Continue

Settings#

Continue reads its models from config.yaml (in ~/.continue/). It has no provider of its own for ITS INCOM AI: use provider: openai with apiBase.

name: ITS INCOM AI
version: 0.0.1
schema: v1

models:
  - name: Qwen3.8 27B
    provider: openai
    model: qwen3.8-27b
    apiBase: https://api.ai.itsincom.org/v1
    apiKey: ${{ secrets.API_KEY }}
    roles: [chat, edit, apply]
    capabilities: [tool_use]
    defaultCompletionOptions:
      contextLength: 131072
      maxTokens: 32768

For another model, add an entry like this one with its id and the context window from Which model.

${{ secrets.API_KEY }} is read from a .env file: ~/.continue/.env, or .continue/.env and .env in your project, which come first.

API_KEY=sk-its-…

The extension does not read your shell's environment variables, so export API_KEY=… in a terminal is not enough.

capabilities: [tool_use] is what turns on Agent mode for a model that Continue does not know. Add image_input only on a model that reads images, such as gemma-4-26b.

Reasoning off#

qwen3.8-27b reasons before every answer. For quick edits you can add a second entry of the same model with reasoning switched off, through requestOptions.extraBodyProperties:

  - name: Qwen3.8 27B, no reasoning
    provider: openai
    model: qwen3.8-27b
    apiBase: https://api.ai.itsincom.org/v1
    apiKey: ${{ secrets.API_KEY }}
    roles: [edit, apply]
    defaultCompletionOptions:
      contextLength: 131072
      maxTokens: 32768
    requestOptions:
      extraBodyProperties:
        reasoning_effort: none

Limits#

• No autocomplete. Continue's tab autocomplete needs fill-in-the-middle, which ITS INCOM AI does not serve. Do not give these models the autocomplete role.
• topK is refused. The API does not know top_k and answers 400: leave topK out of defaultCompletionOptions.
• maxTokens up to 32768. A higher value is refused with 422.