Kristin130/dsh-commandcode-provider ↗★ 1
dsh-commandcode-provider
Command Code provider plugin for DeepSeek Harness (dsh) — works with every Command Code plan including the $1 Go plan; uses the Studio authentication API key over /alpha/generate, not the Provider API
AI 분석
核心用途是将 Command Code 模型服务接入 DSH。适合 Command Code 用户（包括低成本 Go 计划订阅者），需要直接在 DSH 中调用该平台模型。
설치
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Kristin130/dsh-commandcode-providerConfiguration
The commandcode-provider settings section accepts (all optional):
| Field | Default | Meaning |
|---|---|---|
apiKeyEnv | COMMANDCODE_API_KEY | Credential reference resolved per request |
displayName | Command Code | Name shown by selectors |
baseURL | COMMANDCODE_API_BASE env → https://api.commandcode.ai | API base for /alpha/generate (usually leave at default) |
modelsUrl | COMMANDCODE_MODELS_URL env → Provider API | Model discovery endpoint |
modelsTimeoutMs | COMMANDCODE_MODELS_TIMEOUT_MS env → 10000 | Discovery timeout |
modelsCachePath | COMMANDCODE_MODELS_CACHE env → /commandcode/commandcode-models.json | Catalog cache path |
models | — | Optional explicit catalog entries; each overrides (or adds to) the discovered model by id |
defaultContextWindow | 262144 | Context capacity for models neither the catalog nor an override sizes |
defaultMaxTokens | 32768 | Output capability for models neither the catalog nor an override sizes |
timeoutMs | — | Per-attempt HTTP request timeout |
streamIdleTimeoutMs | 300000 | Max idle time while one stream read is outstanding |
retryPolicy | normal defaults | Provider-owned model-request retry policy |