Louis
906c539541
Merge pull request #5531 from menloresearch/config/remove-mcp-production-gate
...
config: remove MCP and tool use production gate
2025-06-25 20:07:15 -07:00
Louis
63761efca2
config: remove MCP and tool use production gate
2025-06-26 10:01:42 +07:00
Louis
ea662c4876
Merge pull request #5528 from menloresearch/fix/default-model-settings-jan-nano
...
🐛 fix: default model settings for jan-nano-128k
2025-06-25 06:07:31 -07:00
Louis
d407ebc4e9
fix: typo
2025-06-25 19:42:22 +07:00
Louis
a7c441ee58
🐛 fix: default model settings for jan-nano-128k
2025-06-25 19:36:34 +07:00
Faisal Amir
3eb31be62e
✨ enhancement: adjust placement exp toggle ( #5525 )
...
* ✨ enhancement: adjust placement exp toggle
* Update web-app/src/routes/settings/general.tsx
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-06-25 17:10:02 +07:00
Louis
54a9d140b5
Merge pull request #5524 from menloresearch/enhancement/jan-nano-128k
...
✨ enhancement: Added jan-nano-128k
2025-06-25 16:31:58 +07:00
Faisal Amir
f5cfe8a537
✨ enhancement: Added jan-nano-128k
2025-06-25 15:56:38 +07:00
Sam Hoang Van
0890de1869
feat: improve local provider connectivity with CORS bypass ( #5458 )
...
* feat: improve local provider connectivity with CORS bypass
- Add @tauri-apps/plugin-http dependency
- Implement dual fetch strategy for local vs remote providers
- Auto-detect local providers (localhost, Ollama:11434, LM Studio:1234)
- Make API key optional for local providers
- Add comprehensive test coverage for provider fetching
refactor: simplify fetchModelsFromProvider by removing preflight check logic
* feat: extend config options to include custom fetch function for CORS handling
* feat: conditionally use Tauri's fetch for openai-compatible providers to handle CORS
2025-06-25 15:42:14 +07:00
Faisal Amir
52d15802d9
✨ enhancement: experimental feature toggle ( #5514 )
2025-06-25 14:10:54 +07:00
Faisal Amir
c463090edb
🐛 fix: delete pre populate remote models ( #5516 )
2025-06-25 13:49:55 +07:00
Louis
6e3852554a
sync: cherry pick v0.6.2 release ( #5515 )
...
* Feat: auto restart mcp (#5226 )
* feat: implement retry mechanism for MCP server activation with exponential backoff
feat: enhance MCP server activation with configurable retry attempts
feat: implement MCP server restart monitoring and cleanup functionality
feat: enhance MCP server restart logic with improved monitoring and configuration handling
feat: add manual deactivation for MCP servers to prevent automatic restarts
* feat: enhance MCP server startup with initial attempt tracking and health monitoring
* 🐛 fix: prevent render error when additional information missing from hardware (#5413 )
---------
Co-authored-by: Sam Hoang Van <samhv.ict@gmail.com>
Co-authored-by: Faisal Amir <urmauur@gmail.com>
2025-06-25 13:15:10 +07:00
Faisal Amir
8fdb65eba5
🐛 fix: prevent render error when additional information missing from hardware ( #5413 )
2025-06-25 11:41:28 +07:00
Sam Hoang Van
329fb7d023
Feat: auto restart mcp ( #5226 )
...
* feat: implement retry mechanism for MCP server activation with exponential backoff
feat: enhance MCP server activation with configurable retry attempts
feat: implement MCP server restart monitoring and cleanup functionality
feat: enhance MCP server restart logic with improved monitoring and configuration handling
feat: add manual deactivation for MCP servers to prevent automatic restarts
* feat: enhance MCP server startup with initial attempt tracking and health monitoring
2025-06-25 11:40:28 +07:00
Louis
5a09317c8d
Merge branch 'dev' into release/v0.6.1
...
# Conflicts:
# extensions/inference-cortex-extension/resources/default_settings.json
# extensions/inference-cortex-extension/src/index.ts
# extensions/model-extension/resources/default.json
# web-app/src/containers/ThreadContent.tsx
# web-app/src/containers/TokenSpeedIndicator.tsx
# web-app/src/hooks/useChat.ts
# web-app/src/lib/version.ts
# web-app/src/routes/hub.tsx
# web-app/src/routes/settings/hardware.tsx
2025-06-20 09:41:43 +07:00
Faisal Amir
67592f3f45
🐛 fix: avoid render html title thread ( #5375 )
...
* 🐛 fix: avoid render html title thread
* chore: minor bump - tokenjs for manual adding models
---------
Co-authored-by: Louis <louis@jan.ai>
2025-06-19 23:08:45 +07:00
Faisal Amir
5a73031d62
fix: remove log ( #5366 )
2025-06-19 15:52:29 +07:00
Faisal Amir
cf17576e1c
fix: download link ( #5365 )
2025-06-19 15:40:54 +07:00
Faisal Amir
85d32a4c70
✨ enhancement: show app size on download dropdown ( #5360 )
...
* ✨ enhancement: show app size on download dropdown
* Update docs/src/utils/format.ts
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* chor: update copy
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-06-19 12:04:16 +07:00
Louis
22396111be
fix: stop api server on page unload ( #5356 )
...
* fix: stop api server on page unload
* fix: check api server status on reload
* refactor: api server state
* fix: should not pop the guard
2025-06-19 00:12:03 +07:00
David
8c507e5569
Merge pull request #5357 from menloresearch/fix/update-broken-installation-url
...
fix: update broken installation url
2025-06-18 22:59:48 +07:00
David
4400d50c30
fix: update broken installation url
2025-06-18 22:57:33 +07:00
Faisal Amir
5b60116d21
🐛 fix: setting provider hide model capabilities ( #5355 )
...
* 🐛 fix: setting provider hide model capabilities
* 🐛 fix: hide tools icon on dropdown model providers
* fix: stop server on app close or reload
* ✨ enhancement: reset heading class
---------
Co-authored-by: Louis <louis@jan.ai>
2025-06-18 21:48:18 +07:00
Faisal Amir
c6cd37d916
fix: built in models capabilities ( #5354 )
2025-06-18 20:28:30 +07:00
Faisal Amir
0681c6bb9e
fix: glitch toggle gpus ( #5353 )
...
* fix: glitch toogle gpu
* fix: Using the GPU's array index as a key for gpuLoading
* enhancement: added try-finally
2025-06-18 19:58:24 +07:00
Bui Quang Huy
f5971b9d03
🔀 Merge: pull request #5351 from menloresearch/fix/window-path-fix
...
🐛 Fix: window path name with a space lead to cannot find correct path to Jan datafolder
2025-06-18 17:17:53 +07:00
Sam Hoang Van
eb5655bbd4
fix(proxy): implement true HTTP streaming for chat completions API ( #5350 )
2025-06-18 16:19:48 +07:00
Sam Hoang Van
6cee466f52
fix(server): add gzip decompression support for /models endpoint filtering ( #5349 )
...
- Add gzip detection using magic number check (0x1f 0x8b)
- Implement gzip decompression before JSON parsing
- Add gzip re-compression for filtered responses
- Fix "invalid utf-8 sequence" error when upstream returns gzipped content
- Maintain Content-Encoding consistency for compressed responses
- Add comprehensive gzip handling with flate2 library
Resolves issue where filtering failed on gzip-compressed model responses.
2025-06-18 15:30:31 +07:00
Faisal Amir
45df0b272d
🐛 fix: render streaming token speed based on thread ID & assistant metadata ( #5346 )
2025-06-18 14:54:56 +07:00
Sam Hoang Van
369ba5ac75
feat(server): filter /models endpoint to show only downloaded models ( #5343 )
...
- Add filtering logic to proxy server for GET /models requests
- Keep only models with status "downloaded" in response
- Remove Content-Length header to prevent mismatch after filtering
- Support both ListModelsResponseDto and direct array formats
- Add comprehensive tests for filtering functionality
- Fix Content-Length header conflict causing empty responses
Fixes issue where all models were returned regardless of download status.
2025-06-18 14:11:53 +07:00
Saugat Acharya
f41c565f95
docs: update continue integration link ( #5344 )
2025-06-18 14:03:55 +07:00
LazyYuuki
a075debb05
🐛 fix: window path problem
2025-06-18 14:02:36 +08:00
Faisal Amir
771105a5b2
🐛 fix: handle NaN value tokenspeed ( #5339 )
2025-06-18 12:35:42 +07:00
Faisal Amir
417b789b5e
🐛 fix: update wording desc vulkan ( #5338 )
...
* 🐛 fix: update wording desc vulkan
* ✨ enhancement: update copy
2025-06-18 12:35:37 +07:00
Sam Hoang Van
b30de3d1ae
fix: sorted-thread-not-stable ( #5336 )
2025-06-18 09:39:18 +07:00
Ramon Perez
06be778e98
improved wording in UI elements ( #5323 )
2025-06-18 09:35:57 +07:00
Sam Hoang Van
1160ea140b
🐛 fix: disable sorting for threads in SortableItem and clean up thread order handling ( #5326 )
2025-06-18 00:23:53 +07:00
Nguyen Ngoc Minh
3f07358125
🐛 fix(updater): terminate sidecar processes before update to avoid file access errors ( #5325 )
2025-06-17 23:43:15 +07:00
Ramon Perez
3b624eb466
improved wording in UI elements ( #5323 )
2025-06-17 23:17:15 +07:00
Louis
52bb54d2d5
fix: glitch model download issue ( #5322 )
2025-06-17 23:01:22 +07:00
Louis
ebc268018b
Sync 0.5.18 to 0.6.0 ( #5320 )
...
* chore: correct binary name for stable version (#5303 )
* ci: enable devtool on prod build (#5317 )
* ci: enable devtool on prod build
---------
Co-authored-by: hiento09 <136591877+hiento09@users.noreply.github.com>
Co-authored-by: Nguyen Ngoc Minh <91668012+Minh141120@users.noreply.github.com>
2025-06-17 21:08:56 +07:00
Faisal Amir
11d767633e
🐛 fix: allow script posthog ( #5316 )
2025-06-17 18:35:02 +07:00
Louis
86079074d2
🐛 fix: update default extension settings ( #5315 )
...
* fix: update default extension settings
* chore: hide language setting on Prod
2025-06-17 17:37:31 +07:00
Louis
2899d58ad7
🐛 fix: llama.cpp default NGL setting does not offload all layers to GPU ( #5310 )
...
* 🐛 fix: llama.cpp default NGL setting does not offload all layers to GPU
* chore: cover more cases
* chore: clean up
* fix: should not show GPU section on Mac
2025-06-17 15:30:07 +07:00
Louis
50c25b65b6
chore: correct binary name for stable version ( #5303 ) ( #5311 )
...
Co-authored-by: hiento09 <136591877+hiento09@users.noreply.github.com>
2025-06-17 13:35:53 +07:00
Faisal Amir
321fb858dd
🐛 fix:safely convert values to numbers and handle NaN cases ( #5309 )
2025-06-17 13:15:40 +07:00
Faisal Amir
f0ec3e03d1
🐛 fix: immediately show download progress ( #5308 )
2025-06-17 12:46:23 +07:00
Faisal Amir
a745d24fbe
🐛 fix: glitch padding speed token ( #5307 )
2025-06-17 10:00:55 +07:00
Faisal Amir
f7b53da898
🐛 fix: hide token speed when assistant params stream false ( #5302 )
2025-06-16 21:50:23 +07:00
Faisal Amir
4dfc9f604a
🐛 fix: remove onboarding local model and hide the edit capabilities model ( #5301 )
...
* 🐛 fix: remove onboarding local model and hide the edit capabilities model
* ♻️ refactor: conditional search params setup screen
2025-06-16 20:53:48 +07:00
