Added 60dB integration#131
Conversation
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 20a37ebb58
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| async fn chat(&self, _messages: &[ChatMessage]) -> Result<Box<dyn ChatResponse>, LLMError> { | ||
| Err(LLMError::ProviderError("Chat not supported".to_string())) |
There was a problem hiding this comment.
Implement 60db chat instead of always erroring
When users select the new LLMBackend::SixtyDb for normal chat flows, this implementation always returns ProviderError("Chat not supported"), so the backend that was added to the provider registry/README cannot be used as an LLM backend. 60db documents an OpenAI-compatible POST /v1/chat/completions endpoint, so chat requests should be routed there (or the provider should not be registered as a chat-capable LLM backend).
Useful? React with 👍 / 👎.
No description provided.