Starstruk Logo MarkStarstruk

v1.0.1

GyulyVGC/sniffnetv1.0.1Jan 6, 2026by asdek

AI Summary

This release focuses on stability and reliability, introducing enhanced error diagnostics, a new DuckDuckGo API integration, and updated OpenAI configurations to bypass content filters and improve output capacity.

Key Highlights

  • Enhanced error diagnostics with auto-adjustment of max_tokens limits.
  • Migrated to a new DuckDuckGo API for improved search reliability.
  • Added authorization framework to bypass OpenAI, Anthropic, and Google content filters.
  • Switched default model from gpt-5 to o4-mini due to evaluation instability.
  • Increased max_tokens limits across multiple agents for better output handling.

New Features

  • Detailed stop reason reporting in error messages.
  • Automatic max_tokens adjustment when stop reason is length.
  • Comprehensive test coverage for DuckDuckGo search scenarios.
  • Explicit authorization framework in all agent prompts.
  • Improved vector store communication formatting with 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