xuhd and Claude 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
fengxiangdebaozi
2f2ba44c7c
添加推荐问题修改接口
2026-05-14 11:07:28 +08:00
xuhd and Claude 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
xuhd and Claude 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
吉鑫升 and Claude 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
吉鑫升
31abad86d5
智能体配置
2026-05-13 20:04:06 +08:00
吉鑫升
a27206c543
Update local frontend and backend changes
2026-05-13 17:17:42 +08:00
吉鑫升
faca2c9a2d
Merge branch 'likun' into master
2026-05-13 17:02:22 +08:00
吉鑫升
aa034f8669
定时任务订阅模式
2026-05-13 14:59:27 +08:00
likun
b8926f00d7
新增用户意图确认功能
2026-05-13 14:36:44 +08:00
吉鑫升
cf2e4bdd9c
智能体分权
2026-05-13 11:36:17 +08:00
吉鑫升
e7a455f22e
Initial commit: deerflow-server (frontend-web + offline-backend-20260512)
2026-05-13 09:36:15 +08:00