Starstruk Logo MarkStarstruk

v0.4.2

RightNow-AI/openfangv0.4.2Mar 14, 2026by jaberjaber23

AI Summary

Improves detection logic for long commands, adds new providers like NVIDIA NIM, and introduces YOLO mode for auto-approval.

Key Highlights

  • LoopGuard now uses keyword-based detection instead of length heuristics
  • Model dropdown now shows provider:model format
  • Telegram typing indicator refreshes continuously during processing
  • Added NVIDIA NIM provider with 5 models
  • Introduced YOLO mode for auto-approving tool calls

New Features

  • NVIDIA NIM provider
  • YOLO mode
  • Skill output persistence in dashboard

Full Release Notes

## Bug Fixes

- **LoopGuard poll detection** (#603): Removed fragile `cmd.len() < 50` heuristic. Poll detection is now purely keyword-based — long kubectl/docker commands are correctly identified.
- **Custom model provider display** (#581): Model switcher dropdown now shows `provider:model` format instead of just the display name.
- **Telegram typing indicator** (#571): Typing indicator now refreshes every 4 seconds continuously during LLM processing, instead of expiring after 5 seconds.
- **"No agent selected" error** (#569): Agents created via API are now immediately registered in the channel router's name cache.
- **Tool calls denied by approval** (#537): Denial message now includes guidance to use `auto_approve = true` in config.toml or `--yolo` flag.
- **WhatsApp sender metadata** (#597): MessageRequest and PromptContext now have sender_id/sender_name fields for identity-aware agents.
- **LLM auth boot failure** (#572): Already fixed in v0.4.0 (auto-detect fallback). Commented for users on older versions.

## Enhancements

- **NVIDIA NIM provider** (#579): Added as OpenAI-compatible provider with 5 models (nemotron-70b, llama-3.1-405b/70b, mistral-large, nemotron-4-340b). Set `NVIDIA_API_KEY` to use.
- **YOLO mode** (#573): `openfang start --yolo` auto-approves all tool calls. Also configurable via `auto_approve = true` in `[approval]` section.
- **Skill output persistence** (#596): Tool/skill output cards in dashboard now default to expanded instead of collapsed, keeping results visible.