| @@ -1,20 +1,20 @@ | ||
| 1 | -=== MxChat - AI Chatbot & Content Generation for WordPress === | |
| 1 | +=== MxChat - AI Chatbot for WordPress with ChatGPT, Claude & Gemini === | |
| 2 | 2 | Contributors: mxchat |
| 3 | 3 | Author: [MxChat](https://mxchat.ai) |
| 4 | -Tags: ai chatbot, chatgpt, woocommerce, customer support, content generation | |
| 4 | +Tags: ai chatbot, chatgpt, woocommerce, customer support, live chat | |
| 5 | 5 | Requires at least: 5.0 |
| 6 | -Tested up to: 7.0 | |
| 6 | +Tested up to: 6.9 | |
| 7 | 7 | Requires PHP: 7.2 |
| 8 | -Stable tag: 3.2.8 | |
| 8 | +Stable tag: 3.0.7 | |
| 9 | 9 | License: GPLv2 or later |
| 10 | 10 | License URI: https://www.gnu.org/licenses/gpl-2.0.html |
| 11 | 11 | |
| 12 | -MxChat is the best free AI chatbot and content generation plugin for WordPress in 2026. 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 | +The best free AI chatbot plugin for WordPress. Train ChatGPT, Claude, Gemini, or Grok on your website content. WooCommerce ready with RAG knowledge base, live chat handoff, and 100+ AI models. | |
| 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 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. | |
| 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? |
| @@ -19,41 +19,37 @@ | ||
| 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 | |
| 24 | -✅ **Live Agent Handoff via Slack**: Seamlessly escalate from AI to human support when customers need personal assistance | |
| 25 | -✅ **Real-Time Debug Panel**: See exactly what your chatbot retrieves and triggers with our admin testing interface | |
| 26 | -✅ **Boost Sales with WooCommerce**: Product cards, cart management, and AI-powered shopping assistance | |
| 27 | -✅ **AI Content Generator**: Create full blog posts and landing pages with AI-generated images, SEO metadata, and real-time preview editing | |
| 28 | -✅ **Extensive Add-On Ecosystem**: Forms, moderation, recommendations, theme customization, and more | |
| 23 | +✅ **Train on Your Website Data**: Advanced RAG technology learns from sitemaps, PDFs, URLs, or manual input for ultra-relevant responses | |
| 24 | +✅ **Live Agent Handoff via Slack**: Seamlessly escalate from AI to human support when customers need personal assistance | |
| 25 | +✅ **Real-Time Debug Panel**: See exactly what your chatbot retrieves and triggers with our admin testing interface | |
| 26 | +✅ **Boost Sales with WooCommerce**: Product cards, cart management, and AI-powered shopping assistance | |
| 27 | +✅ **Extensive Add-On Ecosystem**: Forms, moderation, recommendations, theme customization, and more | |
| 29 | 28 | |
| 30 | -🎬 [Quick Setup with MxChat](https://www.youtube.com/watch?v=3BqoiyWaQiM) – Learn how to quickly setup and understand how your chatbot works | |
| 29 | +### 📦 Optional Premium Add-Ons | |
| 30 | +Extend the free plugin with these optional premium features: | |
| 31 | 31 | |
| 32 | -### 📦 Optional Premium Add-Ons | |
| 33 | -Extend the free plugin with these optional premium features: | |
| 32 | +- [Forms Action Add-On](https://mxchat.ai/forms-action/) – Capture leads and data with custom in-chat forms | |
| 33 | +- [WooCommerce Add-On](https://mxchat.ai/woocommerce/) – AI-powered shopping assistance and product recommendations | |
| 34 | +- [AI Theme Customizer Add-On](https://mxchat.ai/ai-theme-customizer/) – Instantly design chatbot themes with natural language | |
| 35 | +- [Multi-Bot Add-On](https://mxchat.ai/multi-bot/) – Run unlimited AI chatbots with custom knowledge and personalities | |
| 36 | +- [Image Analysis Add-On](https://mxchat.ai/image-analysis/) – Enable AI-powered image analysis and OCR inside chats | |
| 34 | 37 | |
| 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 | |
| 43 | - | |
| 44 | 38 | 👉 [Visit our website to view all add-ons](https://mxchat.ai) |
| 45 | 39 | |
| 46 | -## 🔥 What's New in Version 3.2.8 | |
| 40 | +## 🔥 What's New in Version 3.0.6 | |
| 47 | 41 | |
| 48 | -- **NEW: Total Chatbot Message Limit** — Set a single message cap for the whole chatbot across all users and roles per timeframe (hourly / daily / weekly / monthly), independent of the per-role limits — when both are configured, whichever is hit first stops the conversation. A live usage readout shows how much of the cap is used right now ("10 of 200 used · 190 left · resets in ~6 hours") with a one-click **Reset counter**. Both the global and per-role limits now also accept **Custom** values — any positive integer, not just the presets. Defaults to Unlimited, so existing installs are unchanged. | |
| 49 | -- **IMPROVED: Custom Provider & Azure OpenAI embeddings** — "Use custom provider for embeddings" now works end-to-end: both knowledge-base indexing and live queries use your endpoint's embedding model, so a fully local or Azure OpenAI stack retrieves correctly. Includes a new **Azure OpenAI quick-start** callout with the exact Base URL, API Key, Auth Scheme, and API Version. (If you already had custom embeddings enabled, re-index your knowledge base so the stored vectors are rebuilt with your model.) | |
| 50 | -- **FIXED: Feedback "Send" button visibility** — The helpful / not-helpful feedback **Send** button no longer renders as an invisible white-on-white block. It now fills with your chatbot's font color with a clearly legible label, and adapts to custom colors set via either the built-in color pickers or the MxChat Theme AI customizer. | |
| 42 | +- New: RAG Sources Limit slider - control how many knowledge base sources (3-10) are included in AI responses | |
| 43 | +- New: {visitor_name} placeholder support in Intro Message and AI Behavior settings for personalized greetings | |
| 44 | +- New: Added Claude Opus 4.6 and Claude Opus 4.5 models | |
| 45 | +- Fixed: Chat persistence OFF now correctly starts fresh AI context on page reload | |
| 46 | +- Deprecated: Removed all GPT-4 series, GPT-3.5 Turbo, and Claude 3.x models per provider deprecations | |
| 47 | +- Updated: Users on deprecated models auto-migrated to GPT-5.1/GPT-5 Mini or Claude Opus 4.6/Haiku 4.5 | |
| 51 | 48 | |
| 52 | 49 | ## Core Features That Set MxChat Apart |
| 53 | 50 | |
| 54 | 51 | 🟢 **100+ AI Models** – Access ChatGPT, Claude, Gemini, Grok, DeepSeek, and 100+ models from OpenRouter with a single plugin |
| 55 | -🟢 **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 | |
| 56 | 52 | 🟢 **Chat Transcripts Dashboard** – Review all conversations, analyze chat history, track user engagement, and see exactly which knowledge sources the AI used for each response |
| 57 | 53 | 🟢 **WooCommerce Product Training** – Train your AI chatbot on your entire product catalog including descriptions, pricing, SKUs, and categories for intelligent shopping assistance |
| 58 | 54 | 🟢 **Live Agent Handoff** – Seamlessly escalate conversations from AI to human support via Slack when customers need personal assistance |
| 59 | 55 | 🟢 **ACF Field Control** – Choose exactly which Advanced Custom Fields are included in your knowledge base—perfect for excluding private notes or internal data |
| @@ -60,12 +56,10 @@ | ||
| 60 | 56 | 🟢 **Advanced Action Recognition** – Smart vector embedding system understands user intent and triggers lead capture, appointments, redirects, and custom actions automatically |
| 61 | 57 | 🟢 **Document Processing** – Let visitors upload and chat with PDFs and Word documents directly on your frontend |
| 62 | 58 | 🟢 **Pinecone Vector Storage** – Optional lightning-fast knowledge retrieval for large datasets and enterprise-scale deployments |
| 63 | 59 | 🟢 **Web Search Integration** – Brave search provides real-time information beyond your knowledge base |
| 64 | -🟢 **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 | |
| 65 | -🟢 **Image Generation** – OpenAI GPT Image and Google Imagen for visual content creation within chat conversations | |
| 66 | -🟢 **Streaming Responses** – Real-time response streaming for OpenAI, Claude, and Grok models for the fastest possible chat experience | |
| 67 | -🟢 **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 | |
| 60 | +🟢 **Image Generation** – DALL-E integration for visual content creation within chat conversations | |
| 61 | +🟢 **Streaming Responses** – Real-time response streaming for OpenAI, Claude, and Grok models for the fastest possible chat experience | |
| 68 | 62 | |
| 69 | 63 | ## Choose from 100+ Premium AI Models |
| 70 | 64 | Access the world's most advanced AI models based on your specific needs: |
| 71 | 65 | |
| @@ -70,85 +64,37 @@ | ||
| 70 | 64 | Access the world's most advanced AI models based on your specific needs: |
| 71 | 65 | |
| 72 | 66 | **OpenRouter**: 100+ models from multiple providers with a single API key – including OpenAI, Anthropic, Google, Meta, Mistral, and more! |
| 73 | 67 | **OpenAI**: |
| 74 | -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 | |
| 68 | +GPT-5.2, GPT-5.1 Chat Latest, GPT-5.1, GPT-5, GPT-5-mini, GPT-5-nano | |
| 75 | 69 | **Anthropic Claude**: |
| 76 | -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 | |
| 70 | +Claude Opus 4.6, Claude Opus 4.5, Claude Sonnet 4.5, Claude Opus 4.1, Claude Haiku 4.5, Claude 4 Sonnet, Claude 4 Opus | |
| 77 | 71 | **X.AI**: |
| 78 | -**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 | |
| 72 | +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)** | |
| 79 | 73 | **Google Gemini**: |
| 80 | -Gemini 3.5 Flash, Gemini 3.1 Pro, Gemini 3 Flash, Gemini 3.1 Flash-Lite, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash-Lite | |
| 74 | +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 | |
| 81 | 75 | **DeepSeek**: |
| 82 | 76 | DeepSeek V3 |
| 83 | 77 | |
| 84 | -## Lead Management Dashboard — Turn Chat Traffic Into a Real Lead List | |
| 78 | +## Supercharge Your eCommerce with AI | |
| 85 | 79 | |
| 86 | -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. | |
| 80 | +Transform online shopping with intelligent assistance through direct WooCommerce integration: | |
| 87 | 81 | |
| 88 | -**What You Get:** | |
| 82 | +- Engage visitors in real time with product-aware conversations | |
| 83 | +- Recommend products and upsell with native WooCommerce product cards | |
| 84 | +- Access order history, inventory, and customer data seamlessly | |
| 85 | +- Convert passive users into paying customers with live support | |
| 86 | +- Handle order inquiries and status updates directly through chat | |
| 89 | 87 | |
| 90 | -- **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 | |
| 91 | -- **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 | |
| 92 | -- **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) | |
| 93 | -- **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 | |
| 94 | -- **One-Click View Conversation** — jump from any lead straight into their latest full conversation in the transcripts viewer | |
| 95 | -- **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 | |
| 96 | -- **Clean, Responsive, Native** — works beautifully on desktop, tablet, and phone with the same polished dashboard feel as the rest of MxChat | |
| 97 | -- **Zero Setup, Zero Migration** — uses your existing chat data, no new database tables, no configuration — turn on lead capture and the dashboard just works | |
| 98 | - | |
| 99 | -**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. | |
| 100 | - | |
| 101 | -## AI Content Generator — Create Blog Posts & Landing Pages with AI | |
| 102 | - | |
| 103 | -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. | |
| 104 | - | |
| 105 | -**How It Works:** | |
| 106 | - | |
| 107 | -1. **Describe Your Content** — Enter a topic, title, or detailed prompt and choose between a blog post or landing page layout | |
| 108 | -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 | |
| 109 | -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 | |
| 110 | -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 | |
| 111 | -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 | |
| 112 | - | |
| 113 | -**Key Content Generator Features:** | |
| 114 | - | |
| 115 | -- Choose from multiple AI models for content generation (GPT-5, Claude, Gemini, Grok, and more) | |
| 116 | -- AI-generated images placed directly into your content with automatic media library uploads | |
| 117 | -- SEO title and meta description generation for search engine optimization | |
| 118 | -- Built-in SEO analysis with real-time scoring and one-click AI auto-optimization | |
| 119 | -- Fullwidth and standard layout options with automatic theme compatibility | |
| 120 | -- Content history to revisit and manage previously generated posts | |
| 121 | -- Works with popular page builders and themes including Elementor, Bricks, Divi, Astra, Kadence, and more | |
| 122 | -- 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 | |
| 123 | - | |
| 124 | -## MxChat Anywhere — Deploy Your Chatbot on Any Website | |
| 125 | - | |
| 126 | -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. | |
| 127 | - | |
| 128 | -**Key Features:** | |
| 129 | - | |
| 130 | -- One script tag to add your chatbot to any site — no coding or framework required | |
| 131 | -- Full style isolation via Shadow DOM so host page CSS never breaks your chatbot | |
| 132 | -- All your MxChat settings carry over automatically — colors, themes, quick questions, email collection, streaming, and more | |
| 133 | -- Multi-bot support lets you deploy different chatbot configurations on different sites | |
| 134 | -- Secure domain whitelisting and API key authentication prevent unauthorized usage | |
| 135 | -- Lightweight vanilla JS widget with zero dependencies — no jQuery needed on the target site | |
| 136 | - | |
| 137 | -**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. | |
| 138 | - | |
| 139 | 88 | ## Powerful Add-On Ecosystem |
| 140 | 89 | |
| 141 | -**Pro Add-Ons:** | |
| 142 | -🟢 **MCP Server** – Expose your MxChat install as a Model Context Protocol server so Claude, ChatGPT, and Claude Code can list transcripts, push knowledge, and inspect bots through a JSON-RPC 2.0 endpoint with OAuth + bearer auth — no per-message fees, no middleman API. Includes a WooCommerce extension for product, order, and customer lookups. | |
| 143 | -🟢 **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 | |
| 90 | +**Pro Add-Ons:** | |
| 144 | 91 | 🟢 **Multi-Bot Manager** – Create and manage multiple specialized chatbots with dedicated knowledge databases for different purposes (support, sales, technical, etc.) |
| 145 | 92 | 🟢 **Video Generation** – Generate stunning AI videos using Google's Veo 2 and Veo 3 models with audio support and multiple aspect ratios |
| 146 | 93 | 🟢 **Admin Assistant** – ChatGPT-like interface in WordPress admin with thread management and image generation |
| 147 | -🟢 **Chat Themes** – Visual design editor with AI-powered chatbot theme generation from natural language | |
| 94 | +🟢 **Theme Customizer** – Visual design editor with AI-powered chatbot theme generation from natural language | |
| 148 | 95 | 🟢 **MxChat Forms** – Create chatbot-triggered forms for lead capture and support tickets |
| 149 | 96 | 🟢 **Chat Moderation** – Advanced security with email/IP banning and content filtering |
| 150 | -🟢 **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 | |
| 151 | 97 | 🟢 **Perplexity Integration** – Real-time web search with authoritative, well-sourced responses |
| 152 | 98 | 🟢 **Migration Tool** – Seamlessly switch embedding models and vector databases without losing data, with batch processing and real-time progress tracking |
| 153 | 99 | |
| 154 | 100 | ## 📱 Mobile-Friendly & Fully Customizable |
| @@ -169,31 +115,18 @@ | ||
| 169 | 115 | ## 🆓 Start with MxChat’s Powerful Free Plan |
| 170 | 116 | |
| 171 | 117 | 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: |
| 172 | 118 | |
| 173 | -- Access all AI models from 5 major providers | |
| 174 | -- AI Content Generator for blog posts and landing pages with SEO scoring and AI auto-optimization | |
| 175 | -- Train chatbot on unlimited website content | |
| 176 | -- Loops email capture for lead generation | |
| 177 | -- Web search and image generation capabilities | |
| 178 | -- Real-time admin debug panel | |
| 179 | -- Chat transcript review and export | |
| 180 | -- RAG support & contextual awareness | |
| 119 | +- Access all AI models from 5 major providers | |
| 120 | +- Train chatbot on unlimited website content | |
| 121 | +- Loops email capture for lead generation | |
| 122 | +- Web search and image generation capabilities | |
| 123 | +- Real-time admin debug panel | |
| 124 | +- Chat transcript review and export | |
| 125 | +- RAG support & contextual awareness | |
| 181 | 126 | |
| 182 | 127 | 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. |
| 183 | 128 | |
| 184 | -== Developer Hooks & Filters == | |
| 185 | - | |
| 186 | -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/). | |
| 187 | - | |
| 188 | -= mxchat_before_process_post = | |
| 189 | - | |
| 190 | -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. | |
| 191 | - | |
| 192 | -= mxchat_system_instructions = | |
| 193 | - | |
| 194 | -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. | |
| 195 | - | |
| 196 | 129 | ## ✅ Get Started with MxChat AI Chatbot Today |
| 197 | 130 | |
| 198 | 131 | 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. |
| 199 | 132 | |
| @@ -225,9 +158,9 @@ | ||
| 225 | 158 | == Frequently Asked Questions == |
| 226 | 159 | |
| 227 | 160 | = What AI models does MxChat support? = |
| 228 | 161 | |
| 229 | -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 3.5 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. | |
| 162 | +MxChat supports 100+ AI models including OpenAI GPT-5.2, GPT-5.1, GPT-5, GPT-5 Mini, Anthropic Claude Opus 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. | |
| 230 | 163 | |
| 231 | 164 | = How do I get API keys for the AI chatbot? = |
| 232 | 165 | |
| 233 | 166 | 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. |
| @@ -328,152 +261,8 @@ | ||
| 328 | 261 | *(Note: Screenshots will be added in future updates)* |
| 329 | 262 | |
| 330 | 263 | == Changelog == |
| 331 | 264 | |
| 332 | -= 3.2.8 - June 4, 2026 = | |
| 333 | -* New: Total chatbot message limit — set a single message cap across all users and roles per timeframe (hourly/daily/weekly/monthly), independent of the per-role limits, with a live usage readout ("10 of 200 used · 190 left · resets in ~6 hours") and a one-click Reset to zero the count mid-window. Both the global and per-role limits now also accept Custom values (any positive integer, not just the 1–100 presets). Defaults to Unlimited, so existing installs are unchanged. | |
| 334 | -* Improved: Custom Provider & Azure OpenAI — "use custom provider for embeddings" now works end-to-end (both knowledge-base indexing and live queries use your endpoint's embedding model), plus a new Azure OpenAI quick-start callout with the exact Base URL, API Key, Auth Scheme, and API Version. NOTE: if you already had custom embeddings enabled, re-index your knowledge base (Knowledge → Process Selected) so vectors are rebuilt with your model. | |
| 335 | -* Fixed: The helpful/not-helpful feedback "Send" button no longer renders as an invisible white-on-white block — it fills with your chatbot's font color and adapts to colors set via the built-in pickers or the MxChat Theme AI customizer. | |
| 336 | - | |
| 337 | -= 3.2.7 - May 29, 2026 = | |
| 338 | -* New: Guided onboarding for new users. First-time setup is now a step-by-step wizard — pick your AI model and add your key inline, set how the chatbot should behave, choose an embedding model, optionally add a knowledge base, then finish on a “What’s next” screen that links straight to the in-dashboard test chat, your display settings, and copy-paste embed shortcodes. Reopen it any time from Settings → Tutorials. | |
| 339 | -* New: Latest AI models, with automatic recovery when providers change theirs. Added Claude Opus 4.8 and the current Google Gemini 3.x lineup (Gemini 3.5 Flash, 3.1 Pro, 3 Flash, 3.1 Flash-Lite and more). Models that providers retired or changed are now handled for you: the discontinued Gemini 3 Pro and the retired Grok 2 have been replaced, and Claude Opus 4.7 / 4.8 no longer error on send (Anthropic dropped the temperature setting on those). Any site pinned to a discontinued model is switched to a working one automatically. | |
| 340 | -* New: Reliable first message behind page caches. The chat widget now fetches a fresh security token for each message instead of trusting cached page HTML, eliminating the intermittent “Access denied” error on the first message under full-page caching (WP Rocket, LiteSpeed, FlyingPress, W3 Total Cache, Cloudflare APO). | |
| 341 | -* Improved: More resilient replies. Both streaming and standard chat now automatically retry transient provider problems (overload, rate-limit, 5xx) before showing an error, and streaming fallbacks appear in a second or two instead of leaving visitors on a spinner — across every supported provider. | |
| 342 | -* Improved: Accessibility and polish. The floating chat button is now fully keyboard-operable (Tab to focus, Enter or Space to open, Esc to close, and focus returns to the button on close — WCAG 2.1 Level A), alongside a range of admin interface refinements. | |
| 343 | - | |
| 344 | -= 3.2.6 - May 21, 2026 = | |
| 345 | -* New: Custom Provider (OpenAI-compatible) — point MxChat at any OpenAI-compatible endpoint (Ollama, LM Studio, vLLM, llama.cpp, Azure OpenAI) under MxChat → API Keys, with opt-in routing for `/v1/embeddings` and `/v1/images/generations` through the same endpoint. Includes a one-click **Test Connection** button and a new "Custom / Local" category in the model picker. | |
| 346 | -* New: Image Quality control for OpenAI GPT Image — new **Image Quality** dropdown in the Content Generator (Auto / Low / Medium / High), passed as the `quality` parameter to OpenAI's image API. Auto-disables when a non-GPT-Image model is selected. | |
| 347 | -* New: Latest-generation models added to the picker — Claude Opus 4.7, GPT-5.5, and GPT Image 2 are now selectable from the Select AI Model modal, each tagged "Latest Flagship" at the top of its provider group. | |
| 348 | -* New: ACF PDF auto-indexing — any ACF File/Image field (including PDFs nested in repeater, group, and flexible-content fields) now has its full PDF text extracted into the knowledge base alongside the post, not just the link. Opt-in per import batch via a new checkbox (default off), with per-post PDF counts reported during import, files over 25 MB safely skipped (adjustable via `mxchat_acf_pdf_max_bytes`), and a separate Knowledge → Auto-Sync toggle so editor saves don't re-parse unchanged PDFs. Extracted text is cached per attachment so re-syncs stay fast. | |
| 349 | -* New: `DELETE /wp-json/mxchat/v1/transcripts` endpoint — bulk-delete chat sessions by session_id (bearer-token auth, capped at 1000/call) with optional cascade to translations and URL-click tracking. Useful for GDPR right-to-erasure flows and automated cleanup. | |
| 350 | -* New: `mxchat_embedding_chunk_metadata` filter — developers can now enrich the per-chunk metadata that gets stored alongside every embedding (in both Pinecone and the WordPress DB). The filter receives the metadata array, the chunk text, and a context array (`bot_id`, `content_type`, `source_url`, `part_index`, `part_total`), and chunks now also expose alias keys (`source`, `part_index`, `part_total`) for cross-tool interoperability. | |
| 351 | -* Improved: Page-cache compatibility — MxChat now auto-tells WP Rocket, LiteSpeed, W3 Total Cache, FlyingPress, and WP Super Cache to never cache the chat AJAX endpoint, and a new "Page Cache Compatibility" card under Settings → Optimization & Diagnostics shows per-plugin status with exclusion strings for Cloudflare APO (one-click Copy buttons included). | |
| 352 | -* Fixed: Resolves intermittent "Access denied" error when sending the first chat message on sites running a full-page cache plugin (WP Rocket, LiteSpeed Cache, FlyingPress, W3 Total Cache, Cloudflare APO, etc.). The chat-send (and stream-send, plus PDF/Word upload) now waits for the page-cache nonce refresh to complete before firing, eliminating a race condition that affected the first message of each session. | |
| 353 | -* Fixed: Print preview was blank on every page that had MxChat installed — a stale `@media print` rule from the old "Print Conversation" feature (replaced by "Download Transcript" in v3.2.5) was hiding all page content on print. The dead rule has been removed; printing any page now works normally regardless of whether MxChat is loaded. | |
| 354 | -* New: End-of-session satisfaction rating — after two bot replies and a brief idle, the chat widget shows a "Was this helpful?" prompt with 👍 / 👎 thumbs and an optional feedback box, rendering inside a real bot bubble that inherits your chatbot's theme. Toggle on/off site-wide under Settings → Chatbot → Behavior, with configurable idle timeout (5–600s) and customizable prompt text. Ratings surface in admin as a badge on every Transcripts row, sort options, a **Satisfaction (last 30 days)** dashboard card, and a Feedback row in each session's details drawer. | |
| 355 | - | |
| 356 | -= 3.2.5 - May 12, 2026 = | |
| 357 | -* New: REST API with bearer-token auth — `GET /wp-json/mxchat/v1/transcripts` (read), `POST /wp-json/mxchat/v1/knowledge` (push), `DELETE /wp-json/mxchat/v1/transcripts` (bulk-delete sessions with cascade to translations and URL-click tracking, capped at 1000 session_ids/call), plus a public `/health` endpoint; disabled by default, with constant-time token comparison and prepared statements throughout. | |
| 358 | -* New: API Access admin page styled to match the rest of the MxChat admin UI — sidebar navigation, branded header, themed buttons, status pill, copy-to-clipboard on newly rotated tokens, and a "Last rotated" indicator. | |
| 359 | -* New: Chat-widget header redesign — replaced the minimize arrow with a stroke-based X-close icon and a 3-dot kebab menu (keyboard-accessible dropdown), with refined alignment so the title, "AI Agent" pill, and equal-sized 32×32 icon buttons share a single 48px baseline. | |
| 360 | -* New: **Download Transcript** menu item (replaces "Print conversation") — saves a clean Markdown file of the conversation with sender labels and a timestamped header, toggleable via `mxchat_options[print_button_enabled]`. | |
| 361 | -* New: Sidebar ordering — API Access now sits directly above Pro & Extensions, keeping Pro & Extensions pinned as the trailing CTA via a later `admin_menu` priority. | |
| 362 | -* New: Content Generator now writes Rank Math / Yoast / AIOSEO SEO-title meta and syncs each inline `<img alt="...">` into the attachment's `_wp_attachment_image_alt` postmeta, so SEO plugins, schema markup, and the media library see the alt text instead of only the inline body HTML. | |
| 363 | -* New: Transcript retention — "Custom Retention (Days)" field (1–3650) under Transcripts settings; the daily cron sweep deletes older transcripts with cascade to translations and URL-click tracking, capped at 5000 sessions per run, with a new `mxchat_transcript_retention_days` filter for programmatic overrides. | |
| 364 | -* Fixed: 3-dot header dropdown menu now inherits the bot bubble's colors instead of being hardcoded white/black — no more white-on-white "ghost menu" when using a dark bubble theme. | |
| 365 | - | |
| 366 | -= 3.2.4 - May 3, 2026 = | |
| 367 | -- Fixed: WooCommerce product Short Description Visual tab broken by a 404 on the Gutenberg meta-box script | |
| 368 | -- Fixed: User's last message now scrolls to the top of the chat after streaming replies, matching non-streaming behavior | |
| 369 | - | |
| 370 | -= 3.2.3 - April 29, 2026 = | |
| 371 | -- New: Embedding model switch protection — warning dialog when changing embedding models with content already embedded, plus a persistent admin notice while the active and selected models don't match. Each new embedding is now stamped with the model that produced it (KB, actions, action phrases, and Pinecone metadata) so mismatches are detectable | |
| 372 | -- Improved: Landing Page Generator now plans more sections and writes substantially more copy per section, producing fuller, more conversion-ready pages by default | |
| 373 | -- Fixed: Landing Page "Full Width" option not honored on WordPress block themes (Twenty Twenty-Two through Twenty Twenty-Five) — content was constrained by the theme.json layout system | |
| 374 | -- Fixed: Chatbot citing manually submitted knowledge entries with internal `mxchat://` placeholder URLs — placeholders are now correctly treated as manual entries with no citation across both WordPress-DB and Pinecone retrieval paths | |
| 375 | - | |
| 376 | -= 3.2.2 - April 21, 2026 = | |
| 377 | -- NEW: Lead Management Dashboard — dedicated Leads tab inside Transcripts that deduplicates captured emails into a single list with conversation count, last-seen, and the page that captured them. Includes top-pages analytics, search + date/status/page filters, bulk delete with two-step confirm, CSV export (email-only or email + name), and one-click "View convo" to jump to each lead's latest conversation. | |
| 378 | -- Fixed: Orphaned Pinecone chunk vectors left behind when posts or products were unpublished, trashed, deleted, or had their slugs renamed — deletion is now chunk-aware across all sync paths | |
| 379 | -- Fixed: Source count and chunk count settings were being ignored on certain paths and silently fell back to default values — the configured values now apply everywhere | |
| 380 | - | |
| 381 | -= 3.2.1 - April 17, 2026 = | |
| 382 | -- Fixed: Admin Testing Tab debug panel not displaying similarity scores, action matches, or source data — including when web search + streaming are both enabled | |
| 383 | -- Fixed: Web search responses (streaming and non-streaming) not saving RAG context to chat transcripts, causing the "sources" link to be missing | |
| 384 | - | |
| 385 | -= 3.2.0 - April 15, 2026 = | |
| 386 | -- Added: `mxchat_similarity_results` filter hook after similarity search completes, allowing add-ons to access matched sources and their URLs | |
| 387 | -- Removed: `data-no-optimize` attribute injection on MxChat CSS/JS tags, which was conflicting with third-party cache and optimization plugins | |
| 388 | - | |
| 389 | -= 3.1.9 - April 7, 2026 = | |
| 390 | -- Fixed: Session ownership issues that were causing "session expired" errors | |
| 391 | - | |
| 392 | -= 3.1.8 - April 6, 2026 = | |
| 393 | -- New: Loading indicator displayed while chat is initializing | |
| 394 | -- New: Individual trigger phrase embeddings — each key phrase now gets its own vector for more accurate action matching | |
| 395 | -- Improved: Existing actions remain fully backwards compatible with grouped legacy phrases | |
| 396 | -- New: Admin Testing Tab - embedded chatbot replica with real-time debug panel showing similarity scores, action matches, approved URLs, system prompt, and debug log | |
| 397 | -- Improved: "Delete All" in Knowledge Base now respects the active content type filter — only deletes the filtered type (e.g. Pages) instead of everything | |
| 398 | - | |
| 399 | -= 3.1.7 - April 1, 2026 = | |
| 400 | -- Fixed: Chat history not appearing for returning visitors until first message sent when chat persistence is enabled and email collection is off | |
| 401 | -- Fixed: Lead capture form not displaying for new visitors when email collection is enabled | |
| 402 | -- Fixed: Editing legacy manual knowledge base entries deleting all other manual entries sharing the same source URL | |
| 403 | -- New: Google Drive PDF links are now automatically converted to direct downloads for knowledge base import | |
| 404 | - | |
| 405 | -= 3.1.6 - March 30, 2026 = | |
| 406 | -- Fixed: Pre-chat popup reappearing on every page refresh — it now stays dismissed for 24 hours | |
| 407 | -- Fixed: Links with certain special characters in URLs being cut off | |
| 408 | -- Fixed: Chat history not loading for returning visitors | |
| 409 | -- Fixed: Links displaying as plain text instead of clickable links in chat responses | |
| 410 | - | |
| 411 | -= 3.1.5 - March 25, 2026 = | |
| 412 | -- Improved: Lowered default RAG sources limit from 6 to 3 to reduce token usage for users on lower-tier API plans | |
| 413 | -- Improved: Added per-source chunk cap of 5 to prevent any single document from dominating context | |
| 414 | -- New: RAG Chunks Limit setting — control max total chunks sent to AI (range 8–20, default 15) to balance context quality and token cost | |
| 415 | -- New: Page-level chatbot visibility — show, hide, or use global setting per page/post from the meta box | |
| 416 | -- New: Frontend debugger and transcripts now show actual sources and chunks used counts | |
| 417 | - | |
| 418 | -= 3.1.4 - March 22, 2026 = | |
| 419 | -- New: Added support for OpenAI GPT-5.4, GPT-5.4 Mini, GPT-5.4 Nano, and GPT-5.3 Chat models | |
| 420 | -- New: Edit Default Prompt — customize the AI system prompt for blog posts and landing pages from the Content page, saved per type across sessions | |
| 421 | -- New: Knowledge base entries can be edited inline with automatic re-chunking and re-embedding (works with both database and Pinecone) | |
| 422 | -- New: Sitemap import now supports PDF URLs — bulk import PDFs via XML sitemap | |
| 423 | -- Improved: Performance updates and bug fixes | |
| 424 | -- Fixed: Clear chat session in MxChat debugger now fully clears chat sessions and context history | |
| 425 | - | |
| 426 | -= 3.1.3 - March 16, 2026 = | |
| 427 | -- 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 | |
| 428 | -- New: Chat teaser pop-up message now supports multiple lines. | |
| 429 | -- Improved: Session cookies and tracking now deferred until first user interaction — passive visitors no longer trigger session creation or AJAX calls | |
| 430 | -- Improved: Markdown table rendering with column alignment, responsive scrolling, and alternating row styling | |
| 431 | - | |
| 432 | -= 3.1.2 - March 13, 2026 = | |
| 433 | -- New: Per-check AI fix buttons — hover any failing SEO check to see a sparkle icon that fixes just that item individually | |
| 434 | -- New: SEO dashboard now has row checkboxes with "Optimize Selected" to batch-optimize posts (requires Advanced Content Editor add-on) | |
| 435 | -- Improved: "AI Optimize" button renamed to "Optimize All" for clarity | |
| 436 | -- Improved: SEO modal now includes a "View Page" link and per-check AI fix buttons are always visible | |
| 437 | -- Improved: Post type dropdown now dynamically includes custom post types like WooCommerce Products | |
| 438 | -- 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 | |
| 439 | -- Fixed: Chat transcripts not saving bot responses containing emojis due to database table using utf8mb3 charset — upgraded to utf8mb4 | |
| 440 | -- Fixed: WooCommerce product cards now display with image, price, and button in chat transcripts | |
| 441 | -- Fixed: "Optimize All" now runs SEO fixes sequentially to prevent race conditions — previously internal links and other content-modifying fixes could overwrite each other | |
| 442 | -- Upgraded: Image generation replaced deprecated DALL-E 3 with GPT Image (OpenAI) and added Gemini Imagen 4 action | |
| 443 | - | |
| 444 | -= 3.1.1 - March 4, 2026 = | |
| 445 | -- New: Slack agents can now transfer users back to AI mode by typing `!endchat` in the channel | |
| 446 | -- 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 | |
| 447 | -- New: SEO analysis panel with real-time scoring for posts and pages in the Content section | |
| 448 | -- New: AI Auto-Optimize — one-click AI fixes for meta descriptions, SEO titles, and URL slugs with configurable check selection | |
| 449 | -- New: Google Search Console integration (Pro) — per-page impressions, clicks, CTR, and top search queries directly in the Content editor | |
| 450 | -- New: SEO optimize settings — choose which checks AI Optimize will run from Content > Settings | |
| 451 | -- 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 | |
| 452 | -- Fixed: Security scanner false-positives flagging `file_put_contents` as malware — replaced with `WP_Filesystem` API for transcript and PDF temp files | |
| 453 | -- Improved: PDF parser library now lazy-loaded on demand instead of on every page request | |
| 454 | - | |
| 455 | - | |
| 456 | -= 3.1.0 - March 1, 2026 = | |
| 457 | -- Fixed: Bulk deleting selected knowledge base entries with chunked content causing network timeout error when using Pinecone | |
| 458 | -- Fixed: Manually entered knowledge base content not being used for AI context despite having high similarity scores | |
| 459 | -- Fixed: Chat input remaining blocked after live agent handoff (Slack/Telegram) | |
| 460 | -- 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 | |
| 461 | -- Fixed: Shortcode stripping silently losing all content on pages with large or deeply nested shortcodes (e.g. WPBakery/Visual Composer) due to regex backtracking | |
| 462 | -- New: Added `mxchat_before_process_post` filter hook to allow developers to modify post data before knowledge base processing | |
| 463 | -- New: Added `mxchat_system_instructions` filter hook and shortcode support in system prompt for dynamic data injection | |
| 464 | - | |
| 465 | -= 3.0.9 - February 24, 2026 = | |
| 466 | -- 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 | |
| 467 | -- New: Advanced Content Editor premium add-on — smart internal linking, AI image management, and per-field AI meta generation | |
| 468 | -- New: Dynamic post type filtering in knowledge database dropdown — automatically pulls in all registered post types | |
| 469 | -- Improved: Compatibility with popular optimization and caching plugins | |
| 470 | - | |
| 471 | -= 3.0.8 - February 20, 2026 = | |
| 472 | -- New: Debug & optimization tools with log viewer, settings export, and reset options | |
| 473 | -- New: Added Claude Sonnet 4.6 model | |
| 474 | -- Improved: Performance optimizations and caching plugin compatibility | |
| 475 | - | |
| 476 | 265 | = 3.0.7 - February 15, 2026 = |
| 477 | 266 | - New: Performance optimization |
| 478 | 267 | - Fixed: GPT-5.1 Chat Latest model returning API error when web search was disabled |
| 479 | 268 | |
| @@ -1009,10 +798,11 @@ | ||
| 1009 | 798 | * Fixed error when users didn't have WooCommerce it would return "Error communicating with server". |
| 1010 | 799 | |
| 1011 | 800 | == Upgrade Notice == |
| 1012 | 801 | |
| 1013 | -= 3.2.8 - June 4, 2026 = | |
| 1014 | -Rate limits gain a whole-chatbot total message cap (single ceiling across all users and roles, default Unlimited so existing installs are unchanged) with a live "X of Y used" usage readout, a one-click Reset, and a new "Custom…" option for setting any value beyond the 1–100 presets on both the global and per-role limits. Also fixes custom-provider embeddings end-to-end so indexing and queries use the same model (re-index your knowledge base if you had this on), adds an Azure OpenAI quick-start guide, and fixes the feedback "Send" button rendering as an invisible white-on-white block. | |
| 802 | += 3.0.7 = | |
| 803 | +- New: Performance optimization | |
| 804 | +- Fixed: GPT-5.1 Chat Latest model returning API error when web search was disabled | |
| 1015 | 805 | |
| 1016 | 806 | == License & Warranty == |
| 1017 | 807 | |
| 1018 | 808 | 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. |
