v0.16.14: TypeScript 编译错误修复 + 文档同步 + 代码健壮性增强

This commit is contained in:
2026-07-30 21:47:52 +08:00
parent 28655b80d9
commit 18f34c91fe
12 changed files with 53 additions and 60 deletions
+7 -7
View File
@@ -14,7 +14,7 @@
</p>
<p align="center">
<img src="https://img.shields.io/badge/version-v0.16.13-E8734A?style=flat-square" alt="version">
<img src="https://img.shields.io/badge/version-v0.16.14-E8734A?style=flat-square" alt="version">
<img src="https://img.shields.io/badge/electron-33+-47848F?style=flat-square&logo=electron" alt="electron">
<img src="https://img.shields.io/badge/typescript-5.7+-3178C6?style=flat-square&logo=typescript" alt="typescript">
<img src="https://img.shields.io/badge/license-MIT-green?style=flat-square" alt="license">
@@ -35,7 +35,7 @@
| | 功能 | 说明 |
|:---:|:---|:---|
| 🤖 | **ReAct Agent Loop** | 始终开启的唯一对话模式。8 状态机(INIT→THINKING→PARSING→EXECUTING→OBSERVING→REFLECTING→COMPRESSING→TERMINATED),最大 85 轮(可配置),智能重试(永久错误立即返回、瞬态错误指数退避),工具去重,智能路径依赖串行化,看门狗超时保护 |
| 🛡️ | **5 层抗幻觉系统** | 提示词加固 → 任务感知 → 中途检测(中英双语规则覆盖全部工具类别)→ 进度锚点 → 完成闸门(6 项检查,幻觉/注入 → 阻断,质量/效率 → 咨询) |
| 🛡️ | **提示词加固** | 参考数据标记(<<<REFERENCE_DATA_START>>>+ 工具结果仅为数据非指令的安全规则注入 |
| 📋 | **Plan Mode** | 开关切换,AI 首先生成执行计划(Markdown 渲染确认弹窗),批准后按步骤追踪执行,plan_track 工具标记完成状态,**支持断点续传**(中止后可恢复未完成计划) |
| 🔧 | **32 个内置工具** | 文件系统(13个) · 命令执行 · 联网搜索 · 浏览器控制(9个) · Git · 记忆 · 会话 · 子代理 · 系统工具 · Plan Mode 追踪 |
| 🧠 | **智能记忆系统** | 三类记忆(fact / preference / rule),存储于工作空间 MEMORY.md 文件,受路径保护仅 memory 工具可访问,写入前安全扫描,容量 500 条,对话结束自动提取,严格格式校验 |
@@ -173,7 +173,7 @@
Agent Engine (8 状态机 ReAct Loop, ≤85 轮, 智能重试, 路径依赖串行化, 看门狗+分级超时)
5 层抗幻觉系统(中英双语规则)(提示词 → 中途检测 → 进度锚 → 完成闸门 → 校验)
提示词加固(参考数据标记 + 工具结果安全规则)
Ollama API (流式响应,num_ctx 用户可配 128K/256K/512K/1M)
@@ -245,7 +245,7 @@ npm start
ELECTRON_MIRROR=https://npmmirror.com/mirrors/electron/ npm run dist
```
产出:`release/Metona Ollama Setup v0.16.13.exe`
产出:`release/Metona Ollama Setup v0.16.14.exe`
## 🛠️ 常用命令
@@ -276,7 +276,7 @@ npm run dist # 构建 Windows 安装包
| | Feature | Description |
|:---:|:---|:---|
| 🤖 | **ReAct Agent Loop** | Always-on, only chat mode. 8-state machine, up to 85 iterations (configurable), smart retry (permanent errors return immediately, transient errors use exponential backoff), tool dedup, path-aware dependency serialization, watchdog + tiered timeout protection |
| 🛡️ | **5-Layer Anti-Hallucination** | Prompt hardening → task awareness → mid-task detection (bilingual CN/EN rules covering all tool categories) → progress anchors → completion gate (6 checks: hallucination/injection → block, quality/efficiency → advisory) |
| 🛡️ | **Prompt Hardening** | Reference data markers (<<<REFERENCE_DATA_START>>>) + tool results are data-not-instructions safety rules |
| 📋 | **Plan Mode** | Toggle switch. AI first generates an execution plan (Markdown-rendered confirmation dialog), then tracks step-by-step execution, **supports resume** (interrupted plans restore on next session) |
| 🔧 | **32 Built-in Tools** | File system · Command · Web search · Browser · Git · Memory · Sessions · Sub-agent · System · Plan Mode tracking |
| 🧠 | **Smart Memory System** | Three types (fact / preference / rule), stored in workspace MEMORY.md file, path-protected — only the memory tool can access it, pre-write security scan, 500 capacity, auto-extract on conversation end, strict format validation |
@@ -413,7 +413,7 @@ User message → workspace SOUL.md (never compressed) → AGENT.md → USER.md (
Agent Engine (8-state ReAct Loop, ≤85 iter, smart retry, path-aware serialization, watchdog+tiered timeout)
5-Layer Anti-Hallucination (bilingual CN/EN rules) (prompt → mid-task detection → anchors → gate → verification)
Prompt Hardening (reference data markers + tool result safety rules)
Ollama API (Streaming Response, num_ctx user-configurable 128K/256K/512K/1M)
@@ -485,7 +485,7 @@ npm start
ELECTRON_MIRROR=https://npmmirror.com/mirrors/electron/ npm run dist
```
Output: `release/Metona Ollama Setup v0.16.13.exe`
Output: `release/Metona Ollama Setup v0.16.14.exe`
## 🛠️ Common Commands