mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-09-07 08:26:06 +00:00
5b801c0d3e
* refactor(file_io): update file I/O operations and truncation logic * refactor(memory): update file-based memory compaction logic
62 lines
No EOL
3.5 KiB
YAML
62 lines
No EOL
3.5 KiB
YAML
user_message: |
|
||
Memory Pre-compression Flush Cycle.
|
||
|
||
The current session is about to enter the automatic compression phase. Please capture persistent memory AND session reflections, then write them to disk.
|
||
|
||
Current date: {date}
|
||
Working directory: {working_dir}
|
||
|
||
# Task
|
||
Immediately store persistent memory and reflections to: {memory_dir}/YYYY-MM-DD.md
|
||
|
||
# Workflow
|
||
1. Extract and synthesize content from the current session:
|
||
- Persistent Memory: Facts, user profile updates, project states, and important events.
|
||
- Experience Reflection: Reusable thinking logic derived from user feedback, successful problem-solving strategies, mistakes made/pitfalls to avoid, and actionable insights for future interactions.
|
||
2. `read` {memory_dir}/YYYY-MM-DD.md (if the file doesn’t exist, an error message will be returned)
|
||
- If the file doesn’t exist, use `write` tool directly.
|
||
- If the file exists, intelligently merge new information with existing content, prefer using `edit` to update specific sections.
|
||
- Use `write` to overwrite the entire file only if substantial restructuring is required.
|
||
|
||
# Principles
|
||
- Intelligently merge new information with existing content:
|
||
- Categorize clearly (e.g., separate "Factual Memory" from "Reflections & Logic").
|
||
- Avoid duplicating already recorded information.
|
||
- Enrich existing entries with new details where relevant.
|
||
- Maintain chronological order wherever applicable.
|
||
- Always preserve timestamps and any date/time-related context.
|
||
- Add only genuinely new or meaningfully enriching information.
|
||
- Reflections MUST focus on forming reusable cognitive frameworks based on user feedback, aiming to improve future task execution.
|
||
- Keep entries concise yet complete.
|
||
- If there’s nothing to store or reflect on, respond with [SILENT].
|
||
|
||
user_message_zh: |
|
||
预压缩内存刷新轮次。
|
||
|
||
当前会话即将进入自动压缩阶段；请将持久化记忆与经验反思捕获并写入磁盘。
|
||
|
||
当前日期：{date}
|
||
工作目录：{working_dir}
|
||
|
||
# 任务
|
||
立即存储持久化记忆与反思（使用路径 {memory_dir}/YYYY-MM-DD.md）。
|
||
|
||
# 工作流程
|
||
1. 从当前会话中提取并综合两类内容：
|
||
- 持久化记忆：客观事实、用户信息更新、项目状态及重要事件。
|
||
- 经验反思：基于用户反馈形成的可复用思考逻辑、成功的问题解决策略、犯下的错误/应避免的陷阱，以及对未来交互有帮助的行动指南。
|
||
2. `read` {memory_dir}/YYYY-MM-DD.md（如文件不存在，会返回错误提示）
|
||
- 若文件不存在，直接使用 `write` 工具写入。
|
||
- 若文件已存在，智能合并新信息与现有内容，尽可能使用 `edit` 更新特定部分，仅在需要大幅重构时使用 `write` 覆盖整个文件。
|
||
|
||
# 原则
|
||
- 智能合并新信息与现有内容：
|
||
- 将内容进行清晰的分类（例如明确区分“事实记忆”与“反思与逻辑”）。
|
||
- 避免重复已记录的信息。
|
||
- 在相关时丰富现有条目的新细节。
|
||
- 在适用时保持时间顺序。
|
||
- 始终保留时间戳、日期和时间相关上下文。
|
||
- 仅添加真正新的或有丰富价值的信息。
|
||
- 反思内容必须侧重于根据用户反馈构建可复用的思维逻辑，以改善未来的任务执行。
|
||
- 保持条目简洁但完整。
|
||
- 若无任何新内容可存储或反思，请回复 [SILENT]。 |