Run the DeepSeek Harness on it

The harness talks to any OpenAI-compatible endpoint, so this is a provider entry rather than an integration.

Base URLhttps://189.24.66.33/v1

The form

In the harness, open the provider settings and choose Custom provider. Five fields matter and the rest can stay as they are.

Field	What to put in it
Provider ID	`relay` (lowercase; it is also the credential name — keep it short)
Display name	黑曜
Base URL	`https://189.24.66.33/v1`
API protocol	`openai-completions`
API key	your key, `sk-relay-...`

Base URL keeps the /v1. This is the OpenAI-shaped route, and an openai-completions client appends only /chat/completions. Dropping the /v1 gives a 404 that reads like an auth failure.

The file, if you would rather not click

The same thing lives in ~/.dsh/settings.yaml. The harness ships one provider, deepseek-official, and this repoints it rather than adding a second:

llm-deepseek:
  baseURL: https://189.24.66.33/v1
  apiKeyEnv: DEEPSEEK_API_KEY
  models:
    - id: glm-5.3-flash-xploded
      contextWindow: 131072

agent-default-model:
  provider: deepseek-official
  model: glm-5.3-flash-xploded

The key is read from the environment rather than the file, so it has to be set where the harness will see it:

export DEEPSEEK_API_KEY=sk-relay-...

On Windows that means the user environment, not just the shell you are standing in. Set it and open a new terminal, or the harness starts before the variable exists and fails with an invalid key.

The Models list

The Models list only decides what appears in the picker. An id you leave out can still be sent directly, so there is no need to paste the whole catalogue in; add the two or three you actually use and fetch the rest from the catalogue endpoint.

If it will not start

An invalid-key error immediately after setting the variable is almost always the terminal, not the key: the old shell still carries the old environment. A key that has genuinely stopped working says so in API Keys.