai-writing/AIWritingDraftPanel.tsx` 及各流式展示组件
- `open-canvas/types/ai-writing.ts`(按需扩字段)
- `agents/ai_writing/graph.py`、四个阶段节点、五个暂停点
### 不动
- 旧 `open-canvas/pages/AIWritingPage.tsx` 及 `AIWritingForm`/`WritingFormContext`/`InterventionCard`
---
## 11. 待确认
1. 意图解析引擎是否采用**推荐的方案 A(后端 LLM 节点)**?
2. 新页面是**独立入口**(侧边栏新增)还是先**内部灰度**(仅直链)?
3. 「素材不足自动重搜」首期是否接受**前端实现 pending 续跑**(不动后端 resume 协议)?
4. 问答旁路首期是否接受**意图节点直接带答案**(不新起只读线程)?
> 以上默认按「A / 内部灰度 / 前端 pending / 意图节点带答案」推进,如需调整请指出。
File diff suppressed because it is too large. Load diff
@@ -0,0 +1,362 @@
# 岗位会商交付闭环与内置智能体实现计划
> 页面:`/page/strategy/qa/position-roundtable`
>
> 目标:在现有岗位会商基础上补齐“产物交付、查看、驳回、方案总结、行动规划”的完整闭环,同时继续保持原多智能体会商页面不受影响。
## 实施核对(2026-07-21)
本计划已按“岗位会商独立路由、无总控、各席位直接问答”的边界完成第一轮闭环。实际流程调整为:
```text
任务信息 → 情报分析岗识别并确认意图 → 启动校验并冻结业务链
→ 分阶段席位直接问答/交付 Markdown → 全部有效交付
→ 方案总结智能体(roundtable-summary)→ 行动规划智能体(position-action-planner)
→ 可随时返回交付产物驳回 → 后续阶段及内置产物级联失效 → 重做后重新收口
```
- [x] 情报意图、业务链选择、席位岗位归属和席位智能体配置均在启动前校验;启动后保存业务链快照。
- [x] 普通席位直接调用各自分配的智能体,并注入任务、意图及已完成上游席位的问答/产物;不经过总控智能体。
- [x] 普通席位必须在 `outputs` 中交付 Markdown 才会完成;情报分析岗以确认的结构化意图完成为准。
- [x] 节点、交付卡片、流程图和大图弹窗均展示 `locked / ready / running / done / rejected / stale / error` 状态,并可回看节点会话和产物。
- [x] 驳回要求标题和理由;当前节点转为 `rejected`,后续阶段按依赖转为 `stale/locked`,总结和行动规划同时失效,历史内容保留可查看。
- [x] 被驳回或失效的普通席位必须写入一份**新的或已改写** Markdown 才能再次完成;单纯继续问答且没有新交付不会误使下游产物失效。
- [x] 方案总结复用 `roundtable-summary` 的真实流式线程;行动规划新增 `position-action-planner`,强制输出 Markdown 报告和 `action-plan-subtasks.json`。
- [x] 两个内置智能体的线程、产物快照和来源节点版本栅栏均持久化;流式期间若上游版本变化,旧运行不能覆盖最新状态。
- [x] 右侧“交付产物”可查看内置节点结果、继续同一线程问答/修改交付,并在打开 Markdown 沙箱时自动收起右栏。
设计收敛:当前版本以节点的 `artifact_manifest`、`latest_answer`、版本、驳回记录及 Session 内置快照作为唯一事实来源,已能覆盖统一产物卡片和级联逻辑,因此不新增重复的 `position_roundtable_deliverables` 表。若后续需要“单个文件独立驳回、跨会话检索或完整版本对比”,再将清单归一化为独立产物表,避免现在的双写一致性风险。
## 数据持久化与灾难恢复(2026-07-23)
岗位会商现在使用“两层持久化”,两层职责不同:
1. LangGraph checkpoint/thread 是智能体继续推理与流式问答的执行源。
2. `position_roundtable_sessions` / `position_roundtable_nodes` 是页面历史的数据库恢复源。
数据库恢复源会保存:
- 情报分析岗完整消息、步骤时间线和未发送输入草稿;
- 每个业务链岗位的完整消息和未发送输入草稿;
- 方案总结、行动规划两个收口智能体的完整消息和未发送输入草稿;
- 已确认意图、冻结任务与业务链快照、节点状态、版本、驳回记录;
- Markdown / JSON 等文本产物正文(单文件最多 400 万字符)和文件元数据。
因此即使线上重启后 checkpoint 或沙箱 outputs 卷丢失,历史页仍能从数据库展示对话与产物正文,后续收口智能体也能继续读取数据库中的有效上游交付。新任务在意图识别开始前就会创建 Session,用户不必等到“启动业务链”才获得持久化保护。历史下拉支持删除,删除会显式清理 Session 与全部节点恢复快照,不依赖 SQLite 外键开关。
对应迁移:`20260723_05_position_roundtable_conversations.py`。部署时必须执行到 Alembic head。
## 0. 核心结论
- 方案总结智能体建议复用现有会商里的 `roundtable-summary` 能力,但不要直接搬整套 Step 3 页面流程。
- 可复用:内置智能体 ID、总结报告 prompt 组织方式、Markdown 报告产物、流式对话、报告续问与文件预览能力。
- 需要改造:输入材料从“总控共识 + 各席位交付”改成“任务信息 + 意图结果 + 已通过的岗位产物 + 业务链快照”,并把结果存到岗位会商 Session 下。
- 行动规划智能体建议作为新的内置智能体新增。
- 输入:方案总结报告、各岗位最终有效产物、业务链阶段信息、任务意图。
- 输出:行动规划报告、结构化子任务清单。
- 这个模式仍然不需要总控智能体。情报分析岗负责意图识别,业务链节点直接调用各自配置的智能体,最终再由内置总结/规划智能体收口。
- 驳回不删除历史内容,只改变“当前有效版本”的状态;被驳回节点和后续节点需要重新交付,既保留可追溯性,也方便后续返回查看。
## 1. 目标业务流程
1. 情报分析岗进入页面,查看任务信息并完成意图识别。
2. 用户点击“确认意图并启动业务链”。
3. 启动前做校验:
- 未选择业务链:提示“请先选择业务链”。
- 业务链存在未配置岗位的席位:提示并引导去业务链配置页。
- 业务链席位缺少智能体:提示具体席位名称。
- 意图尚未完成:提示先完成任务意图识别。
4. 校验通过后冻结业务链快照,初始化岗位会商节点。
5. 各岗位只对分配给本岗位的智能体进行问答。
6. 节点问答完成后形成交付产物,右侧产物卡片显示“已完成 / 未完成 / 进行中 / 已驳回 / 已失效”。
7. 左侧流程图显示各节点状态,节点可点击查看该节点对话与产物。
8. 流程图右上角提供“查看”按钮,打开弹窗展示更完整的业务链流程图。
9. 当业务链中所有岗位产物都处于有效已交付状态后,开放“方案总结”。
10. 方案总结完成后开放“行动规划”。
11. 即使进入方案总结或行动规划,用户仍可返回产物列表执行驳回。
12. 若驳回早期阶段产物,后续阶段产物、方案总结、行动规划都一起失效并回到待重新完成状态。
## 2. 状态设计
### 2.1 节点状态
现有节点状态需要扩展或映射为更贴近页面的展示状态:
| 展示状态 | 建议内部状态 | 含义 |
| --- | --- | --- |
| 未完成 | `ready` / `locked` / `rejected` | 尚未有效交付,或被驳回后等待重做 |
| 进行中 | `running` | 当前智能体正在回答或产物正在生成 |
| 已完成 | `done` | 当前节点已有有效交付 |
| 已失效 | `stale` | 上游被更新或驳回,当前结果不可作为最终材料 |
| 异常 | `error` | 生成或保存失败 |
建议新增 `rejected` 状态,便于区分“从未完成”和“被驳回后待重做”。如果第一轮想少改后端,也可以先用 `ready + rejection_record` 表示被驳回。
### 2.2 产物状态
产物状态建议独立于节点状态保存,因为一个节点可能同时有回答文本和多个文件产物。
| 状态 | 含义 |
| --- | --- |
| `pending` | 还没有交付 |
| `running` | 正在生成 |
| `delivered` | 已交付且当前有效 |
| `rejected` | 被用户驳回 |
| `stale` | 受上游驳回或重做影响,已经失效 |
### 2.3 内置收口节点
在流程图中把两个内置节点追加到业务链末尾:
1. `builtin:summary`:方案总结智能体。
2. `builtin:action-plan`:行动规划智能体。
这两个节点不属于普通业务链席位,但要和普通节点一样显示状态、支持点击查看结果。
## 3. 数据模型调整
### 3.1 Session 扩展
`position_roundtable_sessions` 已使用下列持久化字段:
| 字段 | 含义 |
| --- | --- |
| `status` | `intent_pending / active / completed / archived`;总结/规划运行态由前端瞬时状态与对应快照的 `status` 表示,避免一次运行中断后留下伪运行态 |
| `summary_thread_id` | 方案总结智能体线程 |
| `summary_snapshot` | 最新有效总结报告快照 |
| `action_plan_thread_id` | 行动规划智能体线程 |
| `action_plan_snapshot` | 最新有效行动规划快照 |
| `invalidated_at` | 记录在 `summary_snapshot` / `action_plan_snapshot` 内,包含 `invalidated_by`,无需重复写 Session 字段 |
### 3.2 Node 扩展
`position_roundtable_nodes` 已使用下列字段(展示状态由前端按状态映射):
| 字段 | 含义 |
| --- | --- |
| `status` | `locked / ready / running / done / stale / rejected / error`,前端直接映射为展示状态 |
| `rejection_count` | 当前节点累计驳回次数 |
| `last_rejection` | 最新驳回标题、理由、操作者、时间 |
| `revision` | 当前有效交付版本 |
| `invalidated_by` | 导致当前节点失效的上游节点 key |
### 3.3 Deliverable 新表(后续可选)
当需要“单个文件独立驳回、跨会话检索或完整版本对比”时,再新增 `position_roundtable_deliverables`,不要只依赖 `artifact_manifest`。
| 字段 | 含义 |
| --- | --- |
| `id` | 产物 ID |
| `session_id` | 会话 ID |
| `node_key` | 来源节点 |
| `agent_id` | 来源智能体 |
| `position_id` | 来源岗位 |
| `title` | 产物名称 |
| `kind` | `answer / file / summary / action_plan` |
| `content` | 文本产物内容摘要或正文 |
| `artifact_path` | 文件产物虚拟路径 |
| `thread_id` | 所属线程 |
| `status` | `pending / running / delivered / rejected / stale` |
| `revision` | 来源节点版本 |
| `rejection_title` | 驳回标题 |
| `rejection_reason` | 驳回理由 |
| `created_at` | 创建时间 |
| `updated_at` | 更新时间 |
当前第一轮不新增这张表:右侧产物卡片、驳回记录、总结输入材料从节点 `artifact_manifest`、节点版本/驳回记录和 Session 快照聚合,避免节点表与产物表双写。后续引入该表时,应把它提升为唯一事实来源,而不是并行维护两套状态。
## 4. 驳回与级联失效规则
### 4.1 基本驳回
用户点击产物卡片的“驳回”后弹窗填写:
- 驳回标题。
- 驳回理由。
提交后:
- 当前产物状态改为 `rejected`。
- 当前节点状态改为 `rejected` 或 `ready`。
- 当前节点的 `latest_answer` 和历史文件不删除,但不再作为有效交付输入。
- 记录 `last_rejection`,用于页面展示和后续追踪。
### 4.2 级联失效
如果驳回的节点位于第 N 阶段:
- 同阶段其他节点不自动驳回,除非业务链未来明确配置了依赖关系。
- 第 N+1 阶段及之后所有节点的有效产物全部标记为 `stale`。
- 后续节点状态回到未完成展示态。
- `builtin:summary` 和 `builtin:action-plan` 如果已经生成,也标记为 `stale`。
- 页面允许用户继续查看旧报告和旧行动规划,但必须提示“上游产物已变更,需要重新生成”。
### 4.3 重新交付
被驳回节点重新问答并完成后:
- 当前节点产生新的 `revision`。
- 当前节点产物状态变为 `delivered`。
- 只有当该阶段所有必要节点都重新有效交付后,下一阶段才重新解锁。
- 方案总结和行动规划必须基于最新有效产物重新生成。
## 5. 接口规划
### 5.1 启动与校验
| 方法 | 路径 | 用途 |
| --- | --- | --- |
| `POST` | `/api/position-roundtable/sessions/{id}/validate-activation` | 校验业务链、岗位、智能体、意图状态 |
| `POST` | `/api/position-roundtable/sessions/{id}/activate` | 校验通过后冻结链条并初始化节点 |
第一轮也可以先把校验合并在 `activate` 内,前端根据后端返回的错误码提示。
### 5.2 产物
| 方法 | 路径 | 用途 |
| --- | --- | --- |
| `GET` | `/api/position-roundtable/sessions/{id}/results` | 获取右侧统一产物来源节点(前端聚合文件与内置快照) |
| `GET` | `/api/position-roundtable/sessions/{id}/nodes/{node_key}` | 获取节点详情;文件正文由既有线程产物预览接口读取 |
| `POST` | `/api/position-roundtable/sessions/{id}/nodes/{node_key}/reject` | 驳回当前节点交付并触发级联失效 |
| `POST` | `/api/position-roundtable/sessions/{id}/nodes/{node_key}/complete-turn` | 节点回答结束后同步回答与产物 |
### 5.3 方案总结与行动规划
| 方法 | 路径 | 用途 |
| --- | --- | --- |
| `POST` | `/api/position-roundtable/sessions/{id}/summary/prepare` | 服务端准备版本锁定的总结材料和线程信息 |
| `POST` | `/api/position-roundtable/sessions/{id}/summary/ask` | 服务端准备总结的同线程续问材料 |
| `POST` | `/api/position-roundtable/sessions/{id}/summary/complete` | 校验 Markdown 交付与来源版本后持久化总结快照 |
| `POST` | `/api/position-roundtable/sessions/{id}/action-plan/prepare` | 服务端准备行动规划材料和线程信息 |
| `POST` | `/api/position-roundtable/sessions/{id}/action-plan/ask` | 服务端准备行动规划同线程续问材料 |
| `POST` | `/api/position-roundtable/sessions/{id}/action-plan/complete` | 校验 Markdown + JSON 交付与来源版本后持久化行动规划快照 |
可以复用现有 `streamMultiAgent` 流式协议,但建议在岗位会商下包一层 API,由后端负责拼装岗位会商材料,前端不直接拼长 prompt。
## 6. 前端实施步骤
### 阶段 1:状态与启动校验(已完成)
- 扩展 `PositionNodeStatus` 和状态显示映射。
- “确认意图并启动业务链”前补齐校验提示。
- 后端 `activate` 返回未配置岗位、缺智能体、未选择链条等具体错误。
- 左侧流程图节点右上角添加状态小图标。
- 节点样式调整为上方智能体名称、下方岗位名称,移除左侧 logo。
验收标准:未选择业务链、岗位未配齐、意图未完成时都能准确阻止启动;启动后流程图能显示各节点状态。
### 阶段 2:流程图弹窗(已完成)
- 左侧保留小型从上到下流程图。
- 流程图右上角增加“查看”按钮。
- 点击后打开弹窗,展示更大的流程图。
- 弹窗内支持点击节点查看对话与产物,保持和主页面选中节点同步。
验收标准:小图不挤占左侧空间,大图能完整展示业务链和两个内置收口节点。
### 阶段 3:产物卡片与预览(已完成)
- 右侧新增或改造“分析结果”Tab 为“交付产物”列表。
- 卡片展示智能体名称、产物名称、岗位名称、时间、状态。
- 点击卡片打开详情弹窗。
- 文本产物直接展示正文,文件产物复用现有 `ArtifactPreviewModal`。
- 每个有效产物提供“驳回”入口。
验收标准:节点回答和文件产物能进入统一产物列表;点击可查看详情。
### 阶段 4:驳回弹窗与级联失效(已完成)
- 新增 `RejectDeliverableDialog`。
- 驳回表单包含标题和理由,均必填。
- 后端事务内完成当前产物驳回、当前节点状态更新、后续阶段级联失效、总结和行动规划失效。
- 前端刷新 Session、Node、Deliverable 和流程图状态。
- 被驳回节点在对话区显示驳回信息,提示用户重新交付。
验收标准:驳回第一阶段任意节点后,第二阶段及之后产物都显示未完成或已失效;旧内容可查看但不能作为总结输入。
### 阶段 5:方案总结智能体(已完成)
- 封装 `usePositionSummary`,内部复用 `roundtable-summary` 的线程初始化、流式输出和 Markdown 产物预览能力。
- 输入材料改为岗位会商材料:
- 任务信息。
- 情报分析岗意图结果。
- 业务链快照。
- 所有状态为 `delivered` 的岗位产物。
- 已驳回或失效产物只作为历史参考,不进入默认总结材料。
- 方案总结节点追加到流程图末尾。
- 所有产物有效交付后才允许点击“生成方案总结”。
- 总结结果写入 `summary_snapshot`,同时进入产物列表。
验收标准:总结报告使用现有方案总结能力生成 Markdown;刷新页面后可恢复;上游驳回后总结标记失效。
### 阶段 6:行动规划智能体(已完成)
- 新增内置智能体 ID,建议先命名为 `position-action-planner`。
- 新增行动规划 prompt:
- 读取方案总结报告。
- 读取各岗位最终有效产物。
- 拆解为若干子任务。
- 每个子任务包含名称、目标、输入依据、责任岗位建议、前置依赖、交付物、验收标准。
- 输出两类产物:
- `行动规划报告.md`。
- `action-plan-subtasks.json`。
- 行动规划节点追加到方案总结之后。
- 方案总结有效完成后才允许启动行动规划。
验收标准:行动规划能生成可读报告和结构化子任务;刷新可恢复;上游驳回后自动失效。
### 阶段 7:返回修改与重新生成(已完成)
- 用户在方案总结或行动规划视图中仍可切回“交付产物”。
- 驳回后自动显示需要重做的节点。
- 重做节点完成后,允许重新生成方案总结和行动规划。
- 旧总结、旧行动规划保留历史查看,但状态显示“已失效”。
验收标准:不会因为进入总结/规划阶段而锁死前序产物;前序重做后能形成新版本闭环。
### 阶段 8:测试与回归(已完成)
- 后端测试:
- activate 校验。
- 节点完成后产物入库。
- 驳回当前节点。
- 驳回第一阶段时后续阶段级联失效。
- 总结和行动规划失效。
- 前端测试:
- 启动校验提示。
- 状态图标显示。
- 产物卡片筛选和预览。
- 驳回弹窗必填校验。
- 回归验证:
- 原多智能体会商页面不受影响。
- 业务链普通配置入口不显示岗位配置。
- 岗位会商页面刷新恢复正常。
- 深色模式和嵌入模式布局不溢出。
## 7. 推荐提交拆分
1. `feat(position-roundtable): add delivery status model`
2. `feat(position-roundtable): validate chain activation`
3. `feat(position-roundtable): add workflow status graph`
4. `feat(position-roundtable): add deliverable cards and preview`
5. `feat(position-roundtable): support rejection cascade`
6. `feat(position-roundtable): add summary builtin node`
7. `feat(position-roundtable): add action planning builtin node`
8. `test(position-roundtable): cover delivery workflow`
## 8. 第一轮建议范围
第一轮优先做最小可闭环:
```text
意图识别
→ 启动校验
→ 业务链节点状态
→ 节点产物列表
→ 产物详情查看
→ 驳回与级联失效
→ 全部交付后生成方案总结
→ 基于总结生成行动规划
```
如果时间紧,行动规划可以先生成 Markdown 报告,结构化 `subtasks.json` 放到第二轮;但数据模型和 UI 入口第一轮就要预留,否则后面会返工。
@@ -0,0 +1,15 @@
# 岗位会商沙箱文档
本目录存放**岗位会商文件预览沙箱**的对接与排障说明,独立于 `src/position-roundtable/docs/`,避免与模块内其它文档互相覆盖。
| 文档 | 说明 |
| --- | --- |
| [沙箱打开关闭与步骤条.md](./沙箱打开关闭与步骤条.md) | **详细版**:打开/关闭完整时序、步骤条关系、对接接口字段说明、必守规则、历史 bug 根因、排障手册、自测清单、接线示例与代码索引 |
模块总览仍见:`frontend-web/src/position-roundtable/README.md`。
建议读法:
- **从零对接新页面**:正文第 3、5、6、7、8、12、15、16 节
- **线上排障**:第 13、14 节
- **只要一页纸**:文末「附录 A」
@@ -0,0 +1,988 @@
# 岗位会商 · 沙箱打开 / 关闭与步骤条(详细对接与排障指南)
> **文档位置**:`frontend-web/docs/position-roundtable-sandbox/`
> **读者**:下次重做或对接岗位会商页面的同事;线上「沙箱不实时 / 卡死 / 第二次不刷新」时的排障同学。
> **最后依据**:当前仓库 `PositionRoundtablePage` + `PositionNodeChat` 实现(含临时名打开、外部 store、前沿节流、按 tool-call 重挂)。
---
## 目录
1. [文档用途与读法](#1-文档用途与读法)
2. [背景:为什么岗位会商要单独做沙箱](#2-背景为什么岗位会商要单独做沙箱)
3. [用户可见的正确行为(验收标准)](#3-用户可见的正确行为验收标准)
4. [整体架构与数据流](#4-整体架构与数据流)
5. [职责划分:谁拥有什么状态](#5-职责划分谁拥有什么状态)
6. [对接接口详解](#6-对接接口详解)
7. [打开沙箱的完整步骤](#7-打开沙箱的完整步骤)
8. [关闭沙箱的完整步骤](#8-关闭沙箱的完整步骤)
9. [步骤条与沙箱的关系](#9-步骤条与沙箱的关系)
10. [流式内容如何进入沙箱(性能关键)](#10-流式内容如何进入沙箱性能关键)
11. [与普通对话页的对照](#11-与普通对话页的对照)
12. [重做页面时的必守规则](#12-重做页面时的必守规则)
13. [历史问题与根因(务必读)](#13-历史问题与根因务必读)
14. [排障手册(按症状)](#14-排障手册按症状)
15. [对接自测清单](#15-对接自测清单)
16. [最小接线示例](#16-最小接线示例)
17. [关键代码索引](#17-关键代码索引)
18. [术语表](#18-术语表)
---
## 1. 文档用途与读法
### 1.1 这份文档解决什么问题
岗位会商右侧「文件预览沙箱」看起来像普通对话页的产物预览,但实现路径完全不同。历史上这块反复出过:
- 沙箱不实时打开,要等全文写完才弹;
- 打开了但内容冻住,生成完才一口气灌进去;
- 整页卡顿,连消息列表文字都不实时;
- 同轮「重新生成」第二次写入时,步骤条变了,沙箱却不动;
- 第一次正常,关掉后再问就不实时。
这些 bug **特别容易在「重做页面 / 换布局 / 自己重写开沙箱逻辑」时复现**。本文把正确对接方式、时序、接口、禁区和排障步骤写全,方便下一位同事直接按文档接线,而不是再靠猜。
### 1.2 建议读法
| 你的目标 | 先读哪些章节 |
| --- | --- |
| 从零接一个新页面壳 | 第 3、5、6、7、8、12、15、16 节 |
| 只改对话子组件探测逻辑 | 第 7、9、12、13 节 |
| 线上排障 | 第 13、14 节,必要时回看第 10 节 |
| 理解为什么不能用页面 state | 第 2、10、13 节 |
### 1.3 对照代码(以仓库为准)
| 角色 | 路径 |
| --- | --- |
| 页面壳(唯一沙箱宿主) | `frontend-web/src/position-roundtable/pages/PositionRoundtablePage.tsx` |
| 节点对话(探测 write_file、上报预览) | `frontend-web/src/position-roundtable/components/PositionNodeChat.tsx` |
| 收口对话 | `frontend-web/src/position-roundtable/components/PositionBuiltinAgentChat.tsx` |
| 预览 UI(共享组件,勿分叉逻辑) | `frontend-web/src/components/workspace/artifacts/artifact-file-detail.tsx` |
| 流式正文读取 | `frontend-web/src/core/artifacts/loader.ts` → `loadArtifactContentFromToolCall` |
| 普通对话页对照(步骤条自动开) | `frontend-web/src/components/workspace/messages/message-group.tsx` |
| 模块总览 | `frontend-web/src/position-roundtable/README.md` |
---
## 2. 背景:为什么岗位会商要单独做沙箱
### 2.1 普通对话页怎么开沙箱
普通对话页(`ChatPage`)大致是:
```text
ArtifactsProvider(页面级)
└─ ChatBox / MessageList
└─ message-group 渲染 write_file 步骤
└─ 发现 path 且 autoOpen → artifacts.select + setOpen(true)
└─ 右侧 ArtifactFileDetail 读同一套 ThreadContext
```
要点:
- 对话和预览共享同一套 `ThreadContext`(同一个 `useThreadStream`)。
- 步骤条组件自己就能触发打开。
- 流式 `content` 本来就在当前 React 树的 thread 里,不需要「把 thread 镜像到别的地方」。
### 2.2 岗位会商为什么不能照搬
岗位会商页面同时有:
- 左侧任务 / 意图 / 流程图;
- 中间某个节点的对话(`PositionNodeChat`);
- 右侧配置抽屉;
- **以及一个页面级单例沙箱**,它是对话区的**兄弟节点**,不在 `PositionNodeChat` 的 ThreadContext 里面。
因此:
1. 沙箱拿不到节点对话内部的 `thread`,除非节点主动上报;
2. 若把每次流式 thread 写进**页面级 `useState`**,整页(任务卡、意图、流程图、对话)都会按流式频率重渲染,主线程会被打爆;
3. 页面必须自己决定「开 / 关 / 抑制自动再开 / 切节点时清理」,不能让多个子组件各自 `setOpen`。
所以岗位会商采用:
```text
对话子组件探测 + 上报
→ 页面壳统一打开唯一 ArtifactFileDetail
→ 流式 thread 走外部 store,只让沙箱子树订阅
```
### 2.3 和「多智能体会商 Step2 沙箱」的区别
仓库里还有 `frontend-web/docs/roundtable-step2-sandbox-progress.md`,那是另一套圆桌 Step2 沙箱进度文档,**不是**岗位会商这条链路。对接岗位会商时以本文为准。
---
## 3. 用户可见的正确行为(验收标准)
重做或对接完成后,下列行为必须全部成立(用户感知对齐普通对话页):
| # | 行为 | 说明 |
| --- | --- | --- |
| A | 步骤条刚出现「写入文件」时,沙箱应已打开 | **不必等**步骤条上出现文件名 |
| B | 沙箱源码边写边滚;消息列表也实时出字 | 不能整页卡死、不能「生成完一口气刷」 |
| C | content 先于 path 时:先临时名打开,path 到了再改名 | 不闪屏、不重挂 |
| D | 同轮第二次同路径 `write_file`(重新生成) | 沙箱清空并重新流式 |
| E | 整轮结束后自动切 Markdown 预览 | 「正在生成,完成后自动预览」消失 |
| F | 用户手动关闭后,同一次写入不再自动弹 | 下一轮新写入仍可自动开 |
| G | 切岗位 / 切节点 / 新会话 / 切历史 | 沙箱关掉且不串内容 |
**不要误判的正常现象:**
- 流式期间沙箱停在「源码 / 编辑」视图,结束后才切「预览」——这是 `ArtifactFileDetail` 对 markdown/html 的既定行为,与普通对话页相同,**不是**打开时机 bug。
- 步骤条长时间显示「写入文件」、没有路径,但沙箱已经打开并在滚动——content-first 模型下这是**预期**。
---
## 4. 整体架构与数据流
```text
┌──────────────────────────────────────────────────────────────────────────┐
│ PositionRoundtablePage(页面壳) │
│ │
│ state: sandboxArtifact | null │
│ ref: sandboxArtifactRef / closedSandboxKeyRef / latestSnapshotRef │
│ store: createSandboxThreadStore() ←── 禁止改成 useState │
│ │
│ handlePreviewArtifact(artifact) ←──────────────────────────────────┐ │
│ handleNodeThreadSnapshot(...) ←───────────────────────────────┐ │ │
│ closeSandbox() │ │ │
│ │ │ │
│ {sandboxOpen && ( │ │ │
│ SandboxThreadProvider(store) │ │ │
│ └─ ArtifactFileDetail key=sandboxCloseKey(...) │ │ │
│ )} │ │ │
└───────────────────────────────────────────────────────────────────│──│───┘
│ │
┌───────────────────────────────────────────────────────────────────│──│───┐
│ PositionNodeChat / PositionBuiltinAgentChat │ │ │
│ │ │ │
│ useThreadStream → thread.messages / thread.isLoading │ │ │
│ │ │ │ │
│ ├─ MessageList → 步骤条(只展示 tool call) │ │ │
│ │ │ │ │
│ ├─ latestStreamingWriteFile(messages) │ │ │
│ │ → onPreviewArtifact({..., auto:true}) ───────────────────┘ │
│ │ │
│ └─ useEffect → onThreadSnapshot({threadId, thread}) ───────────────┘
└──────────────────────────────────────────────────────────────────────────┘
```
一句话:
- **谁打开**:对话子组件决定「该不该开、开哪次交付」;
- **谁真正开面板**:页面壳;
- **内容怎么更新**:子组件持续上报 thread 快照 → 页面壳 store → 只有沙箱子树重渲染。
---
## 5. 职责划分:谁拥有什么状态
### 5.1 页面壳必须拥有
| 状态 / 能力 | 为什么必须在页面壳 |
| --- | --- |
| `sandboxArtifact` | 唯一预览目标;切节点时要清 |
| `closedSandboxKeyRef` | 用户关过后的抑制;跨子组件生命周期 |
| `sandboxThreadStore` | 流式内容通道;不能进大页面 state |
| `closeSandbox()` | 切岗位 / 切节点 / 新会话统一入口 |
| 唯一 `ArtifactFileDetail` | 避免双实例、关闭失效、深度异常 |
### 5.2 对话子组件必须拥有
| 状态 / 能力 | 作用 |
| --- | --- |
| `autoPreviewRunArmedRef`(armed) | 只有本轮用户发送后才允许自动开 |
| `autoPreviewBaselineCallKeysRef`(baseline) | 忽略发送前已有的历史 write_file |
| `activeWriteFilePreviewRef` | 记录当前打开的 previewKey / path / toolCallId |
| `autoPreviewedArtifactKeyRef` | 同一次 identity 去重,避免每 chunk 重复上报 |
| `latestStreamingWriteFile` | 从 streaming messages 探测可预览的 write |
| `onThreadSnapshot` 上报 | 把 thread 喂给页面壳 |
### 5.3 明确禁止
1. 在 `PositionNodeChat` 内再挂一套 `ArtifactFileDetail`。
2. 让步骤条组件直接 `setOpen(true)` 作为岗位会商主路径(对照普通页可以,岗位会商不行)。
3. 把 `onThreadSnapshot` 落到 `PositionRoundtablePage` 的 `useState`。
4. 用「整个 threadId」做关闭抑制。
5. 用「path 相同」复用 `previewKey`。
---
## 6. 对接接口详解
### 6.1 `PositionArtifactPreview`
```ts
type PositionArtifactPreview = {
threadId: string; // 必填:LangGraph thread id
path: string; // 必填:真实路径,或 write-file: 虚拟 URL,或临时文件名路径
name: string; // 展示名(文件名)
mimeType: string | null; // 如 text/markdown;帮助预览语言判断
previewKey?: string; // 强烈建议:一次交付身份,推荐 `${messageId}:${toolCallId}`
auto?: boolean; // true = 流式自动打开;缺省/false = 用户点击打开
};
```
字段说明:
| 字段 | 详细含义 |
| --- | --- |
| `threadId` | 沙箱用来匹配 `onThreadSnapshot` 的线程;也对关闭抑制键有贡献 |
| `path` | 传给 `ArtifactFileDetail.filepath`。流式阶段通常是 `write-file:...` 虚拟 URL;落盘后的手动打开可以是真实 artifacts 路径 |
| `name` | UI 展示用;临时名阶段可能是 `未命名文件.md` |
| `mimeType` | 当 path 还不稳定时,帮助把语言判成 markdown/html,避免落成 TEXT |
| `previewKey` | **一次交付的身份**。同一次 tool call 的 path 升级要保持不变;新的 tool call 必须变 |
| `auto` | 自动打开才走关闭抑制;手动打开应清抑制 |
### 6.2 `onPreviewArtifact(artifact)` —— 对话 → 页面
页面壳 `handlePreviewArtifact` 当前逻辑顺序:
1. 校验 `threadId`、`path`,缺则 toast 并 return。
2. 计算 `artifactKey = sandboxCloseKey(artifact)`。
3. 若 `artifact.auto === true` 且 `closedSandboxKeyRef.current === artifactKey` → **抑制,直接 return**。
4. 清 `closedSandboxKeyRef`(手动打开或新的自动打开)。
5. `ArtifactsContext.select(path, true)` + `setOpen(true)`。
6. 判断是否同一预览 / 是否仅 path upgrade:
- `isSamePreview`:threadId + path + previewKey 全同 → 不重复 setState。
- `isPathUpgrade`:previewKey 相同、path 不同 → 更新 artifact,**不要**再折叠右侧抽屉。
7. 若不是 same preview:
- `setSandboxArtifact(artifact)`;
- **同步** `sandboxArtifactRef.current = artifact`(关键!flush 会立刻读 ref);
- `sandboxSnapshotAppliedAtRef.current = 0`(允许立刻推首帧内容)。
8. 若 store 里已有别的 thread 快照,先 `publish(null)`。
9. 若 `latestNodeThreadSnapshotRef` 的 threadId 匹配,立刻 `queueSandboxThreadSnapshot`。
10. 非 path upgrade 时 `setRightPanelOpen(false)`。
`sandboxCloseKey`:
```ts
if (artifact.previewKey) {
return `${artifact.threadId}:write:${artifact.previewKey}`;
}
return `${artifact.threadId}:${normalizePreviewArtifactPath(artifact.path)}`;
```
`ArtifactFileDetail` 的 React `key` 必须用这个 key:
**新 previewKey → 组件重挂 → 视觉上「清空再生成」。**
### 6.3 `onThreadSnapshot({ threadId, thread })` —— 对话 → 页面
每次 `thread` 引用变化(消息 chunk 到达)子组件都会调:
```ts
onThreadSnapshot?.({ threadId: activeThreadId, thread });
```
页面壳应:
1. 计算 `signature = sandboxThreadSignature(thread)`(用 isLoading、messages 长度、最近 write_file 的 path/content 长度/尾部等拼签名,用于去重)。
2. 写入 `latestNodeThreadSnapshotRef`(即使沙箱还没开,打开瞬间也要用)。
3. 若当前没有打开的沙箱,或打开的沙箱 threadId 不一致 → **只更新 ref,不 publish**。
4. 若一致 → `queueSandboxThreadSnapshot`(前沿节流后 `store.publish`)。
### 6.4 虚拟 URL 与正文读取
流式阶段 path 形如:
```text
write-file:${sourcePath}?message_id=${messageId}&tool_call_id=${toolCallId}&language=markdown
```
`loadArtifactContentFromToolCall`:
1. 解析 URL 的 `message_id`、`tool_call_id`;
2. 在 `thread.messages` 里找对应 AI message 的 tool call;
3. 返回 `toolCall.args.content`。
结论:
- 沙箱跟的是 **tool call 身份**,不是磁盘文件是否已经写完;
- 没有真实 path 也能显示正文;
- 临时文件名只影响展示名和语言猜测。
### 6.5 对话子组件 → 页面壳的其它相关回调
| 回调 | 用途 |
| --- | --- |
| `onPreviewArtifact` | 打开 / 更新沙箱 |
| `onThreadSnapshot` | 推送流式 thread |
| 页面壳 `closeSandbox` 传给 `ArtifactFileDetail.onClose` | 用户点关闭 |
手动从流程图 / 产物列表打开时,也可以直接调 `handlePreviewArtifact`(通常不带 `auto`,或不带 previewKey)。
---
## 7. 打开沙箱的完整步骤
### 7.1 武装(arm):只有「本轮用户提交」才允许自动开
在 `PositionNodeChat.handleSubmit` 真正 `sendMessage` 之前:
```text
activeWriteFilePreviewRef = null
autoPreviewBaselineCallKeysRef = writeFileCallKeys(thread.messages) // 历史 write 的 messageId:toolCallId
autoPreviewRunArmedRef = true
→ sendMessage(...)
```
发送失败要把 `armed` 设回 `false`。
为什么要 baseline?
线程里往往已经有上几次问答写过的 `write_file`。如果只看「messages 里有没有 write_file」,一提问就会把旧文件再打开一次。baseline 的含义是:**只有这次提交之后新出现的 tool call 才能自动开沙箱**。
### 7.2 探测 `write_file`:不要等完整 path
`write_file` 参数是一整段 JSON 流,**键顺序由模型决定**。
| 模型吐参顺序 | 步骤条表现 | 错误做法的后果 |
| --- | --- | --- |
| path / description 先到,再 content | 很快显示描述和文件名 | 普通对话页常见;等 path 也能开 |
| **content 先到,最后才 path** | 长时间只有「写入文件」,文件名很晚才出现 | 若硬等完整 path,沙箱会晚几十秒甚至一分钟 |
岗位会商报告类 agent **经常是第二种**。
`latestStreamingWriteFile` 规则:
1. 倒序扫描 AI messages 的 `tool_calls`;
2. 工具名是 `write_file` 或 `str_replace`;
3. **有完整扩展名的 path**(`hasCompleteArtifactExtension`)→ 用真实路径;
4. **尚无可用 path,但 `write_file` 的 content 已有非空字符** → 临时文件名:
- 正文头像 HTML → `未命名文件.html`
- 否则 → `未命名文件.md`
5. `str_replace` 必须等真实 path(它改已有文件);
6. 组装:
- `key = messageId:toolCallId`
- `path = write-file:虚拟URL`(write_file)或真实 path(str_replace)
- `mimeType`:markdown 则 `text/markdown`
为什么扩展名必须完整?
流式 path 会经历 `/a/b/report.m` → `/a/b/report.md`。若在 `.m` 时就当真实文件打开,预览语言可能被永久判成 TEXT。
### 7.3 上报 effect 的四个门闩
自动上报 `onPreviewArtifact` 前必须同时满足:
1. `thread.isLoading === true`
2. 探测到 streaming artifact,且其 key **不在** baseline
3. 已有 `previewThreadId`
4. `autoPreviewRunArmedRef === true`
然后处理 previewKey:
```text
若与 activePreview 是同一次 tool call(含 tool-start 前缀兼容)
→ 复用旧 previewKey // 用于临时名 → 真实 path
否则
→ previewKey = 新的 messageId:toolCallId
```
去重键:
```text
`${previewThreadId}:${previewKey}:${sourcePath}`
```
把 `sourcePath` 算进去,是为了:**同 previewKey 下临时名变成真实 path 时,还要再报一次**(path upgrade),但不会每来一个 content chunk 都报。
### 7.4 线程绑定竞态(不要误 disarm)
首轮对话常出现:
1. 用户发送(本地 draft threadId / 稍后 SDK 创建真实 id);
2. 流已经开始、armed=true;
3. 会话 API 把 `node.threadId` 从 `null` 写成真实 id。
这是「本节点绑定自己的新线程」,**不是**切节点。若绑定 effect 无脑清空 armed / baseline,首轮会永远开不了沙箱。
正确:识别 `isOwnThreadBinding`(同 nodeKey、旧 threadId 为空、新 threadId 等于当前 boundThreadId)时 **直接 return,不清 armed**。
### 7.5 path upgrade(改名)≠ 第二次交付
同一次 tool call:
```text
T1 content 到达 → path=未命名文件.md, previewKey=msg:tc1 → 打开
T2 真实 path 到达 → path=/mnt/.../报告.md, previewKey=msg:tc1 → 只改名
```
页面壳看到相同 previewKey、不同 path → `isPathUpgrade`:
- 更新 `sandboxArtifact`;
- **不**重挂(React key 仍基于 previewKey);
- **不**再折叠右侧抽屉。
### 7.6 同路径二次写入(重新生成)
同一次问答里模型可能:
```text
1) write_file → 步骤条「写入文件」→ 打开沙箱
2) 再 write_file 同 path,description=「重新生成优化版…」
```
这是**两次 tool call**,必须两个 previewKey。
若错误地「path 相同就复用 previewKey」:
- 步骤条出现第二条;
- 沙箱 React key 不变;
- 用户看到「重新生成了,但沙箱没变化」。
正确:身份只看 tool call。
### 7.7 时序总图(content-first)
```text
T0 用户发送 → armed=true,拍 baseline
T1 步骤条出现「写入文件」(尚无 path)
T1+ args.content 首字符到达 → 临时名打开沙箱,源码开始滚动
… store 约每 160ms 推一次 thread 快照 …
T2 args.path 拼完整(含 .md)→ path upgrade,标题改真实文件名(不重挂)
T3 write 结束 / isLoading=false → 自动切 Markdown 预览
```
### 7.8 时序总图(同轮二次写入)
```text
T1 write_file#1 → previewKey=msg:tc1 → 打开沙箱 A
T2 #1 结束(可能短暂切预览)
T3 write_file#2(同 path,新 description)→ previewKey=msg:tc2
→ key 变 → 组件重挂清空 → 跟 #2 重新流式
```
---
## 8. 关闭沙箱的完整步骤
### 8.1 用户手动关闭
`closeSandbox()` 应做:
1. `closedSandboxKeyRef = sandboxCloseKey(current)` —— 抑制**这一次**自动再开;
2. 关闭 `ArtifactsContext.open`(若开着);
3. 清节流定时器、pending 快照;
4. `sandboxSnapshotAppliedAtRef = 0`;
5. `sandboxArtifactRef = null` + `setSandboxArtifact(null)`;
6. `sandboxThreadStore.publish(null)`。
抑制与 path upgrade 的关系:
- 关掉临时名面板后,同一次 tool call 升级真实 path **仍被抑制**(同一 previewKey)——符合「用户不要看这次」;
- 下一次新的 `write_file`(新 previewKey)**可以**再自动开。
### 8.2 场景切换时强制关闭
以下操作应先调用 `closeSandbox()`,避免串台:
- 切岗位;
- 切节点;
- 切收口阶段;
- 新建会话;
- 切换历史会话。
是否写入 `closedSandboxKeyRef` 可按产品决定;至少必须清面板和 store。
### 8.3 错误的抑制粒度(历史坑)
若做成「关过一次就整个 thread 不再自动开」:
- 第一次实时开正常;
- 用户关掉;
- 再问一次 → 同 thread 被永久抑制 → 看起来像「第二次不实时 / 要等生成完」。
正确粒度:**单次交付的 `sandboxCloseKey`(含 previewKey)**。
---
## 9. 步骤条与沙箱的关系
### 9.1 步骤条从哪来
步骤条由 `MessageList` → `message-group.tsx` 渲染 tool call:
- 标题:优先 `args.description`;没有则 i18n 兜底「写入文件」;
- 子行:有 `args.path` 才显示路径;
- 普通对话页还会在「有 path + autoOpen」时自己 `select/setOpen`。
岗位会商里,步骤条**仍然只负责展示**;打开沙箱走 `onPreviewArtifact`,不要让两套逻辑抢。
### 9.2 对照表
| 你看到的步骤条 | 含义 | 沙箱应处于 |
| --- | --- | --- |
| 仅「写入文件」,无路径 | tool call 已开始;path/description 可能还没流到 | **应已打开**(临时名),源码在滚 |
| 「写入文件」+ 路径 | path 已可用 | 已打开;若刚从临时名升级则只改名 |
| 带自定义 description 的标题 + 路径 | 模型给了 description | 同上 |
| 第二条「重新生成…」+ 同路径 | 新的 write_file(新 toolCallId) | **应重挂**并重新流式 |
| 顶部「正在生成,完成后自动预览」 | 仍在 code 视图 | 正常,等 isLoading 结束切预览 |
| 生成结束,出现文件卡片 / present_files | 工具结果已落 | 通常已是预览模式;可手动再点开 |
### 9.3 常见误解
**误解 1:**「步骤条出现文件名 = 打开沙箱的正确时机」
→ 错。那是 path 到达的时机。content-first 时正确打开时机更早:content 首字节 / 工具调用已开始。
**误解 2:**「步骤条还在写『写入文件』,沙箱却开了,是 bug」
→ 通常不是。两边数据源相同,但沙箱允许无 path 打开,步骤条标题可能还没 description。
**误解 3:**「等生成完从编辑切预览 = 沙箱打开晚了」
→ 错。那是 `ArtifactFileDetail` 的 viewMode 策略。
---
## 10. 流式内容如何进入沙箱(性能关键)
### 10.1 为什么不能用页面 `useState` 存线程快照
错误写法:
```ts
setSandboxThreadSnapshot(snapshot) // 页面级 useState
```
后果:
- 消息 chunk 约每 30ms 一次,节流后仍约 6 次/秒;
- 每次都重渲染整页:任务卡、意图结果、流程图、节点对话……;
- 主线程占满 → 消息列表停绘、沙箱冻住;
- 纯尾随 `setTimeout(160)` 会被饿死,十几秒不 flush。
这同时解释了两个历史现象:
1. 「沙箱打开了但内容不更新」;
2. 「修完节流后整页更卡、消息也不实时」——因为节流终于开始真正 setState 了。
### 10.2 正确做法:外部 store + 子树订阅
```ts
createSandboxThreadStore()
subscribe / getSnapshot / publish
SandboxThreadProvider
useSyncExternalStore(store.subscribe, store.getSnapshot)
→ ThreadContext.Provider value={{ thread, isMock:false }}
→ ArtifactFileDetail
```
页面壳本身**不**因 snapshot 变化而重渲染;只有 Provider 及其子树重渲染。
### 10.3 节流必须是前沿(leading-edge)
`SANDBOX_SNAPSHOT_MIN_INTERVAL_MS = 160`:
```text
queue(snapshot):
pending = snapshot
if 距上次 publish >= 160ms:
立刻 flush(同步 publish)
else:
若没有在途 timer,则 setTimeout(剩余时间) 做补尾
flush:
清 timer
校验 pending.threadId === sandboxArtifactRef.threadId
publish(pending)
```
**不要**改回:
```ts
if (timer != null) return;
timer = setTimeout(flush, 160);
```
那是纯尾随;忙主线程下会假死。
### 10.4 signature 去重
`sandboxThreadSignature` 用最近 write_file 的 path、content 长度、content 尾 32 字等拼签名。
store.publish 时若 threadId+signature 未变,则不通知订阅者,减少无效渲染。
### 10.5 打开瞬间的首帧
`handlePreviewArtifact` 里往往会立刻 `queueSandboxThreadSnapshot(latestSnapshot)`。
此时 React 的 `setSandboxArtifact` 可能还没提交,若 flush 只读旧的 `sandboxArtifactRef`,会因 threadId 不匹配把首帧丢掉。
所以打开新预览时必须:
```ts
sandboxArtifactRef.current = artifact; // 同步
sandboxSnapshotAppliedAtRef.current = 0;
```
---
## 11. 与普通对话页的对照
| 点 | 普通对话页 | 岗位会商 |
| --- | --- | --- |
| 谁触发打开 | `message-group` 内 `artifacts.select` | 子组件 `onPreviewArtifact` → 页面壳 |
| 是否要求 path | 是(有 path 才自动开) | 否(write_file + content 可临时名开) |
| thread 从哪来 | 同树 ThreadContext | `onThreadSnapshot` + 外部 store |
| 关闭抑制 | 主要靠 ArtifactsContext / 用户操作 | `closedSandboxKeyRef` 按 previewKey |
| 同 path 重写 | 依赖新的 tool call / 选择逻辑 | **必须**新 previewKey 以重挂 |
| 结束后切预览 | ArtifactFileDetail 同一套 | 同一套 |
对齐目标是**用户感知一致**,不是代码路径完全相同。
普通对话页自动开的核心条件(对照用):
```ts
artifacts && isLoading && isLast && autoOpen && autoSelect && path && !result
```
它也要求 path,所以 content-first 时普通页同样会偏晚——只是很多主聊天示例 agent 先吐 path,观感更好。岗位会商报告 agent 更常 content-first,所以必须做临时名提前开。
---
## 12. 重做页面时的必守规则
按优先级:
1. **流式 thread 快照禁止进页面级 `useState`** → 用 store + `useSyncExternalStore`。
2. **节流用前沿 + 补尾**,不要纯尾随 timer。
3. **不要等完整 path 才开**;`write_file` + content 即可临时名打开。
4. **扩展名完整前不要把 path 当最终 path**。
5. **previewKey 按 tool call,不按 path**。
6. **打开时同步写 `sandboxArtifactRef`,并重置节流时间戳**。
7. **主路径扫描 `thread.messages`,不要只靠 `onToolStart`**。
8. **path upgrade 保持 previewKey,不要当第二次交付**。
9. **关闭抑制按 sandboxCloseKey,不要按整 thread**。
10. **沙箱单例在页面壳;子组件只上报**。
11. **本节点 threadId 回写不要 disarm**。
12. **「结束后才切预览」不要当打开 bug 去「修」掉共享组件**,除非产品明确要求边生成边渲染 Markdown(需单独评估性能)。
---
## 13. 历史问题与根因(务必读)
下面每个都在真实联调里出现过。重做时若踩中,优先回来对照。
### 13.1 沙箱要等文件名出来才开(晚几十秒)
**现象:** 步骤条早就「写入文件」,沙箱很晚才开;普通对话页对比显得「实时」。
**根因:** 探测逻辑硬等完整 `path`;而该 agent 先流 `content`、最后才流 `path`。
**修复:** content 首批字符即可用临时名打开;path 到了再 upgrade。
### 13.2 沙箱打开了,内容冻住,生成完才灌满
**现象:** 面板开了,但里面一直是空/旧内容;日志里 queue 很多,flush 很少。
**根因:** 纯尾随 160ms 定时器在忙主线程下被饿死。
**修复:** 前沿节流——到期就在流回调里同步 flush。
### 13.3 修完「内容更新」后,整页卡顿、消息也不实时
**现象:** 沙箱开始更新了,但页面更卡,消息列表也「攒到最后刷」。
**根因:** flush 走的是页面 `useState`,每 160ms 整页重渲染。以前 timer 饿死时反而「不卡」。
**修复:** 快照改外部 store,只让沙箱子树订阅。
### 13.4 第二次「重新生成」步骤有了,沙箱不变
**现象:** 同轮第二条二条 write 步骤,沙箱仍显示第一次完整结果。
**根因:** 用「path 相同」复用了第一次 previewKey,React key 不变,组件不重挂。
**修复:** previewKey 只按 tool call;同 path 新 call 必须新 key。
### 13.5 第一次实时,关掉后再问就不实时
**现象:** 关过沙箱后,下一轮要等生成完才开,或不开。
**根因:** 抑制绑在整个 threadId,或把 path upgrade / 新 call 误判成同一次。
**修复:** 抑制键 = `sandboxCloseKey(previewKey)`;仅抑制那一次交付。
### 13.6 首轮永远不开
**现象:** 新建节点第一次提问,armed 后很快又不满足条件。
**根因:** `node.threadId` 从 null 回写真实 id 时,绑定 effect 误 disarm。
**修复:** `isOwnThreadBinding` 时不清 armed。
### 13.7 预览变成纯文本
**现象:** 明明是 md,却按 TEXT 打开。
**根因:** 在 `.m` 阶段就当完整 path;或临时名没有 `.md` / 没传 language、mimeType;或 path 带空格。
**修复:** `hasCompleteArtifactExtension`;临时名带扩展名;URL 加 `language=markdown`;path trim。
### 13.8 依赖 onToolStart,线上偶发不开
**现象:** 本地偶发正常,联调经常不开。
**根因:** 后端 StreamBridge / worker 可能过滤 tools/events 类 stream mode。
**修复:** 主路径必须是 messages 里渐进出现的 `tool_calls`;onToolStart 只能当补充。
---
## 14. 排障手册(按症状)
排障时建议先看 Chrome Performance / React 重渲染是否整页抖,再看消息里 tool_calls 的 args 是 path-first 还是 content-first。
### 14.1 沙箱开得很晚
检查顺序:
1. `latestStreamingWriteFile` 是否仍要求完整 path?
2. armed 是否被 threadId 回写清掉?
3. 是否命中 `closedSandboxKey`?
4. 新 call 是否被 baseline 当成历史?
5. `previewThreadId` 是否为空(线程还没绑上)?
### 14.2 打开了但内容空白 / 冻住
1. 快照是否进了页面 useState?
2. 节流是否纯尾随?
3. `SandboxThreadProvider` 是否拿到带 messages 的 thread?
4. 虚拟 URL 的 message_id / tool_call_id 是否对得上?
5. 打开时 `sandboxArtifactRef` 是否同步?(首帧是否被 drop)
6. signature 是否因实现错误一直不变,导致 publish 被去重?
### 14.3 整页卡、消息列表也不实时
1. 搜页面壳是否还有 `setSandboxThreadSnapshot` / 类似大对象 state。
2. 是否在每 chunk `console.debug` 打大对象(DevTools 打开时更卡)。
3. 是否错误地让页面壳订阅了 store(页面壳不应 `useSyncExternalStore` 这份 store;只有 Provider 订)。
### 14.4 重新生成不刷新
1. 第二次 write 的 toolCallId 是否变了?
2. previewKey 是否仍用 path 复用?
3. `ArtifactFileDetail` 的 `key=` 是否基于 sandboxCloseKey/previewKey?
### 14.5 关后再问异常
1. 打印 `closedSandboxKeyRef` 与新 artifact 的 sandboxCloseKey。
2. 确认新一轮 send 时 armed/baseline 已重置。
3. 确认抑制不是整 thread。
### 14.6 语言 / 预览模式不对
1. 看打开时的 path / mimeType / language 查询参数。
2. 确认不是在扩展名不完整时打开。
3. 确认「源码→预览」发生在 isLoading false 之后(属正常)。
---
## 15. 对接自测清单
重做页面后至少跑完:
### 功能
- [ ] 首轮:步骤条「写入文件」出现时,沙箱是否已开并开始出字?
- [ ] content-first agent:无文件名阶段是否也能开?
- [ ] path 到达后:是否只改名、不整页闪、不重挂?
- [ ] 同轮第二次同路径 write:是否清空并重新流式?
- [ ] 结束后是否自动切 Markdown 预览?
- [ ] 手动点步骤条路径 / 产物卡片:能否打开正确文件?
### 关闭与抑制
- [ ] 流式中手动关闭:本次是否不再自动弹?
- [ ] 关闭后再发一轮新问题:是否仍可自动开?
- [ ] path upgrade 是否不会绕过「用户刚关闭」的抑制?
### 场景切换
- [ ] 切节点:沙箱关闭,旧内容不残留。
- [ ] 切岗位:同上。
- [ ] 新建会话 / 切历史:同上。
### 性能
- [ ] 流式中消息列表是否实时出字?
- [ ] 页面是否明显掉帧 / 卡死?
- [ ] React DevTools 中,大页面壳是否在每 160ms 整页 update?(不应)
---
## 16. 最小接线示例
### 16.1 页面壳(示意)
```tsx
const [sandboxArtifact, setSandboxArtifact] = useState<PositionArtifactPreview | null>(null);
const sandboxArtifactRef = useRef<PositionArtifactPreview | null>(null);
const closedSandboxKeyRef = useRef<string | null>(null);
const latestNodeThreadSnapshotRef = useRef<SandboxThreadSnapshot | null>(null);
const store = useMemo(createSandboxThreadStore, []);
// pending + timer + appliedAt 用于前沿节流(见 PositionRoundtablePage)
function handlePreviewArtifact(artifact: PositionArtifactPreview) {
if (!artifact.threadId || !artifact.path) return;
const key = sandboxCloseKey(artifact);
if (artifact.auto && closedSandboxKeyRef.current === key) return;
closedSandboxKeyRef.current = null;
artifactsCtx?.select(artifact.path, true);
artifactsCtx?.setOpen(true);
const prev = sandboxArtifactRef.current;
const isSame =
prev?.threadId === artifact.threadId &&
prev.path === artifact.path &&
prev.previewKey === artifact.previewKey;
const isPathUpgrade =
!isSame &&
Boolean(artifact.previewKey) &&
prev?.threadId === artifact.threadId &&
prev.previewKey === artifact.previewKey;
if (!isSame) {
sandboxArtifactRef.current = artifact; // 必须同步
setSandboxArtifact(artifact);
sandboxSnapshotAppliedAtRef.current = 0;
}
if (store.getSnapshot()?.threadId !== artifact.threadId) {
store.publish(null);
}
const latest = latestNodeThreadSnapshotRef.current;
if (latest?.threadId === artifact.threadId) {
queueSandboxThreadSnapshot(latest);
}
if (!isPathUpgrade) setRightPanelOpen(false);
}
function handleNodeThreadSnapshot(snapshot: { threadId: string; thread: BaseStream<AgentThreadState> }) {
const next = { ...snapshot, signature: sandboxThreadSignature(snapshot.thread) };
latestNodeThreadSnapshotRef.current = next;
if (sandboxArtifactRef.current?.threadId !== snapshot.threadId) return;
queueSandboxThreadSnapshot(next);
}
function closeSandbox() {
if (sandboxArtifactRef.current) {
closedSandboxKeyRef.current = sandboxCloseKey(sandboxArtifactRef.current);
}
// clear timer / pending / appliedAt
sandboxArtifactRef.current = null;
setSandboxArtifact(null);
store.publish(null);
artifactsCtx?.setOpen(false);
}
// 渲染
{sandboxArtifact && (
<SandboxThreadProvider
store={store}
threadId={sandboxArtifact.threadId}
fallbackThread={stub}
>
<ArtifactFileDetail
key={sandboxCloseKey(sandboxArtifact)}
filepath={sandboxArtifact.path}
threadId={sandboxArtifact.threadId}
mimeType={sandboxArtifact.mimeType}
onClose={closeSandbox}
allowVirtualMarkdownEdit
/>
</SandboxThreadProvider>
)}
```
### 16.2 对话子组件(示意)
```tsx
// send 前
activeWriteFilePreviewRef.current = null;
autoPreviewBaselineCallKeysRef.current = writeFileCallKeys(thread.messages);
autoPreviewRunArmedRef.current = true;
await sendMessage(...);
// 探测
const streaming = thread.isLoading ? latestStreamingWriteFile(thread.messages) : null;
const next =
streaming && !autoPreviewBaselineCallKeysRef.current.has(streaming.key)
? streaming
: null;
useEffect(() => {
if (!thread.isLoading || !next || !previewThreadId || !autoPreviewRunArmedRef.current) return;
// previewKey:同 tool call 复用,否则用 next.key
// artifactKey = threadId:previewKey:sourcePath 去重
onPreviewArtifact?.({
threadId: previewThreadId,
path: next.path,
name: next.name,
mimeType: next.mimeType,
previewKey,
auto: true,
});
}, [next, previewThreadId, thread.isLoading, onPreviewArtifact]);
useEffect(() => {
onThreadSnapshot?.({ threadId: activeThreadId, thread });
}, [activeThreadId, thread, onThreadSnapshot]);
```
**强烈建议:** 探测 / armed / baseline / 临时名逻辑直接复用或抽取自 `PositionNodeChat`,不要从零重写。
---
## 17. 关键代码索引
| 主题 | 位置 |
| --- | --- |
| 临时名 / 完整扩展名 / latestStreamingWriteFile | `PositionNodeChat.tsx` 中 `provisionalWriteFilePath`、`hasCompleteArtifactExtension`、`latestStreamingWriteFile` |
| armed / baseline / 上报 effect | `PositionNodeChat.tsx` `handleSubmit` + streaming preview `useEffect` |
| 同 tool call 判断 / 二次写入重挂 | 同上,`isSameToolCall` / `previewKey` |
| 线程绑定保护 | `PositionNodeChat.tsx` node binding `useEffect` 中 `isOwnThreadBinding` |
| sandboxCloseKey / store / 前沿节流 | `PositionRoundtablePage.tsx` `sandboxCloseKey`、`createSandboxThreadStore`、`queueSandboxThreadSnapshot` |
| 打开 / path upgrade / 抑制 | `PositionRoundtablePage.tsx` `handlePreviewArtifact` |
| 关闭 | `PositionRoundtablePage.tsx` `closeSandbox` |
| 虚拟 URL 读 content | `core/artifacts/loader.ts` `loadArtifactContentFromToolCall` |
| 源码/预览切换 | `artifact-file-detail.tsx` 中 `viewMode` + `thread.isLoading` |
| 普通页步骤条自动开 | `message-group.tsx` `write_file` 分支 |
相关提交(背景):
- `fix(frontend): 岗位会商沙箱在 write_file 流式阶段实时打开并刷新`
— 临时名打开、外部 store、前沿节流
- `fix(frontend): 同路径二次 write_file 时重挂岗位会商沙箱`
— previewKey 按 tool call,禁止按 path 复用
---
## 18. 术语表
| 术语 | 含义 |
| --- | --- |
| armed | 本轮用户发送后,允许自动打开沙箱的开关 |
| baseline | send 前已有的 write tool call 集合,用于忽略历史产物 |
| previewKey | 一次交付的稳定身份,推荐 `messageId:toolCallId` |
| sandboxCloseKey | 关闭抑制键,同时用作 `ArtifactFileDetail` 的 React key |
| provisional path / 临时名 | 尚无真实 path 时的 `未命名文件.md` / `.html` |
| path upgrade | 同 previewKey 下临时名升级为真实 path |
| sandboxThreadStore | 流式线程外部 store,避免整页重渲染 |
| write-file: URL | 用 message_id + tool_call_id 定位流式 content 的虚拟路径 |
| leading-edge throttle / 前沿节流 | 到期立即在回调里 publish,而不是只挂尾随 timer |
| content-first / path-first | 模型流式 JSON 参数时 content 与 path 哪个先到 |
| isOwnThreadBinding | 本节点把自己的新 threadId 写回 props,不是切节点 |
---
## 附录 A:给对接同学的一页纸摘要
1. 页面壳只挂一个沙箱;子组件只调用 `onPreviewArtifact` / `onThreadSnapshot`。
2. 自动打开时机 ≈ 步骤条出现「写入文件」时,而不是出现文件名时。
3. `write_file` 可以没有 path:临时名打开,path 到了再改名。
4. 流式 thread 进外部 store,进页面 state 会卡死。
5. 节流要前沿;previewKey 看 tool call;关闭抑制看 sandboxCloseKey。
6. 同路径重新生成 = 新 previewKey = 沙箱重挂。
7. 出问题先对照第 13、14 节,再看代码索引第 17 节。
@@ -0,0 +1,822 @@
# 沙箱统一写作管线:可实现开发方案
> 状态:设计稿;本文件只定义实施方案,不包含本轮业务代码改动。
> 覆盖范围:普通沙箱 Markdown、深度研究 `report.md`、现有 Markdown 编辑器的选区/段落改写。
## 1. 目标与结论
目标不是再增加一个“AI 写作页面”,而是将现有的四类能力统一为一个安全、可流式、可追溯的**文档改写管线**:
1. Markdown 编辑器选区改写;
2. Markdown 编辑器段落改写;
3. 深度研究报告的局部候选改写;
4. 沙箱中 Markdown 文件的全文改写。
该管线负责固定原文版本、构造上下文、逐 token 输出、校验 Markdown、生成可核验 diff、按策略提交,以及在全文覆盖时保存可撤销版本。
结论:需求可行,现有工程已有足够的复用基础:
- `frontend-web/src/open-canvas/components/artifact/MarkdownAiEditor.tsx` 已具备局部改写弹窗与人工“替换/插入/重试/追问”交互。
- `frontend-web/src/open-canvas/hooks/useWritingRewrite.ts` 与 `frontend-web/src/open-canvas/api/rewrite.ts` 已具备 SSE 文本流消费。
- `offline-backend-20260512/backend/app/gateway/routers/writing.py` 已具备模型流式读取实现。
- `offline-backend-20260512/backend/app/gateway/routers/deep_research.py` 已具备报告哈希、候选内容和用户确认应用机制。
- `frontend-web/src/components/workspace/messages/message-list.tsx`、`MessageGroup.tsx` 已可承载普通对话的工具步骤条、流式消息和文件卡片。
- `frontend-web/src/pages/deep-research/DeepResearchWorkbench.tsx` 已经通过虚拟消息把研究进度接入普通 `MessageList`。
因此应该复用这些基础,建设一个执行内核;不能为全文改写另建独立聊天列表或独立写作流。
## 2. 产品边界与交互策略
### 2.1 支持范围
第一版仅对 `.md`、`.markdown` 文件显示“AI 全文改写”按钮。
不支持 PDF、DOCX、HTML、图片和二进制文件;不在改写过程中发起新的联网搜索;超大文件不静默截断后覆盖,而是提示用户选择章节改写。
### 2.2 范围、模式和提交策略
| 入口 | 文本范围 | 管线模式 | 提交策略 | 展示位置 |
| --- | --- | --- | --- | --- |
| 编辑器气泡菜单 | 当前选区 | `selection` | `preview_only` | 现有改写预览弹窗 |
| 编辑器段落菜单 | 当前段落 | `paragraph` | `preview_only` | 现有改写预览弹窗 |
| 深度研究“改写第一段/章节” | 被解析出的报告片段 | `report_section` | `manual_apply` | 普通消息列表候选稿 + 确认卡 |
| 文件右上角“AI 全文改写” | 当前完整 Markdown | `document` | `auto_commit_after_validation` | 普通消息列表步骤条 + 右侧沙箱 |
统一内核中的枚举:
~~~python
class RewriteMode(str, Enum):
SELECTION = "selection"
PARAGRAPH = "paragraph"
REPORT_SECTION = "report_section"
DOCUMENT = "document"
class CommitPolicy(str, Enum):
PREVIEW_ONLY = "preview_only"
MANUAL_APPLY = "manual_apply"
AUTO_COMMIT_AFTER_VALIDATION = "auto_commit_after_validation"
~~~
这三类策略必须严格区分:
- `preview_only`:只生成候选,前端编辑器确认后才改本地 TipTap 文档;不写真实沙箱文件。
- `manual_apply`:后端保留基准哈希和候选片段,用户点确认后才将该片段应用进研究报告。
- `auto_commit_after_validation`:全文生成完成并校验通过后,后端进行一次带哈希校验的原子覆盖;同时保存可撤销版本。
### 2.3 局部编辑器:保持当前体验
现有文件:
- `frontend-web/src/open-canvas/components/artifact/MarkdownAiEditor.tsx`
- `frontend-web/src/open-canvas/hooks/useWritingRewrite.ts`
- `frontend-web/src/open-canvas/api/rewrite.ts`
- `offline-backend-20260512/backend/app/gateway/routers/writing.py`
局部改写仍然是:
1. 选中文字或打开段落菜单;
2. 选择润色、扩写、缩写、改写等动作;
3. 在现有弹窗中流式出现候选;
4. 用户手动选择替换、插入、重试或继续追问。
不要让局部改写每次都往普通消息列表插完整步骤条,否则频繁编辑会淹没聊天历史。它只共享底层管线,不共享全文改写的消息展示方式。
需要补充本地版本保护:发起请求时保存当前完整编辑器文本哈希、选区 `from/to` 和选区文本;用户点击“替换原文”前再次检查该范围仍匹配。若用户已修改原文,提示“原文已变化,请重新生成候选稿”,禁止将过期候选替换到错误位置。
### 2.4 右上角“AI 全文改写”
宿主文件:
- `frontend-web/src/components/workspace/artifacts/artifact-file-detail.tsx`
新增独立图标按钮,位置在右上角文件操作区,靠近保存、复制、下载一类操作。它**不能**替代页面中间当前 Sparkles 编辑模式:
| 控件 | 职责 |
| --- | --- |
| 中部 Sparkles/编辑模式 | 打开 `MarkdownAiEditor`,处理选区和段落 |
| 新增右上角 AI 全文改写 | 对整个 Markdown 发起后台全文重写任务 |
建议显示条件:
~~~ts
const canUseFullDocumentRewrite =
isMarkdownFile &&
canEditArtifact &&
!isSkillFile &&
!isMock &&
!useWriteFileStreaming &&
!hasLocalEdits;
~~~
若 `hasLocalEdits` 为真,按钮置灰并提示“请先保存当前修改后再进行全文改写”。后端全文任务从真实文件读取快照,不能在用户本地还有未保存修改时读取旧版本并最终覆盖新修改。
用户体验:
1. 点击按钮,打开简洁配置弹窗。
2. 弹窗显示文件名、原文字数;用户填写改写要求、选择模型、选择风格。
3. 点击开始,左侧普通消息列表创建一组步骤条。
4. 右侧沙箱自动切到源码视图,先显示“正在准备临时草稿,原文件尚未修改”。
5. 新 Markdown 从空临时草稿开始逐 token 写入右侧代码区域。
6. 校验通过后,后端原子替换真实内容;前端再同步真实 Artifact 缓存。
7. 左侧保留最终对比总结、查看 diff 按钮和撤销按钮。
任务进行中,同一个文件的保存、直接编辑、局部编辑和再次全文改写必须禁用;其他文件不受影响。
### 2.5 深度研究报告的约束
普通 Markdown 和深度研究报告使用同一管线,但不能使用同一上下文策略:
| 能力 | 普通沙箱 Markdown | 深度研究 report.md |
| --- | --- | --- |
| 输入上下文 | 原文 + 用户指令 | 原文 + 当前会话已选资料 |
| 联网 | 不联网 | 不联网 |
| 事实约束 | 不新增无依据事实 | 只能引用已选资料,禁止编造 |
| 引用校验 | 可选 | 必须校验来源 ID 白名单 |
| 最终存储 | Artifact 文件 | 研究 session 的 `report_markdown` |
| 局部改写 | 编辑器确认 | 现有确认卡片 |
深度研究右侧的 `report.md` 是由 `ResearchSandboxPanel.tsx` 以虚拟 `write_file` 方式展示的;它不能当作普通磁盘 Artifact 直接写入。全文任务必须通过研究 session 更新 `report_markdown`,并使 `report_html` 缓存失效。
## 3. 总体架构
~~~mermaid
flowchart LR
A["MarkdownAiEditor<br/>选区 / 段落"] --> P
B["ArtifactFileDetail<br/>AI 全文改写"] --> P
C["DeepResearch<br/>局部 / 全文"] --> P
P["Document Rewrite Pipeline<br/>冻结版本 → 构造上下文 → 流式生成<br/>校验 → 差异总结 → 按策略提交"]
P --> I["InlineDocumentSource"]
P --> F["ArtifactDocumentSource"]
P --> R["DeepResearchReportSource"]
P --> E["可恢复 SSE 事件 / Job"]
E --> L["普通 MessageList"]
E --> S["右侧沙箱临时草稿"]
P --> V["内容哈希、版本快照、原子提交"]
~~~
设计原则:
1. 纯执行内核不依赖 FastAPI、路由、用户身份或操作系统路径。
2. 鉴权、线程路径解析、研究 session 获取只在 `app` 层的来源适配器中完成。
3. 完整文档任务使用持久化后台 Job;局部弹窗可维持单次 SSE,避免过度持久化。
4. 全文流式过程中只写临时草稿;真实内容只在最终 compare-and-swap 成功时改变。
不要直接把现有完整“AI 写作 Agent”塞进改写按钮。那个流程适合从主题写新文章,可能包含大纲、资料和章节生命周期;本需求是严格以当前文档为基准改写。第一版复用它的流式视觉表达和消息列表能力,但使用专门的文档改写执行内核。
## 4. 后端模块设计
### 4.1 目录与职责
建议新增:
~~~text
offline-backend-20260512/backend/
├─ packages/harness/deerflow/
│ ├─ document_rewrite/
│ │ ├─ __init__.py
│ │ ├─ models.py # 请求、事件、校验、差异领域模型
│ │ ├─ ports.py # Source / Model / Store 协议
│ │ ├─ pipeline.py # 统一编排,不导入 app.*
│ │ ├─ prompt_builder.py # 普通与深度研究提示词
│ │ ├─ validation.py # Markdown / 引用 / 截断检查
│ │ └─ diff_summary.py # 字数、标题、块、引用差异
│ └─ persistence/
│ └─ document_rewrites/
│ ├─ base.py
│ ├─ model.py
│ └─ sql.py
├─ app/gateway/
│ ├─ routers/document_rewrites.py
│ ├─ document_rewrite_sources.py
│ └─ document_rewrite_executor.py
└─ packages/harness/deerflow/persistence/migrations/versions/
└─ <next_revision>_document_rewrites.py
~~~
`packages/harness/deerflow/document_rewrite` 不能导入 `app.*`,以符合项目 harness→app import firewall。`app/gateway/document_rewrite_sources.py` 负责把已鉴权的 Artifact/研究会话包装成内核端口。
### 4.2 来源端口
~~~python
class DocumentSource(Protocol):
async def read_snapshot(self) -> DocumentSnapshot: ...
async def read_current_hash(self) -> str: ...
async def commit_if_unchanged(
self,
*,
expected_hash: str,
content: str,
metadata: CommitMetadata,
) -> CommitResult: ...
async def restore_if_unchanged(
self,
*,
expected_hash: str,
content: str,
) -> CommitResult: ...
~~~
三种实现:
| 适配器 | 使用场景 | 读取方式 | 提交方式 |
| --- | --- | --- | --- |
| `InlineDocumentSource` | 选区/段落候选 | 前端编辑器快照 | 不提交 |
| `ArtifactDocumentSource` | 普通 Markdown | 复用 Artifact 权限与虚拟路径解析 | 同目录临时文件 + `os.replace` |
| `DeepResearchReportSource` | 研究报告 | session `report_markdown` + 已选来源 | 数据库哈希条件更新 |
`ArtifactDocumentSource` 必须复用 `app/gateway/routers/artifacts.py` 中已有的线程访问校验、虚拟路径解析逻辑,绝不允许请求体传入任意本机绝对路径。
### 4.3 持久化 Job、事件和版本
全文改写使用持久化 Job,参考 `app/gateway/deep_research_job_executor.py` 的后台任务、租约、取消监听和事件重放模式。
#### document_rewrite_jobs
| 字段 | 作用 |
| --- | --- |
| `id` | `drw_xxx` Job ID |
| `user_id` | 发起人 |
| `source_kind` | `artifact` / `deep_research_report` |
| `thread_id`、`artifact_path` | 普通文件来源 |
| `research_session_id` | 研究报告来源 |
| `presentation_thread_id` | 普通消息列表归属 |
| `mode`、`commit_policy` | 范围和提交语义 |
| `instruction`、`style`、`model_name` | 用户配置 |
| `base_sha256` | 原文冻结哈希 |
| `draft_content`、`draft_sha256` | 临时流式草稿 |
| `status`、`stage` | 生命周期 |
| `validation_json`、`diff_summary_json` | 可展示结果 |
| `committed_sha256` | 成功提交后的哈希 |
| `error_message`、时间字段 | 错误、审计、取消 |
#### document_rewrite_events
至少包含 `job_id`、`seq`、`event_type`、`stage`、`payload_json`、`created_at`。`seq` 用于断线重连时通过 `after_seq` 重放。
不必将每个 token 单独入库:每 250ms 或每积累 4KB 持久化一次 `draft_content`;状态转换、警告、完成、冲突、取消必须立即写事件。重连时先发送最新草稿快照,再发送快照序号后的增量事件。
#### document_rewrite_versions
保存真实全文覆盖前的原文版本,字段包含 `job_id`、`source_identity`、`version_no`、`content`、`sha256`、`reason`、`created_at`。初版每个文档保留最近 20 个版本即可。
索引要求:
- `(user_id, presentation_thread_id, created_at DESC)`:恢复历史消息。
- 真实来源标识 + 活跃状态:防止同一文档并行两个全文改写。
### 4.4 Job 状态机
~~~mermaid
stateDiagram-v2
[*] --> queued
queued --> snapshotting
snapshotting --> generating
generating --> validating
validating --> comparing
comparing --> committing
committing --> completed
completed --> reverted
queued --> cancelled
generating --> cancelled
snapshotting --> failed
generating --> failed
validating --> failed
committing --> conflict
committing --> failed
~~~
状态约束:
- 同一真实文档只允许一个活跃 Job。
- 生成期间取消、异常、断线,真实文档绝不能变化。
- 提交前重新读取当前哈希;与 `base_sha256` 不一致时进入 `conflict`,草稿保留但不覆盖。
### 4.5 API 与 SSE 契约
创建全文任务:
~~~http
POST /api/document-rewrites
Content-Type: application/json
~~~
普通 Artifact 请求:
~~~json
{
"source": {
"kind": "artifact",
"thread_id": "thread_xxx",
"path": "/mnt/user-data/outputs/report.md"
},
"presentation_thread_id": "thread_xxx",
"mode": "document",
"instruction": "统一为正式行业分析语气,减少重复,不新增外部事实",
"style": "formal_analysis",
"model_name": "system_default"
}
~~~
深度研究请求:
~~~json
{
"source": {
"kind": "deep_research_report",
"session_id": "drs_xxx"
},
"presentation_thread_id": "collector_thread_xxx",
"mode": "document",
"instruction": "重新组织全文逻辑,保留全部可用引用",
"style": "formal_analysis",
"model_name": "system_default"
}
~~~
其他接口:
~~~text
GET /api/document-rewrites/{job_id}
GET /api/document-rewrites/{job_id}/stream?after_seq=42
POST /api/document-rewrites/{job_id}/cancel
POST /api/document-rewrites/{job_id}/undo
GET /api/document-rewrites?presentation_thread_id={thread_id}
~~~
SSE 事件:
| 事件 | 关键数据 | 前端动作 |
| --- | --- | --- |
| `job_started` | 文件名、模式 | 建立步骤条 |
| `snapshot_fixed` | 原文字数、哈希 | 完成“固定原文版本” |
| `requirements_resolved` | 模型、风格、要求 | 完成“理解改写要求” |
| `rewrite_delta` | `delta`、累计字符数 | 追加右侧临时草稿 |
| `validation_started` | 校验项 | 进入校验步骤 |
| `validation_completed` | passed、warnings | 显示校验结果 |
| `comparison_ready` | `DiffSummary` | 渲染总结数据 |
| `commit_started` | 无 | 显示安全替换中 |
| `committed` | 最终哈希、版本 ID | 刷新真实文件缓存 |
| `completed` | 完整结果 | 固化历史步骤条 |
| `conflict` / `error` / `cancelled` | 原因 | 恢复原文显示,不保存草稿 |
局部改写兼容方案:
- `POST /api/writing/rewrite` 的请求和 SSE 格式先不变。
- `writing.py` 内部逐步把 prompt、模型流、基础 Markdown 校验下沉给统一管线的 `preview_only` 分支。
- 深度研究 `/sessions/{id}/rewrite/stream` 和确认候选接口也先保持 URL、前端行为不变,再内部复用 `manual_apply` 分支。
这样可以先交付全文改写,不会一次性破坏已有编辑器和深度研究流程。
### 4.6 模型、提示词与校验
管线只依赖一个流式模型端口:
~~~python
class StreamingRewriteModel(Protocol):
async def stream_text(
self,
*,
messages: list[BaseMessage],
model_name: str | None,
) -> AsyncIterator[TextChunk]: ...
~~~
第一版可以有两个 adapter:
- 普通文档复用 `writing.py` 的 chat model `astream`;
- 深度研究复用 `deep_research.py` 使用的 `DeerFlowCompletionBackend.stream_complete`。
先统一编排,不强制立即统一所有模型配置实现。
普通 Markdown 系统约束:
~~~text
仅根据原文与用户要求改写,不联网,不补充未给出的事实。
保留有效链接、代码块、表格、标题语义和用户明确要求保留的内容。
只输出完整 Markdown 正文;不得输出解释、前缀或“改写如下”。
~~~
深度研究额外约束:
~~~text
不得联网。事实、数字、结论和引用只能来自当前 session 已选资料。
只允许使用给出的 source_id;资料不足时保持谨慎表述,禁止自行补全。
~~~
校验规则:
| 类别 | 硬失败 | 告警但允许完成 |
| --- | --- | --- |
| 正文 | 空文档、仅空白、无可见内容 | 改写后与原文完全一致 |
| Markdown | 未闭合围栏、明确截断 | 标题层级跳级、章节数明显减少 |
| 深度研究来源 | 未选来源 ID、非法引用 | 引用数量下降、可能需核验的数字断言 |
## 5. 安全提交、对比与撤销
### 5.1 临时草稿不等于真实文件
用户视觉上看到“先清空再逐 token 写入”,但真实文件的处理必须是:
1. 读取原文并保存内容哈希、版本快照。
2. 右侧只展示内存/Job 中的 `draft_content`。
3. 生成完成后做校验和 diff。
4. 提交前再次读取真实来源,并比较 `SHA-256`。
5. 哈希一致才原子替换;否则进入冲突,不覆盖。
普通 Artifact 使用同目录临时文件、刷盘和 `os.replace`;深度研究通过数据库事务内的“旧哈希条件更新”提交。任何失败、取消或断流都保留真实原文。
### 5.2 撤销
撤销流程:
1. 读取该 Job 的 `before_full_rewrite` 快照。
2. 确认当前真实内容哈希仍等于该 Job 的 `committed_sha256`。
3. 若用户在改写后又手工编辑,返回冲突,不盲目覆盖。
4. 先保存当前内容为 `before_undo` 版本。
5. 原子恢复旧版本,Job 状态改为 `reverted`,消息列表卡片同步显示“已撤销”。
### 5.3 结构化 DiffSummary
后端产出结构化差异,前端仅渲染,避免生成空泛结论:
~~~ts
type DiffSummary = {
sourceDisplayName: string;
instruction: string;
modelName: string;
originalCharCount: number;
rewrittenCharCount: number;
charChangeRatio: number;
changedBlockCount: number;
headings: {
added: string[];
removed: string[];
reordered: string[];
levelWarnings: string[];
};
citations?: {
beforeCount: number;
afterCount: number;
retainedCount: number;
removedIds: string[];
invalidIds: string[];
};
requestedOptimizations: string[];
validationWarnings: string[];
};
~~~
推荐总结展示:
~~~text
已完成《新能源汽车市场分析报告》的整体改写。
- 改写范围:全文;要求为“统一正式分析语气、减少重复”;模型:默认模型。
- 数量变化:原文 8,260 字,改写后 8,110 字,减少 1.8%;调整 14 个内容块。
- 结构变化:标题层级保持不变;未新增或删除一级标题。
- 已执行的优化:按要求合并重复表述、统一语气、调整段落衔接。
- 保留情况:保留 35 条已选来源引用,未新增外部来源。
- 风险提示:无。
[查看前后对比] [撤销到改写前版本]
~~~
“已执行的优化”仅来自用户要求和可计算的结构差异;不能无依据宣称“文章更专业、更严谨”。
## 6. 前端实现设计
### 6.1 新增模块
~~~text
frontend-web/src/core/document-rewrite/
├─ types.ts
├─ api.ts
├─ sse.ts
├─ use-document-rewrite-job.ts
├─ document-rewrite-provider.tsx
└─ document-rewrite-presentation.ts
frontend-web/src/components/workspace/document-rewrite/
├─ DocumentRewriteDialog.tsx
├─ DocumentRewriteProgressStep.tsx
├─ DocumentRewriteSummaryCard.tsx
└─ DocumentDiffDialog.tsx
~~~
职责:
| 模块 | 职责 |
| --- | --- |
| `api.ts` | 创建、查询、取消、撤销 Job |
| `sse.ts` | SSE 解析、`after_seq` 重连 |
| `use-document-rewrite-job.ts` | Job 状态、草稿、rAF 合并 token |
| Provider | 同时向文件面板与消息列表提供同一任务状态 |
| `DocumentRewriteDialog` | 改写要求、模型、风格配置 |
| ProgressStep | 普通消息列表内的五步步骤条 |
| SummaryCard | 结构化总结、diff、撤销动作 |
| DiffDialog | 原文与改写后双栏/行级对比 |
模型选择使用项目已有的 `tdesign-react` 选择组件,放在全文改写配置弹窗中;局部编辑器保留当前模型传递方式,后续再统一选择器。
### 6.2 流式平滑:每帧合并 delta
不能因为 SSE 是 token 流就每 token 调一次 `setState`。应当网络层完整读取、渲染层按动画帧合并:
~~~ts
const pendingDeltaRef = useRef("");
const frameRef = useRef<number | null>(null);
function onRewriteDelta(delta: string) {
pendingDeltaRef.current += delta;
if (frameRef.current !== null) return;
frameRef.current = requestAnimationFrame(() => {
const pending = pendingDeltaRef.current;
pendingDeltaRef.current = "";
frameRef.current = null;
setDraftContent((previous) => previous + pending);
});
}
~~~
完成、失败、取消前必须 flush 最后一段缓存。右侧代码编辑器只消费 `draftContent`;真实 Artifact 查询缓存直到 `committed` 事件才更新。
### 6.3 ArtifactFileDetail 改造
在 `artifact-file-detail.tsx` 增加:
~~~ts
type DocumentRewriteTarget =
| {
kind: "artifact";
threadId: string;
path: string;
presentationThreadId: string;
}
| {
kind: "deep_research_report";
sessionId: string;
presentationThreadId: string;
};
~~~
改造步骤:
1. 加入右上角全文改写图标按钮和 `DocumentRewriteDialog`。
2. 有活跃任务时强制 `viewMode = "code"`。
3. 内容优先级为:`activeRewrite.draftContent ?? draftContent ?? artifactContent`。
4. 活跃任务中代码只读,禁用保存、局部编辑和重复全文改写。
5. 收到 `committed` 后用现有 `useUpdateArtifactContent` 或等价 Query cache 更新,使真实文件立即同步。
6. 收到 `conflict/error/cancelled` 时废弃临时草稿显示,回到真实文件内容。
### 6.4 ResearchSandboxPanel 接入
相关文件:
- `frontend-web/src/pages/deep-research/ResearchSandboxPanel.tsx`
- `frontend-web/src/pages/deep-research/useReportSandbox.ts`
- `frontend-web/src/pages/deep-research/DeepResearchWorkbench.tsx`
改造:
1. `ResearchSandboxPanel` 为虚拟 `report.md` 传入 `kind: "deep_research_report"` target。
2. `useReportSandbox` 接受 `externalDraftOverride`:
~~~ts
const visibleReport = activeDocumentRewrite?.isActive
? activeDocumentRewrite.draftContent
: reportMarkdown;
~~~
3. 流式期间只显示临时草稿,不提前写 session 报告。
4. `committed` 后刷新/替换 session 的 `report_markdown`;失败后恢复旧报告。
5. 当前“改写第一段 → 候选消息 → 确认应用”逻辑继续保留,不因全文改写而改变。
### 6.5 普通消息列表接入
复用:
- `frontend-web/src/components/workspace/messages/message-list.tsx`
- `frontend-web/src/components/workspace/messages/MessageGroup.tsx`
- `DeepResearchWorkbench.tsx` 中的虚拟消息注入模式。
`DocumentRewritePresentationProvider` 按 `presentation_thread_id` 读取 Job 历史并投影为:
1. 用户消息:“AI 全文改写《xxx.md》”;
2. AI 工具调用:`document_rewrite_progress`;
3. AI 富消息:`document_rewrite_summary`。
`MessageGroup.tsx` 增加 `document_rewrite_progress` 分支,渲染 `DocumentRewriteProgressStep`。最终摘要渲染 `DocumentRewriteSummaryCard`,其内含“查看前后对比”和“撤销”。
全文步骤固定为:
| 步骤 | 展示内容 |
| --- | --- |
| 固定原文版本 | 文件名、原文字数、快照已保存 |
| 理解改写要求 | 改写目标、模型、风格 |
| 流式重写 Markdown | 正在写入右侧 xxx.md、累计字数 |
| 校验文档 | 非空、标题、围栏、截断;报告还含来源检查 |
| 对比原文并生成说明 | 差异、风险、撤销入口 |
步骤条必须在完成后保留,不能因为流结束被隐藏。
## 7. 核心执行伪代码
~~~python
async def run_document_rewrite(job_id: str) -> None:
job = await jobs.acquire_lease(job_id)
source = source_factory.create(job) # 已完成鉴权的来源适配器
await emit("snapshotting")
snapshot = await source.read_snapshot()
base_hash = sha256(snapshot.content)
await jobs.freeze_snapshot(job_id, snapshot, base_hash)
await emit("snapshot_fixed", char_count=count_chars(snapshot.content))
messages = prompt_builder.build(
mode=job.mode,
source_kind=job.source_kind,
original=snapshot.content,
instruction=job.instruction,
style=job.style,
research_sources=snapshot.allowed_sources,
)
await emit("requirements_resolved", ...)
draft = ""
async for chunk in model.stream_text(messages=messages, model_name=job.model_name):
if await jobs.cancel_requested(job_id):
await jobs.mark_cancelled(job_id)
await emit("cancelled")
return
draft += chunk.text
await jobs.append_draft_periodically(job_id, draft)
await emit("rewrite_delta", delta=chunk.text)
await emit("validation_started")
validation = validate_markdown(
draft,
source_kind=job.source_kind,
allowed_citations=snapshot.allowed_citation_ids,
)
if validation.has_fatal_error:
await jobs.mark_failed(job_id, validation.message)
await emit("error", ...)
return
await emit("validation_completed", ...)
diff = build_diff_summary(snapshot.content, draft, validation)
await jobs.save_diff(job_id, diff)
await emit("comparison_ready", diff)
if job.commit_policy != AUTO_COMMIT_AFTER_VALIDATION:
await jobs.mark_candidate_ready(job_id)
return
await emit("commit_started")
await versions.save_before_rewrite(job, snapshot)
result = await source.commit_if_unchanged(
expected_hash=base_hash,
content=draft,
metadata=CommitMetadata(job_id=job_id),
)
if not result.ok:
await jobs.mark_conflict(job_id)
await emit("conflict", ...)
return
await jobs.mark_completed(job_id, result.sha256)
await emit("committed", ...)
await emit("completed", diff)
~~~
## 8. 实施顺序
### 阶段 A:后端内核与安全基础
1. 新增领域模型、来源端口、校验、确定性 diff。
2. 新增 Job、事件、版本数据表与 migration。
3. 参考深度研究 executor 完成后台任务、取消、SSE 重放。
4. 实现普通 Artifact 读取、哈希比较、原子提交和撤销 API。
5. 编写接口测试。
验收:可以通过 API 对普通 Markdown 创建全文任务;取消、失败、冲突均不改原文件;成功后可撤销。
### 阶段 B:普通沙箱全文 UI
1. 新增 `core/document-rewrite` 前端状态、SSE、rAF hook。
2. 改 `ArtifactFileDetail`:右上角按钮、配置弹窗、临时草稿、禁用态。
3. 接入普通 `MessageList` 的步骤条、总结卡、diff 和撤销。
4. 支持刷新后恢复 Job 状态与已完成历史。
验收:右侧可平滑逐 token 写入;完成后替换真实 Markdown;左侧步骤和总结保留;撤销成功恢复。
### 阶段 C:深度研究接入
1. 实现 `DeepResearchReportSource`。
2. 由 `ResearchSandboxPanel` 传入报告 target。
3. `useReportSandbox` 支持外部临时草稿。
4. 对深度研究添加引用白名单校验。
5. 保持现有报告局部候选确认卡不变,再逐步下沉公共 prompt/校验逻辑。
验收:报告全文改写不触发联网搜索,不允许新来源;局部报告改写依然先确认再应用。
### 阶段 D:局部改写内核迁移
1. 保持 `/api/writing/rewrite` 契约不变。
2. 将 `writing.py` 转为 `InlineDocumentSource + preview_only` 的兼容 facade。
3. 给 `useWritingRewrite` 增加原文快照失效检查。
4. 回归替换、插入、重试、继续追问。
## 9. 测试与验收
建议新增后端测试:
~~~text
offline-backend-20260512/backend/tests/
├─ test_document_rewrite_pipeline.py
├─ test_document_rewrite_api.py
├─ test_document_rewrite_versions.py
└─ test_document_rewrite_deep_research.py
~~~
必须覆盖:
- Job 状态、SSE 顺序和断线恢复;
- 空输出、围栏不闭合、截断、非法深度研究引用;
- 同一文件并发任务;
- 提交前手工修改导致的冲突;
- 取消/异常不改真实文件;
- 正常撤销、撤销前手工编辑导致的冲突;
- 旧 `/api/writing/rewrite`、深度研究 `/rewrite/stream` 兼容回归。
前端必须覆盖:
- 多个 delta 在一帧合并,最终内容不丢失;
- `committed` 前 Artifact 缓存不被临时草稿污染;
- 失败/取消/冲突后右侧恢复原文;
- 活跃任务禁用同文件编辑、保存、重复改写;
- 刷新后历史步骤条与总结仍存在;
- 深度研究虚拟 `report.md` 可用全文改写;
- 局部编辑器原文变化后不能应用过期候选。
执行基线:
~~~powershell
cd offline-backend-20260512/backend
$env:PYTHONPATH = "."
uv run --no-sync pytest tests/test_document_rewrite_pipeline.py -v
uv run --no-sync pytest tests/test_document_rewrite_api.py -v
uv run --no-sync ruff check app packages/harness
cd ../../frontend-web
pnpm typecheck
pnpm build
~~~
## 10. 风险控制
| 风险 | 控制措施 |
| --- | --- |
| 用户误以为真实文件已经清空 | 明确显示“临时草稿,原文件尚未修改” |
| 流式显示仍然卡顿 | 网络完整读取 + `requestAnimationFrame` 合并渲染 |
| 改写中用户手动编辑 | `SHA-256` compare-and-swap,冲突即拒绝覆盖 |
| 输出 Markdown 不完整 | 非空、围栏、截断和标题检查 |
| 深度研究幻觉 | 来源白名单、禁止联网、引用 ID 校验 |
| 文档过大 | 第一版拒绝并提示按章节改写,不隐式截断 |
| 局部编辑污染聊天历史 | 局部只在编辑器弹窗展示,不创建完整步骤条 |
| 历史记录只存在浏览器内存 | 全文 Job/Event/Diff 持久化,按展示线程恢复 |
## 11. 复用点清单
| 现有实现 | 在新方案中的用途 |
| --- | --- |
| `MarkdownAiEditor.tsx` | 保留局部编辑菜单、预览弹窗、确认动作 |
| `useWritingRewrite.ts` | 保留局部流控制,增加快照失效保护 |
| `open-canvas/api/rewrite.ts` | 保持兼容,逐步接入统一内核 |
| `routers/writing.py` | 复用当前模型流式读取,抽取 prompt/流逻辑 |
| `routers/deep_research.py` | 复用报告来源、哈希候选、来源约束 |
| `deep_research_job_executor.py` | 复用后台 Job、取消、事件重放模式 |
| `artifact-file-detail.tsx` | 复用沙箱文件操作、代码/预览、缓存同步 |
| `useUpdateArtifactContent` | 完成后更新普通 Artifact 缓存 |
| `ResearchSandboxPanel.tsx` | 复用研究报告的右侧沙箱宿主 |
| `useReportSandbox.ts` | 加入临时草稿覆盖显示 |
| `MessageList.tsx / MessageGroup.tsx` | 复用普通消息步骤条、总结消息、文件卡片能力 |
| `DeepResearchWorkbench.tsx` | 复用向普通消息列表投影过程事件的模式 |
## 12. 完成定义
完成后应满足:
1. 局部编辑依旧是编辑器弹窗中的人工确认操作。
2. 全文改写在普通消息列表展示完整且不隐藏的步骤条。
3. 右侧沙箱可平滑地逐 token 展示临时 Markdown 草稿。
4. 任何中断、取消、校验失败和冲突都不损坏真实文件。
5. 完成后用户可以看到量化差异、结构变化、来源保留和风险提示。
6. 普通 Markdown 与深度研究报告都可全文改写,但研究报告绝不绕过已选来源约束。
7. 每一次真实全文覆盖都有版本快照,并且能够安全撤销。
+148
View File
@@ -0,0 +1,148 @@
# 定时任务 — 模板填充「源数据抽取」手工测试清单
> 覆盖功能:定时任务「模板数据转换器」内置 agent —— 把用户传入的源数据转换成 HTML
> 模板的 `DATA` 结构并填充生成可预览页面。**重点测「源数据抽取」**:源可能是
> ① 纯 JSON、② 含 JSON 的文本、③ 纯文本,三种形态都要正确处理。
>
> 测试环境:后端 `http://localhost:8001`(`make dev`),前端 `http://localhost:5174`(`pnpm dev`)。
> 相关代码:`deerflow/runtime/scheduler/template_fill.py`(`extract_embedded_json`)、
> `service.py`(`_run_template_fill_attempt` / `_build_conversion_prompt`)、
> `pages/ScheduledTasksPage.tsx`。
---
## 前置 — 进入表单
| # | 步骤 | 预期结果 |
|---|------|----------|
| 0.1 | 任务管理 → 新建定时任务 | 弹出「新建定时任务」对话框 |
| 0.2 | 「执行智能体」下拉选择 **模板数据转换器** | 表单出现「HTML 模板」下拉;「必须生成 HTML/Markdown」两个开关隐藏 |
| 0.3 | 「HTML 模板」下拉选择 **no.1** | 下方出现「上传 .json」按钮 + 源数据文本框;说明含「未提供源 JSON 时,将直接展示该模板的默认数据」|
---
## T1 — 源形态①:纯 JSON
| # | 步骤 / 输入 | 预期结果 |
|---|------|----------|
| 1.1 | 在源数据框粘贴纯 JSON(示例见下「样例 A」) | 文本框正常接收,无报错 |
| 1.2 | 保存任务 → 「立即执行」 | 执行记录新增一条,状态最终 succeeded |
| 1.3 | 打开执行记录 → HTML 预览 | 渲染出 no.1 大屏,**总览指标/各列表数据来自粘贴的 JSON**(而非模板默认值)|
| 1.4 | 执行记录正文 | 文案为「已根据源数据填充模板「no.1」生成页面」|
## T2 — 源形态②:含 JSON 的文本(抽取重点)
| # | 步骤 / 输入 | 预期结果 |
|---|------|----------|
| 2.1 | 粘贴「样例 B」(前后是中文说明,中间夹一段 JSON) | 文本框正常接收 |
| 2.2 | 保存 → 立即执行 → 查看 HTML | 页面数据以**夹带的 JSON 为准**填充;正文里的补充说明(如「重点突出 X」)被一并参考 |
| 2.3 | 验证抽取正确性:JSON 字符串值里含 `}`(如 `"备注": "进度 80%}尚未完成"`) | 不会被误判为 JSON 块提前结束,整段 JSON 被完整抽取 |
## T3 — 源形态③:纯文本(无 JSON)
| # | 步骤 / 输入 | 预期结果 |
|---|------|----------|
| 3.1 | 粘贴「样例 C」(一段纯中文描述,无任何 JSON) | 文本框正常接收 |
| 3.2 | 保存 → 立即执行 → 查看 HTML | 智能体**理解文本语义**后据实填充模板,产出完整可预览页面(数据可能较稀疏但结构完整)|
| 3.3 | 不应报「未返回 JSON」类硬失败(除非模型彻底失败重试耗尽)| 状态 succeeded |
## T4 — 空源 → 模板默认数据
| # | 步骤 | 预期结果 |
|---|------|----------|
| 4.1 | 源数据框留空,保存 → 立即执行 | **不调用模型**,直接用 no.1 模板自带的默认数据生成 |
| 4.2 | 执行记录正文 | 「未提供源数据,已用模板「no.1」的默认数据生成页面」|
| 4.3 | HTML 预览 | 展示模板内置的默认大屏 |
## T5 — 上传 .json 文件
| # | 步骤 | 预期结果 |
|---|------|----------|
| 5.1 | 点击「上传 .json 文件」,选一个合法 `.json` | 文件内容被读入源数据文本框 |
| 5.2 | 上传一个非法 JSON 内容的文件 | toast 提示「文件不是合法 JSON,已填入文本框请检查」,内容仍填入(可手改)|
| 5.3 | 连续上传同一个文件两次 | 第二次仍能触发读取(input 已被重置 value)|
## T6 — no.2(只展示模板)
| # | 步骤 | 预期结果 |
|---|------|----------|
| 6.1 | 「HTML 模板」下拉选 **no.2** | **隐藏**上传按钮与源数据文本框;显示「该模板暂为直接展示已有数据,无需填写」|
| 6.2 | 即使之前填过源数据,保存 → 立即执行 | 忽略源数据,**原样输出** no.2 现有页面 |
| 6.3 | 执行记录正文 | 「已展示模板「no.2」的现有数据」|
## T7 — 编辑回显
| # | 步骤 | 预期结果 |
|---|------|----------|
| 7.1 | 对已保存的模板任务点「编辑」 | 「执行智能体」「HTML 模板」「源数据」均正确回显 |
| 7.2 | 把模板从 no.1 改成 no.2 再保存 | 切到 no.2 时源数据区即时隐藏;保存后执行走只展示分支 |
---
## 样例数据(可直接复制粘贴到源数据框)
### 样例 A — 纯 JSON
```json
{
"overview": {
"核心指标": [
{ "名称": "综合区域", "数值": 7, "单位": "区", "说明": "测试数据" },
{ "名称": "组织与单位", "数值": 188, "单位": "个", "说明": "测试数据" }
]
},
"regions": [
{ "name": "测试区域甲", "scope": "本岛西岸" }
],
"equipment": [
{ "name_zh": "测试装备X", "category": "无人系统", "status": "列装" }
]
}
```
> 预期:总览第一项「综合区域」显示 **7**,「组织与单位」显示 **188**,区域/装备出现「测试区域甲」「测试装备X」。
### 样例 B — 含 JSON 的文本
```
这是本月台海态势数据,请据此填充大屏,重点突出离岛防卫:
{"overview": {"核心指标": [{"名称": "综合区域", "数值": 9, "单位": "区", "说明": "含离岛"}]}, "regions": [{"name": "离岛防区", "scope": "外岛", "备注": "进度 80%}尚未完成"}]}
以上数据来自 6 月例会,务必准确,不要臆造未提供的字段。
```
> 预期:① 数据以中间 JSON 为准(综合区域=9、出现「离岛防区」);② 字符串里的 `}`(`进度 80%}`)不破坏抽取;③ 前后的「重点突出离岛防卫」「务必准确」作为补充说明被模型参考。
### 样例 C — 纯文本
```
请整理一份台湾滨海防卫概览:覆盖本岛沿岸 9 个综合区域,组织与单位约 280 个,
装备条目近百项(含无人系统、防空、海军平台等类别),并列出若干关键节点与近期演习。
数据以离线知识为准,没有的字段留空即可。
```
> 预期:智能体理解语义后据实填充,产出结构完整的页面(具体数值取决于模型,可较稀疏),不报硬失败。
---
## 后端单元测试(自动化补充)
```bash
# 在 offline-backend-20260512/backend/ 下运行
PYTHONPATH=. uv run --no-sync pytest tests/test_template_fill.py -v # 引擎:抽取/校验/填充/注册表
PYTHONPATH=. uv run --no-sync pytest tests/test_template_fill_attempt.py -v # 调度器执行分支:三形态/默认/只展示/重试
PYTHONPATH=. uv run --no-sync pytest tests/test_template_builder_seed.py -v # 内置 agent 种子
```
抽取相关关键用例:
- `test_extract_embedded_json_pure_object` / `_pure_array` —— 纯 JSON。
- `test_extract_embedded_json_text_with_json` / `_fenced` —— 含 JSON 的文本 / ```json 围栏。
- `test_extract_embedded_json_plain_text_returns_none` —— 纯文本返回 None。
- `test_extract_embedded_json_ignores_braces_in_strings` —— 引号内 `}` 不误判。
- `test_text_with_embedded_json_surfaced_in_prompt` —— 转换 prompt 单独标注「识别到的结构化数据」。
- `test_plain_text_source_converts` —— 纯文本仍照常转换。
- `test_empty_source_uses_template_default` —— 空源用模板默认数据。
- `test_display_only_template_renders_as_is` —— no.2 原样输出。
三个文件应全部通过(0 failed)。
+3 -2
View File
@@ -15,8 +15,9 @@
</script>
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<link rel="icon" type="image/svg+xml" href="/favicon.svg" />
<title>CM 助手</title>
</head>
<title>CM 助手</title>
<script src="/runtime-config.js" data-runtime-config></script>
</head>
<body>
<div id="root"></div>
<script type="module" src="/src/main.tsx"></script>
+96 -144
View File
@@ -70,6 +70,7 @@
"hast": "^1.0.0",
"katex": "^0.16.28",
"lucide-react": "^0.562.0",
"mermaid": "^11.15.0",
"motion": "^12.26.2",
"nanoid": "^5.1.6",
"next-themes": "^0.4.6",
@@ -104,6 +105,7 @@
"@types/react": "^19.0.0",
"@types/react-dom": "^19.0.0",
"@vitejs/plugin-react": "^5.0.4",
"lightningcss": "^1.30.2",
"postcss": "^8.5.3",
"tailwindcss": "^4.0.15",
"tw-animate-css": "^1.4.0",
@@ -460,37 +462,11 @@
"resolved": "https://registry.npmjs.org/@cfworker/json-schema/-/json-schema-4.1.1.tgz",
"integrity": "sha512-gAmrUZSGtKc3AiBL71iNWxDsyUC5uMaKKGdvzYsBoTW/xi42JQHl7eKV2OYzCUqvc+D2RCcf7EXY2iCyFIk6og=="
},
"node_modules/@chevrotain/cst-dts-gen": {
"version": "12.0.0",
"resolved": "https://registry.npmjs.org/@chevrotain/cst-dts-gen/-/cst-dts-gen-12.0.0.tgz",
"integrity": "sha512-fSL4KXjTl7cDgf0B5Rip9Q05BOrYvkJV/RrBTE/bKDN096E4hN/ySpcBK5B24T76dlQ2i32Zc3PAE27jFnFrKg==",
"dependencies": {
"@chevrotain/gast": "12.0.0",
"@chevrotain/types": "12.0.0"
}
},
"node_modules/@chevrotain/gast": {
"version": "12.0.0",
"resolved": "https://registry.npmjs.org/@chevrotain/gast/-/gast-12.0.0.tgz",
"integrity": "sha512-1ne/m3XsIT8aEdrvT33so0GUC+wkctpUPK6zU9IlOyJLUbR0rg4G7ZiApiJbggpgPir9ERy3FRjT6T7lpgetnQ==",
"dependencies": {
"@chevrotain/types": "12.0.0"
}
},
"node_modules/@chevrotain/regexp-to-ast": {
"version": "12.0.0",
"resolved": "https://registry.npmjs.org/@chevrotain/regexp-to-ast/-/regexp-to-ast-12.0.0.tgz",
"integrity": "sha512-p+EW9MaJwgaHguhoqwOtx/FwuGr+DnNn857sXWOi/mClXIkPGl3rn7hGNWvo31HA3vyeQxjqe+H36yZJwYU8cA=="
},
"node_modules/@chevrotain/types": {
"version": "12.0.0",
"resolved": "https://registry.npmjs.org/@chevrotain/types/-/types-12.0.0.tgz",
"integrity": "sha512-S+04vjFQKeuYw0/eW3U52LkAHQsB1ASxsPGsLPUyQgrZ2iNNibQrsidruDzjEX2JYfespXMG0eZmXlhA6z7nWA=="
},
"node_modules/@chevrotain/utils": {
"version": "12.0.0",
"resolved": "https://registry.npmjs.org/@chevrotain/utils/-/utils-12.0.0.tgz",
"integrity": "sha512-lB59uJoaGIfOOL9knQqQRfhl9g7x8/wqFkp13zTdkRu1huG9kg6IJs1O8hqj9rs6h7orGxHJUKb+mX3rPbWGhA=="
"version": "11.1.2",
"resolved": "https://registry.npmmirror.com/@chevrotain/types/-/types-11.1.2.tgz",
"integrity": "sha512-U+HFai5+zmJCkK86QsaJtoITlboZHBqrVketcO2ROv865xfCMSFpELQoz1GkX5GzME8pTa+3kbKrZHQtI0gdbw==",
"license": "Apache-2.0"
},
"node_modules/@codemirror/autocomplete": {
"version": "6.20.1",
@@ -1732,11 +1708,12 @@
"integrity": "sha512-l0h88YhZFyKdXIFNfSWpyjStDjGHwZ/U7iobcK1cQQD8sejsONdQtTVU+1wVN1PBw40PiiHB1vA5S7VTfQiP9g=="
},
"node_modules/@mermaid-js/parser": {
"version": "1.1.0",
"resolved": "https://registry.npmjs.org/@mermaid-js/parser/-/parser-1.1.0.tgz",
"integrity": "sha512-gxK9ZX2+Fex5zu8LhRQoMeMPEHbc73UKZ0FQ54YrQtUxE1VVhMwzeNtKRPAu5aXks4FasbMe4xB4bWrmq6Jlxw==",
"version": "1.2.0",
"resolved": "https://registry.npmmirror.com/@mermaid-js/parser/-/parser-1.2.0.tgz",
"integrity": "sha512-oYPyv8A4As1yH5Bx+04iQEQxXuIQDe0GKCNSRgao6z8AM9jixXIfP0vsppRLvGf+nKIOb9/LdpWA4YuJiVvESA==",
"license": "MIT",
"dependencies": {
"langium": "^4.0.0"
"@chevrotain/types": "~11.1.2"
}
},
"node_modules/@opentelemetry/api": {
@@ -4274,6 +4251,66 @@
"node": ">=14.0.0"
}
},
"node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/core": {
"version": "1.7.1",
"dev": true,
"inBundle": true,
"license": "MIT",
"optional": true,
"dependencies": {
"@emnapi/wasi-threads": "1.1.0",
"tslib": "^2.4.0"
}
},
"node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/runtime": {
"version": "1.7.1",
"dev": true,
"inBundle": true,
"license": "MIT",
"optional": true,
"dependencies": {
"tslib": "^2.4.0"
}
},
"node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/wasi-threads": {
"version": "1.1.0",
"dev": true,
"inBundle": true,
"license": "MIT",
"optional": true,
"dependencies": {
"tslib": "^2.4.0"
}
},
"node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@napi-rs/wasm-runtime": {
"version": "1.1.0",
"dev": true,
"inBundle": true,
"license": "MIT",
"optional": true,
"dependencies": {
"@emnapi/core": "^1.7.1",
"@emnapi/runtime": "^1.7.1",
"@tybys/wasm-util": "^0.10.1"
}
},
"node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@tybys/wasm-util": {
"version": "0.10.1",
"dev": true,
"inBundle": true,
"license": "MIT",
"optional": true,
"dependencies": {
"tslib": "^2.4.0"
}
},
"node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/tslib": {
"version": "2.8.1",
"dev": true,
"inBundle": true,
"license": "0BSD",
"optional": true
},
"node_modules/@tailwindcss/oxide-win32-arm64-msvc": {
"version": "4.1.18",
"resolved": "https://registry.npmjs.org/@tailwindcss/oxide-win32-arm64-msvc/-/oxide-win32-arm64-msvc-4.1.18.tgz",
@@ -5650,32 +5687,6 @@
"url": "https://github.com/sponsors/wooorm"
}
},
"node_modules/chevrotain": {
"version": "12.0.0",
"resolved": "https://registry.npmjs.org/chevrotain/-/chevrotain-12.0.0.tgz",
"integrity": "sha512-csJvb+6kEiQaqo1woTdSAuOWdN0WTLIydkKrBnS+V5gZz0oqBrp4kQ35519QgK6TpBThiG3V1vNSHlIkv4AglQ==",
"dependencies": {
"@chevrotain/cst-dts-gen": "12.0.0",
"@chevrotain/gast": "12.0.0",
"@chevrotain/regexp-to-ast": "12.0.0",
"@chevrotain/types": "12.0.0",
"@chevrotain/utils": "12.0.0"
},
"engines": {
"node": ">=22.0.0"
}
},
"node_modules/chevrotain-allstar": {
"version": "0.4.3",
"resolved": "https://registry.npmjs.org/chevrotain-allstar/-/chevrotain-allstar-0.4.3.tgz",
"integrity": "sha512-2X4mkroolSMKqW+H22pyPMUVDqYZzPhephTmg/NODKb1IGYPHfxfhcW0EjS7wcPJNbze2i4vBWT7zT5FKF2lrQ==",
"dependencies": {
"lodash-es": "^4.18.1"
},
"peerDependencies": {
"chevrotain": "^12.0.0"
}
},
"node_modules/class-variance-authority": {
"version": "0.7.1",
"license": "Apache-2.0",
@@ -6547,6 +6558,16 @@
"node": ">= 0.4"
}
},
"node_modules/es-toolkit": {
"version": "1.49.0",
"resolved": "https://registry.npmmirror.com/es-toolkit/-/es-toolkit-1.49.0.tgz",
"integrity": "sha512-G5iZ6Pc/FNRY/soKZHC+TxGDD83rHUDXxzaWhGCX44vAv/tMs56WMusnm/KMNK+luUPsgA9U28cGr4RDlSzL2g==",
"license": "MIT",
"workspaces": [
"docs",
"benchmarks"
]
},
"node_modules/esbuild": {
"version": "0.25.12",
"resolved": "https://registry.npmmirror.com/esbuild/-/esbuild-0.25.12.tgz",
@@ -7354,7 +7375,9 @@
}
},
"node_modules/katex": {
"version": "0.16.28",
"version": "0.16.47",
"resolved": "https://registry.npmmirror.com/katex/-/katex-0.16.47.tgz",
"integrity": "sha512-Eeo8Ys1doU1z+x8AZsPpQu+p/QcZBI5PeOo7QGQdy2x2m0MU/hYagBbGOmXwr5KVbEfVuWv9LpnQWeehogurjg==",
"funding": [
"https://opencollective.com/katex",
"https://github.com/sponsors/katex"
@@ -7372,23 +7395,6 @@
"resolved": "https://registry.npmjs.org/khroma/-/khroma-2.1.0.tgz",
"integrity": "sha512-Ls993zuzfayK269Svk9hzpeGUKob/sIgZzyHYdjQoAdQetRKpOLj+k/QQQ/6Qi0Yz65mlROrfd+Ev+1+7dz9Kw=="
},
"node_modules/langium": {
"version": "4.2.3",
"resolved": "https://registry.npmjs.org/langium/-/langium-4.2.3.tgz",
"integrity": "sha512-sOPIi4hISFnY7twwV97ca1TsxpBtXq0URu/LL1AvxwccPG/RIBBlKS7a/f/EL6w8lTNaS0EFs/F+IdSOaqYpng==",
"dependencies": {
"@chevrotain/regexp-to-ast": "~12.0.0",
"chevrotain": "~12.0.0",
"chevrotain-allstar": "~0.4.3",
"vscode-languageserver": "~9.0.1",
"vscode-languageserver-textdocument": "~1.0.11",
"vscode-uri": "~3.1.0"
},
"engines": {
"node": ">=20.10.0",
"npm": ">=10.2.3"
}
},
"node_modules/langsmith": {
"version": "0.6.0",
"resolved": "https://registry.npmjs.org/langsmith/-/langsmith-0.6.0.tgz",
@@ -8100,43 +8106,32 @@
"integrity": "sha512-Lf+9+2r+Tdp5wXDXC4PcIBjTDtq4UKjCPMQhKIuzpJNW0b96kVqSwW0bT7FhRSfmAiFYgP+SCRvdrDozfh0U5w=="
},
"node_modules/mermaid": {
"version": "11.14.0",
"resolved": "https://registry.npmjs.org/mermaid/-/mermaid-11.14.0.tgz",
"integrity": "sha512-GSGloRsBs+JINmmhl0JDwjpuezCsHB4WGI4NASHxL3fHo3o/BRXTxhDLKnln8/Q0lRFRyDdEjmk1/d5Sn1Xz8g==",
"version": "11.16.0",
"resolved": "https://registry.npmmirror.com/mermaid/-/mermaid-11.16.0.tgz",
"integrity": "sha512-Zvm3kbstgdpvIJPPItlL7fppIZ3kibvc1oZIGxdvk9t6UFz6flv+Jw7FtRGKwfcI8OckmH04LqG6LlS6X4B1pA==",
"license": "MIT",
"dependencies": {
"@braintree/sanitize-url": "^7.1.1",
"@braintree/sanitize-url": "^7.1.2",
"@iconify/utils": "^3.0.2",
"@mermaid-js/parser": "^1.1.0",
"@mermaid-js/parser": "^1.2.0",
"@types/d3": "^7.4.3",
"@upsetjs/venn.js": "^2.0.0",
"cytoscape": "^3.33.1",
"cytoscape": "^3.33.3",
"cytoscape-cose-bilkent": "^4.1.0",
"cytoscape-fcose": "^2.2.0",
"d3": "^7.9.0",
"d3-sankey": "^0.12.3",
"dagre-d3-es": "7.0.14",
"dayjs": "^1.11.19",
"dompurify": "^3.3.1",
"katex": "^0.16.25",
"dayjs": "^1.11.20",
"dompurify": "^3.3.3",
"es-toolkit": "^1.45.1",
"katex": "^0.16.45",
"khroma": "^2.1.0",
"lodash-es": "^4.17.23",
"marked": "^16.3.0",
"roughjs": "^4.6.6",
"stylis": "^4.3.6",
"ts-dedent": "^2.2.0",
"uuid": "^11.1.0"
}
},
"node_modules/mermaid/node_modules/uuid": {
"version": "11.1.1",
"resolved": "https://registry.npmjs.org/uuid/-/uuid-11.1.1.tgz",
"integrity": "sha512-vIYxrBCC/N/K+Js3qSN88go7kIfNPssr/hHCesKCQNAjmgvYS2oqr69kIufEG+O4+PfezOH4EbIeHCfFov8ZgQ==",
"funding": [
"https://github.com/sponsors/broofa",
"https://github.com/sponsors/ctavan"
],
"bin": {
"uuid": "dist/esm/bin/uuid"
"uuid": "^11.1.0 || ^12 || ^13 || ^14.0.0"
}
},
"node_modules/micromark": {
@@ -10414,49 +10409,6 @@
"vite": ">=5.0.0"
}
},
"node_modules/vscode-jsonrpc": {
"version": "8.2.0",
"resolved": "https://registry.npmjs.org/vscode-jsonrpc/-/vscode-jsonrpc-8.2.0.tgz",
"integrity": "sha512-C+r0eKJUIfiDIfwJhria30+TYWPtuHJXHtI7J0YlOmKAo7ogxP20T0zxB7HZQIFhIyvoBPwWskjxrvAtfjyZfA==",
"engines": {
"node": ">=14.0.0"
}
},
"node_modules/vscode-languageserver": {
"version": "9.0.1",
"resolved": "https://registry.npmjs.org/vscode-languageserver/-/vscode-languageserver-9.0.1.tgz",
"integrity": "sha512-woByF3PDpkHFUreUa7Hos7+pUWdeWMXRd26+ZX2A8cFx6v/JPTtd4/uN0/jB6XQHYaOlHbio03NTHCqrgG5n7g==",
"dependencies": {
"vscode-languageserver-protocol": "3.17.5"
},
"bin": {
"installServerIntoExtension": "bin/installServerIntoExtension"
}
},
"node_modules/vscode-languageserver-protocol": {
"version": "3.17.5",
"resolved": "https://registry.npmjs.org/vscode-languageserver-protocol/-/vscode-languageserver-protocol-3.17.5.tgz",
"integrity": "sha512-mb1bvRJN8SVznADSGWM9u/b07H7Ecg0I3OgXDuLdn307rl/J3A9YD6/eYOssqhecL27hK1IPZAsaqh00i/Jljg==",
"dependencies": {
"vscode-jsonrpc": "8.2.0",
"vscode-languageserver-types": "3.17.5"
}
},
"node_modules/vscode-languageserver-textdocument": {
"version": "1.0.12",
"resolved": "https://registry.npmjs.org/vscode-languageserver-textdocument/-/vscode-languageserver-textdocument-1.0.12.tgz",
"integrity": "sha512-cxWNPesCnQCcMPeenjKKsOCKQZ/L6Tv19DTRIGuLWe32lyzWhihGVJ/rcckZXJxfdKCFvRLS3fpBIsV/ZGX4zA=="
},
"node_modules/vscode-languageserver-types": {
"version": "3.17.5",
"resolved": "https://registry.npmjs.org/vscode-languageserver-types/-/vscode-languageserver-types-3.17.5.tgz",
"integrity": "sha512-Ld1VelNuX9pdF39h2Hgaeb5hEZM2Z3jUrrMgWQAu82jMtZp7p3vJT3BzToKtZI7NgQssZje5o0zryOrhQvzQAg=="
},
"node_modules/vscode-uri": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/vscode-uri/-/vscode-uri-3.1.0.tgz",
"integrity": "sha512-/BpdSx+yCQGnCvecbyXdxHDkuk55/G3xwnC0GqY4gmQ3j+A+g8kzzgB4Nk/SINjqn6+waqw3EgbVF2QKExkRxQ=="
},
"node_modules/w3c-keyname": {
"version": "2.2.8",
"resolved": "https://registry.npmjs.org/w3c-keyname/-/w3c-keyname-2.2.8.tgz",
+5 -1
View File
@@ -7,9 +7,12 @@
"dev": "vite",
"build": "node --max-old-space-size=8192 ./node_modules/vite/bin/vite.js build",
"build:sit": "node --max-old-space-size=8192 ./node_modules/vite/bin/vite.js build --mode sit",
"build:test": "node --max-old-space-size=8192 ./node_modules/vite/bin/vite.js build --mode test",
"build:network": "node --max-old-space-size=8192 ./node_modules/vite/bin/vite.js build --mode network",
"preview": "vite preview",
"typecheck": "tsc --noEmit"
"typecheck": "tsc --noEmit",
"check:chrome109-css": "node scripts/check-chrome109-css.mjs",
"check:legacy-chrome-css": "node scripts/check-chrome109-css.mjs"
},
"dependencies": {
"@codemirror/lang-css": "^6.3.1",
@@ -109,6 +112,7 @@
"@types/react": "^19.0.0",
"@types/react-dom": "^19.0.0",
"@vitejs/plugin-react": "^5.0.4",
"lightningcss": "^1.30.2",
"postcss": "^8.5.3",
"tailwindcss": "^4.0.15",
"tw-animate-css": "^1.4.0",
+11 -5
View File
@@ -1,5 +1,11 @@
export default {
plugins: {
"@tailwindcss/postcss": {},
},
};
import tailwindcss from "@tailwindcss/postcss";
import legacyColorFallback from "./scripts/postcss-legacy-color-fallback.mjs";
import lightningCssLegacyChrome from "./scripts/postcss-lightningcss-chrome109.mjs";
export default {
plugins: [
tailwindcss(),
legacyColorFallback(),
lightningCssLegacyChrome(),
],
};
Binary file not shown.

After

Width:  |  Height:  |  Size: 39 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 53 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 27 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 27 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 27 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 33 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 33 KiB

+28
View File
@@ -0,0 +1,28 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 48 48" role="img" aria-labelledby="title">
<title id="title">CM 助手</title>
<defs>
<linearGradient id="logoTopLeft" x1="7" y1="7" x2="25" y2="20" gradientUnits="userSpaceOnUse">
<stop stop-color="#5DB5FF"/>
<stop offset="1" stop-color="#328AF2"/>
</linearGradient>
<linearGradient id="logoTopRight" x1="24" y1="3" x2="43" y2="19" gradientUnits="userSpaceOnUse">
<stop stop-color="#62B2FF"/>
<stop offset="1" stop-color="#4B98F4"/>
</linearGradient>
<linearGradient id="logoLeft" x1="5" y1="14" x2="24" y2="45" gradientUnits="userSpaceOnUse">
<stop stop-color="#2C7CF0"/>
<stop offset="1" stop-color="#1F5EDA"/>
</linearGradient>
<linearGradient id="logoBottom" x1="9" y1="31" x2="43" y2="40" gradientUnits="userSpaceOnUse">
<stop stop-color="#276DE3"/>
<stop offset="1" stop-color="#4E9DF5"/>
</linearGradient>
</defs>
<!-- The mark is drawn as four independent folded faces. Together they form
the open C-shaped cube used in the product reference. -->
<path d="M5 13.5 24 3v10L14 18.5 5 13.5Z" fill="url(#logoTopLeft)"/>
<path d="M24 3 43 13.5 34 18.5 24 13V3Z" fill="url(#logoTopRight)"/>
<path d="M5 13.5 14 18.5v11L24 35v10L5 34.5v-21Z" fill="url(#logoLeft)"/>
<path d="M14 29.5 24 35l10-5.5 9 5L24 45 5 34.5l9-5Z" fill="url(#logoBottom)"/>
</svg>

After

Width:  |  Height:  |  Size: 1.4 KiB

+167
View File
@@ -0,0 +1,167 @@
// 前端运行时配置文件
//
// 说明:
// 1. 本文件会在打包时原样复制到 dist/runtime-config.js。
// 2. 应用启动时会优先读取 window.__CM_RUNTIME_CONFIG__ 里的配置。
// 3. 部署后如果需要切换接口地址,直接修改 dist/runtime-config.js 即可,不需要重新 pnpm build。
// 4. 这里的默认值来自 .env.network;如某个环境不用某项,可以留空字符串。
// 5. 布尔开关也用字符串形式填写:"true" / "false"。
window.__CM_RUNTIME_CONFIG__ = {
// 品牌图片相对路径会以 runtime-config.js 所在目录为基准解析。
// Nginx 以子路径部署时不需要修改前端图片路径。
// 打包后可直接替换 dist/brand-assets/ 内的同名 PNG。
// 也可以把下方图片地址改为其他 PNG 地址,无需重新打包。
// 是否显示整块欢迎页图标区域:"true" 显示,"false" 隐藏,默认隐藏。
VITE_WELCOME_LOGO_VISIBLE: "false",
// 深色主题顶栏 Logo 位置:"center" 显示在中间,"left" 显示在左上角,默认中间。
VITE_DARK_LOGO_POSITION: "center",
// 红白主题的顶栏系统 Logo 图片地址。
VITE_BRAND_LOGO_LIGHT_URL: "brand-assets/brand-logo-light.png",
// 浅蓝主题的顶栏系统 Logo 图片地址。
VITE_BRAND_LOGO_LIGHTBLUE_URL: "brand-assets/brand-logo-lightblue.png",
// 绿色主题可单独替换 Logo;默认复用浅色 Logo。
VITE_BRAND_LOGO_LIGHTGREEN_URL: "brand-assets/brand-logo-light.png",
// 深色主题的顶栏系统 Logo 图片地址。
VITE_BRAND_LOGO_DARK_URL: "brand-assets/brand-logo-dark.png",
// 红白主题的欢迎页 Logo 图片地址:为空时显示原有 CM 文字和渐变背景。
VITE_BRAND_WELCOME_LIGHT_URL: "",
// 浅蓝主题的欢迎页 Logo 图片地址:为空时显示原有 CM 文字和渐变背景。
VITE_BRAND_WELCOME_LIGHTBLUE_URL: "",
VITE_BRAND_WELCOME_LIGHTGREEN_URL: "",
// 深色主题的欢迎页 Logo 图片地址:为空时显示原有 CM 文字和渐变背景。
VITE_BRAND_WELCOME_DARK_URL: "",
// DeerFlow Gateway 地址:前端自有后端接口,例如 /api/agents、/api/auth、/api/threads 等。
// VITE_BACKEND_BASE_URL: "https://ch1.b.uat.4.cn/deerflow",
// LangGraph 流式对话接口地址:普通问答、智能体对话等流式能力使用。
// VITE_LANGGRAPH_BASE_URL: "https://ch1.b.uat.4.cn/deerflow/api",
// Canvas/AI 写作独立 LangGraph 地址:为空时前端会回退使用 VITE_LANGGRAPH_BASE_URL。
VITE_CANVAS_LANGGRAPH_BASE_URL: "",
// routeKey 短路由的用户名直登口令:例如 #/login/admin?routeKey=a。
// 填值时优先使用这里的 password;留空时使用 URL 中的 ?password=。
VITE_ROUTE_LOGIN_PASSWORD: "",
// 轻应用「新建笔记」系列接口地址。
VITE_NOTE_API_BASE_URL: "http://47.88.25.99:8000",
// CMZS 后端接口:任务管理、任务分析、三情分析、行动分析等业务接口。
VITE_API_BASE_URL: "https://ch1.b.uat.4.cn/zncm",
// 8BF 嵌入页专用任务系统接口。部署到其他系统时只需修改这一项,
// 不影响原多智能体会商使用的任务详情接口。
VITE_8BF_TASK_API_BASE_URL: "https://ch1.b.uat.4.cn/zl_consumer",
// 8BF 会商页右上角「返回」按钮的跳转地址(当前窗口 window.location.href)。
// 部署后直接改 dist/runtime-config.js 即可,无需重新打包。留空则点击时提示未配置。
VITE_8BF_ROUNDTABLE_BACK_URL: "",
// 任务深链「宿主路由」按钮的 postMessage targetOrigin(HOST_NAVIGATE)。
// 填宿主系统 origin,例如 https://localhost:4912;生产改成他们线上地址。
// 留空时尝试用 iframe 的 ancestorOrigins / referrer 自动探测,探测失败则不发送。
VITE_HOST_NAVIGATE_ORIGIN: "",
// 佳来模型对话接口。
VITE_AIPI_CHAT_URL: "https://ch1.b.uat.4.cn/gpt",
// 多轮检索/生成接口。
VITE_AIPI_GENERATE_CHAT_URL: "https://ch1.b.uat.4.cn/jialai_b1_chat",
// 任务问答接口。
VITE_AIPI_TASK_CHAT_URL: "https://ch1.b.uat.4.cn/qq_b1_chat",
// B 系统知识库前端地址:用于打开知识详情、原文详情等。
VITE_AIPI_KNOWLEDGE_URL: "https://chlib.b.uat.4.cn/knowlibrary",
// B1 COH 系统地址。
VITE_AIPI_B1COH_URL: "https://ch1.b.uat.4.cn/web",
// B2 行为体/网络资源系统地址。
VITE_AIPI_B2ACTOR_URL: "https://ty.b.uat.4.cn",
// B2 网络 XWT iframe 路径。
VITE_AIPI_B2ACTOR_XWT_PATH: "/fromB/toXWT?isFrame=1",
// 知识库 iframe 地址换取接口。
VITE_AIPI_KNOWLEDGE_IFRAME_API_URL: "https://ch1.b.uat.4.cn/knowes/api/iframeKnowledgeUrl",
// 知识库 iframe 皮肤参数。
VITE_AIPI_KNOWLEDGE_IFRAME_SKIN: "red",
// MopeChat 接口地址。
VITE_AIPI_MOPECHAT_URL: "https://ch1.b.uat.4.cn/likun_b1_mope",
// 工作室/空间后端接口:空间列表、空间详情、素材上传等使用。
VITE_AIPI_BACKENP_URL: "http://47.88.25.99:8000",
// 工作室/空间后端别名:兼容旧配置命名,通常与 VITE_AIPI_BACKENP_URL 保持一致。
VITE_NOTEBOOK_API_BASE_URL: "http://47.88.25.99:8000",
// 工作室/空间前端地址:用于 auth/callback、新建对话等跳转。
VITE_AIPI_FRONTEND_URL: "http://47.88.25.99:3000",
// Consumer 接口:深链任务详情 cop-task-detail、研判情报报告 selectSqReport 等使用。
VITE_AIPI_CONSUMER_URL: "https://ch1.b.uat.4.cn/consumer",
// A 系统跳转地址:人物、组织、事件等列表项打开链接使用。
VITE_AIPI_PRESENT_URL: "http://present.a.uat.4.cn/present/domain",
// B 系统 knowes 根地址。
VITE_AIPI_KNOWES_URL: "http://ch1.b.uat.4.cn/knowes",
// MaxKey 鉴权地址:onlineTicket 换 token 使用。
VITE_AUTH_BASE_URL: "https://auth.y.uat.4.cn",
// PG 中任务 iframe 地址。
VITE_AIPI_PGLINKTO_URL: "https://pg.b.uat.4.cn",
// XK 中任务 iframe 地址。
VITE_AIPI_XKLINKTO_URL: "https://kz.b.uat.4.cn",
// 是否使用真实任务看板数据:true=真实接口;false=本地 mock。
VITE_USE_REAL_DATA: "true",
// 登录深链任务详情是否使用本地 mock:false=真实接口;true=本地 mock。
VITE_MOCK_COP_TASK_DETAIL: "false",
// 岗位会商完整演示数据:true=启动时幂等写入后端;后端不可用时直接使用前端 JSON 兜底。
// 默认关闭,避免演示历史记录出现在正常生产账号中。
VITE_POSITION_ROUNDTABLE_DEMO_MODE: "false",
// 纯前端岗位分析演示:跳过登录,直接进入岗位分析页,并禁止所有后台请求。
// 仅用于离线展台/演示环境,生产环境必须保持 false。
VITE_POSITION_ROUNDTABLE_STANDALONE_MODE: "false",
// 大屏绘制 selectSqReport 是否使用本地 mock:不在运行时强制覆盖,
// 由各环境的 .env 文件决定(开发环境为 true,生产环境为 false)。
// 静态站点模式开关;一般部署业务系统时保持 false。
VITE_STATIC_WEBSITE_ONLY: "false",
// 紧凑导航开关:true 时固定使用简洁布局,工作台左侧栏收起为菜单图标,
// 隐藏系统 Logo、换肤按钮以及“全量/简洁模式”切换。修改后刷新页面即可生效。
VITE_FORCE_COLLAPSED_SIDEBAR: "false",
// 简介模式左侧菜单类型:与菜单管理页「简介模式」里的类型 A / B 对应。
// 两套网页部署时分别填 "A" 或 "B"。不填、留空、或旧配置没有这一项,都按类型 A,
// 继续读取原来的简介菜单数据,无需改旧页面。
VITE_COMPACT_MENU_TYPE: "A",
// GitHub OAuth Token;不使用 GitHub 相关能力时留空。
VITE_GITHUB_OAUTH_TOKEN: "",
// 是否在智能体管理页显示「舆情分析」类型:"true" 显示,"false" 隐藏。
// 关闭后,该智能体的专用对话地址也会自动跳回智能体管理页。
VITE_SENTIMENT_AGENT_VISIBLE: "true",
// 舆情分析智能体:外部流式问答接口地址(POST,SSE 流式返回)。
// 前端会把该地址随请求传给后台转发。留空时该智能体对话页会提示未配置。
VITE_SENTIMENT_AGENT_API_URL: "http://alg.gw.y.uat.cn/a6_report_agent/alg/stream/report-agent",
// 舆情分析智能体:请求头 Authorization Basic Auth 用户名。
VITE_SENTIMENT_AGENT_AUTH_USERNAME: "1054841959975223296",
// 舆情分析智能体:请求头 Authorization Basic Auth 密码。
VITE_SENTIMENT_AGENT_AUTH_PASSWORD: "LzqqMTUxMTIwMjQxNjQ2MjY5MDUduC",
};
@@ -0,0 +1,119 @@
import fs from "node:fs";
import path from "node:path";
import postcss from "postcss";
const unsupportedColor = /(?:color-mix|oklch|oklab|lab|lch)\(/i;
const assetsDir = path.resolve("dist/assets");
if (!fs.existsSync(assetsDir)) {
throw new Error("dist/assets 不存在,请先运行 pnpm build");
}
const cssFiles = fs
.readdirSync(assetsDir)
.filter((file) => file.endsWith(".css"));
if (cssFiles.length === 0) {
throw new Error("dist/assets 中没有 CSS 构建产物");
}
const failures = [];
let modernDeclarations = 0;
const requiredLegacyFallbacks = [
{
file: "src/components/ui/textarea.tsx",
pattern: /rows=\{rows\s*\?\?\s*3\}/,
description: "Textarea needs a native rows fallback",
},
{
file: "src/components/ai-elements/prompt-input.tsx",
pattern: /<InputGroup className="h-auto min-h-16">/,
description: "Prompt textarea must not rely on :has() for its parent height",
},
{
file: "src/core/utils/mermaid.ts",
pattern: /htmlLabels:\s*false[\s\S]*secure:\s*\[[\s\S]*"htmlLabels"/,
description: "Sandbox flowcharts must use native SVG labels in legacy browsers",
},
{
file: "src/core/utils/legacy-html-preview.ts",
pattern: /export function downlevelModernColors[\s\S]*function injectLegacyChartShim/,
description: "Generated HTML charts must downlevel modern CSS colors for Chrome 109",
},
];
for (const file of cssFiles) {
const root = postcss.parse(
fs.readFileSync(path.join(assetsDir, file), "utf8"),
{ from: file },
);
root.walkDecls((declaration) => {
if (!unsupportedColor.test(declaration.value)) return;
modernDeclarations += 1;
let ancestor = declaration.parent;
while (ancestor) {
if (
ancestor.type === "atrule" &&
ancestor.name === "supports" &&
unsupportedColor.test(ancestor.params)
) {
return;
}
ancestor = ancestor.parent;
}
let previous = declaration.prev();
while (previous?.type === "comment") previous = previous.prev();
const hasSafeFallback =
!declaration.prop.startsWith("--") &&
previous?.type === "decl" &&
previous.prop === declaration.prop &&
!unsupportedColor.test(previous.value);
if (!hasSafeFallback) {
failures.push(
`${file}:${declaration.source?.start?.line ?? "?"} ${declaration.prop}: ${declaration.value}`,
);
}
});
}
function walk(directory) {
return fs.readdirSync(directory, { withFileTypes: true }).flatMap((entry) => {
const fullPath = path.join(directory, entry.name);
return entry.isDirectory() ? walk(fullPath) : [fullPath];
});
}
for (const file of walk(path.resolve("src"))) {
if (!/\.[jt]sx?$/.test(file)) continue;
const source = fs.readFileSync(file, "utf8");
if (unsupportedColor.test(source)) {
failures.push(
`${path.relative(process.cwd(), file)} contains a runtime-only modern color function`,
);
}
}
for (const fallback of requiredLegacyFallbacks) {
const source = fs.readFileSync(path.resolve(fallback.file), "utf8");
if (!fallback.pattern.test(source)) {
failures.push(`${fallback.file}: ${fallback.description}`);
}
}
if (failures.length > 0) {
console.error("Legacy Chrome CSS compatibility check failed:\n");
console.error(failures.slice(0, 50).join("\n"));
if (failures.length > 50) {
console.error(`... and ${failures.length - 50} more`);
}
process.exit(1);
}
console.log(
`Legacy Chrome (100+) CSS compatibility check passed (${modernDeclarations} guarded modern declarations).`,
);
@@ -0,0 +1,70 @@
/**
* Tailwind 4 gracefully falls back from color-mix() to the base semantic
* color, but that turns utilities such as bg-primary/5 into an opaque fill on
* Chrome 109. Replace that fallback with an sRGB-channel based alpha color.
* The modern color-mix() declaration remains in its @supports block.
*/
const LEGACY_RGB_TOKENS = new Set([
"accent",
"background",
"border",
"brand-200",
"card",
"destructive",
"foreground",
"input",
"muted",
"muted-foreground",
"primary",
"primary-foreground",
"ring",
"secondary",
"sidebar-accent",
"sidebar-border",
"sidebar-foreground",
"workspace-brand",
]);
const TRANSPARENT_MIX_RE =
/color-mix\(\s*in\s+[\w-]+\s*,\s*var\(--([\w-]+)\)\s+([\d.]+)%\s*,\s*transparent\s*\)/i;
function legacyAlphaColor(value) {
const match = value.match(TRANSPARENT_MIX_RE);
if (!match || !LEGACY_RGB_TOKENS.has(match[1])) return null;
const [, token, percentage] = match;
return `rgb(var(--legacy-${token}-rgb) / ${percentage}%)`;
}
export default function legacyColorFallback() {
return {
postcssPlugin: "postcss-legacy-color-fallback",
OnceExit(root) {
root.walkAtRules("supports", (atRule) => {
if (!atRule.params.includes("color-mix")) return;
atRule.walkDecls((modernDeclaration) => {
const fallbackValue = legacyAlphaColor(modernDeclaration.value);
if (!fallbackValue) return;
// Tailwind emits the old-browser declaration immediately before
// the nested @supports block, in the same utility/variant rule.
let fallbackDeclaration = atRule.prev();
while (fallbackDeclaration?.type === "comment") {
fallbackDeclaration = fallbackDeclaration.prev();
}
if (
fallbackDeclaration?.type === "decl" &&
fallbackDeclaration.prop === modernDeclaration.prop
) {
fallbackDeclaration.value = fallbackValue;
}
});
});
},
};
}
legacyColorFallback.postcss = true;
@@ -0,0 +1,33 @@
import postcss from "postcss";
import { transform } from "lightningcss";
const LEGACY_CHROME = 100 << 16;
/**
* Keep Vite's PostCSS pipeline (required by Tailwind 4), then compile the
* resulting CSS to Chrome 100-compatible syntax for both dev and production.
*/
export default function lightningCssLegacyChrome() {
return {
postcssPlugin: "postcss-lightningcss-legacy-chrome",
OnceExit(root, { result }) {
const filename = root.source?.input.file ?? result.opts.from ?? "style.css";
const output = transform({
filename,
code: Buffer.from(root.toString()),
targets: { chrome: LEGACY_CHROME },
minify: false,
});
const compiled = postcss.parse(output.code.toString(), { from: filename });
root.removeAll();
root.append(compiled.nodes);
for (const warning of output.warnings) {
result.warn(warning.message, { plugin: "lightningcss" });
}
},
};
}
lightningCssLegacyChrome.postcss = true;
+64 -16
View File
@@ -7,6 +7,7 @@ import { FontScaleApplier } from "@/components/font-scale";
import { QueryClientProvider } from "@/components/query-client-provider";
import { AuthSyncWatcher } from "@/core/auth/sync";
import { I18nProvider } from "@/core/i18n/context";
import { fetchYLogConfig } from "@/core/log/y-log-config";
import { detectLocale } from "@/core/i18n/locale";
import { resolveForcedThemeForPath } from "@/core/page-layout/chats-iframe-route";
import { ChatProvider } from "@/contexts/ChatContext";
@@ -36,26 +37,47 @@ import PublicRoundtableSharePage from "./pages/PublicRoundtableSharePage";
import EmbedChatPage from "./pages/EmbedChatPage";
import EmbedRoundtablePage from "./pages/EmbedRoundtablePage";
import DashboardStandalonePage from "@/roundtable-planning/pages/DashboardStandalonePage";
import PositionRoundtablePage from "@/position-roundtable/pages/PositionRoundtablePage";
import WeKnoraWikiPageView from "@/strategy-components/components/resource-management/llmwiki/WeKnoraWikiPageView";
import {
isPositionRoundtableStandaloneMode,
POSITION_ROUNDTABLE_ROUTE,
} from "@/position-roundtable/demo/position-roundtable-demo-config";
import { ChatRuntime } from "./pages/WorkspaceRoutes";
import { NotFoundPage } from "./pages/NotFoundPage";
const PUBLIC_EMBED_PREFIXES = ["/share/", "/public/", "/roundtable-share/"];
const PUBLIC_EMBED_PREFIXES = [
"/share/",
"/public/",
"/roundtable-share/",
"/embed/knowledge/",
];
function AppProviders({ children }: { children: React.ReactNode }) {
const locale = useMemo(() => detectLocale(), []);
const location = useLocation();
const publicEmbedTheme = usePublicEmbedTheme();
const positionStandaloneMode = isPositionRoundtableStandaloneMode();
// iframe 嵌入会话(按标签页 sessionStorage)集中在此同步:任何带 `&embed=1` 的入口(深链登录页
// 或直接深链路由)一进来就启用、`embed=0` 关闭,后续干净路由靠会话维持去 chrome + 强制主题。
useEffect(() => {
syncEmbedSessionFromSearch(location.search);
}, [location.search]);
// 操作日志(Y-Log):启动早期预热上报配置,使 writeYLog 同步读缓存即可工作
// (刷新后 module 缓存清空,token 登录用户也能继续上报)。失败静默。
useEffect(() => {
if (positionStandaloneMode) return;
void fetchYLogConfig();
}, [positionStandaloneMode]);
const forcedTheme = useMemo(() => {
// iframe 嵌入模式(外部系统 `&embed=1`)最高优先:按本标签页的嵌入主题强制明/暗。
// 走 next-themes forcedTheme(不写 localStorage)→ 同浏览器另开的正常系统页不受影响。
const embedTheme = resolveForcedEmbedTheme(location.search);
if (embedTheme) return embedTheme;
const routeTheme = resolveForcedThemeForPath(location.pathname);
const routeTheme = resolveForcedThemeForPath(
location.pathname,
location.search,
);
if (routeTheme) return routeTheme;
if (location.pathname === "/embed/roundtable") {
const wp = readWujieProps();
@@ -80,22 +102,23 @@ function AppProviders({ children }: { children: React.ReactNode }) {
attribute="class"
storageKey="strategy-theme"
defaultTheme="light"
themes={["light", "dark", "lightblue"]}
themes={["light", "dark", "lightblue", "lightgreen", "iceblue", "lightyellow"]}
enableSystem={false}
disableTransitionOnChange
forcedTheme={forcedTheme}
>
<QueryClientProvider>
<I18nProvider initialLocale={locale}>
<ThemeProvider>
<ChatProvider>
<AuthSyncWatcher />
<DesensitizeWordsLoader />
<FontScaleApplier />
{children}
</ChatProvider>
</ThemeProvider>
</I18nProvider>
<AuthSyncWatcher disabled={positionStandaloneMode}>
<I18nProvider initialLocale={locale}>
<ThemeProvider>
<ChatProvider>
{!positionStandaloneMode && <DesensitizeWordsLoader />}
<FontScaleApplier />
{children}
</ChatProvider>
</ThemeProvider>
</I18nProvider>
</AuthSyncWatcher>
</QueryClientProvider>
</NextThemesProvider>
);
@@ -108,17 +131,38 @@ function AppProviders({ children }: { children: React.ReactNode }) {
*/
function RootRedirect() {
const { search } = useLocation();
if (isPositionRoundtableStandaloneMode()) {
return <Navigate to={POSITION_ROUNDTABLE_ROUTE} replace />;
}
return <Navigate to={`/login${search}`} replace />;
}
export function App() {
const positionStandaloneMode = isPositionRoundtableStandaloneMode();
const standaloneLoginRedirect = (
<Navigate to={POSITION_ROUNDTABLE_ROUTE} replace />
);
const pageElement = positionStandaloneMode ? (
<ChatRuntime>
<PositionRoundtablePage compactChrome />
</ChatRuntime>
) : (
<PageRoutes />
);
return (
<HashRouter>
<AppProviders>
<Routes>
<Route path="/" element={<RootRedirect />} />
<Route path="/login" element={<LoginPage />} />
<Route path="/login/:username" element={<LoginPage />} />
<Route
path="/login"
element={positionStandaloneMode ? standaloneLoginRedirect : <LoginPage />}
/>
<Route
path="/login/:username"
element={positionStandaloneMode ? standaloneLoginRedirect : <LoginPage />}
/>
<Route path="/landing" element={<LandingPage />} />
<Route path="/share/:shareCode" element={<PublicSharePage />} />
<Route path="/public/leaderboard" element={<PublicLeaderboardPage />} />
@@ -151,11 +195,15 @@ export function App() {
}
/>
<Route path="/embed/roundtable" element={<EmbedRoundtablePage />} />
<Route
path="/embed/knowledge/:noteId"
element={<WeKnoraWikiPageView publicEmbed />}
/>
<Route
path="/roundtable-dashboard"
element={<DashboardStandalonePage />}
/>
<Route path="/page/*" element={<PageRoutes />} />
<Route path="/page/*" element={pageElement} />
<Route path="*" element={<NotFoundPage />} />
</Routes>
</AppProviders>
@@ -0,0 +1,3 @@
<svg xmlns="http://www.w3.org/2000/svg" width="14" height="12" viewBox="0 0 14 12" fill="none" aria-hidden="true">
<path d="M13 6H1.5M1.5 6L6.2 1.4M1.5 6L6.2 10.6" stroke="#A2E1F9" stroke-width="1.6" stroke-linecap="round" stroke-linejoin="round"/>
</svg>

After

Width:  |  Height:  |  Size: 258 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 39 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 53 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 27 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 27 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 27 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 33 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 33 KiB

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 16 16"><defs><style>.a{fill:#fff;opacity:0;}.b{fill:none;stroke:#fff;stroke-linecap:round;stroke-linejoin:round;}</style></defs><rect class="a" width="16" height="16"/><path class="b" d="M24.036,10l-.012,9.333" transform="translate(-16.016 -6.667)"/><path class="b" d="M10,24h9.333" transform="translate(-6.667 -16)"/></svg>

After

Width:  |  Height:  |  Size: 401 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="36" height="36" viewBox="0 0 36 36"><defs><style>.a,.d{fill:#fff;}.a{opacity:0;}.b{fill:#da2331;}.c{fill:#0a54cf;}.e{fill:#1677ff;}.f{fill:#1e2433;}.g{fill:#10d6ff;}.h{fill:#ff8181;}.i{fill:none;stroke:#10d6ff;stroke-linecap:round;stroke-linejoin:round;}.j{filter:url(#d);}.k{filter:url(#a);}</style><filter id="a"><feOffset dx="4" input="SourceAlpha"/><feGaussianBlur stdDeviation="1" result="b"/><feFlood flood-opacity="0.161" result="c"/><feComposite operator="out" in="SourceGraphic" in2="b"/><feComposite operator="in" in="c"/><feComposite operator="in" in2="SourceGraphic"/></filter><filter id="d"><feOffset dx="-4" input="SourceAlpha"/><feGaussianBlur stdDeviation="1" result="e"/><feFlood flood-opacity="0.161" result="f"/><feComposite operator="out" in="SourceGraphic" in2="e"/><feComposite operator="in" in="f"/><feComposite operator="in" in2="SourceGraphic"/></filter></defs><g transform="translate(0 -1)"><rect class="a" width="36" height="36" transform="translate(0 1)"/><path class="b" d="M23.5,14.75a1.5,1.5,0,0,1-1.5-1.5V9.5a1.5,1.5,0,1,1,3,0v3.75A1.5,1.5,0,0,1,23.5,14.75Z" transform="translate(-5.5 -1)"/><g data-type="innerShadowGroup"><path class="c" d="M-2-2H1C3.206-2,5-.532,5,1.273V3.727C5,5.532,3.206,7,1,7H-2Z" transform="translate(28.66 19.541)"/><g class="k" transform="matrix(1, 0, 0, 1, 0, 1)"><path class="d" d="M-2-2H1C3.206-2,5-.532,5,1.273V3.727C5,5.532,3.206,7,1,7H-2Z" transform="translate(28.66 18.54)"/></g></g><g data-type="innerShadowGroup"><path class="c" d="M5-2H2C-.206-2-2-.532-2,1.273V3.727C-2,5.532-.206,7,2,7H5Z" transform="translate(4.34 19.541)"/><g class="j" transform="matrix(1, 0, 0, 1, 0, 1)"><path class="d" d="M5-2H2C-.206-2-2-.532-2,1.273V3.727C-2,5.532-.206,7,2,7H5Z" transform="translate(4.34 18.54)"/></g></g><path class="e" d="M5.5-2H16a7.508,7.508,0,0,1,7.5,7.5V13A7.508,7.508,0,0,1,16,20.5H5.5A7.508,7.508,0,0,1-2,13V5.5A7.508,7.508,0,0,1,5.5-2Z" transform="translate(7.25 13.5)"/><path class="f" d="M5.25,0h9A5.25,5.25,0,0,1,19.5,5.25V7.5a5.25,5.25,0,0,1-5.25,5.25h-9A5.25,5.25,0,0,1,0,7.5V5.25A5.25,5.25,0,0,1,5.25,0Z" transform="translate(8.25 15.25)"/><circle class="g" cx="1.5" cy="1.5" r="1.5" transform="translate(21 19)"/><circle class="g" cx="1.5" cy="1.5" r="1.5" transform="translate(12 19)"/><path class="d" d="M24,10v3.75" transform="translate(-6 -1.5)"/><circle class="h" cx="3" cy="3" r="3" transform="translate(15 4)"/><path class="i" d="M44,28.667a3.367,3.367,0,0,0,1.922.412,2.841,2.841,0,0,0,1.828-.412" transform="translate(-27.875 -5.017)"/></g></svg>

After

Width:  |  Height:  |  Size: 2.6 KiB

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="96" height="96" viewBox="0 0 96 96"><defs><style>.a{fill:#fff;opacity:0;}.b,.c{fill:none;stroke:#006efe;stroke-width:6px;}.b{stroke-linecap:round;stroke-linejoin:round;}</style></defs><g transform="translate(0 1)"><rect class="a" width="96" height="96" transform="translate(0 -1)"/><path class="b" d="M47,67H38L18,77V67H4V7H84V29" transform="translate(4 8)"/><circle class="c" cx="12" cy="12" r="12" transform="translate(56 45)"/><path class="b" d="M39,32l10,8" transform="translate(39 33)"/><path class="b" d="M12,15H24" transform="translate(12 16)"/><path class="b" d="M12,21H36" transform="translate(12 22)"/></g></svg>

After

Width:  |  Height:  |  Size: 670 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="13" height="11" viewBox="0 0 13 11"><defs><style>.a{stroke:rgba(0,0,0,0);stroke-miterlimit:10;fill:url(#a);}</style><linearGradient id="a" x1="0.277" y1="0.03" x2="0.725" y2="1.083" gradientUnits="objectBoundingBox"><stop offset="0" stop-color="#92eeff"/><stop offset="1" stop-color="#00c7ff"/></linearGradient></defs><path class="a" d="M1,10A1,1,0,1,1,1,8H6a1,1,0,0,1,0,2Zm9.8-.482L7.848,7.361A.445.445,0,0,1,7.661,7a.46.46,0,0,1,.187-.366L10.8,4.481a.45.45,0,0,1,.716.365V9.152a.44.44,0,0,1-.131.317.445.445,0,0,1-.322.136A.454.454,0,0,1,10.8,9.518ZM1,6A1,1,0,1,1,1,4H6A1,1,0,0,1,6,6ZM1,2A1,1,0,1,1,1,0H11a1,1,0,1,1,0,2Z" transform="translate(0.5 0.5)"/></svg>

After

Width:  |  Height:  |  Size: 753 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="13" height="11" viewBox="0 0 13 11"><defs><style>.a{fill:url(#a);}.b{fill:url(#b);}</style><linearGradient id="a" x1="0.023" x2="1" y2="1" gradientUnits="objectBoundingBox"><stop offset="0" stop-color="#92eeff" stop-opacity="0.302"/><stop offset="1" stop-color="#00c7ff" stop-opacity="0.302"/></linearGradient><linearGradient id="b" x1="0.023" x2="1" y2="1" gradientUnits="objectBoundingBox"><stop offset="0" stop-color="#92eeff"/><stop offset="1" stop-color="#00c7ff"/></linearGradient></defs><path class="a" d="M5.5,0,11,8H0Z" transform="translate(13) rotate(90)"/><path class="b" d="M5.5,0,11,8H0Z" transform="translate(8) rotate(90)"/></svg>

After

Width:  |  Height:  |  Size: 735 B

@@ -0,0 +1,12 @@
<svg xmlns="http://www.w3.org/2000/svg" width="12" height="12" viewBox="0 0 12 12">
<defs>
<style>
.hit { fill: rgba(255, 255, 255, 0.8); opacity: 0; }
.mark { fill: #fff; }
</style>
</defs>
<g transform="translate(-2434.135 -67.941)">
<rect class="hit" width="12" height="12" transform="translate(2434.135 67.941)"/>
<path class="mark" d="M.885,0,0,.885,3.692,4.577,4.135,5l.442-.423L8.269.885,7.385,0,4.135,3.25Z" transform="translate(2436 71.942)"/>
</g>
</svg>

After

Width:  |  Height:  |  Size: 501 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 16 16"><defs><style>.a{fill:#fff;opacity:0;}.b,.c{fill:none;stroke:#fff;stroke-linejoin:round;}.b{stroke-linecap:round;}</style></defs><g transform="translate(-1)"><rect class="a" width="16" height="16" transform="translate(1)"/><path class="b" d="M7,42H19" transform="translate(-4 -28)"/><path class="b" d="M0,0H3" transform="translate(9.848 3.848) rotate(45)"/><path class="c" d="M11,12.907v2.427h2.439l6.894-6.9L17.9,6Z" transform="translate(-6.667 -4)"/></g></svg>

After

Width:  |  Height:  |  Size: 545 B

@@ -0,0 +1,14 @@
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 16 16">
<defs>
<style>
.background { fill: none; }
.mark { stroke: rgba(0, 0, 0, 0); stroke-miterlimit: 10; fill: url(#gradient); }
</style>
<linearGradient id="gradient" x1="0.277" y1="0.03" x2="0.725" y2="1.083" gradientUnits="objectBoundingBox">
<stop offset="0" stop-color="#a2e1f9"/>
<stop offset="1" stop-color="#45c3f3"/>
</linearGradient>
</defs>
<rect class="background" width="16" height="16"/>
<path class="mark" d="M14554.5,10202.5a1,1,0,1,1,0-2h5a1,1,0,0,1,0,2Zm9.8-.482-2.95-2.157a.445.445,0,0,1-.187-.361.46.46,0,0,1,.187-.366l2.95-2.152a.45.45,0,0,1,.716.365v4.307a.44.44,0,0,1-.131.317.445.445,0,0,1-.322.136A.454.454,0,0,1,14564.3,10202.019Zm-9.8-3.521a1,1,0,1,1,0-2h5a1,1,0,1,1,0,2Zm0-4a1,1,0,1,1,0-2h10a1,1,0,1,1,0,2Z" transform="translate(-14551.5 -10189.5)"/>
</svg>

After

Width:  |  Height:  |  Size: 913 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 16 16"><defs><style>.a{fill:#fff;opacity:0;}.b{fill:rgba(255,255,255,0.8);}</style></defs><rect class="a" width="16" height="16"/><path class="b" d="M10,1.5A1.5,1.5,0,1,1,11.5,3,1.5,1.5,0,0,1,10,1.5Zm-5,0A1.5,1.5,0,1,1,6.5,3,1.5,1.5,0,0,1,5,1.5Zm-5,0A1.5,1.5,0,1,1,1.5,3,1.5,1.5,0,0,1,0,1.5Z" transform="translate(1.498 6.5)"/></svg>

After

Width:  |  Height:  |  Size: 410 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 16 16"><defs><style>.a{fill:#fff;opacity:0;}.b{fill:rgba(85,166,254,0.6);}</style></defs><rect class="a" width="16" height="16"/><path class="b" d="M12.715,13.421,9.588,10.294a5.841,5.841,0,1,1,.707-.707l3.128,3.128a.5.5,0,0,1-.708.706ZM1,5.833A4.833,4.833,0,1,0,5.834,1,4.838,4.838,0,0,0,1,5.833Z" transform="translate(1.334 1.216)"/></svg>

After

Width:  |  Height:  |  Size: 418 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 16 16"><defs><style>.a{fill:#fff;}</style></defs><path class="a" d="M14.488.053.824,4.256a1.167,1.167,0,0,0-.285,2.1L4.576,8.936a1.167,1.167,0,0,0,1.382-.092L11,4.593A.292.292,0,0,1,11.408,5L7.156,10.043a1.167,1.167,0,0,0-.091,1.382l2.58,4.036a1.168,1.168,0,0,0,2.1-.286l4.2-13.663A1.167,1.167,0,0,0,14.488.053Z" transform="translate(0)"/></svg>

After

Width:  |  Height:  |  Size: 422 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="16.131" height="16" viewBox="0 0 16.131 16"><defs><style>.a{fill:#fff;opacity:0;}.b{fill:none;stroke:#97edff;stroke-linecap:round;stroke-linejoin:round;}</style></defs><rect class="a" width="16" height="16"/><path class="b" d="M6,30V34.12H18.361V30" transform="translate(-2.73 -19.994)"/><path class="b" d="M21.181,9.09,18.09,6,15,9.09" transform="translate(-8.64 -4.235)"/><path class="b" d="M23.992,14.241V6" transform="translate(-14.544 -4.235)"/></svg>

After

Width:  |  Height:  |  Size: 504 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 16 16"><defs><style>.a{fill:#fff;opacity:0;}.b,.c{fill:none;stroke:#346fb1;stroke-linejoin:round;}.c{stroke-linecap:round;}</style></defs><rect class="a" width="16" height="16"/><path class="b" d="M10.667,17.333A6.667,6.667,0,1,0,4,10.667,6.667,6.667,0,0,0,10.667,17.333Z" transform="translate(-2.667 -2.667)"/><path class="c" d="M24.008,12v4l2.826,2.826" transform="translate(-16.005 -8)"/></svg>

After

Width:  |  Height:  |  Size: 473 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="95.001" height="26" viewBox="0 0 95.001 26"><defs><style>.a{fill:rgba(212,120,0,0.5);}</style></defs><path class="a" d="M250.146,407.92h91l-11.4,18.235c-2.679,4.26-5.243,7.5-11.211,7.765H246.146v-22A4,4,0,0,1,250.146,407.92Z" transform="translate(-246.146 -407.92)"/></svg>

After

Width:  |  Height:  |  Size: 320 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="95.001" height="26" viewBox="0 0 95.001 26"><defs><style>.a{fill:rgba(207,19,34,0.5);}</style></defs><path class="a" d="M250.146,407.92h91l-11.4,18.235c-2.679,4.26-5.243,7.5-11.211,7.765H246.146v-22A4,4,0,0,1,250.146,407.92Z" transform="translate(-246.146 -407.92)"/></svg>

After

Width:  |  Height:  |  Size: 320 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="95.001" height="26" viewBox="0 0 95.001 26"><defs><style>.a{fill:rgba(29,171,123,0.5);}</style></defs><path class="a" d="M250.146,407.92h91l-11.4,18.235c-2.679,4.26-5.243,7.5-11.211,7.765H246.146v-22A4,4,0,0,1,250.146,407.92Z" transform="translate(-246.146 -407.92)"/></svg>

After

Width:  |  Height:  |  Size: 321 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="95.001" height="26" viewBox="0 0 95.001 26"><defs><style>.a{fill:rgba(132,85,230,0.5);}</style></defs><path class="a" d="M250.146,407.92h91l-11.4,18.235c-2.679,4.26-5.243,7.5-11.211,7.765H246.146v-22A4,4,0,0,1,250.146,407.92Z" transform="translate(-246.146 -407.92)"/></svg>

After

Width:  |  Height:  |  Size: 321 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="95.001" height="26" viewBox="0 0 95.001 26"><defs><style>.a{fill:rgba(201,181,0,0.5);}</style></defs><path class="a" d="M250.146,407.92h91l-11.4,18.235c-2.679,4.26-5.243,7.5-11.211,7.765H246.146v-22A4,4,0,0,1,250.146,407.92Z" transform="translate(-246.146 -407.92)"/></svg>

After

Width:  |  Height:  |  Size: 320 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="95.001" height="26" viewBox="0 0 95.001 26"><defs><style>.a{fill:rgba(69,195,243,0.5);}</style></defs><path class="a" d="M250.146,407.92h91l-11.4,18.235c-2.679,4.26-5.243,7.5-11.211,7.765H246.146v-22A4,4,0,0,1,250.146,407.92Z" transform="translate(-246.146 -407.92)"/></svg>

After

Width:  |  Height:  |  Size: 321 B

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 16 16"><defs><style>.a{fill:#fff;opacity:0;}.b{fill:none;stroke:#346fb1;stroke-linecap:round;stroke-linejoin:round;}</style></defs><g transform="translate(0 -2)"><rect class="a" width="16" height="16" transform="translate(0 2)"/><path class="b" d="M17.333,8H4V18H9l1.667,1.667L12.333,18h5Z" transform="translate(-2.667 -3.667)"/><circle class="b" cx="1.667" cy="1.667" r="1.667" transform="translate(6.333 6.333)"/><path class="b" d="M21,26.667A2.848,2.848,0,0,0,18,24a2.848,2.848,0,0,0-3,2.667" transform="translate(-10 -14.333)"/></g></svg>

After

Width:  |  Height:  |  Size: 618 B

@@ -1,7 +1,8 @@
"use client";
import { Button } from "@/components/ui/button";
import { cn } from "@/lib/utils";
import { Button } from "@/components/ui/button";
import { copyTextToClipboard } from "@/core/clipboard";
import { cn } from "@/lib/utils";
import { CheckIcon, CopyIcon } from "lucide-react";
import {
type ComponentProps,
@@ -144,18 +145,13 @@ export const CodeBlockCopyButton = ({
...props
}: CodeBlockCopyButtonProps) => {
const [isCopied, setIsCopied] = useState(false);
const { code } = useContext(CodeBlockContext);
const copyToClipboard = async () => {
if (typeof window === "undefined" || !navigator?.clipboard?.writeText) {
onError?.(new Error("Clipboard API not available"));
return;
}
try {
await navigator.clipboard.writeText(code);
setIsCopied(true);
onCopy?.();
const { code } = useContext(CodeBlockContext);
const copyToClipboard = async () => {
try {
await copyTextToClipboard(code);
setIsCopied(true);
onCopy?.();
setTimeout(() => setIsCopied(false), timeout);
} catch (error) {
onError?.(error as Error);
@@ -846,7 +846,10 @@ export const PromptInput = ({
ref={formRef}
{...props}
>
<InputGroup>{children}</InputGroup>
{/* Do not rely on InputGroup's :has(textarea) selector here: Chrome
versions before 105 ignore :has(), retain h-9, and clip the whole
multi-line composer to a single row. */}
<InputGroup className="h-auto min-h-16">{children}</InputGroup>
</form>
</PromptInputValidationContext.Provider>
);
@@ -873,16 +876,48 @@ export type PromptInputTextareaProps = ComponentProps<
typeof InputGroupTextarea
>;
export const PromptInputTextarea = ({
onChange,
className,
placeholder = "What would you like to know?",
...props
}: PromptInputTextareaProps) => {
const controller = useOptionalPromptInputController();
const attachments = usePromptInputAttachments();
const sanitizeIncomingFiles = usePromptInputValidation();
const [isComposing, setIsComposing] = useState(false);
export const PromptInputTextarea = ({
onChange,
onInput,
className,
placeholder = "What would you like to know?",
...props
}: PromptInputTextareaProps) => {
const controller = useOptionalPromptInputController();
const attachments = usePromptInputAttachments();
const sanitizeIncomingFiles = usePromptInputValidation();
const [isComposing, setIsComposing] = useState(false);
const textareaRef = useRef<HTMLTextAreaElement | null>(null);
const resizeForLegacyChrome = useCallback((textarea: HTMLTextAreaElement) => {
if (
typeof CSS !== "undefined" &&
typeof CSS.supports === "function" &&
CSS.supports("field-sizing", "content")
) {
return;
}
// Chrome 109 ignores field-sizing: content. Preserve the same 4rem–12rem
// autosize range used by min-h-16/max-h-48 instead of leaving the prompt
// stuck at its minimum height.
textarea.style.height = "auto";
const height = Math.max(64, Math.min(textarea.scrollHeight, 192));
textarea.style.height = `${height}px`;
textarea.style.overflowY = textarea.scrollHeight > 192 ? "auto" : "hidden";
}, []);
// onInput does not run for a controlled value filled by a suggested question
// or restored draft. Resize once after every render in legacy Chrome too.
useEffect(() => {
const textarea = textareaRef.current;
if (!textarea) return;
const frame = window.requestAnimationFrame(() => {
resizeForLegacyChrome(textarea);
});
return () => window.cancelAnimationFrame(frame);
}, [controller?.textInput.value, resizeForLegacyChrome]);
const handleKeyDown: KeyboardEventHandler<HTMLTextAreaElement> = (e) => {
if (e.key === "Enter") {
@@ -962,12 +997,18 @@ export const PromptInputTextarea = ({
};
return (
<InputGroupTextarea
className={cn("field-sizing-content max-h-48 min-h-16", className)}
name="message"
<InputGroupTextarea
className={cn("field-sizing-content max-h-48 min-h-16", className)}
name="message"
ref={textareaRef}
rows={3}
onCompositionEnd={() => setIsComposing(false)}
onCompositionStart={() => setIsComposing(true)}
onKeyDown={handleKeyDown}
onKeyDown={handleKeyDown}
onInput={(event) => {
resizeForLegacyChrome(event.currentTarget);
onInput?.(event);
}}
onPaste={handlePaste}
placeholder={placeholder}
{...props}
@@ -165,7 +165,7 @@ export const ReasoningTrigger = memo(
export type ReasoningContentProps = ComponentProps<
typeof CollapsibleContent
> & {
children: string;
children: ReactNode;
};
export const ReasoningContent = memo(
@@ -178,7 +178,11 @@ export const ReasoningContent = memo(
)}
{...props}
>
<Streamdown {...reasoningPlugins}>{children}</Streamdown>
{typeof children === "string" ? (
<Streamdown {...reasoningPlugins}>{children}</Streamdown>
) : (
children
)}
</CollapsibleContent>
),
);
@@ -0,0 +1,104 @@
import { FileOutput } from "lucide-react";
import { toast } from "sonner";
import responsibilityIcon from "@/assets/position-roundtable/责任岗位.svg";
import resultTimeIcon from "@/assets/position-roundtable/时间.svg";
import { desensitize } from "@/lib/desensitize";
import { cn } from "@/lib/utils";
import "./analysis-results.css";
import type { AnalysisResultCardItem } from "./types";
function formatResultTime(value: string | undefined, fallback: string): string {
if (!value) return fallback;
const date = new Date(value);
if (Number.isNaN(date.getTime())) return value;
return new Intl.DateTimeFormat("zh-CN", {
month: "2-digit",
day: "2-digit",
hour: "2-digit",
minute: "2-digit",
hour12: false,
}).format(date);
}
export function AnalysisResultCardList({
items,
emptyTitle = "暂无交付产物",
emptyDescription = "第二步研讨与第三步总结生成 Markdown 后,产物会显示在这里。",
padded = true,
onOpen,
}: {
items: AnalysisResultCardItem[];
emptyTitle?: string;
emptyDescription?: string;
padded?: boolean;
onOpen: (item: AnalysisResultCardItem) => void;
}) {
if (items.length === 0) {
return (
<div className="position-roundtable-analysis-results-empty flex h-full min-h-[260px] flex-col items-center justify-center p-6 text-center">
<FileOutput className="mb-3 size-8 text-muted-foreground/50" />
<p className="text-sm font-semibold">{emptyTitle}</p>
<p className="mt-1 max-w-[240px] text-xs leading-5 text-muted-foreground">
{emptyDescription}
</p>
</div>
);
}
return (
<div className={cn("analysis-result-card-list", padded && "p-[15px]")}>
{items.map((item, index) => {
const displayedTime = formatResultTime(
item.updatedAt,
item.fallbackTime || "刚刚",
);
const displayedProductName = item.delivered ? item.productName : "未交付";
return (
<button
key={item.id}
type="button"
className="position-roundtable-analysis-result-card"
onClick={() => {
if (!item.delivered) {
toast.info(
item.unavailableMessage ||
`「${desensitize(item.agentName)}」尚未交付可预览的 Markdown 文件。`,
);
return;
}
onOpen(item);
}}
>
<div className="position-roundtable-analysis-result-card-body">
<div
className={cn(
"position-roundtable-analysis-result-tag",
`position-roundtable-analysis-result-tag--${(index % 6) + 1}`,
)}
aria-label={desensitize(item.agentName)}
>
<span>{desensitize(item.agentName)}</span>
</div>
<p className="position-roundtable-analysis-result-product">
{desensitize(displayedProductName)}
</p>
<footer className="position-roundtable-analysis-result-meta">
<span>
<img src={responsibilityIcon} alt="" aria-hidden="true" />
{desensitize(item.positionName)}
</span>
<i aria-hidden="true" />
<span>
<img src={resultTimeIcon} alt="" aria-hidden="true" />
{displayedTime}
</span>
</footer>
</div>
</button>
);
})}
</div>
);
}
@@ -0,0 +1,141 @@
import { useQuery } from "@tanstack/react-query";
import { FileOutput, Loader2 } from "lucide-react";
import type { ReactNode } from "react";
import { ArtifactFilePreview } from "@/components/workspace/artifacts";
import {
Dialog,
DialogContent,
DialogFooter,
DialogHeader,
DialogTitle,
} from "@/components/ui/dialog";
import { loadArtifactContent } from "@/core/artifacts/loader";
import { desensitize } from "@/lib/desensitize";
import { Button as TButton } from "tdesign-react";
import type { AnalysisResultCardItem } from "./types";
function isArtifactErrorContent(content: string | null | undefined): boolean {
const trimmed = content?.trim();
if (!trimmed || !trimmed.startsWith("{") || !trimmed.endsWith("}")) {
return false;
}
try {
const parsed = JSON.parse(trimmed) as Record<string, unknown>;
const detail = parsed.detail ?? parsed.message ?? parsed.error;
return typeof detail === "string" && detail.trim().length > 0;
} catch {
return false;
}
}
function fallbackContent(item: AnalysisResultCardItem | null): string {
return (
item?.artifactContent?.trim() ||
item?.summary?.trim() ||
"暂无产物正文"
);
}
export function AnalysisResultDetailDialog({
item,
onOpenChange,
extraBody,
footerStart,
}: {
item: AnalysisResultCardItem | null;
onOpenChange: (open: boolean) => void;
extraBody?: ReactNode;
footerStart?: ReactNode;
}) {
const artifactThreadId = item?.artifactThreadId || null;
const artifactPathValue = item?.artifactPath || "";
const artifactContentQuery = useQuery({
queryKey: [
"analysis-results",
"deliverable-artifact-content",
artifactThreadId,
artifactPathValue,
],
queryFn: async () => {
if (!artifactThreadId || !artifactPathValue) return "";
const result = await loadArtifactContent({
filepath: artifactPathValue,
threadId: artifactThreadId,
isMock: false,
});
return result.content;
},
enabled: Boolean(item && artifactThreadId && artifactPathValue),
staleTime: 30_000,
});
const loadedArtifactContent =
typeof artifactContentQuery.data === "string" ? artifactContentQuery.data : "";
const loadedArtifactIsError = isArtifactErrorContent(loadedArtifactContent);
const artifactContent =
loadedArtifactContent.trim() && !loadedArtifactIsError ? loadedArtifactContent : null;
const displayedContent = artifactContent || fallbackContent(item);
const artifactLoadFailed =
(artifactContentQuery.isError || loadedArtifactIsError) &&
!item?.artifactContent?.trim();
return (
<Dialog open={Boolean(item)} onOpenChange={onOpenChange}>
<DialogContent
overlayClassName="!z-[6000]"
className="!z-[6001] flex max-h-[86vh] w-[900px] !max-w-[calc(100vw-2rem)] flex-col gap-0 overflow-hidden p-0"
>
<DialogHeader className="shrink-0 border-b px-5 py-4 dark:border-[#2b8ffe]/25">
<DialogTitle className="flex items-center gap-2 text-base">
<FileOutput className="size-4 text-primary" />
交付产物详情
</DialogTitle>
</DialogHeader>
{!item ? null : (
<div className="custom-scrollbar min-h-0 flex-1 overflow-y-auto px-5 py-4">
<div className="min-w-0">
<p className="text-sm font-extrabold text-slate-900 dark:text-[#e8edf5]">
{desensitize(item.productName)}
</p>
<p className="mt-1 truncate text-xs text-muted-foreground">
{desensitize(item.agentName)} · {desensitize(item.positionName)}
</p>
</div>
{extraBody}
<div className="mt-4 rounded-xl border border-slate-200 bg-white p-3 dark:border-[#2b8ffe]/30 dark:bg-[#042b59]/65">
<div className="mb-2 flex items-center justify-between gap-2">
<p className="text-xs font-bold text-slate-700 dark:text-[#e8edf5]">产物内容</p>
</div>
<div className="h-[52vh] min-h-[320px] overflow-hidden rounded-lg border border-slate-100 bg-slate-50/60 dark:border-[#2b8ffe]/20 dark:bg-[#021d3d]/70">
{artifactContentQuery.isLoading ? (
<div className="flex h-full items-center justify-center gap-2 text-sm text-muted-foreground dark:text-[#8aa0c4]">
<Loader2 className="size-4 animate-spin" />
正在加载 Markdown 文件内容…
</div>
) : (
<ArtifactFilePreview
content={displayedContent}
language="markdown"
threadId={artifactThreadId ?? ""}
/>
)}
</div>
{artifactLoadFailed && (
<p className="mt-2 text-[11px] text-amber-600 dark:text-amber-300">
Markdown 文件内容加载失败,当前展示的是已保存正文。
</p>
)}
</div>
</div>
)}
<DialogFooter className="shrink-0 border-t px-5 py-3 dark:border-[#2b8ffe]/25">
{footerStart}
<TButton variant="outline" onClick={() => onOpenChange(false)}>
关闭
</TButton>
</DialogFooter>
</DialogContent>
</Dialog>
);
}
@@ -0,0 +1,130 @@
.analysis-result-card-list {
display: grid;
gap: 10px;
min-width: 0;
max-width: 100%;
}
.position-roundtable-analysis-result-card {
position: relative;
display: block;
width: 100%;
max-width: 100%;
min-width: 0;
min-height: 102px;
box-sizing: border-box;
padding: 40px 12px 12px;
border: 1px solid rgba(85, 166, 254, 0.1);
border-radius: 4px;
background: rgba(0, 98, 217, 0.1);
color: #ffffff;
text-align: left;
cursor: pointer;
transition: background 160ms ease, border-color 160ms ease, box-shadow 160ms ease;
}
.position-roundtable-analysis-result-card:hover,
.position-roundtable-analysis-result-card:focus-visible {
border-color: #0062d9;
background: rgba(0, 98, 217, 0.3);
box-shadow: 0 4px 14px rgba(0, 44, 110, 0.18);
outline: none;
}
.position-roundtable-analysis-result-card-body {
position: relative;
min-width: 0;
max-width: 100%;
}
.position-roundtable-analysis-result-tag {
position: absolute;
top: -40px;
left: -12px;
display: inline-flex;
width: fit-content;
max-width: calc(100% + 12px);
height: 26px;
align-items: center;
box-sizing: border-box;
padding: 0 22px 0 12px;
overflow: hidden;
border-radius: 4px 0 0 0;
background: rgba(212, 120, 0, 0.5);
color: #ffffff;
font-family: "Noto Sans S Chinese", "Noto Sans SC", sans-serif;
font-size: 16px;
line-height: normal;
white-space: nowrap;
clip-path: polygon(0 0, 100% 0, calc(100% - 14px) 100%, 0 100%);
}
.position-roundtable-analysis-result-tag--1 { background: rgba(212, 120, 0, 0.5); }
.position-roundtable-analysis-result-tag--2 { background: rgba(207, 19, 34, 0.5); }
.position-roundtable-analysis-result-tag--3 { background: rgba(29, 171, 123, 0.5); }
.position-roundtable-analysis-result-tag--4 { background: rgba(132, 85, 230, 0.5); }
.position-roundtable-analysis-result-tag--5 { background: rgba(201, 181, 0, 0.5); }
.position-roundtable-analysis-result-tag--6 { background: rgba(69, 195, 243, 0.5); }
.position-roundtable-analysis-result-tag span {
position: relative;
z-index: 1;
box-sizing: border-box;
min-width: 0;
max-width: 100%;
overflow: hidden;
padding: 0;
text-overflow: ellipsis;
}
.position-roundtable-analysis-result-product {
margin: 0;
overflow: hidden;
color: #ffffff;
font-family: "Noto Sans S Chinese", "Noto Sans SC", sans-serif;
font-size: 18px;
font-weight: 500;
line-height: 24px;
text-overflow: ellipsis;
white-space: nowrap;
}
.position-roundtable-analysis-result-meta {
display: flex;
min-width: 0;
align-items: center;
gap: 10px;
margin-top: 6px;
color: #80b7ff;
font-family: "Noto Sans S Chinese", "Noto Sans SC", sans-serif;
font-size: 16px;
font-weight: 300;
line-height: 24px;
}
.position-roundtable-analysis-result-meta span {
display: inline-flex;
min-width: 0;
align-items: center;
gap: 5px;
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
}
.position-roundtable-analysis-result-meta img {
width: 16px;
height: 16px;
flex: 0 0 auto;
}
.position-roundtable-analysis-result-meta i {
width: 1px;
height: 14px;
flex: 0 0 auto;
background: rgba(128, 183, 255, 0.45);
}
.position-roundtable-analysis-results-empty {
color: #80b7ff;
}
@@ -0,0 +1,3 @@
export { AnalysisResultCardList } from "./AnalysisResultCardList";
export { AnalysisResultDetailDialog } from "./AnalysisResultDetailDialog";
export type { AnalysisResultCardItem } from "./types";
@@ -0,0 +1,17 @@
export interface AnalysisResultCardItem {
id: string;
agentName: string;
productName: string;
positionName: string;
updatedAt?: string;
/** Shown when `updatedAt` is missing. */
fallbackTime?: string;
/** Clickable preview is available. */
delivered: boolean;
artifactPath?: string;
artifactMimeType?: string | null;
artifactThreadId?: string | null;
artifactContent?: string | null;
summary?: string;
unavailableMessage?: string;
}
@@ -26,6 +26,7 @@ import {
import { Button } from "@/components/ui/button";
import { toast } from "sonner";
import { getStoredAuth } from "@/core/auth";
import { readRuntimeEnv } from "@/env";
import { queryClient } from "@/components/query-client-provider";
import { Checkbox } from "@/components/ui/checkbox";
import Empty from "./empty";
@@ -303,11 +304,11 @@ const DocumentUploadPopupContent: FC<{
const searchSpaceId = String(searchSpace?.id);
// 从环境变量获取配置
const backendUrl = import.meta.env.VITE_AIPI_BACKENP_URL || "http://localhost:8001";
const consumerUrl = import.meta.env.VITE_AIPI_CONSUMER_URL || "http://ch1.b.uat.4.cn/consumer";
const presentUrl = import.meta.env.VITE_AIPI_PRESENT_URL || "http://present.a.uat.4.cn/present/domain";
const knowesUrl = import.meta.env.VITE_AIPI_KNOWES_URL || "http://ch1.b.uat.4.cn/knowes";
const knowledgeUrl = import.meta.env.VITE_AIPI_KNOWLEDGE_URL || "http://chlib.b.uat.4.cn/knowlibrary";
const backendUrl = readRuntimeEnv("VITE_AIPI_BACKENP_URL") || "http://localhost:8001";
const consumerUrl = readRuntimeEnv("VITE_AIPI_CONSUMER_URL") || "http://ch1.b.uat.4.cn/consumer";
const presentUrl = readRuntimeEnv("VITE_AIPI_PRESENT_URL") || "http://present.a.uat.4.cn/present/domain";
const knowesUrl = readRuntimeEnv("VITE_AIPI_KNOWES_URL") || "http://ch1.b.uat.4.cn/knowes";
const knowledgeUrl = readRuntimeEnv("VITE_AIPI_KNOWLEDGE_URL") || "http://chlib.b.uat.4.cn/knowlibrary";
const [searchText, setSearchText] = useState("");
const [searchValue, setSearchValue] = useState("");
@@ -405,8 +406,15 @@ const DocumentUploadPopupContent: FC<{
if (response.ok) {
const data = await response.json() as { imported_count?: number };
toast.success(`成功导入 ${data.imported_count || dataList.length} 个来源`);
setListData([]);
handleBatchDelete();
onUploadComplete?.(
selectedSearchSources.map((s) => ({
id: undefined,
title: s.title,
task_id: undefined,
status: "success" as const,
}))
);
onOpenChange(false);
} else {
const errorData = await response.json() as { detail?: string };
toast.error(errorData.detail || "导入失败,请重试");
@@ -826,7 +834,13 @@ const DocumentUploadPopupContent: FC<{
</Button>
</div>
)}
{listData.length === 0 && <Empty />}
{isSearching ? (
<div className="flex items-center justify-center py-16">
<Loader2 className="h-8 w-8 animate-spin text-muted-foreground" />
</div>
) : (
listData.length === 0 && <Empty />
)}
{searchType === "human" && (
<div className="bg-white p-[10px] grid grid-cols-5 gap-[10px]">
{listData.map((item: listDataItem, index: number) => {
@@ -11,6 +11,7 @@ import { Button } from "@/components/ui/button";
import { toast } from "sonner";
import { getStoredAuth } from "@/core/auth";
import { authenticatedFetch } from "@/components/assistant-ui/document-upload-popup";
import { readRuntimeEnv } from "@/env";
interface NetworkActorProps {
@@ -186,9 +187,9 @@ export function NetworkActor({ inputValue, searchSpaceId, onSuccess }: NetworkAc
const [actorCount, setActorCount] = useState<number>(0);
const [directionType, setDirectionType] = useState<string>('TW');
const directionValue = useRef<string>('TW');
const consumerUrl = import.meta.env.VITE_AIPI_CONSUMER_URL || 'https://ch1.b.uat.4.cn/consumer';
const consumerUrl = readRuntimeEnv("VITE_AIPI_CONSUMER_URL") || 'https://ch1.b.uat.4.cn/consumer';
const backendUrl = typeof window !== 'undefined'
? (import.meta.env.VITE_BACKEND_BASE_URL || 'http://localhost:8001')
? (readRuntimeEnv("VITE_BACKEND_BASE_URL") || 'http://localhost:8001')
: 'http://localhost:8001';
const [selectedSearchSources, setSelectedSearchSources] = useState<UserDataItem[]>([]);
const [isImporting, setIsImporting] = useState(false);
@@ -545,7 +546,12 @@ export function NetworkActor({ inputValue, searchSpaceId, onSuccess }: NetworkAc
</div>
)}
<div className="p-[10px]">
<div className="grid grid-cols-4 gap-[10px] user-list">
{isSearching ? (
<div className="flex items-center justify-center py-16">
<Loader2 className="h-8 w-8 animate-spin text-muted-foreground" />
</div>
) : null}
<div className={`grid grid-cols-4 gap-[10px] user-list${isSearching ? ' hidden' : ''}`}>
{userList.map((item, index) => (
<div key={index} className="user-item p-[10px] relative">
<div className="absolute top-[5px] right-[10px]">
@@ -1,6 +1,6 @@
import { useEffect, useState } from "react";
import { injectInPageAnchorHandler } from "@/core/utils/markdown";
import { prepareGeneratedHtml } from "@/core/utils/legacy-html-preview";
/**
* Sandboxed preview of a generated HTML document.
@@ -26,7 +26,7 @@ export function HtmlPreviewFrame({
const [url, setUrl] = useState<string>();
useEffect(() => {
const blob = new Blob([injectInPageAnchorHandler(html ?? "")], {
const blob = new Blob([prepareGeneratedHtml(html ?? "")], {
type: "text/html;charset=utf-8",
});
const objectUrl = URL.createObjectURL(blob);
@@ -508,8 +508,9 @@ export default function ProgressiveSkillsAnimation() {
"deploying",
"done",
].includes(phase) && (
<div className="text-base text-zinc-300">
<span className="text-purple-400">✨</span> Found 3 skills
<div className="flex items-center gap-2 text-base text-zinc-300">
<Sparkles size={16} className="text-purple-400" />
<span>Found 3 skills</span>
</div>
)}
@@ -526,8 +527,9 @@ export default function ProgressiveSkillsAnimation() {
].includes(phase) && (
<div className="mt-4">
<hr className="mb-3 border-zinc-700" />
<div className="mb-3 text-zinc-300">
🔬 Researching...
<div className="mb-3 inline-flex items-center gap-2 text-zinc-300">
<Search size={16} className="text-blue-400" />
<span>Researching...</span>
</div>
<div className="mb-3 space-y-2">
{/* Loading SKILL.md */}
@@ -623,7 +625,10 @@ export default function ProgressiveSkillsAnimation() {
className="mt-4"
>
<hr className="mb-3 border-zinc-700" />
<div className="mb-3 text-zinc-300">🔨 Building...</div>
<div className="mb-3 inline-flex items-center gap-2 text-zinc-300">
<FileText size={16} className="text-zinc-400" />
<span>Building...</span>
</div>
<div className="mb-3 flex items-center gap-2 pl-4 text-zinc-400">
<FileText size={16} />
<span>Loading frontend-design/SKILL.md...</span>
@@ -653,7 +658,10 @@ export default function ProgressiveSkillsAnimation() {
className="mt-4"
>
<hr className="mb-3 border-zinc-700" />
<div className="mb-3 text-zinc-300">🚀 Deploying...</div>
<div className="mb-3 inline-flex items-center gap-2 text-zinc-300">
<Terminal size={16} className="text-zinc-400" />
<span>Deploying...</span>
</div>
<div className="mb-3 space-y-2">
<div className="flex items-center gap-2 pl-4 text-zinc-400">
<FileText size={16} />
@@ -676,8 +684,9 @@ export default function ProgressiveSkillsAnimation() {
animate={{ opacity: 1, scale: 1 }}
className="mt-4 rounded-xl border border-green-500/30 bg-green-500/10 p-4"
>
<div className="text-lg font-medium text-green-500">
✅ Live at biotech-startup.vercel.app
<div className="inline-flex items-center gap-2 text-lg font-medium text-green-500">
<Check size={18} />
<span>Live at biotech-startup.vercel.app</span>
</div>
</motion.div>
)}
@@ -35,27 +35,27 @@ export function SandboxSection({ className }: { className?: string }) {
$ pip install -r requirements.txt
</TypingAnimation>
<AnimatedSpan delay={2000} className="text-green-500">
✔ Installed pygame
[ok] Installed pygame
</AnimatedSpan>
<TypingAnimation delay={2400}>
$ write game.py --lines 156
</TypingAnimation>
<AnimatedSpan delay={3200} className="text-blue-500">
✔ Written 156 lines
[ok] Written 156 lines
</AnimatedSpan>
<TypingAnimation delay={3600}>
$ python game.py --test
</TypingAnimation>
<AnimatedSpan delay={4200} className="text-green-500">
✔ All sprites loaded
[ok] All sprites loaded
</AnimatedSpan>
<AnimatedSpan delay={4500} className="text-green-500">
✔ Physics engine OK
[ok] Physics engine OK
</AnimatedSpan>
<AnimatedSpan delay={4800} className="text-green-500">
✔ 60 FPS stable
[ok] 60 FPS stable
</AnimatedSpan>
{/* Scene 2: Data Analysis */}
@@ -8,6 +8,17 @@
flex-shrink: 0;
}
/* `?hideHeader=1`: keep the menu rail, but let it occupy the Header's space. */
.sidebar-contnet--header-hidden {
top: 0;
height: 100vh;
}
.sidebar-contnet--header-hidden .item-nav-content {
height: calc(100vh - 20px);
min-height: calc(100vh - 20px);
}
.sidebar-contents {
width: 98px;
min-height: calc(100% - 20px);
@@ -564,7 +575,59 @@
background: #ffffff;
}
/* Ice blue has a deliberately light banner. Keep top-level navigation and
its active marker dark enough to remain readable against #9BCEF1. */
html.iceblue .light-topnav-item {
color: rgba(24, 50, 74, 0.78);
}
html.iceblue .light-topnav-item:hover,
html.iceblue .light-topnav-item--active,
html.iceblue .light-topnav-item--active:hover {
color: #18324a;
}
html.iceblue .light-topnav-item--active::after {
background: #3d6e96;
}
/* Pale yellow has the same light-banner contrast requirement as ice blue. */
html.lightyellow .light-topnav-item {
color: rgba(48, 61, 35, 0.78);
}
html.lightyellow .light-topnav-item:hover,
html.lightyellow .light-topnav-item--active,
html.lightyellow .light-topnav-item--active:hover {
color: #303d23;
}
html.lightyellow .light-topnav-item--active::after {
background: #4c6330;
}
/* ── 侧边栏:二级图标卡片列(96px)+ 右侧三级列(展开时整体变宽,带过渡)──────── */
/* Runtime themes use their configurable header gradient rather than the
red/blue banner artwork. Navigation copy follows an automatically chosen
contrasting foreground so both pale and deep brand colours remain legible. */
html[data-custom-theme="true"] .light-topnav-item,
html[data-custom-theme="true"] .top-submenu-item {
color: var(--navigation-foreground);
}
html[data-custom-theme="true"] .light-topnav-item:hover,
html[data-custom-theme="true"] .light-topnav-item--active,
html[data-custom-theme="true"] .light-topnav-item--active:hover,
html[data-custom-theme="true"] .top-submenu-item:hover,
html[data-custom-theme="true"] .top-submenu-item--active {
color: var(--navigation-foreground);
text-shadow: none;
}
html[data-custom-theme="true"] .light-topnav-item--active::after {
background: var(--navigation-foreground);
}
.light-sidebar {
position: fixed;
left: 0;
@@ -587,6 +650,12 @@
width: 236px;
}
/* `?hideHeader=1`: preserve the light sidebar while removing only Header. */
.light-sidebar--header-hidden {
top: 0;
height: 100vh;
}
/* 二级列:固定 96px,竖排图标卡片 + 底部设置 */
.light-sidebar__primary {
flex: 0 0 96px;
@@ -17,9 +17,15 @@ type PageSidebarDarkProps = {
/** 是否收起(true 时只渲染左下角浮动入口,sidebar 主体隐藏) */
collapsed: boolean;
onToggleCollapsed: () => void;
/** 全局 Header 隐藏时,侧边栏从视口顶部开始占满高度。 */
headerHidden?: boolean;
};
export function PageSidebarDark({ collapsed, onToggleCollapsed }: PageSidebarDarkProps) {
export function PageSidebarDark({
collapsed,
onToggleCollapsed,
headerHidden = false,
}: PageSidebarDarkProps) {
const isAdmin = getStoredAuth()?.system_role === "admin";
const visibleMenuItems = useSidebarMenuItems(!!isAdmin);
const inWujieEnv = isWujieEnv();
@@ -196,7 +202,7 @@ export function PageSidebarDark({ collapsed, onToggleCollapsed }: PageSidebarDar
</div>
);
// collapsed 状态:sidebar 主体完全消失(包括占据的宽度),只渲染左下角浮动入口
// 收起时主侧栏不占宽度,保留左下角入口以便随时恢复。
if (collapsed) {
return (
<button
@@ -207,13 +213,17 @@ export function PageSidebarDark({ collapsed, onToggleCollapsed }: PageSidebarDar
onClick={onToggleCollapsed}
>
<PanelLeftOpen className="sidebar-collapse-btn__icon" aria-hidden="true" />
<span className="sidebar-collapse-btn__label">收起面板</span>
<span className="sidebar-collapse-btn__label">展开面板</span>
</button>
);
}
return (
<aside className={`sidebar-contnet ${inWujieEnv ? "" : "sidebar-contnet--top-submenu"}`}>
<aside
className={`sidebar-contnet ${inWujieEnv ? "" : "sidebar-contnet--top-submenu"} ${
headerHidden ? "sidebar-contnet--header-hidden" : ""
}`}
>
<div className="sidebar-contents">
{sidebarMenuItemsToRender.map((item) => (
<div
@@ -244,7 +254,6 @@ export function PageSidebarDark({ collapsed, onToggleCollapsed }: PageSidebarDar
</div>
))}
{/* 底部"收起面板"按钮:独立样式,mt-auto 推到底 */}
<button
type="button"
title="收起侧边栏"
+88 -5
View File
@@ -2,15 +2,20 @@ import { useEffect, useState } from "react";
import { useNavigate, useLocation } from "react-router-dom";
import {
Bell,
Cpu,
ChevronLeft,
ChevronRight,
ChevronsUpDown,
Folder,
FolderOpen,
Gauge,
ListTree,
MessageSquareText,
MousePointerClick,
BriefcaseBusiness,
Settings,
ShieldAlert,
ShieldCheck,
User,
Wrench,
} from "lucide-react";
@@ -47,6 +52,8 @@ import "@/components/page-sdebar.css";
type PageSidebarProps = {
collapsed: boolean;
onToggleCollapsed: () => void;
/** Global Header is hidden but this sidebar remains available. */
headerHidden?: boolean;
};
type SettingsSection = "account" | "appearance" | "memory" | "tools" | "about";
@@ -77,23 +84,28 @@ const findFirstRoutePath = (items?: MenuItem[]): string | null => {
* - wujie 嵌入环境:顶栏被宿主隐藏,一级导航无处安放,故回落到原手风琴整树菜单
* (保证嵌入模式下所有层级仍可达,零回归)。
*/
export function PageSidebar({ collapsed, onToggleCollapsed }: PageSidebarProps) {
export function PageSidebar({
collapsed,
onToggleCollapsed,
headerHidden = false,
}: PageSidebarProps) {
if (isWujieEnv()) {
return (
<LegacyAccordionSidebar
collapsed={collapsed}
onToggleCollapsed={onToggleCollapsed}
headerHidden={headerHidden}
/>
);
}
return <SecondaryNavSidebar />;
return <SecondaryNavSidebar headerHidden={headerHidden} />;
}
/**
* 浅色二级导航侧边栏(图标卡片,红/蓝主题色经 --brand-* 变量自动切换)。
* 浅色模式不支持侧边栏收起,故无收起按钮、不接收 collapsed 相关 props。
*/
function SecondaryNavSidebar() {
function SecondaryNavSidebar({ headerHidden }: { headerHidden: boolean }) {
const isAdmin = getStoredAuth()?.system_role === "admin";
const visibleMenuItems = useSidebarMenuItems(!!isAdmin);
const { t } = useI18n();
@@ -148,7 +160,11 @@ function SecondaryNavSidebar() {
open={notificationOpen}
onOpenChange={setNotificationOpen}
/>
<aside className={`light-sidebar ${expanded ? "light-sidebar--expanded" : ""}`}>
<aside
className={`light-sidebar ${expanded ? "light-sidebar--expanded" : ""} ${
headerHidden ? "light-sidebar--header-hidden" : ""
}`}
>
{/* 一级列:二级图标卡片 + 底部设置 */}
<div className="light-sidebar__primary">
<nav className="light-sidebar__list" aria-label="二级菜单">
@@ -222,6 +238,46 @@ function SecondaryNavSidebar() {
按钮管理
</DropdownMenuItem>
)}
{isAdmin && (
<DropdownMenuItem
onClick={() => navigate("/page/strategy/admin/fixed-questions")}
>
<MessageSquareText className="size-4" />
问题配置
</DropdownMenuItem>
)}
{isAdmin && (
<DropdownMenuItem
onClick={() => navigate("/page/strategy/admin/position-roles")}
>
<BriefcaseBusiness className="size-4" />
岗位角色配置
</DropdownMenuItem>
)}
{isAdmin && (
<DropdownMenuItem
onClick={() => navigate("/page/strategy/admin/login-whitelist")}
>
<ShieldCheck className="size-4" />
白名单管理
</DropdownMenuItem>
)}
{isAdmin && (
<DropdownMenuItem
onClick={() => navigate("/page/workspace/admin/models")}
>
<Cpu className="size-4" />
模型配置
</DropdownMenuItem>
)}
{isAdmin && (
<DropdownMenuItem
onClick={() => navigate("/page/strategy/settings/model-concurrency")}
>
<Gauge className="size-4" />
模型并发限制
</DropdownMenuItem>
)}
{canManageSensitiveWords() && (
<DropdownMenuItem
onClick={() => navigate("/page/strategy/admin/sensitive-words")}
@@ -269,6 +325,7 @@ function SecondaryNavSidebar() {
function LegacyAccordionSidebar({
collapsed,
onToggleCollapsed,
headerHidden,
}: PageSidebarProps) {
const { theme } = useTheme();
const isDark = theme === "dark";
@@ -420,7 +477,9 @@ function LegacyAccordionSidebar({
onOpenChange={setNotificationOpen}
/>
<aside
className={`fixed left-0 top-16 z-40 flex h-[calc(100vh-4rem)] flex-col overflow-hidden shadow-sm theme-transition transition-all duration-300 ${
className={`fixed left-0 z-40 flex flex-col overflow-hidden shadow-sm theme-transition transition-all duration-300 ${
headerHidden ? "top-0 h-screen" : "top-16 h-[calc(100vh-4rem)]"
} ${
isDark
? "border-r border-blue-800/30 bg-slate-900"
: "border-r border-red-100 bg-white"
@@ -508,6 +567,30 @@ function LegacyAccordionSidebar({
按钮管理
</DropdownMenuItem>
)}
{isAdmin && (
<DropdownMenuItem onClick={() => navigate("/page/strategy/admin/fixed-questions")}>
<MessageSquareText className="size-4" />
问题配置
</DropdownMenuItem>
)}
{isAdmin && (
<DropdownMenuItem onClick={() => navigate("/page/strategy/admin/position-roles")}>
<BriefcaseBusiness className="size-4" />
岗位角色配置
</DropdownMenuItem>
)}
{isAdmin && (
<DropdownMenuItem onClick={() => navigate("/page/workspace/admin/models")}>
<Cpu className="size-4" />
模型配置
</DropdownMenuItem>
)}
{isAdmin && (
<DropdownMenuItem onClick={() => navigate("/page/strategy/admin/login-whitelist")}>
<ShieldCheck className="size-4" />
白名单管理
</DropdownMenuItem>
)}
{canManageSensitiveWords() && (
<DropdownMenuItem onClick={() => navigate("/page/strategy/admin/sensitive-words")}>
<ShieldAlert className="size-4" />
+1 -1
View File
@@ -10,7 +10,7 @@ const buttonVariants = cva(
variants: {
variant: {
default:
"cursor-pointer bg-primary text-primary-foreground hover:bg-primary/90",
"cursor-pointer bg-primary text-[var(--button-foreground,var(--primary-foreground))] hover:bg-primary/90",
destructive:
"cursor-pointer bg-destructive text-white hover:bg-destructive/90 focus-visible:ring-destructive/20 dark:focus-visible:ring-destructive/40 dark:bg-destructive/60",
outline:
+11 -9
View File
@@ -71,15 +71,17 @@ const DialogOverlay = React.forwardRef<
DialogOverlay.displayName = DialogPrimitive.Overlay.displayName;
const DialogContent = React.forwardRef<
React.ElementRef<typeof DialogPrimitive.Content>,
React.ComponentPropsWithoutRef<typeof DialogPrimitive.Content> & {
showCloseButton?: boolean;
}
>(({ className, children, showCloseButton = true, ...props }, ref) => {
return (
<DialogPortal data-slot="dialog-portal">
<DialogOverlay />
const DialogContent = React.forwardRef<
React.ElementRef<typeof DialogPrimitive.Content>,
React.ComponentPropsWithoutRef<typeof DialogPrimitive.Content> & {
showCloseButton?: boolean;
/** Use when this dialog is opened from a higher-layer surface such as a Drawer. */
overlayClassName?: string;
}
>(({ className, children, showCloseButton = true, overlayClassName, ...props }, ref) => {
return (
<DialogPortal data-slot="dialog-portal">
<DialogOverlay className={overlayClassName} />
<DialogPrimitive.Content
ref={ref}
data-slot="dialog-content"
+13 -10
View File
@@ -144,21 +144,24 @@ function InputGroupInput({
);
}
function InputGroupTextarea({
className,
...props
}: React.ComponentProps<"textarea">) {
const InputGroupTextarea = React.forwardRef<
HTMLTextAreaElement,
React.ComponentProps<"textarea">
>(function InputGroupTextarea({ className, ...props }, ref) {
return (
<Textarea
data-slot="input-group-control"
<Textarea
data-slot="input-group-control"
ref={ref}
className={cn(
"flex-1 resize-none rounded-none border-0 bg-transparent py-3 shadow-none focus-visible:ring-0 dark:bg-transparent",
className,
)}
{...props}
/>
);
}
{...props}
/>
);
});
InputGroupTextarea.displayName = "InputGroupTextarea";
export {
InputGroup,
+20 -14
View File
@@ -27,7 +27,9 @@ import {
const SIDEBAR_COOKIE_NAME = "sidebar_state";
const SIDEBAR_COOKIE_MAX_AGE = 60 * 60 * 24 * 7;
const SIDEBAR_WIDTH = "16rem";
// Keep the workbench navigation compact across every theme. The visual theme
// only changes tokens; the information density should remain consistent.
const SIDEBAR_WIDTH = "14rem";
const SIDEBAR_WIDTH_MOBILE = "18rem";
const SIDEBAR_WIDTH_ICON = "3rem";
const SIDEBAR_KEYBOARD_SHORTCUT = "b";
@@ -57,18 +59,21 @@ function useSidebarSafe() {
return React.useContext(SidebarContext);
}
function SidebarProvider({
defaultOpen = true,
open: openProp,
onOpenChange: setOpenProp,
className,
function SidebarProvider({
defaultOpen = true,
open: openProp,
onOpenChange: setOpenProp,
disableToggle = false,
className,
style,
children,
...props
}: React.ComponentProps<"div"> & {
defaultOpen?: boolean;
open?: boolean;
onOpenChange?: (open: boolean) => void;
}: React.ComponentProps<"div"> & {
defaultOpen?: boolean;
open?: boolean;
onOpenChange?: (open: boolean) => void;
/** Keep a controlled deployment-level rail from being reopened by hotkeys. */
disableToggle?: boolean;
}) {
const isMobile = useIsMobile();
const [openMobile, setOpenMobile] = React.useState(false);
@@ -92,10 +97,11 @@ function SidebarProvider({
[setOpenProp, open],
);
// Helper to toggle the sidebar.
const toggleSidebar = React.useCallback(() => {
return isMobile ? setOpenMobile((open) => !open) : setOpen((open) => !open);
}, [isMobile, setOpen, setOpenMobile]);
// Helper to toggle the sidebar.
const toggleSidebar = React.useCallback(() => {
if (disableToggle) return;
return isMobile ? setOpenMobile((open) => !open) : setOpen((open) => !open);
}, [disableToggle, isMobile, setOpen, setOpenMobile]);
// Adds a keyboard shortcut to toggle the sidebar.
React.useEffect(() => {
+19 -10
View File
@@ -2,19 +2,28 @@ import * as React from "react";
import { cn } from "@/lib/utils";
function Textarea({ className, ...props }: React.ComponentProps<"textarea">) {
return (
<textarea
data-slot="textarea"
className={cn(
"border-input placeholder:text-muted-foreground/60 flex field-sizing-content min-h-16 w-full rounded-md border bg-transparent px-3 py-2 text-base shadow-xs transition-[color,box-shadow] outline-none disabled:cursor-not-allowed disabled:opacity-50 md:text-sm",
const Textarea = React.forwardRef<
HTMLTextAreaElement,
React.ComponentProps<"textarea">
>(function Textarea({ className, rows, ...props }, ref) {
// `field-sizing` is not available in older Chrome. Keep a native rows
// fallback so a multi-line editor never collapses into a single line.
return (
<textarea
data-slot="textarea"
ref={ref}
rows={rows ?? 3}
className={cn(
"border-input placeholder:text-muted-foreground/60 flex min-h-16 w-full rounded-md border bg-transparent px-3 py-2 text-base shadow-xs transition-[color,box-shadow] outline-none disabled:cursor-not-allowed disabled:opacity-50 md:text-sm",
"dark:border-[#1B477E] dark:bg-[#022248] dark:text-[#AACEFF] ",
"focus-visible:border-ring focus-visible:ring-ring/50 focus-visible:ring-[3px] aria-invalid:ring-destructive/20 dark:aria-invalid:ring-destructive/40 aria-invalid:border-destructive",
className,
)}
{...props}
/>
);
}
{...props}
/>
);
});
Textarea.displayName = "Textarea";
export { Textarea };
@@ -3,7 +3,7 @@ export function EmptyDocumentState() {
return (
<div className="flex h-full items-center justify-center bg-white px-6 text-center dark:bg-slate-900">
<div className="rounded-2xl border border-dashed border-slate-300 bg-slate-50 px-10 py-12 sm:px-12 dark:border-slate-700 dark:bg-slate-800/50">
<div className="mb-4 text-[40px] leading-none">📚</div>
<div className="mb-4 text-[28px] font-semibold leading-none text-slate-500 dark:text-slate-300">文档</div>
<div className="mb-2 text-lg font-bold text-slate-700 dark:text-slate-200">
选择一篇文档开始阅读
</div>
@@ -0,0 +1,71 @@
"use client";
import { markdown, markdownLanguage } from "@codemirror/lang-markdown";
import { languages } from "@codemirror/language-data";
import { basicLightInit } from "@uiw/codemirror-theme-basic";
import { monokaiInit } from "@uiw/codemirror-theme-monokai";
import CodeMirror from "@uiw/react-codemirror";
import { useTheme } from "next-themes";
import { useMemo } from "react";
import { cn } from "@/lib/utils";
import { MarkdownContent } from "@/components/workspace/messages/markdown-content";
import { reasoningPlugins } from "@/core/streamdown";
const lightTheme = basicLightInit({ settings: { background: "transparent", fontSize: "14px" } });
const darkTheme = monokaiInit({
settings: { background: "transparent", gutterBackground: "transparent", fontSize: "14px" },
});
/** Markdown-aware source editor shared by Wiki create/edit dialogs. */
export function MarkdownCodeEditor({
value,
onChange,
className,
}: {
value: string;
onChange: (value: string) => void;
className?: string;
}) {
const { resolvedTheme } = useTheme();
const extensions = useMemo(
() => [markdown({ base: markdownLanguage, codeLanguages: languages })],
[],
);
return (
<div className={cn("grid min-h-[46vh] overflow-hidden rounded-lg border bg-background lg:grid-cols-2", className)}>
<section className="flex min-h-0 flex-col border-b lg:border-r lg:border-b-0">
<div className="flex h-9 shrink-0 items-center border-b bg-muted/40 px-3 text-xs font-medium text-muted-foreground">
Markdown 编辑
</div>
<CodeMirror
value={value}
onChange={onChange}
theme={resolvedTheme === "dark" ? darkTheme : lightTheme}
extensions={extensions}
basicSetup={{
foldGutter: true,
highlightActiveLine: true,
highlightActiveLineGutter: false,
lineNumbers: true,
}}
className="min-h-[42vh] flex-1 overflow-auto font-mono text-sm [&_.cm-editor]:min-h-[42vh] [&_.cm-focused]:outline-none!"
/>
</section>
<section className="flex min-h-0 flex-col bg-muted/10">
<div className="flex h-9 shrink-0 items-center border-b bg-muted/40 px-3 text-xs font-medium text-muted-foreground">
实时渲染
</div>
<div className="min-h-[42vh] flex-1 overflow-auto p-4">
<MarkdownContent
content={value || "*暂无正文*"}
isLoading={false}
remarkPlugins={reasoningPlugins.remarkPlugins}
rehypePlugins={reasoningPlugins.rehypePlugins}
/>
</div>
</section>
</div>
);
}
@@ -0,0 +1,189 @@
"use client";
import { BookOpen, ListTree } from "lucide-react";
import { useCallback, useEffect, useMemo, useRef, useState } from "react";
import { MarkdownContent } from "@/components/workspace/messages/markdown-content";
import { Badge } from "@/components/ui/badge";
import { reasoningPlugins } from "@/core/streamdown";
import { createMarkdownAnchorResolver } from "@/core/utils/markdown";
import { cn } from "@/lib/utils";
import "./wiki.css";
function stripMarkdownToText(markdown: string): string {
return markdown
.replace(/```[\s\S]*?```/g, " ")
.replace(/~~~[\s\S]*?~~~/g, " ")
.replace(/!\[[^\]]*\]\([^)]+\)/g, " ")
.replace(/\[([^\]]+)\]\([^)]+\)/g, "$1")
.replace(/^#{1,6}\s+/gm, "")
.replace(/^[>\-*+\d.)\s]+/gm, "")
.replace(/[`*_~|]/g, "")
.replace(/<[^>]+>/g, " ")
.replace(/\s+/g, " ")
.trim();
}
function getMarkdownExcerpt(markdown: string): string {
const text = stripMarkdownToText(markdown);
if (!text) return "";
return text.length > 150 ? `${text.slice(0, 150)}...` : text;
}
function countReadableWords(markdown: string): number {
const text = stripMarkdownToText(markdown);
if (!text) return 0;
const cjk = text.match(/[\u4e00-\u9fff]/g)?.length ?? 0;
const words = text.replace(/[\u4e00-\u9fff]/g, " ").match(/[A-Za-z0-9]+/g)?.length ?? 0;
return cjk + words;
}
function selectorForId(id: string): string {
const css = window.CSS;
if (css?.escape) return `#${css.escape(id)}`;
return `[id="${id.replace(/\\/g, "\\\\").replace(/"/g, '\\"')}"]`;
}
export function ReportMarkdownView({
content,
title,
subtitle,
badgeLabel = "报告阅读",
className,
compactHeader = false,
}: {
content: string;
title?: string;
subtitle?: string;
badgeLabel?: string;
className?: string;
compactHeader?: boolean;
}) {
const rootRef = useRef<HTMLDivElement>(null);
const anchorResolver = useMemo(() => createMarkdownAnchorResolver(content), [content]);
const headings = useMemo(
() => anchorResolver.headings.filter((item) => item.level >= 1 && item.level <= 3),
[anchorResolver],
);
const [activeHeadingId, setActiveHeadingId] = useState<string | null>(null);
const excerpt = useMemo(() => getMarkdownExcerpt(content), [content]);
const sectionCount = headings.length;
const wordCount = useMemo(() => countReadableWords(content), [content]);
useEffect(() => {
setActiveHeadingId(headings[0]?.id ?? null);
}, [headings]);
useEffect(() => {
const root = rootRef.current;
if (!root || headings.length === 0) return;
const targets = headings
.map((item) => root.querySelector<HTMLElement>(selectorForId(item.id)))
.filter((item): item is HTMLElement => !!item);
if (targets.length === 0) return;
const observer = new IntersectionObserver(
(entries) => {
const visible = entries
.filter((entry) => entry.isIntersecting)
.sort((a, b) => a.boundingClientRect.top - b.boundingClientRect.top)[0];
if (visible?.target.id) setActiveHeadingId(visible.target.id);
},
{
root: root.closest("[data-radix-scroll-area-viewport]") ?? null,
rootMargin: "-96px 0px -65% 0px",
threshold: [0, 1],
},
);
targets.forEach((target) => observer.observe(target));
return () => observer.disconnect();
}, [headings, content]);
const scrollToHeading = useCallback((id: string) => {
const root = rootRef.current;
const target =
root?.querySelector<HTMLElement>(selectorForId(id)) ?? document.getElementById(id);
setActiveHeadingId(id);
target?.scrollIntoView({ behavior: "smooth", block: "start" });
}, []);
return (
<div
ref={rootRef}
className={cn("report-markdown-shell grid min-h-0 gap-5 lg:grid-cols-[minmax(0,1fr)_300px]", className)}
>
<article className="report-markdown-paper min-w-0 overflow-hidden">
<header className={cn("report-markdown-header", compactHeader && "report-markdown-header-compact")}>
<div className="flex flex-wrap items-center gap-2">
<Badge variant="secondary" className="report-markdown-badge">
<BookOpen className="size-3.5" />
{badgeLabel}
</Badge>
{subtitle && (
<span className="max-w-full truncate text-xs text-slate-500 dark:text-slate-400">
{subtitle}
</span>
)}
</div>
{title && <h1 className="report-markdown-title">{title}</h1>}
{!compactHeader && excerpt && <p className="report-markdown-excerpt">{excerpt}</p>}
<div className="report-markdown-metrics">
<span>{sectionCount || 1} 个章节</span>
<span>约 {wordCount} 字</span>
</div>
</header>
<div className="wiki-markdown report-markdown-body">
<MarkdownContent
className="max-w-none"
content={content}
isLoading={false}
remarkPlugins={reasoningPlugins.remarkPlugins}
rehypePlugins={reasoningPlugins.rehypePlugins}
/>
</div>
</article>
<aside className="hidden min-w-0 lg:block">
<div className="report-markdown-toc">
<div className="mb-3 flex items-center justify-between gap-2">
<div className="flex items-center gap-2 text-sm font-semibold text-slate-900 dark:text-slate-100">
<ListTree className="size-4" />
内容目录
</div>
<span className="rounded-md bg-slate-100 px-1.5 py-0.5 text-xs text-slate-500 dark:bg-slate-800 dark:text-slate-400">
{sectionCount || 0}
</span>
</div>
{headings.length > 0 ? (
<nav className="report-markdown-toc-list">
{headings.map((item) => (
<button
key={item.id}
type="button"
className={cn(
"report-markdown-toc-item",
activeHeadingId === item.id && "report-markdown-toc-item-active",
item.level === 2 && "report-markdown-toc-level-2",
item.level === 3 && "report-markdown-toc-level-3",
)}
title={item.text}
onClick={() => scrollToHeading(item.id)}
>
{item.text}
</button>
))}
</nav>
) : (
<div className="rounded-md border border-dashed p-3 text-xs text-slate-500 dark:border-slate-800 dark:text-slate-400">
暂无标题目录
</div>
)}
</div>
</aside>
</div>
);
}
@@ -8,6 +8,7 @@ import {
SlidersHorizontal,
Upload,
} from "lucide-react";
import type { ReactNode } from "react";
import { cn } from "@/lib/utils";
@@ -18,7 +19,7 @@ function HeaderButton({
variant = "outline",
className,
}: {
icon: React.ReactNode;
icon: ReactNode;
label: string;
onClick: () => void;
variant?: "outline" | "primary";
@@ -52,6 +53,7 @@ export function WikiHeader({
onCreate,
onManageFolders,
onManageTemplates,
extraActions,
}: {
onToggleSidebar: () => void;
onImportFile: () => void;
@@ -61,6 +63,7 @@ export function WikiHeader({
onCreate: () => void;
onManageFolders: () => void;
onManageTemplates: () => void;
extraActions?: ReactNode;
}) {
return (
<header className="flex h-14 shrink-0 items-center justify-between border-b border-slate-100 bg-white px-4 sm:px-6 dark:border-slate-800 dark:bg-slate-900">
@@ -74,11 +77,12 @@ export function WikiHeader({
<Menu className="size-5" />
</button>
<div className="text-base font-semibold tracking-tight text-slate-900 dark:text-slate-100">
问答梳理
知识库管理
</div>
</div>
<div className="flex items-center gap-2">
{extraActions}
<HeaderButton
icon={<Upload className="size-4" />}
label="导入文件"
+334
View File
@@ -111,6 +111,340 @@
border-color: #eef1f5;
}
.public-report-markdown {
color: #334155;
font-feature-settings: "kern";
text-rendering: optimizeLegibility;
}
.public-report-markdown h1 {
font-size: 30px;
letter-spacing: 0;
margin-bottom: 24px;
}
.public-report-markdown h2 {
font-size: 22px;
margin-top: 42px;
margin-bottom: 16px;
padding-bottom: 10px;
}
.public-report-markdown h3 {
font-size: 18px;
margin-top: 30px;
margin-bottom: 12px;
}
.public-report-markdown p,
.public-report-markdown li {
font-size: 16px;
line-height: 1.9;
}
.public-report-markdown p {
margin-bottom: 16px;
}
.public-report-markdown ul,
.public-report-markdown ol {
margin: 14px 0 18px;
padding-left: 26px;
}
.public-report-markdown ul {
list-style-type: disc;
}
.public-report-markdown ol {
list-style-type: decimal;
}
.public-report-markdown li {
padding-left: 2px;
}
.public-report-markdown code {
border-radius: 6px;
background: #f1f5f9;
padding: 2px 6px;
color: #be123c;
font-size: 0.92em;
}
.public-report-markdown pre {
margin: 20px 0;
border-radius: 8px;
background: #0f172a;
padding: 16px;
overflow-x: auto;
}
.public-report-markdown pre code {
background: transparent;
padding: 0;
color: inherit;
}
.public-report-markdown table {
display: block;
overflow-x: auto;
border-radius: 8px;
border: 1px solid #e8ecf1;
}
.public-report-markdown th,
.public-report-markdown td {
min-width: 120px;
vertical-align: top;
}
.public-report-markdown blockquote {
margin: 20px 0;
}
.dark .public-report-markdown {
color: #cbd5e1;
}
.dark .public-report-markdown code {
background: #1e293b;
color: #f9a8d4;
}
.dark .public-report-markdown pre {
background: #020617;
}
.dark .public-report-markdown table {
border-color: #334155;
}
.report-markdown-shell {
align-items: start;
padding: 2px;
}
.report-markdown-paper {
border: 1px solid rgba(203, 213, 225, 0.85);
border-radius: 8px;
background:
linear-gradient(180deg, rgba(248, 250, 252, 0.92), rgba(255, 255, 255, 0) 220px),
#ffffff;
box-shadow:
0 1px 2px rgba(15, 23, 42, 0.04),
0 18px 44px rgba(15, 23, 42, 0.07);
}
.report-markdown-header {
border-bottom: 1px solid #e8edf4;
padding: 26px 34px 22px;
}
.report-markdown-header-compact {
padding-bottom: 18px;
}
.report-markdown-badge {
gap: 6px;
border: 1px solid #dbe3ef;
background: #ffffff;
color: #475569;
}
.report-markdown-title {
margin: 14px 0 0;
color: #0f172a;
font-size: 26px;
font-weight: 700;
line-height: 1.35;
letter-spacing: 0;
}
.report-markdown-excerpt {
margin: 14px 0 0;
max-width: 840px;
color: #64748b;
font-size: 14px;
line-height: 1.8;
}
.report-markdown-metrics {
display: flex;
flex-wrap: wrap;
gap: 8px;
margin-top: 16px;
color: #64748b;
font-size: 12px;
}
.report-markdown-metrics span {
border: 1px solid #e2e8f0;
border-radius: 6px;
background: rgba(255, 255, 255, 0.78);
padding: 4px 8px;
}
.report-markdown-body {
max-width: 920px;
margin: 0 auto;
padding: 32px 42px 44px;
}
.report-markdown-body h1 {
font-size: 28px;
}
.report-markdown-body h2 {
position: relative;
margin-top: 44px;
border-bottom-color: #e5edf7;
font-size: 22px;
}
.report-markdown-body h2::before {
content: "";
position: absolute;
left: -16px;
top: 0.34em;
width: 4px;
height: 1.05em;
border-radius: 999px;
background: #2563eb;
}
.report-markdown-body h3 {
color: #1e293b;
font-size: 18px;
}
.report-markdown-body p,
.report-markdown-body li {
font-size: 16px;
line-height: 1.92;
}
.report-markdown-body blockquote {
border-left-color: #2563eb;
background: #f8fbff;
}
.report-markdown-body table {
box-shadow: 0 1px 0 rgba(15, 23, 42, 0.04);
}
.report-markdown-toc {
position: sticky;
top: 16px;
max-height: calc(100vh - 32px);
overflow: hidden;
border: 1px solid rgba(203, 213, 225, 0.82);
border-radius: 8px;
background: rgba(255, 255, 255, 0.92);
padding: 14px;
box-shadow: 0 12px 34px rgba(15, 23, 42, 0.06);
backdrop-filter: blur(10px);
}
.report-markdown-toc-list {
max-height: calc(100vh - 128px);
overflow: auto;
padding-right: 4px;
}
.report-markdown-toc-item {
display: block;
width: 100%;
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
border-left: 2px solid transparent;
border-radius: 6px;
padding: 7px 8px;
color: #64748b;
font-size: 12px;
line-height: 1.4;
text-align: left;
transition: background 160ms ease, border-color 160ms ease, color 160ms ease;
}
.report-markdown-toc-item:hover {
background: #f1f5f9;
color: #0f172a;
}
.report-markdown-toc-item-active {
border-left-color: #2563eb;
background: #eff6ff;
color: #1d4ed8;
font-weight: 600;
}
.report-markdown-toc-level-2 {
padding-left: 18px;
}
.report-markdown-toc-level-3 {
padding-left: 30px;
color: #94a3b8;
}
.dark .report-markdown-paper {
border-color: #1f2937;
background:
linear-gradient(180deg, rgba(15, 23, 42, 0.9), rgba(2, 6, 23, 0) 220px),
#020617;
box-shadow: 0 18px 44px rgba(0, 0, 0, 0.24);
}
.dark .report-markdown-header {
border-bottom-color: #1e293b;
}
.dark .report-markdown-badge,
.dark .report-markdown-metrics span {
border-color: #334155;
background: #0f172a;
color: #cbd5e1;
}
.dark .report-markdown-title {
color: #f8fafc;
}
.dark .report-markdown-excerpt,
.dark .report-markdown-metrics {
color: #94a3b8;
}
.dark .report-markdown-body h3 {
color: #e2e8f0;
}
.dark .report-markdown-body h2::before {
background: #60a5fa;
}
.dark .report-markdown-body blockquote {
background: #0f172a;
border-left-color: #60a5fa;
}
.dark .report-markdown-toc {
border-color: #1f2937;
background: rgba(2, 6, 23, 0.88);
}
.dark .report-markdown-toc-item:hover {
background: #0f172a;
color: #f8fafc;
}
.dark .report-markdown-toc-item-active {
background: rgba(37, 99, 235, 0.16);
color: #93c5fd;
}
/* Anchor target offset so headings clear the floating "目录" pill. */
.wiki-markdown h1,
.wiki-markdown h2,
@@ -204,7 +204,7 @@ export function noteFolderSegments(note: KnowledgeNote): string[] {
/** Breadcrumb segments for a note (folders only; the title is appended by the caller). */
export function noteBreadcrumbSegments(note: KnowledgeNote): string[] {
return ["问答梳理", ...noteFolderSegments(note).map(localizeFolderName)];
return ["知识库管理", ...noteFolderSegments(note).map(localizeFolderName)];
}
function sortTree(nodes: TreeNode[]): void {
@@ -0,0 +1,556 @@
"use client";
import {
Activity,
Gauge,
Loader2,
OctagonX,
RefreshCw,
Square,
Zap,
} from "lucide-react";
import { useId, useMemo, useState } from "react";
import { toast } from "sonner";
import { Badge } from "@/components/ui/badge";
import { Button } from "@/components/ui/button";
import { Switch } from "@/components/ui/switch";
import type {
ActiveRunItem,
ConcurrencyPoint,
Granularity,
TokenSpeedPoint,
} from "@/core/admin/active-runs";
import {
useActiveRuns,
useCancelActiveRun,
useCancelAllActiveRuns,
useConcurrencySeries,
useMonitorSettings,
useTokenSpeedSeries,
useUpdateMonitorSettings,
} from "@/core/admin/hooks";
import { cn } from "@/lib/utils";
/** lookback window (hours) per granularity. */
const LOOKBACK: Record<Granularity, number> = { minute: 3, hour: 48 };
function fmtBucket(iso: string, granularity: Granularity): string {
const date = new Date(iso);
if (Number.isNaN(date.getTime())) return iso;
const mm = String(date.getMonth() + 1).padStart(2, "0");
const dd = String(date.getDate()).padStart(2, "0");
const hh = String(date.getHours()).padStart(2, "0");
const mi = String(date.getMinutes()).padStart(2, "0");
return granularity === "hour" ? `${mm}-${dd} ${hh}:00` : `${hh}:${mi}`;
}
function fmtElapsed(seconds: number): string {
if (seconds < 60) return `${seconds}s`;
const m = Math.floor(seconds / 60);
const s = seconds % 60;
if (m < 60) return `${m}m${s.toString().padStart(2, "0")}s`;
const h = Math.floor(m / 60);
return `${h}h${(m % 60).toString().padStart(2, "0")}m`;
}
interface LineSeries {
name: string;
color: string;
values: (number | null)[];
}
/** Round a value up to a "nice" axis ceiling (1 / 2 / 5 × 10ⁿ). */
function niceCeil(v: number): number {
if (!Number.isFinite(v) || v <= 0) return 1;
const exp = Math.floor(Math.log10(v));
const base = 10 ** exp;
const f = v / base;
const nice = f <= 1 ? 1 : f <= 2 ? 2 : f <= 5 ? 5 : 10;
return nice * base;
}
/**
* Build distinct axis ticks from the data max. For integer series (并发量) this
* yields whole-number ticks with no duplicate labels (fixes the「0 0 0 1 1」
* axis when the max is 1); for floats it uses a nice ceiling at quarters.
*/
function buildTicks(dataMax: number, integer: boolean): number[] {
if (!Number.isFinite(dataMax) || dataMax <= 0) return [0, 1];
if (integer) {
const niceMax = Math.max(1, Math.ceil(dataMax));
const step = Math.max(1, Math.ceil(niceMax / 4)); // ≤5 integer ticks
const top = Math.ceil(niceMax / step) * step;
const ticks: number[] = [];
for (let v = 0; v <= top; v += step) ticks.push(v);
return ticks;
}
const niceMax = niceCeil(dataMax);
return [0, 0.25, 0.5, 0.75, 1].map((r) => niceMax * r);
}
function fmtAxis(v: number, integer: boolean): string {
if (integer) return String(Math.round(v));
if (v === 0) return "0";
return v < 10 ? v.toFixed(1) : String(Math.round(v));
}
/** Last non-null value of a series (for the legend's current reading). */
function latestOf(values: (number | null)[]): number | null {
for (let i = values.length - 1; i >= 0; i -= 1) {
if (values[i] != null) return values[i] as number;
}
return null;
}
/** Minimal dependency-free SVG line chart: legend + 1–2 series + area + caption. */
function LineChart({
labels,
series,
unit,
integer = false,
note,
emptyHint,
}: {
labels: string[];
series: LineSeries[];
unit: string;
integer?: boolean;
note?: string;
emptyHint: string;
}) {
const gradId = `cm-area-${useId().replace(/:/g, "")}`;
const width = 760;
const height = 220;
const pad = { top: 16, right: 16, bottom: 26, left: 44 };
const cw = width - pad.left - pad.right;
const ch = height - pad.top - pad.bottom;
const n = labels.length;
const allValues = series.flatMap((s) => s.values.filter((v): v is number => v != null));
const dataMax = allValues.length ? Math.max(...allValues) : 0;
const ticks = buildTicks(dataMax, integer);
const axisMax = ticks[ticks.length - 1] || 1;
// Legend always renders (even with no data) so the lines are self-explanatory.
const legend = (
<div className="mb-2 flex flex-wrap items-center gap-x-4 gap-y-1">
{series.map((s) => {
const latest = latestOf(s.values);
return (
<span key={s.name} className="flex items-center gap-1.5 text-xs text-[#5F6368] dark:text-slate-300">
<span className="inline-block h-[3px] w-4 rounded-full" style={{ backgroundColor: s.color }} />
{s.name}
{latest != null && (
<span className="font-semibold tabular-nums text-[#231815] dark:text-white">
{Number.isInteger(latest) ? latest : latest.toFixed(1)}
{unit}
</span>
)}
</span>
);
})}
</div>
);
const caption = note ? (
<p className="mt-2 text-[11px] leading-4 text-[#8B6B6B] dark:text-[#7FACF2]">{note}</p>
) : null;
if (n === 0) {
return (
<div>
{legend}
<div className="flex h-[160px] items-center justify-center rounded-lg border border-dashed border-[#F1D6D6] text-sm text-[#5F6368] dark:border-[#213D5E] dark:text-slate-400">
{emptyHint}
</div>
{caption}
</div>
);
}
const xFor = (i: number) => pad.left + (n <= 1 ? cw / 2 : (i / (n - 1)) * cw);
const yFor = (v: number) => pad.top + ch - (v / axisMax) * ch;
const linePath = (vals: (number | null)[]) => {
let d = "";
let started = false;
vals.forEach((v, i) => {
if (v == null) {
started = false;
return;
}
d += `${started ? "L" : "M"} ${xFor(i).toFixed(1)} ${yFor(v).toFixed(1)} `;
started = true;
});
return d.trim();
};
const first = series[0];
const areaPath = (() => {
if (!first) return "";
const line = linePath(first.values);
if (!line) return "";
return `${line} L ${xFor(n - 1).toFixed(1)} ${(pad.top + ch).toFixed(1)} L ${xFor(0).toFixed(1)} ${(pad.top + ch).toFixed(1)} Z`;
})();
const labelStep = Math.max(1, Math.ceil(n / 7));
return (
<div>
{legend}
<svg viewBox={`0 0 ${width} ${height}`} className="w-full" role="img" aria-label="时序折线图">
<defs>
<linearGradient id={gradId} x1="0" x2="0" y1="0" y2="1">
<stop offset="0%" stopColor={first?.color ?? "#C1121F"} stopOpacity="0.18" />
<stop offset="100%" stopColor={first?.color ?? "#C1121F"} stopOpacity="0.02" />
</linearGradient>
</defs>
{ticks.map((t) => {
const y = yFor(t);
return (
<g key={t}>
<line
x1={pad.left}
x2={width - pad.right}
y1={y}
y2={y}
stroke="currentColor"
className="text-[#E5E7EB] dark:text-[#3F3F46]"
strokeWidth="1"
/>
<text x={pad.left - 6} y={y + 3} textAnchor="end" className="fill-[#9CA3AF] text-[10px]">
{fmtAxis(t, integer)}
</text>
</g>
);
})}
{areaPath && <path d={areaPath} fill={`url(#${gradId})`} />}
{series.map((s) => (
<path
key={s.name}
d={linePath(s.values)}
fill="none"
stroke={s.color}
strokeWidth="2"
strokeLinecap="round"
strokeLinejoin="round"
/>
))}
{labels.map((label, i) => {
if (i !== 0 && i !== n - 1 && i % labelStep !== 0) return null;
return (
<text key={`${label}-${i}`} x={xFor(i)} y={height - 8} textAnchor="middle" className="fill-[#6B7280] text-[10px]">
{label}
</text>
);
})}
{series.map((s) =>
s.values.map((v, i) =>
v == null ? null : (
<circle key={`${s.name}-${i}`} cx={xFor(i)} cy={yFor(v)} r={2.5} fill={s.color}>
<title>{`${labels[i]} · ${s.name}: ${v}${unit}`}</title>
</circle>
),
),
)}
</svg>
{caption}
</div>
);
}
function ChartCard({
icon: Icon,
title,
subtitle,
children,
}: {
icon: typeof Activity;
title: string;
subtitle: string;
children: React.ReactNode;
}) {
return (
<section className="rounded-lg border border-[#F1D6D6] bg-white p-4 shadow-sm dark:border-[#213D5E] dark:bg-[#02244C]">
<div className="mb-3 flex items-center gap-2">
<Icon className="size-4 text-[#C1121F] dark:text-[#7FACF2]" />
<h3 className="font-semibold text-[#231815] dark:text-white">{title}</h3>
<span className="ml-auto text-xs text-[#8B6B6B] dark:text-[#7FACF2]">{subtitle}</span>
</div>
{children}
</section>
);
}
function ActiveRunRow({
run,
onStop,
stopping,
}: {
run: ActiveRunItem;
onStop: (runId: string) => void;
stopping: boolean;
}) {
return (
<div className="grid grid-cols-[minmax(0,1.4fr)_minmax(0,1.2fr)_72px_64px_64px_72px] items-center gap-3 border-b border-[#F1D6D6] px-3 py-2 text-sm last:border-b-0 dark:border-[#213D5E]">
<div className="min-w-0">
<div className="truncate font-medium text-[#202124] dark:text-white">{run.user_name || "未知用户"}</div>
<div className="truncate text-xs text-[#5F6368] dark:text-slate-400" title={run.thread_title}>
{run.thread_title || run.thread_id}
</div>
</div>
<div className="min-w-0 truncate text-[#202124] dark:text-slate-100">{run.agent_name}</div>
<Badge variant="outline" className="justify-center">
{run.kind}
</Badge>
<span
className={cn(
"text-center text-xs font-medium",
run.status === "running" ? "text-[#0F766E] dark:text-teal-300" : "text-[#B45309] dark:text-amber-300",
)}
>
{run.status === "running" ? "运行中" : "排队中"}
</span>
<span className="text-center text-xs tabular-nums text-[#5F6368] dark:text-slate-400">
{fmtElapsed(run.elapsed_seconds)}
</span>
<Button
size="sm"
variant="outline"
className="h-7 border-[#C1121F]/40 text-[#C1121F] hover:bg-[#FFF1F1] dark:border-rose-400/40 dark:text-rose-200"
disabled={stopping}
onClick={() => onStop(run.run_id)}
>
{stopping ? <Loader2 className="size-3.5 animate-spin" /> : <Square className="size-3.5" />}
停止
</Button>
</div>
);
}
export function ConcurrencyMonitorPanel() {
const [open, setOpen] = useState(true);
const [granularity, setGranularity] = useState<Granularity>("minute");
const { data: live, isLoading: liveLoading, refetch, isRefetching } = useActiveRuns(open);
const concurrency = useConcurrencySeries(granularity, LOOKBACK[granularity], open);
const tokenSpeed = useTokenSpeedSeries(granularity, LOOKBACK[granularity], open);
const { data: settings } = useMonitorSettings();
const updateSettings = useUpdateMonitorSettings();
const cancelOne = useCancelActiveRun();
const cancelAll = useCancelAllActiveRuns();
const [stoppingId, setStoppingId] = useState<string | null>(null);
const count = live?.count ?? 0;
const runs = live?.runs ?? [];
const samplerOn = settings?.enabled ?? false;
const concurrencyChart = useMemo(() => {
const points: ConcurrencyPoint[] = concurrency.data?.points ?? [];
return {
labels: points.map((p) => fmtBucket(p.bucket, granularity)),
series: [
{ name: "峰值并发", color: "#C1121F", values: points.map((p) => p.peak) },
{ name: "平均并发", color: "#F59E0B", values: points.map((p) => p.avg) },
] as LineSeries[],
};
}, [concurrency.data, granularity]);
const tokenChart = useMemo(() => {
const points: TokenSpeedPoint[] = tokenSpeed.data?.points ?? [];
return {
labels: points.map((p) => fmtBucket(p.bucket, granularity)),
series: [
{ name: "平均速度", color: "#2563EB", values: points.map((p) => p.avg_tokens_per_sec) },
{ name: "最慢", color: "#9333EA", values: points.map((p) => p.min_tokens_per_sec) },
] as LineSeries[],
};
}, [tokenSpeed.data, granularity]);
const handleStop = async (runId: string) => {
setStoppingId(runId);
try {
const res = await cancelOne.mutateAsync(runId);
toast[res.cancelled ? "success" : "info"](res.cancelled ? "已停止该对话调用" : "该调用已结束或不存在");
} catch (e) {
toast.error(e instanceof Error ? e.message : "停止失败");
} finally {
setStoppingId(null);
}
};
const handleStopAll = async () => {
if (runs.length === 0) return;
if (!window.confirm(`确定要停止当前全部 ${count} 个并发调用吗?这会中断这些用户正在生成的回答。`)) return;
try {
const res = await cancelAll.mutateAsync();
toast.success(`已停止 ${res.cancelled_count} 个调用`);
} catch (e) {
toast.error(e instanceof Error ? e.message : "全部停止失败");
}
};
const handleToggleSampler = async (next: boolean) => {
try {
await updateSettings.mutateAsync(next);
toast.success(next ? "已开启并发采样" : "已关闭并发采样(折线图不再新增历史点)");
} catch (e) {
toast.error(e instanceof Error ? e.message : "切换失败");
}
};
return (
<section className="space-y-4 rounded-xl border border-[#F1D6D6] bg-[#FFF7F7] p-4 shadow-sm dark:border-[#213D5E] dark:bg-[#011226]">
{/* header */}
<div className="flex flex-wrap items-center gap-3">
<div className="flex items-center gap-2">
<span className="flex size-9 items-center justify-center rounded-lg bg-[#C1121F] text-white dark:bg-[#2563EB]">
<Activity className="size-5" />
</span>
<div>
<div className="font-semibold text-[#231815] dark:text-white">实时并发监控</div>
<div className="text-xs text-[#8B6B6B] dark:text-[#7FACF2]">
监控大模型并发压力,可直接停止任意对话调用
</div>
</div>
</div>
<div className="ml-auto flex flex-wrap items-center gap-3">
<div className="flex items-center gap-2 rounded-lg border border-[#F1D6D6] bg-white px-3 py-1.5 dark:border-[#213D5E] dark:bg-[#02244C]">
<span className="text-xs text-[#5F6368] dark:text-slate-300">当前并发</span>
<span
className={cn(
"text-2xl font-semibold tabular-nums",
count > 0 ? "text-[#C1121F] dark:text-[#7FACF2]" : "text-[#202124] dark:text-white",
)}
>
{count}
</span>
</div>
<div className="flex items-center gap-2 rounded-lg border border-[#F1D6D6] bg-white px-3 py-1.5 dark:border-[#213D5E] dark:bg-[#02244C]">
<span className="text-xs text-[#5F6368] dark:text-slate-300">后台采样</span>
<Switch checked={samplerOn} onCheckedChange={handleToggleSampler} disabled={updateSettings.isPending} />
</div>
<Button variant="outline" size="sm" onClick={() => refetch()} disabled={isRefetching}>
<RefreshCw className={cn("mr-1 size-4", isRefetching && "animate-spin")} />
刷新
</Button>
<Button
variant="outline"
size="sm"
className="border-[#C1121F]/50 text-[#C1121F] hover:bg-[#FFF1F1] dark:border-rose-400/40 dark:text-rose-200"
onClick={handleStopAll}
disabled={cancelAll.isPending || runs.length === 0}
>
<OctagonX className="mr-1 size-4" />
全部停止
</Button>
<Button variant="ghost" size="sm" onClick={() => setOpen((v) => !v)}>
{open ? "收起" : "展开"}
</Button>
</div>
</div>
{open && (
<>
{!samplerOn && (
<div className="rounded-lg border border-amber-300/60 bg-amber-50 px-3 py-2 text-xs text-amber-800 dark:border-amber-300/30 dark:bg-amber-300/10 dark:text-amber-100">
后台采样默认关闭:实时并发数与「停止」功能始终可用。需要并发量历史折线图时,打开右上角「后台采样」开关即可开始记录(对线上服务影响极小,可随时关闭)。
</div>
)}
{/* granularity toggle */}
<div className="flex items-center gap-2">
<span className="text-xs text-[#5F6368] dark:text-slate-300">统计粒度</span>
{(["minute", "hour"] as Granularity[]).map((g) => (
<Button
key={g}
size="sm"
variant={granularity === g ? "default" : "outline"}
className={cn("h-7", granularity === g && "bg-[#C1121F] hover:bg-[#A50F1A] dark:bg-[#2563EB]")}
onClick={() => setGranularity(g)}
>
{g === "minute" ? "按分钟" : "按小时"}
</Button>
))}
<span className="text-xs text-[#8B6B6B] dark:text-[#7FACF2]">
{granularity === "minute" ? "近 3 小时" : "近 48 小时"}
</span>
</div>
{/* charts */}
<div className="grid gap-3 xl:grid-cols-2">
<ChartCard icon={Gauge} title="并发量(系统压力)" subtitle={`每${granularity === "hour" ? "小时" : "分钟"}一个点`}>
{concurrency.isLoading ? (
<div className="flex h-[220px] items-center justify-center text-sm text-[#5F6368] dark:text-slate-400">
<Loader2 className="mr-2 size-4 animate-spin" /> 加载中
</div>
) : (
<LineChart
labels={concurrencyChart.labels}
series={concurrencyChart.series}
unit=" 个"
integer
note="红线=该时段同时进行的最多调用数(峰值);橙线=该时段平均值。数值越高、越靠上,说明同时打大模型的请求越多、系统压力越大。"
emptyHint="暂无并发采样数据(需打开「后台采样」开关后才开始记录)"
/>
)}
</ChartCard>
<ChartCard icon={Zap} title="大模型出字速度" subtitle={`每${granularity === "hour" ? "小时" : "分钟"}一个点`}>
{tokenSpeed.isLoading ? (
<div className="flex h-[220px] items-center justify-center text-sm text-[#5F6368] dark:text-slate-400">
<Loader2 className="mr-2 size-4 animate-spin" /> 加载中
</div>
) : (
<LineChart
labels={tokenChart.labels}
series={tokenChart.series}
unit=" t/s"
note="蓝线=该时段所有大模型调用的平均出字速度(tokens/秒,越高越快);紫线=该时段最慢的一次调用。某段时间线明显下凹,说明那会儿模型/供应商变慢,是压力或瓶颈所在。"
emptyHint="暂无大模型调用记录"
/>
)}
</ChartCard>
</div>
{/* active run list */}
<section className="rounded-lg border border-[#F1D6D6] bg-white dark:border-[#213D5E] dark:bg-[#02244C]">
<div className="flex items-center gap-2 border-b border-[#F1D6D6] px-3 py-2 dark:border-[#213D5E]">
<span className="font-semibold text-[#231815] dark:text-white">正在进行的调用</span>
<Badge variant="outline">{count}</Badge>
{liveLoading && <Loader2 className="size-3.5 animate-spin text-[#8B6B6B]" />}
</div>
{runs.length === 0 ? (
<div className="py-10 text-center text-sm text-[#5F6368] dark:text-slate-400">
当前没有正在进行的大模型调用
</div>
) : (
<div>
<div className="grid grid-cols-[minmax(0,1.4fr)_minmax(0,1.2fr)_72px_64px_64px_72px] gap-3 border-b border-[#F1D6D6] px-3 py-2 text-xs text-[#8B6B6B] dark:border-[#213D5E] dark:text-[#7FACF2]">
<span>用户 / 会话</span>
<span>智能体</span>
<span className="text-center">类型</span>
<span className="text-center">状态</span>
<span className="text-center">已运行</span>
<span className="text-center">操作</span>
</div>
{runs.map((run) => (
<ActiveRunRow
key={run.run_id}
run={run}
onStop={handleStop}
stopping={stoppingId === run.run_id}
/>
))}
</div>
)}
</section>
</>
)}
</section>
);
}
export default ConcurrencyMonitorPanel;
@@ -213,7 +213,7 @@ const errorToastDarkOptions = {
</div>
<div className="flex flex-1 flex-wrap items-center gap-1.5">
{summary && Object.keys(summary.by_category).length === 0 && (
<span className="text-muted-foreground text-sm">暂无失败记录 🎉</span>
<span className="text-muted-foreground text-sm">暂无失败记录</span>
)}
{summary &&
Object.entries(summary.by_category)
@@ -24,12 +24,60 @@ const AGENT_COLORS_DARK = [
{ from: "#69B1FF", to: "#003EB3" }, // 浅蓝 → 主色按下
] as const;
/** 按 agent id 稳定散列出一对渐变色(from → to)。`isDark` 切换深蓝/浅色调色板。 */
export function agentColor(id: string, isDark: boolean) {
/** 按 agent id 稳定散列出一对渐变色,并根据当前主题返回可读的图标前景色。 */
const AGENT_COLORS_ICEBLUE = [
{ from: "#eff8fd", to: "#b7dcf5" },
{ from: "#e3f2fb", to: "#9bcef1" },
{ from: "#ebf6fb", to: "#add8e9" },
{ from: "#edf2fc", to: "#b7cdef" },
{ from: "#e9f7f5", to: "#afe0dc" },
] as const;
const AGENT_COLORS_LIGHTYELLOW = [
{ from: "#fbfdef", to: "#e4efbf" },
{ from: "#f7fae9", to: "#F3FBD9" },
{ from: "#f9fbe8", to: "#dcebad" },
{ from: "#faf8e9", to: "#e7dfb9" },
{ from: "#f1f8e5", to: "#cce0af" },
] as const;
type AgentAvatarTheme =
| "dark"
| "iceblue"
| "lightyellow"
| "light"
| "lightblue"
| "lightgreen"
| `custom-theme-${string}`;
/** Returns a stable avatar gradient and readable icon color for each theme. */
export function agentColor(id: string, theme: AgentAvatarTheme) {
if (theme.startsWith("custom-theme-")) {
return {
from: "var(--accent)",
to: "var(--brand-200)",
foreground: "var(--accent-foreground)",
};
}
let hash = 0;
for (let i = 0; i < id.length; i++) {
hash = (hash * 31 + id.charCodeAt(i)) >>> 0;
}
const palette = isDark ? AGENT_COLORS_DARK : AGENT_COLORS_LIGHT;
return palette[hash % palette.length]!;
const palette =
theme === "dark"
? AGENT_COLORS_DARK
: theme === "iceblue"
? AGENT_COLORS_ICEBLUE
: theme === "lightyellow"
? AGENT_COLORS_LIGHTYELLOW
: AGENT_COLORS_LIGHT;
return {
...palette[hash % palette.length]!,
foreground:
theme === "iceblue"
? "#2d587a"
: theme === "lightyellow"
? "#4c6330"
: "#ffffff",
};
}
@@ -35,7 +35,7 @@ export function AgentWelcome({
className,
)}
>
<div className="bg-primary/10 ring-primary/15 mb-2 flex h-[72px] w-[72px] items-center justify-center rounded-3xl ring-1">
<div className="agent-avatar bg-primary/10 ring-primary/15 mb-2 flex h-[72px] w-[72px] items-center justify-center rounded-3xl ring-1">
<BotIcon className="text-primary h-9 w-9" />
</div>
<div className="text-3xl font-bold tracking-tight">
@@ -0,0 +1,55 @@
"use client";
import agentAvatarDark from "@/assets/img/agent-avatar.png";
import agentAvatarLight from "@/assets/img/agent-avatar-red.png";
import { useTheme } from "@/contexts/ThemeContext";
import { cn } from "@/lib/utils";
type AgentBrandIconProps = {
className?: string;
size?: "nav" | "sm" | "md" | "lg";
};
const SIZE_STYLES = {
nav: {
frame: "size-[22px] rounded-md",
},
sm: {
frame: "size-10 rounded-full",
},
md: {
frame: "size-12 rounded-full",
},
lg: {
frame: "size-16 rounded-full",
},
} as const;
export function AgentBrandIcon({
className,
size = "md",
}: AgentBrandIconProps) {
const styles = SIZE_STYLES[size];
const { theme } = useTheme();
const avatarSrc =
theme === "light" ? agentAvatarLight : agentAvatarDark;
return (
<span
aria-hidden="true"
data-agent-brand-icon={size}
className={cn(
"relative inline-flex shrink-0 overflow-hidden rounded-full",
styles.frame,
className,
)}
>
<img
src={avatarSrc}
alt=""
className="size-full object-contain"
draggable={false}
/>
</span>
);
}
Loaded 100 of 1860 files, more files were not shown because too many files have changed in this diff. Show more