Faisal Amir
872284b770
enhancement: offload model when provider not active
2025-08-19 14:18:39 +07:00
Louis
55390de070
Merge pull request #6222 from menloresearch/feat/model-tool-use-detection
...
feat: #5917 - model tool use capability should be auto detected
2025-08-19 13:55:08 +07:00
Louis
d7cf258a40
fix: tool indicator in hub
2025-08-19 10:40:11 +07:00
Louis
0dc0a9a4a3
fix: tests
2025-08-19 09:57:10 +07:00
Louis
bfe671d7b4
feat: #5917 - model tool use capability should be auto detected
2025-08-19 09:51:36 +07:00
Louis
3e6757300c
fix: update token.js to remove retired models
2025-08-18 22:33:20 +07:00
Dinh Long Nguyen
2d486d7b3a
feat: add support for reasoning fields (OpenRouter) ( #6206 )
...
* add support for reasoning fields (OpenRouter)
* reformat
* fix linter
* Update web-app/src/utils/reasoning.ts
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>
2025-08-18 21:59:14 +07:00
Faisal Amir
1eb1bb91ce
chore: update placeholder
2025-08-18 12:17:24 +07:00
Faisal Amir
d2cc9cc13b
enhancement: mcp disable save button when server name still empty
2025-08-18 12:13:55 +07:00
Louis
362324cb87
Merge pull request #6188 from menloresearch/feat/mcp-enhancement
...
feat: mcp enhancement
2025-08-18 09:55:44 +07:00
Faisal Amir
b1b2ca1987
Merge pull request #6006 from menloresearch/feat/fav-model
...
🚀 feat: allow user mark model as favorite
2025-08-17 23:14:26 +07:00
Louis
83b53210ee
Merge pull request #6092 from cmppoon/fix-default-predefine-color-palette
...
fix: default color not selected in appearance color palette
2025-08-16 20:17:25 +07:00
Jasper Morgal
4ba56f1377
Fix Issue #6199
...
Fix Issue: Jan UI Bottlenecks Token Rendering Speed to ~300 TPS Despite Faster Cerebras API Output
2025-08-15 15:00:29 -07:00
Louis
c8d9592ab8
chore: mcp group server, action and import json
2025-08-15 11:37:21 +07:00
Dinh Long Nguyen
e1c8d98bf2
Backend Architecture Refactoring ( #6094 ) ( #6162 )
...
* add llamacpp plugin
* Refactor llamacpp plugin
* add utils plugin
* remove utils folder
* add hardware implementation
* add utils folder + move utils function
* organize cargo files
* refactor utils src
* refactor util
* apply fmt
* fmt
* Update gguf + reformat
* add permission for gguf commands
* fix cargo test windows
* revert yarn lock
* remove cargo.lock for hardware plugin
* ignore cargo.lock file
* Fix hardware invoke + refactor hardware + refactor tests, constants
* use api wrapper in extension to invoke hardware call + api wrapper build integration
* add newline at EOF (per Akarshan)
* add vi mock for getSystemInfo
2025-08-15 08:59:01 +07:00
Louis
dcb46174ff
fix: test
2025-08-14 14:30:43 +07:00
Minh141120
aa8fb0464c
Merge branch 'dev' into fix/feature-toggle-auto-updater
2025-08-14 13:42:27 +07:00
Minh141120
388959a1fe
chore: gate check auto updater
2025-08-14 12:39:48 +07:00
Faisal Amir
a66d83c598
Merge pull request #6172 from menloresearch/fix/model-id-special-char
...
fix: handle modelId special char
2025-08-14 12:33:58 +07:00
Faisal Amir
6acdf22e41
chore: reorder error
2025-08-14 12:02:47 +07:00
Faisal Amir
10f3f7cea5
chore: handle copy error object message
2025-08-14 11:57:28 +07:00
Louis
16bfd6eafb
fix: full url search
2025-08-14 11:33:03 +07:00
Louis
83bb765bcc
Apply suggestion from @ellipsis-dev[bot]
...
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-08-14 10:55:49 +07:00
Louis
8c28f9b6a6
fix: should normalize model ID from source instead of frontend
2025-08-14 10:54:40 +07:00
Louis
526e532e2d
fix: normalize model id from source preparation
2025-08-14 10:50:50 +07:00
Faisal Amir
5657b6d917
chore: fix sanitaize
2025-08-14 10:28:11 +07:00
Faisal Amir
dd5b9e23f5
chore: update progress bar variant model
2025-08-14 10:22:57 +07:00
Louis
da08becd93
fix: duplicate HF search results
2025-08-14 10:15:33 +07:00
Louis
4350d4c9a0
fix: feature toggle for auto updater
2025-08-14 09:58:46 +07:00
Faisal Amir
ace8214d4d
chore: make utils sanitize modelId
2025-08-14 09:42:47 +07:00
Faisal Amir
1f0e79e934
chore: update handle download variant
2025-08-14 09:26:54 +07:00
Faisal Amir
b338849952
fix: handle modelId special char
2025-08-14 09:18:03 +07:00
Faisal Amir
985a8f31ae
fix: migrations model setting ( #6165 )
2025-08-13 18:21:48 +07:00
Faisal Amir
5266583e5b
enhancement: Add support for mmproj models ( #6150 )
2025-08-13 10:05:25 +07:00
Louis
7b2d0432e6
fix: weird HF readme accessibility
2025-08-12 12:46:57 +07:00
Louis
1a72a592b9
fix: visualize readme content for private repo with HF token
2025-08-12 12:07:25 +07:00
Louis
8e5fac83fd
fix: deprecate addSource tests since the function was removed
2025-08-12 11:25:47 +07:00
Louis
736790473e
fix: duplicate model while searching
2025-08-12 11:17:00 +07:00
Louis
276a286853
fix: tests
2025-08-12 10:37:00 +07:00
Louis
25a0c14be8
chore: whitelist jan model with tool use support by default
2025-08-12 10:33:41 +07:00
Louis
c355649759
fix: HF token is not used while searching repositories
2025-08-11 15:29:50 +07:00
Louis
f3dd26e499
fix: uvx and npx dirs should be not be relocated
2025-08-11 14:33:58 +07:00
Louis
b924156a15
fix: bring back GPU detection
2025-08-11 13:52:20 +07:00
Louis
3fc85c59e0
Merge pull request #6109 from B0sh/fix/ime-fix
...
fix: Prevent accidental message submitting on ChatInput for IME users
2025-08-11 11:40:41 +07:00
Louis
4f5d9b8222
Merge pull request #6089 from menloresearch/fix/clean-up-unused-apis
...
refactor: clean up unused hardware apis
2025-08-11 00:02:31 +07:00
B0sh
9b8fb62790
fix: Prevent accidental message submitting on ChatInput for users with IME input languages
2025-08-09 11:28:58 -05:00
Chaiyapruek Muangsiri
b2b0c64c48
fix: default color not selected in appearance color palette
2025-08-08 09:03:46 +08:00
Akarshan Biswas
0cfc745954
feat: Introduce structured error handling for llamacpp extension ( #6087 )
...
* feat: Introduce structured error handling for llamacpp extension
This commit introduces a structured error handling system for the `llamacpp` extension. Instead of returning simple string errors, we now use a custom `LlamacppError` struct with a specific `ErrorCode` enum. This allows the frontend to display more user-friendly and actionable error messages based on the code, rather than raw debug logs.
The changes include:
- A new `ErrorCode` enum to categorize errors (e.g., `OutOfMemory`, `ModelArchNotSupported`, `BinaryNotFound`).
- A `LlamacppError` struct to encapsulate the code, a user-facing message, and optional detailed logs.
- A static method `from_stderr` that intelligently parses llama.cpp's standard error output to identify and map common issues like Out of Memory errors to a specific error code.
- Refactored `ServerError` enum to wrap the new `LlamacppError` and provide a consistent serialization format for the Tauri frontend.
- Updated all relevant functions (`load_llama_model`, `get_devices`) to return the new structured error type, ensuring a more robust and predictable error flow.
- A reduced timeout for model loading from 300 to 180 seconds.
This work lays the groundwork for a more intuitive and helpful user experience, as the application can now provide clear guidance to users when a model fails to load.
* Update src-tauri/src/core/utils/extensions/inference_llamacpp_extension/server.rs
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* Update src-tauri/src/core/utils/extensions/inference_llamacpp_extension/server.rs
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* chore: update FE handle error object from extension
* chore: fix property type
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: Faisal Amir <urmauur@gmail.com>
2025-08-07 23:28:25 +05:30
Faisal Amir
4d67418b0d
fix: update ux recemmend backend label into desc setting ( #6088 )
2025-08-07 22:14:23 +07:00
Louis
ab44faeda3
test: fix test
2025-08-07 20:09:07 +07:00
