Remove remote/OpenAI-compatible server support, focus on local GGUF only - #903
Closed
Auseven9 wants to merge 1 commit into
Closed
Remove remote/OpenAI-compatible server support, focus on local GGUF only#903Auseven9 wants to merge 1 commit into
Auseven9 wants to merge 1 commit into
Conversation
Strips the ModelOrigin.REMOTE model type, ServerStore, the OpenAI-compatible completion engine, RemoteModelSheet/ServerDetailsSheet, and all associated capability-probing, reasoning-routing, and context-banner logic. The app now only ever runs GGUF models through llama.rn's LocalCompletionEngine. The full native generation parameter panel (system prompt, temperature, top-k/p, min-p, repetition penalties, Mirostat) is untouched, and the existing Talents/AgentRunner tool-calling loop (including the web_search talent that injects live search results into the context window) already worked against any CompletionEngine and needed no changes to keep working for local models. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014iBLsPRqM5fAHYVYuDQexr
Author
|
WiP |
Owner
|
Thanks for the contribution. I'm going to close this as not planned for now. |
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Strips the ModelOrigin.REMOTE model type, ServerStore, the OpenAI-compatible completion engine, RemoteModelSheet/ServerDetailsSheet, and all associated capability-probing, reasoning-routing, and context-banner logic. The app now only ever runs GGUF models through llama.rn's LocalCompletionEngine.
The full native generation parameter panel (system prompt, temperature, top-k/p, min-p, repetition penalties, Mirostat) is untouched, and the existing Talents/AgentRunner tool-calling loop (including the web_search talent that injects live search results into the context window) already worked against any CompletionEngine and needed no changes to keep working for local models.
Claude-Session: https://claude.ai/code/session_014iBLsPRqM5fAHYVYuDQexr
Description
Provide a brief description of the changes made and the issue(s) this resolves.
Fixes # (issue number)
Platform Affected
Checklist