What's Changed
- feat(model-picker): add Performance filter for 'Runs Well' / 'Hide Too Large' (#946) by @jjang-ai
- fix(speech): adopt FluidAudio 0.14 decoderState parameter (#945) by @mimeding
- fix(security): harden import/export trust boundaries for attachments and shared artifacts (#925) by @mimeding
- fix(provider): send max_tokens to non-OpenAI-reasoning endpoints (#928) by @mimeding
🚀 Features
🧰 Maintenance
- reinforced with more unit tests, fixed kv caching calls, tighten up code. Enabled TurboQuant by default (#938) by @tpae
Full Changelog: 0.17.5...0.17.6