remembering-conversations

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Remembering Conversations

对话记忆使用指南

Core principle: Search before reinventing. Searching costs nothing; reinventing or repeating mistakes costs everything.

核心原则： 先搜索再创新。搜索无需成本，重复造轮子或重蹈覆辙代价高昂。

Mandatory: Use the Search Agent

强制要求：使用搜索Agent

YOU MUST dispatch the search-conversations agent for any historical search.

Announce: "Dispatching search agent to find [topic]."

Then use the Task tool with

subagent_type: "search-conversations"

Task tool:
  description: "Search past conversations for [topic]"
  prompt: "Search for [specific query or topic]. Focus on [what you're looking for - e.g., decisions, patterns, gotchas, code examples]."
  subagent_type: "search-conversations"

The agent will:

Search with the
```
search
```
tool
Read top 2-5 results with the
```
show
```
tool
Synthesize findings (200-1000 words)
Return actionable insights + sources

Saves 50-100x context vs. loading raw conversations.

任何历史搜索都必须调度search-conversations agent。

请告知：“正在调度搜索Agent以查找[主题]。”

然后使用Task工具，参数

subagent_type: "search-conversations"

：

Task tool:
  description: "Search past conversations for [topic]"
  prompt: "Search for [specific query or topic]. Focus on [what you're looking for - e.g., decisions, patterns, gotchas, code examples]."
  subagent_type: "search-conversations"

该Agent将：

使用
```
search
```
工具进行搜索
使用
```
show
```
工具查看排名前2-5的结果
整合发现内容（200-1000词）
返回可执行的见解+来源

相比加载原始对话，可节省50-100倍的上下文空间。

When to Use

使用场景

You often get value out of consulting your episodic memory once you understand what you're being asked. Search memory in these situations:

After understanding the task:

User asks "how should I..." or "what's the best approach..."
You've explored current codebase and need to make architectural decisions
User asks for implementation approach after describing what they want

When you're stuck:

You've investigated a problem and can't find the solution
Facing a complex problem without obvious solution in current code
Need to follow an unfamiliar workflow or process

When historical signals are present:

User says "last time", "before", "we discussed", "you implemented"
User asks "why did we...", "what was the reason..."
User says "do you remember...", "what do we know about..."

Don't search first:

For current codebase structure (use Grep/Read to explore first)
For info in current conversation
Before understanding what you're being asked to do

当你理解用户需求后，参考对话记忆通常能带来价值。在以下场景中搜索记忆：

理解任务后：

用户询问“我应该如何...”或“最佳方法是什么...”
你已探索当前代码库，需要做出架构决策
用户描述需求后询问实现方案

陷入困境时：

你已调查问题但无法找到解决方案
面对复杂问题，当前代码中没有明显的解决方法
需要遵循不熟悉的工作流程或流程规范

存在历史信号时：

用户提到“上次”、“之前”、“我们讨论过”、“你实现过”
用户询问“我们为什么要...”、“原因是什么...”
用户说“你还记得...吗”、“我们对...了解多少”

无需优先搜索的场景：

当前代码库结构（先使用Grep/Read工具探索）
当前对话中的信息
尚未理解用户需求时

Direct Tool Access (Discouraged)

直接使用工具（不推荐）

You CAN use MCP tools directly, but DON'T:

mcp__plugin_episodic-memory_episodic-memory__search

mcp__plugin_episodic-memory_episodic-memory__show

Using these directly wastes your context window. Always dispatch the agent instead.

See MCP-TOOLS.md for complete API reference if needed for advanced usage.

你可以直接使用MCP工具，但请勿使用：

mcp__plugin_episodic-memory_episodic-memory__search

mcp__plugin_episodic-memory_episodic-memory__show

直接使用这些工具会浪费你的上下文窗口。请始终调度Agent来完成。

如需高级用法，请查看MCP-TOOLS.md获取完整API参考。