deepseekplugins

DeepSeek Harness plugin

dsh-commandcode-go-provider

Command Code Go provider adapter for dsh: scan the Go-plan catalog and serve generation through the harness LLM seam.

Models & Providers
Jump to install

Source facts

Repository
jiesou/dsh-commandcode-go-provider
Latest update
Aug 21, 2026
Category
Models & Providers
GitHub stars
3
Format
plugin
Catalog evidence
Upstream dsh.bundle evidence
Evidence path
package.json#dsh.bundle
Checked against
0.1.0-rc.8
Upstream check date
2026-08-20

This evidence comes from the upstream catalog. This site has not installed, run, or security-reviewed the plugin.

Install

Start with a prompt that asks an agent to review the GitHub repository and source. Switch to the command if you want to install it yourself.

Copy this prompt into DSH, Codex, or another agent and ask it to review the GitHub repository and source first.

Do not install or run any commands yet. Read this plugin's GitHub repository, README, and relevant source code. Then answer the questions below clearly and directly so I can decide whether it fits my needs:

1. What is this plugin, and what problem does it solve?
2. Who is it for, and what are its typical use cases?
3. How is it used after installation? Include one minimal example.
4. What known limitations or privacy, security, compatibility, or maintenance risks does it have?
5. Give a clear recommendation: recommend, conditionally recommend, or do not recommend, with reasons.

Distinguish statements documented by the repository, inferences from source code, and unknowns. If evidence is insufficient, say so explicitly. Do not guess or simply repeat the README.

GitHub: https://github.com/jiesou/dsh-commandcode-go-provider
Plugin: dsh-commandcode-go-provider
Author: jiesou

Check the source files

Read the README and other files from this plugin directory before installing.

File explorer4 files
README.en.mdSource · read only
README language

dsh-commandcode-go-provider

Command Code Go API provider for dsh.

简体中文

Command Code subscriptions come in two flavors:

1. Provider API: standard OpenAI-compatible endpoints that plug into any agent harness directly, no third-party plugin needed. 2. Go / GOAT / Pro Plan: calling the Provider API returns 403 upgrade_required; these plans can only be used through Command Code's private CLI gateway /alpha/generate (vendor lock-in).

This plugin solves the second case: it streams over /alpha/generate through DSH's native LlmAdapter, letting Go / GOAT / Pro Plan users use their subscribed models directly inside DSH. Models are never hardcoded — the plugin periodically fetches the live catalog from /provider/v1/models and filters it by the Go plan membership rule:

  • Open-source models are kept by default (deepseek, Qwen, MiniMaxAI, xiaomi, stepfun, tencent, nvidia, moonshotai, etc.).
  • A few premium exceptions are hardcoded for the ones the Go plan includes, e.g. GPT-5.6 Luna, Grok 4.5, Muse Spark 1.2 Contributor.
  • All other premium models (Claude, Gemini, Grok 4.6, ...) are excluded.

It then merges each model's Reasoning Effort support from the official CLI catalog (CDN).

Install

From npm (prebuilt, recommended):

dsh plugin --profile web add @jiesou/dsh-commandcode-go-provider

Or from GitHub:

dsh plugin --profile web add github:jiesou/dsh-commandcode-go-provider

Your Command Code API key should be written to ~/.dsh/.credentials.yaml:

echo 'COMMANDCODE_API_KEY: [your key, be like user_xxxx]' >> ~/.dsh/.credentials.yaml

After installing

Store your API key through DSH's credentials service (written by the web Models page).

No model config is needed — on startup the plugin syncs the models included in your Go plan from /provider/v1/models, and merges per-model Reasoning Effort support from the official CLI catalog (CDN). After install, just pick the Command Code Go provider and a model in the web Models page.

Configuration

All fields optional, defaults work out of the box:

- id: commandcode-go
  name: '@jiesou/dsh-commandcode-go-provider'
  config:
    apiKeyEnv: COMMANDCODE_API_KEY
    baseURL: https://api.commandcode.ai
    maxTokens: 64000
    defaultContextWindow: 1000000
FieldTypeDefaultDescription
apiKeyEnvstring"COMMANDCODE_API_KEY"Env var name (or credential ref) holding the API key
baseURLstring"https://api.commandcode.ai"Command Code gateway base URL; /alpha/generate is appended
maxTokensnumber64000Per-request output token cap
defaultContextWindownumber1000000Fallback context capacity when a model has no exact value

Reasoning effort needs no configuration: the plugin merges each model's supported levels from the official CLI catalog (CDN); models without known levels expose the full ladder (off plus minimal to max), and the gateway decides the default depth.

Credit

Port of brent-weatherall/opencode-commandcode-provider to DSH.

This plugin adds dynamic reasoning effort extraction, parsed from <https://cdn.jsdelivr.net/npm/command-code@latest/dist/bundled/command-code-knowledge/reference/models.md>.

License

[MIT](LICENSE)

Back to searchOpen GitHub repository

More related plugins

View category