DeepSeek Harness

DeepSeek Harness (dsh) is DeepSeek’s open-source coding agent harness. It provides workspaces, a terminal, file editing, Skills, planning, and a Web UI. Its OpenAI Chat Completions compatibility lets it connect to AIHubMix.

This guide was tested on August 14, 2026 with DeepSeek Harness 0.1.0-rc.6. Harness is still a developer preview, so later releases may change fields or UI details.

Quick summary

The integration requires four values:

Setting	Value
Provider ID	`aihubmix`
Base URL	`https://aihubmix.com/v1`
API protocol	`openai-completions`
API key environment variable	`AIHUBMIX_API_KEY`

After configuration, the Models page shows AIHubMix as configured.

AIHubMix configured on the DeepSeek Harness Models page

What do you need?

Before you begin, prepare:

An active AIHubMix API key
Node.js 22.19.0 or later, including Node.js 24+
Network access to the npm registry and https://aihubmix.com

Check Node.js and npm:

node --version
npm --version

How do you install DeepSeek Harness?

Install the published npm package without cloning the source repository:

npm install -g @deepseek-ai/dsh

Verify the installation:

dsh --version

If the shell reports dsh: command not found, run npm config get prefix and make sure its bin directory is included in PATH.

How do you start the Web UI?

Run the following command from the directory you want to use as the workspace:

dsh web --port 3080

Open this URL:

http://127.0.0.1:3080

On first use, select or add a workspace before sending an Agent request.

How do you configure the AIHubMix provider?

Open Settings > Models > Add a custom provider, then enter the following values:

Custom provider form in DeepSeek Harness

Field	Recommended value	Notes
Provider ID	`aihubmix`	Lowercase identifier; use `aihubmix-gateway` if it is already taken
Display name	`AIHubMix`	Name shown in the model selector
Base URL	`https://aihubmix.com/v1`	Must include `/v1`
API protocol	`openai-completions`	OpenAI Chat Completions compatible protocol
API key	Your AIHubMix API key	Harness stores it as a credential and does not show the plaintext value again

Harness appends /chat/completions to the Base URL. The resulting endpoint is:

https://aihubmix.com/v1/chat/completions

Do not put the full /chat/completions path in the Base URL field.

Add auto or another model

After entering the Base URL and API key, select Fetch available models. Harness requests GET https://aihubmix.com/v1/models and shows the currently available model IDs.

Available AIHubMix models discovered by DeepSeek Harness

For an initial connection test, you can add only auto and set its display name to Auto. auto is AIHubMix’s automatic model selection entry point. To use a specific model, select it from the fetched list or choose Add model and enter the exact model ID. The graphical model selector only shows models registered in the current provider catalog.

Select Create provider to save the configuration.

auto vs specific models

Choice	When to use it
`auto`	Initial connection tests, or automatic model selection by AIHubMix
Specific model ID	A fixed model capability, version, or reproducible result is required

Both choices use the same provider, Base URL, and API key. Switching models does not require creating the provider again.

Store the API key in an environment variable

For development machines and CI, Harness can reference an environment variable. Edit $HOME/.dsh/settings.yaml:

llm-pi-ai:
  providers:
    aihubmix:
      displayName: AIHubMix
      apiKeyEnv: AIHUBMIX_API_KEY
      api: openai-completions
      baseURL: https://aihubmix.com/v1
      models:
        - id: auto
          name: Auto
          contextWindow: 1000000
          maxTokens: 32768

agent-default-model:
  provider: aihubmix
  model: auto

Set the key before starting Harness:

export AIHUBMIX_API_KEY='sk-***'
dsh web --port 3080

When the key comes from the launch environment, the settings page displays a read-only message without revealing the value.

AIHubMix provider details in DeepSeek Harness

Restart Harness after changing the environment variable.

Select a model and test a conversation

Close Settings, open the model selector at the lower right of the prompt box, and choose Auto or another model you added.

Auto selected in the DeepSeek Harness model selector

Send a minimal test message:

Reply with exactly: AIHubMix connection successful

Receiving the expected response confirms the connection between Harness, the OpenAI Chat Completions compatible endpoint, and AIHubMix.

Successful AIHubMix response in DeepSeek Harness

Run a headless test

You can also test without the Web UI:

export AIHUBMIX_API_KEY='sk-***'
dsh --profile headless \
  'Reply with exactly DSH_AIHUBMIX_OK and do not use tools.'

A successful run prints DSH_AIHUBMIX_OK.

FAQ

Why does Harness show MISSING_CREDENTIAL?

Harness did not receive AIHUBMIX_API_KEY from its launch environment. Set the variable and launch Harness from the same terminal:

test -n "$AIHUBMIX_API_KEY" && echo configured

Why does model discovery return 401?

Check that the API key is valid and does not contain extra spaces or line breaks. The model discovery request uses Bearer authentication.

Why is Auto the only model in the selector?

The selector shows only models registered in the current provider catalog. Open Settings > Models > AIHubMix > Edit, then use Fetch available models or add an exact model ID manually.

Why does Harness report UNKNOWN_MODEL?

The current provider catalog does not contain that model ID. Model IDs are case-sensitive, so use the exact value returned by model discovery.

Why does the connection time out?

Check DNS, your organization network, and local proxy settings. If the browser uses a system proxy but the terminal does not, configure HTTP_PROXY, HTTPS_PROXY, and NODE_USE_ENV_PROXY=1 in the terminal that launches dsh.

Security guidance

Do not commit API keys to Git or include them in screenshots and shared scripts
Prefer Harness credential storage or the AIHUBMIX_API_KEY environment variable
Do not print a complete API key while troubleshooting
Use the CI platform’s secret management feature to inject environment variables

Last updated: August 14, 2026

Coding Agents

IDE Integrations

Agent / Workflow

SDKs & Frameworks

Quick summary

What do you need?

How do you install DeepSeek Harness?

How do you start the Web UI?

How do you configure the AIHubMix provider?

Add auto or another model

auto vs specific models

Store the API key in an environment variable

Select a model and test a conversation

Run a headless test

FAQ

Why does Harness show MISSING_CREDENTIAL?

Why does model discovery return 401?

Why is Auto the only model in the selector?

Why does Harness report UNKNOWN_MODEL?

Why does the connection time out?

Security guidance

​Quick summary

​What do you need?

​How do you install DeepSeek Harness?

​How do you start the Web UI?

​How do you configure the AIHubMix provider?

​Add auto or another model

​auto vs specific models

​Store the API key in an environment variable

​Select a model and test a conversation

​Run a headless test

​FAQ

​Why does Harness show MISSING_CREDENTIAL?

​Why does model discovery return 401?

​Why is Auto the only model in the selector?

​Why does Harness report UNKNOWN_MODEL?

​Why does the connection time out?

​Security guidance

Quick summary

What do you need?

How do you install DeepSeek Harness?

How do you start the Web UI?

How do you configure the AIHubMix provider?

Add auto or another model

auto vs specific models

Store the API key in an environment variable

Select a model and test a conversation

Run a headless test

FAQ

Why does Harness show MISSING_CREDENTIAL?

Why does model discovery return 401?

Why is Auto the only model in the selector?

Why does Harness report UNKNOWN_MODEL?

Why does the connection time out?

Security guidance