Skip to main content

JetBrains with Continue and Verdictan

Continue uses the same YAML model configuration in its JetBrains and VS Code extensions.

Configure a local secret​

Put the model-client token in a git-ignored Continue environment file, such as ~/.continue/.env:

VERDICTAN_IDE_TOKEN=<client-api-token>

The IDE extension does not inherit all values from an interactive shell environment. After you change this file, start the IDE again.

Configure the model​

name: Verdictan
version: 1.0.0
schema: v1

models:
  - name: Verdictan Chat
    provider: openai
    model: your-model-id
    apiBase: http://127.0.0.1:41002/v1
    apiKey: ${{ secrets.VERDICTAN_IDE_TOKEN }}
    roles:
      - chat
      - edit
      - apply

Replace your-model-id with a model returned by /v1/models. Continue's deprecated config.json examples and generic IDE proxy settings are not part of this integration.

See Continue's config reference for the format.

Verify​

Select Verdictan Chat. Send a request. Make sure that the event tail shows the request in verdictan events tail --since 10m --follow.

Next steps​