agent-import

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Agent Import — Migration Bundle Loader

Agent导入 — 迁移包加载器

Download and load a migration bundle into this Starchild agent. The bundle is created by another agent using the

agent-export

skill.

将迁移包下载并加载到本Starchild agent中。该迁移包由另一个agent使用

agent-export

技能创建。

Quick Start

快速开始

When user provides a migration code and download token:

1. Run the import script to download & extract
2. Review the extracted data with the user
3. Apply each component using native tools

当用户提供迁移代码和下载令牌时：

1. 运行导入脚本进行下载和解压
2. 与用户一起查看解压后的数据
3. 使用原生工具应用每个组件

Step 1 — Download & Extract

步骤1 — 下载与解压

The user will provide two values from the source agent: a CODE (8 chars) and a DOWNLOAD_TOKEN.

bash

python3 sc-agent-migration/skills/agent-import/scripts/download.py <CODE> <DOWNLOAD_TOKEN>

This downloads from the relay over the public internet — no special network required. The download token authorizes the download; it is single-use and expires with the code (1 hour TTL).

On success the script extracts the bundle to

migration/

and prints a summary of what's included.

用户将从源agent提供两个值：CODE（8位字符）和DOWNLOAD_TOKEN。

bash

python3 sc-agent-migration/skills/agent-import/scripts/download.py <CODE> <DOWNLOAD_TOKEN>

此操作通过公共互联网从relay下载——无需特殊网络。下载令牌用于授权下载；它是一次性的，且会随代码一起过期（TTL为1小时）。

成功后，脚本会将包解压到

migration/

目录，并打印包含内容的摘要。

Step 2 — Review Contents

步骤2 — 查看内容

Read and summarize what the bundle contains before applying anything:

bash

cat migration/manifest.json
cat migration/memory/agent.json 2>/dev/null
cat migration/memory/user.json 2>/dev/null
cat migration/identity/profile.json 2>/dev/null
cat migration/identity/soul.md 2>/dev/null
cat migration/user/settings.json 2>/dev/null
cat migration/tasks/tasks.json 2>/dev/null
cat migration/env/keys.json 2>/dev/null
find migration/files/ -type f 2>/dev/null

Always show the user a summary and ask for confirmation before applying.

在应用任何内容之前，先读取并总结包中包含的信息：

bash

cat migration/manifest.json
cat migration/memory/agent.json 2>/dev/null
cat migration/memory/user.json 2>/dev/null
cat migration/identity/profile.json 2>/dev/null
cat migration/identity/soul.md 2>/dev/null
cat migration/user/settings.json 2>/dev/null
cat migration/tasks/tasks.json 2>/dev/null
cat migration/env/keys.json 2>/dev/null
find migration/files/ -type f 2>/dev/null

在应用之前，务必向用户展示摘要并请求确认。

Step 3 — Apply Components

步骤3 — 应用组件

Apply each component using Starchild native tools. The order matters:

使用Starchild原生工具应用每个组件。顺序很重要：

3a. User Settings (first — sets timezone/language for everything else)

3a. 用户设置（优先设置——为其他所有内容配置时区/语言）

Read

migration/user/settings.json

, then call:

user_settings(action="update", settings={
  "name": "...",
  "what_to_call": "...",
  "timezone": "...",
  "language": "..."
})

Only include fields that are present in the JSON.

读取

migration/user/settings.json

，然后调用：

user_settings(action="update", settings={
  "name": "...",
  "what_to_call": "...",
  "timezone": "...",
  "language": "..."
})

仅包含JSON中存在的字段。

3b. Agent Identity

3b. Agent身份信息

Read

migration/identity/profile.json

, then call:

agent_profile(action="update", profile={
  "name": "...",
  "vibe": "...",
  "emoji": "...",
  "creature": "..."
})

读取

migration/identity/profile.json

，然后调用：

agent_profile(action="update", profile={
  "name": "...",
  "vibe": "...",
  "emoji": "...",
  "creature": "..."
})

3c. SOUL.md

migration/identity/soul.md

exists, read it and write to

prompt/SOUL.md

Merge with existing SOUL.md if it has content. Don't overwrite platform defaults blindly — integrate the personality bits.

如果

migration/identity/soul.md

存在，读取该文件并写入

prompt/SOUL.md

。

如果已有SOUL.md内容，进行合并。不要盲目覆盖平台默认设置——整合个性相关内容。

3d. Memory — Agent

3d. 记忆 — Agent

Read

migration/memory/agent.json

, for each entry call:

memory(action="add", target="memory", content="<entry>")

⚠️ Memory has a 5000 char limit. If the bundle has many entries, prioritize the most useful ones. Check current usage with

memory(action="read")

first.

读取

migration/memory/agent.json

，对每个条目调用：

memory(action="add", target="memory", content="<entry>")

⚠️ 记忆有5000字符限制。如果包中有多个条目，优先处理最有用的内容。先使用

memory(action="read")

检查当前使用情况。

3e. Memory — User

3e. 记忆 — 用户

Read

migration/memory/user.json

, for each entry call:

memory(action="add", target="user", content="<entry>")

⚠️ User memory has a 3000 char limit. Prioritize preferences and corrections.

读取

migration/memory/user.json

，对每个条目调用：

memory(action="add", target="user", content="<entry>")

⚠️ 用户记忆有3000字符限制。优先处理偏好和修正内容。

3f. Tasks

3f. 任务

Read

migration/tasks/tasks.json

, for each task:

scheduled_task(action="register", title=..., schedule=..., description=..., channels=...)

Write the
```
run.py
```
script based on the description
Test it:
```
bash("python3 tasks/{job_id}/run.py")
```

scheduled_task(action="activate", job_id=...)

Tasks need actual implementation — the description is a spec, not runnable code. Use your judgment to build each task's script.

读取

migration/tasks/tasks.json

，对每个任务执行以下操作：

scheduled_task(action="register", title=..., schedule=..., description=..., channels=...)

根据描述编写
```
run.py
```
脚本
测试脚本：
```
bash("python3 tasks/{job_id}/run.py")
```

scheduled_task(action="activate", job_id=...)

任务需要实际实现——描述只是规范，并非可运行代码。请自行判断构建每个任务的脚本。

3g. Environment Keys

3g. 环境密钥

Read

migration/env/keys.json

, then call:

request_env_input(env_vars=[...], reason="Migration from <source>")

This prompts the user to enter values securely.

读取

migration/env/keys.json

，然后调用：

request_env_input(env_vars=[...], reason="Migration from <source>")

这会提示用户安全输入值。

3h. Files

3h. 文件

Copy files from

migration/files/

to the workspace:

bash

cp -r migration/files/* . 2>/dev/null

Review what's being copied and skip anything that would overwrite important existing files.

将

migration/files/

中的文件复制到工作区：

bash

cp -r migration/files/* . 2>/dev/null

检查要复制的内容，跳过任何会覆盖重要现有文件的内容。

Step 4 — Cleanup

步骤4 — 清理

bash

rm -rf migration/ migration-bundle.tar.gz

bash

rm -rf migration/ migration-bundle.tar.gz

Error Handling

错误处理

Error	Cause	Fix
`401 unauthorized`	Wrong or missing download token	Re-check the token from the source agent output
`404 not found`	Code already used or never existed	Ask source agent to re-export
`410 expired`	Code older than 1 hour	Ask source agent to re-export
`429 rate limited`	Too many failed attempts	Wait 1 hour
Invalid tar.gz	Corrupted upload	Re-export from source agent
No manifest.json	Invalid bundle structure	Bundle must have manifest.json at root

错误	原因	修复方法
`401 unauthorized`	下载令牌错误或缺失	重新检查源agent输出中的令牌
`404 not found`	代码已被使用或从未存在	请求源agent重新导出
`410 expired`	代码已超过1小时	请求源agent重新导出
`429 rate limited`	失败尝试过多	等待1小时
Invalid tar.gz	上传文件损坏	从源agent重新导出
No manifest.json	包结构无效	包的根目录必须包含manifest.json