Starstruk Logo MarkStarstruk

v1.0.1

browser-use/video-usev1.0.1Jan 6, 2026by asdek

AI Summary

This update enhances error diagnostics, improves DuckDuckGo search reliability, and introduces authorization frameworks to bypass provider guardrails. It also adjusts OpenAI configuration to ensure stability.

Key Highlights

  • Enhanced Error Diagnostics with stop reason logging
  • DuckDuckGo Search stability via new HTML response parsing
  • Provider Guardrails Bypass authorization framework
  • OpenAI Configuration updates (switch to o4-mini, increased max_tokens)
  • Human-in-the-loop mode recommendation for OpenAI

Breaking Changes

  • Default model switched from gpt-5 to o4-mini
  • Increased max_tokens limits across multiple agents

New Features

  • Stop reason logging for troubleshooting LLM failures
  • New DuckDuckGo API integration with test coverage
  • Authorization framework for penetration testing context
  • Enhanced message formatting 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