memory-tasks

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Memory Tasks

基于Basic Memory的任务管理

Manage work-in-progress using Basic Memory's schema system. Tasks are just notes with

type: Task

— they live in the knowledge graph, validate against a schema, and survive context compaction.

使用Basic Memory的schema系统管理进行中的工作。任务本质是标记为

type: Task

的笔记——它们存储在知识图谱中，可通过schema验证，且能在上下文压缩后留存。

When to Use

适用场景

Starting multi-step work (3+ steps, or anything that might outlast the context window)
After compaction/restart — search for active tasks to resume
Pre-compaction flush — update all active tasks with current state
On demand — user asks to create, check, or manage tasks

启动多步骤工作（3个及以上步骤，或任何可能超出上下文窗口的工作）
压缩/重启后——搜索活跃任务以恢复工作
压缩前同步——更新所有活跃任务的当前状态
按需操作——用户要求创建、检查或管理任务

Task Schema

任务Schema

Tasks use the BM schema system (SPEC-SCHEMA). The schema note lives at

memory/schema/Task.md

yaml

---
title: Task
type: schema
entity: Task
version: 1
schema:
  description: string, what needs to be done
  status?(enum): [active, blocked, done, abandoned], current state
  assigned_to?: string, who is working on this
  steps?(array): string, ordered steps to complete
  current_step?: integer, which step number we're on (1-indexed)
  context?: string, key context needed to resume after memory loss
  started?: string, when work began
  completed?: string, when work finished
  blockers?(array): string, what's preventing progress
  parent_task?: Task, parent task if this is a subtask
settings:
  validation: warn
---

任务采用BM的schema系统（SPEC-SCHEMA）。Schema笔记存储在

memory/schema/Task.md

：

yaml

---
title: Task
type: schema
entity: Task
version: 1
schema:
  description: string, what needs to be done
  status?(enum): [active, blocked, done, abandoned], current state
  assigned_to?: string, who is working on this
  steps?(array): string, ordered steps to complete
  current_step?: integer, which step number we're on (1-indexed)
  context?: string, key context needed to resume after memory loss
  started?: string, when work began
  completed?: string, when work finished
  blockers?(array): string, what's preventing progress
  parent_task?: Task, parent task if this is a subtask
settings:
  validation: warn
---

Creating a Task

创建任务

When work qualifies, create a task note. Use

write_note

with

note_type="Task"

and put queryable fields in

metadata

python

write_note(
  title="Descriptive task name",
  directory="tasks",
  note_type="Task",
  metadata={
    "status": "active",
    "priority": "high",
    "current_step": 1,
    "steps": ["First step", "Second step", "Third step"]
  },
  tags=["task"],
  content="""# Descriptive task name

当工作符合条件时，创建任务笔记。使用

write_note

函数并指定

note_type="Task"

，将可查询字段放入

metadata

：

python

write_note(
  title="Descriptive task name",
  directory="tasks",
  note_type="Task",
  metadata={
    "status": "active",
    "priority": "high",
    "current_step": 1,
    "steps": ["First step", "Second step", "Third step"]
  },
  tags=["task"],
  content="""# Descriptive task name

Observations

[description] What needs to be done, concisely
[status] active
[assigned_to] claude
[current_step] 1

[description] What needs to be done, concisely
[status] active
[assigned_to] claude
[current_step] 1

Steps

Context

What future-you needs to pick up this work. Include:

Key file paths and repos involved
Decisions already made and why
What was tried and what worked/didn't
Where to look for related context""" )


**Why both frontmatter and observations?** Fields in `metadata` (stored as frontmatter) power `search_notes` with `metadata_filters`. Fields as observations (`- [status] active`) power `schema_validate`. Include queryable fields in both places for full coverage.

What future-you needs to pick up this work. Include:

Key file paths and repos involved
Decisions already made and why
What was tried and what worked/didn't
Where to look for related context""" )


**为何同时使用前置元数据（frontmatter）和观测项？** `metadata`中的字段（存储为前置元数据）支持`search_notes`的`metadata_filters`功能。观测项中的字段（如`- [status] active`）支持`schema_validate`功能。将可查询字段同时放入两处以实现全面覆盖。

Key Principles

核心原则

Steps are concrete and checkable — "Implement X in file Y", not "figure out stuff"
Context is for post-amnesia resumption — Write it as if explaining to a smart person who knows nothing about what you've been doing

Relations link to other entities —

parent_task [[Other Task]]

related_to [[Some Note]]

note_types
is case-sensitive —
```
write_note(note_type="Task")
```
stores the type as lowercase
```
task
```
in frontmatter. Use
```
note_types=["task"]
```
(lowercase) in search queries.

步骤需具体且可核查——例如“在文件Y中实现X”，而非“处理相关事项”
上下文用于失忆后恢复——撰写时假设要向完全不了解当前工作的聪明人解释
关联关系链接至其他实体——使用
```
parent_task [[Other Task]]
```
或关联关系连接相关工作
note_types
区分大小写——
```
write_note(note_type="Task")
```
会将类型以小写
```
task
```
存储在前置元数据中。搜索查询时需使用
```
note_types=["task"]
```
（小写）。

Resuming After Compaction

上下文压缩后恢复任务

On session start or after compaction:

Search for active tasks:

python

search_notes(note_types=["task"], status="active")

Read the task note to get full context
Resume from
current_step
using the
```
context
```
field
Update as you progress — increment
```
current_step
```
, update context, check off steps

在会话启动或压缩后：

搜索活跃任务：

python

search_notes(note_types=["task"], status="active")

读取任务笔记以获取完整上下文
从
current_step
恢复工作，借助
```
context
```
字段
随进度更新——递增
```
current_step
```
，更新上下文，标记已完成步骤

Updating Tasks

更新任务

As work progresses, update the task note:

markdown

undefined

随着工作推进，更新任务笔记：

markdown

undefined

Steps

First step — done, resulted in X
Second step — done, changed approach because Y
Third step — next up

First step — done, resulted in X
Second step — done, changed approach because Y
Third step — next up

Context

Updated context reflecting current state...


Update frontmatter too:
```yaml
current_step: 3

Updated context reflecting current state...


同时更新前置元数据：
```yaml
current_step: 3

Completing Tasks

完成任务

When done:

yaml

status: done
completed: YYYY-MM-DD

Add a brief summary of what was accomplished and any follow-up needed.

任务完成时：

yaml

status: done
completed: YYYY-MM-DD

添加一段简要总结说明完成的内容及后续需处理的事项。

Pre-Compaction Flush

压缩前同步

When a compaction event is imminent:

Find all active tasks:

search_notes(note_types=["task"], status="active")

For each, update:
- ```
current_step
```
  to reflect actual progress
- ```
context
```
  with everything needed to resume
- Step checkboxes to show what's done
This is critical — context not written down is context lost

当即将发生压缩事件时：

查找所有活跃任务：

search_notes(note_types=["task"], status="active")

对每个任务进行更新：
- ```
current_step
```
  反映实际进度
- ```
context
```
  包含恢复工作所需的所有信息
- 步骤复选框标记已完成项
这一步至关重要——未记录的上下文将会丢失

Querying Tasks

查询任务

With BM's schema system, tasks are fully queryable:

Query	What it finds
`search_notes(note_types=["task"])`	All tasks
`search_notes(note_types=["task"], status="active")`	Active tasks
`search_notes(note_types=["task"], status="blocked")`	Blocked tasks
`search_notes(note_types=["task"], metadata_filters={"assigned_to": "claude"})`	My tasks
`search_notes("blockers", note_types=["task"])`	Tasks with blockers
`schema_validate(noteType="Task")`	Validate all tasks against schema
`schema_diff(noteType="Task")`	Detect drift between schema and actual task notes

借助BM的schema系统，任务可被全面查询：

查询语句	查询结果
`search_notes(note_types=["task"])`	所有任务
`search_notes(note_types=["task"], status="active")`	活跃任务
`search_notes(note_types=["task"], status="blocked")`	受阻任务
`search_notes(note_types=["task"], metadata_filters={"assigned_to": "claude"})`	我的任务
`search_notes("blockers", note_types=["task"])`	包含阻碍项的任务
`schema_validate(noteType="Task")`	验证所有任务是否符合schema
`schema_diff(noteType="Task")`	检测schema与实际任务笔记之间的偏差

Guidelines

使用准则

One task per unit of work — Don't cram multiple projects into one task
Externalize early — If you think "I should remember this", write it down NOW
Context > steps — Steps tell you what to do; context tells you why and how
Close finished tasks — Don't leave completed work as
```
active
```
Link related tasks — Use
```
parent_task [[X]]
```
or relations to connect related work
Schema validation is your friend — Run
```
schema_validate(noteType="Task")
```
periodically to catch incomplete tasks

每项任务对应一个工作单元——不要将多个项目塞进一个任务
尽早外部化记录——当你觉得“我应该记住这个”时，立即写下来
上下文优先于步骤——步骤告诉你要做什么；上下文告诉你原因和方法
关闭已完成任务——不要将已完成的工作标记为
```
active
```
关联相关任务——使用
```
parent_task [[X]]
```
或关联关系连接相关工作
Schema验证是好帮手——定期运行
```
schema_validate(noteType="Task")
```
以发现不完整的任务