wsk/deerflow-code
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,219 Commits 39 Branches 0 Tags
089d3e171f60194de23a6772e9a96b467abe82d2
Commit Graph
1219 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
fengxiangdebaozi 6b1f17d6a8 页面导入 2026-05-14 16:51:32 +08:00
xuhdandClaude Opus 4.7 cf191ef874 feat(skills/notifications): 多租户阶段 2 — 路由 + 级联 + 启动迁移 
后端工作：

deps.py
- 挂载 skill_store / notification_store 到 app.state
- 启动时 set_notification_store(...) 注入到 harness sender；
  关闭时清空，保证测试和 embedded 模式不留状态
- 加 get_skill_store / get_notification_store FastAPI 依赖

routers/skills.py
- 加 _current_user_id / _is_admin_user / _get_owned_skill_or_raise /
  _get_editable_skill_or_raise（对齐 routers/agents.py）
- SkillResponse 加 owner_user_id / published / builtin 字段，
  _skill_to_response 接受 SkillStore 记录映射
- GET /api/skills 与 GET /api/skills/custom 改 per-user 可见性过滤
- POST /api/skills/install + /install-upload 预解析 archive 名校验
  全局 name 不被他人持有；安装后 ensure_legacy 注册 owner=current
- DELETE /api/skills/custom/{name} 走 _get_editable_skill_or_raise，
  调 cascade（owner 自删 = delete，admin 跨用户 = admin_takedown），
  SkillStore.delete / delete_admin 同步清除 DB 记录
- 新增 PUT /api/skills/custom/{name}/published 切换发布状态；
  从 published → unpublished 时触发 cascade（unpublish / admin_takedown）

skills/cascade.py（新）
- 扫所有 .deer-flow/agents/{id}/config.yaml，把指定 skill 从其 skills
  数组移除，并通过 deerflow.persistence.notifications.notify 给受
  影响 agent 的 owner 发站内信；admin 强制下架时另给 skill owner 发
  一条
- 操作类型：unpublish / delete / admin_takedown，对应不同文案

routers/notifications.py（新）+ app.include_router
- GET /api/notifications（unread_only / limit）
- GET /api/notifications/unread_count（红点用）
- POST /api/notifications/{id}/read
- POST /api/notifications/read_all
- DELETE /api/notifications/{id}

app.py lifespan
- _sync_legacy_skills(app)：每次启动扫 skills/custom/ 把没在 DB
  的 skill 落库为 admin owner + published=True，幂等、非阻塞失败
- 调用顺序：_ensure_admin_user → _sync_legacy_skills → 启动 curator

测试：19 个旧用例继续通过；阶段 4 会写 test_skills_multitenancy.py

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-14 16:24:42 +08:00
董宏凯 f6d3d013fd Merge branch 'dhk-2' into 'master' 
样式修改

See merge request knowledge-base-bj/deerflow-server!13
 2026-05-14 08:04:28 +00:00
fengxiangdebaozi e6ad3c414f 页面布局调整 2026-05-14 16:01:25 +08:00
xuhdandClaude Opus 4.7 8162719e36 feat(skills/notifications): 多租户阶段 1 — 持久化层 
新增两套 persistence 模块，仿 persistence/agents/ 模板：

1. persistence/skills/
   - SkillRow ORM (PK=name, owner_user_id, published, timestamps)
   - SkillStore 抽象：list_visible / get_visible / get_any /
     get_owned / create / ensure_legacy / update / update_admin /
     delete / delete_admin
   - SqlAlchemy 实现 SkillRepository
   - MemorySkillStore 用于测试
   - 可见性 = owner OR published OR builtin

2. persistence/notifications/
   - NotificationRow ORM (id, user_id, type, title, body, payload JSON,
     read, created_at)
   - NotificationStore 抽象：create / list_for_user / unread_count /
     mark_read / mark_all_read / delete
   - SqlAlchemy 实现 NotificationRepository
   - MemoryNotificationStore 用于测试
   - sender.notify(user_id, type, ...) 全局接口；harness 不能 import
     app.*，所以用 set_notification_store / get_notification_store
     注入模式

3. persistence/models/__init__.py 注册 SkillRow + NotificationRow

后续阶段会接入路由、cascade、curator per-user 重构、前端。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-14 15:44:36 +08:00
xuhdandClaude Opus 4.7 f5bc02d598 fix: skills 路由两个小修复 
skills.py:
- update_curator_config 直接 await get_curator_config() 报错
  ('Depends' object has no attribute 'skill_evolution')。FastAPI 路由
  默认参数 Depends(...) 只在请求时被框架解析，直接调用拿到的是依赖标记。
  抽出 _build_curator_config_response(config) 让 GET 和 PUT 共用。

skill_manage_tool.py:
- 模型把 action='list' 当成可用动作误调 skill_manage 报
  Unsupported action。补两个 read-only 别名 list/view，分别委派到
  skill_list_tool 和 skill_view_tool，docstring 同步更新。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-14 15:43:26 +08:00
fengxiangdebaozi 139dfb76e4 bug修改 2026-05-14 14:59:12 +08:00
fengxiangdebaozi f4769c4046 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-2 2026-05-14 14:28:31 +08:00
fengxiangdebaozi fea3cc741f 系统合并 2026-05-14 14:28:17 +08:00
xuhdandClaude Opus 4.7 4e764350a4 feat(agents): 创建专家页面加模型选择 
NewAgentPage 在两处加 Select 下拉：
- 左侧聊天框上方 "当前对话模型"：透传给 useThreadStream 的
  context.model_name，控制当前 bootstrap 对话调用的 LLM
- 右侧表单 "模型"：写入 agent.model，控制专家保存后被使用时调用
  的 LLM

两个下拉互相独立，复用 useModels() 拉 /api/models。页面加载完
模型列表后自动 seed 到列表第一个（与 config.yaml 全局默认对齐），
用户可随时切换。

杂项：.gitignore 忽略 skills/ 与 hermes-agent-main/ 运行时目录。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-14 12:59:10 +08:00
xuhd c63811367e 123 2026-05-14 12:45:04 +08:00
xuhdandClaude Opus 4.7 4cc8b3198b fix: 修复 setup_agent 创建专家流程的多个问题 
后端 (setup_agent_approval_middleware.py)：
- 拦截策略从 wrap_tool_call + Command(goto=END) 改为
  after_model + jump_to="end"。在 tool_node 执行前直接终止图，
  避免模型并行调多个 tool_call 时 Command 输出被稀释、graph
  路由不稳定的问题（症状：审批 ToolMessage 发出后流不结束）。
- 用 @hook_config(can_jump_to=["end"]) 装饰器声明跳转能力，
  否则 LangChain 不会为该 hook 构造 conditional edge。

前端 (NewAgentPage.tsx)：
- 聊天阶段不再调 ensureAgent / POST /api/agents，placeholder
  agent 不再落库；agent 仅在用户点右上角“保存”时创建。
- 自动生成的占位名 "未命名专家-xxx" 不再回写到输入框，保持空白
  直到用户输入或 setup_agent 审批回填。
- handleApproveSetupAgent 仅把模型 propose 的 payload 填入表单，
  不再 PUT /api/agents/{id}；落库交给手动保存按钮。
- onToolEnd 不再 getAgentWithRetry —— 工具被 middleware 拦截、
  根本不会执行，没有 agent 状态可拉。清理对应死代码（getAgent
  import、wait()、AGENT_READ_RETRY_DELAYS_MS、getAgentWithRetry）。
- 路由跳转补齐 /page 前缀：返回按钮、“开始对话”按钮。
- 右侧表单：SOUL.md textarea 加 max-h-[400px]，技能列表外框加
  max-h-[240px]，各自 overflow-y-auto，避免长内容撑高整列。

前端 (agent-card.tsx)：
- 列表卡片“聊天”按钮的跳转路径补齐 /page 前缀，避免点击后 404。

无新依赖。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-14 12:35:49 +08:00
xuhdandClaude Opus 4.7 5c6ac06656 feat(skills): 自我进化前端 — Skills 独立侧边栏 + /skills/evolution 页面 
UI 重构：
- settings-dialog.tsx：把 Skills section 从设置弹窗移除
- workspace-nav-chat-list.tsx + WorkspaceRoutes.tsx + SkillsPage.tsx：
  Skills 提升为独立侧边栏导航项，/workspace/skills 路由直接渲染
  SkillSettingsPage（同事原型已就绪）
- skill-settings-page.tsx：顶部追加 "自我进化" 跳转按钮

自我进化页面：
- /workspace/skills/evolution 子路由 → SkillEvolutionPage 包装
- skill-evolution-panel.tsx：三段式
  · 状态卡：启用/暂停徽章 + 累计运行次数 + 上次运行时间/摘要 +
    技能计数 (total/active/stale/archived) + 立即执行按钮
  · 配置表单：enabled / curator.enabled / interval_hours /
    stale_after_days / archive_after_days / moderation_model_name
    本地暂存 → 保存调 PUT，热生效
  · 日志面板：拉 GET /api/curator/logs，2 秒自动刷新，monospace
    展示，warning 黄、error 红
- core/curator/api.ts + hooks.ts + types.ts：TanStack Query 包装
  status / config (GET/PUT) / run / logs

i18n：
- types.ts 新增 settings.skillEvolution.* 类型签名
- zh-CN.ts / en-US.ts：状态卡 / 配置表单 / 日志面板文案，
  以及 settings.skills.goToEvolution

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-14 12:00:54 +08:00
xuhdandClaude Opus 4.7 9b6b94d919 feat(skills): 自我进化后端 — curator 配置可编辑 + 运行日志可读 
后端骨架：
- curator.py / usage.py / skill_tools.py：基于使用计数的生命周期管理
  + LLM 合并/归档建议（同事已有原型，集中提交）
- skill_evolution_config.py：CuratorConfig 嵌套模型
- app.py：启动时按间隔触发 curator 后台线程
- tools.py：开启自我进化时一并注册 skill_list / skill_view 工具
- skill_manage_tool.py：agent 创建技能时标记 source=agent

本次新增：
- skill_evolution_runtime.py：skill_evolution.json 读写，原子写入
- app_config.py：把 overrides 深合并到 AppConfig.skill_evolution，
  并把 overrides 的 mtime 纳入缓存失效条件，前端 PUT 后热生效
- curator_log.py：进程内 ring buffer (maxlen=200)，所有 record/get
  操作内部兜异常，保证 logging 永远不会让 curator 跑挂
- curator.py 关键节点插桩：run_started / 自动转换计数 / 候选数 /
  LLM agent invoke / 解析结果 / archive 动作 / run complete
- routers/skills.py：GET/PUT /api/curator/config（写到
  skill_evolution.json + reset_app_config）+ GET /api/curator/logs

测试：
- tests/test_skill_evolution_runtime.py：overrides 往返、损坏 JSON
  容错、AppConfig 合并、ring buffer 线程安全、record 异常吞咽

杂项：
- .gitignore：忽略 .deer-flow/* 与 skills/* 等运行时目录
- uv.lock：跟随依赖锁更新
- 清理已废弃的 agent runtime 数据 SOUL.md

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-14 12:00:21 +08:00
董宏凯 8f4af5ece4 Merge branch 'dhk-2' into 'master' 
添加提示词权限

See merge request knowledge-base-bj/deerflow-server!12
 2026-05-14 03:52:27 +00:00
fengxiangdebaozi 2d9248889f Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-2 2026-05-14 11:51:51 +08:00
fengxiangdebaozi 804f37dcfa 提示词权限配置 2026-05-14 11:51:29 +08:00
董宏凯 bf98713a55 Merge branch 'dhk-2' into 'master' 
推荐问题接口添加

See merge request knowledge-base-bj/deerflow-server!11
 2026-05-14 03:08:14 +00:00
fengxiangdebaozi 2f2ba44c7c 添加推荐问题修改接口 2026-05-14 11:07:28 +08:00
fengxiangdebaozi 62292500ba Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-2 2026-05-14 10:52:08 +08:00
fengxiangdebaozi a7f1e89ce9 提示词修改 2026-05-14 10:51:29 +08:00
董宏凯 20c7e2841c Merge branch 'dhk-2' into 'master' 
提示词修改

See merge request knowledge-base-bj/deerflow-server!10
 2026-05-14 02:45:46 +00:00
fengxiangdebaozi c79f5c5a7a 样式修改 2026-05-14 10:42:37 +08:00
xu hd d3771ed31f Merge branch 'xuhd' into 'master' 
feat: skill 名字允许下划线分隔

See merge request knowledge-base-bj/deerflow-server!9
 2026-05-14 02:42:15 +00:00
xuhdandClaude Opus 4.7 230eec1baf feat: skill 名字允许下划线分隔 
放宽 skill 命名校验：除连字符外也接受下划线作为分隔符，首尾和连续
分隔符的限制扩展到 _ 与混合分隔（--、__、-_、_- 都拒绝）。前置
frontmatter 校验与存储层正则同步放宽。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-14 10:41:37 +08:00
xu hd 0bae393e07 Merge branch 'xuhd' into 'master' 
fix: /login/admin 自动把历史 admin 账户升级为 admin 角色

See merge request knowledge-base-bj/deerflow-server!8
 2026-05-14 02:28:42 +00:00
xuhdandClaude Opus 4.7 434cf40b36 fix: /login/admin 自动把历史 admin 账户升级为 admin 角色 
历史上以 username=admin 自动注册的账户曾被建成 system_role=user，
登录时按 username 修正一次，避免老库需要手工改表。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-14 10:25:24 +08:00
xu hd 7417a1c950 Merge branch 'xuhd' into 'master' 
feat: admin可删除内置专家

See merge request knowledge-base-bj/deerflow-server!7
 2026-05-14 02:18:33 +00:00
xu hd 799ccbe300 Merge branch 'xuhd' into 'master' 
feat: admin可编辑内置专家 + agent列表Tab分组

See merge request knowledge-base-bj/deerflow-server!6
 2026-05-14 02:06:42 +00:00
xuhdandClaude Opus 4.7 43044232bb feat: admin可删除内置专家 
复用 _get_editable_or_raise 分支，给 AgentStore 增加 delete_builtin，
路由按 edit_mode 决定走 delete 还是 delete_builtin；前端 agent-card
为 admin 显示内置 agent 的删除按钮。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-14 09:53:13 +08:00
董宏凯 4567db8836 Merge branch 'dhk-2' into 'master' 
页面结构调整

See merge request knowledge-base-bj/deerflow-server!5
 2026-05-14 01:43:08 +00:00
fengxiangdebaozi e286e59431 页面结构调整 2026-05-14 09:42:12 +08:00
fengxiangdebaozi 65e89a4248 样式修改 2026-05-14 09:36:45 +08:00
fengxiangdebaozi db63086c38 文档修改 2026-05-14 09:35:15 +08:00
xuhdandClaude Sonnet 4.6 2abdf28eba feat: admin可编辑内置专家 + agent列表Tab分组 
- /login/admin 登录时自动赋予 admin 角色，允许编辑内置专家
- agent列表页新增「全部」(内置+已发布) 和「自己的」两个Tab

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-13 23:16:18 +08:00
董宏凯 2476f04a26 Merge branch 'dhk-1' into 'master' 
接口地址填写

See merge request knowledge-base-bj/deerflow-server!4
 2026-05-13 14:29:34 +00:00
董宏凯 e458f1eab4 接口地址填写 2026-05-13 22:29:05 +08:00
fengxiangdebaozi b15b2649f8 文档修改 2026-05-13 22:22:59 +08:00
fengxiangdebaozi 4fce7ba09a Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server 2026-05-13 22:19:02 +08:00
fengxiangdebaozi 1a1369f115 代码提交 2026-05-13 22:18:55 +08:00
董宏凯 9434ffabdc Merge branch 'dhk-1' into 'master' 
Dhk 1

See merge request knowledge-base-bj/deerflow-server!3
 2026-05-13 14:17:47 +00:00
董宏凯 6aeb428796 Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1 2026-05-13 22:17:25 +08:00
董宏凯 8cabf32ebe 提交 2026-05-13 22:16:59 +08:00
董宏凯 85a98fcfd6 Merge branch 'dhk-v3' into 'master' 
ceshi1

See merge request knowledge-base-bj/deerflow-server!2
 2026-05-13 14:09:07 +00:00
董宏凯 aa1f81a30a ceshi1 2026-05-13 22:08:37 +08:00
fengxiangdebaozi 1c50c73aa4 样式修改 2026-05-13 21:41:13 +08:00
fengxiangdebaozi 6cc28c7edd Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server 2026-05-13 21:25:40 +08:00
fengxiangdebaozi 1c2cf768f8 样式修改 2026-05-13 21:25:29 +08:00
吉鑫升 481e718d86 Merge remote-tracking branch 'origin/master' 2026-05-13 21:02:27 +08:00
吉鑫升andClaude Opus 4.7 29f74afbf6 fix(scheduler): give every scheduled run its own throwaway thread 
All scheduled tasks for a user shared one scheduler thread, so each run
appended its messages to the same LangGraph checkpoint. Over time the
history blew past the model's input window and every task on that
account started failing with context-too-long.

_execute_task now mints a fresh thread_id per run and threads it through
ensure_thread_meta / snapshot / start_run / extract_*. The per-task
scheduler_thread_id column is left in place for backwards compatibility
but no longer drives the LLM call.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-13 20:58:23 +08:00