Skip to navigation
IntegrationIntegrationsCoding Agents

DeepSeek Harness (gateway)

Route DeepSeek Harness’ LLM calls through the Respan gateway for automatic logging, caching, and model switching. dsh supports custom OpenAI-compatible and Anthropic-compatible providers, so only your RESPAN_API_KEY is needed.

Setup

1

Install dsh

npm install -g @deepseek-ai/dsh
2

Add Respan as a provider

Edit $DSH_HOME/settings.yaml (defaults to ~/.dsh/settings.yaml) and add a provider under the llm-pi-ai section:

llm-pi-ai:
  providers:
    respan:
      apiKeyEnv: RESPAN_API_KEY
      api: openai-completions
      baseURL: https://api.respan.ai/api
      models:
        - id: gpt-4o
        - id: claude-sonnet-4-5-20250929

apiKeyEnv is the name of the environment variable that holds your key. Export it in your shell profile:

export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

You can do the same from the web UI: run dsh web, open Settings, then Models, choose Add a custom provider, and fill in the provider ID respan, the base URL https://api.respan.ai/api, the openai-completions protocol, your key, and at least one model.

No separate provider key needed. The Respan gateway handles provider authentication.

3

Make Respan the default model

dsh’s profiles default to the deepseek-official route. Override the default model with a patch overlay. Save this as ~/.dsh/respan.yml:

- id: agent-default-model
  config:
    provider: respan
    model: gpt-4o
4

Run dsh

dsh --profile tui --patch ~/.dsh/respan.yml

For a one-shot, non-interactive run:

dsh --profile headless --patch ~/.dsh/respan.yml "your task"

All LLM calls now route through Respan.

Switch models

Add more entries under models and change model in the patch overlay (or pick a model in the UI) to use any of the 1000+ models available through the gateway.

gpt-4o
claude-sonnet-4-5-20250929
gemini/gemini-3.5-flash

See the full model list.