Files
nexus/wiki/concepts/System-Prompt-Layering.md
2026-05-03 05:42:12 +08:00

36 lines
1.1 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
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 promptChat 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]]