名称: ontology
描述: 用于结构化智能体记忆与可组合技能的类型化知识图谱。适用于创建/查询实体(人员、项目、任务、事件、文档)、链接相关对象、强制执行约束、将多步骤行动规划为图变换,或当技能需要共享状态时。触发场景包括:“记住”、“关于X我知道什么”、“将X链接到Y”、“显示依赖关系”、实体增删改查或跨技能数据访问。
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。
一切皆为实体,具有类型、属性以及与其他实体的关系。每次变更在提交前都会根据类型约束进行验证。
实体: { id, type, properties, relations, created, updated }
关系: { from_id, relation_type, to_id, properties }
| 触发场景 | 对应操作 |
|---|---|
| “记住...” | 创建/更新实体 |
| “关于X我知道什么?” | 查询图谱 |
| “将X链接到Y” | 创建关系 |
| “显示项目Z的所有任务” | 图遍历 |
| “什么依赖于X?” | 依赖关系查询 |
| 规划多步骤工作 | 建模为图变换 |
| 技能需要共享状态 | 读写本体对象 |
# 智能体与人员
Person: { name, email?, phone?, notes? }
Organization: { name, type?, members[] }
# 工作
Project: { name, status, goals[], owner? }
Task: { title, status, due?, priority?, assignee?, blockers[] }
Goal: { description, target_date?, metrics[] }
# 时间与地点
Event: { title, start, end?, location?, attendees[], recurrence? }
Location: { name, address?, coordinates? }
# 信息
Document: { title, path?, url?, summary? }
Message: { content, sender, recipients[], thread? }
Thread: { subject, participants[], messages[] }
Note: { content, tags[], refs[] }
# 资源
Account: { service, username, credential_ref? }
Device: { name, type, identifiers[] }
Credential: { service, secret_ref } # 切勿直接存储密钥
# 元数据
Action: { type, target, timestamp, outcome? }
Policy: { scope, rule, enforcement }
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"}
可通过脚本或直接文件操作进行查询。对于复杂图谱,可迁移至 SQLite。
处理现有本体数据或模式时,应追加/合并变更,而非覆盖文件。这有助于保留历史记录并避免破坏先前的定义。
python3 scripts/ontology.py create --type Person --props '{"name":"Alice","email":"alice@example.com"}'
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
python3 scripts/ontology.py relate --from proj_001 --rel has_task --to task_001
python3 scripts/ontology.py validate # 检查所有约束
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: "如果存在 end,则 end >= start"
Credential:
required: [service, secret_ref]
forbidden_properties: [password, secret, token] # 强制间接引用
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
使用本体的技能应声明:
# 在 SKILL.md 的前置元数据或头部中
ontology:
reads: [Task, Project, Person]
writes: [Task, Action]
preconditions:
- "Task.assignee 必须存在"
postconditions:
- "创建的 Task 其 status=open"
将多步骤计划建模为一系列图操作:
计划: “安排团队会议并创建后续任务”
1. CREATE Event { title: "Team Sync", attendees: [p_001, p_002] }
2. RELATE Event -> has_project -> proj_001
3. CREATE Task { title: "Prepare agenda", assignee: p_001 }
4. RELATE Task -> for_event -> event_001
5. CREATE Task { title: "Send summary", assignee: p_001, blockers: [task_001] }
每一步在执行前都会进行验证。若违反约束,则回滚。
将本体变更记录为因果行动:
# 创建/更新实体时,同时记录到因果行动日志
action = {
"action": "create_entity",
"domain": "ontology",
"context": {"type": "Task", "project": "proj_001"},
"outcome": "created"
}
# 邮件技能创建承诺
commitment = ontology.create("Commitment", {
"source_message": msg_id,
"description": "周五前发送报告",
"due": "2026-01-31"
})
# 任务技能接收处理
tasks = ontology.query("Commitment", {"status": "pending"})
for c in tasks:
ontology.create("Task", {
"title": c.description,
"due": c.due,
"source": c.id
})
# 初始化本体存储
mkdir -p memory/ontology
touch memory/ontology/graph.jsonl
# 创建模式(可选但推荐)
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
references/schema.md — 完整的类型定义和约束模式references/queries.md — 查询语言和遍历示例运行时指令操作本地文件(memory/ontology/graph.jsonl 和 memory/ontology/schema.yaml),并提供用于创建/查询/链接/验证的 CLI 用法;这属于范围内。技能会读写工作空间文件,并在使用时创建 memory/ontology 目录。验证包括属性/枚举/禁止项检查、关系类型/基数验证、标记为 acyclic: true 的关系的无环性检查,以及 Event 的 end >= start 检查;其他更高层级的约束可能仍仅为文档说明,除非在代码中实现。