v0.4.1

RightNow-AI/openfangv0.4.1Mar 14, 2026by jaberjaber23

AI Summary

Fixes memory recall loops, sanitizes errors in channels, and improves configuration handling and backups.

Key Highlights

Fixed memory recall loop to prevent redundant function calls
Channel bridge now sanitizes LLM errors for user-friendly display
HAND.toml parser now accepts both flat and table formats
Config backup is created before any auto-rewrite
Log level configuration now takes effect

Full Release Notes

## Bug Fixes

- **Memory recall loop** (#583): `build_memory_section()` no longer tells the model to call `memory_recall` when memories are already injected into the prompt. Models now use provided memories directly.
- **Raw errors in channels** (#584): Channel bridge sanitizes LLM error messages before sending to users. Rate limits, auth errors, and JSON dumps are replaced with clean user-friendly messages.
- **HAND.toml format** (#588): Parser now accepts both flat root-level format and the documented `[hand]` table format.
- **Token quota exceeded** (#591): Pre-emptive quota-aware compaction triggers before LLM calls when session token count approaches remaining hourly quota headroom.
- **log_level config** (#594): `log_level` in config.toml now takes effect. Priority: `RUST_LOG` env var > config.toml `log_level` > default `"info"`.
- **Max iterations error** (#599): Error message now includes guidance on configuring `[autonomous] max_iterations` in agent.toml.
- **Config backup** (#578): config.toml is backed up to config.toml.bak before any auto-rewrite (provider key save, config set/unset).

## Enhancements

- **Default model in Web UI** (#593): Spawn wizard fetches default_provider/default_model from `/api/status` instead of hardcoding groq/llama-3.3-70b-versatile.