What's Changed
- test: add model parameter validation rules and persistence tests by @louis-jan in #3618
- Add support for 'o1-preview' and 'o1-mini' models by @RONNCC in #3659
- fix: phi3 medium prompt template by @louis-jan in #3670
- fix: #3667 - The recommended label should be hidden by @louis-jan in #3687
- fix: #3476 - Mismatch id between model json and path by @louis-jan in #3645
- Fix: #1142 setting groups toggle does not turn off it's nested settings by @louis-jan in #3681
- fix: small leftover issues with new starter screen by @urmauur in #3661
- feat: textarea auto resize by @urmauur in #3695
- chore: Copyfix by @0xSage in #3694
- fix: update the condition for generating the title by @urmauur in #3702
- fix: enhance various minor UI elements by @urmauur in #3706
- test: add web helpers, services, utils tests by @louis-jan in #3669
- fix: thread title for remote model from first prompt by @urmauur in #3712
- fix: remove title local API server page by @urmauur in #3710
- test: update test coverage UI component Joi by @urmauur in #3707
- test: add missing tests to Jan core modules by @louis-jan in #3716
- fix: #3693 broken thread.json should not break the entire threads by @louis-jan in #3709
- fix: toolbar overlap chat input by @urmauur in #3720
- chore: The monorepo jest configs should not cover extensions - they would be moved to mini repositories soon by @louis-jan in #3723
- fix: #3558 wrong model metadata import or download from HuggingFace by @louis-jan in #3725
- fix: #3513 - Anthropic extension does not forward the system prompt by @louis-jan in #3724
- fix: #3515 - The default assistant instructions are ignored by @louis-jan in #3721
- fix: #3698 - o1 preview models do not work with max_tokens by @louis-jan in #3728
- enhance: tabs component in model selection by @urmauur in #3730
- fix: #3673 - API responds with Request body is too large by @louis-jan in #3729
- fix: #3727 LLM model download fail can still be used by @louis-jan in #3731
- fix: #3703 - Deepseek-Coder-33B-Instruct is incompatible by @louis-jan in #3732
- fix: wrong model download location when there is a mismatch model_id by @louis-jan in #3733
- ci: auto trigger jan docs ci for new release by @hiento09 in #3734
- fix: #3491 - Unable to use tensorrt-llm by @louis-jan in #3741
- fix: correct model dropdown for local models by @louis-jan in #3736
- fix: model dropdown should show recommended models to download by @louis-jan in #3742
- fix: XML not render correctly by @urmauur in #3743
- chore: improve models and threads caching by @louis-jan in #3744
- release: Jan Release Cut v0.5.5 by @louis-jan in #3746
- fix: Optimize resource watching by @louis-jan in #3747
- chore: add llama3.2 and qwen2.5 models by @louis-jan in #3751
- fix: overlap text on model selector and loader by @urmauur in #3757
- fix: error handling for model imports should be handled gracefully by @louis-jan in #3763
- chore: move Jan Docs back into Jan Repo by @hiento09 in #3790
- fix: update base url edit page docs by @urmauur in #3795
- ci: Update jan-docs.yml by @hiento09 in #3799
- feat: save instruction for new threads as a stable feature by @urmauur in #3798
- fix: issue ellipsis text on model selector and model start loader by @urmauur in #3802
New Contributors
Full Changelog: v0.5.4...v0.5.7-rc1-beta