dsh-llm-opencode
用于 DSH harness LLM 接口的 OpenCode Zen 提供商适配器
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:bobowsh/dsh-llm-opencode#9fdc810da3a939ef20b64336018e90a7b9b429e1Llm Opencode 以 dsh-llm-opencode 发布，当前版本为 0.1.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
OpenCode Zen free model provider adapter for DeepSeek Harness (DSH).
Registers the opencode-zen provider route in DSH's LLM seam, giving your coding agent access to OpenCode Zen's free-tier models — no API key required for free models, no credit card, no setup friction.
| Model | ID | Context | Max Output | Notes |
|---|---|---|---|---|
| DeepSeek V4 Flash Free | deepseek-v4-flash-free | 200K | 128K | DeepSeek's V4 Flash, SWE-bench ~79% |
| Nemotron 3 Ultra Free | nemotron-3-ultra-free | 1M | 128K | NVIDIA's flagship, huge context |
| MiMo V2.5 Free | mimo-v2.5-free | 200K | 32K | Xiaomi's coding model |
| Big Pickle | big-pickle | 200K | 128K | Stealth general-purpose model |
Free models are served through OpenCode Zen's public gateway. Availability may change; the adapter auto-discovers models tagged
freefrom the/modelsendpoint.
# From npm (prebuilt, recommended)
dsh plugin --profile web add dsh-llm-opencode
# Or from GitHub directly
dsh plugin --profile web add "github:bobowsh/dsh-llm-opencode#main"
deepseek-v4-flash-free) and start coding — no API key needed.Paid models require an API key. Set
OPENCODE_API_KEYin DSH credentials (Settings → Credentials) or as an environment variable.
This plugin implements the LlmAdapter interface from @deepseek-ai/dsh-llm and registers a single provider route opencode-zen. When DSH routes a request to this provider:
UNSUPPORTED_CONTENT).eventsource-parser and translated into harness StreamChunk events (block-start, text-delta, reasoning-delta, tool-call-delta, usage, finish).User-Agent: opencode/1.0.0 and related headers to satisfy OpenCode Zen's client identity check (the default deepseek-harness/... user-agent is rejected by the gateway).OPENCODE_API_KEY) or the ambient environment. Free models work without a key; paid models require one./models from the gateway and filters for free-tagged entries.The adapter is configurable through DSH's settings system (llm-opencode section in settings.yaml). Changes take effect immediately without restart.
| Setting | Default | Description |
|---|---|---|
baseURL | https://opencode.ai/zen/v1 | Gateway endpoint |
apiKeyEnv | OPENCODE_API_KEY | Credential store key for the API token |
maxTokens | 128000 | Default max output tokens per request |
defaultContextWindow | 1000000 | Fallback context window for unknown models |
streamIdleTimeoutMs | 300000 | Max idle time (ms) before stream is considered dead |
models | (built-in catalog) | Override the model catalog |
retryPolicy | (built-in) | Retry behavior for transient errors |
settings.yaml snippetllm-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.
The included cordis.patch.yml registers the llm-opencode plugin row into the DSH bundle loader, so the plugin is auto-loaded when installed into a profile.
npm install
npm test
npm run lint
>= 0.1.0-rc.7@deepseek-ai/cordis ^4.0.1 (peer dependency)MIT © bobowsh