dsh-opencode-provider
无需单独的提供商 API 密钥，即可在 DeepSeek Harness 中使用 OpenCode 模型。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-opencode-provider@0.1.0Opencode Provider 以 dsh-opencode-provider 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。
Use models available through a local OpenCode server inside DeepSeek Harness without a DeepSeek API key.
DeepSeek Harness (DSH)
└─ LLM Runtime
└─ opencode-local provider route
└─ OpenCodeAdapter (dsh-opencode-provider)
├─ POST /api/session → create session
├─ POST /api/session/{id}/prompt → serialized conversation
├─ GET /api/session/{id}/event → SSE stream
└─ POST /api/session/{id}/interrupt → best-effort cancel
↕ HTTP + SSE
OpenCode Server (127.0.0.1:4096)
↕
Model (mimo-v2.5-free)
The adapter serializes the full DSH conversation (system prompt + messages) into a single prompt string, sends it to the OpenCode server, and translates the SSE event stream into DSH StreamChunk values. OpenCode runs its own internal agent/tool loop, so the adapter exposes text output only — structured DSH tool calling is not available.
session.text.delta, session.execution.succeeded) and current (session.next.text.delta, session.next.step.ended) event envelopesdata.wrapper envelopes are unwrapped defensivelyhttp://127.0.0.1:4096)dsh plugin --profile web add dsh-opencode-provider
git clone https://github.com/goku54477/dsh-opencode-provider.git
cd dsh-opencode-provider
pnpm dsh
opencode serve --hostname 127.0.0.1 --port 4096
The adapter auto-configures with the default base URL (http://127.0.0.1:4096). No additional setup is needed.
In DeepSeek Harness, select the model:
opencode-local/mimo-v2.5-free
All fields are optional. Defaults work out of the box with a local OpenCode server.
# Inside your DSH cordis.yml or plugin config
llm-opencode:
# Endpoint of the OpenCode server
baseURL: "http://127.0.0.1:4096"
# Context window reported to the harness (default: 128000)
defaultContextWindow: 128000
# Max output tokens per request (default: 16384)
maxTokens: 16384
# Advisory model list for discovery consumers
models:
- id: mimo-v2.5-free
name: mimo-v2.5-free
description: "OpenCode local agent (text output only)"
contextWindow: 128000
# Retry policy
retryPolicy:
mode: always
backoff:
initialDelayMs: 100
maxDelayMs: 5000
jitterRatio: 0.2
POST /api/session with { model: { id, providerID: "opencode" } }GET /api/session/{id}/event) and prompt delivery (POST /api/session/{id}/prompt) concurrently. This avoids a deadlock where the OpenCode server withholds SSE headers until the session has activity.[System]\n...\n\n[User]\n...\n\n[Assistant]\n... and embedded in the prompt.session.text.delta, session.next.step.ended, session.execution.succeeded, etc.) are mapped to DSH StreamChunk types (block-start, text-delta, block-end, finish).# Build
npm run build
# Type-check
npm run typecheck
# Run tests
npm run test
# Build + test
npm run check
# Clean output
npm run clean
This plugin communicates with a local HTTP server (no TLS by default). Do not expose the OpenCode server to untrusted networks. The default binding (127.0.0.1) restricts access to the local machine.
v0.1.0 has been tested on the following exact environment:
| Component | Version |
|---|---|
| OS | Windows 11 |
| Node.js | 22.23.2 |
| DeepSeek Harness | 0.1.0-rc.8 |
| OpenCode | 1.18.19 |
| Model | opencode/mimo-v2.5-free |
Other platforms, Node versions, harness releases, OpenCode versions, and models have not been verified. The adapter may work elsewhere, but no guarantees are made.
inputModalities: ["text"] only. Image/audio/video inputs are not forwarded.mimo-v2.5-free. Adding models requires manual config; the adapter does not dynamically discover available models from the server.stream() call creates a fresh OpenCode session. Conversation state is not preserved across requests.127.0.0.1. Remote servers require manual baseURL configuration and appropriate network access.