Files

root 29d15707f5 docs: 重构为 docs/zh/ + docs/en/ 子文件夹结构

- 拆分为 docs/zh/(中文) 和 docs/en/(英文)
- README 索引对应语言子文件夹
- 保留所有文档内容

2026-04-14 13:25:53 +08:00

4.8 KiB

Raw Blame History

TrulyMEM Working Memory Chain Mechanism

Overview

TrulyMEM maintains conversation continuity through the working memory chain mechanism. Since there's no traditional message history array, the graph database is the only memory carrier, making the working memory chain the key mechanism for maintaining conversation context.

Core Problems

Traditional AI chat systems have these problems when handling continuous tasks:

No working memory chain: AI cannot remember the current task status being processed
Task context lost: When a topic is interrupted, AI cannot recover the previous task
Lack of task state management: No clear marking of task completion status

Problem Example

User: Let's play idiom chain! I'll start with 为所欲为
AI: Okay! My turn: 为虎作伥!

User: Nagato Yuki  (topic interrupted)
AI: (discusses Nagato Yuki)

User: About the idiom chain just now, I don't know how to connect to your idiom
AI: [Guessing] It seems we haven't played an idiom chain game before...

Problem: AI completely forgot the previous idiom chain game.

Solution

Dedicated Tools

The system provides 4 dedicated task tools:

Tool	Function	Use Case
`task_create`	Create task node	Start new task
`task_set_state`	Set task state	Update in_progress/completed/paused/cancelled
`task_delete`	Delete task	Clean up completed task
`task_link_info`	Link info node	Connect task with specific information

Task States

in_progress: Task is executing
completed: Task completed successfully
paused: Task interrupted, can be resumed
cancelled: Task cancelled

Usage Flow

Must Execute Per Turn

Query persona graph (highest priority)

Call memory_recall
Parameters: {"query_intent": "AI,persona,role,character,tone", "depth": 2}

Query working memory chain

Call memory_recall
Parameters: {"query_intent": "TaskNode,working_memory,task_chain", "depth": 2}

Generate reply based on context
Update working memory chain (if necessary)

Complete Example: Idiom Chain Game

Turn 1: User starts game

User: Let's play idiom chain! I'll start with 为所欲为

AI Actions:
1. Query persona graph → Get current persona (e.g., catgirl)
2. Query working memory chain → No active task
3. Record game state:
   Call memory_commit
   Parameters: {
     "triplets": [
       {"subject": "idiom_chain_current", "relation": "content", "object": "为所欲为"},
       {"subject": "idiom_chain_current", "relation": "game", "object": "idiom_chain"}
     ]
   }
4. Create task node:
   Call task_create
   Parameters: {
     "task_id": "Task_idiom_chain",
     "description": "Idiom chain game, current idiom: 为所欲为",
     "info_nodes": ["idiom_chain_current"]
   }
5. Reply: "Okay~! My turn: 为虎作伥~!"

Turn 2: Topic interrupted

User: Nagato Yuki

AI Actions:
1. Query persona graph → Get current persona (catgirl)
2. Query working memory chain → Found Task_idiom_chain status "in_progress"
3. Pause task:
   Call task_set_state
   Parameters: {"task_id": "Task_idiom_chain", "state": "paused"}
4. Create new task:
   Call task_create
   Parameters: {"task_id": "Task_nagato_yuki", "description": "Discuss Nagato Yuki"}
5. Reply about Nagato Yuki

Turn 3: User asks to continue game

User: About the idiom chain just now, I don't know how to connect to your idiom

AI Actions:
1. Query persona graph → Get current persona (catgirl)
2. Query working memory chain → Found Task_idiom_chain status "paused"
3. Resume task:
   Call task_set_state
   Parameters: {"task_id": "Task_idiom_chain", "state": "in_progress"}
4. Query info node → Get current idiom "为虎作伥"
5. Reply: "Okay~! The last idiom was '为虎作伥', your turn: 伥鬼害人~!"

API Reference

task_create

Create task node to track continuous tasks.

{
  "task_id": "Task_idiom_chain",
  "description": "Task overview",
  "info_nodes": ["associated info node names"]
}

task_set_state

Set task state.

{
  "task_id": "Task_idiom_chain",
  "state": "in_progress"  // in_progress/completed/paused/cancelled
}

task_delete

Delete task node.

{
  "task_id": "Task_idiom_chain",
  "delete_info_nodes": true  // whether to delete associated info nodes
}

task_link_info

Associate info nodes to task.

{
  "task_id": "Task_idiom_chain",
  "info_node_names": ["idiom_chain_current", "idiom_chain_last"]
}

Notes

Persona graph has highest priority: Must query persona graph first each turn
Working memory chain is the only context carrier: No traditional message history
Task state must be updated timely: Ensure correct state transitions
Use dedicated tools: Prefer task_* tools over memory_commit for task-related operations

4.8 KiB Raw Blame History