Repository navigation
feat: OpenAI-compatible providers and hybrid prompt strategy - #159
Merged
Merged
Conversation
Support LM Studio and similar servers via an openai-compatible provider, keep prompts short with auto diff-vs-summaries selection, and document non-thinking model recommendations.
This was referenced Oct 20, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
openai-compatibleprovider support for LM Studio and similar local servers (alongside Ollama), including model listing and JSON-only commit generation.promptStrategy(auto/diff/summaries) so small stages use a single diff→commit call, with summarize-first as the fallback for larger changes.Test plan
pnpm test/ typecheck / lint passprovidertoopenai-compatible, endpointhttp://127.0.0.1:1234/v1, load Qwen2.5-Coder 3B with Reasoning off, generate a commitpromptStrategy: auto, a small staged change uses one model call; a large multi-file stage falls back to summaries