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
ogimageby @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