Starstruk Logo MarkStarstruk

v1.0.1

vxcontrol/pentagiv1.0.1Jan 6, 2026by asdek

AI Summary

Bug fix release improving error diagnostics with stop reason tracking, migrating DuckDuckGo search to new API, adding provider guardrails bypass for penetration testing context, and updating OpenAI configuration for stability.

Key Highlights

  • Enhanced Error Diagnostics with stop reason in error messages
  • DuckDuckGo Search Stability improvements via new API
  • Provider Guardrails Bypass for penetration testing content filters
  • OpenAI Configuration Updates with o4-mini model and increased max_tokens

New Features

  • Stop reason tracking (e.g., 'length' indicates need to increase max_tokens)
  • DuckDuckGo API migration with HTML response parsing
  • Explicit authorization framework in agent prompts for content filters
  • Temporary switch from gpt-5 to o4-mini for stability
  • Improved message formatting in vector store communications

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