dsh-llm-mimo
Xiaomi MiMo v2.5 adapter for DeepSeek Harness LLM seam with thinking chain support
AI 分析
核心用途是将小米MiMo大模型平台接入DSH。适合使用MiMo API服务的开发者。支持在Web UI中展示模型的思考过程，必要条件是需在环境变量或.env中配置MIMO_API_KEY。
インストール
検証済み bundle がないか、互換性チェックに失敗しています。先にリポジトリの説明を読んでください。 README 全文を読む ↗
ドキュメント
README 全文を読む ↗Configuration
Set your MiMo API key:
export MIMO_API_KEY="your-api-key-here"
Or in .env file:
MIMO_API_KEY=your-api-key-here
Get your API key from MiMo Platform.
Usage
With DeepSeek Harness Web UI
### Programmatic usage
```typescript
import { Context } from '@deepseek-ai/cordis'
import llmMimo from 'dsh-llm-mimo'
const ctx = new Context()
ctx.plugin(llmMimo, {
apiKeyEnv: 'MIMO_API_KEY',
baseURL: 'https://api.xiaomimimo.com/v1',
enableThinking: true,
})
Configuration Options
| Option | Type | Default | Description |
|---|---|---|---|
apiKeyEnv | string | MIMO_API_KEY | Credential reference (environment-variable name) for the API key |
baseURL | string | https://api.xiaomimimo.com/v1 | API endpoint base URL |
enableThinking | boolean | true | Whether thinking mode is enabled by default |
maxTokens | number | 256000 | Default per-request output token cap |
defaultContextWindow | number | 1000000 | Default context window size |
models | MiMoCatalogModel[] | V2.5, V2.5-Pro | Advisory model catalog |
streamIdleTimeoutMs | number | 300000 | Stream idle timeout (ms) |
retryPolicy | RetryPolicyConfig | — | Custom retry policy |