v0.6.0

abus-aikorea/voice-prov0.6.0Feb 3, 2025by danielcampagnolitg

AI Summary

This release adds new LLM models including OpenAI o1 and o3-mini, and introduces the CePO multi-agent implementation. It also adds caching capabilities for agents and chats in the UI, along with temperature and topK controls.

Key Highlights

Add OpenAI o1 and o3-mini
Add CePO multi-agent implementation
Cache agents and chats in the UI
Update Perplexity LLM to use sonar models
Add Multi-agent debate LLM implementation

New Features

OpenAI o1 and o3-mini support
DeepSeek R1 for multiple providers
CePO multi-agent implementation
Cache agents and chats in the UI
Add temperature, topK to chat UI
Add chat keyboard shortcuts
Update Perplexity LLM to use sonar models
Add LLM maxRetries option
Update project detection to use filesystem tree
Update listing of files to account for .gitignore
Multi-agent debate LLM implementation
Create fastLlama70b.ts implementation
Update GitLab merge request review

Full Release Notes

## What's Changed

* Update cost calculations for cached input tokens

* Add OpenAI o1 and o3-mini

* Add DeepSeek R1 for multiple providers

* Add CePO (Cerebras Planning and Optimization) multi-agent implementation of the LLM interface

* Cache agents and chats in the UI

* Add temperature, topK etc to chat UI

* Add chat keyboard shortcuts

* Update Perplexity LLM and tool to use the sonar models

* Add LLM maxRetries opt

* Update project detection to use the filesystem tree to handle larger projects

* Update listing of files to account for .gitignore in parent directories

* Add Multi-agent debate LLM implementation with reasoning models

* Create fastLlama70b.ts LLM implementation

* Update GitLab merge request review

* Various other fixes/updates

## New Contributors
* @shaneholloman made their first contribution in https://github.com/TrafficGuard/sophia/pull/45

**Full Changelog**: https://github.com/TrafficGuard/sophia/compare/v0.5.0...v0.6.0