0.6.9

What's Changed

• ci: add disable auto update flag by @Minh141120 in #6143
• add disable auto updater input for nightly build by @Minh141120 in #6159
• enhancement: Add support for mmproj models by @urmauur in #6150
• ci: fix tauri build nightly for linux by @Minh141120 in #6161
• feat: Add GGUF metadata reading functionality by @qnixsynapse in #6120
• fix: handle modelId special char by @urmauur in #6172
• fix: feature toggle auto updater by @Minh141120 in #6175
• feat: add flatpak ci by @Minh141120 in #6177
• Feat: Add flatpak manifest by @qnixsynapse in #4732
• refactor: flathub submission by @Minh141120 in #6182
• Backend Architecture Refactoring (#6094) by @dinhlongviolin1 in #6162
• chore: replace md5 with sha256 for CUDA by @Minh141120 in #6193
• New tutoriasl for v0.6.8 docs by @ramonpzg in #6196
• Fix Issue #6199 by @Jasper-256 in #6200
• fix: default color not selected in appearance color palette by @cmppoon in #6092
• blog: Add Deep Research Piece by @danielcwq in #6039
• 🚀feat: allow user mark model as favorite by @urmauur in #6006
• feat: mcp enhancement by @louis-menlo in #6188
• enhancement: mcp disable save button when server name still empty by @urmauur in #6214
• fix: re-enable Vulkan backend in integrated GPUs with enough memory by @qnixsynapse in #6215
• feat: add support for reasoning fields (OpenRouter) by @dinhlongviolin1 in #6206
• fix: update token.js to remove retired models by @louis-menlo in #6219
• feat: #5917 - model tool use capability should be auto detected by @louis-menlo in #6222
• fix: cancel stream mid run (#6221) by @dinhlongviolin1 in #6227
• fix: should use custom fetch provided by app by @louis-menlo in #6224
• fix: Auto select model only for active provider by @urmauur in #6229
• enhancement: offload model when provider not active by @urmauur in #6226
• feat: Pass API key via environment variable instead of command line arg by @qnixsynapse in #6225
• fix: downloaded model should from variant level instead of the model level by @urmauur in #6234
• fix: improve ux import model by @urmauur in #6233
• feat: add tool call cancellation by @louis-menlo in #6236
• feat: attachment UI by @urmauur in #6134
• fix: resolve issue #6025 - default color selection in appearance page by @Louis454545 in #6198
• Add contributing section for jan (#6231) by @dinhlongviolin1 in #6232
• Fix: Validate GGUF files before loading by @qnixsynapse in #6238
• fix: prevent scroll position jump when AI completes response while user reading by @Louis454545 in #6203
• enhancement: remove validate file extension from select file when import gguf by @urmauur in #6242
• chore: update new domain for jan docs by @Minh141120 in #6245
• fix: local api server log (#6240) by @dinhlongviolin1 in #6244
• fix: hidden sort filter when searching model by @urmauur in #6246
• chore: re enable reasoning_content in backend by @qnixsynapse in #6228
• feat: allow user to set max_attempt for MCP to avoid looping by @louis-menlo in #6241
• ci: add autoqa reliability workflow for windows by @Minh141120 in #6248
• enhancement: vision icon hub model list by @urmauur in #6251
• feat: MCP server error handling by @louis-menlo in #6252
• feat: support inserting current date into assistant prompt by @kamal in #6205
• feat: detect cpu arch in runtime by @louis-menlo in #6249
• fix: emoji picker remains stuck in the open state in AddEditAssistant component by @cmppoon in #6211
• feat: add Polish translation by @0rzech in #5874
• feat: run on startup setting for local api server by @urmauur in #6250
• fix: remove experimental toggle by @louis-menlo in #6255
• fix: enable back app language setting by @louis-menlo in #6257
• ci: add autoqa migration workflow by @Minh141120 in #6261
• feat: gguf file size + hash validation (#5266) by @dinhlongviolin1 in #6259
• fix: bring back manual model capability edit modal by @louis-menlo in #6260
• feat: Add support for custom environmental variables to llama.cpp by @qnixsynapse in #6256
• fix: Update placeholder text and error message by @qnixsynapse in #6263
• feat: Add model compatibility check and memory estimation by @qnixsynapse in #6243
• fix: add missing Polish translations by @0rzech in #6262
• ci: add job condition for auto assign milestone by @Minh141120 in #6264
• fix: check for env value before setting by @qnixsynapse in #6266
• fix: update linux build script to be consistent with CI by @qnixsynapse in #6269
• fix: compatibility imported model by @urmauur in #6271
• fix: update copy offload_mmproj setting desc by @urmauur in #6272
• docs: add blog for jan v1 research by @new5558 in #6197
• docs: fix OG image URL and update publication date by @eckartal in #6274
• fix: jan research blog ogimage by @urmauur in #6282
• fix: handle manual toggle vision for remote model by @urmauur in #6281
• removed orphan pages and polished wording of main page by @ramonpzg in #6273
• fix: system monitor window permission by @urmauur in #6285
• fix: update ui info by @urmauur in #6283
• chore: update credit description by @Minh141120 in #6288
• Bring QA (0.6.9) changes to dev by @dinhlongviolin1 in #6296
• chore: bundle license to app by @Minh141120 in #6294
• fix: handle paste image on linux by @urmauur in #6299
• feat: add regression checklist by @Minh141120 in #6302
• fix: mcp cleanup dropodown tool availabel and sort list by @urmauur in #6305
• fix: handle conditional UI regenerate resp by @urmauur in #6309
• fix: code generation more than 300 line by @urmauur in #6312
• make validation message infinite by @dinhlongviolin1 in #6318
• fix: handle checking model gated by @urmauur in #6316
• fix: Use 80% total memory for compatibility check by @qnixsynapse in #6321

New Contributors

• @Jasper-256 made their first contribution in #6200
• @Louis454545 made their first contribution in #6198
• @kamal made their first contribution in #6205
• @0rzech made their first contribution in #5874
• @new5558 made their first contribution in #6197

Full Changelog: v0.6.8...v0.6.9

0.6.8

What's Changed

• Sync Release/v0.6.6 into dev by @louis-menlo in #5973
• fix: thread sorting issue by @cmppoon in #5976
• ✨enhancement: blurry logo model provider by @urmauur in #5986
• fix: missing text color responsive left panel by @urmauur in #5989
• fix assistant dropdown onClick not triggered consistently by @cmppoon in #5991
• Sync Release/v0.6.6 into dev by @louis-menlo in #5997
• Add comprehensive Products section and reorganize documentation structure by @ramonpzg in #5958
• Sync release/v0.6.6 into dev by @louis-menlo in #6004
• refactor: clean up cortex by @louis-menlo in #6003
• ci: enable PR trigger for dev branch in tauri nightly workflow by @Minh141120 in #6014
• fix: react state loop from hooks useMediaQuery by @urmauur in #6031
• fix: wrong desc setting cont_batching by @urmauur in #6034
• Fix: Llama.cpp server hangs on model load by @qnixsynapse in #6030
• feat(docs): Docs v2 Astro migration by @ramonpzg in #5950
• feat: Improve llama.cpp argument handling and add device parsing tests by @qnixsynapse in #6041
• fix: show error toast message on download error by @cmppoon in #6044
• fix: Generate A Response button does not show context size error dialog by @urmauur in #6029
• fix connected servers status not in sync when edit mcp json by @cmppoon in #6020
• feat: Add check for AVX2 instruction support for MCP on MacOS with Intel CPUs by @shmutalov in #5530
• chore: skip nightly build workflow for external contributor by @Minh141120 in #6050
• fix: support missing llamacpp cuda backends by @louis-menlo in #6046
• ci: disable autoqa on nightly build by @Minh141120 in #6051
• ✨feat: recommended label llamacpp setting by @urmauur in #6052
• Fix: Improve Llama.cpp model path handling and error handling by @qnixsynapse in #6045
• ✨feat: jinja template customize per model instead provider level by @urmauur in #6053
• fix: Jan hub model detail and deep link by @louis-menlo in #6024
• fix: Add conditional Vulkan support check for better GPU compatibility by @qnixsynapse in #6066
• Readme Update and Additional Model Providers by @ramonpzg in #6064
• fix: gpt-oss thinking block by @urmauur in #6071
• fix: should not include reasoning text in the chat completion request by @louis-menlo in #6072
• chore: update workflow name by @Minh141120 in #6073
• ci: deprecate jan docs new release workflow in favor of jan-docs by @Minh141120 in #6078
• Add gpt-oss local installation blog post by @eckartal in #6075
• feat: Add support for overriding tensor buffer type by @qnixsynapse in #6062
• refactor: move session management & port allocation to backend by @qnixsynapse in #6083
• 🐛fix: onboarding loop by @urmauur in #6054
• refactor: Use more precise terminology in API server logs by @qnixsynapse in #6085
• fix: update ux recemmend backend label into desc setting by @urmauur in #6088
• feat: Introduce structured error handling for llamacpp extension by @qnixsynapse in #6087
• refactor: clean up unused hardware apis by @louis-menlo in #6089
• added v0.6.7 changelog and jupyter mcp tutorial by @ramonpzg in #6116
• fix: Prevent accidental message submitting on ChatInput for IME users by @B0sh in #6109
• adding handbook, blog, and changelog to jan docs v2 by @ramonpzg in #6118
• fix: bring back gpu detection - app data relocate issue by @louis-menlo in #6119
• ci: update generate release note and jan docs release by @Minh141120 in #6121
• docs: Update 3-epic.md by @freelerobot in #6124
• docs: Update 4-goal.md by @freelerobot in #6125
• ci: add path for tauri nightly build by @Minh141120 in #6130
• fix: HF token is not used while searching repositories by @louis-menlo in #6137
• fix: factory reset process got blocked by @louis-menlo in #6140
• fix: visualize readme content for private repo with HF token by @louis-menlo in #6141
• fix: Improve error message for invalid version/backend format by @qnixsynapse in #6149
• fix: migrations model setting by @urmauur in #6165
• fix: handle modelId special char by @urmauur and @louis-menlo on #6172
• fix: feature toggle auto updater by @Minh141120 and @louis-menlo on #6175

New Contributors

• @cmppoon made their first contribution in #5976
• @shmutalov made their first contribution in #5530
• @B0sh made their first contribution in #6109

Full Changelog: v0.6.6...v0.6.8

0.6.7

Changes

• fix: should not include reasoning text in the chat completion request @louis-menlo (#6072)
• fix: gpt-oss thinking block @urmamur (#6071)
• fix: react state loop from hooks useMediaQuery @urmamur (#6031)

Contributor

@louis-menlo and @urmauur

0.6.6

Changes

• hotfix: regression issue with colon in model name @louis-menlo (#6008)
• Add RunEvent::Exit event to tauri to handle macos context menu exit @qnixsynapse (#6005)
• fix: remove auto refresh model custom provider @urmauur (#6002)
• fix: generate response button disappear on tool call @louis-menlo (#5988)
• fix: title tooltip MCP edit json @urmauur (#5987)
• fix: download progress missing when left panel scrollable @urmauur (#5984)
• fix: failed provider models list due to broken cortex import @louis-menlo (#5983)
• Sync Release/v0.6.6 into dev @louis-menlo (#5973)
• fix: use direct process termination instead of console events on Windows @qnixsynapse (#5972)
• fix: rename thread dialog shows previous thread @urmauur (#5963)
• chore: allow all HTTPS image sources in img-src directive @Minh141120 (#5970)
• feat: Enhance port selection with availability check @qnixsynapse (#5966)
• fix: csp including img.shields.io and cdn-uploads.huggingface.co in img-src directive @Minh141120 (#5967)
• ci: tolerate artifact upload @Minh141120 (#5969)
• fix: assistant with last used and fix metadata @urmauur (#5955)
• fix: search models result in hub should be sorted by weight @louis-menlo (#5954)
• fix: factory reset fail with access denied error @louis-menlo (#5952)
• fix: set autoUnload in onLoad() @qnixsynapse (#5956)
• fix: update edge case experimental feature MCP @urmauur (#5951)
• fix: correctly apply auto_unload setting from config @qnixsynapse (#5953)
• fix: Prevent race condition with auto-unload during rapid model loading @qnixsynapse (#5947)
• chore: uninstall when upgrading windows installer @Minh141120 (#5945)
• fix: openrouter unselect itself @louis-menlo (#5943)
• fix: tool approval params scrollable @urmauur (#5941)
• fix: migrate app settings to the new version @louis-menlo (#5936)
• fix: Remove sInfo from activeSessions before unloading @qnixsynapse (#5938)
• fix: update default GPU toggle, and simplify state @urmauur (#5937)
• chore: revert back to passive mode on windows installer @Minh141120 (#5934)
• fix: update ui version_backend, mem usage hardware @urmauur (#5932)
• fix: Frontend updates when llama.cpp backend auto-downloads @qnixsynapse (#5926)
• fix: calculation memory on hardware and system monitor @urmauur (#5922)
• fix: persist model capabilities refresh app @urmauur (#5918)
• fix: validate name assistant and improve area clickable @urmauur (#5920)
• fix: Allow N-GPU Layers (NGL) to be set to 0 in llama.cpp @qnixsynapse (#5907)
• fix: models hub should show latest data only @louis-menlo (#5925)
• fix: Persist 'Auto-Unload Old Models' setting in llama.cpp @qnixsynapse (#5906)
• feat: Enhance Llama.cpp backend management with persistence @qnixsynapse (#5886)
• Chore cua mac runner @hiento09 (#5888)
• fix: provider settings should be refreshed on page load @louis-menlo (#5887)
• 🐛fix: get system info and system usage @urmauur (#5884)
• fix: gpu detected from backend version @urmauur (#5882)
• fix: bring back HF repo ID search in Hub @louis-menlo (#5880)
• chore: revert app artifact name for macos linux and windows builds @Minh141120 (#5878)
• feat: add support for querying available backend devices @qnixsynapse (#5877)
• fix: llama.cpp backend shows blank list sometime @louis-menlo (#5876)
• ci: rename app github artifact on windows and linux build @Minh141120 (#5875)
• ci: autoqa github artifact @Minh141120 (#5873)
• fix: jan should have a general assistant instruction @louis-menlo (#5872)
• fix: tmp download file should be removed on cancel @louis-menlo (#5849)
• 🐛fix: remove sampling parameters from llamacpp extension @urmauur (#5871)
• 🐛fix: update vulkan active syntax @urmauur (#5869)
• fix: app should not show manually deleted models @louis-menlo (#5868)
• feat: migrate cortex models to llamacpp extension @louis-menlo (#5838)
• fix: charmap encoding @Minh141120 (#5865)
• fix: HuggingFace provider should be non-deletable @louis-menlo (#5856)
• fix: gemini tool call support - version bump @louis-menlo (#5848)
• Fix: engine unable to find dlls on when running on Windows @qnixsynapse (#5863)
• chore: update build appimage script @Minh141120 (#5866)
• ✨enhancement: dialog model error trigger from provider screen @urmauur (#5858)
• fix: support load model configurations @urmauur (#5843)
• fix: delete all thread should not include fav @urmauur (#5864)
• Chore: enrich autoqa log @hiento09 (#5862)
• refactor: Improve Llama.cpp backend management and auto-update @qnixsynapse (#5845)
• fix: autoqa prompt template @Minh141120 (#5854)
• feat: add vcruntime for windows installer @Minh141120 (#5852)
• ✨enhancement: auto focus always allow action from tool approval dialog and add req parameters @urmauur (#5836)
• enhancement: better error page component @urmauur (#5834)
• chore: sync make build with dev @Minh141120 (#5847)
• refactor: standardize build process and remove build-tauri target @Minh141120 (#5846)
• fix: custom tauri nsis template CheckIfAppIsRunning macro @Minh141120 (#5840)
• fix: update @taur-apps/cli to newest verison to fix appimage download @Minh141120 (#5839)
• fix: prevent terminal window from opening on model load on WindowsOS @qnixsynapse (#5837)
• feat: add claude-4 @louis-menlo (#5829)
• feat: support per-model overrides in llama.cpp load() @qnixsynapse (#5820)
• fix: llama.cpp integration model load and chat experience @louis-menlo (#5823)
• test: deprecate webdriver test in favor of auto qa using CUA @louis-menlo (#5825)
• Revert "chore(deps): update rand requirement from 0.8 to 0.9 in /src-tauri" @louis-menlo (#5824)
• fix: Legacy threads show on top of new threads (#5696) @louis-menlo (#5810)
• fix: llama.cpp backend download on windows @louis-menlo (#5813)
• fix: dependabot should just update security patch @louis-menlo (#5814)
• chore(deps): update rand requirement from 0.8 to 0.9 in /src-tauri @dependabot (#5399)
• docs: Add Instruction for Toggling Experimental Features Before Toggling MCP Servers @bytrangle (#5771)
• chore(deps): bump @radix-ui/react-hover-card from 1.1.11 to 1.1.14 @dependabot (#5603)
• Fix autoqa lib dependencies @hiento09 (#5812)
• refactor: simplify proxy settings by removing unused SSL verification options @louis-menlo (#5809)
• feat: Add Hugging Face as a provider @gary149 (#5808)
• fix: Improve stream error handling and parsing @qnixsynapse (#5807)
• feat: add autoqa @hiento09 (#5779)
• set line number userSelect to none so that code can be copied without line number @ethanova (#5782)
• feat: add model load error handling to improve UX @louis-menlo (#5802)
• fix: Add --reasoning-format none to support rendering of reasoning content @qnixsynapse (#5803)
• feat: proxy support for the new downloader @louis-menlo (#5795)
• Sync release/0.6.5 into dev to start new development cycle @louis-menlo (#5801)
• refactor: move thinking toggle to runtime settings for dynamic control @qnixsynapse (#5800)
• test: deprecate webdriver test in favor of auto qa using CUA @louis-menlo (#5797)
• Documentation Updates for v0.6.5 @ramonpzg (#5799)

Contributor

@Minh141120, @bytrangle, @dependabot, @dependabot[bot], @ethanova, @gary149, @hiento09, @louis-menlo, @qnixsynapse, @ramonpzg and @urmauur

0.6.5

Changes

• ✨enhancement: support base layout responsive Ul @urmauur (#5472)
• ✨enhancement: setting responsive @urmauur (#5615)
• ✨feat: bump version of llama.cpp - b5857 @louis-menlo (#5742)
• 🐛fix: revert back stat hover for three dots @urmauur (#5777)
• 🐛fix: download icon when left panel close @urmauur (#5776)
• 🐛fix: revert installationmode in nsis template @Minh141120 (#5778)
• 🐛fix: make three dots default show 3 dots and can trigger with right click @urmauur (#5712)
• 🐛fix: custom based url and header by upgrade token.js version @samhvw8 (#5596)
• 🐛fix: update base URL for Anthropic provider @samhvw8 (#5600)
• 🐛fix: Tauri Applmage failing to render on wayland + mesa @DistractionRectangle (#5463)
• 🐛fix: fetch models from custom provider causes app to crash @louis-menlo (#5791)
• 🔧 config: all yml to md for issue template @LazyYuuki (#5661)
• 🔧 config: fix bug template @LazyYuuki (#5658)
• 🔧 config: from yml to md for template @LazyYuuki (#5657)

Contributors

@LazyYuuki, @Minh141120, @louis-menlo, @samhvw8, @DistractionRectangle and @urmauur

0.6.4

Changes

• fix: top_k validation @louis-menlo (#5650)
• fix: some of the model settings are not applied @louis-menlo (#5644)
• fix: min_p validation on model load @louis-menlo (#5568)

Contributor

@louis-menlo

0.6.3

Changes

• fix: handle context shift setting from old app versions @louis-menlo (#5547)
• 🐛fix: modal action light mode @urmauur (#5545)
• hotfix: increase context size window does not popup first time @louis-menlo (#5542)

Contributor

@louis-menlo and @urmauur

0.6.2

Changes

• 🔧config: remove MCP and tool use production gate @louis-menlo (#5531)
• 🐛fix: default model settings @louis-menlo (#5528)
• ✨enhancement: adjust placement exp toggle @urmauur (#5525)
• ✨feat: improve local provider connectivity with CORS bypass @samhvw8 (#5458)
• ✨enhancement: experimental feature toggle @urmauur (#5514)
• 🐛fix: delete pre populate remote models @urmauur (#5516)
• ♻️ sync: cherry pick v0.6.2 release @louis-menlo (#5515)

Contributor

@louis-menlo, @samhvw8 and @urmauur

0.6.1

Changes

• 🐛 fix: avoid rendering the HTML title of the thread @urmauur (#5375)

Contributor

@urmauur

0.6.0

🚀 Features

• ✨enhancement: Model sources should not be hard coded from frontend @louis-menlo (#5270)
• ✨enhancement: add setting chat width container @urmauur (#5289)
• ✨ Feat: Token Speed Display Feature @LazyYuuki (#5278)
• ✨enhancement: out of context troubleshooting @louis-menlo (#5275)
• ✨enhancement: model run improvement @louis-menlo (#5268)
• ✨enhancement: masking sensitive values in environment variables @urmauur (#5276)
• feat: improve ui search @samhvw8 (#5052)
• feat: hide docs link @samhvw8 (#5240)
• feat(local-api-server): add button to open API documentation and improve layout @samhvw8 (#5238)
• feat: render mcp content @samhvw8 (#5229)
• enhancement: mcp server activation response and error handling @louis-menlo (#5220)
• enhancement: tmp hide attachment icon @urmauur (#5160)
• enhancement: open folder log and change data folder dialog confirm @urmauur (#5159)
• enhancement: ux tool call permission dialog and state active @urmauur (#5157)
• enhancement: querry search hub include list of model @urmauur (#5147)
• enhancement: all platform layout @urmauur (#5119)
• enhancement: make the model selector popup responsive and wider for bigger screens @ethanova (#5025)
• enhancement: wrap long line codeblock @urmauur (#5069)
• enhancement: show assistant info on message @urmauur (#5064)
• enhance: setup screen redirect to hub @urmauur (#5061)
• enhancement: disabled config when server is running @urmauur (#5058)
• enhancement: update layout hub when left panel collapse @urmauur (#5059)
• enhancement: message toolbar using tooltip @urmauur (#5055)
• enhancement: built-in custom emoji and show metadata message @urmauur (#5085)
• feat: store last use model create thread @urmauur (#5201)
• feat: integrate fuzzy search into model dropdown @samhvw8 (#5197)
• feat: Jan API Server should have API Key setting @louis-menlo (#5193)
• feat: setting toggle vulkan @urmauur (#5126)
• feat: handle open Jan on HF GGUF repo @louis-menlo (#5173)
• feat: migrate legacy local storage data to new app @louis-menlo (#5156)
• feat: add refresh button list model remote provider @urmauur (#5136)
• feat: start and stop model @urmauur (#5133)
• feat: predefined params @urmauur (#5128)
• feat: filter downloaded model on hub screen @urmauur (#5113)
• feat: Support download resume @gau-nernst (#5111)
• feat: add quick access model setting via dropdown model @urmauur (#5104)
• feat: add couple section about us on general settings @urmauur (#5098)
• feat: product analytic @urmauur (#5099)
• feat: file upload thumbnail @urmauur (#5088)
• feat: improve download extension @gau-nernst (#5073)
• feat: Hardware info replacement for cortex @gau-nernst (#4925)
• feat: Implement Cortex server auto-restart and webview notification @samhvw8 (#5074)
• feat: add assistant emoji picker @urmauur (#5057)
• feat: initial app logs @urmauur (#5060)
• feat: add custom OpenAI provider @louis-menlo (#5033)
• feat: Jan supports multiple assistants @louis-menlo (#5024)
• feat: handle stop streaming message, scroll to bottom and model loads @louis-menlo (#5023)
• feat: add MCP server connection status @louis-menlo (#5018)
• feat: new frontend with model download function @louis-menlo (#5008)
• feat: tool use render UI @urmauur (#5004)
• feat: Download manager for llama.cpp extension @gau-nernst (#4933)
• feat: Add Tauri as an Alternative Build Option for Jan @louis-menlo (#4844)

🐛 Fixes

• fix(server): enhance CORS handling for local API network access @samhvw8 (#5236)
• Fix: fuzzy search model case sensitive @samhvw8 (#5228)
• fix: should not show vulkan options in cpu only mode @louis-menlo (#5210)
• Fix: mcp server file system missing param @david-menloai (#5204)
• Fix: headers validations for local api server @david-menloai (#5186)
• fix: relocate jan data folder @louis-menlo (#5179)
• fix: thread update after chat @samhvw8 (#5180)
• fix: stop api server on page unload @louis-menlo (#5356)
• fix: built in models capabilities @urmauur (#5354)
• fix: glitch toggle gpus @urmauur (#5353)
• 🐛fix: setting provider hide model capabilities @urmauur (#5355)
• 🐛 Fix: window path name with a space lead to cannot find correct path to Jan datafolder @LazyYuuki (#5351)
• fix(proxy): implement true HTTP streaming for chat completions API @samhvw8 (#5350)
• fix(server): add gzip decompression support for /models endpoint filtering @samhvw8 (#5349)
• 🐛fix: render streaming token speed based on thread ID & assistant metadata @urmauur (#5346)
• feat(server): filter /models endpoint to show only downloaded models @samhvw8 (#5343)
• 🐛fix: handle NaN value tokenspeed @urmauur (#5339)
• 🐛fix: update wording desc vulkan @urmauur (#5338)
• Fix: sorted thread not stable @samhvw8 (#5336)
• 🐛 fix: thread sorted not correctly after reload @samhvw8 (#5326)
• 🐛 fix(updater): terminate sidecar processes before update to avoid file access errors @Minh141120 (#5325)
• fix: glitch model download issue @louis-menlo (#5322)
• 🐛fix: allow script posthog @urmauur (#5316)
• 🐛fix: update default extension settings @louis-menlo (#5315)
• 🐛fix: llama.cpp default NGL setting does not offload all layers to GPU @louis-menlo (#5310)
• 🐛fix: safely convert values to numbers and handle NaN cases @urmauur (#5309)
• 🐛fix: immediately show download progress @urmauur (#5308)
• 🐛fix: glitch padding speed token @urmauur (#5307)
• 🐛fix: hide token speed when assistant params stream false @urmauur (#5302)
• 🐛fix: remove onboarding local model and hide the edit capabilities model @urmauur (#5301)
• 🐛fix: typo in build type check @louis-menlo (#5297)
• ✨enhancement: masking sensitive values in environment variables @urmauur (#5276)
• fix: glitch download from onboarding @urmauur (#5269)
• 🐛fix: showing release notes for beta and prod @urmauur (#5292)
• 🐛fix: optional additional information gpu @urmauur (#5291)
• 🐛fix: Jan-nano repo name changed @louis-menlo (#5274)
• 🐛fix: default onboarding model should use recommended quantizations @louis-menlo (#5273)
• fix: thinking block @urmauur (#5263)
• fix: default settings should leave empty @louis-menlo (#5257)
• fix: add cortex_killed_intentionally state to manage sidecar process termination @samhvw8 (#5255)
• fix: recheck tools approval state @urmauur (#5259)
• fix: replace close think tag from text segment @urmauur (#5258)
• fix: reduce app state left panel @urmauur (#5256)
• fix: cleanup console error and warning render FE @urmauur (#5253)
• fix: avoid persisting threads and messages on local storage @louis-menlo (#5249)
• fix: minor ui @urmauur (#5247)
• fix: tool call block width code @urmauur (#5246)
• fix: update style cortex dialog @urmauur (#5245)
• fix: update hgf jan nano @urmauur (#5242)
• fix: could not add custom models @louis-menlo (#5241)
• fix: tauri path env @louis-menlo (#5233)
• fix: MCP server should not spawn shell window @louis-menlo (#5223)
• fix: clean up cortex processes @louis-menlo (#5215)
• fix: tools call available dropdown @urmauur (#5222)
• fix: ui glitch dots truncated @urmauur (#5219)
• fix: conditional button refresh model @urmauur (#5221)
• fix: glitch UI thinking or duplicate content when multiple think after tools call @urmauur (#5217)
• fix: prettify json when pasting content @urmauur (#5216)
• fix: avoid spamming server restarts @louis-menlo (#5212)
• fix: path resolver in windows @louis-menlo (#5209)
• fix: load threads from api instead of states @louis-menlo (#5206)
• fix: force provider avatar to render in high quality @urmauur (#5203)
• fix: migrate provider settings @louis-menlo (#5205)
• fix: dropdown model position @urmauur (#5199)
• fix: truncate tool name @urmauur (#5198)
• fix: add missing default host ip @david-menloai (#5196)
• fix: remind me later updater @urmauur (#5191)
• fix: hub refresh state @urmauur (#5190)
• fix: handle tool availability states @louis-menlo (#5183)
• fix: avatar assistants render @urmauur (#5181)
• fix: migration should wait for extensions load @louis-menlo (#5177)
• fix: handle undefined search index in getFilteredThreads @samhvw8 (#5175)
• fix: model run failed on windows @louis-menlo (#5168)
• fix: app updater state @urmauur (#5171)
• fix: sticky action scroll to bottom when edit message @urmauur (#5169)
• fix: Fix hwinfo bugs @gau-nernst (#5164)
• fix: create new provider should not have previous settings @louis-menlo (#5166)
• fix: race condition get Assistant @urmauur (#5161)
• fix: remove capitalize class from provider name @urmauur (#5158)
• fix: extension settings are not retained in new sessions @louis-menlo (#5154)
• fix: avoid floating content when render table markdown @urmauur (#5148)
• fix: state model threadId @urmauur (#5144)
• fix: thread list state order after dragable @urmauur (#5141)
• fix: reverse setting local provider @urmauur (#5140)
• fix: content overflow when long text without space @urmauur (#5142)
• fix: tool call block spacing @urmauur (#5139)
• fix: support delete file for fs.rm() @gau-nernst (#5117)
• fix: chore UI issues @louis-menlo (#5116)
• fix: correct app data folder name @louis-menlo (#5115)
• fix: remove chat message on GUI @louis-menlo (#5114)
• fix: overflow content codeblock @urmauur (#5110)
• fix: prevent send message when empty message @urmauur (#5109)
• fix: enhance tool use and model provider not persisted issues @louis-menlo (#5094)
• fix: ci remove pr review trigger @Minh141120 (#5105)
• fix: fileStat returned object in JS @gau-nernst (#5102)
• fix: broken ui download count when leftpanel close @urmauur (#5089)
• fix: text component scaling @urmauur (#5090)
• fix: model import name issues @louis-menlo (#5093)
• fix: copy:lib on macos when directory already exists @gau-nernst (#5084)
• fix: provider activation status @louis-menlo (#5081)
• fix: bundle libraries on Linux and Windows @vansangpfiev (#5078)
• fix: mcp info when long string without space @urmauur (#5080)
• f...