Support Agent mode with Llama.cpp provider.

[cgruver]

Validations

• I believe this is a way to improve. I'll try to join the Continue Discord for questions
• I'm not able to find an open issue that requests the same enhancement

Problem

With this PR merged - ggml-org/llama.cpp#12379 - Llama.cpp now supports streaming tool calls.

Solution

Enable Agent mode when the model provider is Llama.cpp

[drrros]

@cgruver
You can add

    capabilities:
      - tool_use

to your config and agent mode would be enabled for llama.cpp provider

[cgruver]

@drrros Yes, that's what I am currently doing. I can use the OpenAI compatible API. But, Llama.cpp also has its own API as well. I'm currently using it with the provider type of openai

[github-actions]

This issue hasn't been updated in 90 days and will be closed after an additional 10 days without activity. If it's still important, please leave a comment and share any new information that would help us address the issue.

[github-actions]

This issue was closed because it wasn't updated for 10 days after being marked stale. If it's still important, please reopen + comment and we'll gladly take another look!