| @@ -1,20 +1,20 @@ | ||
| 1 | 1 | === MxChat - AI Chatbot & Content Generation for WordPress === |
| 2 | 2 | Contributors: mxchat |
| 3 | 3 | Author: [MxChat](https://mxchat.ai) |
| 4 | 4 | Tags: ai chatbot, chatgpt, woocommerce, customer support, content generation |
| 5 | -Requires at least: 5.0 | |
| 6 | -Tested up to: 6.9 | |
| 7 | -Requires PHP: 7.2 | |
| 8 | -Stable tag: 3.2.1 | |
| 5 | +Requires at least: 5.3 | |
| 6 | +Tested up to: 7.1 | |
| 7 | +Requires PHP: 7.4 | |
| 8 | +Stable tag: 3.2.24 | |
| 9 | 9 | License: GPLv2 or later |
| 10 | 10 | License URI: https://www.gnu.org/licenses/gpl-2.0.html |
| 11 | 11 | |
| 12 | -The best free AI chatbot and content generation plugin for WordPress. Train ChatGPT, Claude, Gemini, or Grok on your website content. Generate full blog posts and landing pages with AI. WooCommerce ready with RAG knowledge base, live chat handoff, and 100+ AI models. | |
| 12 | +Free AI chatbot and content generation for WordPress. Train ChatGPT, Claude, Gemini or Grok on your content. WooCommerce ready with RAG. | |
| 13 | 13 | |
| 14 | 14 | == Description == |
| 15 | 15 | |
| 16 | -**MxChat is the most powerful free AI chatbot and content generation plugin for WordPress** — connecting your website to ChatGPT, Claude, Gemini, Grok, DeepSeek, and 100+ AI models through a single, easy-to-use interface. Train your AI chatbot on your website content, WooCommerce products, PDFs, and more using advanced RAG (Retrieval-Augmented Generation) technology. Now with a built-in AI Content Generator to create full blog posts and landing pages complete with images, SEO metadata, and inline AI editing. | |
| 16 | +**MxChat is the most powerful free AI chatbot and content generation plugin for WordPress** — connecting your website to ChatGPT, Claude, Gemini, Grok, DeepSeek, and 100+ AI models through a single, easy-to-use interface. Train your AI chatbot on your website content, WooCommerce products, PDFs, YouTube videos, and more using advanced RAG (Retrieval-Augmented Generation) technology. Now with a built-in AI Content Generator to create full blog posts and landing pages complete with images, SEO metadata, and inline AI editing. | |
| 17 | 17 | |
| 18 | 18 | [Documentation](https://mxchat.ai/documentation/) | [Demo Videos](https://www.youtube.com/@MxChat/videos) |
| 19 | 19 | |
| 20 | 20 | ## Why Choose MxChat as Your WordPress AI Chatbot? |
| @@ -19,9 +19,9 @@ | ||
| 19 | 19 | |
| 20 | 20 | ## Why Choose MxChat as Your WordPress AI Chatbot? |
| 21 | 21 | |
| 22 | 22 | ✅ **6 Major AI Providers in One Plugin**: OpenRouter, OpenAI GPT, Claude, Gemini, xAI Grok, and DeepSeek - switch between 100+ models instantly |
| 23 | -✅ **Train on Your Website Data**: Advanced RAG technology learns from sitemaps, PDFs, URLs, or manual input for ultra-relevant responses | |
| 23 | +✅ **Train on Your Website Data**: Advanced RAG technology learns from sitemaps, PDFs, URLs, YouTube videos, or manual input for ultra-relevant responses | |
| 24 | 24 | ✅ **Live Agent Handoff via Slack**: Seamlessly escalate from AI to human support when customers need personal assistance |
| 25 | 25 | ✅ **Real-Time Debug Panel**: See exactly what your chatbot retrieves and triggers with our admin testing interface |
| 26 | 26 | ✅ **Boost Sales with WooCommerce**: Product cards, cart management, and AI-powered shopping assistance |
| 27 | 27 | ✅ **AI Content Generator**: Create full blog posts and landing pages with AI-generated images, SEO metadata, and real-time preview editing |
| @@ -28,40 +28,39 @@ | ||
| 28 | 28 | ✅ **Extensive Add-On Ecosystem**: Forms, moderation, recommendations, theme customization, and more |
| 29 | 29 | |
| 30 | 30 | 🎬 [Quick Setup with MxChat](https://www.youtube.com/watch?v=3BqoiyWaQiM) – Learn how to quickly setup and understand how your chatbot works |
| 31 | 31 | |
| 32 | -### 📦 Optional Premium Add-Ons | |
| 33 | -Extend the free plugin with these optional premium features: | |
| 32 | +### 📦 Optional Premium Add-Ons | |
| 33 | +Extend the free plugin with these optional premium features: | |
| 34 | 34 | |
| 35 | -- [Advanced Content Editor Add-On](https://mxchat.ai/advanced-content-editor/) – Smart internal linking, AI image management, readability analysis, Google Search Console integration, advanced SEO optimization, and 30-day AI Content Calendar for automated blog scheduling | |
| 36 | -- [WooCommerce Add-On](https://mxchat.ai/woocommerce/) – AI-powered shopping assistance with product-aware conversations, native product cards with images and pricing, upselling and recommendations, order inquiry handling, cart management, and real-time inventory awareness | |
| 37 | -- [Forms Action Add-On](https://mxchat.ai/forms-action/) – Capture leads and data with custom in-chat forms | |
| 38 | -- [MxChat Anywhere Add-On](https://mxchat.ai/mxchat-anywhere-deploy-your-ai-chatbot-on-any-website-with-one-script-tag/) – Deploy your chatbot on any website with one script tag — Shopify, Squarespace, Wix, static HTML, and more | |
| 39 | -- [AI Chatbot Theme Customizer Add-On](https://mxchat.ai/ai-theme-customizer/) – Instantly design chatbot themes with natural language using AI | |
| 40 | -- [Multi-Bot Add-On](https://mxchat.ai/multi-bot/) – Run unlimited AI chatbots with custom knowledge and personalities | |
| 41 | -- [Image Analysis Add-On](https://mxchat.ai/image-analysis/) – Enable AI-powered image analysis and OCR inside chats | |
| 35 | +- [MCP Server Add-On](https://mxchat.ai/add-ons/mxchat-mcp/) – Turn your MxChat install into a Model Context Protocol server so Claude, ChatGPT, and Claude Code list transcripts, push knowledge, and inspect bots natively — JSON-RPC 2.0 + OAuth + bearer auth, no per-message fees | |
| 36 | +- [Advanced Content Editor Add-On](https://mxchat.ai/add-ons/mxchat-advanced-content/) – Smart internal linking, AI image management, readability analysis, Google Search Console integration, advanced SEO optimization, and 30-day AI Content Calendar for automated blog scheduling | |
| 37 | +- [WooCommerce Add-On](https://mxchat.ai/add-ons/mxchat-woo/) – AI-powered shopping assistance with product-aware conversations, native product cards with images and pricing, upselling and recommendations, order inquiry handling, cart management, and real-time inventory awareness | |
| 38 | +- [Forms Add-On](https://mxchat.ai/add-ons/mxchat-forms/) – Capture leads and data with custom in-chat forms | |
| 39 | +- [MxChat Anywhere Add-On](https://mxchat.ai/add-ons/mxchat-embed/) – Deploy your chatbot on any website with one script tag — Shopify, Squarespace, Wix, static HTML, and more | |
| 40 | +- [AI Chatbot Theme Customizer Add-On](https://mxchat.ai/add-ons/mxchat-theme/) – Instantly design chatbot themes with natural language using AI | |
| 41 | +- [Multi-Bot Add-On](https://mxchat.ai/add-ons/mxchat-multi-bot/) – Run unlimited AI chatbots with custom knowledge and personalities | |
| 42 | +- [Image Analysis Add-On](https://mxchat.ai/add-ons/mxchat-vision/) – Enable AI-powered image analysis and OCR inside chats | |
| 42 | 43 | |
| 43 | 44 | 👉 [Visit our website to view all add-ons](https://mxchat.ai) |
| 44 | 45 | |
| 45 | -## 🔥 What's New in Version 3.2.1 | |
| 46 | - | |
| 47 | -- **Admin Testing Tab Fixes** — Resolved issues preventing the debug panel from displaying similarity scores, action matches, and source data — including when web search and streaming are both enabled. | |
| 48 | -- **Web Search Transcript Sources** — Chat transcripts now correctly show the "sources" link for responses generated with OpenAI web search enabled in both streaming and non-streaming modes. | |
| 49 | - | |
| 50 | 46 | ## Core Features That Set MxChat Apart |
| 51 | 47 | |
| 52 | 48 | 🟢 **100+ AI Models** – Access ChatGPT, Claude, Gemini, Grok, DeepSeek, and 100+ models from OpenRouter with a single plugin |
| 49 | +🟢 **Lead Management Dashboard** – Dedicated Leads tab inside Transcripts shows every captured email and name deduplicated by lead, with filters, bulk delete, CSV export, and one-click jump to each lead's latest conversation | |
| 53 | 50 | 🟢 **Chat Transcripts Dashboard** – Review all conversations, analyze chat history, track user engagement, and see exactly which knowledge sources the AI used for each response |
| 54 | 51 | 🟢 **WooCommerce Product Training** – Train your AI chatbot on your entire product catalog including descriptions, pricing, SKUs, and categories for intelligent shopping assistance |
| 55 | 52 | 🟢 **Live Agent Handoff** – Seamlessly escalate conversations from AI to human support via Slack when customers need personal assistance |
| 56 | 53 | 🟢 **ACF Field Control** – Choose exactly which Advanced Custom Fields are included in your knowledge base—perfect for excluding private notes or internal data |
| 57 | -🟢 **Advanced Action Recognition** – Smart vector embedding system understands user intent and triggers lead capture, appointments, redirects, and custom actions automatically | |
| 54 | +🟢 **Advanced Action Recognition** – Trigger Phrases use a smart vector embedding system to understand user intent and fire lead capture, appointments, redirects, and custom actions automatically — precise, deterministic control over when each action runs | |
| 55 | +🟢 **AI Tools (Function Calling)** – Let the chatbot decide on its own when to run an enabled action straight from natural language, with no phrases to set up. Use Trigger Phrases, AI Tools, or both together (function calling needs a tool-capable AI model) | |
| 58 | 56 | 🟢 **Document Processing** – Let visitors upload and chat with PDFs and Word documents directly on your frontend |
| 59 | 57 | 🟢 **Pinecone Vector Storage** – Optional lightning-fast knowledge retrieval for large datasets and enterprise-scale deployments |
| 60 | 58 | 🟢 **Web Search Integration** – Brave search provides real-time information beyond your knowledge base |
| 61 | 59 | 🟢 **AI Content Generator** – Create full blog posts and landing pages from a prompt with AI images, SEO metadata, real-time preview, and inline AI editing via chat |
| 62 | 60 | 🟢 **Image Generation** – OpenAI GPT Image and Google Imagen for visual content creation within chat conversations |
| 63 | -🟢 **Streaming Responses** – Real-time response streaming for OpenAI, Claude, and Grok models for the fastest possible chat experience | |
| 61 | +🟢 **Streaming Responses** – Real-time response streaming for OpenAI, Claude, Grok, and DeepSeek models for the fastest possible chat experience | |
| 62 | +🟢 **REST API** – Bearer-token endpoints to read transcripts, push knowledge, and bulk-delete sessions — wire MxChat into n8n, Zapier, analytics dashboards, GDPR workflows, or your own agents | |
| 64 | 63 | |
| 65 | 64 | ## Choose from 100+ Premium AI Models |
| 66 | 65 | Access the world's most advanced AI models based on your specific needs: |
| 67 | 66 | |
| @@ -66,18 +65,35 @@ | ||
| 66 | 65 | Access the world's most advanced AI models based on your specific needs: |
| 67 | 66 | |
| 68 | 67 | **OpenRouter**: 100+ models from multiple providers with a single API key – including OpenAI, Anthropic, Google, Meta, Mistral, and more! |
| 69 | 68 | **OpenAI**: |
| 70 | -GPT-5.2, GPT-5.1 Chat Latest, GPT-5.1, GPT-5, GPT-5-mini, GPT-5-nano | |
| 69 | +GPT-5.5, GPT-5.4, GPT-5.4 Mini, GPT-5.4 Nano, GPT-5.3 Chat, GPT-5.2, GPT-5.1 Chat Latest, GPT-5.1, GPT-5, GPT-5 Mini, GPT-5 Nano | |
| 71 | 70 | **Anthropic Claude**: |
| 72 | -Claude Opus 4.6, Claude Sonnet 4.6, Claude Opus 4.5, Claude Sonnet 4.5, Claude Opus 4.1, Claude Haiku 4.5, Claude 4 Sonnet, Claude 4 Opus | |
| 71 | +Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, Claude Opus 4.5, Claude Sonnet 4.5, Claude Opus 4.1, Claude Haiku 4.5, Claude 4 Opus, Claude 4 Sonnet | |
| 73 | 72 | **X.AI**: |
| 74 | -Grok-4, Grok-3, Grok-3 Fast, Grok-3 Mini, Grok-3 Mini Fast, Grok-2, **Grok 4.1 Fast (Reasoning)**, **Grok 4.1 Fast (Non-Reasoning)** | |
| 73 | +**Grok 4.1 Fast (Reasoning)**, **Grok 4.1 Fast (Non-Reasoning)**, Grok 4, Grok-3, Grok-3 Fast, Grok-3 Mini, Grok-3 Mini Fast | |
| 75 | 74 | **Google Gemini**: |
| 76 | -Gemini 3 Pro Preview, Gemini 3 Flash Preview, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash-Lite, Gemini 2.0 Flash, Gemini 2.0 Flash-Lite, Gemini 1.5 Pro, Gemini 1.5 Flash | |
| 75 | +Gemini 3.8 Flash, Gemini 3.7 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash, Gemini 3.1 Pro, Gemini 3 Flash, Gemini 3.5 Flash-Lite, Gemini 3.1 Flash-Lite, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash-Lite | |
| 77 | 76 | **DeepSeek**: |
| 78 | 77 | DeepSeek V3 |
| 79 | 78 | |
| 79 | +## Lead Management Dashboard — Turn Chat Traffic Into a Real Lead List | |
| 80 | + | |
| 81 | +Every email and name your chatbot captures now lands in one clean, sortable dashboard — so you can finally see your leads as a list instead of hunting through individual transcripts. | |
| 82 | + | |
| 83 | +**What You Get:** | |
| 84 | + | |
| 85 | +- **One Row Per Lead** — emails captured across multiple sessions are automatically deduplicated, so each lead appears once with a conversation count and a "last seen" timestamp | |
| 86 | +- **Top Pages Capturing Leads** — instantly see which pages on your site are driving the most lead captures; click any page to filter the list to leads from that page only | |
| 87 | +- **Powerful Filtering** — search by email or name, filter by date range (24h / 7d / 30d / 90d / all-time), or filter by status (leads with a conversation vs. orphan leads who submitted the form but never chatted) | |
| 88 | +- **Orphan Lead Tracking** — visitors who drop their email in the pre-chat form but never send a message are surfaced separately so you never lose a captured contact | |
| 89 | +- **One-Click View Conversation** — jump from any lead straight into their latest full conversation in the transcripts viewer | |
| 90 | +- **Bulk Delete + CSV Export** — select multiple leads to delete or export in one action; CSV export supports email-only or email + name + conversation count + last-seen + top page | |
| 91 | +- **Clean, Responsive, Native** — works beautifully on desktop, tablet, and phone with the same polished dashboard feel as the rest of MxChat | |
| 92 | +- **Zero Setup, Zero Migration** — uses your existing chat data, no new database tables, no configuration — turn on lead capture and the dashboard just works | |
| 93 | + | |
| 94 | +**Perfect for** sales teams managing inbound leads, agencies reporting to clients, and anyone who wants to see the actual ROI of their chatbot at a glance without digging through individual conversations. | |
| 95 | + | |
| 80 | 96 | ## AI Content Generator — Create Blog Posts & Landing Pages with AI |
| 81 | 97 | |
| 82 | 98 | MxChat includes a built-in AI Content Generator that lets you create full blog posts and landing pages directly from your WordPress dashboard — no external tools or copy-pasting required. |
| 83 | 99 | |
| @@ -83,9 +99,9 @@ | ||
| 83 | 99 | |
| 84 | 100 | **How It Works:** |
| 85 | 101 | |
| 86 | 102 | 1. **Describe Your Content** — Enter a topic, title, or detailed prompt and choose between a blog post or landing page layout |
| 87 | -2. **AI Generates Everything** — The AI produces fully styled HTML with responsive CSS, ready-to-publish content, and optional AI-generated images using DALL-E, Gemini, or Grok | |
| 103 | +2. **AI Generates Everything** — The AI produces fully styled HTML with responsive CSS, ready-to-publish content, and optional AI-generated images using OpenAI GPT Image, Gemini, or Grok | |
| 88 | 104 | 3. **Real-Time Preview** — See your content exactly as it will appear on your site with a live scaled preview, including desktop and mobile viewport switching |
| 89 | 105 | 4. **Edit with AI Chat** — Use the built-in AI chat panel to request changes like "make the heading bigger" or "change the background to blue" — the AI updates your content in real time |
| 90 | 106 | 5. **Publish Instantly** — Content is saved as a native WordPress post or page with clean HTML, SEO metadata, and responsive design that works with any theme |
| 91 | 107 | |
| @@ -97,13 +113,13 @@ | ||
| 97 | 113 | - Built-in SEO analysis with real-time scoring and one-click AI auto-optimization |
| 98 | 114 | - Fullwidth and standard layout options with automatic theme compatibility |
| 99 | 115 | - Content history to revisit and manage previously generated posts |
| 100 | 116 | - Works with popular page builders and themes including Elementor, Bricks, Divi, Astra, Kadence, and more |
| 101 | -- Optional [Advanced Content Editor Add-On](https://mxchat.ai/advanced-content-editor/) for Google Search Console analytics, smart internal linking, readability analysis, and advanced SEO optimization | |
| 117 | +- Optional [Advanced Content Editor Add-On](https://mxchat.ai/add-ons/mxchat-advanced-content/) for Google Search Console analytics, smart internal linking, readability analysis, and advanced SEO optimization | |
| 102 | 118 | |
| 103 | 119 | ## MxChat Anywhere — Deploy Your Chatbot on Any Website |
| 104 | 120 | |
| 105 | -Your WordPress site powers the AI, but your chatbot doesn't have to live there. The [MxChat Anywhere Add-On](https://mxchat.ai/mxchat-anywhere-deploy-your-ai-chatbot-on-any-website-with-one-script-tag/) lets you deploy your fully configured chatbot on any website with a single script tag — Shopify, Squarespace, Wix, static HTML, SaaS apps, documentation sites, or anything with an HTML page. | |
| 121 | +Your WordPress site powers the AI, but your chatbot doesn't have to live there. The [MxChat Anywhere Add-On](https://mxchat.ai/add-ons/mxchat-embed/) lets you deploy your fully configured chatbot on any website with a single script tag — Shopify, Squarespace, Wix, static HTML, SaaS apps, documentation sites, or anything with an HTML page. | |
| 106 | 122 | |
| 107 | 123 | **Key Features:** |
| 108 | 124 | |
| 109 | 125 | - One script tag to add your chatbot to any site — no coding or framework required |
| @@ -114,22 +130,8 @@ | ||
| 114 | 130 | - Lightweight vanilla JS widget with zero dependencies — no jQuery needed on the target site |
| 115 | 131 | |
| 116 | 132 | **Ideal for** SaaS products with a WordPress blog but a separate web app, e-commerce brands on Shopify, documentation sites, or any business that needs their chatbot beyond WordPress. |
| 117 | 133 | |
| 118 | -## Powerful Add-On Ecosystem | |
| 119 | - | |
| 120 | -**Pro Add-Ons:** | |
| 121 | -🟢 **Advanced Content Editor** – Google Search Console integration with per-page impressions, clicks, and search queries. Smart internal linking, AI readability optimization, image ALT text generation, and advanced SEO checks | |
| 122 | -🟢 **Multi-Bot Manager** – Create and manage multiple specialized chatbots with dedicated knowledge databases for different purposes (support, sales, technical, etc.) | |
| 123 | -🟢 **Video Generation** – Generate stunning AI videos using Google's Veo 2 and Veo 3 models with audio support and multiple aspect ratios | |
| 124 | -🟢 **Admin Assistant** – ChatGPT-like interface in WordPress admin with thread management and image generation | |
| 125 | -🟢 **Chat Themes** – Visual design editor with AI-powered chatbot theme generation from natural language | |
| 126 | -🟢 **MxChat Forms** – Create chatbot-triggered forms for lead capture and support tickets | |
| 127 | -🟢 **Chat Moderation** – Advanced security with email/IP banning and content filtering | |
| 128 | -🟢 **MxChat Anywhere** – Deploy your chatbot on any website with one script tag — Shopify, Squarespace, Wix, static HTML, and custom web apps with Shadow DOM style isolation | |
| 129 | -🟢 **Perplexity Integration** – Real-time web search with authoritative, well-sourced responses | |
| 130 | -🟢 **Migration Tool** – Seamlessly switch embedding models and vector databases without losing data, with batch processing and real-time progress tracking | |
| 131 | - | |
| 132 | 134 | ## 📱 Mobile-Friendly & Fully Customizable |
| 133 | 135 | |
| 134 | 136 | MxChat’s chatbot widget adapts seamlessly to all devices — desktop, tablet, or mobile. Customize colors, greetings, and placement to match your brand and provide a smooth experience across your entire website. |
| 135 | 137 | |
| @@ -147,9 +149,9 @@ | ||
| 147 | 149 | ## 🆓 Start with MxChat’s Powerful Free Plan |
| 148 | 150 | |
| 149 | 151 | MxChat offers a fully functional free plan that includes everything you need to get started with AI chatbot and customer support. With no credit card required, you can: |
| 150 | 152 | |
| 151 | -- Access all AI models from 5 major providers | |
| 153 | +- Access all AI models from 6 major providers | |
| 152 | 154 | - AI Content Generator for blog posts and landing pages with SEO scoring and AI auto-optimization |
| 153 | 155 | - Train chatbot on unlimited website content |
| 154 | 156 | - Loops email capture for lead generation |
| 155 | 157 | - Web search and image generation capabilities |
| @@ -158,46 +160,11 @@ | ||
| 158 | 160 | - RAG support & contextual awareness |
| 159 | 161 | |
| 160 | 162 | Whether you're running a small business or launching a new online store, MxChat’s free plan gives you the tools to offer intelligent customer support and grow your business — without paying a cent. |
| 161 | 163 | |
| 162 | -== Developer Hooks & Filters == | |
| 163 | - | |
| 164 | -MxChat provides WordPress filter hooks so developers can extend and customize chatbot behavior without modifying core plugin files. [View full documentation with code examples](https://mxchat.ai/mxchat-developer-hooks-filters/). | |
| 165 | - | |
| 166 | -= mxchat_before_process_post = | |
| 167 | - | |
| 168 | -Runs during knowledge base indexing and lets you modify a post's data before MxChat processes it. Use this to include custom field data (e.g. product specifications or ACF fields), strip internal content you don't want the chatbot to learn, or transform posts based on bot ID. Receives the WP_Post object and the bot ID. | |
| 169 | - | |
| 170 | -= mxchat_system_instructions = | |
| 171 | - | |
| 172 | -Dynamically modify the system prompt before every AI response. Use this to inject live data such as business hours, inventory status, or user-specific context into the prompt at runtime. Receives the instructions text, bot ID, and session ID. MxChat also supports WordPress shortcodes directly in the system prompt field — any registered shortcodes are automatically expanded before being sent to the AI. | |
| 173 | - | |
| 174 | -## ✅ Get Started with MxChat AI Chatbot Today | |
| 175 | - | |
| 176 | -Installing MxChat for WordPress takes just a few clicks. Get started with our free plan and upgrade anytime to access our complete add-on ecosystem and premium features. | |
| 177 | - | |
| 178 | -## 💰 Pricing | |
| 179 | - | |
| 180 | -Most powerful features are included in the free plan. Upgrade to Pro for the complete add-on ecosystem and advanced capabilities. | |
| 181 | -[View all pricing options](https://mxchat.ai/) | |
| 182 | - | |
| 183 | -== Use of Third-Party Services == | |
| 184 | - | |
| 185 | -This plugin connects to AI service providers to generate responses: | |
| 186 | - | |
| 187 | -**Service Providers:** | |
| 188 | -- [OpenRouter](https://openrouter.ai/) - [Terms](https://openrouter.ai/terms) | [Privacy](https://openrouter.ai/privacy) | |
| 189 | -- [OpenAI](https://openai.com/) - [Terms](https://openai.com/policies/terms-of-use/) | [Privacy](https://openai.com/policies/privacy-policy/) | |
| 190 | -- [Anthropic](https://anthropic.com/) - [Terms](https://www.anthropic.com/terms) | [Privacy](https://www.anthropic.com/privacy) | |
| 191 | -- [Google](https://ai.google.dev/) - [Terms](https://ai.google.dev/terms) | [Privacy](https://policies.google.com/privacy) | |
| 192 | -- [X.AI](https://x.ai/) - [Terms](https://x.ai/terms-of-service) | [Privacy](https://x.ai/privacy-policy) | |
| 193 | -- [DeepSeek](https://deepseek.com/) - [Terms](https://deepseek.com/terms) | [Privacy](https://deepseek.com/privacy) | |
| 194 | - | |
| 195 | -Please ensure compliance with applicable terms and data privacy laws. | |
| 196 | - | |
| 197 | 164 | == Installation == |
| 198 | 165 | |
| 199 | -1. Upload the `mxchat` folder to the `/wp-content/plugins/` directory. | |
| 166 | +1. Upload the `mxchat-basic` folder to the `/wp-content/plugins/` directory. | |
| 200 | 167 | 2. Activate the plugin through the 'Plugins' menu in WordPress. |
| 201 | 168 | 3. Navigate to the 'MxChat' settings page to configure your OpenAI API key and other settings. |
| 202 | 169 | |
| 203 | 170 | == Frequently Asked Questions == |
| @@ -203,9 +170,9 @@ | ||
| 203 | 170 | == Frequently Asked Questions == |
| 204 | 171 | |
| 205 | 172 | = What AI models does MxChat support? = |
| 206 | 173 | |
| 207 | -MxChat supports 100+ AI models including OpenAI GPT-5.2, GPT-5.1, GPT-5, GPT-5 Mini, Anthropic Claude Opus 4.6, Claude Sonnet 4.6, Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Google Gemini 2.0 Flash, Gemini 1.5 Pro, xAI Grok 4, Grok 3, DeepSeek Chat, and many more. With OpenRouter integration, you get access to models from OpenAI, Anthropic, Google, Meta, Mistral, and other providers with a single API key. | |
| 174 | +MxChat supports 100+ AI models including OpenAI GPT-5.5, GPT-5.1 Chat Latest, GPT-5, Anthropic Claude Opus 4.8, Claude Sonnet 4.6, Claude Haiku 4.5, Google Gemini 3.8 Flash, Gemini 3.1 Pro, xAI Grok 4, Grok 3, DeepSeek V3, and many more. With OpenRouter integration, you get access to models from OpenAI, Anthropic, Google, Meta, Mistral, and other providers with a single API key. | |
| 208 | 175 | |
| 209 | 176 | = How do I get API keys for the AI chatbot? = |
| 210 | 177 | |
| 211 | 178 | For OpenAI, visit platform.openai.com and create an account. For Anthropic Claude, visit console.anthropic.com. For Google Gemini, visit ai.google.dev. For xAI Grok, visit x.ai. For DeepSeek, visit platform.deepseek.com. For OpenRouter (100+ models), visit openrouter.ai. Each provider offers different pricing tiers and free credits for new users. |
| @@ -223,9 +190,9 @@ | ||
| 223 | 190 | Yes. MxChat includes full WooCommerce integration. The AI chatbot can be trained on your product catalog including titles, descriptions, pricing, SKUs, categories, and custom fields. Enable auto-sync to automatically update the knowledge base when products change. Your chatbot can answer questions about products, pricing, availability, and help customers find what they need. |
| 224 | 191 | |
| 225 | 192 | = Can I customize the AI chatbot appearance? = |
| 226 | 193 | |
| 227 | -Yes. MxChat offers extensive customization options including custom colors, chatbot icon, AI avatar, chat bubble size, light/dark/system themes, positioning (left/right), custom CSS, greeting messages, placeholder text, and widget layouts. Use the built-in AI Theme Generator to describe your ideal design and let AI create custom styling automatically. | |
| 194 | +Yes. The free plugin lets you set the widget position (left or right), the greeting and placeholder text, and add your own custom CSS. The MxChat Theme Customizer add-on (Pro) handles the rest of the look: custom colors for around 20 widget elements, your own chatbot icon and avatar image, chat bubble size, light, dark and system themes, widget layouts, and a built-in CSS editor. Its AI Theme Generator lets you describe the design you want and generates the theme for you. | |
| 228 | 195 | |
| 229 | 196 | = How do I add the chatbot to my WordPress site? = |
| 230 | 197 | |
| 231 | 198 | You can add the chatbot using the shortcode `[mxchat_chatbot floating="yes"]` for a floating widget or `[mxchat_chatbot floating="no"]` for an embedded chat. Alternatively, enable "Append to Body" in settings to automatically display the chatbot on all pages without shortcodes. |
| @@ -231,9 +198,9 @@ | ||
| 231 | 198 | You can add the chatbot using the shortcode `[mxchat_chatbot floating="yes"]` for a floating widget or `[mxchat_chatbot floating="no"]` for an embedded chat. Alternatively, enable "Append to Body" in settings to automatically display the chatbot on all pages without shortcodes. |
| 232 | 199 | |
| 233 | 200 | = Does MxChat support streaming responses? = |
| 234 | 201 | |
| 235 | -Yes. MxChat supports real-time streaming responses for OpenAI, Anthropic Claude, and xAI Grok models. Streaming displays AI responses word-by-word as they're generated, providing a faster, more engaging chat experience for your visitors. | |
| 202 | +Yes. MxChat supports real-time streaming responses for OpenAI, Anthropic Claude, xAI Grok, and DeepSeek models. Streaming displays AI responses word-by-word as they're generated, providing a faster, more engaging chat experience for your visitors. | |
| 236 | 203 | |
| 237 | 204 | = What is the Chat Transcripts feature? = |
| 238 | 205 | |
| 239 | 206 | The Chat Transcripts dashboard provides comprehensive conversation management. View all chat histories, see detailed conversation flows, track which knowledge sources the AI used for each response, monitor user engagement, and analyze chat analytics including daily activity, peak hours, and user distribution. |
| @@ -267,10 +234,15 @@ | ||
| 267 | 234 | Yes. MxChat integrates with Slack for live agent handoff. When the AI cannot help or a visitor requests human support, conversations can be seamlessly transferred to your team via Slack. |
| 268 | 235 | |
| 269 | 236 | = What are Actions and how do they work? = |
| 270 | 237 | |
| 271 | -Actions are custom triggers that execute when user intent is detected. Create actions for lead capture, appointment booking, support tickets, page redirects, or custom JavaScript. The AI automatically recognizes when users want to perform these actions and triggers them contextually. | |
| 238 | +Actions are capabilities your chatbot can perform — lead capture, appointment booking, support tickets, page redirects, image generation, web search, or custom JavaScript. MxChat gives you two ways to fire them, and you can use either one or both together: | |
| 272 | 239 | |
| 240 | +* **Trigger Phrases** – the original system. A smart vector embedding match fires an action when a visitor's message matches a phrase you've set up. Precise, deterministic control over exactly when each action runs. | |
| 241 | +* **AI Tools (function calling)** – the chatbot decides on its own when to run an enabled action, straight from natural language, with no phrases to configure. The easiest way to get started; it needs a tool-capable AI model. | |
| 242 | + | |
| 243 | +Manage both from the Actions area in your MxChat settings, which holds Trigger Phrases and AI Tools side by side. | |
| 244 | + | |
| 273 | 245 | = Can visitors upload documents to chat? = |
| 274 | 246 | |
| 275 | 247 | Yes. Enable document uploads to let visitors chat with PDFs and Word documents. The AI extracts and processes document content in real-time, allowing contextual Q&A about uploaded files. |
| 276 | 248 | |
| @@ -275,9 +247,9 @@ | ||
| 275 | 247 | Yes. Enable document uploads to let visitors chat with PDFs and Word documents. The AI extracts and processes document content in real-time, allowing contextual Q&A about uploaded files. |
| 276 | 248 | |
| 277 | 249 | = Does MxChat support image generation? = |
| 278 | 250 | |
| 279 | -Yes. With DALL-E integration, the AI chatbot can generate images based on user descriptions directly within the chat conversation. | |
| 251 | +Yes. With OpenAI GPT Image and Google Imagen integration, the AI chatbot can generate images based on user descriptions directly within the chat conversation. | |
| 280 | 252 | |
| 281 | 253 | = How does the knowledge base auto-sync work? = |
| 282 | 254 | |
| 283 | 255 | Enable auto-sync for posts, pages, WooCommerce products, or custom post types. When you publish or update content, MxChat automatically updates the knowledge base with the new information. No manual re-importing required. |
| @@ -287,667 +259,530 @@ | ||
| 287 | 259 | Yes. MxChat fully supports Advanced Custom Fields. ACF field data is automatically included when importing content. Use the ACF Field Settings to control which custom fields are included or excluded from the knowledge base—perfect for hiding private notes or internal data from the chatbot. |
| 288 | 260 | |
| 289 | 261 | = What embedding models does MxChat support? = |
| 290 | 262 | |
| 291 | -MxChat supports multiple embedding models for vector search including OpenAI text-embedding-ada-002, text-embedding-3-small, text-embedding-3-large, Google Gemini embedding, and Voyage AI embeddings. Choose the model that best fits your accuracy and cost requirements. | |
| 263 | +Built in: OpenAI (text-embedding-ada-002, text-embedding-3-small, text-embedding-3-large), Google Gemini embedding, and Voyage AI. You can also use any OpenAI-compatible embeddings endpoint — Ollama, LM Studio, vLLM, LocalAI, or Azure OpenAI — by configuring the Custom Provider under Settings, then enabling "Use custom provider for embeddings" and naming your embedding model (for example nomic-embed-text) in the Custom Embedding Model field. Both knowledge base indexing and live queries then use that endpoint. Re-index your knowledge base after changing embedding models so stored vectors match query vectors. | |
| 292 | 264 | |
| 293 | -= Is there a free version of MxChat? = | |
| 265 | += Can I use a local model such as Ollama or LM Studio? = | |
| 294 | 266 | |
| 295 | -Yes. MxChat is available for free on the WordPress plugin repository with full AI chatbot functionality. Premium add-ons are available for advanced features like the AI Theme Generator and priority support. | |
| 267 | +Yes. MxChat's Custom Provider setting accepts any OpenAI-compatible API endpoint, including locally hosted ones like Ollama, LM Studio, vLLM, and LocalAI. Point the Custom Provider base URL at your server, choose your chat model, and optionally enable "Use custom provider for embeddings" with a local embedding model such as nomic-embed-text or mxbai-embed-large to keep the entire pipeline — chat and vector search — on your own hardware with no per-token costs. | |
| 296 | 268 | |
| 297 | -== Screenshots == | |
| 269 | += Is there a free version of MxChat? = | |
| 298 | 270 | |
| 299 | -1. **Chat Transcripts Insights** - Review and analyze conversations insights to see engagement rate, peak activity, and user distribution. | |
| 300 | -2. **Chat Transcripts Insights** - View 7 day activity trend graph. | |
| 301 | -3. **Knowledge & Sitemap Submission** - Submit custom content to enhance the chatbot's responses. | |
| 302 | -4. **Action Page** - Set custom action triggers to complete specific actions. | |
| 303 | -5. **Plugin Settings Page** - Configure your API key and other settings. | |
| 304 | -6. **MxChat Debug Panel** - Easily debug and view your content matching scores, citation URLs, triggered actions and more. | |
| 271 | +Yes. MxChat is available for free on the WordPress plugin repository with full AI chatbot functionality. Premium add-ons are available for advanced features such as the Theme Customizer with its AI Theme Generator, and come with priority support. | |
| 305 | 272 | |
| 306 | -*(Note: Screenshots will be added in future updates)* | |
| 273 | +== Developer Hooks & Filters == | |
| 307 | 274 | |
| 308 | -== Changelog == | |
| 275 | +MxChat provides WordPress filter hooks so developers can extend and customize chatbot behavior without modifying core plugin files. [View full documentation with code examples](https://mxchat.ai/mxchat-developer-hooks-filters/). | |
| 309 | 276 | |
| 310 | -= 3.2.1 - April 17, 2026 = | |
| 311 | -- Fixed: Admin Testing Tab debug panel not displaying similarity scores, action matches, or source data — including when web search + streaming are both enabled | |
| 312 | -- Fixed: Web search responses (streaming and non-streaming) not saving RAG context to chat transcripts, causing the "sources" link to be missing | |
| 277 | += mxchat_before_process_post = | |
| 313 | 278 | |
| 314 | -= 3.2.0 - April 15, 2026 = | |
| 315 | -- Added: `mxchat_similarity_results` filter hook after similarity search completes, allowing add-ons to access matched sources and their URLs | |
| 316 | -- Removed: `data-no-optimize` attribute injection on MxChat CSS/JS tags, which was conflicting with third-party cache and optimization plugins | |
| 279 | +Runs during knowledge base indexing and lets you modify a post's data before MxChat processes it. Use this to include custom field data (e.g. product specifications or ACF fields), strip internal content you don't want the chatbot to learn, or transform posts based on bot ID. Receives the WP_Post object and the bot ID. | |
| 317 | 280 | |
| 318 | -= 3.1.9 - April 7, 2026 = | |
| 319 | -- Fixed: Session ownership issues that were causing "session expired" errors | |
| 281 | += mxchat_system_instructions = | |
| 320 | 282 | |
| 321 | -= 3.1.8 - April 6, 2026 = | |
| 322 | -- New: Loading indicator displayed while chat is initializing | |
| 323 | -- New: Individual trigger phrase embeddings — each key phrase now gets its own vector for more accurate action matching | |
| 324 | -- Improved: Existing actions remain fully backwards compatible with grouped legacy phrases | |
| 325 | -- New: Admin Testing Tab - embedded chatbot replica with real-time debug panel showing similarity scores, action matches, approved URLs, system prompt, and debug log | |
| 326 | -- Improved: "Delete All" in Knowledge Base now respects the active content type filter — only deletes the filtered type (e.g. Pages) instead of everything | |
| 283 | +Dynamically modify the system prompt before every AI response. Use this to inject live data such as business hours, inventory status, or user-specific context into the prompt at runtime. Receives the instructions text, bot ID, and session ID. MxChat also supports WordPress shortcodes directly in the system prompt field — any registered shortcodes are automatically expanded before being sent to the AI. | |
| 327 | 284 | |
| 328 | -= 3.1.7 - April 1, 2026 = | |
| 329 | -- Fixed: Chat history not appearing for returning visitors until first message sent when chat persistence is enabled and email collection is off | |
| 330 | -- Fixed: Lead capture form not displaying for new visitors when email collection is enabled | |
| 331 | -- Fixed: Editing legacy manual knowledge base entries deleting all other manual entries sharing the same source URL | |
| 332 | -- New: Google Drive PDF links are now automatically converted to direct downloads for knowledge base import | |
| 285 | += Added in 3.2.22 = | |
| 333 | 286 | |
| 334 | -= 3.1.6 - March 30, 2026 = | |
| 335 | -- Fixed: Pre-chat popup reappearing on every page refresh — it now stays dismissed for 24 hours | |
| 336 | -- Fixed: Links with certain special characters in URLs being cut off | |
| 337 | -- Fixed: Chat history not loading for returning visitors | |
| 338 | -- Fixed: Links displaying as plain text instead of clickable links in chat responses | |
| 287 | +mxchat_client_ip (the visitor address behind a trusted proxy), mxchat_current_datetime_line (the date and time line sent with each message), mxchat_transcript_user_message and mxchat_ai_conversation_history (what humans and the model each see of a transcript), mxchat_chat_toolbar_items with the mxchat:toolbar-ready and mxchat:opened browser events (toolbar buttons from an add-on), mxchat_handoff_card_sections (extra sections on the Telegram and Slack handoff card), and the MxChat_Utils::save_session_message helper for writing to a transcript. Each is documented with examples on the page linked above. | |
| 339 | 288 | |
| 340 | -= 3.1.5 - March 25, 2026 = | |
| 341 | -- Improved: Lowered default RAG sources limit from 6 to 3 to reduce token usage for users on lower-tier API plans | |
| 342 | -- Improved: Added per-source chunk cap of 5 to prevent any single document from dominating context | |
| 343 | -- New: RAG Chunks Limit setting — control max total chunks sent to AI (range 8–20, default 15) to balance context quality and token cost | |
| 344 | -- New: Page-level chatbot visibility — show, hide, or use global setting per page/post from the meta box | |
| 345 | -- New: Frontend debugger and transcripts now show actual sources and chunks used counts | |
| 289 | +## ✅ Get Started with MxChat AI Chatbot Today | |
| 346 | 290 | |
| 347 | -= 3.1.4 - March 22, 2026 = | |
| 348 | -- New: Added support for OpenAI GPT-5.4, GPT-5.4 Mini, GPT-5.4 Nano, and GPT-5.3 Chat models | |
| 349 | -- New: Edit Default Prompt — customize the AI system prompt for blog posts and landing pages from the Content page, saved per type across sessions | |
| 350 | -- New: Knowledge base entries can be edited inline with automatic re-chunking and re-embedding (works with both database and Pinecone) | |
| 351 | -- New: Sitemap import now supports PDF URLs — bulk import PDFs via XML sitemap | |
| 352 | -- Improved: Performance updates and bug fixes | |
| 353 | -- Fixed: Clear chat session in MxChat debugger now fully clears chat sessions and context history | |
| 291 | +Installing MxChat for WordPress takes just a few clicks. Get started with our free plan and upgrade anytime to access our complete add-on ecosystem and premium features. | |
| 354 | 292 | |
| 355 | -= 3.1.3 - March 16, 2026 = | |
| 356 | -- New: Content Calendar tab added to Content page — shows locked preview when Advanced Content Editor is not installed, fully functional when add-on is active | |
| 357 | -- New: Chat teaser pop-up message now supports multiple lines. | |
| 358 | -- Improved: Session cookies and tracking now deferred until first user interaction — passive visitors no longer trigger session creation or AJAX calls | |
| 359 | -- Improved: Markdown table rendering with column alignment, responsive scrolling, and alternating row styling | |
| 293 | +## 💰 Pricing | |
| 360 | 294 | |
| 361 | -= 3.1.2 - March 13, 2026 = | |
| 362 | -- New: Per-check AI fix buttons — hover any failing SEO check to see a sparkle icon that fixes just that item individually | |
| 363 | -- New: SEO dashboard now has row checkboxes with "Optimize Selected" to batch-optimize posts (requires Advanced Content Editor add-on) | |
| 364 | -- Improved: "AI Optimize" button renamed to "Optimize All" for clarity | |
| 365 | -- Improved: SEO modal now includes a "View Page" link and per-check AI fix buttons are always visible | |
| 366 | -- Improved: Post type dropdown now dynamically includes custom post types like WooCommerce Products | |
| 367 | -- Fixed: AI Optimize now runs all addon checks (readability, internal links, image ALT, featured image) in the content editor — previously only meta description, title, and slug were included | |
| 368 | -- Fixed: Chat transcripts not saving bot responses containing emojis due to database table using utf8mb3 charset — upgraded to utf8mb4 | |
| 369 | -- Fixed: WooCommerce product cards now display with image, price, and button in chat transcripts | |
| 370 | -- Fixed: "Optimize All" now runs SEO fixes sequentially to prevent race conditions — previously internal links and other content-modifying fixes could overwrite each other | |
| 371 | -- Upgraded: Image generation replaced deprecated DALL-E 3 with GPT Image (OpenAI) and added Gemini Imagen 4 action | |
| 295 | +Most powerful features are included in the free plan. Upgrade to Pro for the complete add-on ecosystem and advanced capabilities. | |
| 296 | +[View all pricing options](https://mxchat.ai/) | |
| 372 | 297 | |
| 373 | -= 3.1.1 - March 4, 2026 = | |
| 374 | -- New: Slack agents can now transfer users back to AI mode by typing `!endchat` in the channel | |
| 375 | -- 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 | |
| 376 | -- New: SEO analysis panel with real-time scoring for posts and pages in the Content section | |
| 377 | -- New: AI Auto-Optimize — one-click AI fixes for meta descriptions, SEO titles, and URL slugs with configurable check selection | |
| 378 | -- New: Google Search Console integration (Pro) — per-page impressions, clicks, CTR, and top search queries directly in the Content editor | |
| 379 | -- New: SEO optimize settings — choose which checks AI Optimize will run from Content > Settings | |
| 380 | -- 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 | |
| 381 | -- Fixed: Security scanner false-positives flagging `file_put_contents` as malware — replaced with `WP_Filesystem` API for transcript and PDF temp files | |
| 382 | -- Improved: PDF parser library now lazy-loaded on demand instead of on every page request | |
| 298 | +== Use of Third-Party Services == | |
| 383 | 299 | |
| 300 | +This plugin connects to AI service providers to generate responses: | |
| 384 | 301 | |
| 385 | -= 3.1.0 - March 1, 2026 = | |
| 386 | -- Fixed: Bulk deleting selected knowledge base entries with chunked content causing network timeout error when using Pinecone | |
| 387 | -- Fixed: Manually entered knowledge base content not being used for AI context despite having high similarity scores | |
| 388 | -- Fixed: Chat input remaining blocked after live agent handoff (Slack/Telegram) | |
| 389 | -- 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 | |
| 390 | -- Fixed: Shortcode stripping silently losing all content on pages with large or deeply nested shortcodes (e.g. WPBakery/Visual Composer) due to regex backtracking | |
| 391 | -- New: Added `mxchat_before_process_post` filter hook to allow developers to modify post data before knowledge base processing | |
| 392 | -- New: Added `mxchat_system_instructions` filter hook and shortcode support in system prompt for dynamic data injection | |
| 302 | +**Service Providers:** | |
| 303 | +- [OpenRouter](https://openrouter.ai/) - [Terms](https://openrouter.ai/terms) | [Privacy](https://openrouter.ai/privacy) | |
| 304 | +- [OpenAI](https://openai.com/) - [Terms](https://openai.com/policies/terms-of-use/) | [Privacy](https://openai.com/policies/privacy-policy/) | |
| 305 | +- [Anthropic](https://anthropic.com/) - [Terms](https://www.anthropic.com/terms) | [Privacy](https://www.anthropic.com/privacy) | |
| 306 | +- [Google](https://ai.google.dev/) - [Terms](https://ai.google.dev/terms) | [Privacy](https://policies.google.com/privacy) | |
| 307 | +- [X.AI](https://x.ai/) - [Terms](https://x.ai/terms-of-service) | [Privacy](https://x.ai/privacy-policy) | |
| 308 | +- [DeepSeek](https://deepseek.com/) - [Terms](https://deepseek.com/terms) | [Privacy](https://deepseek.com/privacy) | |
| 393 | 309 | |
| 394 | -= 3.0.9 - February 24, 2026 = | |
| 395 | -- 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 | |
| 396 | -- New: Advanced Content Editor premium add-on — smart internal linking, AI image management, and per-field AI meta generation | |
| 397 | -- New: Dynamic post type filtering in knowledge database dropdown — automatically pulls in all registered post types | |
| 398 | -- Improved: Compatibility with popular optimization and caching plugins | |
| 310 | +Please ensure compliance with applicable terms and data privacy laws. | |
| 399 | 311 | |
| 400 | -= 3.0.8 - February 20, 2026 = | |
| 401 | -- New: Debug & optimization tools with log viewer, settings export, and reset options | |
| 402 | -- New: Added Claude Sonnet 4.6 model | |
| 403 | -- Improved: Performance optimizations and caching plugin compatibility | |
| 312 | +== Screenshots == | |
| 404 | 313 | |
| 405 | -= 3.0.7 - February 15, 2026 = | |
| 406 | -- New: Performance optimization | |
| 407 | -- Fixed: GPT-5.1 Chat Latest model returning API error when web search was disabled | |
| 314 | +1. **Chat Transcripts Insights** - Review and analyze conversations insights to see engagement rate, peak activity, and user distribution. | |
| 315 | +2. **Chat Transcripts Insights** - View 7 day activity trend graph. | |
| 316 | +3. **Knowledge & Sitemap Submission** - Submit custom content to enhance the chatbot's responses. | |
| 317 | +4. **Action Page** - Set up Trigger Phrases and AI Tools (function calling) to complete specific actions. | |
| 318 | +5. **Plugin Settings Page** - Configure your API key and other settings. | |
| 319 | +6. **MxChat Debug Panel** - Easily debug and view your content matching scores, citation URLs, triggered actions and more. | |
| 408 | 320 | |
| 409 | -= 3.0.6 - February 11, 2026 = | |
| 410 | -- New: RAG Sources Limit slider - control how many knowledge base sources (3-10) are included in AI responses | |
| 411 | -- New: {visitor_name} placeholder support in Intro Message and AI Behavior settings for personalized greetings | |
| 412 | -- New: Added Claude Opus 4.6 and Claude Opus 4.5 models | |
| 413 | -- Fixed: Chat persistence OFF now correctly starts fresh AI context on page reload (previously AI retained full history) | |
| 414 | -- Deprecated: Removed all GPT-4 series and GPT-3.5 Turbo from model selection (OpenAI deprecation) | |
| 415 | -- Deprecated: Removed Claude 3.x series models (3.7 Sonnet, 3.5 Sonnet, 3 Opus, 3 Sonnet, 3 Haiku) per Anthropic deprecation | |
| 416 | -- Updated: Users on deprecated OpenAI models auto-migrated to GPT-5.1 Chat Latest (or GPT-5 Mini for mini models) | |
| 417 | -- Updated: Users on deprecated Claude models auto-migrated to Claude Opus 4.6 (or Claude Haiku 4.5 for Haiku users) | |
| 321 | +*(Note: Screenshots will be added in future updates)* | |
| 418 | 322 | |
| 419 | -= 3.0.5 - January 28, 2026 = | |
| 420 | -- Fixed: Updated Gemini embedding model from deprecated `gemini-embedding-exp-03-07` to stable `gemini-embedding-001` | |
| 421 | -- Fixed: Notification settings not saving on new installations | |
| 422 | -- Fixed: Save indicators not visible on settings fields (API keys, Slack, Telegram, Loops, Brave Search) | |
| 423 | -- Added: Warning notice for WordPress database users recommending Pinecone for large knowledge bases | |
| 424 | -- Improved: Minor admin UI updates for better user experience | |
| 323 | +== Changelog == | |
| 425 | 324 | |
| 426 | -= 3.0.4 - January 24, 2026 = | |
| 427 | -- New: Added latest Google Gemini models (3 Pro Preview, 3 Flash Preview, 2.5 Pro, 2.5 Flash, 2.5 Flash-Lite) | |
| 428 | -- New: Transcript translation feature - auto-translate chat transcripts to any language | |
| 429 | -- New: Action scores visible in transcript sources modal - see document rankings and triggered actions | |
| 430 | -- Fixed: Lead capture forms not working due to multi-bot class ID changes | |
| 325 | += 3.2.24 - October 2, 2026 = | |
| 326 | +* Fixed: A live-agent message Slack refuses (deleted or archived channel, revoked token) now tells the visitor instead of being reported as sent, ends the handoff so the chatbot takes over again, and shows the error on the Slack tab. Slack messages also no longer begin with stray characters. | |
| 327 | +* Fixed: The WordPress personal data export now includes visitors who filled in the pre-chat form without chatting (email, name and consent record). | |
| 328 | +* Fixed: A media file whose knowledge entry was deleted is indexed again the next time it is saved, instead of being skipped as unchanged. | |
| 329 | +* Fixed: View indexed content now works for entries whose address carries encoded characters (non-Latin pages, addresses with spaces) and for manually added Pinecone entries, and shows a long entry in full. | |
| 330 | +* Fixed: Links in chatbot replies now open in Safari on iPhone, iPad and Mac when Open Links in New Tab is on. Safari's pop-up blocker was silently blocking them. | |
| 331 | +* Fixed: The video card for a matching YouTube entry now appears on streamed answers from GPT-5 and GPT-6 models. Before, it needed AI Tools on or streaming off. | |
| 332 | +* Fixed: A chat message containing a document link no longer fails on chatbots embedded with MxChat Anywhere. | |
| 333 | +* Fixed: Answers name an uploaded document or PDF in plain text instead of showing its file name as a link, including files uploaded before this update. | |
| 334 | +* Fixed: A PDF added through PDF Upload keeps its file name. Its pages are listed under the file, answers name the file and page, and uploading the same PDF again replaces its pages instead of adding a second copy. PDFs uploaded earlier are left as they are: upload once more for a clean set, then delete the old pages. | |
| 335 | +* Fixed: On a Pinecone document index, part numbers and codes that start with digits are found again, such as an order number like 5872EF or 4471AB12 for a part printed 4471-AB-12. Entries written earlier keep their old codes: run Migrate again or re-save the entry to refresh them. | |
| 336 | +* Fixed: Sites embedding through a Custom Provider can add knowledge through the REST API without an OpenAI key, and a Pinecone document index is sized from the custom model's real dimension. The Knowledge listing, search, action phrases and import notice follow the custom model too. | |
| 337 | +* New: Document Upload and PDF Upload each have an optional Source URL field. Give the page the file lives on and answers drawn from it link to that page. | |
| 338 | +* New: WooCommerce product tags are included in each product's knowledge-base text, beside its categories. Re-save or re-import a product to pick them up. | |
| 339 | +* New: Re-import affected entries, on the Knowledge screen and as the wp mxchat kb-reimport command. It finds entries that earlier versions stored with currency signs or accents missing, HTML character codes left in, or right-to-left PDF text saved backwards. It shows the list first and changes nothing until you confirm. Uploaded files are not kept on the server, so for those only text direction can be repaired. | |
| 340 | +* Improved: Delete old index now refuses while Multi-Bot bots still use that index, and names them. | |
| 341 | +* Improved: With Multi-Bot on a site that keeps knowledge in the WordPress database, the Knowledge screen now says the content is shared with all bots. Per-bot separation needs Pinecone or an OpenAI Vector Store. | |
| 342 | +* Improved: Admin polish. The warning status pill is styled, the importer's selection counter has its spacing, the Pinecone card's status follows the host you typed, and namespace lists keep a stable order. | |
| 431 | 343 | |
| 432 | -= 3.0.3 - January 21, 2026 = | |
| 433 | -- Fixed: Bug when web search was enabled the chat input was not enabled again. | |
| 344 | += 3.2.23 - September 29, 2026 = | |
| 345 | +* Fixed: Pressing Enter with an empty message no longer locks the chat input. The box stays usable, and only a real message disables it while the reply is generated. A message made only of spaces or blank lines now counts as empty too, so nothing is sent to the model for it. | |
| 346 | +* Improved: Pages imported from a web address or a sitemap now remember their own page title (from the page's title tag or its social-sharing title, with the site name trimmed off). Add-ons that name a source, such as MxChat AI Search's source cards, can show the real title instead of a guess made from the address. | |
| 347 | +* Improved: On a Pinecone document index, part numbers typed without their spaces, hyphens or dots now find the right record. R165321320 reaches the records that describe R1653 213 20 or the R1653 family, in any letter case, and an exact match always ranks above a family match. Records copied or added from now on carry the matching tokens; run Migrate again to add them to records copied earlier. | |
| 348 | +* Improved: Migrate now copies your vector index into the document index while the chatbot keeps answering from the vector index. Nothing switches until you save the Pinecone settings, and saving is held back while a copy into that index is still running unless you tick Switch anyway. An interrupted copy continues from where it stopped, each request copies several batches and retries a dropped connection on its own, the real reason is shown if it does stop, and the progress line reports records remaining, records in other namespaces that are not copied, and the count the document index itself reports when done. | |
| 349 | +* Fixed: Create index for me no longer fails with an HTTP 409 when the Index Name field still holds your vector index's name. Switching to the document index type suggests a free name ending in -docs, an existing name is refused in plain words with a suggestion filled in, and creating or checking an index no longer moves the chatbot to it before you save. | |
| 350 | +* New: The GPT-6 models are in the model picker: GPT-6 Astra (recommended), GPT-6 Sol and GPT-6 Luna. They work for chat, the content generator and the editor assistant, and the request settings each one requires are applied automatically. | |
| 351 | +* Improved: When AI Tools are on, the model is now told how many tool calls it may make for a message, is told how many remain after each round, and is asked for a single call when only one is left. Before, a model could request several lookups at once when only one was allowed, have the rest refused, and answer from partial results. | |
| 352 | +* Fixed: Delete old index now checks every namespace of the old vector index, not just the one copied last. It refuses, and names the namespace, while any namespace with records has no finished copy whose count matches. Before, a site with several namespaces (one per bot, or a namespace from an earlier setup) could delete records that were never copied. | |
| 353 | +* New: Migrate can copy every namespace of the vector index in one run. When the source index holds records in other namespaces, the Pinecone card offers a Copy every namespace switch beside Migrate. Each namespace is copied into the same-named namespace of the document index, so every bot keeps reading its own; the progress line shows which namespace is being copied and the counts for each, an interrupted copy continues with the right namespace, and a namespace already copied is kept rather than copied again. | |
| 434 | 354 | |
| 435 | -= 3.0.2 - January 21, 2026 = | |
| 436 | -- New: Telegram Live Agent integration for live chat handoff via Telegram forum topics | |
| 437 | -- New: Telegram settings page (Settings > Integrations > Telegram) | |
| 438 | -- New: Telegram action type in Actions page for intent-based handoff | |
| 439 | -- New: Citation Links toggle to enable/disable source URLs in AI responses (Chatbot > Behavior) | |
| 440 | -- Changed: Renamed "Live Agent" settings tab to "Slack" | |
| 441 | 355 | |
| 442 | -= 3.0.1 - January 18, 2026 = | |
| 443 | -- New: Multi-select entries with bulk "Delete Selected" in knowledge base | |
| 444 | -- New: OpenAI Vector Store integration for knowledge retrieval | |
| 445 | -- New: Custom Post Meta whitelist for including non-ACF meta fields in embeddings | |
| 446 | -- Improved: WordPress database search now filters to matching records only | |
| 447 | -- Improved: WordPress import shows 100 items by default with cross-page selection | |
| 448 | -- Fixed: ACF Field Settings now displays correctly in Knowledge Base sidebar | |
| 449 | -- Changed: Chatbot CSS selectors migrated from IDs to classes for multi-bot support | |
| 450 | -- Note: AI Theme Customizer users must update add-on and click "Migrate" on their theme | |
| 356 | += 3.2.22 - September 20, 2026 = | |
| 357 | +* New: An opt-in Pinecone Document index with full-text search, so a question carrying a part number, SKU or code finds the record that holds it. Create index for me, Check index and Migrate move an existing index across with no re-embedding, and classic vector indexes are untouched. | |
| 358 | +* New: The chatbot knows the current date and time in your site's timezone, so it can tell past events from upcoming ones. The line travels with each message and does not affect prompt caching; {current_date} and {current_datetime} also work as placeholders in the instructions. | |
| 359 | +* New: Knowledge base content can be restricted to any role on your site, including custom ones from User Role Editor, Members or a membership plugin. The built-in Subscribers and Above through Administrators Only choices behave exactly as before. | |
| 360 | +* New: Every post and page has a Knowledge base access setting in the MxChat box on its edit screen, so content without tags is no longer stuck as public. Where both apply, the stricter of the tag rule and the page setting wins. | |
| 361 | +* New: PDF, Word, text and Markdown files already in your media library can be imported into the knowledge base, with the text read from the file itself. The Media source now lists only those four types. | |
| 362 | +* New: Switch on Media under Advanced Custom Post Sync Settings and a supported file adds itself to the knowledge base on upload, updates its entry when replaced and is removed when deleted. | |
| 363 | +* New: The pre-chat lead form can be shown to signed-in visitors too, pre-filled from their profile, and the email address can be made optional so you can collect a name and consent alone. Leads captured either way appear in the Leads tab and the CSV export. | |
| 364 | +* New: The API can remove knowledge base entries by source URL, singly or up to 50 at a time, so a document deleted in SharePoint, Drive or your CMS can be taken out of the chatbot by your sync job. Deleting a URL that is not stored is reported as nothing removed, not an error. | |
| 365 | +* New: Lead capture submissions can be read over the API, with paging and a since filter, so leads can be synced into a CRM or spreadsheet automatically. | |
| 366 | +* New: Gemini 3.8 Flash, 3.7 Flash and 3.6 Flash join the model picker, with 3.8 Flash as the recommended Gemini default and 3.5 Flash-Lite as the lowest-cost choice. Sites already on 3.5 Flash keep it until they pick something else. | |
| 367 | +* New for developers: Add-ons can put a button in the chat toolbar with the mxchat_chat_toolbar_items filter, and the mxchat:toolbar-ready and mxchat:opened page events mean no more watching the page or running requests on every view. The WooCommerce cart button is the first to use it. | |
| 368 | +* New for developers: Add-ons can append to a chat transcript with save_session_message, shape what humans read with mxchat_transcript_user_message and mxchat_ai_conversation_history, and add sections to the Telegram and Slack handoff card with mxchat_handoff_card_sections. | |
| 369 | +* Security: Hardened how links are written into the chat window and how a visitor's own earlier messages are restored after a page reload. Ordinary links, encoded addresses and file names with brackets look and behave exactly as before. | |
| 370 | +* Security: Hardened per-visitor rate limiting and its hourly reset. A visitor's allowance is now counted against the address the request really came from, with Cloudflare handled automatically, and daily, weekly and monthly limits hold for the full period; other proxies can use the new mxchat_client_ip filter. | |
| 371 | +* Fixed: Restricting a knowledge entry to a custom role no longer leaves it readable by every signed-in visitor. | |
| 372 | +* Fixed: Choosing Media in the WordPress Content importer now lists your files instead of coming back empty on every site. | |
| 373 | +* Fixed: With Pinecone, the Knowledge Entries heading shows the vector count Pinecone reports instead of 50 for any index over 500 vectors, paging uses Previous and Next and continues where the last page ended, and a bot with its own empty namespace shows 0. | |
| 374 | +* Fixed: With Contextual Awareness on, sending a message on a page with a video or audio player no longer starts an invisible copy playing or downloads the media again. The page text is read from an inert copy, gathered once per page. | |
| 375 | +* Fixed: The function-calling loop no longer sends an invalid request when the per-turn tool budget is reached. Every tool call gets a result, the model answers from what it has, and a provider failure after a tool has run is logged even with developer mode off. | |
| 376 | +* Fixed: Words joined with underscores, such as file names, SKUs and placeholders, no longer lose their underscores and turn italic. A backslash writes an underscore, asterisk, tilde or backtick literally, and anything inside backticks is shown exactly as written. | |
| 377 | +* Improved: The Hybrid keyword boost now applies to Pinecone document indexes as well as the WordPress database, and the Transcripts and Testing panels label each match Vector, Keyword or Both. | |
| 378 | +* Improved: With AI Tools active, questions that need no tool are generated once instead of twice, so replies arrive sooner and ordinary turns use roughly half the output tokens. Those replies arrive as one message; the mxchat_fc_keep_first_hop_text filter restores the old behaviour. | |
| 379 | +* Improved: Gemini 3 series models are asked for a low thinking level on every chat reply, natively and through the OpenAI-compatible provider, so you stop paying for hidden reasoning tokens. A developer can change it with the mxchat_gemini_thinking_level filter. | |
| 380 | +* Improved: The API Access screen documents every endpoint in one place, with ready-to-run examples for removing a deleted document and syncing new leads. | |
| 381 | +* Improved: The plugin listing's appearance FAQ now says which customization options are in the free plugin and which come with the Theme Customizer add-on. | |
| 382 | +* Changed: The plugin now declares WordPress 5.3 and PHP 7.4 as its minimum versions, matching what the code has required for some time. Every MxChat add-on already required PHP 7.4. | |
| 451 | 383 | |
| 452 | -= 3.0.0 - January 14, 2026 = | |
| 453 | -- New: Complete admin UI overhaul with modern sidebar navigation across all pages | |
| 454 | -- New: Clean, professional design with consistent styling throughout the plugin | |
| 455 | -- New: Automatic sitemap detection with one-click "Process Sitemap" button | |
| 456 | -- New: Real-time knowledge base updates - new entries appear instantly without page refresh | |
| 457 | -- New: Consolidated Pro Upgrade and Add-ons pages into a unified interface | |
| 458 | -- New: Improved mobile responsiveness with collapsible menus and slide-up detail panels | |
| 384 | += 3.2.21 - September 6, 2026 = | |
| 385 | +* Fixed: Ending a Telegram live agent conversation, from MxChat or from Telegram itself, now retires its topic and returns the visitor to the AI. The visitor's next request used to post into the closed topic, where agents could not reply. | |
| 386 | +* Fixed: The conversation history shared with Telegram agents now always arrives, sent in parts within Telegram's message limit as readable text. A long conversation could previously drop the entire handoff card without a trace. | |
| 387 | +* Fixed: Slack agents who reply in a thread on a handoff message now reach the visitor. Those threaded replies were silently discarded in the default per-conversation mode. | |
| 388 | +* Fixed: With Chat Persistence on, Start new chat now leaves only your greeting, and a restored conversation keeps the greeting above it. A returning visitor was previously left with one old reply and no greeting. | |
| 389 | +* Fixed: The Open Telegram settings button on the webhook security notice now opens the Telegram settings tab instead of the onboarding screen. | |
| 390 | +* Improved: Telegram handoffs share the last 10 messages, labeled with the count, and any Telegram delivery failure is shown on the Telegram settings screen with Telegram's own explanation. Failures used to leave no trace anywhere. | |
| 391 | +* Improved: When your site rejects Telegram's incoming requests, the Telegram settings screen and a dashboard notice now say how many, when, why, and how to fix it. Sites behind Cloudflare with no webhook secret previously dropped every reply in silence. | |
| 392 | +* Improved: When a Slack message cannot be relayed to the visitor, such as an edit or a file upload, the agent now sees a short note in the channel explaining how to get it through. Dropped replies are logged when debug mode is on. | |
| 393 | +* Improved: If your shared Slack handoff channel is private, the Slack settings screen now warns that your Slack app needs the message.groups event subscription. Without it, handoffs post but agent replies never reach the visitor. | |
| 394 | +* Improved: On the Pro and Extensions page, the button for an add-on you have not installed is now Get the ZIP from My Account and opens your account Downloads page. It used to open the same page as the Documentation button. | |
| 459 | 395 | |
| 460 | -= 2.6.4 - January 6, 2026 = | |
| 461 | -- 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. | |
| 462 | -- 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. | |
| 463 | -- 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. | |
| 464 | -- 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. | |
| 465 | -- 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. | |
| 466 | -- 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. | |
| 396 | += 3.2.20 - August 28, 2026 = | |
| 397 | +* New: The knowledge base can now populate and maintain your OpenAI Vector Store — every addition, edit and deletion is mirrored automatically, and an Import Existing Knowledge Base button (or the wp mxchat vectorstore-import command) uploads what you already have in resumable batches; role-restricted entries are never uploaded. | |
| 398 | +* New: Chat answers can no longer link to pages that do not exist — every finished answer, streaming included, is checked and links to your own site that would 404 are removed while the sentence stays intact. | |
| 399 | +* New: A Strip Unapproved Links setting separates link enforcement from Citation Links, so invented links are removed even with citations off; on for new installs, opt-in for existing sites. | |
| 400 | +* New: A third live-agent handoff destination, Webhook — send handoffs to your helpdesk, CRM or automation flow as a signed JSON POST, with its own availability schedule and delivery errors shown on the settings screen. | |
| 401 | +* New: The pre-chat email form can show a consent checkbox with your own label and Privacy Policy link, optionally required, enforced on the server — and each capture records whether it was ticked, when, and the exact label shown, visible in Leads, the CSV export and privacy exports. | |
| 402 | +* New: The chatbot can be placed with a Gutenberg block, or an Elementor widget on Elementor 3.5+ — inline or floating, with a bot picker when Multi-Bot is active, and a neutral placeholder in the editor instead of a live chat. | |
| 403 | +* New: A Document Upload import method takes .docx, .txt and .md files straight into the knowledge base; the file itself is never stored and re-uploading the same name replaces rather than duplicates. | |
| 404 | +* New: A Custom Retention (Days) field on Transcripts lets you delete transcripts after any number of days instead of only the weekly and monthly presets. | |
| 405 | +* New: Pinecone knowledge entries can now be edited in the admin — saving re-chunks and re-embeds in place, so fixing a typo no longer means delete and re-import. | |
| 406 | +* New: Each ACF field group gains a group-level toggle that includes or excludes every field in it at once, with a distinct half-way state when only some are included. | |
| 407 | +* New: Add-on AI tools now receive the model's full tool-call arguments, so a tool declaring typed parameters gets them delivered instead of everything but the query being discarded. | |
| 408 | +* New: Three developer hooks for custom retrieval — mxchat_retrieval_query rewrites the lookup text without touching the transcript, mxchat_pinecone_query_body tunes Pinecone queries, and mxchat_session_ended fires on both deletion and retention expiry. | |
| 409 | +* New: The mxchat_final_response_text filter runs on the complete answer on every response path, streaming included, before it is shown and saved. | |
| 410 | +* Security: With Contextual Awareness on, page text captured from the visitor's browser is now fenced as untrusted reference material, capped at 8,000 characters and required to belong to your own site, so instructions hidden in comments or reviews are far less likely to be followed. | |
| 411 | +* Fixed: ACF field toggles now identify each field precisely, so same-named fields in different groups no longer share one toggle or switch each other back off; existing exclusions are migrated on the safe side with a one-time notice. | |
| 412 | +* Fixed: All remaining Pinecone reads use the correct call shape and respect a configured namespace, so listings, chunked answers and already-indexed detection work on serverless indexes instead of silently returning nothing. | |
| 413 | +* Fixed: Long manually pasted entries each keep their own identity — previously a second long pasted document silently deleted the first one's content, in Pinecone and the local database alike. | |
| 414 | +* Fixed: Shortening an entry below the chunking threshold now removes its old chunk records, so answers can no longer draw on stale text alongside the new version. | |
| 415 | +* Fixed: Knowledge entries whose address contains percent-encoded characters, such as non-English permalinks, no longer go missing or save a duplicate under a different identity. | |
| 416 | +* Fixed: Importing Persian, Hindi and other Indic-script content no longer splits words at invisible joiner characters; re-import content added earlier to repair it. | |
| 417 | +* Fixed: The pre-chat email form now scrolls when taller than the chat window, so the submit button stays reachable — especially on phones with the keyboard open. | |
| 418 | +* Fixed: Product cards from filtered WooCommerce searches display correctly after a refresh instead of showing raw markup, and history replay now recognizes every MxChat card type automatically. | |
| 419 | +* Fixed: Cards from an AI tool answer keep their position below the answer text when the chat is refreshed or reopened, matching the order the visitor originally saw. | |
| 420 | +* Fixed: A floating chatbot placed by shortcode or block on a page that also auto-displays one no longer renders two overlapping bubbles with duplicate element ids. | |
| 421 | +* Fixed: With citation links on, real published pages on your own site and web-search source links are no longer stripped from answers as unknown. | |
| 422 | +* Fixed: The Sources tab in Message Context now lists the documents behind tool-answered replies, and tells apart a search that found nothing from a reply with no recorded retrieval. | |
| 423 | +* Fixed: The "Translation loading for the mxchat domain was triggered too early" notice on WordPress 6.7 and newer is resolved. | |
| 424 | +* Fixed: A custom retention value set by hand or by code is no longer reset to zero when other transcript settings are saved. | |
| 425 | +* Fixed: Status pills on admin screens outside API Access now render with their intended styling instead of as plain text. | |
| 426 | +* Fixed: The chat message input has a real accessible name for screen readers, rather than relying on placeholder text that disappears on typing. | |
| 427 | +* Fixed: Sites that saved the AI Tools screen on earlier versions now receive the recommended usage guidance for the handoff tools; hints you wrote yourself are never changed. | |
| 428 | +* Improved: Screen reader support for the conversation is complete — a streamed answer is announced once when it finishes rather than continuously as it types, the waiting state and error notices are read out, and restored history stays silent. | |
| 429 | +* Improved: On phones and tablets the chat input no longer takes focus after each reply, so the keyboard stays closed while the visitor reads; desktop is unchanged and the mxchat_autofocus_after_reply filter forces either behavior. | |
| 430 | +* Improved: Saving a WooCommerce product no longer generates two knowledge-base embeddings for the same product, halving embedding API usage on product saves. | |
| 431 | +* Improved: The daily model health check now watches every model in use, including per-bot models from Multi-Bot, via the new mxchat_models_in_use filter. | |
| 432 | +* Improved: Replacements for retired AI models live in one shared mapping used across the plugin and its add-ons, and content generation is now rescued from any retired model. | |
| 433 | +* Improved: The Content Generation model picker derives from the central model catalog, so new models appear automatically and a saved model that is no longer offered stays selected and labeled. | |
| 434 | +* Improved: The Video Card Match Threshold is now a slider with a live value readout, matching the other threshold controls; its range and limits are unchanged. | |
| 435 | +* Improved: The admin Testing panel reports how many links the guard checked and which it removed, which was previously silent. | |
| 436 | +* Improved: On non-English sites, the chat widget's default texts are saved in the site language on a fresh install. | |
| 437 | +* Improved: A Pinecone listing call that genuinely fails now logs that the fallback fired instead of masking it. | |
| 467 | 438 | |
| 468 | -= 2.6.3 - December 31, 2025 = | |
| 469 | -- New: Text chunking for RAG - large content is automatically split into semantic chunks for improved retrieval accuracy | |
| 470 | -- New: Chunk count display in WordPress Import modal - shows "(X chunks)" badge for multi-chunk content | |
| 471 | -- New: Collapsible chunk groups in Knowledge Base table - entries with multiple chunks are grouped under a single expandable row | |
| 472 | -- New: Chunk labels show "Chunk 1 of 5", "Chunk 2 of 5" etc. when chunks are expanded | |
| 473 | -- New: Chunking settings in Knowledge Database Settings tab - configure chunk size (default 4000 chars) | |
| 474 | -- New: Option to show/hide frontend debug panel in Chatbot Settings | |
| 475 | -- Enhancement: Improved retrieval - finds best matching chunks, then fetches all chunks for top URLs and reassembles | |
| 476 | -- Enhancement: Chat input is now disabled while waiting for bot response, preventing duplicate message submissions | |
| 477 | -- Enhancement: When streaming is turned on it automatically checks if compatible and disables if not. | |
| 478 | -- Fixed: Markdown formatting now preserved correctly when streaming is disabled (newlines were being stripped) | |
| 439 | += 3.2.19 - August 15, 2026 = | |
| 440 | +* Fixed: Hebrew, Arabic and other right-to-left PDFs no longer import with reversed text, and a new WP-CLI repair command fixes entries imported before this update in place. | |
| 441 | +* Fixed: Sites still set to the retired Claude Opus 4.1, or to older retired Claude models, are automatically moved to the current Claude generation of the same tier and shown a notice. | |
| 442 | +* New: MxChat checks once a day that your selected AI model still exists and warns you on the AI Models screen and dashboard before a retired model can silence your chatbot. | |
| 443 | +* Improved: Claude API costs drop on most sites — Anthropic prompt caching now runs automatically, ahead of Anthropic's September 1 Claude Sonnet 5 price change. | |
| 444 | +* Fixed: Content generation no longer fails with an Unsupported value error on GPT-5.4 Mini and GPT-5.4 Nano, and any model that rejects a reasoning setting is retried once without it. | |
| 445 | +* Improved: The xAI Grok lineup is current again — Grok 4.6 and the rest of the new generation are offered first, and existing selections keep working. | |
| 446 | +* New: Settings edits are protected — changed fields show an Unsaved marker, leaving mid-edit asks for confirmation, and edits are handed to the browser for saving if you leave anyway. | |
| 447 | +* Fixed: Imported content keeps its currency symbols, and Arabic, Hebrew, Hindi and Thai text keeps the marks its script requires; re-import content added through the bulk website, URL or PDF import tools to repair entries indexed earlier. | |
| 448 | +* Improved: Leftover HTML character codes are converted to readable text before indexing; re-import affected entries to clean up existing ones. | |
| 449 | +* Fixed: Draft posts published by import tools or scripts are no longer indexed under your homepage address. | |
| 450 | +* Fixed: WooCommerce prices are indexed in your store's base currency with the currency code, and on multi-currency stores the chatbot no longer mixes two currencies in one reply; re-import products to update older entries. | |
| 451 | +* New: The Notification Email field accepts up to five comma-separated addresses, and an invalid address is refused with a message naming it instead of silently breaking notifications. | |
| 452 | +* Improved: Visitor names and emails from the pre-chat form move into MxChat's sessions storage automatically — the Leads tab and live-agent greetings work exactly as before. | |
| 453 | +* Improved: Link-click records are covered by WordPress's privacy export and erasure tools, and old records anonymize and delete themselves over time. | |
| 454 | +* Fixed: A YouTube video card now appears only when the video actually matches the question, with a new match threshold setting — and video cards can be switched off entirely. | |
| 455 | +* New: Transcripts show which AI Tools ran on each message, with timings and errors; tools handling money, customer records or handoffs log only that they ran. | |
| 456 | +* Improved: The Slack and Telegram handoff tools arrive with their usage note prefilled, so automatic handoff works without extra setup; you can reword or clear it. | |
| 457 | +* Fixed: Inspecting a Pinecone knowledge entry works, and deletes on Pinecone setups using a namespace remove the right copy. | |
| 458 | +* Improved: Conversations are stored once instead of duplicated into the options table, and leftover duplicates clean themselves up in the background. | |
| 459 | +* Fixed: Shared admin features work again on the Transcripts and License pages, and two pieces of admin text no longer point at settings that do not exist. | |
| 479 | 460 | |
| 480 | -= 2.6.2 - December 22, 2025 = | |
| 481 | -- Fixed: Critical error when viewing Knowledge Database with large Pinecone datasets (10K+ products) | |
| 482 | -- Fixed: Optimized Pinecone API queries to prevent memory exhaustion and PHP timeouts | |
| 483 | -- Fixed: Chatbot no longer gets cut off when browser has bookmarks bar or is zoomed above 100% | |
| 484 | -- New: Post type visibility control - include or exclude specific post types from auto-display chatbot | |
| 485 | -- New: Semantic search in admin now searches ALL Pinecone records using embedded query vectors | |
| 461 | += 3.2.18 - August 8, 2026 = | |
| 462 | +* Fixed: OpenAI Vector Store knowledge base search works again — an outdated request parameter caused every search to fail silently, so the chatbot answered without your knowledge base content. | |
| 463 | +* Fixed: The knowledge base status readout now correctly shows how many vector stores are configured instead of always reporting none. | |
| 464 | +* Fixed: Content updates made outside the editor are no longer skipped. When a post was published by an import tool, a scheduled post going live, or a script, the first edit after it was silently left out of the knowledge base, so the chatbot kept answering from the original version. | |
| 465 | +* Fixed: PDFs shared in chat no longer store unreadable pages when an embedding request fails part-way through. Failed pages are skipped and recorded in the Debug Mode log, and if no page can be read the chatbot now gives the real reason instead of calling the file empty or unsupported. | |
| 466 | +* Fixed: Clearing a conversation, deleting a transcript, or erasing a visitor's data through WordPress's privacy tools now removes every trace of that session's stored state. Some of it was previously left behind forever. | |
| 467 | +* Fixed: Job listings imported from the content selector now include their location, job type and company name, matching listings saved in the editor. Listings imported earlier keep their old text until you import them again. | |
| 468 | +* Fixed: Post titles are now added to the knowledge base exactly as written. Curly quotes, apostrophes and long dashes were stored as raw character codes, and protected or private posts gained a Protected prefix — all of which could surface in answers. Entries indexed earlier keep their old titles until you import them again. | |
| 469 | +* Fixed: A short description made up only of page-builder shortcodes or spaces no longer adds an empty Short Description heading to the indexed text. | |
| 470 | +* Improved: Custom field names containing hyphens now read as words in the indexed text on both import routes, instead of only one of them. | |
| 471 | +* Improved: Chat sessions no longer bloat your site's options table. Per-session details were saved as settings rows that were never cleaned up, so busy sites accumulated thousands, some loading on every page view. Sessions now live in their own table, and existing rows are moved across automatically in the background after you update. | |
| 472 | +* New: Old chat sessions are tidied up on their own. Sessions untouched for 30 days are removed automatically — the window is adjustable with a developer filter — and the cleanup runs even on sites with WordPress scheduled tasks disabled. | |
| 473 | +* Fixed: Sitemap imports now tell you why they failed instead of pointing at an empty status area — for example, an API key missing the required permission is now named as the reason. | |
| 474 | +* Improved: Knowledge base import errors from OpenAI, Gemini and Voyage now pass along the provider's own explanation instead of a generic invalid key message. | |
| 475 | +* Improved: Chat-side embedding failures are now recorded in the Debug Mode log with the provider's real reason, matching knowledge base imports. | |
| 476 | +* Fixed: In the content selector, a selected item's tick mark was white on a white box and effectively invisible. Selected items now show a clearly filled checkbox. | |
| 486 | 477 | |
| 487 | -= 2.6.1 - December 17, 2025 = | |
| 488 | -- Fixed: Send button now includes aria-label for screen reader accessibility | |
| 489 | -- Fixed: Translations now load from /wp-content/languages/plugins/ first, preserving custom translations during updates | |
| 478 | += 3.2.17 - August 5, 2026 = | |
| 479 | +* Fixed: Japanese, Chinese and Thai content is no longer erased, split into oversized chunks, or stripped of rare characters during knowledge base imports. | |
| 480 | +* Fixed: Custom embedding providers such as Ollama, LM Studio and Azure now work end to end — the permanent mismatch banner is gone, and no cloud API key is needed for imports or automatic post syncing. | |
| 481 | +* Fixed: Scheduled posts now enter the knowledge base the moment they go live, and the developer hook for customizing indexed content also runs during automatic post syncing. | |
| 482 | +* Fixed: The WordPress content import window now fits phone screens, so its buttons are always reachable. | |
| 483 | +* Fixed: The hybrid keyword boost and smart asset loading toggles now show the saved confirmation like every other setting. | |
| 484 | +* New: Every settings tab has its own shareable link that opens directly on that tab, including nested and add-on tabs. | |
| 485 | +* Improved: Knowledge settings are centralized under Knowledge — ACF PDF extraction is now a persistent setting on the ACF Fields tab, and the hybrid keyword boost lives on the new Chunking and Retrieval tab. Saved choices carry over. | |
| 486 | +* Improved: The Editor Assistant toggle moved to the Content page's Settings tab, next to the other content tools. | |
| 487 | +* Improved: The FAQ now documents custom and local embedding providers such as Ollama and LM Studio. | |
| 488 | +* Improved: Settings holding a Pinecone API key are no longer loaded into memory on every page view. | |
| 490 | 489 | |
| 491 | -= 2.6.0 - December 12, 2025 = | |
| 492 | -- New: OpenAI GPT-5.2 model support - best general-purpose and agentic model with fast responses | |
| 493 | -- New: Markdown rendering in transcripts - bot responses display formatted text with clickable links, bold, italic, code blocks, and headers | |
| 494 | -- New: Retrieved documents viewer in transcripts - click "Sources →" link on any bot response to see knowledge base documents used, similarity scores, and citation URLs | |
| 495 | -- Improved: Session security now auto-recovers when user IP changes instead of showing "Unauthorized access" error | |
| 496 | -- Improved: Seamless experience for mobile users switching between WiFi and cellular networks | |
| 490 | += 3.2.16 - August 2, 2026 = | |
| 491 | +* New: Chat conversations are now covered by WordPress's built-in privacy tools — export requests return readable transcripts, and erasure requests delete conversations, captured emails, saved history and document traces, for both logged-in and anonymous visitors. | |
| 492 | +* New: Optional hybrid keyword boost for the WordPress-database knowledge base, off by default. It combines keyword matching with the existing similarity search so exact tokens such as product codes, SKUs and error codes find the right document, and Transcripts labels each match Vector, Keyword or Both. | |
| 493 | +* New: If your AI provider starts rejecting the configured model, MxChat now shows a persistent admin notice naming the model and linking to Settings. Previously only visitors saw the error. | |
| 494 | +* Fixed: Security — hardened validation of chat session identifiers throughout the plugin. Sites using automatic transcript emails should update. | |
| 495 | +* Fixed: Security — tightened the permission checks around MxChat's admin scripts and admin-only actions, so they load and run only for users who can manage plugin options. | |
| 496 | +* Fixed: Security — removed an unused block of stored settings data that was no longer needed. | |
| 497 | +* Fixed: OpenAI retires the GPT-5.1 Chat Latest and GPT-5.3 Chat models on August 10, 2026. Both are removed from the picker and affected sites switch to GPT-5.6 Sol automatically, with an admin notice explaining the change. | |
| 498 | +* Fixed: Unpublishing, trashing or making a post private now always removes it from the knowledge base, including status changes made by scheduled-expiry plugins that bypass the save screen. A new command, wp mxchat prune-unpublished, clears entries left by earlier unpublishes. | |
| 499 | +* Fixed: Streaming replies arrive word by word again on hosts behind a proxy such as nginx, instead of all at once after a pause. Four PHP warnings per affected chat are gone with it. | |
| 500 | +* Fixed: Quick Question buttons render at their normal size again. In 3.2.15 the new theme-protection styles let the list compress its buttons to fit the box, so the scrollbar never appeared. | |
| 501 | +* Fixed: The Loops email-capture messages no longer send you looking for a field that is not on that screen. Both now name the API Keys tab and link straight to it. | |
| 502 | +* Fixed: Removed a duplicate save-action registration on the knowledge-bot selector that pointed at code which does not exist. It would have crashed the admin screen if load ordering ever changed. | |
| 503 | +* Improved: Knowledge base import errors now carry the embedding provider's real reason, such as an invalid API key or exhausted credit, name the model, and say whether embedding or storage failed. | |
| 504 | +* Improved: Models with an announced retirement date now show that date in the picker and disappear once it passes. A model you already have selected stays visible in Settings. | |
| 505 | +* Improved: When the knowledge base has nothing relevant, the chatbot is now told so directly instead of receiving a no-information note dressed up as knowledge base content, so it simply says it does not know. | |
| 497 | 506 | |
| 498 | -= 2.5.9 - December 6, 2025 = | |
| 499 | -- Fix: Shortcode stripping now preserves content inside shortcodes instead of removing it entirely | |
| 507 | += 3.2.15 - July 28, 2026 = | |
| 508 | +* Fixed: DeepSeek chat works again. DeepSeek retired its older API model names on July 24, 2026, which broke every DeepSeek-powered chat; the model picker now offers DeepSeek V4 Flash and V4 Pro, and sites still set to an older DeepSeek model switch to V4 Flash automatically on update. | |
| 509 | +* New: Claude Opus 5 is available in the model picker — Anthropic's newest Opus model, the same price as Claude Opus 4.8, working across chat, streaming and the AI content tools. | |
| 510 | +* New: Optional performance setting to load chatbot files only on pages where the chatbot actually appears. Off by default, and helpful for reduce-unused-CSS-and-JS findings in performance audits. | |
| 511 | +* New: Slack live agent handoff can route every conversation into one shared channel your team already monitors, one thread per visitor, instead of creating a channel per visitor. Leave the new field blank and nothing changes. | |
| 512 | +* New: Optional setting to archive a conversation's Slack channel when an agent ends the chat, so channels stop piling up. Off by default. | |
| 513 | +* New: Place your knowledge base content anywhere in your AI instructions using the context placeholder. Leave it out and MxChat works exactly as before. | |
| 514 | +* New: The SEO content table now shows an average search position column from the last 28 days, available with the Advanced Content add-on connected to Search Console. | |
| 515 | +* Improved: When Search Console is not connected yet, the SEO content table now explains that connecting it fills the clicks, impressions and position columns, with a link to the Settings tab, instead of showing unexplained dashes. | |
| 516 | +* Improved: SEO content table sorting now keeps every post in the list on every filter, with posts that have no data grouped at the end. | |
| 517 | +* Improved: X.AI errors now include the provider's specific reason, such as the exact model name it could not find, alongside the general explanation. | |
| 518 | +* Improved: Sites using a delayed or on-interaction script loading strategy no longer perform an unnecessary database write on every page view. | |
| 519 | +* Fixed: The chat widget now defends itself against website themes whose styles bleed into it, including the header menu. Your own custom widget CSS keeps working unchanged. | |
| 520 | +* Fixed: When an AI provider returns a successful but empty reply, the chatbot now shows a clear message asking the visitor to try again instead of an empty chat bubble. Streaming chats close out the same way. | |
| 521 | +* Fixed: Provider errors now pass along the provider's actual explanation instead of a generic Unknown error, across image providers, embeddings, knowledge base search, web search, streamed replies and OpenRouter. | |
| 522 | +* Fixed: Conversations handled by a human now show as Live Agent in the Transcripts viewer and in emailed transcripts, instead of everything being labeled AI Assistant. | |
| 523 | +* Fixed: The streaming test button on the settings page now works with the newest Claude models, which previously returned an error even though chat itself worked. | |
| 524 | +* Fixed: Turning on developer mode no longer re-runs the plugin's activation and database migration routine on every page load. | |
| 525 | +* Fixed: The hourly rate-limit reset now re-creates itself if the scheduled task ever goes missing, so visitors are never left rate-limited longer than intended. | |
| 526 | +* Fixed: On sites where WordPress scheduled tasks are disabled, the hourly fallback check no longer loads a duplicate copy of the plugin's internals mid-request. | |
| 500 | 527 | |
| 501 | -= 2.5.8 - December 5, 2025 = | |
| 502 | -- New: Auto-email full transcript feature - sends transcript as .txt file attachment after 15, 30, or 60 minutes of user inactivity | |
| 503 | -- New: Conditional transcript emails - option to only send transcripts when visitors provide contact info (email or phone/WhatsApp) in chat | |
| 504 | -- New: Smart contact detection - automatically detects email addresses and phone numbers (including international WhatsApp formats) in chat messages | |
| 505 | -- Compatibility: Tested and compatible with WordPress 6.9 | |
| 528 | += 3.2.14 - July 18, 2026 = | |
| 529 | +* New: Editor Assistant — optional AI writing actions right inside the WordPress block editor. Select a paragraph, heading, list, or quote block and rewrite it (concise, expanded, formal, or casual), summarize it, translate it to another language, continue writing, or fix grammar and spelling, then Accept or Discard. It is off by default and uses the AI model you already configured. | |
| 530 | +* New: You can now add YouTube videos to your knowledge base. A new YouTube option on the Import screen takes a video link and, per video, either auto-fetches its title, channel, and captions or lets you write your own description. When a visitor's question matches a video, the answer includes it as a playable embed right inside the chat that loads no YouTube player or Google cookies until the visitor taps play. | |
| 531 | +* New: Live agent handoff can now follow an availability schedule, so visitors are only offered a human during the days and hours your team is actually reachable, and the chatbot simply keeps answering outside them. Slack and Telegram each get their own independent schedule on their own settings tab, so a channel staffed at different hours keeps its own calendar. It is off by default and uses your site timezone. | |
| 532 | +* New: Added the latest OpenAI GPT-5.6 models — Sol, Terra, and Luna — for both your chatbot and content generation. | |
| 533 | +* New: MxChat AI Search now appears on the Pro and Extensions page alongside the other add-ons, so you can discover it from inside your dashboard. | |
| 534 | +* New: Developers can now add their own trusted links to the chatbot's allowed-links list with the new mxchat_valid_urls filter, so links returned by custom function-calling tools stay clickable in replies. | |
| 535 | +* Fixed: Editing a Knowledge Base entry no longer throws away your work. Clicking outside the edit box, or selecting text and releasing the mouse just past its edge, used to close it and discard everything you had typed. The box now closes only when you ask it to — the close or cancel button, the Escape key, or a successful save — and confirms first if you have unsaved changes. The same fix applies to the Add Tool and Edit Tool dialog on the Actions screen. | |
| 536 | +* Fixed: Product and image search now correctly refine your search terms when a GPT-5 model is selected. Previously the refinement step silently stopped working and fell back to the raw text, weakening results. | |
| 537 | +* Fixed: The Telegram live-agent webhook is no longer accepted without verification when a secret token has not been set; requests are now validated by origin and a reminder is shown to configure a secret. | |
| 538 | +* Fixed: The Testing page's chatbot replica now uses the exact same knowledge base as your live chatbot. On sites running Pinecone with the Multi-Bot add-on active, the testing chat was quietly searching the WordPress database instead. | |
| 539 | +* Fixed: Automatic transcript deletion now repairs its own schedule if the scheduled cleanup task is ever lost, so old transcripts no longer stop being deleted while your settings still say retention is on. The Transcripts settings also now show when the next cleanup will run. | |
| 506 | 540 | |
| 507 | -= 2.5.7 - December 2, 2025 = | |
| 508 | -- Fix: Streaming fallback bug - bot responses now properly saved to chat transcripts when streaming fails and falls back to regular response mode | |
| 509 | -- Enhancement: Added comprehensive metrics dashboard to Transcripts page with 3 tabs (Overview, Activity, Insights) | |
| 510 | -- Enhancement: Added 7-day activity trend chart with custom visualization | |
| 511 | -- Enhancement: Added new metrics including daily/weekly/monthly chat counts, peak activity hours, and engagement rates | |
| 512 | -- Enhancement: Added auto-delete transcripts feature with configurable intervals (1 week, 2 weeks, 1 month) for better database management and privacy | |
| 513 | -- Enhancement: WooCommerce product imports now include complete pricing metadata (regular price, sale price, price ranges for variable products, SKU, categories) | |
| 514 | -- Improvement: Updated transcript settings modal for better usability on desktop and mobile | |
| 515 | -- Improvement: Various CSS fixes for metrics dashboard display | |
| 541 | += 3.2.13 - July 10, 2026 = | |
| 542 | +* New: Claude Sonnet 5 is now selectable as both a chat model and a content generation model. | |
| 543 | +* New: The Knowledge Base Custom Post Meta section can scan your content and suggest custom meta keys as clickable options, so you can add non-ACF meta to the embedding whitelist without knowing the exact key names. | |
| 544 | +* Fixed: Knowledge Base imports of PDFs and web pages no longer fail with a 403 error on firewall-protected hosts (SiteGround, Wordfence, Cloudflare) — MXChat now identifies itself with an honest, versioned MXChatBot user agent you can allowlist if needed. | |
| 545 | +* Fixed: PDFs a visitor links in a live chat now use the same MXChatBot identity, so a firewall that allowlists MXChatBot lets them through too. | |
| 546 | +* Fixed: The close button on the pre-chat greeting bubble now works on chatbots with a custom bot ID, including Multi-Bot setups, not just the default chatbot. | |
| 547 | +* Improved: The Custom Post Meta help text now points to the built-in key scanner and notes that array and repeater values are flattened during embedding. | |
| 516 | 548 | |
| 517 | -= 2.5.6 - November 30, 2025 = | |
| 518 | -- Security: Improved session ID validation with server-side checks | |
| 519 | -- Security: Added session ownership verification to prevent unauthorized access to chat sessions | |
| 520 | -- Fixed: Database error "Unknown column 'bot_id'" for multi-bot configurations with automatic migration | |
| 521 | -- Improvement: Enhanced session security with consistent ownership verification | |
| 522 | -- Improvement: Added automatic database schema migration system | |
| 523 | -- Improvement: WooCommerce import improvements to support Custom Tabs information | |
| 524 | -- Improvement: Database management with a new filtering option. Filter by posts, pages, products, PDF | |
| 549 | += 3.2.12 - June 30, 2026 = | |
| 550 | +* Fixed: Resolved a WordPress.org packaging issue from the previous release that could cause the update to fail to download or appear to hang in the WordPress dashboard on some sites. This maintenance release republishes the plugin so every site can update normally and receive the recent improvements from 3.2.11 — including the per-provider Test API key buttons, built-in WPML and Polylang translation for the chat widget, Google Gemini web search, the optional Max Input Length character counter, cleaner Slack live-agent links, the Knowledge View indexed content panel, and the security and Pinecone matching fixes. No functional changes from 3.2.11; no settings or data are affected. | |
| 525 | 551 | |
| 526 | -= 2.5.5 - November 21, 2025 = | |
| 527 | -- Fixed: Issue with non-streaming mode failing to format URLs and paragraphs correctly | |
| 528 | -- Fixed: Bug with shortcodes still appearing in the knowledge database | |
| 529 | -- Enhancement: Minor adjustments to improve compatibility with multi-bot setups requiring email-to-chat forms | |
| 530 | -- New: Added Grok 4.1 Fast (Reasoning) model — 2M context, reasoning | |
| 531 | -- New: Added Grok 4.1 Fast (Non-Reasoning) model — 2M context, faster responses | |
| 532 | -- New: Added OpenAI GPT-5.1 model — flagship for coding & agentic tasks with low reasoning and 400K context | |
| 552 | += 3.2.11 - June 29, 2026 = | |
| 553 | +* New: Each AI provider API key field (OpenAI, X.AI, Claude, DeepSeek, Google Gemini, OpenRouter) now has a Test key button that checks whether the key actually works in one click, so you can confirm a key is valid right after pasting it instead of finding out only when a chat fails. It runs a quick, free validation check and never spends credits. | |
| 554 | +* Fixed: When restricting knowledge by tag under Knowledge then Role Restrictions, you can now enter a tag by its display name or its slug. Previously only the exact slug worked, so typing a real tag's name returned a confusing error; the field is now labeled Tag (name or slug) and gives an actionable message when no matching tag exists. | |
| 555 | +* Fixed: On sites using Pinecone for knowledge, answers added directly through Knowledge then Import Options then Direct Content (manual entries with no source link) are now used by the chatbot when they are the best match. Previously the bot could reply that it did not have the information even though the manual entry clearly matched, and the testing panel showed zero sources used; both are now correct. | |
| 556 | +* New: Built-in WPML and Polylang compatibility for the chat widget text. The widget's visible strings (top bar title, greeting, AI agent label, input placeholder, the email and name capture form copy, and the satisfaction prompts) now show up automatically in WPML String Translation, so you can translate the widget into each language without registering every field by hand. | |
| 557 | +* New: Optional Max Input Length setting caps how many characters a visitor can type or paste into a single message, so you can stop overly long pastes from being sent to the AI. It sits just below the Input Placeholder option in the chatbot settings. Leave it at 0 for unlimited, which is the default and keeps existing behavior unchanged. | |
| 558 | +* Fixed: Security hardening for the chat intro message setting, following a Wordfence advisory. The intro message is now escaped when shown on the settings page and sanitized when saved, so a crafted value can no longer run script in the admin area on multisite sites or sites where unfiltered HTML is disabled. | |
| 559 | +* Fixed: When a live agent replies from Slack with a link, the website visitor now sees a clean, clickable link instead of Slack's raw formatting with a stray closing bracket. Slack user and channel mentions and escaped characters are also tidied up before the message reaches the visitor. | |
| 560 | +* New: The Slack live-agent channel now shows the visitor's name and email at the top of the conversation when they were captured at the start of the chat, so your agent can see who they are talking to instead of just a session ID and a user ID of zero for guests. | |
| 561 | +* Improved: When a maximum message length is set, the chat box now shows a small live character counter as the visitor nears the limit, ramping from a neutral color to amber to red, with a gentle nudge if they reach the cap. This replaces the old behavior where typing past the limit silently did nothing and looked broken. The counter uses only numbers, so it reads correctly on sites in any language. | |
| 562 | +* New: When the built-in Web Search option is on, chatbots using a Google Gemini model now answer using live Google Search results, just like OpenAI models already do. Previously the Web Search setting only affected OpenAI models and silently did nothing for Gemini, so Gemini users had to add the separate Perplexity add-on to get web-grounded answers. Gemini's built-in search uses the Google API key you already configured, at no extra cost. | |
| 563 | +* New: Each Knowledge entry now has a View indexed content button that opens a read-only panel showing exactly what the chatbot indexed for it: the stored text broken into the same chunks the search uses, each chunk's length, and for Pinecone the stored metadata fields. This makes it easy to confirm what was actually saved and searched for a page or a manual entry, so you can tell at a glance why a piece of content is or is not being matched, without changing anything. | |
| 533 | 564 | |
| 534 | -= 2.5.4 - November 12, 2025 = | |
| 535 | -- New: Accordion-Style Knowledge Base Viewer for cleaner, expandable database entry previews | |
| 536 | -- New: Smart Shortcode Stripping for WPBakery and Elementor during content submission to improve vectorization accuracy | |
| 537 | -- New: Unique Citation URLs when submitting direct content, allowing multiple linked submissions without overwriting | |
| 538 | -- Improvement: WooCommerce products now include both short and full descriptions during data processing | |
| 565 | += 3.2.10 - June 19, 2026 = | |
| 566 | +* New: AI Tools (function calling) — the chatbot can now decide on its own when to use your enabled tools, such as web search, image generation, answering from an uploaded PDF, and active add-on actions like WooCommerce, straight from natural language with no trigger phrases to set up. Turn it on under Actions then AI Tools (off by default; needs a tool-capable AI model), add the tools you want with a guided picker, and optionally tell the assistant in plain language when to use each one. Tools that spend money, expose customer data, or hand off to a human stay off until you enable them deliberately | |
| 567 | +* New: Optional "Start new chat" button in the chat window menu — lets visitors clear the current conversation and start fresh in one click, without turning off chat persistence (off by default; enable it under Chatbot then Display, with a customizable label) | |
| 568 | +* Improved: The Actions area is clearer — the original phrase-matching system is now called Trigger Phrases and sits alongside AI Tools under one Actions menu, with AI Tools listed first as the recommended path and a plain-language explainer of when to use each | |
| 569 | +* Improved: Readable, leak-safe AI error messages now cover every provider (Claude, OpenAI, xAI, Google Gemini, DeepSeek and OpenRouter) for both API errors and connection or timeout failures — site admins get an actionable hint such as choosing another model in Settings, while visitors only ever see a friendly fallback and never raw API or network details | |
| 570 | +* Improved: Applying or changing an AI theme, and toggling Pinecone, now auto-clears supported page caches the same way other settings changes do — no more stale widget appearance after a theme change | |
| 571 | +* Fixed: On multi-bot sites, non-streaming replies now correctly use the bot assigned to the visitor's session instead of falling back to the default bot's prompt and knowledge, and a repeated PHP notice in the debug log is gone | |
| 572 | +* Fixed: Images created with the Gemini image generator now display correctly in the chat window — previously the bot reported it had made an image but nothing appeared, because the file was saved with the wrong file type | |
| 573 | +* Fixed: The Slack live-agent setup notice in Settings now links to the current setup guide on the MxChat Core documentation page | |
| 574 | +* Fixed: Two older Claude models that Anthropic has now retired (Claude 4 Opus and Claude 4 Sonnet, the May 2025 versions) have been removed from the model pickers; if your site had either one selected, it is automatically switched to the current equivalent (Claude Opus 4.8 or Claude Sonnet 4.6) so chat keeps working without any action from you | |
| 575 | += 3.2.9 - June 11, 2026 = | |
| 576 | +* New: Claude Fable 5 — Anthropic's newest flagship model — available in the Select AI Model picker and the Content Generator | |
| 577 | +* Fixed: Claude Opus 4.7 and 4.8 now work as the Content Generator model (these models reject the temperature setting; it is no longer sent) | |
| 578 | +* New: Stop button — visitors can halt a streaming response mid-answer; the text already written is kept | |
| 579 | +* New: "Show Download Transcript Button" toggle to hide the chat menu's Download Transcript item (on by default) | |
| 580 | +* Improved: Settings changes now apply immediately on cached sites — MxChat purges supported page caches on save, and the chat widget fetches fresh settings when opened, so toggles no longer require clearing caches | |
| 581 | +* New: "Images per Article" slider (1–5, default 3) in the Content Generator's image settings | |
| 582 | +* Fixed: Chat widget interface text no longer appears in your pages' Google search-result snippets | |
| 583 | +* Fixed: Admin navigation now displays correctly on right-to-left language sites (Arabic, Hebrew, Persian, and others) | |
| 584 | +* Fixed: In-chat PDF and Word document upload works again, including for signed-in administrators | |
| 585 | +* Fixed: Messages sent right after a bot reply no longer vanish on sites running the Image Analysis add-on | |
| 586 | +* Fixed: The "Was this helpful?" rating prompt only appears when its setting is turned on | |
| 587 | +* Fixed: Rebuilt translation template (mxchat.pot) — syncing a translation no longer discards existing translations | |
| 588 | +* Fixed: PHP 8.2 deprecation notices no longer logged during chat requests | |
| 539 | 589 | |
| 540 | -= 2.5.3 - November 9, 2025 = | |
| 541 | -- New: Dedicated API Key Management Tab - All API keys organized in one central location for easier management | |
| 542 | -- Improvement: GPT-5 performance optimization with minimal reasoning effort mode for significantly faster response times | |
| 543 | -- Fix: Resolved URL and PDF link encoding issues causing broken or unclickable links in responses | |
| 544 | -- Improvement: Various performance enhancements for improved stability and faster processing | |
| 590 | += 3.2.8 - June 4, 2026 = | |
| 591 | +* New: Total chatbot message limit — one cap across all users and roles per timeframe, with a live usage readout and one-click reset | |
| 592 | +* New: Global and per-role rate limits accept custom values beyond the presets | |
| 593 | +* Improved: Custom Provider and Azure OpenAI embeddings work end-to-end for indexing and live queries (re-index if you had this enabled) | |
| 594 | +* Fixed: Feedback "Send" button no longer renders as an invisible white-on-white block | |
| 545 | 595 | |
| 546 | -= 2.5.2 - November 3, 2025 = | |
| 547 | -- New: URL Hallucination Prevention System - AI only cites URLs from knowledge base or system instructions, with automatic removal of invalid links | |
| 548 | -- Improvement: Brand new robust queue-based processing system for sitemap and PDF imports with real-time progress tracking | |
| 549 | -- Improvement: Optimized knowledge retrieval from 5 to 3 documents for faster response times and improved accuracy | |
| 550 | -- Improvement: Increased URL column size to TEXT type for support of long URLs and special characters (Hebrew, Arabic, etc.) | |
| 551 | -- Fix: Resolved URL double-encoding issue causing malformed PDF and document links | |
| 552 | -- Fix: Corrected citation-style bracket handling for AI responses containing [URL] format | |
| 553 | -- Fix: Fixed empty markdown link processing to prevent broken link generation | |
| 596 | += 3.2.7 - May 29, 2026 = | |
| 597 | +* New: Guided onboarding wizard for first-time setup — reopen any time from Settings → Tutorials | |
| 598 | +* New: Claude Opus 4.8 and the Google Gemini 3.x lineup; sites on retired models are migrated automatically | |
| 599 | +* Improved: First message is reliable behind full-page caches (WP Rocket, LiteSpeed, FlyingPress, W3 Total Cache, Cloudflare APO) | |
| 600 | +* Improved: Streaming and standard chat retry transient provider errors before showing a failure | |
| 601 | +* Improved: Floating chat button is fully keyboard-operable (WCAG 2.1 Level A) | |
| 554 | 602 | |
| 555 | -= 2.5.1 - October 30, 2025 = | |
| 556 | -- New: Tag-based role restrictions for chatbot knowledge base - automatically control what content the chatbot can access based on WordPress tags and user roles | |
| 557 | -- Update: Migrated users from deprecated Claude 3.5 Sonnet to Claude 3.7 Sonnet with improved performance | |
| 558 | -- Fix: Removed deprecated Claude model from selection options | |
| 603 | += 3.2.6 - May 21, 2026 = | |
| 604 | +* New: Custom Provider (OpenAI-compatible) — point MxChat at Ollama, LM Studio, vLLM, llama.cpp, or Azure OpenAI, with a Test Connection button | |
| 605 | +* New: End-of-session "Was this helpful?" satisfaction rating with admin reporting and a dashboard card | |
| 606 | +* New: ACF PDF auto-indexing — PDF text from ACF file fields is extracted into the knowledge base (opt-in) | |
| 607 | +* New: Image Quality control for OpenAI GPT Image in the Content Generator | |
| 608 | +* New: Claude Opus 4.7, GPT-5.5, and GPT Image 2 in the model picker | |
| 609 | +* New: REST bulk-delete endpoint for chat sessions and an embedding chunk-metadata filter for developers | |
| 610 | +* Improved: Page-cache plugins are automatically told not to cache the chat endpoint, with a per-plugin status card | |
| 611 | +* Fixed: Intermittent "Access denied" on the first chat message under full-page caching | |
| 612 | +* Fixed: Print preview was blank on pages with MxChat installed | |
| 559 | 613 | |
| 560 | -= 2.5.0 - October 25, 2025 = | |
| 561 | -- Fix: Resolved PDF URL encoding issue that caused broken links to PDF documents | |
| 562 | -- Fix: Improved UI feedback when selecting chat models | |
| 563 | -- Fix: Enhanced OpenRouter flow selection interface | |
| 614 | += 3.2.5 - May 12, 2026 = | |
| 615 | +* New: REST API with bearer-token auth — read transcripts, push knowledge, bulk-delete sessions (disabled by default) | |
| 616 | +* New: Download Transcript menu item — saves the conversation as a Markdown file (replaces Print Conversation) | |
| 617 | +* New: Redesigned chat-widget header with X-close icon and keyboard-accessible 3-dot menu | |
| 618 | +* New: Content Generator writes SEO-title meta for Rank Math/Yoast/AIOSEO and syncs image alt text to the media library | |
| 619 | +* New: Transcript retention setting (1–3650 days) with automatic daily cleanup | |
| 620 | +* Fixed: Header dropdown menu inherits the bubble theme colors instead of hardcoded white | |
| 564 | 621 | |
| 565 | -= 2.4.8 - October 16, 2025 = | |
| 566 | -- New: OpenRouter integration - access 100+ AI models with a single API key | |
| 567 | -- New: Added Claude Sonnet 4.5, Claude Opus 4.1, and Claude Haiku 4.5 support | |
| 622 | += 3.2.4 - May 3, 2026 = | |
| 623 | +* Fixed: WooCommerce product Short Description Visual tab broken by a script 404 | |
| 624 | +* Fixed: User's last message scrolls to the top after streaming replies | |
| 568 | 625 | |
| 569 | -= 2.4.7 - October 13, 2025 = | |
| 570 | -- Security: Fixed Server-Side Request Forgery (SSRF) vulnerability in PDF processing (CVE-2025-10705) | |
| 626 | += 3.2.3 - April 29, 2026 = | |
| 627 | +* New: Embedding model switch protection — warning dialog and admin notice when stored embeddings don't match the selected model | |
| 628 | +* Improved: Landing Page Generator plans more sections and writes fuller copy | |
| 629 | +* Fixed: Landing Page "Full Width" option honored on WordPress block themes | |
| 630 | +* Fixed: Manual knowledge entries no longer cited with internal placeholder URLs | |
| 571 | 631 | |
| 572 | -= 2.4.5 - September 30, 2025 = | |
| 573 | -- Bug Fix: Restored missing CSS properties for popular questions collapse/toggle buttons that were accidentally removed during code cleanup. | |
| 574 | -- Bug Fix: Fixed button hover, focus, and active states for question navigation controls. | |
| 575 | -- Bug Fix: Restored proper SVG styling and display logic for collapsible question buttons. | |
| 632 | += 3.2.2 - April 21, 2026 = | |
| 633 | +* New: Lead Management Dashboard — deduplicated lead list with filters, top-pages analytics, CSV export, and one-click jump to conversations | |
| 634 | +* Fixed: Orphaned Pinecone vectors removed when posts or products are unpublished, deleted, or renamed | |
| 635 | +* Fixed: Source and chunk count settings now apply on all retrieval paths | |
| 576 | 636 | |
| 577 | -= 2.4.4 - September 24, 2025 = | |
| 578 | -- Bug Fix: Default similarity is now accurate across all settings. | |
| 579 | -- Bug Fix: Improved streaming responses to prevent dropped characters or words. | |
| 580 | -- Enhanced: Removed unnecessary Pinecone caching in the knowledge database for more accurate results. | |
| 637 | += 3.2.1 - April 17, 2026 = | |
| 638 | +* Fixed: Admin Testing Tab debug panel missing similarity scores and sources when web search and streaming were both enabled | |
| 639 | +* Fixed: Web search responses now save their sources to chat transcripts | |
| 581 | 640 | |
| 582 | -= 2.4.3 - September 23, 2025 = | |
| 583 | -- Added: Support for upcoming multi-bot update that allows for more customized settings such as individual chat models. | |
| 584 | -- Improved: CSS for chatbot UI & more robust markdown support. | |
| 641 | += 3.2.0 - April 15, 2026 = | |
| 642 | +* New: mxchat_similarity_results filter hook for add-ons | |
| 643 | +* Fixed: Removed attribute injection that conflicted with cache and optimization plugins | |
| 585 | 644 | |
| 586 | -= 2.4.2 - September 18, 2025 = | |
| 587 | -- Added: Multi-bot support via the new Multi-Bot Manager premium add-on. | |
| 588 | -- Improved: Minor CSS adjustments for better compatibility. | |
| 589 | -- Updated: Add-on links and references throughout the plugin. | |
| 645 | += 3.1.9 - April 7, 2026 = | |
| 646 | +* Fixed: "Session expired" errors caused by session-ownership issues | |
| 590 | 647 | |
| 591 | -= 2.4.1 - September 4, 2025 = | |
| 592 | -- Fixed: Email collection form not submitting properly when "Require email to chat" is enabled. | |
| 593 | -- Improved: PDF processing now provides clearer error messages with repair suggestions when corrupted files are detected. | |
| 648 | += 3.1.8 - April 6, 2026 = | |
| 649 | +* New: Admin Testing Tab — embedded chatbot replica with a real-time debug panel | |
| 650 | +* New: Individual trigger-phrase embeddings for more accurate action matching | |
| 651 | +* New: Loading indicator while chat initializes | |
| 652 | +* Improved: "Delete All" in the Knowledge Base respects the active content-type filter | |
| 594 | 653 | |
| 595 | -= 2.4.0 - September 3, 2025 = | |
| 596 | -- Added new MxChat Video Generation add-on with support for Google Veo 2 and Veo 3 models, featuring audio generation and multiple aspect ratios. | |
| 597 | -- Fixed console error when "Require email to chat" option is disabled by adding proper validation check. | |
| 598 | -- Resolved "error chat history not found" message when chat persistence is enabled but user has no existing chat history. | |
| 599 | -- Fixed agent indicator not updating properly when switching between live agent and chatbot modes without page refresh. | |
| 654 | += 3.1.7 - April 1, 2026 = | |
| 655 | +* New: Google Drive PDF links auto-convert to direct downloads for knowledge import | |
| 656 | +* Fixed: Chat history not appearing for returning visitors with persistence on and email collection off | |
| 657 | +* Fixed: Lead capture form not displaying for new visitors when email collection is enabled | |
| 658 | +* Fixed: Editing a legacy manual knowledge entry no longer deletes others sharing the same source URL | |
| 600 | 659 | |
| 601 | -= 2.3.9 - August 17, 2025 = | |
| 602 | -- Updated Slack channel naming logic to prioritize client’s name, falling back to email, then chat ID. | |
| 603 | -- Added streaming response support for DeepSeek models. | |
| 604 | -- Enabled multiple direct content entries without requiring a source URL. | |
| 605 | -- Fixed auto sync drafts so posts moved from posted to draft are removed from the knowledge database. | |
| 606 | -- Implemented role-based chatbot information access restrictions for enhanced security and relevance. | |
| 607 | -- Added option in the admin panel’s post edit page to hide the floating chatbot on specific pages. | |
| 660 | += 3.1.6 - March 30, 2026 = | |
| 661 | +* Fixed: Pre-chat popup stays dismissed for 24 hours instead of reappearing on every refresh | |
| 662 | +* Fixed: Chat history not loading for returning visitors | |
| 663 | +* Fixed: Links with special characters being cut off or rendered as plain text | |
| 608 | 664 | |
| 609 | -= 2.3.8 - August 12, 2025 = | |
| 610 | -- Fixed extra backslashes appearing in knowledgebase content during editing. | |
| 611 | -- Added optional name field to Require Email to Chat form; transcripts now display email and name if enabled. | |
| 612 | -- 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. | |
| 665 | += 3.1.5 - March 25, 2026 = | |
| 666 | +* New: RAG Chunks Limit setting and tuned source defaults to balance answer quality and token cost | |
| 667 | +* New: Per-page chatbot visibility control from the page editor meta box | |
| 668 | +* Improved: Debugger and transcripts show the actual sources and chunks used | |
| 613 | 669 | |
| 614 | -= 2.3.7 - August 8, 2025 = | |
| 615 | -- 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. | |
| 616 | -= 2.3.6 - August 6, 2025 = | |
| 617 | -- Bug Fix: Fixed streaming fallback to properly display responses when streaming fails, preventing blank chat bubbles. | |
| 618 | -- New Feature: Added streaming test button to help users verify if streaming is compatible with their setup. | |
| 670 | += 3.1.4 - March 22, 2026 = | |
| 671 | +* New: OpenAI GPT-5.4 family and GPT-5.3 Chat models | |
| 672 | +* New: Editable default prompts for blog posts and landing pages in the Content Generator | |
| 673 | +* New: Inline knowledge-entry editing with automatic re-chunking and re-embedding | |
| 674 | +* New: Sitemap import supports PDF URLs | |
| 619 | 675 | |
| 620 | -= 2.3.5 - August 6, 2025 = | |
| 621 | -- Redesigned chat transcript UI for a cleaner, more professional experience. | |
| 622 | -- Transcripts now show the page where the chat started and any links clicked. | |
| 623 | -- Added ability to select and delete transcripts directly from the header. | |
| 676 | += 3.1.3 - March 16, 2026 = | |
| 677 | +* New: Content Calendar tab on the Content page | |
| 678 | +* New: Multi-line chat teaser pop-up messages | |
| 679 | +* Improved: Session cookies deferred until first interaction — passive visitors no longer create sessions | |
| 680 | +* Improved: Markdown table rendering with column alignment and responsive scrolling | |
| 624 | 681 | |
| 625 | -= 2.3.4 - July 30, 2025 = | |
| 626 | -- Fixed streaming compatibility issues with Cloudflare and WP Engine by implementing automatic fallback to regular chat when streaming is buffered. | |
| 627 | -- 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. | |
| 682 | += 3.1.2 - March 13, 2026 = | |
| 683 | +* New: Per-check AI fix buttons and batch "Optimize Selected" on the SEO dashboard | |
| 684 | +* Improved: Image generation upgraded from deprecated DALL-E 3 to GPT Image and Gemini Imagen 4 | |
| 685 | +* Fixed: Emojis in bot responses no longer prevent transcripts from saving | |
| 686 | +* Fixed: WooCommerce product cards display correctly in chat transcripts | |
| 687 | +* Fixed: "Optimize All" runs SEO fixes sequentially so they no longer overwrite each other | |
| 628 | 688 | |
| 629 | -= 2.3.3 - July 29, 2025 = | |
| 630 | -- Improved streaming performance by fixing output buffering issues using enhanced flush logic. | |
| 631 | -- Added contextual awareness support via the new `data-mxchat-context` HTML attribute. | |
| 632 | -- Revamped license key management system with domain linking, deactivation, and real-time usage dashboard. | |
| 633 | -- Fixed transcript timestamp display to use WordPress site's local timezone correctly. | |
| 689 | += 3.1.1 - March 4, 2026 = | |
| 690 | +* New: SEO analysis panel with real-time scoring and one-click AI Auto-Optimize | |
| 691 | +* New: Google Search Console integration (Pro) in the Content editor | |
| 692 | +* New: Slack agents can hand the conversation back to AI with !endchat, optionally with a farewell message | |
| 693 | +* Fixed: Stale nonce causing "Invalid nonce" errors on sites with full-page caching | |
| 694 | +* Fixed: Security-scanner false positives on transcript and PDF temp files | |
| 634 | 695 | |
| 635 | -= 2.3.2 - July 24, 2025 = | |
| 636 | -- Added full support for OpenAI Assistants API via the new Assistant add-on. | |
| 637 | -- Improved email collection form performance and reliability with better loading states and timeout handling. | |
| 638 | -- Enhanced WooCommerce product labeling accuracy in WordPress import with improved URL matching. | |
| 639 | -- Fixed ACF field processing errors when handling WP_Post objects and relationship fields. | |
| 696 | += 3.1.0 - March 1, 2026 = | |
| 697 | +* New: mxchat_before_process_post and mxchat_system_instructions filter hooks, with shortcode support in the system prompt | |
| 698 | +* Fixed: Manually entered knowledge content not used despite high similarity scores | |
| 699 | +* Fixed: Chat input remaining blocked after live-agent handoff | |
| 700 | +* Fixed: Pinecone scans failing with text-embedding-3-large (wrong vector dimension) | |
| 701 | +* Fixed: Shortcode stripping losing content on pages with large or deeply nested shortcodes | |
| 640 | 702 | |
| 641 | -= 2.3.1 - July 20, 2025 = | |
| 642 | -- Enhanced hyperlink functionality to include mailto links, enabling email addresses in bot responses to be clickable. | |
| 643 | -- 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. | |
| 644 | -- Added message filtering hooks system for developers to customize prompts and responses without modifying core plugin files. | |
| 703 | += 3.0.9 - February 24, 2026 = | |
| 704 | +* New: AI Content Generator — full blog posts and landing pages from a prompt, with AI images, SEO metadata, live preview, and inline AI editing | |
| 705 | +* New: Advanced Content Editor premium add-on | |
| 706 | +* Improved: Compatibility with optimization and caching plugins | |
| 645 | 707 | |
| 646 | -= 2.3.0 - July 13, 2025 = | |
| 647 | -- Added Grok-4 model support, the world's smartest AI model available. | |
| 648 | -- Added streaming response support for all Grok models (Grok-4, Grok-3, etc.), delivering real-time response generation for faster and smoother chat experiences. | |
| 708 | += 3.0.8 - February 20, 2026 = | |
| 709 | +* New: Debug and optimization tools with log viewer, settings export, and reset options | |
| 710 | +* New: Claude Sonnet 4.6 model | |
| 649 | 711 | |
| 650 | -= 2.2.9 - July 6, 2025 = | |
| 651 | -- Improved quick question UI: suggestions now collapse after user input and can be toggled with up/down icons | |
| 652 | -- Increased sitemap batch processing limit from 5 to 50 for faster indexing | |
| 653 | -- Expanded action similarity threshold range to support values from 10 to 95 | |
| 712 | += 3.0.7 - February 15, 2026 = | |
| 713 | +* Fixed: GPT-5.1 Chat Latest returning an API error when web search was disabled | |
| 654 | 714 | |
| 655 | -= 2.2.8 - June 27, 2025 = | |
| 656 | -- Added brand new contextual awareness option that automatically provides chatbot access to current page content and URL for contextually relevant responses | |
| 657 | -- Enhanced WordPress knowledge base import to include Advanced Custom Fields (ACF) data for more comprehensive content training | |
| 658 | -- Major README structure update with improved formatting and visual presentation | |
| 715 | += 3.0.6 - February 11, 2026 = | |
| 716 | +* New: RAG Sources Limit slider and {visitor_name} placeholder for personalized greetings | |
| 717 | +* New: Claude Opus 4.6 and Claude Opus 4.5 models | |
| 718 | +* Fixed: Chat persistence OFF now starts a fresh AI context on page reload | |
| 719 | +* Updated: Deprecated OpenAI GPT-4/GPT-3.5 and Claude 3.x models removed; affected sites migrated automatically | |
| 659 | 720 | |
| 660 | -= 2.2.7 = | |
| 661 | -- Fixed a bug that occured when deleting all pinecone records & added support for markdown hyperlinking in rate limit messages. | |
| 721 | += 3.0.5 - January 28, 2026 = | |
| 722 | +* Fixed: Gemini embedding model updated to the stable gemini-embedding-001 | |
| 723 | +* Fixed: Notification settings not saving on new installations | |
| 724 | +* Fixed: Save indicators not visible on several settings fields | |
| 662 | 725 | |
| 663 | -= 2.2.6 = | |
| 664 | -- 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. | |
| 665 | -- Fixed Pinecone Single Entry Deletion – Resolved a bug that prevented individual entries from being properly deleted from Pinecone vector storage. | |
| 666 | -- Improved Pinecone UI Records Retrieval – Enhanced the Pinecone database panel with better record loading and display functionality for smoother management of your vector database. | |
| 667 | -- 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. | |
| 726 | += 3.0.4 - January 24, 2026 = | |
| 727 | +* New: Latest Google Gemini models | |
| 728 | +* New: Transcript translation — auto-translate chat transcripts to any language | |
| 729 | +* Fixed: Lead capture forms broken by multi-bot class ID changes | |
| 668 | 730 | |
| 669 | -= 2.2.5 = | |
| 670 | -- 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. | |
| 671 | -- Slack Live Agent Fix – Resolved a minor bug that occasionally caused duplicate messages in Slack during live agent conversations. | |
| 672 | -- Pinecone UI Update – Fixed a UI display issue in the Pinecone database panel when using the TE3 model. | |
| 731 | += 3.0.3 - January 21, 2026 = | |
| 732 | +* Fixed: Chat input not re-enabling when web search was on | |
| 673 | 733 | |
| 674 | -= 2.2.4 = | |
| 675 | -- Critical update to error when working with large databases in Pinecone. | |
| 734 | += 3.0.2 - January 21, 2026 = | |
| 735 | +* New: Telegram Live Agent integration for live chat handoff | |
| 736 | +* New: Citation Links toggle to show or hide source URLs in AI responses | |
| 676 | 737 | |
| 677 | -= 2.2.3 = | |
| 678 | -- Various critical bug fixes that occured from the codebase refactoring. | |
| 738 | += 3.0.1 - January 18, 2026 = | |
| 739 | +* New: OpenAI Vector Store integration and custom post-meta whitelist for embeddings | |
| 740 | +* New: Multi-select with bulk "Delete Selected" in the knowledge base | |
| 741 | +* Improved: Chatbot CSS migrated from IDs to classes for multi-bot support (Theme Customizer users: update the add-on and click "Migrate") | |
| 679 | 742 | |
| 680 | -= 2.2.2 = | |
| 681 | -- Enhanced Slack integration: live agent handoff now creates new Slack channels per conversation; agents can reply directly in channel to chat with website users. | |
| 682 | -- Major codebase refactoring for improved organization and optimization. | |
| 683 | -- Improved sitemap and PDF processing: added retry mechanism, display of failed pages/URLs, and manual batch processing button. | |
| 684 | -- Fixed Pinecone setting not toggling on for users who previously did not have the add-on. | |
| 743 | += 3.0.0 - January 14, 2026 = | |
| 744 | +* New: Complete admin UI overhaul with modern sidebar navigation across all pages | |
| 745 | +* New: Automatic sitemap detection with one-click processing | |
| 746 | +* New: Real-time knowledge base updates and improved mobile responsiveness | |
| 685 | 747 | |
| 686 | -= 2.2.1 = | |
| 687 | -- Added Claude Sonnet 4 and Claude Opus 4 chat models. | |
| 688 | -- Integrated Google Gemini embedding model (gemini-embedding-001). | |
| 689 | -- Built Pinecone vector database support directly into core plugin. | |
| 690 | -- Removed dependency on separate Pinecone add-on. | |
| 748 | +Older releases are archived in the plugin's full version history on WordPress.org. | |
| 691 | 749 | |
| 692 | -= 2.2.0 = | |
| 693 | -- Added WordPress Content Importer for posts and pages. | |
| 694 | -- Implemented tabbed interface for knowledge base management. | |
| 695 | -- Added content filtering by type and knowledge base status. | |
| 696 | -- Added bulk import with real-time progress tracking. | |
| 750 | +== Upgrade Notice == | |
| 697 | 751 | |
| 698 | -= 2.1.9 = | |
| 699 | -- Added email notification feature for new chat sessions. | |
| 700 | -- Implemented pagination on transcripts page (50 per page) to improve performance. | |
| 701 | -- Fixed bug with Brave image search not returning images correctly from the API. | |
| 702 | -- Enhanced performance by changing chat transcripts to disable autoload. | |
| 752 | += 3.2.24 = | |
| 753 | +Fixes links in chatbot replies not opening in Safari on iPhone, iPad and Mac, and live-agent messages being reported as sent when Slack refused them. Uploaded documents and PDFs are now named properly in answers, can carry a Source URL, and no longer duplicate when re-uploaded, and part numbers starting with digits work again on a Pinecone document index. Adds Re-import affected entries, which rebuilds knowledge entries that earlier versions stored with missing accents, HTML character codes or reversed right-to-left text. | |
| 703 | 754 | |
| 704 | -= 2.1.7 = | |
| 705 | -- Fixed Pro activation issues when the plugin has been translated. | |
| 706 | -- Improved tab behavior to always default to the first tab. | |
| 707 | -- Major rework to rate limits: added custom rate limit timeframes and messages for each individual role. | |
| 708 | -- Fixed bug with Loops where manual list selection from dropdown was required for functionality. | |
| 755 | += 3.2.23 = | |
| 756 | +Fixes the chat input locking up for good when a visitor pressed Enter on an empty message. On a Pinecone document index, Delete old index now refuses while any namespace is still uncopied, Migrate can copy every namespace in one run and continues where it stopped, part numbers typed without spaces find their records, and Create index for me suggests a free name instead of failing on an existing one. Adds the GPT-6 models (Astra, Sol and Luna) to the model picker, and tells the chatbot its AI Tools call budget so it no longer answers from partial results when only one call is allowed. | |
| 709 | 757 | |
| 710 | -= 2.1.6 = | |
| 711 | -- Added new AI models: GPT-4.1 and the complete suite of Grok 3 models. | |
| 712 | -- Updated AI service providers to use their official SVG logos for better visual representation. | |
| 713 | -- Fixed an issue where API key fields would try to autosave when no data was entered. | |
| 714 | -- Various other minor bug fixes for improved stability and performance. | |
| 715 | 758 | |
| 716 | -= 2.1.5 = | |
| 717 | -- Added RTL Language support, allowing languages that align right to automatically do so in both chat input and AI responses. | |
| 718 | -- Improved error messaging for API calls in the frontend of the chatbot, and enhanced error messages when submitting sitemaps, URLs, and PDFs. | |
| 719 | -- Fixed an auto save issue that caused an error if no changes were made. | |
| 720 | -- Various other minor bug fixes for improved stability and performance. | |
| 759 | += 3.2.22 = | |
| 760 | +Adds the current date and time to every chat, knowledge restrictions for custom roles and single pages, media library imports with auto-sync, and an optional Pinecone full-text document index. Also hardens chat links and rate limiting, fixes function calling and underscore rendering, and adds Gemini 3.8 Flash. Now requires WordPress 5.3 and PHP 7.4. | |
| 721 | 761 | |
| 722 | -= 2.1.4 = | |
| 723 | -- Added the ability to easily customize the "AI Agent" text displayed in the top bar for greater personalization. | |
| 724 | -- Fixed a bug where data scraping failed to retrieve all content from certain websites. | |
| 725 | -- Added HTML support in the intro message for richer customization. | |
| 726 | -- Resolved an issue where API input fields triggered browser autofill, improving user input accuracy. | |
| 762 | += 3.2.21 = | |
| 763 | +Live agent chat is more reliable on both channels: Telegram conversations can be ended and restarted cleanly, conversation history always arrives, and both Telegram delivery failures and rejected incoming requests now show on the settings screen. Slack agents can reply in thread and are told when a message could not be relayed. Start new chat now works correctly with Chat Persistence on. | |
| 727 | 764 | |
| 728 | -= 2.1.3 = | |
| 729 | -- Added support for Google Gemini models: Gemini 2.0 Flash, Gemini 2.0 Flash-Lite, Gemini 1.5 Pro, and Gemini 1.5 Flash. | |
| 730 | -- Improved chat model selection UI for a more intuitive user experience. | |
| 731 | -- Redesigned embedding model selection UI for better clarity and usability. | |
| 732 | -- Enhanced error handling for sitemap submissions with more helpful user feedback. | |
| 733 | -- Fixed an issue in the knowledge database where editing entries erased or prevented changes to citation URLs. | |
| 765 | += 3.2.20 = | |
| 766 | +The knowledge base can now populate and maintain your OpenAI Vector Store — every change is mirrored automatically and a resumable import uploads what you already have, where before the store was read-only. Chat answers can no longer link to pages that do not exist, a new Webhook destination routes live-agent handoffs to your own helpdesk or automation flow, and the chatbot is placeable as a Gutenberg block or an Elementor widget. Also adds a consent checkbox for the pre-chat form, completes screen reader support for the conversation, and fixes Pinecone reads on serverless indexes. Re-import Persian, Hindi and other Indic-script content to repair entries indexed earlier. | |
| 734 | 767 | |
| 735 | -= 2.1.2 = | |
| 736 | -- Rebranded intents page to "Actions" with a revamped UI, displaying pro/add-on requirements and brief descriptions. | |
| 737 | -- Added ability to toggle actions on/off without deleting; moved image generation action from pro to free tier. | |
| 738 | -- Introduced advanced knowledge base sync feature to pull in custom post data. | |
| 768 | += 3.2.19 = | |
| 769 | +Big maintenance release. Retired AI models are now handled automatically — stranded sites are moved to a current model and a new daily check warns you before a retired model can silence your chatbot — and Claude prompt caching cuts API costs ahead of Anthropic's September 1 price change. Re-import content added through the bulk, URL or PDF import tools, plus WooCommerce products, to repair older entries; if you use the Forms or Anywhere add-ons, update them alongside core. | |
| 739 | 770 | |
| 740 | -= 2.1.1 = | |
| 741 | -- Made Claude and X.AI API models available to all users. | |
| 742 | -- Improved API key management UI - only showing relevant API key fields based on selected models. | |
| 743 | -- Enhanced knowledge import interface with clear credit requirement warnings. | |
| 744 | -- Fixed embedding error notifications for better clarity. | |
| 771 | += 3.2.18 = | |
| 772 | +Critical for OpenAI Vector Store users: knowledge base search was failing silently, leaving the chatbot to answer without your content. Per-conversation data also moves out of the options table into its own table, migrated automatically in the background after you update. Plus clearer import errors and several knowledge base indexing fixes. | |
| 745 | 773 | |
| 746 | -= 2.1.0 = | |
| 747 | -- Fixed a bug impacting the header color in the output. | |
| 748 | -- Updated embedding error notification when submitting sitemaps or PDFs. | |
| 749 | -- Improved context extraction parser. | |
| 774 | += 3.2.17 = | |
| 775 | +Big knowledge base update: Japanese, Chinese and Thai imports are no longer damaged, scheduled posts sync the moment they go live, and custom embedding providers such as Ollama work end to end without a cloud API key. Settings gain shareable per-tab links and centralized knowledge options, and the import window now fits phone screens. Recommended for all sites. | |
| 750 | 776 | |
| 751 | -= 2.0.9 = | |
| 752 | -- Revamped UI on the main settings page to match the rest of the plugin. | |
| 753 | -- Added real-time updates for sitemap and PDF processing. | |
| 754 | -- Renamed "MxChat Intent Tester" add-on to "MxChat Similarity Tester". | |
| 755 | -- Various minor bug fixes and improvements. | |
| 777 | += 3.2.16 = | |
| 778 | +Security hardening, plus chat conversations now work with WordPress's built-in privacy tools. The GPT-5.1 Chat Latest and GPT-5.3 models that OpenAI retires on August 10, 2026 are removed, and affected sites switch over automatically. Also fixes knowledge base cleanup on unpublish, streaming behind proxies, and Quick Question sizing. | |
| 756 | 779 | |
| 757 | -= 2.0.8 = | |
| 758 | -- Minor bug fix impacting similarity adjustment. | |
| 780 | += 3.2.15 = | |
| 781 | +Restores DeepSeek chat after DeepSeek retired its older API model names on July 24, 2026, automatically switching affected sites to DeepSeek V4 Flash. Adds Claude Opus 5, a shared-channel mode for Slack live agent handoff, a context placeholder for positioning knowledge base content in your AI instructions, and an optional setting to load chatbot files only on pages where the chatbot appears. Also hardens the chat widget against theme style bleed and fixes empty AI replies, provider error messages, live agent transcript labels and several scheduled-task issues. | |
| 759 | 782 | |
| 760 | -= 2.0.7 = | |
| 761 | -- **Perplexity Integration Add-On** – Added Perplexity web search, integrated into intent management with a toolbar toggle. | |
| 762 | -- **Sonnet 3.7 Support** – Introduced Anthropic’s Claude Sonnet 3.7, the latest high-intelligence model. | |
| 763 | -- **Bug Fixes & Improvements** – Fixed title tag formatting in responses and tightened knowledge database similarity range to 20. | |
| 764 | - | |
| 765 | -= 2.0.5 = | |
| 766 | -- **Auto-Expanding AI Instructions** – AI instructions text field now auto-expands to fit content. | |
| 767 | -- **Chat Transcripts UI & Export** – Redesigned chat transcripts UI and added Excel export feature. | |
| 768 | -- **Quick Questions Rebrand** – Renamed "Popular Questions" to "Quick Questions" with updated copy. | |
| 769 | -- **Security Enhancement** – Improved security to better prevent XSS attacks. | |
| 770 | -- **Intent Testing Add-On** – Integrated new Intent Tester add-on for enhanced chatbot performance. | |
| 771 | - | |
| 772 | -= 2.0.4 = | |
| 773 | -- **Markdown Response Fix** – Resolved markdown formatting issues in the chatbot UI. | |
| 774 | -- **Agent Mode Customization** – Improved indicator text theme and background styling. | |
| 775 | -- **WooCommerce Core Extraction** – Moved WooCommerce features to the dedicated MxChat WooCommerce add-on. | |
| 776 | - | |
| 777 | -= 2.0.3 = | |
| 778 | -- **Bug Fix:** Resolved issues preventing DeepSeek and Claude models from working correctly. | |
| 779 | -- **New:** Added integration for the MxChat Form Collection add-on (Pro only). | |
| 780 | -- **New:** Forms now display dynamically within the chat interface in real-time. | |
| 781 | -- **New:** Automatic intent handling for seamless form triggering. | |
| 782 | -- **Update:** Improved submission management with CSV export functionality. | |
| 783 | - | |
| 784 | -= 2.0.2 = | |
| 785 | -- **Bug Fix:** Auto-sync now properly deletes posts/pages when enabled. | |
| 786 | -- **Update:** Theme customization moved to an add-on with live preview support. | |
| 787 | -- **New:** Added MxChat Moderation plugin to ban users by email or IP. | |
| 788 | - | |
| 789 | -= 2.0.1 = | |
| 790 | -- **Bug Fix:** Fixed a DivisionByZeroError in sitemap processing that occurred when submitting an empty or malformed sitemap. | |
| 791 | -- **Bug Fix:** Resolved a similar DivisionByZeroError in PDF processing to prevent crashes when handling PDFs with 0 pages. | |
| 792 | - | |
| 793 | -= 2.0.0 = | |
| 794 | -- **New UI & Branding:** Redesigned the entire plugin interface to align with the new MXChat brand for a modern and seamless experience. | |
| 795 | -- **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. | |
| 796 | -- **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. | |
| 797 | - | |
| 798 | -= 1.6.5 = | |
| 799 | -- Optimized knowledge database retrieval to prevent memory issues with large product databases (2000+ products) | |
| 800 | -- Fixed bug with tab switching control in chat interface | |
| 801 | - | |
| 802 | -= 1.6.4 = | |
| 803 | -- Added chat notifications for improved user experience when chat persistence is enabled. | |
| 804 | -- Made the entire plugin fully translatable, allowing compatibility with translation services like Loco Translate. | |
| 805 | -- 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. | |
| 806 | - | |
| 807 | -= 1.6.4 = | |
| 808 | -- Added chat notifications for improved user experience when chat persistence is enabled. | |
| 809 | -- Made the entire plugin fully translatable, allowing compatibility with translation services like Loco Translate. | |
| 810 | -- 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. | |
| 811 | - | |
| 812 | -= 1.6.3 = | |
| 813 | -- Added the new "Rate Limit by User Role" feature, replacing the previous rate limit for logged-in users. | |
| 814 | -- Introduced DeepSeek as a new AI service provider, with full support for their models. | |
| 815 | -- Integrated DeepSeek V3, enhancing chatbot natural language understanding and performance. | |
| 816 | - | |
| 817 | -= 1.6.2 = | |
| 818 | -- Fixed a bug preventing the ability to save edits in the knowledge database. | |
| 819 | - | |
| 820 | -= 1.6.0 = | |
| 821 | -- Redesigned knowledgebase UI for a cleaner, more user-friendly interface. | |
| 822 | -- Introduced auto-sync functionality for posts and pages, enabling automatic addition of new or updated content to the knowledgebase. | |
| 823 | -- Enhanced XML sitemap submission to prevent duplicate entries by checking and updating existing pages or adding new ones as needed. | |
| 824 | -- Reworked chatbot settings to enable individual autosave after updates, removing the need for manual saving. | |
| 825 | -- Fixed paragraph formatting in the chatbot UI to display line breaks and improve readability. | |
| 826 | - | |
| 827 | -= 1.5.9 = | |
| 828 | -- Enhanced transcripts page with new analytics dashboard and improved UI | |
| 829 | -- Added support for X.AI's Grok model | |
| 830 | -- Improved message formatting to preserve paragraphs in intro messages | |
| 831 | -- Updated admin panel interface with better organization and styling | |
| 832 | -- Added better mobile responsiveness across admin screens | |
| 833 | - | |
| 834 | -= 1.5.8 = | |
| 835 | -- Introduced a new setting to require an email address before starting a chat. When enabled, this email will be displayed at the top of the chat transcript if needed. | |
| 836 | - | |
| 837 | -= 1.5.7 = | |
| 838 | -- Enhanced Complianz plugin integration to support the premium version and improve reliability. | |
| 839 | -- Fixed an issue where names were not appearing in chat transcripts for logged-in users. | |
| 840 | -- Added the ability to customize the title bar icon in the theme settings. | |
| 841 | -- Grouped intents by category in dropdown menus for better organization and usability. | |
| 842 | - | |
| 843 | -= 1.5.6 = | |
| 844 | -- Improved "Add to Cart" and product recommendation intents for WooCommerce. | |
| 845 | -- Enhanced Brave Search intent for more accurate and structured results. | |
| 846 | -- Added an **Edit** button to the intent management section for easier adjustments. | |
| 847 | -- Fixed the Word document upload toolbar button for seamless functionality. | |
| 848 | - | |
| 849 | -= 1.5.5 = | |
| 850 | -- Chat transcripts now display in newest-to-oldest order and are mobile responsive. | |
| 851 | -- Updated various setting texts with clearer descriptions for better usability. | |
| 852 | -- Fixed issue with rate limit not working properly. | |
| 853 | -- Added Word document upload to the frontend toolbar for direct chatbot interface use. | |
| 854 | -- Improved chatbot's contextual response accuracy. | |
| 855 | -- Major enhancements to "Add to Cart," "Checkout," and "Chat with PDF via URL" intents. | |
| 856 | - | |
| 857 | -= 1.5.4 = | |
| 858 | -- Enhanced chat transcripts layout for improved readability, better formatting support (e.g., bold, italics), and inclusion of test agent names from **MxChat AI Agents**. | |
| 859 | -- Introduced **MxChat AI Agents**, now available free for Pro users for a limited time, providing a revolutionary way to test and deploy your chatbot. | |
| 860 | - | |
| 861 | -= 1.5.3 = | |
| 862 | -- Major bug fix to the similarity threshold comparison which prevented the chatbot from finding relevant content. | |
| 863 | - | |
| 864 | -= 1.5.2 = | |
| 865 | -- Enhanced checkout intent functionality to work more robustly, no longer requiring add-to-cart intent trigger. | |
| 866 | -- Fixed issue with send button not displaying properly on iPhone/iOS devices. | |
| 867 | -- Added admin control for similarity threshold matching to fine-tune relevant content results. | |
| 868 | - | |
| 869 | -= 1.5.1 = | |
| 870 | -- Vastly improved the ability for the chatbot to give contextually relevant responses from the knowledge database. | |
| 871 | -- Fixed the issue with loops in the lead capture intent. | |
| 872 | -- Updated the PDF upload icon in the frontend chatbot UI to a clearer design, now showing a PDF file icon. | |
| 873 | -- Enhanced the order history intent, recommendation intent, and product card intent for more robust and contextually relevant responses. | |
| 874 | - | |
| 875 | -= 1.5 = | |
| 876 | -- **Live Agent Transfer**: Seamless integration for live agent handoffs and AI chatbot switching. | |
| 877 | -- **PDF Toolbar**: Added PDF upload to the chatbot interface and knowledge base processing with cron jobs. | |
| 878 | - | |
| 879 | -= 1.4.6 = | |
| 880 | -- **Product Recommendation Intent**: Added personalized product recommendations based on order history, cart contents, and trending items. | |
| 881 | -- **Custom Chatbot Icon**: Users can upload custom PNG icons for a more personalized chatbot appearance. | |
| 882 | -- **Codeblock Copy Button**: Introduced a copy button for codeblocks to simplify copying code snippets. | |
| 883 | -- **Expanded Popular Questions**: Increased flexibility by allowing more than the default three popular questions. | |
| 884 | -- **CSS Compatibility Fixes**: Improved chatbot CSS for better theme compatibility. | |
| 885 | - | |
| 886 | -= 1.4.5 = | |
| 887 | -- **Fixed "Open Links in New Tab" Setting**: Resolved an issue where the setting to open links in a new tab was not functioning as expected. | |
| 888 | - | |
| 889 | -= 1.4.4 = | |
| 890 | -- **Custom Rate Limits**: Set different rate limits for logged-in and logged-out users. | |
| 891 | -- **PDF Intent Enhancements**: Added customizable trigger, success, and error messages, plus a max PDF page limit setting. | |
| 892 | -- **Improved Flexibility**: Greater control over chatbot behavior and user interactions. | |
| 893 | - | |
| 894 | -= 1.4.3 = | |
| 895 | -- **PDF Intent**: Added support for processing and analyzing PDF content via provided URLs using vector embeddings. | |
| 896 | -- **Compatibility Fix**: Fixed a rendering issue that prevented the chatbot from displaying in certain environments. | |
| 897 | - | |
| 898 | -= 1.4.2 = | |
| 899 | -- **Fixed Knowledge Search**: Fixed a bug impacting the ability to search knowledge database information. | |
| 900 | - | |
| 901 | -= 1.4.1 = | |
| 902 | -- **Fixed Intent Loading Issue**: Fixed a bug which prevented new intents from being shown on certain installs. | |
| 903 | - | |
| 904 | -= 1.4 = | |
| 905 | -- **Customizable Sensitivity Threshold**: Added support for individual sensitivity thresholds on each intent, offering more precise control over intent recognition. | |
| 906 | -- **Enhanced Usability Improvements**: Introduced a "Delete All" button for quick knowledgebase management, resolved activation key UI issues to prevent unnecessary re-activation, and improved chatbot viewport scrolling for better visibility of longer responses. | |
| 907 | - | |
| 908 | -= 1.3 = | |
| 909 | -- **Advanced Intent Recognition**: Introduced vector embedding for enhanced intent detection, improving chatbot responsiveness. | |
| 910 | -- **New Integrations**: Added **Brave Web Search**, **Brave Image Search**, and **DALL-E Image Generation** intents. | |
| 911 | -- **Security Update**: Minor update to unserialization handling for enhanced security. | |
| 912 | - | |
| 913 | -= 1.2.1 = | |
| 914 | -- **Product Card Display**: Added a dynamic product card for WooCommerce users, showing product image, price, and an "Add to Cart" button triggered by product-related keywords. | |
| 915 | -- Enhanced **Popular Questions** and **Pre-Chat Message** functionalities for improved user engagement and streamlined chat initiation. | |
| 916 | - | |
| 917 | -= 1.2 = | |
| 918 | -- Added **Popular Questions Buttons** with one free question and two available in the **Pro version**. | |
| 919 | -- Added **Inline Edit Button** to the Knowledge Database for easy content management. | |
| 920 | - | |
| 921 | -= 1.1.9 = | |
| 922 | -- Added integration with Claude (Anthropic) API (Pro feature) for advanced conversational models like `Claude 3.5 Sonnet` and `Claude 3 Haiku`. | |
| 923 | - | |
| 924 | -= 1.1.8 = | |
| 925 | -- Added integration with X.AI API (Pro feature) for advanced chat completions using models like `grok-beta`. | |
| 926 | -- Introduced new model selection dropdown that separates OpenAI and X.AI models, with X.AI models disabled for free users. | |
| 927 | -- Enhanced API key management, allowing users to input and manage both OpenAI and X.AI API keys in settings. | |
| 928 | - | |
| 929 | -= 1.1.7 = | |
| 930 | -* Added chat session persistence option for users to maintain conversations across visits for up to 24 hours. | |
| 931 | -* Updated navigation tabs CSS and scripts to prevent conflicts with other plugins. | |
| 932 | -* Rate limit settings are now available to all users, offering better control over chat usage. | |
| 933 | - | |
| 934 | -= 1.1.6 = | |
| 935 | -* Minor CSS update. | |
| 936 | - | |
| 937 | -= 1.1.5 = | |
| 938 | -* Fixed error when users didn't have WooCommerce it would return "Error communicating with server". | |
| 939 | - | |
| 940 | -== Upgrade Notice == | |
| 941 | - | |
| 942 | -= 3.2.1 = | |
| 943 | -Fixed Admin Testing Tab debug panel and web search transcript sources not displaying correctly. | |
| 944 | - | |
| 945 | -== License & Warranty == | |
| 946 | - | |
| 947 | -This plugin is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. | |
| 948 | - | |
| 949 | -This plugin is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. | |
| 783 | += 3.2.14 = | |
| 784 | +Adds the Editor Assistant, YouTube videos in the knowledge base with consent-safe in-chat embeds, independent Slack and Telegram live agent availability schedules, and the latest GPT-5.6 models. Also fixes a Knowledge Base edit data-loss bug, GPT-5 product and image search, and self-healing automatic transcript deletion — existing sites are unaffected until you turn the new features on. | |
| 950 | 785 | |
| 951 | 786 | == Credits == |
| 952 | 787 | |
| 953 | 788 | This plugin incorporates the following third-party library: |
