Connect Continue to OpenLLM Buddy

Connect Continue (VS Code and JetBrains) to OpenLLM Buddy with an OpenAI-compatible model entry in config.yaml.

Coding · Integration guide

What is Continue?

Continue is an open-source coding assistant for VS Code and JetBrains with chat, inline edit, and autocomplete, configured from a single YAML file. Visit Continue.

Why connect OpenLLM Buddy?

Continue's openai provider accepts a custom apiBase, so your own OpenLLM Buddy deployment can power chat and edits with no extra gateway.

Before you start, create an API key in the console and deploy a model. If anything fails, run the curl test in Step 4 first: no tool can fix a broken endpoint.

1

Install Continue

Install the Continue extension from the VS Code Marketplace or the JetBrains Marketplace, then open its side panel.

2

Edit config.yaml

Open the config from the gear icon in the Continue panel, or edit ~/.continue/config.yaml directly, and add the model.

~/.continue/config.yaml
yaml
name: OpenLLM Buddy
version: 1.0.0
schema: v1
models:
  - name: OpenLLM Buddy
    provider: openai
    model: gemma4:26b
    apiBase: https://openllmbuddy-proxy.botbuddytech.workers.dev/v1
    apiKey: YOUR_API_KEY
    roles:
      - chat
      - edit
      - apply

Continue reloads the file on save. Add an autocomplete role only if your deployment is fast enough for inline suggestions.

3

Chat and edit

Pick OpenLLM Buddy in the model dropdown. Use Ctrl/Cmd + L for chat and Ctrl/Cmd + I for inline edits on selected code.

4

Test the endpoint with curl

Confirm the key, URL, and model id work before debugging Continue. A short JSON reply means the endpoint is healthy.

Terminal
bash
curl -sS https://openllmbuddy-proxy.botbuddytech.workers.dev/v1/chat/completions   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{"model": "gemma4:26b", "messages": [{"role": "user", "content": "Reply with OK"}], "max_tokens": 16}'

Troubleshooting

  • Model does not appear — YAML indentation errors are silent. Open the Continue logs from the panel menu to see the parse error.
  • Older config.json — newer Continue releases read config.yaml. Use the equivalent provider, model, and apiBase keys if you are still on JSON.
  • 401 or 403 — the API key is wrong, revoked, or missing the Bearer prefix. Create a fresh key in the console.
  • 404 on /chat/completions — the base URL must end in /v1, with no trailing /chat/completions and no extra path.
  • Model not found — the model id must match your deployment exactly. Run the curl test and copy the id you used.
  • Timeouts on the first request — a GPU that was idle may still be loading the model. Retry after a minute.
  • Connection refused from Docker or a remote host — use the public HTTPS base URL, never localhost.

Connection details

Use these values wherever Continue asks for an OpenAI-compatible provider.

Reference
text
Base URL:  https://openllmbuddy-proxy.botbuddytech.workers.dev/v1
Chat URL:  https://openllmbuddy-proxy.botbuddytech.workers.dev/v1/chat/completions
API key:   your key from the console
Model id:  gemma4:26b