MxChat – AI Chatbot & Content Generation for WordPress
Changelog
3.1.1 – March 4, 2026
New: Slack agents can now transfer users back to AI mode by typing !endchat in the channel
New: Agents can include a custom farewell message (e.g. !endchat Thanks, have a nice day!) — the message is delivered to the user before the handoff
New: SEO analysis panel with real-time scoring for posts and pages in the Content section
New: AI Auto-Optimize — one-click AI fixes for meta descriptions, SEO titles, and URL slugs with configurable check selection
New: Google Search Console integration (Pro) — per-page impressions, clicks, CTR, and top search queries directly in the Content editor
New: SEO optimize settings — choose which checks AI Optimize will run from Content > Settings
Fixed: Stale nonce causing “Invalid nonce” errors on sites with full-page caching (WP Rocket, LiteSpeed, W3 Total Cache) — nonce is now refreshed via AJAX on page load
Fixed: Security scanner false-positives flagging file_put_contents as malware — replaced with WP_Filesystem API for transcript and PDF temp files
Improved: PDF parser library now lazy-loaded on demand instead of on every page request
3.1.0 – March 1, 2026
Fixed: Bulk deleting selected knowledge base entries with chunked content causing network timeout error when using Pinecone
Fixed: Manually entered knowledge base content not being used for AI context despite having high similarity scores
Fixed: Chat input remaining blocked after live agent handoff (Slack/Telegram)
Fixed: Pinecone knowledge base scan returning “Not In Knowledge Base” when using text-embedding-3-large (TE3 Large) due to hardcoded 1536 dimension instead of 3072
Fixed: Shortcode stripping silently losing all content on pages with large or deeply nested shortcodes (e.g. WPBakery/Visual Composer) due to regex backtracking
New: Added mxchat_before_process_post filter hook to allow developers to modify post data before knowledge base processing
New: Added mxchat_system_instructions filter hook and shortcode support in system prompt for dynamic data injection
3.0.9 – February 24, 2026
New: AI Content Generator — generate full blog posts and landing pages from a single prompt with AI images, SEO metadata, real-time preview, inline AI editing, and content history
New: Advanced Content Editor premium add-on — smart internal linking, AI image management, and per-field AI meta generation
New: Dynamic post type filtering in knowledge database dropdown — automatically pulls in all registered post types
Improved: Compatibility with popular optimization and caching plugins
3.0.8 – February 20, 2026
New: Debug & optimization tools with log viewer, settings export, and reset options
New: Added Claude Sonnet 4.6 model
Improved: Performance optimizations and caching plugin compatibility
3.0.7 – February 15, 2026
New: Performance optimization
Fixed: GPT-5.1 Chat Latest model returning API error when web search was disabled
3.0.6 – February 11, 2026
New: RAG Sources Limit slider – control how many knowledge base sources (3-10) are included in AI responses
New: {visitor_name} placeholder support in Intro Message and AI Behavior settings for personalized greetings
New: Added Claude Opus 4.6 and Claude Opus 4.5 models
Fixed: Chat persistence OFF now correctly starts fresh AI context on page reload (previously AI retained full history)
Deprecated: Removed all GPT-4 series and GPT-3.5 Turbo from model selection (OpenAI deprecation)
Deprecated: Removed Claude 3.x series models (3.7 Sonnet, 3.5 Sonnet, 3 Opus, 3 Sonnet, 3 Haiku) per Anthropic deprecation
Updated: Users on deprecated OpenAI models auto-migrated to GPT-5.1 Chat Latest (or GPT-5 Mini for mini models)
Updated: Users on deprecated Claude models auto-migrated to Claude Opus 4.6 (or Claude Haiku 4.5 for Haiku users)
3.0.5 – January 28, 2026
Fixed: Updated Gemini embedding model from deprecated gemini-embedding-exp-03-07 to stable gemini-embedding-001
Fixed: Notification settings not saving on new installations
Fixed: Save indicators not visible on settings fields (API keys, Slack, Telegram, Loops, Brave Search)
Added: Warning notice for WordPress database users recommending Pinecone for large knowledge bases
Improved: Minor admin UI updates for better user experience
3.0.4 – January 24, 2026
New: Added latest Google Gemini models (3 Pro Preview, 3 Flash Preview, 2.5 Pro, 2.5 Flash, 2.5 Flash-Lite)
New: Transcript translation feature – auto-translate chat transcripts to any language
New: Action scores visible in transcript sources modal – see document rankings and triggered actions
Fixed: Lead capture forms not working due to multi-bot class ID changes
3.0.3 – January 21, 2026
Fixed: Bug when web search was enabled the chat input was not enabled again.
3.0.2 – January 21, 2026
New: Telegram Live Agent integration for live chat handoff via Telegram forum topics
New: Telegram action type in Actions page for intent-based handoff
New: Citation Links toggle to enable/disable source URLs in AI responses (Chatbot > Behavior)
Changed: Renamed “Live Agent” settings tab to “Slack”
3.0.1 – January 18, 2026
New: Multi-select entries with bulk “Delete Selected” in knowledge base
New: OpenAI Vector Store integration for knowledge retrieval
New: Custom Post Meta whitelist for including non-ACF meta fields in embeddings
Improved: WordPress database search now filters to matching records only
Improved: WordPress import shows 100 items by default with cross-page selection
Fixed: ACF Field Settings now displays correctly in Knowledge Base sidebar
Changed: Chatbot CSS selectors migrated from IDs to classes for multi-bot support
Note: AI Theme Customizer users must update add-on and click “Migrate” on their theme
3.0.0 – January 14, 2026
New: Complete admin UI overhaul with modern sidebar navigation across all pages
New: Clean, professional design with consistent styling throughout the plugin
New: Automatic sitemap detection with one-click “Process Sitemap” button
New: Real-time knowledge base updates – new entries appear instantly without page refresh
New: Consolidated Pro Upgrade and Add-ons pages into a unified interface
New: Improved mobile responsiveness with collapsible menus and slide-up detail panels
2.6.4 – January 6, 2026
New: ACF Field Control for Knowledge Base imports. Users with Advanced Custom Fields can now control which ACF fields are included when importing content to the knowledge base. A new “ACF Field Settings” section appears in the Knowledge Database Settings tab, displaying all registered ACF field groups and their fields with toggle switches. This allows you to exclude sensitive fields like private notes or internal data from being embedded in the chatbot’s knowledge base.
Fixed: Knowledge Database entries now display in correct newest-to-oldest order. Previously, entries appeared in seemingly random order because the sorting was based on source URL rather than timestamp. New submissions now correctly appear at the top of the list.
Fixed: Knowledge Database pagination now works correctly when searching. Previously, clicking to page 2 or beyond while viewing search results would show an empty table because the search parameters were lost during pagination. The search query and security nonce are now properly preserved across all paginated pages.
Fixed: Manual content submissions no longer display a broken “View Source” link. When submitting direct content without a source URL, the Knowledge Database now correctly shows “Manual Content” instead of an empty or invalid link. This applies to both the main table view and individual entry displays.
Fixed: Editing knowledge entries with manual content no longer shows internal mxchat:// URLs in the source field. The URL field now correctly appears empty for manual content entries, allowing users to optionally add a real source URL if desired.
Fixed: Knowledge entries with short content can now be edited properly. Previously, if the content was too short to trigger the expand/collapse accordion, the edit textarea was hidden and inaccessible. The edit button now automatically expands the content area regardless of content length.
2.6.3 – December 31, 2025
New: Text chunking for RAG – large content is automatically split into semantic chunks for improved retrieval accuracy
New: Chunk count display in WordPress Import modal – shows “(X chunks)” badge for multi-chunk content
New: Collapsible chunk groups in Knowledge Base table – entries with multiple chunks are grouped under a single expandable row
New: Chunk labels show “Chunk 1 of 5”, “Chunk 2 of 5” etc. when chunks are expanded
New: Option to show/hide frontend debug panel in Chatbot Settings
Enhancement: Improved retrieval – finds best matching chunks, then fetches all chunks for top URLs and reassembles
Enhancement: Chat input is now disabled while waiting for bot response, preventing duplicate message submissions
Enhancement: When streaming is turned on it automatically checks if compatible and disables if not.
Fixed: Markdown formatting now preserved correctly when streaming is disabled (newlines were being stripped)
2.6.2 – December 22, 2025
Fixed: Critical error when viewing Knowledge Database with large Pinecone datasets (10K+ products)
Fixed: Optimized Pinecone API queries to prevent memory exhaustion and PHP timeouts
Fixed: Chatbot no longer gets cut off when browser has bookmarks bar or is zoomed above 100%
New: Post type visibility control – include or exclude specific post types from auto-display chatbot
New: Semantic search in admin now searches ALL Pinecone records using embedded query vectors
2.6.1 – December 17, 2025
Fixed: Send button now includes aria-label for screen reader accessibility
Fixed: Translations now load from /wp-content/languages/plugins/ first, preserving custom translations during updates
2.6.0 – December 12, 2025
New: OpenAI GPT-5.2 model support – best general-purpose and agentic model with fast responses
New: Markdown rendering in transcripts – bot responses display formatted text with clickable links, bold, italic, code blocks, and headers
New: Retrieved documents viewer in transcripts – click “Sources →” link on any bot response to see knowledge base documents used, similarity scores, and citation URLs
Improved: Session security now auto-recovers when user IP changes instead of showing “Unauthorized access” error
Improved: Seamless experience for mobile users switching between WiFi and cellular networks
2.5.9 – December 6, 2025
Fix: Shortcode stripping now preserves content inside shortcodes instead of removing it entirely
2.5.8 – December 5, 2025
New: Auto-email full transcript feature – sends transcript as .txt file attachment after 15, 30, or 60 minutes of user inactivity
New: Conditional transcript emails – option to only send transcripts when visitors provide contact info (email or phone/WhatsApp) in chat
New: Smart contact detection – automatically detects email addresses and phone numbers (including international WhatsApp formats) in chat messages
Compatibility: Tested and compatible with WordPress 6.9
2.5.7 – December 2, 2025
Fix: Streaming fallback bug – bot responses now properly saved to chat transcripts when streaming fails and falls back to regular response mode
Enhancement: Added comprehensive metrics dashboard to Transcripts page with 3 tabs (Overview, Activity, Insights)
Enhancement: Added 7-day activity trend chart with custom visualization
Enhancement: Added new metrics including daily/weekly/monthly chat counts, peak activity hours, and engagement rates
Enhancement: Added auto-delete transcripts feature with configurable intervals (1 week, 2 weeks, 1 month) for better database management and privacy
Enhancement: WooCommerce product imports now include complete pricing metadata (regular price, sale price, price ranges for variable products, SKU, categories)
Improvement: Updated transcript settings modal for better usability on desktop and mobile
Improvement: Various CSS fixes for metrics dashboard display
2.5.6 – November 30, 2025
Security: Improved session ID validation with server-side checks
Security: Added session ownership verification to prevent unauthorized access to chat sessions
Fixed: Database error “Unknown column ‘bot_id’” for multi-bot configurations with automatic migration
Improvement: Enhanced session security with consistent ownership verification
Improvement: Added automatic database schema migration system
Improvement: WooCommerce import improvements to support Custom Tabs information
Improvement: Database management with a new filtering option. Filter by posts, pages, products, PDF
2.5.5 – November 21, 2025
Fixed: Issue with non-streaming mode failing to format URLs and paragraphs correctly
Fixed: Bug with shortcodes still appearing in the knowledge database
Enhancement: Minor adjustments to improve compatibility with multi-bot setups requiring email-to-chat forms
New: Added Grok 4.1 Fast (Reasoning) model — 2M context, reasoning
New: Added Grok 4.1 Fast (Non-Reasoning) model — 2M context, faster responses
New: Added OpenAI GPT-5.1 model — flagship for coding & agentic tasks with low reasoning and 400K context
2.5.4 – November 12, 2025
New: Accordion-Style Knowledge Base Viewer for cleaner, expandable database entry previews
New: Smart Shortcode Stripping for WPBakery and Elementor during content submission to improve vectorization accuracy
New: Unique Citation URLs when submitting direct content, allowing multiple linked submissions without overwriting
Improvement: WooCommerce products now include both short and full descriptions during data processing
2.5.3 – November 9, 2025
New: Dedicated API Key Management Tab – All API keys organized in one central location for easier management
Improvement: GPT-5 performance optimization with minimal reasoning effort mode for significantly faster response times
Fix: Resolved URL and PDF link encoding issues causing broken or unclickable links in responses
Improvement: Various performance enhancements for improved stability and faster processing
2.5.2 – November 3, 2025
New: URL Hallucination Prevention System – AI only cites URLs from knowledge base or system instructions, with automatic removal of invalid links
Improvement: Brand new robust queue-based processing system for sitemap and PDF imports with real-time progress tracking
Improvement: Optimized knowledge retrieval from 5 to 3 documents for faster response times and improved accuracy
Improvement: Increased URL column size to TEXT type for support of long URLs and special characters (Hebrew, Arabic, etc.)
Fix: Resolved URL double-encoding issue causing malformed PDF and document links
Fix: Corrected citation-style bracket handling for AI responses containing [URL] format
Fix: Fixed empty markdown link processing to prevent broken link generation
2.5.1 – October 30, 2025
New: Tag-based role restrictions for chatbot knowledge base – automatically control what content the chatbot can access based on WordPress tags and user roles
Update: Migrated users from deprecated Claude 3.5 Sonnet to Claude 3.7 Sonnet with improved performance
Fix: Removed deprecated Claude model from selection options
2.5.0 – October 25, 2025
Fix: Resolved PDF URL encoding issue that caused broken links to PDF documents
Fix: Improved UI feedback when selecting chat models
Fix: Enhanced OpenRouter flow selection interface
2.4.8 – October 16, 2025
New: OpenRouter integration – access 100+ AI models with a single API key
New: Added Claude Sonnet 4.5, Claude Opus 4.1, and Claude Haiku 4.5 support
2.4.7 – October 13, 2025
Security: Fixed Server-Side Request Forgery (SSRF) vulnerability in PDF processing (CVE-2025-10705)
2.4.5 – September 30, 2025
Bug Fix: Restored missing CSS properties for popular questions collapse/toggle buttons that were accidentally removed during code cleanup.
Bug Fix: Fixed button hover, focus, and active states for question navigation controls.
Bug Fix: Restored proper SVG styling and display logic for collapsible question buttons.
2.4.4 – September 24, 2025
Bug Fix: Default similarity is now accurate across all settings.
Bug Fix: Improved streaming responses to prevent dropped characters or words.
Enhanced: Removed unnecessary Pinecone caching in the knowledge database for more accurate results.
2.4.3 – September 23, 2025
Added: Support for upcoming multi-bot update that allows for more customized settings such as individual chat models.
Improved: CSS for chatbot UI & more robust markdown support.
2.4.2 – September 18, 2025
Added: Multi-bot support via the new Multi-Bot Manager premium add-on.
Improved: Minor CSS adjustments for better compatibility.
Updated: Add-on links and references throughout the plugin.
2.4.1 – September 4, 2025
Fixed: Email collection form not submitting properly when “Require email to chat” is enabled.
Improved: PDF processing now provides clearer error messages with repair suggestions when corrupted files are detected.
2.4.0 – September 3, 2025
Added new MxChat Video Generation add-on with support for Google Veo 2 and Veo 3 models, featuring audio generation and multiple aspect ratios.
Fixed console error when “Require email to chat” option is disabled by adding proper validation check.
Resolved “error chat history not found” message when chat persistence is enabled but user has no existing chat history.
Fixed agent indicator not updating properly when switching between live agent and chatbot modes without page refresh.
2.3.9 – August 17, 2025
Updated Slack channel naming logic to prioritize client’s name, falling back to email, then chat ID.
Added streaming response support for DeepSeek models.
Enabled multiple direct content entries without requiring a source URL.
Fixed auto sync drafts so posts moved from posted to draft are removed from the knowledge database.
Implemented role-based chatbot information access restrictions for enhanced security and relevance.
Added option in the admin panel’s post edit page to hide the floating chatbot on specific pages.
2.3.8 – August 12, 2025
Fixed extra backslashes appearing in knowledgebase content during editing.
Added optional name field to Require Email to Chat form; transcripts now display email and name if enabled.
Updated Slack channel naming for live agent notifications: uses user’s email if logged in, email if Require Email to Chat is enabled, or chat ID otherwise.
2.3.7 – August 8, 2025
New Models: Added GPT-5 family (GPT-5, GPT-5 Mini, GPT-5 Nano) to expand capabilities with faster, smarter, and more cost-efficient options.
2.3.6 – August 6, 2025
Bug Fix: Fixed streaming fallback to properly display responses when streaming fails, preventing blank chat bubbles.
New Feature: Added streaming test button to help users verify if streaming is compatible with their setup.
2.3.5 – August 6, 2025
Redesigned chat transcript UI for a cleaner, more professional experience.
Transcripts now show the page where the chat started and any links clicked.
Added ability to select and delete transcripts directly from the header.
2.3.4 – July 30, 2025
Fixed streaming compatibility issues with Cloudflare and WP Engine by implementing automatic fallback to regular chat when streaming is buffered.
Enhanced email capture intents to use AI-generated conversational responses instead of hard-coded messages, allowing for more natural user interactions while maintaining the same functionality.
2.3.3 – July 29, 2025
Improved streaming performance by fixing output buffering issues using enhanced flush logic.
Added contextual awareness support via the new data-mxchat-context HTML attribute.
Revamped license key management system with domain linking, deactivation, and real-time usage dashboard.
Fixed transcript timestamp display to use WordPress site’s local timezone correctly.
2.3.2 – July 24, 2025
Added full support for OpenAI Assistants API via the new Assistant add-on.
Improved email collection form performance and reliability with better loading states and timeout handling.
Enhanced WooCommerce product labeling accuracy in WordPress import with improved URL matching.
Fixed ACF field processing errors when handling WP_Post objects and relationship fields.
2.3.1 – July 20, 2025
Enhanced hyperlink functionality to include mailto links, enabling email addresses in bot responses to be clickable.
Added full support for the new MxChat Image Analysis add-on, allowing users to upload and analyze images directly in chat using OpenAI Vision and Grok APIs.
Added message filtering hooks system for developers to customize prompts and responses without modifying core plugin files.
2.3.0 – July 13, 2025
Added Grok-4 model support, the world’s smartest AI model available.
Added streaming response support for all Grok models (Grok-4, Grok-3, etc.), delivering real-time response generation for faster and smoother chat experiences.
2.2.9 – July 6, 2025
Improved quick question UI: suggestions now collapse after user input and can be toggled with up/down icons
Increased sitemap batch processing limit from 5 to 50 for faster indexing
Expanded action similarity threshold range to support values from 10 to 95
2.2.8 – June 27, 2025
Added brand new contextual awareness option that automatically provides chatbot access to current page content and URL for contextually relevant responses
Enhanced WordPress knowledge base import to include Advanced Custom Fields (ACF) data for more comprehensive content training
Major README structure update with improved formatting and visual presentation
2.2.7
Fixed a bug that occured when deleting all pinecone records & added support for markdown hyperlinking in rate limit messages.
2.2.6
Brand New Admin Debug Panel – Added a comprehensive frontend debug panel for administrators! You can now see retrieved documents, triggered actions, and other debug and setting information in real-time while testing your chatbot, making it easier than ever to fine-tune your bot’s performance.
Fixed Pinecone Single Entry Deletion – Resolved a bug that prevented individual entries from being properly deleted from Pinecone vector storage.
Improved Pinecone UI Records Retrieval – Enhanced the Pinecone database panel with better record loading and display functionality for smoother management of your vector database.
Fixed WordPress KB Entry Editing – Resolved an issue where editing knowledge base entries in the WordPress database wasn’t working properly, ensuring seamless content management.
2.2.5
Streaming Response Support – You can now enable streaming responses for OpenAI and Claude models. This delivers a faster, smoother chat experience for users by displaying replies in real-time as they’re generated.
Slack Live Agent Fix – Resolved a minor bug that occasionally caused duplicate messages in Slack during live agent conversations.
Pinecone UI Update – Fixed a UI display issue in the Pinecone database panel when using the TE3 model.
2.2.4
Critical update to error when working with large databases in Pinecone.
2.2.3
Various critical bug fixes that occured from the codebase refactoring.
2.2.2
Enhanced Slack integration: live agent handoff now creates new Slack channels per conversation; agents can reply directly in channel to chat with website users.
Major codebase refactoring for improved organization and optimization.
Improved sitemap and PDF processing: added retry mechanism, display of failed pages/URLs, and manual batch processing button.
Fixed Pinecone setting not toggling on for users who previously did not have the add-on.
2.2.1
Added Claude Sonnet 4 and Claude Opus 4 chat models.
Integrated Google Gemini embedding model (gemini-embedding-001).
Built Pinecone vector database support directly into core plugin.
Removed dependency on separate Pinecone add-on.
2.2.0
Added WordPress Content Importer for posts and pages.
Implemented tabbed interface for knowledge base management.
Added content filtering by type and knowledge base status.
Added bulk import with real-time progress tracking.
2.1.9
Added email notification feature for new chat sessions.
Implemented pagination on transcripts page (50 per page) to improve performance.
Fixed bug with Brave image search not returning images correctly from the API.
Enhanced performance by changing chat transcripts to disable autoload.
2.1.7
Fixed Pro activation issues when the plugin has been translated.
Improved tab behavior to always default to the first tab.
Major rework to rate limits: added custom rate limit timeframes and messages for each individual role.
Fixed bug with Loops where manual list selection from dropdown was required for functionality.
2.1.6
Added new AI models: GPT-4.1 and the complete suite of Grok 3 models.
Updated AI service providers to use their official SVG logos for better visual representation.
Fixed an issue where API key fields would try to autosave when no data was entered.
Various other minor bug fixes for improved stability and performance.
2.1.5
Added RTL Language support, allowing languages that align right to automatically do so in both chat input and AI responses.
Improved error messaging for API calls in the frontend of the chatbot, and enhanced error messages when submitting sitemaps, URLs, and PDFs.
Fixed an auto save issue that caused an error if no changes were made.
Various other minor bug fixes for improved stability and performance.
2.1.4
Added the ability to easily customize the “AI Agent” text displayed in the top bar for greater personalization.
Fixed a bug where data scraping failed to retrieve all content from certain websites.
Added HTML support in the intro message for richer customization.
Resolved an issue where API input fields triggered browser autofill, improving user input accuracy.
2.1.3
Added support for Google Gemini models: Gemini 2.0 Flash, Gemini 2.0 Flash-Lite, Gemini 1.5 Pro, and Gemini 1.5 Flash.
Improved chat model selection UI for a more intuitive user experience.
Redesigned embedding model selection UI for better clarity and usability.
Enhanced error handling for sitemap submissions with more helpful user feedback.
Fixed an issue in the knowledge database where editing entries erased or prevented changes to citation URLs.
2.1.2
Rebranded intents page to “Actions” with a revamped UI, displaying pro/add-on requirements and brief descriptions.
Added ability to toggle actions on/off without deleting; moved image generation action from pro to free tier.
Introduced advanced knowledge base sync feature to pull in custom post data.
2.1.1
Made Claude and X.AI API models available to all users.
Improved API key management UI – only showing relevant API key fields based on selected models.
Enhanced knowledge import interface with clear credit requirement warnings.
Fixed embedding error notifications for better clarity.
2.1.0
Fixed a bug impacting the header color in the output.
Updated embedding error notification when submitting sitemaps or PDFs.
Improved context extraction parser.
2.0.9
Revamped UI on the main settings page to match the rest of the plugin.
Added real-time updates for sitemap and PDF processing.
Renamed “MxChat Intent Tester” add-on to “MxChat Similarity Tester”.
Various minor bug fixes and improvements.
2.0.8
Minor bug fix impacting similarity adjustment.
2.0.7
Perplexity Integration Add-On – Added Perplexity web search, integrated into intent management with a toolbar toggle.
Sonnet 3.7 Support – Introduced Anthropic’s Claude Sonnet 3.7, the latest high-intelligence model.
Bug Fixes & Improvements – Fixed title tag formatting in responses and tightened knowledge database similarity range to 20.
2.0.5
Auto-Expanding AI Instructions – AI instructions text field now auto-expands to fit content.
Quick Questions Rebrand – Renamed “Popular Questions” to “Quick Questions” with updated copy.
Security Enhancement – Improved security to better prevent XSS attacks.
Intent Testing Add-On – Integrated new Intent Tester add-on for enhanced chatbot performance.
2.0.4
Markdown Response Fix – Resolved markdown formatting issues in the chatbot UI.
Agent Mode Customization – Improved indicator text theme and background styling.
WooCommerce Core Extraction – Moved WooCommerce features to the dedicated MxChat WooCommerce add-on.
2.0.3
Bug Fix: Resolved issues preventing DeepSeek and Claude models from working correctly.
New: Added integration for the MxChat Form Collection add-on (Pro only).
New: Forms now display dynamically within the chat interface in real-time.
New: Automatic intent handling for seamless form triggering.
Update: Improved submission management with CSV export functionality.
2.0.2
Bug Fix: Auto-sync now properly deletes posts/pages when enabled.
Update: Theme customization moved to an add-on with live preview support.
New: Added MxChat Moderation plugin to ban users by email or IP.
2.0.1
Bug Fix: Fixed a DivisionByZeroError in sitemap processing that occurred when submitting an empty or malformed sitemap.
Bug Fix: Resolved a similar DivisionByZeroError in PDF processing to prevent crashes when handling PDFs with 0 pages.
2.0.0
New UI & Branding: Redesigned the entire plugin interface to align with the new MXChat brand for a modern and seamless experience.
Add-Ons System Introduced: Added a dedicated Add-Ons page, allowing users to extend the plugin with optional features. Add-ons are completely optional and do not impact core functionality.
First Add-On Released – Pinecone DB Manager: Now available for free! This add-on provides an intuitive interface for managing your Pinecone vector database directly within MXChat.
1.6.5
Optimized knowledge database retrieval to prevent memory issues with large product databases (2000+ products)
Fixed bug with tab switching control in chat interface
1.6.4
Added chat notifications for improved user experience when chat persistence is enabled.
Made the entire plugin fully translatable, allowing compatibility with translation services like Loco Translate.
Improved Slack integration: When a user requests a live agent, the last five messages from the conversation are now sent to Slack for better context.
1.6.4
Added chat notifications for improved user experience when chat persistence is enabled.
Made the entire plugin fully translatable, allowing compatibility with translation services like Loco Translate.
Improved Slack integration: When a user requests a live agent, the last five messages from the conversation are now sent to Slack for better context.
1.6.3
Added the new “Rate Limit by User Role” feature, replacing the previous rate limit for logged-in users.
Introduced DeepSeek as a new AI service provider, with full support for their models.
Integrated DeepSeek V3, enhancing chatbot natural language understanding and performance.
