Bug: GitHub Copilot is unable to fetch Ollama models

[curia-damiano]

Select Topic Area

Bug

Body

I have freshly installed Ollama on my Mac.
GitHub Copilot (latest stable version as of today, with latest stable version of VS Code) finds the Ollama model.
But then:

• the plugin crashes when trying to invoke the model. It says there is a network error. Meanwhile, the model is currently working perfectly in Ollama
• since that, retrieving the Ollama model list crashes.

[github-actions[bot]]

💬 Your Product Feedback Has Been Submitted 🎉

Thank you for taking the time to share your insights with us! Your feedback is invaluable as we build a better GitHub experience for all our users.

Here's what you can expect moving forward ⏩

• Your input will be carefully reviewed and cataloged by members of our product teams. 
  • Due to the high volume of submissions, we may not always be able to provide individual responses.
  • Rest assured, your feedback will help chart our course for product improvements.
• Other users may engage with your post, sharing their own perspectives or experiences. 
• GitHub staff may reach out for further clarification or insight. 
  • We may 'Answer' your discussion if there is a current solution, workaround, or roadmap/changelog post related to the feedback.

Where to look to see what's shipping 👀

• Read the Changelog for real-time updates on the latest GitHub features, enhancements, and calls for feedback.
• Explore our Product Roadmap, which details upcoming major releases and initiatives.

What you can do in the meantime 💻

• Upvote and comment on other user feedback Discussions that resonate with you.
• Add more information at any point! Useful details include: use cases, relevant labels, desired outcomes, and any accompanying screenshots.

As a member of the GitHub community, your participation is essential. While we can't promise that every suggestion will be implemented, we want to emphasize that your feedback is instrumental in guiding our decisions and priorities.

Thank you once again for your contribution to making GitHub even better! We're grateful for your ongoing support and collaboration in shaping the future of our platform. ⭐

[m-djawadi]

It sounds like Copilot may be having trouble communicating with the local Ollama server.

A few things to try:

• Make sure Ollama is running and accessible via http://localhost:11434/ (or whatever port it uses)
• Restart VS Code after launching Ollama
• Check for any firewall or network restrictions that might block local requests
• Ensure you're using the latest versions of both Copilot and the Ollama plugin

If it still fails, checking the Developer Tools console in VS Code (Help → Toggle Developer Tools) might show more detailed errors.

Hope this helps narrow it down!

[agarzon-orangerine]

What if I have my ollama API running in a different computer (same network)?

I still can access my ollama API from any other LLM client, it fails only with vscode.

Where can I modify those settings?

[philferriere]

I run ollama on the same network using a beefier machine. It would be great if it was possible to configure ollama host address and port settings to be used by GitHub Copilot. Thanks!

[rpm0372]

I have the same problem. Also, I've noticed that vscode seems to completely ignore Ollama's OLLAMA_HOST environment variable. I guess for now I'll stick with Theia IDE. It works flawlessly.

[curia-damiano]

In my case, I am running Ollama locally. Ollama is installed with homebrew. I start the service with: brew services start ollama ollama run deepseek-r1:70b From the terminal, ollama is perfectly working. From VS Code, it fails fetching the models, even if Ollama is installed locally. What can I do to troubleshoot this?

…

On Tue, Apr 15, 2025 at 7:07 PM Phil Ferriere ***@***.***> wrote: I run ollama on the same network using a beefier machine. It would be great if it was possible to configure ollama host address and port settings to be used by GitHub Copilot. Thanks! — Reply to this email directly, view it on GitHub <#156568 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AEN72M7EYZN6Y33AGRHTMYD2ZU4GLAVCNFSM6AAAAAB3BLDQAWVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTEOBUGQ4DINA> . You are receiving this because you authored the thread.Message ID: ***@***.***>

-- *Damiano Curia* Swiss mobile: +41 76 50 40 60 2 Italian mobile: +39 348/360.25.73 skype: curia.damiano email: ***@***.*** www: http://curia.me

[clusterfuck-cyber]

I'm having the exact same issue. Failed to fetch models.

[ViniciusRed]

i was having the same problem on linux i was using the package that comes with archlinux but after installing it using the download from their official website it solved the problem