Starstruk Logo MarkStarstruk

v1.0.1

met4citizen/TalkingHeadv1.0.1Jan 6, 2026by asdek

AI Summary

This release focuses on stabilizing the agent system by improving error reporting, search reliability, and content filter bypass capabilities. Key updates include a migration to a new DuckDuckGo API, enhanced diagnostic tools for LLM failures, and a temporary switch to a more stable model configuration.

Key Highlights

  • Migrated to new DuckDuckGo API with HTML response parsing for significantly improved reliability
  • Added explicit authorization framework to prevent blocking by OpenAI and Anthropic content filters
  • Enhanced error diagnostics by adding stop reasons and auto-adjusting max_tokens limits
  • Temporarily switched primary agent from `gpt-5` to `o4-mini` to address prompt evaluation instability
  • Added customer interaction protocol for the AskUser tool

New Features

  • Added customer interaction protocol for AskUser tool
  • Enhanced message formatting in vector store communications with document match scores
  • Added explicit authorization framework to all agent prompts

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