dsh-model-proxy

Route selected models through an outbound proxy in DeepSeek Harness, falling back to a direct connection while that proxy is unavailable. 适合需要对特定模型或域名配置代理、并在失效时自动回落直连的用户。

パッケージ

dsh-model-proxy

互換性

未検証

バージョン

0.1.0

ライセンス

MIT

最終更新

2026/09/25

Configuration

- id: model-proxy
  config:
    enabled: true
    proxy: http://127.0.0.1:10793
    origins:
      - opencode.ai
    models:
      - grok-*
      - gpt-*-luna
    fallbackToDirect: true
    probeTimeoutMs: 300
    probeCacheMs: 2000
    peekBytes: 16384

Field	Meaning
`enabled`	When false the plugin installs nothing and every request keeps its route.
`proxy`	Endpoint the matching models use. `http:` or `https:`, with optional credentials.
`origins`	Hosts whose models may be routed. Requests to every other host are untouched.
`models`	Model patterns; `*` matches any run of characters, every other character matches itself.
`fallbackToDirect`	While the proxy refuses connections, matching requests use the previous route instead of failing.
`probeTimeoutMs`	TCP connect timeout for the reachability probe.
`probeCacheMs`	How long one probe verdict is reused, so a burst of requests probes once.
`peekBytes`	How many body bytes may be inspected before giving up on finding a model name.

Edit the row in /profiles/ /cordis.patch.yml (hot-reloaded), or override the same id from a settings layer. A configuration value that cannot be used fails the activation instead of silently routing traffic to the wrong place.

dsh-model-proxy

同名パッケージの別リポジトリ

インストール

ドキュメント

Configuration