bobowsh/dsh-llm-opencode0

dsh-llm-opencode

OpenCode Zen provider adapter for DSH harness LLM seam

包名
dsh-llm-opencode
版本
0.1.0
许可证
MIT
最近更新
2026年8月23日

安装

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bobowsh/dsh-llm-opencode

Configuration

The adapter is configurable through DSH's settings system (llm-opencode section in settings.yaml). Changes take effect immediately without restart.

SettingDefaultDescription
baseURLhttps://opencode.ai/zen/v1Gateway endpoint
apiKeyEnvOPENCODE_API_KEYCredential store key for the API token
maxTokens128000Default max output tokens per request
defaultContextWindow1000000Fallback context window for unknown models
streamIdleTimeoutMs300000Max idle time (ms) before stream is considered dead
models(built-in catalog)Override the model catalog
retryPolicy(built-in)Retry behavior for transient errors

Example settings.yaml snippet

llm-opencode:
  baseURL: "https://opencode.ai/zen/v1"
  maxTokens: 64000
  models:
    - id: deepseek-v4-flash-free
      name: DeepSeek V4 Flash Free
      contextWindow: 200000
      maxTokens: 128000

See settings.example.yaml for a full annotated example.