admin/aiagent
1
0
Fork 0
Code Issues 25 Pull Requests Actions Packages Projects Releases Wiki Activity
77 Commits 3 Branches 0 Tags
dca60207301b4ca6947d685fb1487aa149618da5
Commit Graph

7 Commits

Author SHA1 Message Date
renjianbo
02d7cf8f62 feat: add Goal/Task data models, service layer, and API routes (Phase 1) 
Main Agent 数字员工工厂基础设施：
- 新增 Goal 和 Task SQLAlchemy 数据模型
- Agent 模型新增 agent_type / input_schema / output_schema
- Execution 模型新增 goal_id 关联
- 新增 Goal/Task CRUD 服务层（含依赖检查、任务树、进度计算）
- 新增 /api/v1/goals (9端点) + /api/v1/tasks (8端点)
- 数据库迁移 013_add_goals_tasks

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-05-08 19:50:16 +08:00
renjianbo
9054f42cda feat: Agent间知识共享 — 全局知识池（去重+置信度+过期） 
- GlobalKnowledge 模型新增 confidence 和 expires_at 字段
- save_global_knowledge 增加 MD5 去重、置信度评分、TTL过期
- _global_knowledge_search 增加过期过滤、置信度优先排序
- run()/run_stream() 所有完成路径补齐知识提取调用
- 新增 Alembic 迁移 010_add_global_knowledge

Cl  oses #9

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-05-06 22:04:56 +08:00
renjianbo
eabf90c496 feat: add AI学习助手 agent (KG+RAG ideal) and renshenguo feishu bot 
- Add AI学习助手 agent creation script with all 39 tools, 3-layer KG+RAG memory
- Add renshenguo (人参果) feishu bot integration (app_service + ws_handler)
- Register renshenguo WS client in main.py startup
- Add RENSHENGUO_APP_ID / RENSHENGUO_APP_SECRET / RENSHENGUO_AGENT_ID config
- Reorganize docs from root into docs/ subdirectories
- Move startup scripts to scripts/startup/
- Various backend optimizations and tool improvements

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-05-06 01:37:13 +08:00
renjianbo
592bca4f39 feat: Phase 4 - LLM/Agent fallback chain, cross-agent knowledge sharing, async agent execution 
- 4.1 Fallback chain: LLM fallback_llm config in AgentLLMConfig, retry with alternate model on API failure; Agent fallback_agent in DAG nodes
- 4.2 Knowledge sharing: GlobalKnowledge model with embedding-based semantic search, auto-extraction of tool names as tags after execution
- 4.3 Async execution: execute_agent_task fully implemented with AgentRuntime, scheduler dual-path for workflow/non-workflow agents

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-05-05 00:27:54 +08:00
renjianbo
b8b01254ca feat: Phase 1 - output quality verification + node-level auto-retry 
- Add enterprise_review tool (35th builtin) for LLM-based quality assessment
- Add evaluator workflow node type for quality gating in DAG
- Add AgentRuntime built-in self-review with auto-correction loop
- Rewrite error_handler node from stub to real retry mechanism
- Add engine-level per-node retry with configurable max_retries/delay/on_exhausted
- Add AgentExtension model for extension tracking
- Enhance validation in agent_create_tool and tool_register_tool
- Update 全能助手 system prompt with self-evolution workflow
- Docs: 缺失能力.md and 解决缺失能力计划.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-05-04 22:05:28 +08:00
renjianbo
0608161c82 feat: 完善企业场景多线路由与执行稳定性 
补齐平台模板与场景 DSL、预算控制、执行看板和企业场景脚本，增强 Windows 启动/迁移与前端代理和聊天会话记忆，修复执行创建阶段 500 与异步链路排障体验。

Made-with: Cursor
 2026-04-09 21:58:53 +08:00
rjb
6674060f2f 第一次提交 2026-01-19 00:09:36 +08:00