dsh-reconnect
Safe model-request retry for DeepSeek Harness with exponential backoff, model-availability recovery, and configurable unknown-error limits. 适合需要应对网络波动、自动重试失败模型请求的任务。
同名パッケージの別リポジトリ
インストール
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mrbeandev/dsh-reconnectドキュメント
README 全文を読む ↗Configuration
- insert:
- id: reconnect
name: dsh-reconnect
config:
maxDelayMs: 15000
retryQuota: false
retryUnknown: true
unknownMaxRetries: 3
| Setting | Type | Default | Description |
|---|---|---|---|
maxDelayMs | integer | 60000 | Maximum local exponential-backoff delay in milliseconds |
retryQuota | boolean | false | Retry quota or exhausted-balance errors indefinitely |
retryUnknown | boolean | true | Retry unknown error codes indefinitely |
unknownMaxRetries | integer | 3 | Consecutive unknown-error limit when retryUnknown is disabled |
maxDelayMs limits only the local exponential delay. It does not cap a
Provider Retry-After value or the total retry duration.