ishenwei/nexus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Auto-sync: 2026-04-21 17:12

Browse Source
This commit is contained in:
weishen
2026-04-21 17:12:45 +08:00
parent 914c8f6925
commit 0fe7ba237f
1888 changed files with 220 additions and 68174 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
wiki/concepts/Context-Passing.md
View File

@@ -1,41 +0,0 @@
---
title: "Context Passing"
type: concept
tags: [multi-agent, workflow, communication]
last_updated: 2026-04-21
---
## Definition
上下文传递（Context Passing）是一种多智能体通信模式，在智能体之间传递完整的上下文信息，而非摘要或压缩版本。
## Core Principle
**"Copy-paste agent outputs between steps — don't summarize, use the full output"**
## Problem It Solves
- 摘要会丢失关键细节
- 压缩可能遗漏重要上下文
- 智能体不具备共享记忆
## Best Practices
1. **完整复制**：将上一智能体的输出完整粘贴到下一智能体的输入
2. **不要摘要**：即使很长也要完整传递
3. **不要解释**：让接收智能体自己解析和处理完整信息
4. **包含所有内容**：原始输出、元数据、证据、决策理由等
## Example
在 Multi-Agent Workflow: Startup MVP 中：
```
Sprint Prioritizer 输出 → [完整粘贴] → Backend Architect 输入
UX Researcher 输出 → [完整粘贴] → Backend Architect 输入
Backend Architect 输出 → [完整粘贴] → Frontend Developer 输入
```
## Trade-offs
- **优点**：最大化信息保留，便于接收智能体做出完整判断
- **缺点**：消耗更多上下文窗口，可能需要更长的处理时间
## Related Concepts
- [[Sequential Handoffs]]：顺序交接模式
- [[Parallel Work]]：并行工作模式
- [[Quality Gates]]：质量门控
- [[Multi-Agent Team]]：多智能体团队