0.8.3

What's Changed

• docs: add v0.8.2 changelog by @qnixsynapse in #8246
• merge release/v0.8.2 to main by @qnixsynapse in #8250
• chore: add flatpak manifest 0.8.2 by @Minh141120 in #8259
• fix: use Windows copy command in build-cli Makefile target by @ianmohney in #8293
• Updated translation by @albanobattistella in #8262
• fix(mcp): browser port leak and auto-disable ux by @abn in #8317
• Merge dev/v0.8.3 to main by @qnixsynapse in #8310
• docs: clarify Jan model quick-start flow by @archit-goyal in #8323
• Fix: correct sampler defaults, fix sheet layout under window controls, and harden backend installs by @qnixsynapse in #8327
• fix(csp): allow data:/blob: media so video uploads load by @qnixsynapse in #8330
• fix(markdown): render lone in a code fence; don't extract nested in real code by @qnixsynapse in #8332
• fix(chat): render media on first-message send by @qnixsynapse in #8337

New Contributors

• @ianmohney made their first contribution in #8293
• @abn made their first contribution in #8317
• @archit-goyal made their first contribution in #8323

Full Changelog: v0.8.2...v0.8.3

0.8.2

What's Changed

• fix(rag): honor configured attachment size limit in document parser by @qnixsynapse in #8248
• fix(mlx): register mlx capability so its commands pass ACL on macOS by @qnixsynapse
• fix(threads): persist assistant parameters so sampler settings survive restart by @qnixsynapse
• fix(csp): stop Tauri nonce-ing style-src so unsafe-inline works by @qnixsynapse
• test(extensions): run llamacpp-extension tests in the global suite by @qnixsynapse
• fix(llamacpp): raise default ctx-size to 8192 by @qnixsynapse
• fix(ui): move toast accent tint to CSS class to satisfy CSP by @qnixsynapse
• fix(ui): restore toast styling on Windows; tint toast with accent color by @qnixsynapse
• fix(ui): make notification toast visible and theme-aware by @qnixsynapse
• fix(i18n): add Italian to language switcher, fix Catalan locale code by @qnixsynapse
• fix(providers): surface friendly message on transport-level request failures by @qnixsynapse
• feat(providers): add copy and reveal buttons to API key inputs by @qnixsynapse
• fix(updater): bind requestIdleCallback to window to avoid Illegal invocation by @qnixsynapse
• perf(llamacpp): defer backend dep verification to browser idle by @qnixsynapse
• perf(updater): defer backend update check to browser idle by @qnixsynapse
• build(mlx): build the MLX plugin and extension on macOS only by @qnixsynapse
• perf(updater): defer initial app update check until after first paint by @qnixsynapse
• fix(llamacpp): start router before deferring backend update check by @qnixsynapse
• fix(server): list MLX models in Local API Server default model picker by @qnixsynapse
• fix(chat): make attachment chip text legible in user bubble by @qnixsynapse
• feat(settings): add toggle for automatic app update check by @qnixsynapse
• fix(assistant): make the thread's agent authoritative so in-chat switching works by @qnixsynapse
• fix(startup): increase logo–caption gap and center loader caption by @qnixsynapse
• feat(downloads): pause and resume model downloads from the hub panel by @qnixsynapse
• fix(chat): route prompt-too-big errors to the Increase Context Size banner by @qnixsynapse
• fix(llamacpp): recover crashed models and surface mid-request crashes by @qnixsynapse
• feat(startup): branded loader with phased status; defer MCP past first paint by @qnixsynapse
• fix(linux): keep tao's draggable Wayland titlebar; follow GNOME button-layout by @qnixsynapse
• feat(llamacpp): add HIP (AMD ROCm) backend support by @qnixsynapse
• fix(llamacpp): unblock UI from router startup; watchdog against blank window by @qnixsynapse
• style(message): use primary color for user message bubble by @qnixsynapse
• chore(release): bump app and plugin versions to 0.8.2 by @qnixsynapse

Full Changelog: v0.8.1...v0.8.2

0.8.1

What's Changed

• Add Italian Translation by @albanobattistella in #8157
• chore: merge release v0.8.0 to main by @qnixsynapse in #8170
• chore: fix build due to missing comma in italian i18n by @qnixsynapse in #8171
• docs: update for v0.8.0 by @qnixsynapse in #8164
• chore: update manifest and changelog release 0.8.0 by @Minh141120 in #8172
• docs: remove connectors note from 0.8.0 changelog by @qnixsynapse in #8173
• chore: update filename changelog by @Minh141120 in #8177
• fix(docs): guard null entity arrays in TweetCard by @qnixsynapse in #8187
• fix: clear deletedModels tombstones for re-downloaded models by @qnixsynapse in #8178
• chore(ci): pin all GitHub Actions to SHAs and add cancel-in-progress by @Minh141120 in #8193
• fix(tls): use OS-native TLS trust store on desktop by @FyrbyAdditive in #8186
• chore(ci): bump dcarbone/install-jq-action from v2.0.1 to v3.2.0 by @Minh141120 in #8199
• chore: merge dev branch fix/macos backend-install-ux by @qnixsynapse in #8197
• fix(llamacpp): disable auto-fit by default, default ctx_len to 8192 by @qnixsynapse in #8204
• Merge fix/pre-r-dev branch to main by @qnixsynapse in #8207
• Fix/system theme launch by @qnixsynapse in #8217
• fix(hardware): skip NVIDIA/Vulkan GPU probes on macOS by @qnixsynapse in #8219
• fix(threads): avoid router invariant in PromptProgress by @qnixsynapse in #8220
• fix(settings): restore Attachments entry in settings menu by @qnixsynapse in #8222

New Contributors

• @albanobattistella made their first contribution in #8157
• @FyrbyAdditive made their first contribution in #8186

Full Changelog: v0.8.0...v0.8.1

0.8.0

What's Changed

• feat: add MiniMax as a predefined cloud provider with M2.7 default by @octo-patch in #7738
• feat: replace Foundation Models Swift HTTP server with direct Rust FFI via fm-rs by @dev-miro26 in #7781
• fix: add pointer cursor to tool header when hovering by @bytrangle in #7785
• docs: changelog for v0.7.9 by @Vanalite in #7795
• chore: resolve conflict of main & release v0.7.9 by @Vanalite in #7797
• chore: merge release v0.7.9 to main by @Vanalite in #7798
• fix: Making Makefile compilable from powershell Windows by @thewulf7 in #7771
• Chore/update template windows ci by @Minh141120 in #7805
• fix: resolve MCP stdio transport disconnect and add auto-reconnect by @dev-miro26 in #7791
• feat: add assistant chat button and fix random assistant issue by @markmehere in #7750
• fix: latest model toast check with better logic by @Vanalite in #7806
• feat: add /v1/orchestrations for server-side MCP tool execution by @claytonlin1110 in #7800
• feat: add GUI toggle for server-side tool execution on /chat/completi… by @claytonlin1110 in #7808
• fix: auto-approve internal RAG tools for embedded documents by @claytonlin1110 in #7809
• docs: require screenshot or video record by @Vanalite in #7811
• fix: prevent data loss on app reload by @linuxid10t in #7810
• Fix OpenAI chat crash in web runtime (invoke undefined) by @dataCenter430 in #7815
• feat: paragraph-level Edit with AI for assistant markdown by @claytonlin1110 in #7812
• Update README to fix build commands by @SuperCowProducts in #7829
• Add Korean localization by @hooray804 in #7767
• Add translation to Catalan language by @anebot in #7319
• fix: missing redirects by @louis-jan in #7837
• feat: orchestrate MCP tools - route servers, avoid loading all tools by @dataCenter430 in #7793
• feat: auto-summarize thread titles after first response with cancellable background inference by @statxc in #7816
• fix: align KV cache default settings with actual runtime behavior by @linuxid10t in #7832
• feat: add configurable token limits and auto-compact for remote model providers by @dev-miro26 in #7799
• feat: enhance Tauri opener service for Linux file exploration by @Dexterity104 in #7827
• feat(gguf): fix model compatibility heuristic for Apple Silicon unified memory by @dataCenter430 in #7842
• Update Settings sidebar grouping and rename MCP to Connectors by @claytonlin1110 in #7839
• feat/fix: add regenerate button on failed message responses by @linuxid10t in #7844
• Updated Arm64 linux build instructions for latest app release + GPU acceleration by @SuperCowProducts in #7841
• fix: let users scroll and read thinking content during streaming without being interrupted by @bittoby in #7843
• chore: update icon privacy and code claude by @urmauur in #7853
• fix: improve model selection bar usability by @claytonlin1110 in #7852
• fix: model capability toggles resetting after restart in edit model settings by @EndlessLucky in #7819
• chore: take back hardware setting menu by @urmauur in #7860
• feat: add highlight on dragabble area and also add cursor change by @corevibe555 in #7830
• feat: add optional health check auto-restart for crashed model sessions by @claytonlin1110 in #7855
• feat: clarify that models are stored in appdata too by @abitrolly in #7866
• feat(mcp): optional lightweight router model for MCP tool routing by @dataCenter430 in #7846
• docs: update notes for the openclaw discontinuation by @Vanalite in #7873
• fix: show message timestamps by @corevibe555 in #7872
• fix: display message timestamps in local timezone by @urmauur in #7876
• feat: queue messages during streaming with auto-send, two-stage stop and editable pending chips in input area by @statxc in #7836
• feat: allow retrieving last typed message by pressing up arrow key by @bittoby in #7867
• feat: add API key fallbacks with automatic rotation by @claytonlin1110 in #7877
• fix: ctx_size overflow causing model load failure after reopening chat by @EndlessLucky in #7879
• docs: update cli doc with correct commands by @Vanalite in #7887
• fix: configurable toast placement by @claytonlin1110 in #7886
• feat: store all user settings in local files instead of browser localStorage by @bittoby in #7821
• fix: normalize tool parameter schemas missing type by @smartcoder0777 in #7854
• Create .gitattributes to suppress local Cargo.lock diffs by @DuncanBetts in #7884
• feat: add options to preserve user data during factory reset by @dev-miro26 in #7858
• feat(mcp): routing telemetry, locale strings, and telemetry docs by @dataCenter430 in #7875
• feat: implement initial Chain of Thought by @qnixsynapse in #7897
• fix: avoid CoT wrapper when group has no reasoning parts by @qnixsynapse in #7899
• feat: expand supported file types for document attachments to include many other extensions by @T03N in #7859
• fix: hide llama.cpp backend update prompt when provider is disabled by @smartcoder0777 in #7906
• fix: responsive setting by @urmauur in #7909
• fix: verify stdio MCP tools/list before emitting ready event by @jdmills-edu in #7892
• fix: handle pdf parser panic and enforce file size limit by @github-roushan in #7157
• fix: remove font style last used assistant options by @urmauur in #7910
• fix: add Flatpak CUDA library path discovery and GL extension support for NVIDIA GPU access by @bittoby in #7905
• fix(desktop): persist app config in Tauri app data dir by @EndlessLucky in #7903
• chore: Fix warnings and move foundation models to MacOS only by @qnixsynapse in #7923
• fix: don't select CUDA backend if GPU has insufficient memory by @abitrolly in #7894
• fix: restore no-mmproj-offload flag wiring for multimodal models (#7924) by @owldev127 in #7925
• docs: add Chinese translation (README.zh.md) by @JasonYeYuhe in #7745
• fix: improve llama.cpp context meter for tool-heavy chats by @smartcoder0777 in #7913
• fix: centralize Jan data folder path resolution (#7522) by @owldev127 in #7929
• fix: remove core default permissions to unblock Tauri dev build by @EndlessLucky in #7902
• fix: restore Gemini SDK adapter for MCP tool calls (#7535) by @owldev127 in #7927
• refactor: extract duplicated window instance object into helper by @bitcompass in #7938
• feat: File attachment progress bar by @dataCenter430 in #7942
• fix: embeddings/inline inject ux by @qnixsynapse in #7963
• CI: Add Rust coverage job to CI workflows by @qnixsynapse in #7964
• fix(web): detect real Tauri runtime on localhost by @EndlessLucky in #7962
• fix: prevent long non-breaking URLs from overflowing project view (#7… by @web-dev0521 in #7961
• test: add comprehensive JS test coverage by @qnixsynapse in #7970
• Hide Gemma models reasoning tags by @kirsenn in #7948
• fix: normalize MCP tool schemas for strict provider validation (#7017) by @owldev127 in #7941
• fix: restore MCP startup error dialog (#7038) by @owldev127 in #7940
• fix: prevent CUDA paths from being overwritten by library path setup by @qnixsynapse in #7978
• docs: add Japanese README by @eltociear in #8001
• fix: prevent dual download toast and "stuck at Initializing" symptom by @qnixsynapse in #7994
• docs: remo...

0.7.9

What's Changed

• fix: clean up ANTHROPIC_* env vars from shell config when server stops or app exits by @since-2017-hub in #7628
• fix: add redirect from /guides to /docs by @louis-jan in #7669
• docs: update troubleshooting guides by @louis-jan in #7670
• docs: restructure Reference by @louis-jan in #7674
• docs: agents availability by @louis-jan in #7682
• docs: add community cards to desktop overview by @louis-jan in #7687
• chore: resolve release main conflict 0.7.8 by @Vanalite in #7713
• Sync release/v0.7.8 to main branch by @louis-jan in #7711
• doc: add changelog for v0.7.8 by @Vanalite in #7714
• docs: update CLI and agents docs for v0.7.8 by @louis-jan in #7715
• feat: update flatpak manifest v0.7.8 by @Minh141120 in #7717
• fix: resolve Anthropic 400 error on serial tool calls by @atoz96 in #7696
• Revert: clear ANTHROPIC_ env on app exit #7628 by @louis-jan in #7718
• Merge pull request #7695 from oolokioo7/fix/edit-dialog-width by @louis-jan in #7719
• Fix: gpu detection losing by @dataCenter430 in #7605
• fix: system theme not updating when switching dark/light mode on KDE Linux by @since-2017-hub in #7629
• docs: add Windows data folder relocation troubleshooting section by @louis-jan in #7724
• docs: add troubleshooting for timeout port by @Vanalite in #7730
• fix: fix error on openclaw doc by @Vanalite in #7731
• fix: prevent duplicate backend downloads during llamacpp update by @atoz96 in #7721
• fix: render code block without lang spec correcty by @cs-cat in #7741
• refactor: fix normalizeLatex logic and improve performance by @cs-cat in #7743
• docs: troubleshooting update for jan CLI on Windows by @louis-jan in #7736
• docs: add instructions to uninstall openclaw by @Vanalite in #7754
• docs: Add instruction to install HIP/ROCm llamacpp backend for AMD by @Vanalite in #7755
• fix: update CLI help examples to use Jan model ID by @louis-jan in #7753
• fix: kv-cache defaults and fit migration by @louis-jan in #7751
• feat: default model for local api server by @urmauur in #7735
• chore: remove the 32k ctx_len enforcement upon API server start by @Vanalite in #7756
• feat: add default assistant setting by @urmauur in #7725
• doc: update CONTRIBUTING.md by @Vanalite in #7764
• fix: wrong display shortcut create project by @urmauur in #7757
• feat: add foundation models plugin with server management capabilities by @dev-miro26 in #7744
• feat: add Spanish (Español) locale by @dev-miro26 in #7765
• fix: change data location that has accident symlink failed by @Vanalite in #7763
• fix: resolve downloaded model toggle bug by handling developer prefix by @jamesdam in #7648
• feat: safe define remove dir list during the factory reset by @Vanalite in #7766
• chore: remove openclaw installation by @Vanalite in #7762
• fix: cli install method on Window by @Vanalite in #7768
• feat: add NVIDIA NIM as a predefined cloud provider by @MauroDruwel in #7740
• fix: api server cors vulnerability by @Vanalite in #7769
• refactor: replace toggle with chevron for show variants in Hub by @Lokimorty in #7059
• feat: settings to auto increase ctx_len by @Vanalite in #7770
• doc: temporary remove the MCP example section which was previously nuked by @Vanalite in #7776
• feat: expand supported file types for document attachments by @dev-miro26 in #7772
• fix: Hub behavior issues by @Vanalite in #7777
• chore: disable foundation model for RC by @Vanalite in #7778
• feat: remote model update by @Vanalite in #7782
• fix: Fix auto-increase context size bugs by @Vanalite in #7783
• fix: restore default localhost on API Server start by @Vanalite in #7794

New Contributors

• @atoz96 made their first contribution in #7696
• @dataCenter430 made their first contribution in #7605
• @cs-cat made their first contribution in #7741
• @MauroDruwel made their first contribution in #7740

Full Changelog: v0.7.8...v0.7.9

0.7.8

What's Changed

• Sync Release/v0.7.7 to main by @louis-jan in #7504
• docs: changelog for v0.7.7 by @Vanalite in #7507
• chore: update flatpak manifest v0.7.7 by @Minh141120 in #7510
• chore: update landing page app screenshots by @urmauur in #7511
• fix: duplicate url manifest flatpak by @Minh141120 in #7519
• Sync new change from Release/v0.7.7 to main by @louis-jan in #7518
• ci: add condition for nightly external by @Minh141120 in #7523
• fix: conditional show message toolbar by @urmauur in #7524
• fix: adjustment dragable app window by @urmauur in #7521
• fix: incorrect links in docs by @statxc in #7517
• fix: thinking render with long content by @urmauur in #7527
• fix: sorting provider name by @urmauur in #7526
• fix: simplify mlx-server backend with new ChatSession update by @louis-jan in #7538
• fix: gpt-oss disallows quantized cache types due to its use of attention sinks by @louis-jan in #7541
• fix: MLX import dialog uses folder picker instead of file picker by @louis-jan in #7554
• fix: long text error apikey by @urmauur in #7557
• fix: replace AbortSignal.any with manual polyfill for WebKit compatibility by @since-2017-hub in #7552
• fix: navigation back from detail hub page by @urmauur in #7569
• fix: use libappindicator3-1 for deb package to fix Ubuntu 22.04 install conflict by @dev-miro26 in #7570
• feat: add xAI provider by @louis-jan in #7551
• fix: add dir=auto for bidirectional text support by @sesajad in #7542
• fix: hide capability for mlx model by @urmauur in #7579
• docs: add Jan-Code-4B, Jan-v3-4B, and Jan-v2-VL model pages by @louis-jan in #7598
• fix: add back linux native top panel tauri by @urmauur in #7580
• feat: openclaw integration by @Vanalite in #7583
• fix: disconnect channel and add spinner by @Vanalite in #7599
• feat: polish the initialize flow by @Vanalite in #7602
• feat: Jan CLI support by @louis-jan in #7576
• fix: update flash attention handling in ArgumentBuilder by @dev-miro26 in #7565
• fix: overlap z-index model setting and dropdown model provider by @urmauur in #7600
• enhancement: better setting organizations by @urmauur in #7601
• feat: Jan manages Context Allocation dynamically by @louis-jan in #7609
• fix: disable auto fit setting by default by @louis-jan in #7610
• fix: scrollable dropdown assistant by @urmauur in #7607
• enhancement: recommend small model by @urmauur in #7606
• fix: correct model eval chart by @louis-jan in #7614
• fix(tauri): handle non-UTF-8 paths in default_data_folder_path by @eren-karakus0 in #7577
• enhancement: add model provider options by @urmauur in #7611
• fix: allow different images with same filename by deduplicating on co… by @mykh-hailo in #7563
• fix: text color readme detail model screen by @urmauur in #7617
• feat: agent mode toggle and sandbox config isolation for OpenClaw by @Vanalite in #7612
• fix: add deeplink open in jan from models by @louis-jan in #7616
• feat: starter screen and download management update UI by @urmauur in #7548
• fix: mlx provider only show for MacOs by @urmauur in #7620
• fix: setup failed ui openClaw, and run local api server when run agent by @urmauur in #7619
• fix: missing command on window and linux by @Vanalite in #7621
• fix: bundle jan-cli.exe in Windows NSIS installer by @louis-jan in #7618
• chore: update left panel menu with agent chat by @urmauur in #7622
• chore: update logo xai by @urmauur in #7623
• fix: conditional menu chat with agent by @urmauur in #7625
• chore: auto download model, and remove default thread and project by @urmauur in #7626
• feat: update Jan Docs by @louis-jan in #7627
• docs: local api servers by @louis-jan in #7633
• docs: update nav bar and remove some of redundant topics by @louis-jan in #7637
• fix: show header left panel windows and linux by @urmauur in #7635
• fix: menu chat agent by @urmauur in #7634
• fix: project should use normal chat by @urmauur in #7630
• docs: nuke deprecated docs by @louis-jan in #7639
• docs: update prerequisites by @jamesdam in #7631
• fix: hide token counter when using agent mode by @urmauur in #7638
• feat: spawn openclaw in pre-installed bun by @Vanalite in #7624
• fix: default minimum 32k for models starting with local api server by @louis-jan in #7636
• fix: improve textarea text wrapping with wrap-anywhere by @mykh-hailo in #7562
• sync: merge main into release by @louis-jan in #7649
• fix: dropdown model selector project by @urmauur in #7650
• fix: state server running when save config claude code by @urmauur in #7651
• feat: add validation step by @Vanalite in #7652
• fix: last used model local api server by @urmauur in #7653
• feat: Validate docker on Window and Linux by @Vanalite in #7655
• fix: detect docker in release build by @Vanalite in #7660
• fix: env path issue on windows by @louis-jan in #7662
• fix: auto select model from onboarding by @urmauur in #7664
• fix: pre-assign 32k context size for local model to support agent mode by @Vanalite in #7667
• chore: translate agent and missing texts by @Vanalite in #7671
• fix: label experimental by @urmauur in #7672
• fix: disabled provider by @urmauur in #7673
• feat: add openclaw qol shortcuts by @louis-jan in #7675
• chore: integration troubleshooting by @Vanalite in #7676
• fix: should show OpenClaw Folder only when it's enabled by @louis-jan in #7677
• fix: non blocking command check [glitch on Windows] by @louis-jan in #7679
• fix: change gateway pinging mech by @Vanalite in #7678
• feat: bump openclaw to fix plugin config on window and linux by @Vanalite in #7683
• fix: openclaw direct run does not have dashboard bundled by @louis-jan in #7689
• fix: unify data folder by @Vanalite in #7690
• feat: remove all node & npm dependency, always use bun by @Vanalite in #7692
• fix: adjust flow openclaw integration first install by @urmauur in #7694
• fix: OpenClaw stopped working on gateway restart by @louis-jan in #7693
• fix: label experimantal for section integrations by @urmauur in #7698
• fix: label experimental lowercase by @urmauur in #7699
• fix: hide shell prompt on cli install by @louis-jan in #7702
• fix: auto select download model from onboarding on windows by @urmauur in #7704
• fix: enable openclaw when remote provider already setup by @urmauur in #7705
• fix: resolve runtime on window upon gateway restart by @Vanalite in #7706
• fix: openclaw onboarding by @louis-jan in #7708
• chore: show back the instruction to require nodejs by @Vanalite in #7707
• fix: openclaw runtime error by @louis-jan in #7709
• fix: append localhost as allowedOrigins on docker path by @Vanalite in #7710

New Contributors

• @statxc made their first contribution in #7517
• @dev-miro26 made their ...

0.7.7

What's Changed

• fix: theme set loop on Windows by @louis-jan in #7407
• fix: left panel full height by @urmauur in #7409
• fix: throttle renderer to reduce pressure to the thread by @louis-jan in #7408
• feat: prompt to download Jan VL model for vision capability by @Vanalite in #7410
• docs: changelog for v0.7.6 by @Vanalite in #7418
• chore: update manifest for flatpak jan 0.7.6 by @Minh141120 in #7419
• chore: onboard new user with q4 k xl by @louis-jan in #7420
• Fix: inconsistent code block formatting in Markdown rendering by @bytrangle in #7049
• fix: accept x-api-key header in place of custom header by @louis-jan in #7421
• fix: Display embedding models in settings with visual distinction by @bittoby in #7393
• chore: sync release branch for merging by @Vanalite in #7425
• chore: merge release branch by @Vanalite in #7424
• fix: update api docs by @louis-jan in #7426
• fix: default instruction update by @louis-jan in #7427
• feat: streamable http exa default search mcp by @louis-jan in #7428
• chore: disable auto updater for flatpak build by @hiento09 in #7432
• ci: move config yarn makefile to ci by @Minh141120 in #7433
• ui: revamp layout by @urmauur in #7431
• fix: minor badge capabilities by @urmauur in #7435
• fix: dynamically generate OpenAPI spec with actual server host and port by @Eruis2579 in #7434
• fix: take back refresh and add model remote provider by @urmauur in #7436
• fix: prefill value when rename thread by @urmauur in #7437
• chore: delete all thread by @urmauur in #7447
• fix: edit message with files attachment by @urmauur in #7446
• chore: update font from local instead cdn by @urmauur in #7449
• chore: avoid warning dialog components by @urmauur in #7450
• chore: assistant assign into projects by @urmauur in #7441
• feat: add delete all thread inside projects by @urmauur in #7453
• fix: inline math latex by @urmauur in #7454
• fix: hover menu dots for delete all chat by @urmauur in #7455
• fix: notarize mlx bin by @Minh141120 in #7458
• feat: add new backend - MLX by @louis-jan in #7459
• chore: adjustment drag area by @urmauur in #7464
• fix: chat performance rerender issue by @urmauur in #7465
• fix: issue descendant element by @urmauur in #7466
• fix: hub screen scroll and loader by @urmauur in #7467
• fix: prompt cache - cannot infer the shape of an empty array by @louis-jan in #7470
• chore: refactor modelhub by @hiento09 in #7468
• chore: base layout windows by @urmauur in #7471
• feat: implement fit settings in llamacpp extension and overhaul argument builder tests by @qnixsynapse in #7442
• chore: update copy for setup screen by @urmauur in #7472
• feat: local api server improvement by @urmauur in #7460
• chore: update copy web by @urmauur in #7474
• refactor: remove model planner since now use auto fit setting by @louis-jan in #7473
• fix: pass model parameters in fetch body for all providers by @louis-jan in #7475
• fix: overflow scroll thinking by @urmauur in #7476
• chore: update icon project by @urmauur in #7478
• fix: stop MLX model inference when client aborts chat/completions by @louis-jan in #7477
• fix: package mlx only for mac by @louis-jan in #7479
• fix: disable custom parameters for remote providers by @louis-jan in #7481
• fix: select none assistant remote provider by @urmauur in #7480
• fix: ui remove thumbnail image by @urmauur in #7483
• fix: disable fit does not work well - llama.cpp somehow use max ctx-size by @louis-jan in #7482
• fix: tool call message malformed by @louis-jan in #7484
• fix: custom parameters by @louis-jan in #7487
• fix: patch env not work on windows by @louis-jan in #7486
• fix: local api server stream transform by @louis-jan in #7489
• fix: visibility toolbar state window on local api server by @urmauur in #7488
• fix: thumb default interface accent color based on theme color by @urmauur in #7490
• fix: new chat with first options assistants by @urmauur in #7491
• fix: state icon collapsible log inline local api server by @urmauur in #7493
• fix: start new chat from hub auto select model by @urmauur in #7494
• fix: disable --fit for mac by @louis-jan in #7495
• fix: correct creating env param for claude code integration by @Vanalite in #7492
• fix: bump router plugin to fix vite crash by @Vanalite in #7496
• fix: bash support for cc by @louis-jan in #7497
• fix: hub model filter condition by @louis-jan in #7499
• fix: hub rendering performance issue by @louis-jan in #7500
• fix: disable edit message while isn't selected model by @urmauur in #7498
• fix: register tools on new chat in a project by @Vanalite in #7501
• fix: allow users to cancel mlx model download by @louis-jan in #7502
• fix: update hub catalog v2 by @louis-jan in #7503
• fix: temporary disable prompt cache by @louis-jan in #7505
• fix: broken assistant selection by @louis-jan in #7506
• fix: assistant for project does not work by @louis-jan in #7509

New Contributors

• @Eruis2579 made their first contribution in #7434

Full Changelog: v0.7.6...v0.7.7

0.7.6

What's Changed

• docs: update homepage SEO meta title and description by @eckartal in #7024
• chore: update flatpak manifest by @Minh141120 in #7025
• blog: optimize "run AI locally" blog post for SEO by @eckartal in #7028
• feat: combine attachments icon by @urmauur in #6998
• fix: cstdint patch flatpak by @Minh141120 in #7032
• Fix/appstream caption by @Minh141120 in #7033
• feat: Update Russian localization by @Kuzmich55 in #7039
• SEO: Improve offline-chatgpt-alternative content by @eckartal in #7040
• feat: flatpak disable auto updater by @Minh141120 in #7054
• Update flatpak metainfo by @eckartal in #7064
• fix: flatpak appstream metadata validation errors by @Minh141120 in #7067
• docs: add Microsoft Store and Flathub badges by @qnixsynapse in #7068
• feat: add Polish metainfo translation by @0rzech in #7050
• fix: improve Hub download button UX for installed models by @Lokimorty in #7060
• Resolve Clippy Warnings and Apply Consistent Code Formatting by @github-roushan in #7010
• feat: Update Russian localization by @Kuzmich55 in #7082
• feat: complete Czech translations by @MichalZem in #7081
• Update metadata for ai.jan.Jan by @razzeee in #7045
• chore: update flatpak release 0.7.4 by @Minh141120 in #7117
• chore: add change log doc for v0.7.4 by @Vanalite in #7110
• refactor: clean up JoyRide by @louis-jan in #7073
• chore: update flatpak manifest for v0.7.5 by @Minh141120 in #7133
• chore: add change log doc for v0.7.5 by @Vanalite in #7132
• chore: resolve conflicts between dev and 0.7.5 release branch by @Vanalite in #7135
• chore: merge release 0.7.5 into dev branch by @Vanalite in #7134
• refactor: move llama.cpp config handling to Rust by @qnixsynapse in #7047
• fix: publisher name on windows by @Minh141120 in #7144
• feat: Update Russian localization by @Kuzmich55 in #7149
• feat: Improve toast messages and errors by @github-roushan in #6892
• feat: improve sidebar UI with distinct sections and better empty states by @github-roushan in #6745
• fix: prevent CUDA backend install failure by removing invalid fs.mkdir args by @qnixsynapse in #7162
• fix: responsive button action hero landing page by @urmauur in #7274
• refactor: jan web ci to use main branch and deprecate old workflows by @Minh141120 in #7332
• refactor: migrate llamacpp backend logic to rust plugin by @qnixsynapse in #7171
• feat: add portable windows by @Minh141120 in #7350
• feat: chat enhancement by @louis-jan in #7361
• feat: persist token usage into message metadata by @louis-jan in #7366
• ci: update matrix test on windows by @Minh141120 in #7367
• fix: tools availability and model settings by @louis-jan in #7368
• fix: file upload function and assistant migration by @louis-jan in #7369
• fix: missing shiki lib and import css katex by @urmauur in #7372
• fix: remove setting codeblock by @urmauur in #7371
• fix: font setup by @urmauur in #7373
• Make it easy to install on ARM by @SuperCowProducts in #7353
• docs: fix dead links to /docs/server and /docs/models by @chindris-mihai-alexandru in #7342
• feat: search dialog by @urmauur in #7374
• chore: refactor updater by @hiento09 in #7377
• fix: update renderer using plugins by @louis-jan in #7376
• chore: fix race condition in updater by @hiento09 in #7378
• fix: mcp tool approval by @louis-jan in #7379
• refactor: decouple platform guard logics by @louis-jan in #7380
• fix: resolve link api-reference page by @bittoby in #7384
• fix: regression - model download - users could not download with HF_TOKEN by @louis-jan in #7386
• fix: mcp overflow env by @louis-jan in #7387
• fix: disable fullscreen marmaid diagram by @urmauur in #7388
• enhancement: quickstart UI card by @urmauur in #7385
• fix: total download number by @urmauur in #7390
• feat: edit message and delete by @urmauur in #7391
• feat: Enable proxy to llama.cpp for Anthropic Messages API support. by @louis-jan in #7395
• fix: app updater does not remind for new update without restarting by @louis-jan in #7389
• fix: csp issue that blocking image upload on Windows by @louis-jan in #7396
• fix: openai raw tool call issue by @louis-jan in #7397
• fix: wrong cached model and provider first time create chat by @louis-jan in #7398
• fix: wrong trouble shooting guide url by @louis-jan in #7400
• fix: migrate mistral ai provider to have correct base url by @louis-jan in #7399
• fix: Remove trailing slash from changelog link to avoid redirect by @janpio in #7381
• fix: disable link open with dialog confirmation by @urmauur in #7402
• fix: text overflow error generations by @urmauur in #7404
• fix: leftpanel toggle on windows by @urmauur in #7401
• fix: reduce max-width model selector by @urmauur in #7403
• fix: should not regenerate on assistant message edit by @louis-jan in #7405
• feat: handle show dialog new jan model by @urmauur in #7406
• chore: Cherry pick to release/v0.7.6 by @Vanalite in #7411
• Chore/flatpak manifest 0.7.6 by @Minh141120 in #7412
• fix: mmproj path for vision capability by @Vanalite in #7414
• chore: setup screen q4 k xl by @louis-jan in #7417

New Contributors

• @MichalZem made their first contribution in #7081
• @razzeee made their first contribution in #7045
• @SuperCowProducts made their first contribution in #7353
• @chindris-mihai-alexandru made their first contribution in #7342
• @bittoby made their first contribution in #7384
• @janpio made their first contribution in #7381

Full Changelog: v0.7.5...v0.7.6

0.7.5

What's Changed

• fix: model import issue on Windows by @louis-jan in #7124
• fix: users couldn’t import the mmproj vision model if the base name didn’t match. by @louis-jan in #7127
• fix: correct CUDA backend installation and migration issues by @qnixsynapse in #7130
• fix: kill mcp server on app termination by @Vanalite in #7131

Full Changelog: v0.7.4...v0.7.5

0.7.4

What's Changed

• feat: add backend migration mapping and update backend handling by @qnixsynapse in #6917
• ci: clean up deduplicate issue workflow by @Minh141120 in #6923
• Enhance localization by completing missing translations across all locales + czech support by @github-roushan in #6758
• feat: Add official jan browser mcp by @Vanalite in #6929
• docs: add changelog v0.7.3 by @Minh141120 in #6951
• Merge release 0.7.3 to dev by @Vanalite in #6967
• fix: csp restrictions from inline styles by @urmauur in #6970
• fix: glib issue on linux by @Minh141120 in #6975
• fix: app blocks image input by @louis-jan in #6982
• fix: disable autocorrect in model search input by @Lokimorty in #6952
• French translation menu item missing by @fredatgithub in #6974
• chore: separate the loader style by @urmauur in #6984
• fix: changing tools while conversing results in incorrect tool use by @louis-jan in #6985
• Enable desktop file attachments feature by @dinhlongviolin1 in #6989
• feat: migrate assistant screen into setting by @urmauur in #6986
• fix: trafficlight icon mac responsive by @urmauur in #6994
• fix: reenable zoom hotkey by @urmauur in #6995
• feat: add CUDA 13 support to backend by @qnixsynapse in #6996
• chore: add CUDA 13 backend as a priority backend by @qnixsynapse in #7005
• chore: bump token.js by @Vanalite in #7006
• Correct the "Why Open-Source" URL by @trunghaiy in #6965
• docs: update handbook by @mmngn in #7007
• feat: move proactive mode to MCP settings by @Vanalite in #7008
• feat: lockfile to kill conflict MCP's port by @Vanalite in #7012
• fix: keep the untouched properties after modifying mcp settings by @Vanalite in #7014
• fix: preserve dollar sign followed by numbers in markdown rendering by @qnixsynapse in #7027
• fix: reattach the same file after deletion fix by @Vanalite in #7030
• feat: add embedding flag to model metadata and automatic detection by @qnixsynapse in #7031
• fix: Fix extension installation link by @Vanalite in #7042
• fix: spawn new process with window close flag by @Vanalite in #7043
• feat: update link to chrome store for Jan extension by @Vanalite in #7051
• fix: disable context menu list projects by @urmauur in #7056
• fix: ui check be version by @urmauur in #7057
• feat: update flatpak build by @Minh141120 in #7061
• fix: flatpak upload s3 by @Minh141120 in #7062
• fix: Enable JIT compilation to fix MCP server memory allocation errors by @louis-jan in #7072
• feat: quick start with Jan model by @Vanalite in #7052
• fix: Toast and dismiss validating toast using model_id by @Vanalite in #7065
• fix: cancel failed download task by @Vanalite in #7077
• fix: fix linter with missing parameters by @Vanalite in #7078
• feat: close app in background by @Vanalite in #7076
• feat: jan browser mcp as chat input shortcut by @louis-jan in #7074
• fix: skip model verification on quick start by @louis-jan in #7083
• fix: killing process with name checking logic by @Vanalite in #7085
• feat: Dialog to install Jan extension by @Vanalite in #7086
• fix: model import name should be filename instead of GGUF baseName by @louis-jan in #7088
• fix: could not save image edit by @louis-jan in #7089
• feat: Cancellation mechanism during mcp connectivity check by @Vanalite in #7090
• Feat/improve file attachments by @dinhlongviolin1 in #7080
• fix: attachment parsing error (exit gracefully) by @dinhlongviolin1 in #7093
• fix: handle API request errors and log them in llamacpp extension by @qnixsynapse in #7094
• fix: disable tool step limit in assistant by @louis-jan in #7096
• feat: add instruction to system_prompt to perform search when needed by @Vanalite in #7095
• feat: simplify onboarding flow and extension instruction by @Vanalite in #7097
• fix: lost first message using local llamacpp by @Vanalite in #7099
• fix: ensure cleanup functions complete before app exit by @qnixsynapse in #7101
• fix: quick start preparation in background by @Vanalite in #7100
• Improve file attachments re submit by @dinhlongviolin1 in #7102
• ci: reproduce linter test out of space on ubuntu by @Minh141120 in #7105
• fix: deprecate unstable restart mechanism that blocking browse feature by @louis-jan in #7109

New Contributors

• @trunghaiy made their first contribution in #6965
• @mmngn made their first contribution in #7007

Full Changelog: v0.7.3...v0.7.4