* fix: avoid error validate nested dom
* fix: correct context shift flag handling in LlamaCPP extension (#6404) (#6431)
* fix: correct context shift flag handling in LlamaCPP extension
The previous implementation added the `--no-context-shift` flag when `cfg.ctx_shift` was disabled, which conflicted with the llama.cpp CLI where the presence of `--context-shift` enables the feature.
The logic is updated to push `--context-shift` only when `cfg.ctx_shift` is true, ensuring the extension passes the correct argument and behaves as expected.
* feat: detect model out of context during generation
---------
Co-authored-by: Dinh Long Nguyen <dinhlongviolin1@gmail.com>
* chore: add install-rust-targets step for macOS universal builds
* fix: make install-rust-targets a dependency
* enhancement: copy MCP permission
* chore: make action mutton capitalize
* Update web-app/src/locales/en/tool-approval.json
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* chore: simplify macos workflow
* fix: KVCache size calculation and refactor (#6438)
- Removed the unused `getKVCachePerToken` helper and replaced it with a unified `estimateKVCache` that returns both total size and per‑token size.
- Fixed the KV cache size calculation to account for all layers, correcting previous under‑estimation.
- Added proper clamping of user‑requested context lengths to the model’s maximum.
- Refactored VRAM budgeting: introduced explicit reserves, fixed engine overhead, and separate multipliers for VRAM and system RAM based on memory mode.
- Implemented a more robust planning flow with clear GPU, Hybrid, and CPU pathways, including fallback configurations when resources are insufficient.
- Updated default context length handling and safety buffers to prevent OOM situations.
- Adjusted usable memory percentage to 90 % and refined logging for easier debugging.
* fix: detect allocation failures as out-of-memory errors (#6459)
The Llama.cpp backend can emit the phrase “failed to allocate” when it runs out of memory.
Adding this check ensures such messages are correctly classified as out‑of‑memory errors,
providing more accurate error handling CPU backends.
* fix: pathname file install BE
* fix: set default memory mode and clean up unused import (#6463)
Use fallback value 'high' for memory_util config and remove unused GgufMetadata import.
* fix: auto update should not block popup
* fix: remove log
* fix: imporove edit message with attachment image
* fix: imporove edit message with attachment image
* fix: type imageurl
* fix: immediate dropdown value update
* fix: linter
* fix/validate-mmproj-from-general-basename
* fix/revalidate-model-gguf
* fix: loader when importing
* fix/mcp-json-validation
* chore: update locale mcp json
* fix: new extension settings aren't populated properly (#6476)
* chore: embed webview2 bootstrapper in tauri windows
* fix: validat type mcp json
* chore: prevent click outside for edit dialog
* feat: add qa checklist
* chore: remove old checklist
* chore: correct typo in checklist
* fix: correct memory suitability checks in llamacpp extension (#6504)
The previous implementation mixed model size and VRAM checks, leading to inaccurate status reporting (e.g., false RED results).
- Simplified import statement for `readGgufMetadata`.
- Fixed RAM/VRAM comparison by removing unnecessary parentheses.
- Replaced ambiguous `modelSize > usableTotalMemory` check with a clear `totalRequired > usableTotalMemory` hard‑limit condition.
- Refactored the status logic to explicitly handle the CPU‑GPU hybrid scenario, returning **YELLOW** when the total requirement fits combined memory but exceeds VRAM.
- Updated comments for better readability and maintenance.
* fix: thread rerender issue
* chore: clean up console log
* chore: uncomment irrelevant fix
* fix: linter
* chore: remove duplicated block
* fix: tests
* Merge pull request #6469 from menloresearch/fix/deeplink-not-work-on-windows
fix: deeplink issue on Windows
* fix: reduce unnessary rerender due to current thread retrieval
* fix: reduce app layout rerender due to router state update
* fix: avoid the entire app layout re render on route change
* clean: unused import
* Merge pull request #6514 from menloresearch/feat/web-gtag
feat: Add GA Measurement and change keyboard bindings on web
* chore: update build tauri commands
* chore: remove unused task
* fix: should not rerender thread message components when typing
* fix re render issue
* direct tokenspeed access
* chore: sync latest
* feat: Add Jan API server Swagger UI (#6502)
* feat: Add Jan API server Swagger UI
- Serve OpenAPI spec (`static/openapi.json`) directly from the proxy server.
- Implement Swagger UI assets (`swagger-ui.css`, `swagger-ui-bundle.js`, `favicon.ico`) and a simple HTML wrapper under `/docs`.
- Extend the proxy whitelist to include Swagger UI routes.
- Add routing logic for `/openapi.json`, `/docs`, and Swagger UI static files.
- Update whitelisted paths and integrate CORS handling for the new endpoints.
* feat: serve Swagger UI at root path
The Swagger UI endpoint previously lived under `/docs`. The route handling and
exclusion list have been updated so the UI is now served directly at `/`.
This simplifies access, aligns with the expected root URL in the Tauri
frontend, and removes the now‑unused `/docs` path handling.
* feat: add model loading state and translations for local API server
Implemented a loading indicator for model startup, updated the start/stop button to reflect model loading and server starting states, and disabled interactions while pending. Added new translation keys (`loadingModel`, `startingServer`) across all supported locales (en, de, id, pl, vn, zh-CN, zh-TW) and integrated them into the UI. Included a small delay after model start to ensure backend state consistency. This improves user feedback and prevents race conditions during server initialization.
* fix: tests
* fix: linter
* fix: build
* docs: update changelog for v0.6.10
* fix(number-input): preserve '0.0x' format when typing (#6520)
* docs: update url for gifs and videos
* chore: update url for jan-v1 docs
* fix: Typo in openapi JSON (#6528)
* enhancement: toaster delete mcp server
* Update 2025-09-18-auto-optimize-vision-imports.mdx
* Merge pull request #6475 from menloresearch/feat/bump-tokenjs
feat: fix remote provider vision capability
* fix: prevent consecutive messages with same role (#6544)
* fix: prevent consecutive messages with same role
* fix: tests
* fix: first message should not be assistant
* fix: tests
* feat: Prompt progress when streaming (#6503)
* feat: Prompt progress when streaming
- BE changes:
- Add a `return_progress` flag to `chatCompletionRequest` and a corresponding `prompt_progress` payload in `chatCompletionChunk`. Introduce `chatCompletionPromptProgress` interface to capture cache, processed, time, and total token counts.
- Update the Llamacpp extension to always request progress data when streaming, enabling UI components to display real‑time generation progress and leverage llama.cpp’s built‑in progress reporting.
* Make return_progress optional
* chore: update ui prompt progress before streaming content
* chore: remove log
* chore: remove progress when percentage >= 100
* chore: set timeout prompt progress
* chore: move prompt progress outside streaming content
* fix: tests
---------
Co-authored-by: Faisal Amir <urmauur@gmail.com>
Co-authored-by: Louis <louis@jan.ai>
* chore: add ci for web stag (#6550)
* feat: add getTokensCount method to compute token usage (#6467)
* feat: add getTokensCount method to compute token usage
Implemented a new async `getTokensCount` function in the LLaMA.cpp extension.
The method validates the model session, checks process health, applies the request template, and tokenizes the resulting prompt to return the token count. Includes detailed error handling for crashed models and API failures, enabling callers to assess token usage before sending completions.
* Fix: typos
* chore: update ui token usage
* chore: remove unused code
* feat: add image token handling for multimodal LlamaCPP models
Implemented support for counting image tokens when using vision-enabled models:
- Extended `SessionInfo` with optional `mmprojPath` to store the multimodal project file.
- Propagated `mmproj_path` from the Tauri plugin into the session info.
- Added import of `chatCompletionRequestMessage` and enhanced token calculation logic in the LlamaCPP extension:
- Detects image content in messages.
- Reads GGUF metadata from `mmprojPath` to compute accurate image token counts.
- Provides a fallback estimation if metadata reading fails.
- Returns the sum of text and image tokens.
- Introduced helper methods `calculateImageTokens` and `estimateImageTokensFallback`.
- Minor clean‑ups such as comment capitalization and debug logging.
* chore: update FE send params message include content type image_url
* fix mmproj path from session info and num tokens calculation
* fix: Correct image token estimation calculation in llamacpp extension
This commit addresses an inaccurate token count for images in the llama.cpp extension.
The previous logic incorrectly calculated the token count based on image patch size and dimensions. This has been replaced with a more precise method that uses the clip.vision.projection_dim value from the model metadata.
Additionally, unnecessary debug logging was removed, and a new log was added to show the mmproj metadata for improved visibility.
* fix per image calc
* fix: crash due to force unwrap
---------
Co-authored-by: Faisal Amir <urmauur@gmail.com>
Co-authored-by: Louis <louis@jan.ai>
* fix: custom fetch for all providers (#6538)
* fix: custom fetch for all providers
* fix: run in development should use built-in fetch
* add full-width model names (#6350)
* fix: prevent relocation to root directories (#6547)
* fix: prevent relocation to root directories
* Update web-app/src/locales/zh-TW/settings.json
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>
* feat: web remote conversation (#6554)
* feat: implement conversation endpoint
* use conversation aware endpoint
* fetch message correctly
* preserve first message
* fix logout
* fix broadcast issue locally + auth not refreshing profile on other tabs+ clean up and sync messages
* add is dev tag
---------
Co-authored-by: Faisal Amir <urmauur@gmail.com>
Co-authored-by: Akarshan Biswas <akarshan@menlo.ai>
Co-authored-by: Minh141120 <minh.itptit@gmail.com>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: Nguyen Ngoc Minh <91668012+Minh141120@users.noreply.github.com>
Co-authored-by: Louis <louis@jan.ai>
Co-authored-by: Bui Quang Huy <34532913+LazyYuuki@users.noreply.github.com>
Co-authored-by: Roushan Singh <github.rtron18@gmail.com>
Co-authored-by: hiento09 <136591877+hiento09@users.noreply.github.com>
Co-authored-by: Alexey Haidamaka <gdmkaa@gmail.com>
* feat: implement conversation endpoint
* use conversation aware endpoint
* fetch message correctly
* preserve first message
* fix logout
* fix broadcast issue locally + auth not refreshing profile on other tabs+ clean up and sync messages
* add is dev tag
* feat: add getTokensCount method to compute token usage
Implemented a new async `getTokensCount` function in the LLaMA.cpp extension.
The method validates the model session, checks process health, applies the request template, and tokenizes the resulting prompt to return the token count. Includes detailed error handling for crashed models and API failures, enabling callers to assess token usage before sending completions.
* Fix: typos
* chore: update ui token usage
* chore: remove unused code
* feat: add image token handling for multimodal LlamaCPP models
Implemented support for counting image tokens when using vision-enabled models:
- Extended `SessionInfo` with optional `mmprojPath` to store the multimodal project file.
- Propagated `mmproj_path` from the Tauri plugin into the session info.
- Added import of `chatCompletionRequestMessage` and enhanced token calculation logic in the LlamaCPP extension:
- Detects image content in messages.
- Reads GGUF metadata from `mmprojPath` to compute accurate image token counts.
- Provides a fallback estimation if metadata reading fails.
- Returns the sum of text and image tokens.
- Introduced helper methods `calculateImageTokens` and `estimateImageTokensFallback`.
- Minor clean‑ups such as comment capitalization and debug logging.
* chore: update FE send params message include content type image_url
* fix mmproj path from session info and num tokens calculation
* fix: Correct image token estimation calculation in llamacpp extension
This commit addresses an inaccurate token count for images in the llama.cpp extension.
The previous logic incorrectly calculated the token count based on image patch size and dimensions. This has been replaced with a more precise method that uses the clip.vision.projection_dim value from the model metadata.
Additionally, unnecessary debug logging was removed, and a new log was added to show the mmproj metadata for improved visibility.
* fix per image calc
* fix: crash due to force unwrap
---------
Co-authored-by: Faisal Amir <urmauur@gmail.com>
Co-authored-by: Louis <louis@jan.ai>
* feat: Prompt progress when streaming
- BE changes:
- Add a `return_progress` flag to `chatCompletionRequest` and a corresponding `prompt_progress` payload in `chatCompletionChunk`. Introduce `chatCompletionPromptProgress` interface to capture cache, processed, time, and total token counts.
- Update the Llamacpp extension to always request progress data when streaming, enabling UI components to display real‑time generation progress and leverage llama.cpp’s built‑in progress reporting.
* Make return_progress optional
* chore: update ui prompt progress before streaming content
* chore: remove log
* chore: remove progress when percentage >= 100
* chore: set timeout prompt progress
* chore: move prompt progress outside streaming content
* fix: tests
---------
Co-authored-by: Faisal Amir <urmauur@gmail.com>
Co-authored-by: Louis <louis@jan.ai>
