linyuhang
/
PMFlow
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
61 Commits 4 Branches 0 Tags 6.1 GiB
Commit Graph

35 Commits

Author SHA1 Message Date
Yuuuu 38adaed6e6 Harden PMFlow context binding and world model snapshots 2026-04-07 09:36:40 +08:00
Yuuuu e372b88541 Upgrade mounted runtime context and plan mode 2026-04-05 17:08:36 +08:00
Yuuuu ecfaa7336c Implement mounted AI runtime and retire legacy Feishu brains 2026-04-05 01:46:06 +08:00
Yuuuu 7bdc9f3a65 Refine Feishu reply rendering and confirmation card layout 2026-04-03 09:30:01 +08:00
Yuuuu 5985f34a98 Refine PMFlow workflows and strengthen backend integrations 2026-04-01 17:13:07 +08:00
Yuuuu 9ab2e14838 Refine AI PMO grounding runtime and consultant flow 2026-04-01 08:50:39 +08:00
Yuuuu 6bb8354b8d Strengthen AI system charter and governance constraints 2026-03-31 14:23:55 +08:00
Yuuuu a01c451195 Revamp AI steward executive briefing workflows 2026-03-30 17:27:28 +08:00
Yuuuu 1b2b64d575 feat: add executive briefing center 2026-03-30 10:50:59 +08:00
Yuuuu d2672702bc Add consultant dispatch contract and Feishu logging 2026-03-28 09:06:12 +08:00
Yuuuu 0e87cec76d Centralize PMFlow workflow semantics and routing 2026-03-27 11:34:52 +08:00
Yuuuu 2860f11cec feat: auto materialize project signal sources 2026-03-26 17:36:31 +08:00
Yuuuu 8b85e19b54 Create signal sources from project analysis 2026-03-26 16:40:27 +08:00
Yuuuu 77a094e363 Add scoped trend controls to feedback center 2026-03-26 11:49:34 +08:00
Yuuuu 4da49c7fc4 Add unified feedback center and task learning loop 2026-03-26 10:50:16 +08:00
Yuuuu 4268d791ed Implement structured AI task breakdown and auto scheduling 2026-03-26 09:40:36 +08:00
Yuuuu 2e3de00c04 Unify AI PMO ingress flow and add draft confirmation execution ledger 2026-03-23 17:50:07 +08:00
Yuuuu 67b553688d Refactor AI PMO services and harden ingress error handling 2026-03-18 22:24:47 +08:00
Yuuuu 90b7e4301f Document front-end page updates 2026-03-15 21:30:28 +08:00
Yuuuu d59b1489a1 Review AI agent updates 2026-03-14 00:00:00 +08:00
Yuuuu 8dde37448e Update PMFlow docs and services 2026-03-13 01:19:35 +08:00
Yuuuu 5b7cf23aeb 完成 GLM5 信号计划与主题修复任务 2026-03-12 21:15:20 +08:00
Yuuuu d7cc718538 Add GLM-5 Planner 需求链路 2026-03-12 17:37:27 +08:00
Yuuuu fea6328ab2 Add 模型连通检测启动器}0987654321 2026-03-12 11:23:22 +08:00
Yuuuu a3a4ce61ff Update AI steward and audit logic 2026-03-12 09:10:36 +08:00
Yuuuu 2e358bc2a4 使用北京时间更新数据库写入」}Sorry seems odd maybe 2026-03-11 14:39:42 +08:00
Yuuuu 2fd932e395 制定双Agent能力提升与路由治理方案 2026-03-11 12:05:16 +08:00
Yuuuu 331e9109e2 执行全项目配置隐患与模型命名扫描清单 2026-03-11 10:07:51 +08:00
Yuuuu 93185369b9 refactor: modularize SSTC workspace panels and dialogs 2026-03-10 16:24:42 +08:00
Yuuuu 7f9571c3fa chore: snapshot current code before refactor 2026-03-10 15:18:23 +08:00
Yuuuu 16f30bc2c6 feat: complete PMFlow implementation 2026-02-27 08:56:49 +08:00
Yuuuu 319a422362 feat: 添加 LLM 服务按需启动功能 
新增功能:
- 后端新增 /ai/start API，支持启动本地 Ollama
- 后端改进 /ai/status API，返回提供商类型
- 前端看板页面添加启动/停止控制按钮
- 提供商感知 UI：云端 API 无需启动，本地 Ollama 可按需控制

用户体验:
- 云端模式：显示"云端服务已就绪"，直接可分析
- 本地模式：显示"启动 Ollama"按钮，按需启动节省内存
- 分析完成后：仅本地模式自动停止 Ollama

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-21 00:01:43 +08:00
Yuuuu 3376c224e3 refactor: 重构设置页面为 Linear.app 风格 
设计改进:
- 左侧窄边栏 (200px) + 小图标 (18px)
- 主内容区单列居中 (最大宽度 720px)
- Segmented Control 风格的供应商选择
- 统一表单控件规格 (36px 高度, 6px 圆角)
- 深靛蓝 (#4f46e5) 主色调
- 极简专业的视觉风格

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-20 23:41:30 +08:00
Yuuuu 689cf94d4b feat: 前端添加 LLM 配置设置页面 
新增功能:
- 前端设置页面可切换 LLM 提供商
- 支持 DeepSeek, OpenAI, Qwen, Ollama
- API 密钥配置界面
- 配置保存到 .env 文件

后端 API:
- GET /ai/config - 获取当前配置
- POST /ai/config - 更新配置

使用方式:
1. 打开前端 "⚙️ 设置" 页面
2. 选择 LLM 提供商
3. 输入 API 密钥（云端）或设置地址（本地）
4. 保存配置并重启后端

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-20 22:48:38 +08:00
Yuuuu 0981acb06c Initial commit: Neural Sync - AI-native project management platform 
Features:
- Signal monitoring with AI strategic analysis
- Experiment management with score tracking
- Context knowledge nodes with RAG
- Multi-model voting for high-impact signals
- Ollama integration for local LLM

Tech stack:
- Backend: FastAPI + SQLAlchemy + PostgreSQL
- Frontend: Vue 3 + Naive UI + TypeScript
- AI: Ollama (llama3, nomic-embed-text)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-20 18:06:39 +08:00