Add a switchable local Ollama brain for the voice loop - #25
Open
tomavic wants to merge 1 commit into
Open
Conversation
Lets the voice console swap between Claude and a local Ollama model
live ("switch to local model" / "switch to claude"), for fully
offline, no-cost conversation. The local brain gets read-only
read_file/list_directory tools, gated through the same spoken
yes/no/details permission flow Claude's tools already use. Reasoning
mode (think) is disabled by default for latency: Qwen3 was measured
at 30s to first word with it on vs under a second with it off.
Also fixes Kokoro's "Defaulting repo_id" console print and quiets
cosmetic torch/huggingface_hub warnings on every launch.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcG3U9PUE5r8Uk9xUTN2Jj
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Lets the voice console swap between Claude and a local Ollama model live ("switch to local model" / "switch to claude"), for fully offline, no-cost conversation. The local brain gets read-only read_file/list_directory tools, gated through the same spoken yes/no/details permission flow Claude's tools already use. Reasoning mode (think) is disabled by default for latency: Qwen3 was measured at 30s to first word with it on vs under a second with it off.
Also fixes Kokoro's "Defaulting repo_id" console print and quiets cosmetic torch/huggingface_hub warnings on every launch.
Claude-Session: https://claude.ai/code/session_01EcG3U9PUE5r8Uk9xUTN2Jj