Update nexus wiki content
This commit is contained in:
35
wiki/concepts/System-Prompt-Layering.md
Normal file
35
wiki/concepts/System-Prompt-Layering.md
Normal file
@@ -0,0 +1,35 @@
|
||||
---
|
||||
title: "System-Prompt-Layering"
|
||||
type: concept
|
||||
tags: []
|
||||
sources: [expose-hermes-agent-as-an-openai-compatible-api-for-any-frontend]
|
||||
last_updated: 2026-05-02
|
||||
---
|
||||
|
||||
## Definition
|
||||
System Prompt Layering 是一种前端提示词与 Agent 核心提示词分层叠加的机制,确保前端传入的提示词不会覆盖 Agent 原有的工具集和能力。
|
||||
|
||||
## Mechanism
|
||||
当通过 API Server 调用 Hermes Agent 时:
|
||||
1. **基础层**:Agent 核心系统提示词(包含完整工具集、Skills、记忆配置)
|
||||
2. **叠加层**:前端传入的 system prompt(Chat Completions 的 `system` 消息,或 Responses API 的 `instructions` 字段)
|
||||
3. **结果**:两层提示词叠加,Agent 保留全部原生能力
|
||||
|
||||
## Example
|
||||
```json
|
||||
// Chat Completions 请求
|
||||
{
|
||||
"model": "hermes-agent",
|
||||
"messages": [
|
||||
{"role": "system", "content": "你是一个友好的助手"}, // 叠加层
|
||||
{"role": "user", "content": "hello"}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
## Key Benefit
|
||||
前端可以定制对话风格(如角色扮演、语气调整),同时不影响 Agent 的核心工具能力。
|
||||
|
||||
## Related
|
||||
- [[OpenAI-Compatible-API]]
|
||||
- [[Conversation-State-Persistence]]
|
||||
Reference in New Issue
Block a user