Add support for local models

[Obsidiannite21]

It seems like you already have most of what you need to make this work. Under "Add Model / OpenAI Compatible," I would just enter my Ollama IP address and model name. However, the current issue is that Chaterm requires an API key, which Ollama does not use, so the connection fails. Perhaps we could make the API key optional? I'm not a programmer, so I don't know if there is more that needs to be done, but having local model support would be amazing and something I've been looking for in an SSH client for some time.

[zhouyu123666]

@Obsidiannite21 Thank you for your feedback. Currently, all the solutions for configuring the local LLM are authenticated through API Key. Based on what you said about the Ollama approach, let's see how to handle it here.

[zhouyu123666]

Starting from version 0.5.2, support for ollama was added. If you have time, you can upgrade to the latest version and give it a try!

[Obsidiannite21]

Thank you! Will do!