ChadCSong/dsh-cliproxyapi-provider ↗★ 2

dsh-cliproxyapi-provider

CLIProxyAPI provider for DeepSeek Harness with local auto-discovery, dynamic model sync, and native model switching. 适合使用CLIProxyAPI作为模型代理、需要动态同步模型列表的用户。

パッケージ
dsh-cliproxyapi-provider
互換性
未検証
Harness ピア範囲
*
Cordis ピア範囲
*
バージョン
0.1.9
ライセンス
MIT
最終更新
2026/09/16

インストール

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ChadCSong/dsh-cliproxyapi-provider

ドキュメント

README 全文を読む ↗

Setup and usage

  1. Start CLIProxyAPI. Leave the URL empty when it listens on the default port, 8317.
  2. Open Settings → Plugins → CLIProxyAPI (auto discovery) in DSH.
  3. If CPA bearer authentication is enabled, enter the API key once.
  4. Return to a conversation and select any model under CLIProxyAPI (auto) in DSH's native picker.

Useful commands:

/cpa-status
/cpa-refresh

/cpa-status reports the current endpoint and synchronized model count. /cpa-refresh immediately probes CPA and refreshes the DSH model catalog.

Configuration

The settings namespace intentionally remains dsh-cliproxyapi for upgrade compatibility:

dsh-cliproxyapi:
  enabled: true
  # Empty means local auto-discovery. Remote CPA is also supported.
  baseURL: ''
  apiKeyEnv: CLIPROXYAPI_API_KEY
  protocol: openai-completions
  refreshIntervalSeconds: 300
  probeTimeoutMs: 2000

Endpoint resolution

Candidates are deduplicated and tried in this order:

  1. Explicit baseURL setting
  2. CLIPROXYAPI_BASE_URL from the DSH launch environment
  3. Local loopback candidates on port 8317

A non-loopback service is contacted only when you explicitly configure it.

API key storage

apiKeyEnv is a credential reference, not the secret itself. The settings UI writes the key through DSH's credential service. The default reference is CLIPROXYAPI_API_KEY.

Inference protocol

The default, openai-completions, uses CPA's /v1/chat/completions route. Select openai-responses only when your CPA deployment exposes the target models through the Responses API.

Image input

The plugin forwards the input capabilities reported by CPA. Models that declare image input receive images through DSH's official adapter; text-only models remain text-only. There is no separate vision model, image-to-text preprocessing, or capability override. DSH applies its native compatibility rules when a session contains images.