v0.6.0
TrafficGuard/typedaiv0.6.0Feb 3, 2025by danielcampagnolitg
AI Summary
Feature-rich release adding OpenAI o1/o3-mini, DeepSeek R1 multi-provider, CePO multi-agent implementation, UI enhancements with caching and chat parameters, and multi-agent debate capabilities.
Key Highlights
- Added OpenAI o1 and o3-mini
- DeepSeek R1 for multiple providers
- CePO (Cerebras Planning and Optimization) multi-agent implementation
- UI caching for agents and chats
- Added temperature, topK parameters to chat UI
- Multi-agent debate LLM implementation with reasoning models
New Features
- OpenAI o1 and o3-mini models
- DeepSeek R1 multi-provider support
- CePO multi-agent implementation
- Agent and chat UI caching
- Chat UI parameters (temperature, topK, etc.)
- Chat keyboard shortcuts
- Perplexity sonar models
- LLM maxRetries option
- Improved project detection using filesystem tree
- Multi-agent debate implementation
- fastLlama70b LLM implementation
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