| Age | Commit message (Expand) | Author |
|---|
| 4 days | fix: sglomni retry contract, booting detection, CLI keys, companion refresh, ...HEADmain | historia |
| 5 days | fix: warn before using a likely too-big chunk size for sglang-omni models | historia |
| 5 days | fix: ZONOS2 only generating 1024 tokens max | historia |
| 6 days | feat: sglang backend support | historia |
| 7 days | slop refactor/dedup | historia |
| 7 days | fix: spec santizer for glm, outetts, miotts, minimax. | historia |
| 7 days | fix: hide speech-to-speech only models from config wizard | historia |
| 7 days | fix: better errors for generate all models | historia |
| 7 days | feat: generate a book with all installed models to compare | historia |
| 8 days | feat: model capabilities lined up in tui menu | historia |
| 8 days | fix: non-clone models correctly supported in tui, restart server when needed | historia |
| 11 days | refactor: overhaul config.py, remove cli default options | historia |
| 11 days | fix: silently failing whisper transcription | historia |
| 12 days | feat: help menu in tui | historia |
| 12 days | feat: menu for language options | historia |
| 12 days | feat: design model support for qwen-tts backend. remove unnecessary port spli... | historia |
| 13 days | feat: combined install/configure tui screens into one menu, removed extraneou... | historia |
| 13 days | refactor: split tts.py into per-backend packages | historia |
