| Version | Change log |
| Moto assistant 0.5.11 Dec 17, 2024 |
Sync main to dev after 0.5.11 is released. by @louis-jan in #4225 chore: bump web version 0.5.11 by @louis-jan in #4224 feat: update app download universal for macos by @urmauur in #4230 chore: update download url for macos universal by @hiento09 in #4232 chore: fix beta ci by @hiento09 in #4233 chore: roadmap template fix by @gabrielle-ong in #4227 fix: list style off screen by @urmauur in #4231 fix: hide Vulkan option for users who don't have GPU by @louis-jan in #4226 enhancement: default open Jan Input Box Settings and Right panel by @urmauur in #4234 feat: add auto build when PR is approved by @hiento09 in #4241 fix: performance issue when pasting long content into the chat input box by @urmauur in #4240 fix: crash markdown render code block without triple backtick by @urmauur in #4248 chore: fix openai vision models by @louis-jan in #4246 enhancement: better error handing for remote models when there's no internet connection by @urmauur in #4252 fix: auto scrolling to bottom by @urmauur in #4256 chore: 4244 - deprecate groq llama 3.1 70B Versatile by @louis-jan in #4265 chore: add ci janhq/core publish npm by @hiento09 in #4259 fix: markdown inline inputbox by @urmauur in #4269 fix: 4238 - fix default max_tokens set on remote models by @louis-jan in #4266 feat: add cicd for janhq/joi by @hiento09 in #4270 fix: disabled start model from mymodel list when server is running by @urmauur in #4277 enhancement: move token speed to bottom by @urmauur in #4276 enhancement: remove tooltip local api server when server start by @urmauur in #4275 feat: product analytic UI by @urmauur in #4262 Fix: Fix issue with duplicate events on Enter key press during CJK character composition in chat input by @cuhong in #4268 feat: reroute threads and messages requests to cortex.cpp backend by @louis-jan in #4249 |
| Moto assistant 0.5.11 Dec 5, 2024 |
Features: feat: macos universal @hiento09 (#4197) Fixes: fix: syntax highlight configurations that made everything dark @louis-jan (#4223) fix: react-markdown crash on code highlighting - threads switching do not take effect sometime @louis-jan (#4216) fix: 4208 - Empty title with special characters @louis-jan (#4212) fix: 4209 - Inconsistent max tokens value persistence @louis-jan (#4213) fix: 4155 - Queue up health check on server restarting @louis-jan (#4201) fix: 4162 - Graceful OpenRouter error handling @louis-jan (#4200) fix: 4165 - Refactor message builder to avoid sending empty messages @louis-jan (#4199) fix: 4178 - current generated message options should be visible @louis-jan (#4196) Maintenance: chore: Hotfix 0.5.11 - Release cut @louis-jan (#4217) chore: Sync main to dev after 0.5.10 @louis-jan (#4194) chore: add NGL settings for vision models @louis-jan (#4214) chore: update the docs for the new Cortex server port @louis-jan (#4190) |
| Moto assistant 0.5.10 Dec 3, 2024 |
Features: feat: Privacy docs @eckartal (#4080) feat: update Jan’s client request to adapt API changes from Cortex @louis-jan (#4130) enhancement: increased max-token limit claude-3.5 @urmauur (#4112) feat: stop word model setting @urmauur (#4113) feat: add more Groq models @sharunkumar (#3843) feat: Anthropic Model Updates @px100 (#3888) Fixes: fix: scrollbar issue css @louis-jan (#4191) fix: 4171 - Model loading gets stuck on stop @louis-jan (#4177) fix: high performance large convo rendering @louis-jan (#4166) fix: smooth the loader animation @louis-jan (#4167) fix: Glitch theme applies on launch @louis-jan (#4168) fix: token speed should not be calculated based on state updates @louis-jan (#4159) fix: remove filter on recommend model @urmauur (#4156) fix: scroll bottom when switch thread @urmauur (#4152) fix: convo component re-render every single token yield @louis-jan (#4150) fix: default local model from starter screen @urmauur (#4151) fix: app re-render issues caused by bad state handling @louis-jan (#4146) fix: handle case stop word too long @urmauur (#4145) fix: wrong component wrapping and state handling cause excessive app re-render @louis-jan (#4141) fix: 4098 - factory reset closes the app & never opens again on Linux @louis-jan (#4139) fix: memory leak lowlight dependencies @urmauur (#4134) fix: default local model from starter screen @urmauur (#4135) fix: 4096 - failed to get huggingface models @louis-jan (#4133) fix: 4094 - gpu mode toggle on by default but not affect for the first time launch @louis-jan (#4132) fix: 4012 - active model should be gone as soon as cortex.cpp server is killed @louis-jan (#4131) fix: 3986 - invalid request should show clear error message @louis-jan (#4119) fix: memory leak when the code block response is too long @urmauur (#4129) fix: Line-number and border color code block UI @urmauur (#4105) fix: 4086 - editing message should not send follow-up messages @louis-jan (#4116) fix: handle case markdown value no space @urm |
| Moto assistant 0.5.9 Nov 22, 2024 |
Features: Feat: configure HTTP Proxy via cortex.cpp Feat: configure HuggingFace API Token via cortex.cpp Enhancement: UX local server page Chore: refactor re-render components Feat: support cortex.cpp engine variants Feat: new UI code block and Enable copying of code blocks or plain text mid-stream Fixes: Fix: model parameters settings local API server Fix: factory reset hang on wiping data Fix: Phi 3 Mini Instruct model download URL replacement Fix: edge cases empty code block Fix: correct download script to relocate DLL files properly Fix: temporary create a deps folder to have cortex.cpp work Fix: disable timeout on model load Fix: bump cortex.cpp to latest version - recursively scanning models folder should also include remote models Fix: correct OpenAI o1 model parameters Fix: inconsistent error handling Fix: handle symlink model import failure - fallback to legacy model run Fix: model import edge cases Fix: improper line break on response message Fix: Jan 0.5.8 - Couldn’t upload documents to threads Fix: API local server max ctx_len not update when switch model Fix: max tokens parameters - OpenRouter Maintenance: Chore: version bump 0.5.9 Chore: remote models error handling Chore: refactor re-render components Chore: correct discord message notification |
| Moto assistant 0.5.7 Oct 24, 2024 |
Features: feat: support markdown on user message @urmauur (#3848) feat: save instruction for new threads as a stable feature @urmauur (#3798) feat: Jan beta version @hiento09 (#3835) Fixes: fix: update broken/outdated hyperlink @Haleshot (#3857) fix: hardware section @urmauur (#3866) fix: inconsistent state of downloading multi-modal @urmauur (#3862) fix: context length input value isn't update @urmauur (#3854) fix: correct eos token of llava models @louis-jan (#3847) fix: api playground text overlap button and search hub model @urmauur (#3833) fix: enable scroll modal component @urmauur (#3816) fix: reset window state after disconnected from multi monitor @urmauur (#3797) fix: issue ellipsis text on model selector and model start loader @urmauur (#3802) fix: update base url edit page docs @urmauur (#3795) Maintenance: chore: replace windows codesign cert @hiento09 (#3839) ci: disable turbo cache @hiento09 (#3836) ci: Update jan-docs.yml @hiento09 (#3799) chore: move Jan Docs back into Jan Repo @hiento09 (#3790) |
| Moto assistant 0.5.7 Oct 24, 2024 |
Features: feat: support markdown on user message @urmauur (#3848) feat: save instruction for new threads as a stable feature @urmauur (#3798) feat: Jan beta version @hiento09 (#3835) Fixes: fix: update broken/outdated hyperlink @Haleshot (#3857) fix: hardware section @urmauur (#3866) fix: inconsistent state of downloading multi-modal @urmauur (#3862) fix: context length input value isn't update @urmauur (#3854) fix: correct eos token of llava models @louis-jan (#3847) fix: api playground text overlap button and search hub model @urmauur (#3833) fix: enable scroll modal component @urmauur (#3816) fix: reset window state after disconnected from multi monitor @urmauur (#3797) fix: issue ellipsis text on model selector and model start loader @urmauur (#3802) fix: update base url edit page docs @urmauur (#3795) Maintenance: chore: replace windows codesign cert @hiento09 (#3839) ci: disable turbo cache @hiento09 (#3836) ci: Update jan-docs.yml @hiento09 (#3799) chore: move Jan Docs back into Jan Repo @hiento09 (#3790) |
| Moto assistant 0.5.6 Oct 4, 2024 | Hotfix: graceful error handling model import @louis-jan (#3766) |
| Moto assistant 0.5.6 Oct 4, 2024 | Hotfix: graceful error handling model import @louis-jan (#3766) |
| Moto assistant 0.5.5 Oct 2, 2024 |
Fixes: fix: thread title for remote model from first prompt @urmauur (#3712) fix: #1142 setting groups toggle does not turn off it's nested settings @louis-jan (#3681) fix: overlap text on model selector and loader @urmauur (#3756) fix: XML not render correctly @urmauur (#3743) fix: model dropdown should show recommended models to download @louis-jan (#3742) fix: correct model dropdown for local models @louis-jan (#3736) fix: #3491 - Unable to use tensorrt-llm @louis-jan (#3741) fix: wrong model download location when there is a mismatch model_id @louis-jan (#3733) fix: #3703 - Deepseek-Coder-33B-Instruct is incompatible @louis-jan (#3732) fix: #3727 LLM model download fail can still be used @louis-jan (#3731) fix: #3673 - API responds with Request body is too large @louis-jan (#3729) fix: #3698 - o1 preview models do not work with max_tokens @louis-jan (#3728) fix: #3515 - The default assistant instructions are ignored @louis-jan (#3721) fix: #3513 - Anthropic extension does not forward the system prompt @louis-jan (#3724) fix: #3558 wrong model metadata import or download from HuggingFace @louis-jan (#3725) fix: toolbar overlap chat input @urmauur (#3720) fix: #3693 broken thread.json should not break the entire threads @louis-jan (#3709) fix: remove title local API server page @urmauur (#3710) fix: enhance various minor UI elements @urmauur (#3706) fix: update the condition for generating the title @urmauur (#3702) fix: small leftover issues with new starter screen @urmauur (#3661) fix: #3476 - Mismatch id between model json and path @louis-jan (#3645) fix: #3667 - The recommended label should be hidden @louis-jan (#3687) |
| Moto assistant 0.5.5 Oct 2, 2024 |
Fixes: fix: thread title for remote model from first prompt @urmauur (#3712) fix: #1142 setting groups toggle does not turn off it's nested settings @louis-jan (#3681) fix: overlap text on model selector and loader @urmauur (#3756) fix: XML not render correctly @urmauur (#3743) fix: model dropdown should show recommended models to download @louis-jan (#3742) fix: correct model dropdown for local models @louis-jan (#3736) fix: #3491 - Unable to use tensorrt-llm @louis-jan (#3741) fix: wrong model download location when there is a mismatch model_id @louis-jan (#3733) fix: #3703 - Deepseek-Coder-33B-Instruct is incompatible @louis-jan (#3732) fix: #3727 LLM model download fail can still be used @louis-jan (#3731) fix: #3673 - API responds with Request body is too large @louis-jan (#3729) fix: #3698 - o1 preview models do not work with max_tokens @louis-jan (#3728) fix: #3515 - The default assistant instructions are ignored @louis-jan (#3721) fix: #3513 - Anthropic extension does not forward the system prompt @louis-jan (#3724) fix: #3558 wrong model metadata import or download from HuggingFace @louis-jan (#3725) fix: toolbar overlap chat input @urmauur (#3720) fix: #3693 broken thread.json should not break the entire threads @louis-jan (#3709) fix: remove title local API server page @urmauur (#3710) fix: enhance various minor UI elements @urmauur (#3706) fix: update the condition for generating the title @urmauur (#3702) fix: small leftover issues with new starter screen @urmauur (#3661) fix: #3476 - Mismatch id between model json and path @louis-jan (#3645) fix: #3667 - The recommended label should be hidden @louis-jan (#3687) |
