mirror of
https://github.com/TencentCloud/TencentDB-Agent-Memory
synced 2026-07-10 12:34:27 +00:00
memory-tdai CLI
openclaw memory-tdai 命令空间,提供离线数据管理工具。
seed — 导入历史对话数据
将历史对话 JSON 文件导入到记忆管线中,完整执行 L0→L1→L2→L3 流程。适用于:
- 将已有对话数据灌入记忆系统
- 批量测试记忆提取效果
- 迁移/恢复记忆数据
用法
openclaw memory-tdai seed --input <file> [options]
参数
| 参数 | 必填 | 说明 |
|---|---|---|
--input <file> |
✅ | 输入 JSON 文件路径 |
--output-dir <dir> |
— | 输出目录(默认自动生成带时间戳的目录) |
--session-key <key> |
— | 回退 session key(当输入数据缺少时使用) |
--config <file> |
— | 配置覆盖文件(JSON,与 openclaw.json 插件配置深度合并) |
--strict-round-role |
— | 严格校验每轮对话必须包含 user 和 assistant 消息 |
--yes |
— | 跳过交互确认(如时间戳自动填充确认) |
示例
# 基本用法
openclaw memory-tdai seed --input conversations.json
# 指定输出目录
openclaw memory-tdai seed --input data.json --output-dir ./seed-output
# 使用自定义配置覆盖(如调整 pipeline 参数)
openclaw memory-tdai seed --input data.json --config seed-config.json
# 跳过所有确认
openclaw memory-tdai seed --input data.json --yes
# 严格模式 + 自定义配置
openclaw memory-tdai seed --input data.json --config seed-config.json --strict-round-role --yes
输入文件格式
支持两种 JSON 格式:
Format A:对象包装
{
"sessions": [
{
"sessionKey": "user-alice",
"sessionId": "conv-001",
"conversations": [
[
{ "role": "user", "content": "你好", "timestamp": 1711929600000 },
{ "role": "assistant", "content": "你好!有什么可以帮你?", "timestamp": 1711929601000 }
],
[
{ "role": "user", "content": "今天天气怎么样?" },
{ "role": "assistant", "content": "今天晴天,适合出门。" }
]
]
}
]
}
Format B:顶层数组
[
{
"sessionKey": "user-alice",
"conversations": [
[
{ "role": "user", "content": "你好" },
{ "role": "assistant", "content": "你好!" }
]
]
}
]
字段说明
| 字段 | 类型 | 必填 | 说明 |
|---|---|---|---|
sessionKey |
string | ✅ | Session 标识(如用户 ID、频道名) |
sessionId |
string | — | 会话实例 ID(同一 sessionKey 下可有多个 sessionId) |
conversations |
message[][] | ✅ | 对话轮次数组,每个轮次是一组消息 |
role |
string | ✅ | 消息角色:user 或 assistant |
content |
string | ✅ | 消息内容 |
timestamp |
number | string | — | 时间戳:epoch 毫秒或 ISO 8601 字符串。缺失时 seed 会提示自动填充 |
配置覆盖
--config 接受一个 JSON 文件,与 openclaw.json 中的插件配置两级深度合并:
- 顶层 key 如果两边都是对象 → 浅合并(保留 base 中未覆盖的字段)
- 其他类型 → 直接覆盖
常见场景:seed 时使用更激进的 pipeline 参数以加速处理:
{
"pipeline": {
"everyNConversations": 3,
"enableWarmup": false,
"l1IdleTimeoutSeconds": 2,
"l2DelayAfterL1Seconds": 1,
"l2MinIntervalSeconds": 1,
"l2MaxIntervalSeconds": 10
}
}
如果需要 seed 到独立的 TCVDB 数据库:
{
"storeBackend": "tcvdb",
"tcvdb": {
"database": "my_seed_test_db"
},
"pipeline": {
"everyNConversations": 3,
"enableWarmup": false,
"l1IdleTimeoutSeconds": 2
}
}
输出目录结构
<output-dir>/
├── conversations/ — L0 JSONL 文件
├── records/ — L1 JSONL 文件
├── scene_blocks/ — L2 场景块
├── vectors.db — SQLite 向量数据库(仅 sqlite 后端)
├── .metadata/
│ ├── manifest.json — 元数据(store 绑定 + seed 运行记录)
│ └── checkpoint.json — 管线进度
└── .backup/ — 滚动备份
Seed 完成后,manifest.json 会记录本次运行信息:
{
"version": 1,
"createdAt": "2026-04-01T22:00:00.000Z",
"store": {
"type": "sqlite",
"sqlite": { "path": "vectors.db" }
},
"seed": {
"inputFile": "conversations.json",
"sessions": 3,
"rounds": 42,
"messages": 128,
"startedAt": "2026-04-01T22:00:00.000Z",
"completedAt": "2026-04-01T22:05:30.000Z"
}
}