Skip to content

ThunderAI too slow in loading messages when using auto features #862

Description

@desrod

The problem

I have a local LLM running on my MacBook and my Linux laptop, also a DGX on my LAN, accessible via DNS name and direct IP. Standard ports are exposed and works fine with all of my LAN agents and services.

Except ThunderAI, which cannot seem to reach the LLM at all, on localhost, 127.0.0.1, nor the DGX on 192.168.4.x. All are pingable, reachable, and works fine with other scripts and agents from the same client machine.

Sad, because the project looked so promising, but data governance rules strictly prohibit any egress to any public AI models.

Which Operative System are you using?

macOS 26.6.2 (25G82), Linux (26.10)

Which version of Thunderbird are you using?

140.2.1esr-bb10 (aarch64)

Which version of ThunderAI has the issue?

5.0.0pre4

Which integration are you using?

Ollama API

Anything in the Thunderbird console logs that might be useful?

Additional information

No response

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

bugSomething isn't workingstatus: ready for releaseWork complete in the next release branch.

Projects

No projects

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions