Release Notes

Version 3.0.4

Safari and Chrome

• Translation now completes in a single request. A translated draft appears only once it really is in the target language, and when a model keeps answering in the original language the extension reports the translation as failed and suggests another model instead of showing untouched text as a translation.

• Pages still running an older version of the extension after an update now ask you to reload the page in a centered dialog instead of failing quietly. Requests from those pages time out, so the license check, side panel, and paywall no longer spin forever.

• A post is scored once. When a post you already scored shows up again, its stored score is reused, so its full text is not fetched and the model is not called again. Full text is kept for 7 days (up to 300 posts), and each page session fetches at most 20.

Chrome

• Score-cache cleanup now discards the post-ID index along with the cached scores, so changing the filtering rules cannot bring old scores back.

Version 3.0.3

Safari and Chrome

• Added a long-post penalty based on estimated reading time, with a score breakdown showing the original score, penalty, and reading estimate. The reading speed is adjustable; the deduction itself is fixed at 5 points per 10 seconds beyond the first 10, capped at 40.

Chrome

• Chrome reads the full text of folded X posts for scoring without expanding them in the feed.

• Chrome built-in Gemini can score post images when its vision model is available; otherwise, scoring falls back to the configured model.

Version 3.0.1

Chrome

• Connect OpenAI-compatible services or Ollama by entering the server address, with automatic protocol detection and fallback when fetching models.

• Adding models now opens in batch mode. Fetch the list, select multiple models, and save them without waiting for each model to load and run a connection test. Single-model entry still checks the connection.

• Reuse an existing service address and API key when adding more models.

• Accept server addresses without an http:// prefix and preserve full model identifiers, including local model paths.

• Improve scoring compatibility with thinking models and strict API servers, and retry empty scoring responses with a larger output budget.

• Keep existing model settings during the update and show the installed version consistently in settings.

Version 2.8.2

Chrome

• Improved score-cache cleanup and eviction to reduce storage quota failures while preserving recent scores.

• Invisible characters that spam comments insert between letters no longer slip past comment keyword filtering, and are removed before a post is sent for scoring.

• Changing comment keywords, their score, or their opacity now takes effect on pages that are already open, without a reload.

Version 2.8.1

Chrome

• Fixed comment keyword filtering when a comment links to a quoted post or another thread: the comment's own link is now used, so the filter no longer matches the wrong post.

Version 2.8.0

Release Date: 2026-08-30

Safari and Chrome

• Added comment keyword filtering on X post detail pages. Keyword-matched comments can use a separate fixed score and opacity, while other comments continue to use normal model scoring.

• Added a settings popup dark mode that follows the system appearance.

• Added a button to restore the default comment keywords.

• Updated the extension version to 2.8.0.

Version 2.7.0

Release Date: 2026-08-14

Chrome

• Added permanent Pro purchases through Creem, with a license key delivered after checkout

• Added Pro license activation and browser deactivation, supporting up to two computers or browsers per license

• Added a full Pro trial for up to 7 days before purchase

Safari for macOS

• Added Mac App Store availability with a separate one-time Pro unlock and Restore Purchases support

Version 2.6.2

Release Date: 2026-08-11

Chrome

• Fixed the Chrome extension popup width so its contents are displayed correctly

Safari for macOS

• Improved Apple Translation source-language detection for Chinese, Japanese, and Korean text, so translation requests can use a more reliable source language

Version 2.6.1 (Safari and Chrome)

New Features

• Added Safari for macOS support for filtering, score actions, translations, and in-page side panel explanations on X and Weibo

• Added Apple Intelligence filtering scores on supported Macs

• Added Apple Translation with language-pack download support, falling back to the configured LLM when a language pair is unavailable

• Added Simplified Chinese localization for the Safari host app and extension

Improvements

• Chrome translation retries can switch between Chrome translation and a configured LLM without changing the default model

• Batch model setup now keeps successful additions when some model checks fail

Fixes

• Japanese-to-Chinese translations that return mostly untranslated Japanese are now detected as failures, so they can be retried instead of being shown as completed

Version 2.6.0

Release Date: 2026-07-15

New Features

• Added batch model setup: fetch the models available from a configured service and add multiple selections at once

• Added a cleanup action for removing model configurations that are no longer available from their service

Improvements

• Improved multi-model management with separate manual and batch-add flows, plus clearer highlighting for the default model

• When the same model name is available from multiple services, its source is now shown so you can choose the right model for translations and side panel explanations

• Settings now save automatically and take effect immediately, with no separate save action required

Fixes

• Improved compatibility after extension updates, reducing unnecessary error notices when an already-open page has an expired extension connection

Version 2.5.0

Release Date: 2026-07-01

New Features

• Added media-aware side panel explanations for both X and Weibo posts, including image and video-cover previews from main posts and quoted posts

• Added multimodal support for local model backends, including local OpenAI-compatible servers, LM Studio, and Ollama, so side panel explanations can include attached media

• Added temporary model switching for side panel reruns and translation retries, so one request can use a different configured model without changing the default API

Improvements

• Filtering now defaults to text-only scoring for a faster timeline experience, while media-aware scoring remains available as an opt-in setting

• Improved side panel tab isolation, loading states, and media preview behavior so explanations stay scoped to the current tab and current post

• Weibo media previews are now hydrated through the page context, improving preview reliability for protected image URLs

Fixes

• Fixed Weibo detail-page scoring after SPA navigation and improved score badge placement on Weibo detail pages

• Fixed translation placement for reposts and Weibo detail pages, and made empty or no-op translation responses less likely to be accepted as valid results

• Fixed whitelist handling so trusted tweets can apply the whitelist result immediately and stale whitelist-only cached scores no longer persist incorrectly

Version 2.4.0

Release Date: 2026-06-25

New Features

• Added Weibo support for filtering, score badges, translation actions, and side panel explanations

• Added platform-scoped whitelist entries: X uses handles like x/owen, while Weibo uses numeric IDs like weibo/6882232397

Improvements

• Extended post extraction, score actions, and side panel context so the same core workflow now works across both X and Weibo

Version 2.3.0

Release Date: 2026-06-11

New Features

• Added an extension side panel for explaining the current tweet text from the score menu

• Added follow-up chat in the side panel so you can keep asking about the same tweet

• Added model response streaming for side panel explanations and LLM translations

• Added side panel i18n text and Chrome side panel permission/configuration

Improvements

• Updated the extension display name, settings title, and footer branding to X Recommender Plus

• Persisted side panel state so the current tweet and explanation can be restored after reopening

Fixes

• Fixed side panel follow-up request handling so later questions keep the current tweet context

• Fixed stale side panel loading states by recovering old in-progress states after timeout

• Prevented older translation responses from overwriting newer translation requests

Version 2.2.0

Release Date: 2026-06-02

New Features

• Added reputation-based score badges that accumulate scoring history per account

• Added a reputation summary entry in the score menu so you can view scored count, average score, and current badge status for a user

• Added a quick profile shortcut from the score menu and reputation modal to open the user’s X profile

Improvements

• Badge colors now automatically follow a user’s accumulated average score after enough history is collected

• Whitelisted accounts now use a dedicated reputation state so the shield-style badge and menu messaging stay consistent

Fixes

• Fixed whitelist reputation handling so whitelisted accounts are excluded from reputation statistics and no longer show misleading reputation data

• Improved compatibility for old cached score data by rebuilding reputation summaries from stored detail records when needed

Version 2.1.0

Release Date: 2026-05-30

New Features

• Added Chrome built-in Gemini (Prompt API) support check in Filter settings

• Added a new toggle to prefer Chrome built-in Gemini for tweet filtering scores

Improvements

• Added automatic fallback to the configured external LLM when Chrome Gemini is unavailable or scoring fails

• Kept existing filter behavior unchanged when the Gemini toggle is off

• Added full i18n text coverage for the new Gemini filter settings and status labels

Version 2.0.0

Release Date: 2026-05-19

New Features

• Added a score-badge action menu: clicking the top-right score now opens a menu with quick translation targets (English and Simplified Chinese by default)

• Added tweet translation for both main tweet text and quoted tweet text, while preserving original content and rendering translation blocks below

• Added translation settings in popup: target languages are now multi-select and persisted

Improvements

• Added translation engine strategy options: Ask on first use, Force Chrome, or Force LLM

• Added Chrome Translator API detection and status display in settings, with engine options enabled/disabled by availability

• Changed single-click score behavior from direct toggle to menu entry, while keeping “Toggle Filter” and preserving double-click score details

Fixes

• Improved repeated translation behavior by reusing existing translation blocks for the same language, preventing duplicate stacking

• Added complete i18n keys for translation UI and status/error messaging in both languages

Version 1.7.0

Release Date: 2026-03-15

New Features

• Added “Clear Cache” button to manually clear all cached scores

Improvements

• Added localization support for the new cache clearing feature

Version 1.6.4

Release Date: 2026-03-15

Fixes

• Improved LM Studio compatibility for Qwen-style models by making the no-thinking fallback path more robust

• Prevented score parsing from accidentally reading reasoning step numbers as final scores

Improvements

• Added an LM Studio setup hint recommending non-thinking models first

• Added guidance for advanced users to disable thinking via LM Studio Prompt Template settings

Version 1.6.3

Release Date: 2026-03-13

Fix

• Fix issue where preset APIs like Ollama couldn’t be added after changing URL to LAN IP (preset values overriding user input)

Improvements

• Preset API name and URL now prioritize user input

Improvements

• Thread pass-through optimization: tweets in the same conversation now reuse the first scored result, avoiding repeated scoring for follow-up tweets

• Improved conversation detection by prioritizing conversation_id grouping (with safe fallback logic), covering mixed-author thread cases like repost + comment chains

• Reduced scroll flicker by disabling opacity transition on cached re-apply paths during timeline refresh/scroll

• Moved adaptive viewport timeout controls under hide mode only; these options are now shown only when filter mode is set to hide

Version 1.6.1

Release Date: 2026-03-04

Improvements

• Pre-hide unscored tweets: New tweets stay hidden until scored, then are shown or hidden by score (reduces timeline jumps)

• Changed batch size from 5 to 1 to lower timeline jump probability

• Changed temperature from 0.1 to 0 for more stable scoring

• Added cache check before scoring to avoid duplicate requests

• Added viewport detection to prevent large-scale node removal outside viewport causing scroll anchor jumps

• Optimized tweet ID extraction logic

Version 1.6.0

Release Date: 2026-03-03

New Features

• Added support for multiple models - you can now configure and switch between multiple LLM APIs

• Added thinking mode auto-disable for Ollama and OpenAI compatible APIs

Fixes

• Fixed issue where adding a second model would not display in the list (race condition and storage sync delay)

Version 1.5.1

Release Date: 2026-02-27

Fixes

• Fixed hide mode filtering to only use the hide threshold, preventing overlap with opacity behavior

• Improved tweet text fallback extraction (innerText || textContent) to reduce unstable hide/show flicker

• Updated extension version to 1.5.1

Version 1.5.0

Release Date: 2026-02-21

New Features

• ID Whitelist: Add trusted users to a whitelist - their tweets will not be filtered and display as ∞

• Filter Mode: Choose between opacity (fade) or hide completely

• No-Text Tweet Scoring: Option to score tweets with only images/videos

• Feedback Link: Added feedback and follow link in the footer

• Three-Tab Settings: Reorganized settings into API, Filter, and Whitelist tabs

Improvements

• Fixed whitelist matching to correctly extract username from author text

• Unified blue background for all scores (removed color variation by score)

• Adjusted retweet badge position

• Prevented duplicate API entries

• Removed API config from filter tab

1.3.0 (2026-02-18)

• Redesigned app icon with transparent background

• Added multi-language support for Chrome Web Store

• Improved transparency controls

1.2.0

• Added support for local LLM models (LM Studio, Ollama, llama.cpp)

• Introduced customizable scoring prompts

• Improved caching mechanism

1.1.0

• Added opacity controls for low-quality tweets

• Improved performance and stability

1.0.0

• Initial release

• Basic tweet scoring with OpenAI API support