Config.yaml Issue: Connecting to local Jan.ai Server Body:

[swapnil0545]

Before submitting your bug report

• I've tried using the "Ask AI" feature on the Continue docs site to see if the docs have an answer
• I believe this is a bug. I'll try to join the Continue Discord for questions
• I'm not able to find an open issue that reports the same bug
• I've seen the troubleshooting guide on the Continue Docs

Relevant environment info

OS: Windows 11
Continue Version: 1.2.8 (check via VS Code → Extensions → Continue → About)
IDE Version: VSCode 1.105.0
Model: DeepSeek-Coder-V2-Lite-Instruct-IQ4_XS (running in Jan AI)
Config:
YAML

name: My Continue Configuration  
version: 1.0.0  
schema: https://continue.dev/schemas/config.json  
models:  
  - name: DeepSeek-Coder-V2-Lite-Instruct  
    provider: ollama  
    model: DeepSeek-Coder-V2-Lite-Instruct-IQ4_XS  
    apiBase: http://localhost:1337/v1/chat/completions  
    apiKey: Bearer janai  
    roles:  
      - chat  
      - edit  
      - apply  
      - summarize  
  

  
  OR link to agent in Continue hub:

Description

To Reproduce
Steps to reproduce the behavior:

Start the Jan.ai application.
Download and load the DeepSeek-Coder-V2-Lite-Instruct-IQ4_XS model.
Start the local server from within Jan.ai (which runs on http://localhost:1337).
Attempt to use the configuration below in continue.dev.
The connection fails.
Expected behavior
continue.dev should successfully connect to the local Jan.ai server and be able to query the DeepSeek-Coder-V2-Lite-Instruct model.

Screenshots / Logs
If applicable, add screenshots or logs to help explain your problem.

Environment (please complete the following information):
Tool: continue.dev
Local Server: Jan.ai
Server Version: [e.g., v0.2.1] (if you know it)
Model: DeepSeek-Coder-V2-Lite-Instruct-IQ4_XS
Configuration File
Here is my current config.yaml:

YAML

name: My Continue Configuration
version: 1.0.0
schema: https://continue.dev/schemas/config.json
models:

• name: DeepSeek-Coder-V2-Lite-Instruct
  provider: ollama # <-- I suspect this is the issue
  model: DeepSeek-Coder-V2-Lite-Instruct-IQ4_XS
  apiBase: http://localhost:1337/v1/chat/completions
  apiKey: Bearer janai
  roles:
  • chat
  • edit
  • apply
  • summarize
    Additional context
    The Jan.ai server is confirmed to be running and accessible. I can interact with it via its built-in Swagger UI at http://localhost:1337/v1/chat/completions.

My hypothesis is that the provider: ollama setting is incorrect for this use case. Since Jan.ai provides an OpenAI-compatible API endpoint, the provider might need to be set to openai. I am unsure of the correct syntax or provider name to use for a local, OpenAI-compatible server.

Could you please provide guidance on the correct configuration to connect continue.dev to a local Jan.ai server?

Thank you

To reproduce

No response

Log output

[bdougie]

Jan is not a provide we support to day, but with the projec tbeing open sourced, we would be happy to take the contribution for this. If you have interest feel free to take a look. Otherwise, I would recommend choosing a provider we support already.

https://docs.continue.dev/customize/model-providers/overview