
Security News
OpenCode User Hit with Hostile Backlash After Reporting Free AI Loophole
An OpenCode user faced harassment after reporting a free AI usage loophole, drawing a bitter backlash in a GitHub thread that has since been deleted.
thousandsailagent
Advanced tools
千帆竞发,万舸争流 — 多 AI Agent 编排框架,用声明式 YAML 定义 Agent 协作流程。
npm install -g thousandsailagent
tsail config
交互式引导,选择 LLM Provider 并输入 API Key:
◆ 选择要配置的 Provider
│ ● DeepSeek(深度求索)
│ ○ 智谱 GLM(ChatGLM)
│ ○ 通义千问(Qwen)
│ ○ Moonshot(Kimi)
│ ○ 豆包(火山引擎)
│ ○ Anthropic(Claude)
│ ○ OpenAI(GPT)
│ ○ 自定义 Provider
└ ○ 完成配置
创建 pipeline.yaml:
name: code-review-pipeline
steps:
- id: code
agent: coder
model: deepseek/deepseek-chat
prompt: "根据以下需求实现功能: {{input.requirement}}"
tools: [file_write, file_read, terminal]
- id: review
agent: reviewer
model: glm/glm-4-flash
prompt: "审查代码,检查安全和性能问题: {{steps.code.output}}"
depends_on: [code]
tools: [file_read]
- id: refine
agent: coder
model: deepseek/deepseek-chat
prompt: "根据审查意见修改代码: {{steps.review.output}}"
depends_on: [review]
tools: [file_write, file_read, terminal]
tsail run pipeline.yaml -i requirement="实现一个HTTP服务器"
| 命令 | 说明 |
|---|---|
tsail run <file> | 运行工作流 YAML |
tsail config | 交互式配置 Provider |
tsail providers | 查看已配置的 Provider |
tsail list | 列出当前目录的工作流文件 |
tsail history [id] | 查看运行历史 |
-i, --input <k=v...> 传入输入参数
-d, --db <path> 指定数据库路径
--verbose 显示详细输出
name: <工作流名称>
steps:
- id: <步骤ID> # 必填,唯一标识
agent: <Agent类型> # coder / reviewer / tester
model: <provider/model> # 必填,模型引用
prompt: <提示词> # 必填,支持模板变量
tools: [file_read, ...] # 可用工具列表
depends_on: [step_id, ...] # 依赖的步骤(可选)
max_steps: <number> # 最大工具调用轮数(可选)
| 变量 | 说明 |
|---|---|
{{input.xxx}} | 运行时传入的参数 |
{{steps.xxx.output}} | 上游步骤的 LLM 输出 |
无 depends_on 的步骤会并行执行,有依赖的步骤等待上游完成后才启动。
| Provider | 类型 | 默认模型 |
|---|---|---|
| DeepSeek | OpenAI-compatible | deepseek-chat |
| 智谱 GLM | OpenAI-compatible | glm-4-flash |
| 通义千问 | OpenAI-compatible | qwen-plus |
| Moonshot | OpenAI-compatible | moonshot-v1-8k |
| 豆包 | OpenAI-compatible | doubao-pro-32k |
| Anthropic | Anthropic | claude-sonnet-4-20250514 |
| OpenAI | OpenAI-compatible | gpt-4o |
也支持通过 tsail config 添加任意 OpenAI-compatible API。
当前版本:V0.2.0
git clone https://github.com/Lion-1209/ThousandSailAgent.git
cd ThousandSailAgent
npm install
npm test # 运行测试
npm run dev -- --help # 开发模式运行
MIT
FAQs
千帆 Agent — 多 AI Agent 编排框架,用声明式 YAML 定义 Agent 协作流程
The npm package thousandsailagent receives a total of 16 weekly downloads. As such, thousandsailagent popularity was classified as not popular.
We found that thousandsailagent demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.

Security News
An OpenCode user faced harassment after reporting a free AI usage loophole, drawing a bitter backlash in a GitHub thread that has since been deleted.

Threat Research
/Security News
319 browser extensions installed by 13.4 million users hijack searches, capture queries, and collect referral payments from Yahoo and Bing.

Threat Research
Malicious Firefox extensions mimic Phantom, Jupiter, and Bitget wallets to steal recovery phrases and private keys, with one fetching its payload remotely.