docs: 更新 README v1.1 特性 + 帮助面板实际内容
- README: 新增 SOUL.md/技能v1.1/上下文自动检测/系统提示词卡片特性 - README: 架构图加入 SOUL.md 不可压缩层 + 技能匹配层 - helpModal: 新增 SOUL.md 自定义人格、技能v1.1、Token实时监控说明 - helpModal: 更新聊天功能、上下文长度自动检测描述
This commit is contained in:
@@ -37,14 +37,17 @@
|
||||
| 🤖 | **ReAct Agent Loop** | Thought → Action → Observation → Reflection 完整循环,最大 85 轮(可配置),自动重试 2 次,工具去重,并行/链式执行 |
|
||||
| 🔧 | **38 个内置工具** | 文件系统 · 命令执行 · 联网搜索 · 浏览器控制 · Git · 记忆 · 技能 · 会话 · 子代理 |
|
||||
| 🧠 | **智能记忆系统** | 三类记忆(fact / preference / rule),FTS5 全文搜索 + 向量语义搜索,写入前安全扫描,容量 500 条,90 天衰减 |
|
||||
| 📋 | **SOUL.md 自定义人格** | 工作空间下创建 SOUL.md 定义 AI 身份与行为准则,每次发送自动注入为最高优先级系统提示词,永远不可压缩 |
|
||||
| 🎯 | **技能自动生成 v1.1** | 工具调用链自动提取 → 语义匹配 → 参数自优化 → 未使用衰减 → 技能链合并,越用越精准 |
|
||||
| 🌐 | **MCP 协议扩展** | JSON-RPC 2.0 over stdio,动态工具发现,Shadowing 防护 |
|
||||
| 🔍 | **三引擎联网搜索** | Bing + 百度 + Google 聚合,web_search → web_fetch 链式抓取 |
|
||||
| 🌏 | **浏览器控制** | 打开网页 · 截图 · 执行 JS · 提取内容 · 点击 · 输入 · 滚动 · 关闭 |
|
||||
| 🖥️ | **工作空间面板** | 终端(实时流式输出)+ 文件浏览器,命令安全检查 |
|
||||
| 📊 | **技能自动生成** | 从成功的工具调用链自动提取可复用技能(≥2 步),Level 0 摘要 |
|
||||
| 🗜️ | **上下文管理** | 滑动窗口 + LLM 摘要压缩(50% 自动触发)+ /compress 手动触发 |
|
||||
| 🔢 | **上下文长度自动检测** | 切换模型时自动从 model_info 获取实际支持的上下文长度,无需手动配置 |
|
||||
| 🗜️ | **智能上下文管理** | 滑动窗口 + Token 自动校准 + 消息重要性评分 + LLM 结构化 JSON 压缩 |
|
||||
| 👥 | **子代理委派** | spawn_task 工具,独立上下文 + 超时保护 |
|
||||
| 📈 | **Token 仪表盘** | 全局 + 会话统计,消耗趋势图,2 秒刷新 |
|
||||
| 📈 | **Token 仪表盘** | 全局 + 会话统计,消耗趋势柱状图,2 秒刷新,输入/输出分色 |
|
||||
| 📋 | **系统提示词卡片** | 每条 AI 回复顶部折叠卡片,点击查看实际发送给模型的完整上下文 |
|
||||
| 🎨 | **暖色调 UI** | 奶白 `#FAF7F2` + 珊瑚橙 `#E8734A`,长时间使用不疲劳 |
|
||||
| 🔔 | **系统托盘** | 原生托盘集成 |
|
||||
| 🔐 | **AES-256-GCM** | 数据加密支持 |
|
||||
@@ -150,11 +153,15 @@
|
||||
## 🏗️ 架构
|
||||
|
||||
```
|
||||
用户消息 → Agent Engine (ReAct Loop, ≤85轮)
|
||||
用户消息 → 扫描工作空间 SOUL.md(不可压缩层)
|
||||
↓
|
||||
Agent Engine (ReAct Loop, ≤85轮)
|
||||
↓
|
||||
记忆检索 (FTS5 + 向量语义搜索) → 上下文注入
|
||||
↓
|
||||
Ollama API (流式响应)
|
||||
技能匹配 (语义匹配 + 参数自优化 + 衰减 + 链合并)
|
||||
↓
|
||||
Ollama API (流式响应,num_ctx 自动检测)
|
||||
↓
|
||||
Tool Registry (38 内置 + MCP 动态)
|
||||
↓
|
||||
@@ -258,14 +265,17 @@ npm run dist # 构建 Windows 安装包
|
||||
| 🤖 | **ReAct Agent Loop** | Full Thought → Action → Observation → Reflection cycle, up to 85 iterations (configurable), auto-retry 2 times, tool dedup, parallel/chain execution |
|
||||
| 🔧 | **38 Built-in Tools** | File system · Command · Web search · Browser · Git · Memory · Skills · Sessions · Sub-agent |
|
||||
| 🧠 | **Smart Memory System** | Three types (fact / preference / rule), FTS5 + vector semantic search, pre-write security scan, 500 capacity, 90-day decay |
|
||||
| 📋 | **SOUL.md Custom Persona** | Define AI identity & rules in workspace SOUL.md, auto-injected as highest-priority system prompt, never compressed |
|
||||
| 🎯 | **Auto Skill Generation v1.1** | Tool chain extraction → semantic matching → parameter self-optimization → decay → chain merging |
|
||||
| 🌐 | **MCP Protocol Extension** | JSON-RPC 2.0 over stdio, dynamic tool discovery, Shadowing protection |
|
||||
| 🔍 | **Triple-engine Web Search** | Bing + Baidu + Google aggregation, web_search → web_fetch chain |
|
||||
| 🌏 | **Browser Control** | Open pages · Screenshot · JS execution · Content extraction · Click · Type · Scroll · Close |
|
||||
| 🖥️ | **Workspace Panel** | Terminal (real-time streaming) + file browser, command security checks |
|
||||
| 📊 | **Auto Skill Generation** | Extracts reusable skills from successful tool call chains (≥2 steps), Level 0 summaries |
|
||||
| 🗜️ | **Context Management** | Sliding window + LLM summary compression (auto at 50%) + /compress manual trigger |
|
||||
| 🔢 | **Auto Context Length Detection** | Reads actual context_length from model metadata on model switch — no manual config needed |
|
||||
| 🗜️ | **Smart Context Manager** | Sliding window + Token auto-calibration + message importance scoring + LLM structured JSON compression |
|
||||
| 👥 | **Sub-agent Delegation** | spawn_task tool, isolated context + timeout protection |
|
||||
| 📈 | **Token Dashboard** | Global + session stats, consumption trend chart, 2s refresh |
|
||||
| 📈 | **Token Dashboard** | Global + session stats, consumption trend bar chart, 2s refresh, input/output color-coded |
|
||||
| 📋 | **System Prompt Card** | Collapsible card atop each AI reply — click to inspect the full context sent to the model |
|
||||
| 🎨 | **Warm-tone UI** | Cream `#FAF7F2` + coral `#E8734A`, fatigue-free for extended use |
|
||||
| 🔔 | **System Tray** | Native tray integration |
|
||||
| 🔐 | **AES-256-GCM** | Data encryption support |
|
||||
|
||||
Reference in New Issue
Block a user