Releases: n4ze3m/page-assist
v1.5.4
What's Changed
- feat: System prompts now support a key to retrieve the current date and time.
- feat: Added an option for the user chat bubble.
- feat: Added a copy button to user messages.
- chore: Updated French translations by @hgourvest in #477
- chore: Updated Chinese translations by @Nriver in #478
- refactor: Added error handling and cleaned up code by @garyhuangdev in #482
- fix: Fixed the Model Nickname bug.
Note for Firefox Users
As I mentioned in the 1.5.3 release, the Firefox extension now requires a human review, which will delay the release or the availability of the latest updates. I will upload the latest version to the add-on store every week and hope they approve it quickly
Note for Chrome Users
Somehow, version 1.5.3 has not yet been reviewed by the Chrome Web Store. So, in this case, I am including the CRX file of the latest release, which you can simply drag and drop into chrome://extensions/
. This will automatically update Page Assist to the latest version without removing any data.
New Contributors
- @hgourvest made their first contribution in #477
- @Nriver made their first contribution in #478
- @garyhuangdev made their first contribution in #482
Full Changelog: v1.5.3...v1.5.4
v1.5.3
What's Changed
- feat: Added nickname and avatar functionality for models.
- feat: Added Struct search provider.
- feat: Added Startpage search provider.
- feat(readme): Added a Simplified Chinese series introduction to Page Assist by @usersync in #468
- fix: Fixed a typo in the variable name by @KGESH in #470
Note for Firefox Users
I submitted version 1.5.2 last week. The current version, 1.5.3, has also been submitted, but it has not yet been approved by the Firefox Add-ons store. Extensions with over 10,000 users now require a human review. Sorry for the delay—it's out of my control. :(
New Contributors
Full Changelog: v1.5.2...v1.5.3
v1.5.2
What's Changed
- feat(search): Added Bing as a search engine by @zwlcoding in #431
- feat(i18n): Added Traditional Chinese language support by @sk5s in #440
- feat(settings): Added an option to collapse reasoning by default
- feat: Added LLaMa.cpp (llama-server) support
- fix(sidepanel): Adjusted layout and improved image handling
- fix Replaced ClipboardIcon with CopyIcon
- fix: Adjusted composition handling for non-Firefox browsers
- style(Header): Updated Select component width to min-w-80 for better responsiveness
- fix(search): Implemented a selected model fallback for embedding
New Contributors
- @zwlcoding made their first contribution in #436
- @sk5s made their first contribution in #440
Full Changelog: v1.5.1...v1.5.2
v1.5.1
What's Changed
- feat: Added wide-mode by @yz778 in #325
- feat: Added pagination to Google Search by @wysh3 in #344
- feat: Added support for SiliconFlow, VolcEngine, TencentCloud, and AliBaBaCloud providers by @popcell in #373
- fix (Firefox): Fixed missing TTS speaking state update by @drendog in #376
- fix: Enhanced LaTeX preprocessing for code blocks and expressions
- fix (Sidebar): Addressed website embedding requirements in the chat form
- feat: Added an automatic CORS fix toggle for Ollama integration
- refactor: Renamed "Number of Contexts" to "Context Window Size"
- feat: Added the ability to disable Ollama integration in Page Assist
- feat: Enabled exporting chat conversations as images with improved visual fidelity
New Contributors
- @wysh3 made their first contribution in #344
- @popcell made their first contribution in #373
- @drendog made their first contribution in #376
Full Changelog: v1.5.0...v1.5.1
v1.5.0
What's Changed
- feat: Enhanced Chat UI
- feat: Added support for the
reasoning_content
field for DeepSeek and similar API providers (#343) - feat: Added a ChatGPT-like floating copy button for code blocks
- feat: Page Assist published to the Edge Add-on Store
- feat: Added a setting to enable/disable the removal of reasoning tokens in TTS (default: enabled)
- fix:
keep_alive
should not be sent if empty - fix: Resolved layout shift caused by hovering over icons and other miscellaneous items (@yz778, #323)
- fix: Corrected some typos by @yz778 in PR #332
Full Changelog: v1.4.5...v1.5.0
v1.4.5
v1.4.4
What's Changed
- feat: added support for 'thinking collapsible' in reasoning models messages
- fix: add error handling to fetch advanced Ollama settings data
- feat: change default search provider to DuckDuckGo
- fix: add query invalidation for sidebar settings after saving changes
- feat: no need for an embedding model for simple internet search
- fix: Revert to old model selection due to performance issues with the new one
Full Changelog: v1.4.3...v1.4.4
v1.4.3
What's Changed
- feat: Added an option to download chats as images
- feat: Added an option to enable chat with a website by default
- feat: Added DeepSeek as provider
- fix: Resolved the model name issue when copying Markdown.
Full Changelog: v1.4.2...v1.4.3
v1.4.2
What's Changed
- feat: Add chat history and functionality to the side panel chat/copilot
- feat: Add option to enable internet search by default
- feat: Improve UI and UX
Full Changelog: v1.4.1...v1.4.2
v1.4.1
What's Changed
- feat: Added support for Mistral (api) as a provider.
- feat: Added text splitting configuration options (
CharacterTextSplitter
,RecursiveCharacterTextSplitter
). - feat: Added additional Ollama model settings
tfsZ
,numKeep
,numThread
, anduseMlock
. - fix: Resolved various minor bugs.
Full Changelog: v1.4.0...v1.4.1