terminaluse

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

TerminalUse

Build, deploy, interact with agents. Flow: init → deploy → create task → send messages.

Full docs: https://docs.terminaluse.com/llms-full.txt

构建、部署并与Agent交互。流程：初始化 → 部署 → 创建任务 → 发送消息。

完整文档：https://docs.terminaluse.com/llms-full.txt

CLI Setup

CLI 配置

The

tu

CLI is provided by the

terminaluse

Python package. Before running any

tu

commands:

Verify
tu
is available:
bash
```
which tu || echo "tu CLI not found"
```
If not installed, ask user whether they would like to install it or if there's a venv they would like to source
Ensure you have an active token with
```
tu login
```
. You can run the command which will open a browser for the user to login.

tu

CLI由

terminaluse

Python包提供。在运行任何

tu

命令之前：

验证
tu
是否可用：
bash
```
which tu || echo "tu CLI not found"
```
若未安装，询问用户是否想要安装它，或者是否有想要激活的虚拟环境（venv）
使用
```
tu login
```
确保你拥有有效的令牌。运行该命令会打开浏览器供用户登录。

Context Requirement

上下文要求

Most

tu

commands require

config.yaml

in current directory to know what agent to target. Before running commands:

bash

ls config.yaml || echo "Not in agent directory"

If not present,

cd

into the agent project folder first.

大多数

tu

命令需要当前目录下存在

config.yaml

来指定目标Agent。在运行命令之前：

bash

ls config.yaml || echo "Not in agent directory"

若不存在，先切换到Agent项目文件夹中。

Quick Reference

快速参考

Action	Command
Login	`tu login` , `tu whoami`
Init agent	`tu init` (creates agent directory, no need to mkdir first)
Deploy	`tu deploy -y`
List deployments	`tu ls`
Rollback	`tu rollback`
Add env var	`tu env add <KEY> -v <val> -e prod\|preview\|all [--secret]`
Import env file	`tu env import <file> -e <env> [--secret KEY]`
Create task	`tu tasks create -f <fs-id> -m "message"`
Create task (auto-create fs)	`tu tasks create -p <project-id> -m "message"`
Send message	`tu tasks send <task-id> -m "message"`

操作	命令
登录	`tu login` , `tu whoami`
初始化Agent	`tu init` （创建Agent目录，无需提前创建文件夹）
部署	`tu deploy -y`
列出部署记录	`tu ls`
回滚	`tu rollback`
添加环境变量	`tu env add <KEY> -v <val> -e prod\|preview\|all [--secret]`
导入环境变量文件	`tu env import <file> -e <env> [--secret KEY]`
创建任务	`tu tasks create -f <fs-id> -m "message"`
创建任务（自动创建文件系统）	`tu tasks create -p <project-id> -m "message"`
发送消息	`tu tasks send <task-id> -m "message"`

Workflows

工作流

Task	Reference
Create a new agent	./workflows/create.md
Deploy to platform	./workflows/deploy.md
Test/interact with agent	./workflows/interact.md

You must look at the corresponding workflow files based on user intent.

任务	参考文档
创建新Agent	./workflows/create.md
部署到平台	./workflows/deploy.md
测试/与Agent交互	./workflows/interact.md

需根据用户的需求查看对应的工作流文件。

Anti-patterns

反模式

Creating task without filesystem or project. Tasks either need a filesystem. If project is provided, a filesystem is auto-created in the project
Modifying Dockerfile
```
ENTRYPOINT
```
/
```
CMD
```
→ breaks deployment
Trying to use the agent right after updating secrets. You must wait for the new version to become active. Check with
```
tu ls
```

未指定文件系统（filesystem）或项目就创建任务。任务必须关联文件系统；若提供了项目，系统会自动在该项目中创建一个文件系统。
修改Dockerfile的
```
ENTRYPOINT
```
/
```
CMD
```
→ 会导致部署失败
在更新密钥后立即尝试使用Agent。你必须等待新版本激活后再使用。可通过
```
tu ls
```
检查状态。

Error Recovery

错误恢复

Error	Action
Deploy fails	`tu ls <branch>` lists deployments events for branch → find FAILED → fix → redeploy
Need rollback	`tu rollback`

错误	操作
部署失败	`tu ls <branch>` 会列出分支的部署事件 → 找到FAILED状态的事件 → 修复问题 → 重新部署
需要回滚	`tu rollback`

Docs/Skills Feedback

文档/技能反馈

If docs or skills are wrong/unclear, ask user permission to send feedback to (include the feedback in the user request): Never include any sensitive information.

bash

curl -X POST 'https://uutzjuuimuclittwbvef.supabase.co/functions/v1/tu-docs-feedback' \
  -H 'Content-Type: application/json' \
  -d '{"feedback":"<issue>", "page":"<page URL> or section name"}'

若文档或技能存在错误/表述不清，需先征得用户同意，再将反馈发送至（反馈内容需包含在用户请求中）：请勿包含任何敏感信息。

bash

curl -X POST 'https://uutzjuuimuclittwbvef.supabase.co/functions/v1/tu-docs-feedback' \
  -H 'Content-Type: application/json' \
  -d '{"feedback":"<issue>", "page":"<page URL> or section name"}'