jan

What's Changed

• feat: add MiniMax as a predefined cloud provider with M2.7 default by @octo-patch in https://github.com/janhq/jan/pull/7738
• feat: replace Foundation Models Swift HTTP server with direct Rust FFI via fm-rs by @dev-miro26 in https://github.com/janhq/jan/pull/7781
• fix: add pointer cursor to tool header when hovering by @bytrangle in https://github.com/janhq/jan/pull/7785
• docs: changelog for v0.7.9 by @Vanalite in https://github.com/janhq/jan/pull/7795
• chore: resolve conflict of main & release v0.7.9 by @Vanalite in https://github.com/janhq/jan/pull/7797
• chore: merge release v0.7.9 to main by @Vanalite in https://github.com/janhq/jan/pull/7798
• fix: Making Makefile compilable from powershell Windows by @thewulf7 in https://github.com/janhq/jan/pull/7771
• Chore/update template windows ci by @Minh141120 in https://github.com/janhq/jan/pull/7805
• fix: resolve MCP stdio transport disconnect and add auto-reconnect by @dev-miro26 in https://github.com/janhq/jan/pull/7791
• feat: add assistant chat button and fix random assistant issue by @markmehere in https://github.com/janhq/jan/pull/7750
• fix: latest model toast check with better logic by @Vanalite in https://github.com/janhq/jan/pull/7806
• feat: add /v1/orchestrations for server-side MCP tool execution by @claytonlin1110 in https://github.com/janhq/jan/pull/7800
• feat: add GUI toggle for server-side tool execution on /chat/completi… by @claytonlin1110 in https://github.com/janhq/jan/pull/7808
• fix: auto-approve internal RAG tools for embedded documents by @claytonlin1110 in https://github.com/janhq/jan/pull/7809
• docs: require screenshot or video record by @Vanalite in https://github.com/janhq/jan/pull/7811
• fix: prevent data loss on app reload by @linuxid10t in https://github.com/janhq/jan/pull/7810
• Fix OpenAI chat crash in web runtime (invoke undefined) by @dataCenter430 in https://github.com/janhq/jan/pull/7815
• feat: paragraph-level Edit with AI for assistant markdown by @claytonlin1110 in https://github.com/janhq/jan/pull/7812
• Update README to fix build commands by @SuperCowProducts in https://github.com/janhq/jan/pull/7829
• Add Korean localization by @hooray804 in https://github.com/janhq/jan/pull/7767
• Add translation to Catalan language by @anebot in https://github.com/janhq/jan/pull/7319
• fix: missing redirects by @louis-jan in https://github.com/janhq/jan/pull/7837
• feat: orchestrate MCP tools - route servers, avoid loading all tools by @dataCenter430 in https://github.com/janhq/jan/pull/7793
• feat: auto-summarize thread titles after first response with cancellable background inference by @statxc in https://github.com/janhq/jan/pull/7816
• fix: align KV cache default settings with actual runtime behavior by @linuxid10t in https://github.com/janhq/jan/pull/7832
• feat: add configurable token limits and auto-compact for remote model providers by @dev-miro26 in https://github.com/janhq/jan/pull/7799
• feat: enhance Tauri opener service for Linux file exploration by @Dexterity104 in https://github.com/janhq/jan/pull/7827
• feat(gguf): fix model compatibility heuristic for Apple Silicon unified memory by @dataCenter430 in https://github.com/janhq/jan/pull/7842
• Update Settings sidebar grouping and rename MCP to Connectors by @claytonlin1110 in https://github.com/janhq/jan/pull/7839
• feat/fix: add regenerate button on failed message responses by @linuxid10t in https://github.com/janhq/jan/pull/7844
• Updated Arm64 linux build instructions for latest app release + GPU acceleration by @SuperCowProducts in https://github.com/janhq/jan/pull/7841
• fix: let users scroll and read thinking content during streaming without being interrupted by @bittoby in https://github.com/janhq/jan/pull/7843
• chore: update icon privacy and code claude by @urmauur in https://github.com/janhq/jan/pull/7853
• fix: improve model selection bar usability by @claytonlin1110 in https://github.com/janhq/jan/pull/7852
• fix: model capability toggles resetting after restart in edit model settings by @EndlessLucky in https://github.com/janhq/jan/pull/7819
• chore: take back hardware setting menu by @urmauur in https://github.com/janhq/jan/pull/7860
• feat: add highlight on dragabble area and also add cursor change by @corevibe555 in https://github.com/janhq/jan/pull/7830
• feat: add optional health check auto-restart for crashed model sessions by @claytonlin1110 in https://github.com/janhq/jan/pull/7855
• feat: clarify that models are stored in appdata too by @abitrolly in https://github.com/janhq/jan/pull/7866
• feat(mcp): optional lightweight router model for MCP tool routing by @dataCenter430 in https://github.com/janhq/jan/pull/7846
• docs: update notes for the openclaw discontinuation by @Vanalite in https://github.com/janhq/jan/pull/7873
• fix: show message timestamps by @corevibe555 in https://github.com/janhq/jan/pull/7872
• fix: display message timestamps in local timezone by @urmauur in https://github.com/janhq/jan/pull/7876
• feat: queue messages during streaming with auto-send, two-stage stop and editable pending chips in input area by @statxc in https://github.com/janhq/jan/pull/7836
• feat: allow retrieving last typed message by pressing up arrow key by @bittoby in https://github.com/janhq/jan/pull/7867
• feat: add API key fallbacks with automatic rotation by @claytonlin1110 in https://github.com/janhq/jan/pull/7877
• fix: ctx_size overflow causing model load failure after reopening chat by @EndlessLucky in https://github.com/janhq/jan/pull/7879
• docs: update cli doc with correct commands by @Vanalite in https://github.com/janhq/jan/pull/7887
• fix: configurable toast placement by @claytonlin1110 in https://github.com/janhq/jan/pull/7886
• feat: store all user settings in local files instead of browser localStorage by @bittoby in https://github.com/janhq/jan/pull/7821
• fix: normalize tool parameter schemas missing type by @smartcoder0777 in https://github.com/janhq/jan/pull/7854
• Create .gitattributes to suppress local Cargo.lock diffs by @DuncanBetts in https://github.com/janhq/jan/pull/7884
• feat: add options to preserve user data during factory reset by @dev-miro26 in https://github.com/janhq/jan/pull/7858
• feat(mcp): routing telemetry, locale strings, and telemetry docs by @dataCenter430 in https://github.com/janhq/jan/pull/7875
• feat: implement initial Chain of Thought by @qnixsynapse in https://github.com/janhq/jan/pull/7897
• fix: avoid CoT wrapper when group has no reasoning parts by @qnixsynapse in https://github.com/janhq/jan/pull/7899
• feat: expand supported file types for document attachments to include many other extensions by @T03N in https://github.com/janhq/jan/pull/7859
• fix: hide llama.cpp backend update prompt when provider is disabled by @smartcoder0777 in https://github.com/janhq/jan/pull/7906
• fix: responsive setting by @urmauur in https://github.com/janhq/jan/pull/7909
• fix: verify stdio MCP tools/list before emitting ready event by @jdmills-edu in https://github.com/janhq/jan/pull/7892
• fix: handle pdf parser panic and enforce file size limit by @github-roushan in https://github.com/janhq/jan/pull/7157
• fix: remove font style last used assistant options by @urmauur in https://github.com/janhq/jan/pull/7910
• fix: add Flatpak CUDA library path discovery and GL extension support for NVIDIA GPU access by @bittoby in https://github.com/janhq/jan/pull/7905
• fix(desktop): persist app config in Tauri app data dir by @EndlessLucky in https://github.com/janhq/jan/pull/7903
• chore: Fix warnings and move foundation models to MacOS only by @qnixsynapse in https://github.com/janhq/jan/pull/7923
• fix: don't select CUDA backend if GPU has insufficient memory by @abitrolly in https://github.com/janhq/jan/pull/7894
• fix: restore no-mmproj-offload flag wiring for multimodal models (#7924) by @owldev127 in https://github.com/janhq/jan/pull/7925
• docs: add Chinese translation (README.zh.md) by @JasonYeYuhe in https://github.com/janhq/jan/pull/7745
• fix: improve llama.cpp context meter for tool-heavy chats by @smartcoder0777 in https://github.com/janhq/jan/pull/7913
• fix: centralize Jan data folder path resolution (#7522) by @owldev127 in https://github.com/janhq/jan/pull/7929
• fix: remove core default permissions to unblock Tauri dev build by @EndlessLucky in https://github.com/janhq/jan/pull/7902
• fix: restore Gemini SDK adapter for MCP tool calls (#7535) by @owldev127 in https://github.com/janhq/jan/pull/7927
• refactor: extract duplicated window instance object into helper by @bitcompass in https://github.com/janhq/jan/pull/7938
• feat: File attachment progress bar by @dataCenter430 in https://github.com/janhq/jan/pull/7942
• fix: embeddings/inline inject ux by @qnixsynapse in https://github.com/janhq/jan/pull/7963
• CI: Add Rust coverage job to CI workflows by @qnixsynapse in https://github.com/janhq/jan/pull/7964
• fix(web): detect real Tauri runtime on localhost by @EndlessLucky in https://github.com/janhq/jan/pull/7962
• fix: prevent long non-breaking URLs from overflowing project view (#7… by @web-dev0521 in https://github.com/janhq/jan/pull/7961
• test: add comprehensive JS test coverage by @qnixsynapse in https://github.com/janhq/jan/pull/7970
• Hide Gemma models reasoning tags by @kirsenn in https://github.com/janhq/jan/pull/7948
• fix: normalize MCP tool schemas for strict provider validation (#7017) by @owldev127 in https://github.com/janhq/jan/pull/7941
• fix: restore MCP startup error dialog (#7038) by @owldev127 in https://github.com/janhq/jan/pull/7940
• fix: prevent CUDA paths from being overwritten by library path setup by @qnixsynapse in https://github.com/janhq/jan/pull/7978
• docs: add Japanese README by @eltociear in https://github.com/janhq/jan/pull/8001
• fix: prevent dual download toast and "stuck at Initializing" symptom by @qnixsynapse in https://github.com/janhq/jan/pull/7994
• docs: remove Connectors section from landing page by @qnixsynapse in https://github.com/janhq/jan/pull/7989
• fix(server): allow any host when binding to 0.0.0.0 by @web-dev0521 in https://github.com/janhq/jan/pull/7979
• feat: add support for Hindi language by @tejasashinde in https://github.com/janhq/jan/pull/8009
• fix(sidebar): reduce left sidebar max width to prevent content cramping by @octo-patch in https://github.com/janhq/jan/pull/7990
• refactor: extract model transformation helpers in threads service by @bitcompass in https://github.com/janhq/jan/pull/7955
• chore: remove unused thread-scroll default constant and type guard by @bitcompass in https://github.com/janhq/jan/pull/8022
• test: add more test coverage by @qnixsynapse in https://github.com/janhq/jan/pull/7988
• refactor: deduplicate Tauri invoke_handler command registration #7976 by @enjoyandlove in https://github.com/janhq/jan/pull/7977
• fix: manual install backend by @qnixsynapse in https://github.com/janhq/jan/pull/8062
• feat: move backend download/management logic to Rust plugin and add deps verification by @qnixsynapse in https://github.com/janhq/jan/pull/8026
• chore: remove commented-out toast notification code in chat-session-store by @dev-miro26 in https://github.com/janhq/jan/pull/8079
• feat(llamacpp): expand server flags + wire llamacpp-only sampling params by @qnixsynapse in https://github.com/janhq/jan/pull/8099
• refactor: add formatBytes helper by @mykh-hailo in https://github.com/janhq/jan/pull/7982
• refactor: consolidate CUDA download logic in llamacpp backend by @bitcompass in https://github.com/janhq/jan/pull/7954
• test: fix flaky SecurityConfigDialog tab/content races by @qnixsynapse in https://github.com/janhq/jan/pull/8101
• chore: remove Apple Foundation Models integration by @qnixsynapse in https://github.com/janhq/jan/pull/8120
• feat: split provider list into local and remote sections by @qnixsynapse in https://github.com/janhq/jan/pull/8126
• feat: add tooltip and bulk delete for downloaded models by @qnixsynapse in https://github.com/janhq/jan/pull/8119
• fix: ship mlx-swift Cmlx bundle with default.metallib by @qnixsynapse in https://github.com/janhq/jan/pull/8132
• fix: restore pre-CoT reasoning duration + prevent action flicker during tool calls by @qnixsynapse in https://github.com/janhq/jan/pull/8133
• ci: increase timeout to fix some failing tests on Windows runner by @qnixsynapse in https://github.com/janhq/jan/pull/8134
• Feat: llamacpp router mode by @qnixsynapse in https://github.com/janhq/jan/pull/8130
• fix: keep in-flight work alive across thread navigation by @qnixsynapse in https://github.com/janhq/jan/pull/8137
• feat: prompt user on llama-server shutdown when models are busy by @qnixsynapse in https://github.com/janhq/jan/pull/8139
• feat: inline MCP approval, citation cards, and RAG grounding markers by @qnixsynapse in https://github.com/janhq/jan/pull/8140
• feat: clearer variants, local fit check, and download lifecycle fixes by @qnixsynapse in https://github.com/janhq/jan/pull/8141
• chore: upgrade Vercel AI SDK to v6 and harden remote provider workflow by @qnixsynapse in https://github.com/janhq/jan/pull/8142
• fix: vision-aware attachments, orphan tool-call recovery, Groq reasoning fix, table export polish, etc by @qnixsynapse in https://github.com/janhq/jan/pull/8150
• fix: strip identity preamble on upgrade from v2 default prompt in assistant by @qnixsynapse in https://github.com/janhq/jan/pull/8155
• revert: default KV cache K/V type back to f16 by @qnixsynapse in https://github.com/janhq/jan/pull/8151
• fix: restore hub fit badge, bump mlx-swift, fix stuck download UI in mlx provider by @qnixsynapse in https://github.com/janhq/jan/pull/8153
• fix: repair llamacpp/hardware ACL by @qnixsynapse in https://github.com/janhq/jan/pull/8158
• fix: humanize project file upload errors by @qnixsynapse in https://github.com/janhq/jan/pull/8161
• fix: persist file ingestion progress + cleaner citations and spell check by @qnixsynapse in https://github.com/janhq/jan/pull/8162
• fix: tool-call schemas, predefined provider base_url, i18n by @qnixsynapse in https://github.com/janhq/jan/pull/8166
• chore: update llamacpp settings by @qnixsynapse in https://github.com/janhq/jan/pull/8168

New Contributors

• @octo-patch made their first contribution in https://github.com/janhq/jan/pull/7738
• @thewulf7 made their first contribution in https://github.com/janhq/jan/pull/7771
• @claytonlin1110 made their first contribution in https://github.com/janhq/jan/pull/7800
• @linuxid10t made their first contribution in https://github.com/janhq/jan/pull/7810
• @hooray804 made their first contribution in https://github.com/janhq/jan/pull/7767
• @anebot made their first contribution in https://github.com/janhq/jan/pull/7319
• @Dexterity104 made their first contribution in https://github.com/janhq/jan/pull/7827
• @EndlessLucky made their first contribution in https://github.com/janhq/jan/pull/7819
• @corevibe555 made their first contribution in https://github.com/janhq/jan/pull/7830
• @abitrolly made their first contribution in https://github.com/janhq/jan/pull/7866
• @smartcoder0777 made their first contribution in https://github.com/janhq/jan/pull/7854
• @DuncanBetts made their first contribution in https://github.com/janhq/jan/pull/7884
• @T03N made their first contribution in https://github.com/janhq/jan/pull/7859
• @jdmills-edu made their first contribution in https://github.com/janhq/jan/pull/7892
• @owldev127 made their first contribution in https://github.com/janhq/jan/pull/7925
• @JasonYeYuhe made their first contribution in https://github.com/janhq/jan/pull/7745
• @bitcompass made their first contribution in https://github.com/janhq/jan/pull/7938
• @web-dev0521 made their first contribution in https://github.com/janhq/jan/pull/7961
• @kirsenn made their first contribution in https://github.com/janhq/jan/pull/7948
• @tejasashinde made their first contribution in https://github.com/janhq/jan/pull/8009
• @enjoyandlove made their first contribution in https://github.com/janhq/jan/pull/7977

Full Changelog: https://github.com/janhq/jan/compare/v0.7.9...v0.8.0