ontology - 类型化知识图谱用于结构化代理记忆与可组合技能

一个 类型化词汇表 + 约束系统，用于将知识表示为可验证的图结构。

核心概念

一切都是 实体，拥有 类型、属性 与指向其他实体的 关系。每一次变更在提交前都会依据类型约束进行校验。

Entity: { id, type, properties, relations, created, updated }
Relation: { from_id, relation_type, to_id, properties }

何时使用

核心类型

# Agents & People
Person: { name, email?, phone?, notes? }
Organization: { name, type?, members[] }
# Work
Project: { name, status, goals[], owner? }
Task: { title, status, due?, priority?, assignee?, blockers[] }
Goal: { description, target_date?, metrics[] }
# Time & Place
Event: { title, start, end?, location?, attendees[], recurrence? }
Location: { name, address?, coordinates? }
# Information
Document: { title, path?, url?, summary? }
Message: { content, sender, recipients[], thread? }
Thread: { subject, participants[], messages[] }
Note: { content, tags[], refs[] }
# Resources
Account: { service, username, credential_ref? }
Device: { name, type, identifiers[] }
Credential: { service, secret_ref }  # Never store secrets directly
# Meta
Action: { type, target, timestamp, outcome? }
Policy: { scope, rule, enforcement }

存储

默认路径: memory/ontology/graph.jsonl

{"op":"create","entity":{"id":"p_001","type":"Person","properties":{"name":"Alice"}}}
{"op":"create","entity":{"id":"proj_001","type":"Project","properties":{"name":"Website Redesign","status":"active"}}}
{"op":"relate","from":"proj_001","rel":"has_owner","to":"p_001"}

通过脚本或直接文件操作进行查询。对于复杂图，可迁移至 SQLite。

追加写入规则

在处理已有本体数据或 schema 时，请 追加/合并 更改而非覆写文件，以保留历史记录并避免冲突。

工作流

创建实体

python3 scripts/ontology.py create --type Person --props '{"name":"Alice","email":"alice@example.com"}'

查询

python3 scripts/ontology.py query --type Task --where '{"status":"open"}'
python3 scripts/ontology.py get --id task_001
python3 scripts/ontology.py related --id proj_001 --rel has_task

关联实体

python3 scripts/ontology.py relate --from proj_001 --rel has_task --to task_001

校验

python3 scripts/ontology.py validate  # 检查所有约束

约束

在 memory/ontology/schema.yaml 中定义：

types:
  Task:
    required: [title, status]
    status_enum: [open, in_progress, blocked, done]
  
  Event:
    required: [title, start]
    validate: "end >= start if end exists"
  Credential:
    required: [service, secret_ref]
    forbidden_properties: [password, secret, token]  # 强制使用间接引用
relations:
  has_owner:
    from_types: [Project, Task]
    to_types: [Person]
    cardinality: many_to_one
  
  blocks:
    from_types: [Task]
    to_types: [Task]
    acyclic: true  # 禁止循环依赖

技能约定

使用本体的技能需在 SKILL.md 前置或头部声明：

ontology:
  reads: [Task, Project, Person]
  writes: [Task, Action]
  preconditions:
    - "Task.assignee must exist"
  postconditions:
    - "Created Task has status=open"

将计划建模为图转换

把多步骤计划视为一系列图操作：

Plan: "Schedule team meeting and create follow-up tasks"
CREATE Event { title: "Team Sync", attendees: [p_001, p_002] }
RELATE Event -> has_project -> proj_001
CREATE Task { title: "Prepare agenda", assignee: p_001 }
RELATE Task -> for_event -> event_001
CREATE Task { title: "Send summary", assignee: p_001, blockers: [task_001] }

每一步在执行前都会校验，若出现约束冲突则回滚。

集成模式

与 Causal Inference 结合

将本体变更记录为因果动作：

# 创建/更新实体时，同时写入因果动作日志
action = {
    "action": "create_entity",
    "domain": "ontology",
    "context": {"type": "Task", "project": "proj_001"},
    "outcome": "created"
}

跨技能通信

# Email skill 创建承诺对象
commitment = ontology.create("Commitment", {
    "source_message": msg_id,
    "description": "Send report by Friday",
    "due": "2026-01-31"
})
# Task skill 获取并转化为任务
tasks = ontology.query("Commitment", {"status": "pending"})
for c in tasks:
    ontology.create("Task", {
        "title": c.description,
        "due": c.due,
        "source": c.id
    })

快速入门

# 初始化本体存储
mkdir -p memory/ontology
touch memory/ontology/graph.jsonl
# 可选创建 schema（推荐）
python3 scripts/ontology.py schema-append --data '{
  "types": {
    "Task": { "required": ["title", "status"] },
    "Project": { "required": ["name"] },
    "Person": { "required": ["name"] }
  }
}'
# 开始使用
python3 scripts/ontology.py create --type Person --props '{"name":"Alice"}'
python3 scripts/ontology.py list --type Person

参考资料

• references/schema.md — 完整类型定义与约束模式
• references/queries.md — 查询语言与遍历示例

指令范围

运行时指令仅操作本地文件(memory/ontology/graph.jsonl 与 memory/ontology/schema.yaml)，并提供 CLI 用于创建、查询、关联、校验；属于预期范围。技能会读取/写入工作区文件，并在首次使用时自动创建 memory/ontology 目录。校验包括属性/枚举/禁用字段检查、关系类型/基数校验、标记为 acyclic: true 的关系环路检测，以及 Event 的 end >= start 检查；其它更高层约束可能仅在文档中说明，除非在代码中实现。