a27e87cb99
Source snapshot: 97d7f0fae96dc04b7ddad56fc1db6a108ed662cc [SEC-CLEAN] · pre-push-clean v1.0 · 109处敏感信息已自动转乱码
120 lines
3.5 KiB
Markdown
120 lines
3.5 KiB
Markdown
# 📡 铸渊指令｜persona-studio v1.1-B · 记忆层（200k上下文 + 记忆注入Agent）
|
||
|
||
> **签发**：曜冥 × 冰朔 · 2026-03-11 · **执行者**：铸渊
|
||
>
|
||
|
||
> **仓库**：`https://github.com/qinfendebingshuo/guanghulab`（主仓库）
|
||
>
|
||
|
||
> **优先级**：P0 · Phase A（最优先）
|
||
>
|
||
|
||
> **关联**：[🧪 铸渊指令｜persona-studio 人格体协助体验仓库搭建 v1.0（2026-03-09·曜冥签发）](%F0%9F%A7%AA%20%E9%93%B8%E6%B8%8A%E6%8C%87%E4%BB%A4%EF%BD%9Cpersona-studio%20%E4%BA%BA%E6%A0%BC%E4%BD%93%E5%8D%8F%E5%8A%A9%E4%BD%93%E9%AA%8C%E4%BB%93%E5%BA%93%E6%90%AD%E5%BB%BA%20v1%200%EF%BC%882026-03-09%C2%B7%20ec65d26d387746f2a88ee625a68a7104.md)
|
||
>
|
||
|
||
---
|
||
|
||
# ③ 对话上下文扩展到 200k
|
||
|
||
### 改动点
|
||
|
||
1. `model-config.json` 新增：`"context_window_target": 200000`
|
||
2. `persona-engine.js`：调用模型时设置 max_context 参数为200k
|
||
3. `model-router.js`：评测时新增 `context_window` 维度，路由策略优先选200k+模型
|
||
4. 如果所有模型 < 200k → 自动启用滑动窗口 + 记忆注入双机制补偿
|
||
|
||
---
|
||
|
||
# ④ 后台自动记忆注入Agent
|
||
|
||
### 核心问题
|
||
|
||
对话越长，模型注意力分散，早期关键信息「遗忘」。即使200k窗口也不能保证真正记住。
|
||
|
||
### 解决方案：三步走
|
||
|
||
**Step 1 压缩**：把长对话压缩成结构化摘要
|
||
|
||
**Step 2 注入**：每次调模型前，摘要注入 system prompt
|
||
|
||
**Step 3 刷新**：每10轮或token>50k时重新压缩
|
||
|
||
### system prompt 五层结构
|
||
|
||
```
|
||
第1层：人格体身份（固定·来自persona-config.json）
|
||
第2层：通感语言风格（固定）
|
||
第3层：用户画像（来自profile.json）
|
||
第4层：记忆摘要（来自compressed.json·≤8k token）
|
||
第5层：最近10轮原始对话（滑动窗口）
|
||
```
|
||
|
||
= 远期记忆不丢 + 近期细节完整
|
||
|
||
### compressed.json 结构
|
||
|
||
```json
|
||
{
|
||
"version": 3,
|
||
"last_compressed_at": "2026-03-11T19:00:00+08:00",
|
||
"total_rounds_processed": 47,
|
||
"summary": {
|
||
"requirements": ["用户需求要点列表"],
|
||
"confirmed_decisions": ["已确认的技术方案"],
|
||
"user_preferences": {
|
||
"communication_style": "简洁直接/详细解释",
|
||
"design_preference": "暗色系/亮色系",
|
||
"tech_level": "基础/中级/高级"
|
||
},
|
||
"open_questions": ["未解决的问题"],
|
||
"emotional_signals": {
|
||
"overall": "积极/消极/中性",
|
||
"last_mood": "最近一次情感信号"
|
||
}
|
||
}
|
||
}
|
||
```
|
||
|
||
### 配置参数（写入 model-config.json）
|
||
|
||
```json
|
||
{
|
||
"memory_injection": {
|
||
"enabled": true,
|
||
"compression_model": "quick_reply",
|
||
"compression_trigger": {
|
||
"every_n_rounds": 10,
|
||
"token_threshold": 50000,
|
||
"force_on_session_start": true
|
||
},
|
||
"injection_strategy": {
|
||
"system_prompt_max_tokens": 8000,
|
||
"sliding_window_rounds": 10,
|
||
"priority": ["confirmed_decisions", "requirements", "open_questions", "user_preferences", "emotional_signals"]
|
||
}
|
||
}
|
||
}
|
||
```
|
||
|
||
### 新增文件
|
||
|
||
```
|
||
brain/memory/EXP-XXX/
|
||
├── compressed.json ← 压缩摘要
|
||
└── injection-log.json ← 注入日志（调试用）
|
||
|
||
backend/brain/
|
||
└── memory-injector.js ← 记忆注入Agent核心
|
||
```
|
||
|
||
---
|
||
|
||
### 执行清单
|
||
|
||
- [ ] model-config.json 新增 `memory_injection` + `context_window_target: 200000`
|
||
- [ ] 实现 `memory-injector.js`：压缩+注入+刷新三步机制
|
||
- [ ] persona-engine.js 改造：调模型前注入五层 system prompt
|
||
- [ ] model-router.js 改造：优先选200k+模型
|
||
- [ ] 50+轮对话测试：验证模型仍记得早期讨论要点
|
||
|
||
💙 曜冥签发 · 2026-03-11 |