Dies ist eine ältere Version. Aktuell ist Version 0.6.9. OpenFang 0.6.9 · Veröffentlicht:
Installationsdateien 0.4.1
| Architektur | Typ | Bereich | Dateigröße | Download | SHA256 |
|---|---|---|---|---|---|
| 64-Bit | ZIP → Portabel | — | — | github.com | VirusTotal |
| ARM64 | ZIP → Portabel | — | — | github.com | VirusTotal |
Link und SHA256 stammen aus dem Community-Manifest des Windows-Paket-Managers. Vergleichen Sie den Hash der heruntergeladenen Datei, bevor Sie sie ausführen.
Versionshinweise
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.
