Merged
Conversation
intentionally-left-nil
approved these changes
Aug 27, 2025
rgbkrk
reviewed
Sep 3, 2025
and add new subclass for groq
read env vars during class declaration for more concise subclassing drop openai from member methods
Contributor
Author
|
@rgbkrk , I've added reading the version from deno.json, but I'm concerned that it would only work when executing from a clone of the repo and not on the published package. Is it possible to include the deno.json in the published package? Or would there be a better approach. |
Contributor
Author
|
What do you think about adding a function here to write the version string to something like |
Contributor
Author
|
I've added VERSION attribute to |
from deno publish --dry-run
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Here in this PR a small-ish refactor of AI Clients is provided to streamline discovering models and running the agentic response loop.
Since many LLM services provide OpenAI-like API endpoints the RuntOpenAIClient can now be used as a base class as-needed. Important factors are
More could be done to have ollama and openai-like clients share a common ancestor for essential members like
.discoverAiModels,.generateAgenticResponseand others that are essential to external operation, but I'll leave that for another PR.Finally, the RUNT_API_KEY (for anaconda idp) can now be used to request chat/completions from an Anaconda endpoint. This means that user need not set any other AI keys or have ollama running to use the AI agent.