Starstruk Logo MarkStarstruk

v1.0.1

hpcaitech/Open-Sorav1.0.1Jan 6, 2026by asdek

AI Summary

This release focuses on stability and configuration improvements for the Pentagi agent framework. It addresses LLM error handling, migrates search API, and updates OpenAI model configurations to bypass content filters.

Key Highlights

  • Enhanced error diagnostics for LLM tool calls and stop reasons
  • Migrated DuckDuckGo to new API for improved reliability
  • Added authorization framework to bypass provider guardrails
  • Switched OpenAI model to o4-mini due to prompt instability

New Features

  • Customer interaction protocol for AskUser tool
  • Enhanced message formatting in vector stores with document match scores

Full Release Notes

## 🐛 Bug Fixes & Improvements

### Enhanced Error Diagnostics
- Added stop reason to error messages when LLM fails to generate tool calls
- If stop reason is `length`, increase `max_tokens` parameter for the affected agent in provider settings
- Improves troubleshooting and configuration optimization

### DuckDuckGo Search Stability
- Migrated to new DuckDuckGo API with HTML response parsing
- Added comprehensive test coverage with real-world search scenarios
- Significantly improved reliability and result quality

### Provider Guardrails Bypass
- Added explicit authorization framework to all agent prompts
- Prevents blocking by OpenAI, Anthropic, and Google Gemini content filters
- Clarified penetration testing context as pre-authorized activity

### OpenAI Configuration Updates
- Temporarily switched from `gpt-5` to `o4-mini` for primary agent and assistant due to OpenAI prompt evaluation instability
- Increased `max_tokens` limits across multiple agents for better output capacity
- **Recommendation**: Enable Human-in-the-loop mode (`ASK_USER=true` in `.env`) when using OpenAI provider for improved stability

### Additional Improvements
- Enhanced message formatting in vector store communications with document match scores
- Improved clarity in generator and refiner prompts for user task interpretation
- Added customer interaction protocol for AskUser tool

---

**Full Changelog**: https://github.com/vxcontrol/pentagi/compare/v1.0.0...v1.0.1