mxchat-basic / readme.txt

readme.txt in MxChat – AI Chatbot & Content Generation for WordPress 3.2.5, at readme.txt

1,011 lines 75.5 KB

Raw Download Zip

1	=== MxChat - AI Chatbot & Content Generation for WordPress ===
2	Contributors: mxchat
3	Author: [MxChat](https://mxchat.ai)
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: 3.2.5
9	License: GPLv2 or later
10	License URI: https://www.gnu.org/licenses/gpl-2.0.html
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.
13
14	== Description ==
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.
17
18	[Documentation](https://mxchat.ai/documentation/) \| [Demo Videos](https://www.youtube.com/@MxChat/videos)
19
20	## Why Choose MxChat as Your WordPress AI Chatbot?
21
22	�
23	6 Major AI Providers in One Plugin: OpenRouter, OpenAI GPT, Claude, Gemini, xAI Grok, and DeepSeek - switch between 100+ models instantly
24	�
25	Train on Your Website Data: Advanced RAG technology learns from sitemaps, PDFs, URLs, or manual input for ultra-relevant responses
26	�
27	Live Agent Handoff via Slack: Seamlessly escalate from AI to human support when customers need personal assistance
28	�
29	Real-Time Debug Panel: See exactly what your chatbot retrieves and triggers with our admin testing interface
30	�
31	Boost Sales with WooCommerce: Product cards, cart management, and AI-powered shopping assistance
32	�
33	AI Content Generator: Create full blog posts and landing pages with AI-generated images, SEO metadata, and real-time preview editing
34	�
35	Extensive Add-On Ecosystem: Forms, moderation, recommendations, theme customization, and more
36
37	🎬 [Quick Setup with MxChat](https://www.youtube.com/watch?v=3BqoiyWaQiM) – Learn how to quickly setup and understand how your chatbot works
38
39	### 📦 Optional Premium Add-Ons
40	Extend the free plugin with these optional premium features:
41
42	- [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
43	- [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
44	- [Forms Action Add-On](https://mxchat.ai/forms-action/) – Capture leads and data with custom in-chat forms
45	- [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
46	- [AI Chatbot Theme Customizer Add-On](https://mxchat.ai/ai-theme-customizer/) – Instantly design chatbot themes with natural language using AI
47	- [Multi-Bot Add-On](https://mxchat.ai/multi-bot/) – Run unlimited AI chatbots with custom knowledge and personalities
48	- [Image Analysis Add-On](https://mxchat.ai/image-analysis/) – Enable AI-powered image analysis and OCR inside chats
49
50	👉 [Visit our website to view all add-ons](https://mxchat.ai)
51
52	## 🔥 What's New in Version 3.2.5
53
54	- NEW: REST API — Bearer-token-authenticated endpoints to read chat transcripts (`GET /wp-json/mxchat/v1/transcripts`), push content into the knowledge base (`POST /wp-json/mxchat/v1/knowledge`), and bulk-delete sessions (`DELETE /wp-json/mxchat/v1/transcripts`) from external tools — analytics dashboards, automations (n8n / Zapier / Make), data exports, GDPR right-to-erasure flows, custom RAG pipelines, or your own agents. Disabled by default; generate a token from the new MxChat → API Access admin page when you're ready to use it. Includes filters for date range, role, session, and "no-RAG-context" answers (perfect for finding gaps in your knowledge base).
55	- NEW: Redesigned chat-widget header — A clean stroke-based X-close icon replaces the old minimize arrow, paired with a 3-dot kebab menu that opens a keyboard-accessible dropdown for future actions. Title, "AI Agent" pill, and 32×32 icon buttons sit on a single tidy baseline for a more modern, native feel.
56	- NEW: Download Transcript — A new menu item in the chat header saves the conversation as a clean Markdown file with sender labels and a timestamp, replacing the old print-dialog flow. Toggleable from MxChat settings.
57	- NEW: Custom Transcript Retention — Set any retention window from 1 to 3650 days under Transcripts settings; the daily cron sweep deletes older transcripts and cascades the delete to translations and URL-click tracking. Capped at 5000 sessions per run for large-site safety, with a new `mxchat_transcript_retention_days` filter for developer overrides.
58	- IMPROVED: Content Generator SEO — Generated posts now write the SEO title to Rank Math, Yoast, and AIOSEO metadata, and inline `<img alt="...">` text is synced into each attachment's `_wp_attachment_image_alt` so the media library, schema markup, and SEO plugins all pick up the right alt text.
59
60	## Core Features That Set MxChat Apart
61
62	🟢 100+ AI Models – Access ChatGPT, Claude, Gemini, Grok, DeepSeek, and 100+ models from OpenRouter with a single plugin
63	🟢 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
64	🟢 Chat Transcripts Dashboard – Review all conversations, analyze chat history, track user engagement, and see exactly which knowledge sources the AI used for each response
65	🟢 WooCommerce Product Training – Train your AI chatbot on your entire product catalog including descriptions, pricing, SKUs, and categories for intelligent shopping assistance
66	🟢 Live Agent Handoff – Seamlessly escalate conversations from AI to human support via Slack when customers need personal assistance
67	🟢 ACF Field Control – Choose exactly which Advanced Custom Fields are included in your knowledge base—perfect for excluding private notes or internal data
68	🟢 Advanced Action Recognition – Smart vector embedding system understands user intent and triggers lead capture, appointments, redirects, and custom actions automatically
69	🟢 Document Processing – Let visitors upload and chat with PDFs and Word documents directly on your frontend
70	🟢 Pinecone Vector Storage – Optional lightning-fast knowledge retrieval for large datasets and enterprise-scale deployments
71	🟢 Web Search Integration – Brave search provides real-time information beyond your knowledge base
72	🟢 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
73	🟢 Image Generation – OpenAI GPT Image and Google Imagen for visual content creation within chat conversations
74	🟢 Streaming Responses – Real-time response streaming for OpenAI, Claude, and Grok models for the fastest possible chat experience
75	🟢 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
76
77	## Choose from 100+ Premium AI Models
78	Access the world's most advanced AI models based on your specific needs:
79
80	OpenRouter: 100+ models from multiple providers with a single API key – including OpenAI, Anthropic, Google, Meta, Mistral, and more!
81	OpenAI:
82	GPT-5.2, GPT-5.1 Chat Latest, GPT-5.1, GPT-5, GPT-5-mini, GPT-5-nano
83	Anthropic Claude:
84	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
85	X.AI:
86	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)
87	Google Gemini:
88	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
89	DeepSeek:
90	DeepSeek V3
91
92	## Lead Management Dashboard — Turn Chat Traffic Into a Real Lead List
93
94	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.
95
96	What You Get:
97
98	- 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
99	- 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
100	- 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)
101	- 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
102	- One-Click View Conversation — jump from any lead straight into their latest full conversation in the transcripts viewer
103	- 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
104	- Clean, Responsive, Native — works beautifully on desktop, tablet, and phone with the same polished dashboard feel as the rest of MxChat
105	- Zero Setup, Zero Migration — uses your existing chat data, no new database tables, no configuration — turn on lead capture and the dashboard just works
106
107	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.
108
109	## AI Content Generator — Create Blog Posts & Landing Pages with AI
110
111	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.
112
113	How It Works:
114
115	1. Describe Your Content — Enter a topic, title, or detailed prompt and choose between a blog post or landing page layout
116	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
117	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
118	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
119	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
120
121	Key Content Generator Features:
122
123	- Choose from multiple AI models for content generation (GPT-5, Claude, Gemini, Grok, and more)
124	- AI-generated images placed directly into your content with automatic media library uploads
125	- SEO title and meta description generation for search engine optimization
126	- Built-in SEO analysis with real-time scoring and one-click AI auto-optimization
127	- Fullwidth and standard layout options with automatic theme compatibility
128	- Content history to revisit and manage previously generated posts
129	- Works with popular page builders and themes including Elementor, Bricks, Divi, Astra, Kadence, and more
130	- 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
131
132	## MxChat Anywhere — Deploy Your Chatbot on Any Website
133
134	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.
135
136	Key Features:
137
138	- One script tag to add your chatbot to any site — no coding or framework required
139	- Full style isolation via Shadow DOM so host page CSS never breaks your chatbot
140	- All your MxChat settings carry over automatically — colors, themes, quick questions, email collection, streaming, and more
141	- Multi-bot support lets you deploy different chatbot configurations on different sites
142	- Secure domain whitelisting and API key authentication prevent unauthorized usage
143	- Lightweight vanilla JS widget with zero dependencies — no jQuery needed on the target site
144
145	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.
146
147	## Powerful Add-On Ecosystem
148
149	Pro Add-Ons:
150	🟢 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
151	🟢 Multi-Bot Manager – Create and manage multiple specialized chatbots with dedicated knowledge databases for different purposes (support, sales, technical, etc.)
152	🟢 Video Generation – Generate stunning AI videos using Google's Veo 2 and Veo 3 models with audio support and multiple aspect ratios
153	🟢 Admin Assistant – ChatGPT-like interface in WordPress admin with thread management and image generation
154	🟢 Chat Themes – Visual design editor with AI-powered chatbot theme generation from natural language
155	🟢 MxChat Forms – Create chatbot-triggered forms for lead capture and support tickets
156	🟢 Chat Moderation – Advanced security with email/IP banning and content filtering
157	🟢 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
158	🟢 Perplexity Integration – Real-time web search with authoritative, well-sourced responses
159	🟢 Migration Tool – Seamlessly switch embedding models and vector databases without losing data, with batch processing and real-time progress tracking
160
161	## 📱 Mobile-Friendly & Fully Customizable
162
163	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.
164
165	## 🔐 Reliable, Fast, Secure
166
167	MxChat is optimized for performance and security. Your AI chatbot runs smoothly, loads fast, and protects your customer data with enterprise-grade security measures.
168
169	## 🌟 What Makes MxChat the Best AI Chatbot for WordPress?
170
171	- Used by hundreds of WordPress websites worldwide
172	- 5-star average rating from satisfied customers
173	- Native WordPress integration - no external dependencies
174	- Setup in under 2 minutes with simple API key configuration
175
176	## 🆓 Start with MxChat’s Powerful Free Plan
177
178	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:
179
180	- Access all AI models from 5 major providers
181	- AI Content Generator for blog posts and landing pages with SEO scoring and AI auto-optimization
182	- Train chatbot on unlimited website content
183	- Loops email capture for lead generation
184	- Web search and image generation capabilities
185	- Real-time admin debug panel
186	- Chat transcript review and export
187	- RAG support & contextual awareness
188
189	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.
190
191	== Developer Hooks & Filters ==
192
193	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/).
194
195	= mxchat_before_process_post =
196
197	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.
198
199	= mxchat_system_instructions =
200
201	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.
202
203	## �
204	Get Started with MxChat AI Chatbot Today
205
206	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.
207
208	## 💰 Pricing
209
210	Most powerful features are included in the free plan. Upgrade to Pro for the complete add-on ecosystem and advanced capabilities.
211	[View all pricing options](https://mxchat.ai/)
212
213	== Use of Third-Party Services ==
214
215	This plugin connects to AI service providers to generate responses:
216
217	Service Providers:
218	- [OpenRouter](https://openrouter.ai/) - [Terms](https://openrouter.ai/terms) \| [Privacy](https://openrouter.ai/privacy)
219	- [OpenAI](https://openai.com/) - [Terms](https://openai.com/policies/terms-of-use/) \| [Privacy](https://openai.com/policies/privacy-policy/)
220	- [Anthropic](https://anthropic.com/) - [Terms](https://www.anthropic.com/terms) \| [Privacy](https://www.anthropic.com/privacy)
221	- [Google](https://ai.google.dev/) - [Terms](https://ai.google.dev/terms) \| [Privacy](https://policies.google.com/privacy)
222	- [X.AI](https://x.ai/) - [Terms](https://x.ai/terms-of-service) \| [Privacy](https://x.ai/privacy-policy)
223	- [DeepSeek](https://deepseek.com/) - [Terms](https://deepseek.com/terms) \| [Privacy](https://deepseek.com/privacy)
224
225	Please ensure compliance with applicable terms and data privacy laws.
226
227	== Installation ==
228
229	1. Upload the `mxchat` folder to the `/wp-content/plugins/` directory.
230	2. Activate the plugin through the 'Plugins' menu in WordPress.
231	3. Navigate to the 'MxChat' settings page to configure your OpenAI API key and other settings.
232
233	== Frequently Asked Questions ==
234
235	= What AI models does MxChat support? =
236
237	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.
238
239	= How do I get API keys for the AI chatbot? =
240
241	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.
242
243	= Can I train the AI chatbot on my website content? =
244
245	Yes. MxChat supports unlimited knowledge base training using RAG (Retrieval-Augmented Generation) technology. Import content from WordPress pages, posts, WooCommerce products, custom post types, PDFs, Word documents, text files, sitemaps, and manual Q&A entries. The AI chatbot will use your content to provide accurate, contextually relevant responses.
246
247	= What is RAG technology and how does it work? =
248
249	RAG (Retrieval-Augmented Generation) is an AI technique that retrieves relevant information from your knowledge base before generating responses. When a visitor asks a question, MxChat searches your trained content using vector embeddings, finds the most relevant matches, and provides that context to the AI model. This ensures accurate, factual answers based on your actual website content rather than generic AI responses.
250
251	= Does MxChat work with WooCommerce? =
252
253	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.
254
255	= Can I customize the AI chatbot appearance? =
256
257	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.
258
259	= How do I add the chatbot to my WordPress site? =
260
261	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.
262
263	= Does MxChat support streaming responses? =
264
265	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.
266
267	= What is the Chat Transcripts feature? =
268
269	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.
270
271	= Can I see which content the AI chatbot used to answer questions? =
272
273	Yes. MxChat includes full knowledge source transparency. In the Chat Transcripts and the optional debug panel, you can see exactly which pages, posts, products, or Q&A entries the AI retrieved and used to generate each response, along with relevance scores.
274
275	= Is Pinecone vector database required? =
276
277	No. MxChat includes free, unlimited local vector storage in your WordPress database. Pinecone integration is optional and recommended only for enterprise-scale knowledge bases with thousands of entries requiring faster search performance.
278
279	= Does MxChat support multiple languages? =
280
281	Yes. The AI chatbot supports multi-language conversations and automatically responds in the language your visitors use. MxChat also supports right-to-left (RTL) languages like Arabic and Hebrew.
282
283	= How much do AI API calls cost? =
284
285	API costs depend on your chosen provider and model. OpenAI, Anthropic, Google, and others charge based on token usage. DeepSeek and Google Gemini offer generous free tiers. MxChat includes intelligent token optimization to minimize API costs. You can also set rate limits for guests and logged-in users to control usage.
286
287	= Is MxChat GDPR compliant? =
288
289	Yes. All conversation data is stored locally on your WordPress site, giving you complete control. Configure automatic data retention policies, export chat transcripts, or delete conversations as needed for compliance.
290
291	= Can I restrict chatbot access to certain users? =
292
293	Yes. MxChat includes role-based access controls. Restrict the chatbot to logged-in users only, specific user roles, or keep it public. You can also restrict specific knowledge base content to certain user roles.
294
295	= Does MxChat support live chat handoff? =
296
297	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.
298
299	= What are Actions and how do they work? =
300
301	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.
302
303	= Can visitors upload documents to chat? =
304
305	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.
306
307	= Does MxChat support image generation? =
308
309	Yes. With DALL-E integration, the AI chatbot can generate images based on user descriptions directly within the chat conversation.
310
311	= How does the knowledge base auto-sync work? =
312
313	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.
314
315	= Can I use Advanced Custom Fields (ACF) with MxChat? =
316
317	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.
318
319	= What embedding models does MxChat support? =
320
321	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.
322
323	= Is there a free version of MxChat? =
324
325	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.
326
327	== Screenshots ==
328
329	1. Chat Transcripts Insights - Review and analyze conversations insights to see engagement rate, peak activity, and user distribution.
330	2. Chat Transcripts Insights - View 7 day activity trend graph.
331	3. Knowledge & Sitemap Submission - Submit custom content to enhance the chatbot's responses.
332	4. Action Page - Set custom action triggers to complete specific actions.
333	5. Plugin Settings Page - Configure your API key and other settings.
334	6. MxChat Debug Panel - Easily debug and view your content matching scores, citation URLs, triggered actions and more.
335
336	(Note: Screenshots will be added in future updates)
337
338	== Changelog ==
339
340	= 3.2.5 - May 11, 2026 =
341	* 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.
342	* 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.
343	* 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.
344	* New: Download Transcript menu item — saves a clean Markdown file of the conversation with sender labels and a timestamped header
345	* 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.
346	* 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.
347
348	= 3.2.4 - May 3, 2026 =
349	- Fixed: WooCommerce product Short Description Visual tab broken by a 404 on the Gutenberg meta-box script
350	- Fixed: User's last message now scrolls to the top of the chat after streaming replies, matching non-streaming behavior
351
352	= 3.2.3 - April 29, 2026 =
353	- 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
354	- Improved: Landing Page Generator now plans more sections and writes substantially more copy per section, producing fuller, more conversion-ready pages by default
355	- 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
356	- 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
357
358	= 3.2.2 - April 21, 2026 =
359	- 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.
360	- 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
361	- 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
362
363	= 3.2.1 - April 17, 2026 =
364	- Fixed: Admin Testing Tab debug panel not displaying similarity scores, action matches, or source data — including when web search + streaming are both enabled
365	- Fixed: Web search responses (streaming and non-streaming) not saving RAG context to chat transcripts, causing the "sources" link to be missing
366
367	= 3.2.0 - April 15, 2026 =
368	- Added: `mxchat_similarity_results` filter hook after similarity search completes, allowing add-ons to access matched sources and their URLs
369	- Removed: `data-no-optimize` attribute injection on MxChat CSS/JS tags, which was conflicting with third-party cache and optimization plugins
370
371	= 3.1.9 - April 7, 2026 =
372	- Fixed: Session ownership issues that were causing "session expired" errors
373
374	= 3.1.8 - April 6, 2026 =
375	- New: Loading indicator displayed while chat is initializing
376	- New: Individual trigger phrase embeddings — each key phrase now gets its own vector for more accurate action matching
377	- Improved: Existing actions remain fully backwards compatible with grouped legacy phrases
378	- New: Admin Testing Tab - embedded chatbot replica with real-time debug panel showing similarity scores, action matches, approved URLs, system prompt, and debug log
379	- Improved: "Delete All" in Knowledge Base now respects the active content type filter — only deletes the filtered type (e.g. Pages) instead of everything
380
381	= 3.1.7 - April 1, 2026 =
382	- Fixed: Chat history not appearing for returning visitors until first message sent when chat persistence is enabled and email collection is off
383	- Fixed: Lead capture form not displaying for new visitors when email collection is enabled
384	- Fixed: Editing legacy manual knowledge base entries deleting all other manual entries sharing the same source URL
385	- New: Google Drive PDF links are now automatically converted to direct downloads for knowledge base import
386
387	= 3.1.6 - March 30, 2026 =
388	- Fixed: Pre-chat popup reappearing on every page refresh — it now stays dismissed for 24 hours
389	- Fixed: Links with certain special characters in URLs being cut off
390	- Fixed: Chat history not loading for returning visitors
391	- Fixed: Links displaying as plain text instead of clickable links in chat responses
392
393	= 3.1.5 - March 25, 2026 =
394	- Improved: Lowered default RAG sources limit from 6 to 3 to reduce token usage for users on lower-tier API plans
395	- Improved: Added per-source chunk cap of 5 to prevent any single document from dominating context
396	- New: RAG Chunks Limit setting — control max total chunks sent to AI (range 8–20, default 15) to balance context quality and token cost
397	- New: Page-level chatbot visibility — show, hide, or use global setting per page/post from the meta box
398	- New: Frontend debugger and transcripts now show actual sources and chunks used counts
399
400	= 3.1.4 - March 22, 2026 =
401	- New: Added support for OpenAI GPT-5.4, GPT-5.4 Mini, GPT-5.4 Nano, and GPT-5.3 Chat models
402	- New: Edit Default Prompt — customize the AI system prompt for blog posts and landing pages from the Content page, saved per type across sessions
403	- New: Knowledge base entries can be edited inline with automatic re-chunking and re-embedding (works with both database and Pinecone)
404	- New: Sitemap import now supports PDF URLs — bulk import PDFs via XML sitemap
405	- Improved: Performance updates and bug fixes
406	- Fixed: Clear chat session in MxChat debugger now fully clears chat sessions and context history
407
408	= 3.1.3 - March 16, 2026 =
409	- 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
410	- New: Chat teaser pop-up message now supports multiple lines.
411	- Improved: Session cookies and tracking now deferred until first user interaction — passive visitors no longer trigger session creation or AJAX calls
412	- Improved: Markdown table rendering with column alignment, responsive scrolling, and alternating row styling
413
414	= 3.1.2 - March 13, 2026 =
415	- New: Per-check AI fix buttons — hover any failing SEO check to see a sparkle icon that fixes just that item individually
416	- New: SEO dashboard now has row checkboxes with "Optimize Selected" to batch-optimize posts (requires Advanced Content Editor add-on)
417	- Improved: "AI Optimize" button renamed to "Optimize All" for clarity
418	- Improved: SEO modal now includes a "View Page" link and per-check AI fix buttons are always visible
419	- Improved: Post type dropdown now dynamically includes custom post types like WooCommerce Products
420	- 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
421	- Fixed: Chat transcripts not saving bot responses containing emojis due to database table using utf8mb3 charset — upgraded to utf8mb4
422	- Fixed: WooCommerce product cards now display with image, price, and button in chat transcripts
423	- Fixed: "Optimize All" now runs SEO fixes sequentially to prevent race conditions — previously internal links and other content-modifying fixes could overwrite each other
424	- Upgraded: Image generation replaced deprecated DALL-E 3 with GPT Image (OpenAI) and added Gemini Imagen 4 action
425
426	= 3.1.1 - March 4, 2026 =
427	- New: Slack agents can now transfer users back to AI mode by typing `!endchat` in the channel
428	- 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
429	- New: SEO analysis panel with real-time scoring for posts and pages in the Content section
430	- New: AI Auto-Optimize — one-click AI fixes for meta descriptions, SEO titles, and URL slugs with configurable check selection
431	- New: Google Search Console integration (Pro) — per-page impressions, clicks, CTR, and top search queries directly in the Content editor
432	- New: SEO optimize settings — choose which checks AI Optimize will run from Content > Settings
433	- 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
434	- Fixed: Security scanner false-positives flagging `file_put_contents` as malware — replaced with `WP_Filesystem` API for transcript and PDF temp files
435	- Improved: PDF parser library now lazy-loaded on demand instead of on every page request
436
437
438	= 3.1.0 - March 1, 2026 =
439	- Fixed: Bulk deleting selected knowledge base entries with chunked content causing network timeout error when using Pinecone
440	- Fixed: Manually entered knowledge base content not being used for AI context despite having high similarity scores
441	- Fixed: Chat input remaining blocked after live agent handoff (Slack/Telegram)
442	- 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
443	- Fixed: Shortcode stripping silently losing all content on pages with large or deeply nested shortcodes (e.g. WPBakery/Visual Composer) due to regex backtracking
444	- New: Added `mxchat_before_process_post` filter hook to allow developers to modify post data before knowledge base processing
445	- New: Added `mxchat_system_instructions` filter hook and shortcode support in system prompt for dynamic data injection
446
447	= 3.0.9 - February 24, 2026 =
448	- 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
449	- New: Advanced Content Editor premium add-on — smart internal linking, AI image management, and per-field AI meta generation
450	- New: Dynamic post type filtering in knowledge database dropdown — automatically pulls in all registered post types
451	- Improved: Compatibility with popular optimization and caching plugins
452
453	= 3.0.8 - February 20, 2026 =
454	- New: Debug & optimization tools with log viewer, settings export, and reset options
455	- New: Added Claude Sonnet 4.6 model
456	- Improved: Performance optimizations and caching plugin compatibility
457
458	= 3.0.7 - February 15, 2026 =
459	- New: Performance optimization
460	- Fixed: GPT-5.1 Chat Latest model returning API error when web search was disabled
461
462	= 3.0.6 - February 11, 2026 =
463	- New: RAG Sources Limit slider - control how many knowledge base sources (3-10) are included in AI responses
464	- New: {visitor_name} placeholder support in Intro Message and AI Behavior settings for personalized greetings
465	- New: Added Claude Opus 4.6 and Claude Opus 4.5 models
466	- Fixed: Chat persistence OFF now correctly starts fresh AI context on page reload (previously AI retained full history)
467	- Deprecated: Removed all GPT-4 series and GPT-3.5 Turbo from model selection (OpenAI deprecation)
468	- Deprecated: Removed Claude 3.x series models (3.7 Sonnet, 3.5 Sonnet, 3 Opus, 3 Sonnet, 3 Haiku) per Anthropic deprecation
469	- Updated: Users on deprecated OpenAI models auto-migrated to GPT-5.1 Chat Latest (or GPT-5 Mini for mini models)
470	- Updated: Users on deprecated Claude models auto-migrated to Claude Opus 4.6 (or Claude Haiku 4.5 for Haiku users)
471
472	= 3.0.5 - January 28, 2026 =
473	- Fixed: Updated Gemini embedding model from deprecated `gemini-embedding-exp-03-07` to stable `gemini-embedding-001`
474	- Fixed: Notification settings not saving on new installations
475	- Fixed: Save indicators not visible on settings fields (API keys, Slack, Telegram, Loops, Brave Search)
476	- Added: Warning notice for WordPress database users recommending Pinecone for large knowledge bases
477	- Improved: Minor admin UI updates for better user experience
478
479	= 3.0.4 - January 24, 2026 =
480	- New: Added latest Google Gemini models (3 Pro Preview, 3 Flash Preview, 2.5 Pro, 2.5 Flash, 2.5 Flash-Lite)
481	- New: Transcript translation feature - auto-translate chat transcripts to any language
482	- New: Action scores visible in transcript sources modal - see document rankings and triggered actions
483	- Fixed: Lead capture forms not working due to multi-bot class ID changes
484
485	= 3.0.3 - January 21, 2026 =
486	- Fixed: Bug when web search was enabled the chat input was not enabled again.
487
488	= 3.0.2 - January 21, 2026 =
489	- New: Telegram Live Agent integration for live chat handoff via Telegram forum topics
490	- New: Telegram settings page (Settings > Integrations > Telegram)
491	- New: Telegram action type in Actions page for intent-based handoff
492	- New: Citation Links toggle to enable/disable source URLs in AI responses (Chatbot > Behavior)
493	- Changed: Renamed "Live Agent" settings tab to "Slack"
494
495	= 3.0.1 - January 18, 2026 =
496	- New: Multi-select entries with bulk "Delete Selected" in knowledge base
497	- New: OpenAI Vector Store integration for knowledge retrieval
498	- New: Custom Post Meta whitelist for including non-ACF meta fields in embeddings
499	- Improved: WordPress database search now filters to matching records only
500	- Improved: WordPress import shows 100 items by default with cross-page selection
501	- Fixed: ACF Field Settings now displays correctly in Knowledge Base sidebar
502	- Changed: Chatbot CSS selectors migrated from IDs to classes for multi-bot support
503	- Note: AI Theme Customizer users must update add-on and click "Migrate" on their theme
504
505	= 3.0.0 - January 14, 2026 =
506	- New: Complete admin UI overhaul with modern sidebar navigation across all pages
507	- New: Clean, professional design with consistent styling throughout the plugin
508	- New: Automatic sitemap detection with one-click "Process Sitemap" button
509	- New: Real-time knowledge base updates - new entries appear instantly without page refresh
510	- New: Consolidated Pro Upgrade and Add-ons pages into a unified interface
511	- New: Improved mobile responsiveness with collapsible menus and slide-up detail panels
512
513	= 2.6.4 - January 6, 2026 =
514	- 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.
515	- 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.
516	- 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.
517	- 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.
518	- 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.
519	- 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.
520
521	= 2.6.3 - December 31, 2025 =
522	- New: Text chunking for RAG - large content is automatically split into semantic chunks for improved retrieval accuracy
523	- New: Chunk count display in WordPress Import modal - shows "(X chunks)" badge for multi-chunk content
524	- New: Collapsible chunk groups in Knowledge Base table - entries with multiple chunks are grouped under a single expandable row
525	- New: Chunk labels show "Chunk 1 of 5", "Chunk 2 of 5" etc. when chunks are expanded
526	- New: Chunking settings in Knowledge Database Settings tab - configure chunk size (default 4000 chars)
527	- New: Option to show/hide frontend debug panel in Chatbot Settings
528	- Enhancement: Improved retrieval - finds best matching chunks, then fetches all chunks for top URLs and reassembles
529	- Enhancement: Chat input is now disabled while waiting for bot response, preventing duplicate message submissions
530	- Enhancement: When streaming is turned on it automatically checks if compatible and disables if not.
531	- Fixed: Markdown formatting now preserved correctly when streaming is disabled (newlines were being stripped)
532
533	= 2.6.2 - December 22, 2025 =
534	- Fixed: Critical error when viewing Knowledge Database with large Pinecone datasets (10K+ products)
535	- Fixed: Optimized Pinecone API queries to prevent memory exhaustion and PHP timeouts
536	- Fixed: Chatbot no longer gets cut off when browser has bookmarks bar or is zoomed above 100%
537	- New: Post type visibility control - include or exclude specific post types from auto-display chatbot
538	- New: Semantic search in admin now searches ALL Pinecone records using embedded query vectors
539
540	= 2.6.1 - December 17, 2025 =
541	- Fixed: Send button now includes aria-label for screen reader accessibility
542	- Fixed: Translations now load from /wp-content/languages/plugins/ first, preserving custom translations during updates
543
544	= 2.6.0 - December 12, 2025 =
545	- New: OpenAI GPT-5.2 model support - best general-purpose and agentic model with fast responses
546	- New: Markdown rendering in transcripts - bot responses display formatted text with clickable links, bold, italic, code blocks, and headers
547	- New: Retrieved documents viewer in transcripts - click "Sources →" link on any bot response to see knowledge base documents used, similarity scores, and citation URLs
548	- Improved: Session security now auto-recovers when user IP changes instead of showing "Unauthorized access" error
549	- Improved: Seamless experience for mobile users switching between WiFi and cellular networks
550
551	= 2.5.9 - December 6, 2025 =
552	- Fix: Shortcode stripping now preserves content inside shortcodes instead of removing it entirely
553
554	= 2.5.8 - December 5, 2025 =
555	- New: Auto-email full transcript feature - sends transcript as .txt file attachment after 15, 30, or 60 minutes of user inactivity
556	- New: Conditional transcript emails - option to only send transcripts when visitors provide contact info (email or phone/WhatsApp) in chat
557	- New: Smart contact detection - automatically detects email addresses and phone numbers (including international WhatsApp formats) in chat messages
558	- Compatibility: Tested and compatible with WordPress 6.9
559
560	= 2.5.7 - December 2, 2025 =
561	- Fix: Streaming fallback bug - bot responses now properly saved to chat transcripts when streaming fails and falls back to regular response mode
562	- Enhancement: Added comprehensive metrics dashboard to Transcripts page with 3 tabs (Overview, Activity, Insights)
563	- Enhancement: Added 7-day activity trend chart with custom visualization
564	- Enhancement: Added new metrics including daily/weekly/monthly chat counts, peak activity hours, and engagement rates
565	- Enhancement: Added auto-delete transcripts feature with configurable intervals (1 week, 2 weeks, 1 month) for better database management and privacy
566	- Enhancement: WooCommerce product imports now include complete pricing metadata (regular price, sale price, price ranges for variable products, SKU, categories)
567	- Improvement: Updated transcript settings modal for better usability on desktop and mobile
568	- Improvement: Various CSS fixes for metrics dashboard display
569
570	= 2.5.6 - November 30, 2025 =
571	- Security: Improved session ID validation with server-side checks
572	- Security: Added session ownership verification to prevent unauthorized access to chat sessions
573	- Fixed: Database error "Unknown column 'bot_id'" for multi-bot configurations with automatic migration
574	- Improvement: Enhanced session security with consistent ownership verification
575	- Improvement: Added automatic database schema migration system
576	- Improvement: WooCommerce import improvements to support Custom Tabs information
577	- Improvement: Database management with a new filtering option. Filter by posts, pages, products, PDF
578
579	= 2.5.5 - November 21, 2025 =
580	- Fixed: Issue with non-streaming mode failing to format URLs and paragraphs correctly
581	- Fixed: Bug with shortcodes still appearing in the knowledge database
582	- Enhancement: Minor adjustments to improve compatibility with multi-bot setups requiring email-to-chat forms
583	- New: Added Grok 4.1 Fast (Reasoning) model — 2M context, reasoning
584	- New: Added Grok 4.1 Fast (Non-Reasoning) model — 2M context, faster responses
585	- New: Added OpenAI GPT-5.1 model — flagship for coding & agentic tasks with low reasoning and 400K context
586
587	= 2.5.4 - November 12, 2025 =
588	- New: Accordion-Style Knowledge Base Viewer for cleaner, expandable database entry previews
589	- New: Smart Shortcode Stripping for WPBakery and Elementor during content submission to improve vectorization accuracy
590	- New: Unique Citation URLs when submitting direct content, allowing multiple linked submissions without overwriting
591	- Improvement: WooCommerce products now include both short and full descriptions during data processing
592
593	= 2.5.3 - November 9, 2025 =
594	- New: Dedicated API Key Management Tab - All API keys organized in one central location for easier management
595	- Improvement: GPT-5 performance optimization with minimal reasoning effort mode for significantly faster response times
596	- Fix: Resolved URL and PDF link encoding issues causing broken or unclickable links in responses
597	- Improvement: Various performance enhancements for improved stability and faster processing
598
599	= 2.5.2 - November 3, 2025 =
600	- New: URL Hallucination Prevention System - AI only cites URLs from knowledge base or system instructions, with automatic removal of invalid links
601	- Improvement: Brand new robust queue-based processing system for sitemap and PDF imports with real-time progress tracking
602	- Improvement: Optimized knowledge retrieval from 5 to 3 documents for faster response times and improved accuracy
603	- Improvement: Increased URL column size to TEXT type for support of long URLs and special characters (Hebrew, Arabic, etc.)
604	- Fix: Resolved URL double-encoding issue causing malformed PDF and document links
605	- Fix: Corrected citation-style bracket handling for AI responses containing [URL] format
606	- Fix: Fixed empty markdown link processing to prevent broken link generation
607
608	= 2.5.1 - October 30, 2025 =
609	- New: Tag-based role restrictions for chatbot knowledge base - automatically control what content the chatbot can access based on WordPress tags and user roles
610	- Update: Migrated users from deprecated Claude 3.5 Sonnet to Claude 3.7 Sonnet with improved performance
611	- Fix: Removed deprecated Claude model from selection options
612
613	= 2.5.0 - October 25, 2025 =
614	- Fix: Resolved PDF URL encoding issue that caused broken links to PDF documents
615	- Fix: Improved UI feedback when selecting chat models
616	- Fix: Enhanced OpenRouter flow selection interface
617
618	= 2.4.8 - October 16, 2025 =
619	- New: OpenRouter integration - access 100+ AI models with a single API key
620	- New: Added Claude Sonnet 4.5, Claude Opus 4.1, and Claude Haiku 4.5 support
621
622	= 2.4.7 - October 13, 2025 =
623	- Security: Fixed Server-Side Request Forgery (SSRF) vulnerability in PDF processing (CVE-2025-10705)
624
625	= 2.4.5 - September 30, 2025 =
626	- Bug Fix: Restored missing CSS properties for popular questions collapse/toggle buttons that were accidentally removed during code cleanup.
627	- Bug Fix: Fixed button hover, focus, and active states for question navigation controls.
628	- Bug Fix: Restored proper SVG styling and display logic for collapsible question buttons.
629
630	= 2.4.4 - September 24, 2025 =
631	- Bug Fix: Default similarity is now accurate across all settings.
632	- Bug Fix: Improved streaming responses to prevent dropped characters or words.
633	- Enhanced: Removed unnecessary Pinecone caching in the knowledge database for more accurate results.
634
635	= 2.4.3 - September 23, 2025 =
636	- Added: Support for upcoming multi-bot update that allows for more customized settings such as individual chat models.
637	- Improved: CSS for chatbot UI & more robust markdown support.
638
639	= 2.4.2 - September 18, 2025 =
640	- Added: Multi-bot support via the new Multi-Bot Manager premium add-on.
641	- Improved: Minor CSS adjustments for better compatibility.
642	- Updated: Add-on links and references throughout the plugin.
643
644	= 2.4.1 - September 4, 2025 =
645	- Fixed: Email collection form not submitting properly when "Require email to chat" is enabled.
646	- Improved: PDF processing now provides clearer error messages with repair suggestions when corrupted files are detected.
647
648	= 2.4.0 - September 3, 2025 =
649	- Added new MxChat Video Generation add-on with support for Google Veo 2 and Veo 3 models, featuring audio generation and multiple aspect ratios.
650	- Fixed console error when "Require email to chat" option is disabled by adding proper validation check.
651	- Resolved "error chat history not found" message when chat persistence is enabled but user has no existing chat history.
652	- Fixed agent indicator not updating properly when switching between live agent and chatbot modes without page refresh.
653
654	= 2.3.9 - August 17, 2025 =
655	- Updated Slack channel naming logic to prioritize client’s name, falling back to email, then chat ID.
656	- Added streaming response support for DeepSeek models.
657	- Enabled multiple direct content entries without requiring a source URL.
658	- Fixed auto sync drafts so posts moved from posted to draft are removed from the knowledge database.
659	- Implemented role-based chatbot information access restrictions for enhanced security and relevance.
660	- Added option in the admin panel’s post edit page to hide the floating chatbot on specific pages.
661
662	= 2.3.8 - August 12, 2025 =
663	- Fixed extra backslashes appearing in knowledgebase content during editing.
664	- Added optional name field to Require Email to Chat form; transcripts now display email and name if enabled.
665	- 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.
666
667	= 2.3.7 - August 8, 2025 =
668	- 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.
669	= 2.3.6 - August 6, 2025 =
670	- Bug Fix: Fixed streaming fallback to properly display responses when streaming fails, preventing blank chat bubbles.
671	- New Feature: Added streaming test button to help users verify if streaming is compatible with their setup.
672
673	= 2.3.5 - August 6, 2025 =
674	- Redesigned chat transcript UI for a cleaner, more professional experience.
675	- Transcripts now show the page where the chat started and any links clicked.
676	- Added ability to select and delete transcripts directly from the header.
677
678	= 2.3.4 - July 30, 2025 =
679	- Fixed streaming compatibility issues with Cloudflare and WP Engine by implementing automatic fallback to regular chat when streaming is buffered.
680	- 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.
681
682	= 2.3.3 - July 29, 2025 =
683	- Improved streaming performance by fixing output buffering issues using enhanced flush logic.
684	- Added contextual awareness support via the new `data-mxchat-context` HTML attribute.
685	- Revamped license key management system with domain linking, deactivation, and real-time usage dashboard.
686	- Fixed transcript timestamp display to use WordPress site's local timezone correctly.
687
688	= 2.3.2 - July 24, 2025 =
689	- Added full support for OpenAI Assistants API via the new Assistant add-on.
690	- Improved email collection form performance and reliability with better loading states and timeout handling.
691	- Enhanced WooCommerce product labeling accuracy in WordPress import with improved URL matching.
692	- Fixed ACF field processing errors when handling WP_Post objects and relationship fields.
693
694	= 2.3.1 - July 20, 2025 =
695	- Enhanced hyperlink functionality to include mailto links, enabling email addresses in bot responses to be clickable.
696	- 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.
697	- Added message filtering hooks system for developers to customize prompts and responses without modifying core plugin files.
698
699	= 2.3.0 - July 13, 2025 =
700	- Added Grok-4 model support, the world's smartest AI model available.
701	- Added streaming response support for all Grok models (Grok-4, Grok-3, etc.), delivering real-time response generation for faster and smoother chat experiences.
702
703	= 2.2.9 - July 6, 2025 =
704	- Improved quick question UI: suggestions now collapse after user input and can be toggled with up/down icons
705	- Increased sitemap batch processing limit from 5 to 50 for faster indexing
706	- Expanded action similarity threshold range to support values from 10 to 95
707
708	= 2.2.8 - June 27, 2025 =
709	- Added brand new contextual awareness option that automatically provides chatbot access to current page content and URL for contextually relevant responses
710	- Enhanced WordPress knowledge base import to include Advanced Custom Fields (ACF) data for more comprehensive content training
711	- Major README structure update with improved formatting and visual presentation
712
713	= 2.2.7 =
714	- Fixed a bug that occured when deleting all pinecone records & added support for markdown hyperlinking in rate limit messages.
715
716	= 2.2.6 =
717	- Brand New Admin Debug Panel â€“ 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.
718	- Fixed Pinecone Single Entry Deletion â€“ Resolved a bug that prevented individual entries from being properly deleted from Pinecone vector storage.
719	- Improved Pinecone UI Records Retrieval â€“ Enhanced the Pinecone database panel with better record loading and display functionality for smoother management of your vector database.
720	- Fixed WordPress KB Entry Editing â€“ Resolved an issue where editing knowledge base entries in the WordPress database wasn't working properly, ensuring seamless content management.
721
722	= 2.2.5 =
723	- Streaming Response Support â€“ 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 theyâ€™re generated.
724	- Slack Live Agent Fix â€“ Resolved a minor bug that occasionally caused duplicate messages in Slack during live agent conversations.
725	- Pinecone UI Update â€“ Fixed a UI display issue in the Pinecone database panel when using the TE3 model.
726
727	= 2.2.4 =
728	- Critical update to error when working with large databases in Pinecone.
729
730	= 2.2.3 =
731	- Various critical bug fixes that occured from the codebase refactoring.
732
733	= 2.2.2 =
734	- Enhanced Slack integration: live agent handoff now creates new Slack channels per conversation; agents can reply directly in channel to chat with website users.
735	- Major codebase refactoring for improved organization and optimization.
736	- Improved sitemap and PDF processing: added retry mechanism, display of failed pages/URLs, and manual batch processing button.
737	- Fixed Pinecone setting not toggling on for users who previously did not have the add-on.
738
739	= 2.2.1 =
740	- Added Claude Sonnet 4 and Claude Opus 4 chat models.
741	- Integrated Google Gemini embedding model (gemini-embedding-001).
742	- Built Pinecone vector database support directly into core plugin.
743	- Removed dependency on separate Pinecone add-on.
744
745	= 2.2.0 =
746	- Added WordPress Content Importer for posts and pages.
747	- Implemented tabbed interface for knowledge base management.
748	- Added content filtering by type and knowledge base status.
749	- Added bulk import with real-time progress tracking.
750
751	= 2.1.9 =
752	- Added email notification feature for new chat sessions.
753	- Implemented pagination on transcripts page (50 per page) to improve performance.
754	- Fixed bug with Brave image search not returning images correctly from the API.
755	- Enhanced performance by changing chat transcripts to disable autoload.
756
757	= 2.1.7 =
758	- Fixed Pro activation issues when the plugin has been translated.
759	- Improved tab behavior to always default to the first tab.
760	- Major rework to rate limits: added custom rate limit timeframes and messages for each individual role.
761	- Fixed bug with Loops where manual list selection from dropdown was required for functionality.
762
763	= 2.1.6 =
764	- Added new AI models: GPT-4.1 and the complete suite of Grok 3 models.
765	- Updated AI service providers to use their official SVG logos for better visual representation.
766	- Fixed an issue where API key fields would try to autosave when no data was entered.
767	- Various other minor bug fixes for improved stability and performance.
768
769	= 2.1.5 =
770	- Added RTL Language support, allowing languages that align right to automatically do so in both chat input and AI responses.
771	- Improved error messaging for API calls in the frontend of the chatbot, and enhanced error messages when submitting sitemaps, URLs, and PDFs.
772	- Fixed an auto save issue that caused an error if no changes were made.
773	- Various other minor bug fixes for improved stability and performance.
774
775	= 2.1.4 =
776	- Added the ability to easily customize the "AI Agent" text displayed in the top bar for greater personalization.
777	- Fixed a bug where data scraping failed to retrieve all content from certain websites.
778	- Added HTML support in the intro message for richer customization.
779	- Resolved an issue where API input fields triggered browser autofill, improving user input accuracy.
780
781	= 2.1.3 =
782	- Added support for Google Gemini models: Gemini 2.0 Flash, Gemini 2.0 Flash-Lite, Gemini 1.5 Pro, and Gemini 1.5 Flash.
783	- Improved chat model selection UI for a more intuitive user experience.
784	- Redesigned embedding model selection UI for better clarity and usability.
785	- Enhanced error handling for sitemap submissions with more helpful user feedback.
786	- Fixed an issue in the knowledge database where editing entries erased or prevented changes to citation URLs.
787
788	= 2.1.2 =
789	- Rebranded intents page to "Actions" with a revamped UI, displaying pro/add-on requirements and brief descriptions.
790	- Added ability to toggle actions on/off without deleting; moved image generation action from pro to free tier.
791	- Introduced advanced knowledge base sync feature to pull in custom post data.
792
793	= 2.1.1 =
794	- Made Claude and X.AI API models available to all users.
795	- Improved API key management UI - only showing relevant API key fields based on selected models.
796	- Enhanced knowledge import interface with clear credit requirement warnings.
797	- Fixed embedding error notifications for better clarity.
798
799	= 2.1.0 =
800	- Fixed a bug impacting the header color in the output.
801	- Updated embedding error notification when submitting sitemaps or PDFs.
802	- Improved context extraction parser.
803
804	= 2.0.9 =
805	- Revamped UI on the main settings page to match the rest of the plugin.
806	- Added real-time updates for sitemap and PDF processing.
807	- Renamed "MxChat Intent Tester" add-on to "MxChat Similarity Tester".
808	- Various minor bug fixes and improvements.
809
810	= 2.0.8 =
811	- Minor bug fix impacting similarity adjustment.
812
813	= 2.0.7 =
814	- Perplexity Integration Add-On â€“ Added Perplexity web search, integrated into intent management with a toolbar toggle.
815	- Sonnet 3.7 Support â€“ Introduced Anthropicâ€™s Claude Sonnet 3.7, the latest high-intelligence model.
816	- Bug Fixes & Improvements â€“ Fixed title tag formatting in responses and tightened knowledge database similarity range to 20.
817
818	= 2.0.5 =
819	- Auto-Expanding AI Instructions â€“ AI instructions text field now auto-expands to fit content.
820	- Chat Transcripts UI & Export â€“ Redesigned chat transcripts UI and added Excel export feature.
821	- Quick Questions Rebrand â€“ Renamed "Popular Questions" to "Quick Questions" with updated copy.
822	- Security Enhancement â€“ Improved security to better prevent XSS attacks.
823	- Intent Testing Add-On â€“ Integrated new Intent Tester add-on for enhanced chatbot performance.
824
825	= 2.0.4 =
826	- Markdown Response Fix â€“ Resolved markdown formatting issues in the chatbot UI.
827	- Agent Mode Customization â€“ Improved indicator text theme and background styling.
828	- WooCommerce Core Extraction â€“ Moved WooCommerce features to the dedicated MxChat WooCommerce add-on.
829
830	= 2.0.3 =
831	- Bug Fix: Resolved issues preventing DeepSeek and Claude models from working correctly.
832	- New: Added integration for the MxChat Form Collection add-on (Pro only).
833	- New: Forms now display dynamically within the chat interface in real-time.
834	- New: Automatic intent handling for seamless form triggering.
835	- Update: Improved submission management with CSV export functionality.
836
837	= 2.0.2 =
838	- Bug Fix: Auto-sync now properly deletes posts/pages when enabled.
839	- Update: Theme customization moved to an add-on with live preview support.
840	- New: Added MxChat Moderation plugin to ban users by email or IP.
841
842	= 2.0.1 =
843	- Bug Fix: Fixed a DivisionByZeroError in sitemap processing that occurred when submitting an empty or malformed sitemap.
844	- Bug Fix: Resolved a similar DivisionByZeroError in PDF processing to prevent crashes when handling PDFs with 0 pages.
845
846	= 2.0.0 =
847	- New UI & Branding: Redesigned the entire plugin interface to align with the new MXChat brand for a modern and seamless experience.
848	- 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.
849	- First Add-On Released â€“ Pinecone DB Manager: Now available for free! This add-on provides an intuitive interface for managing your Pinecone vector database directly within MXChat.
850
851	= 1.6.5 =
852	- Optimized knowledge database retrieval to prevent memory issues with large product databases (2000+ products)
853	- Fixed bug with tab switching control in chat interface
854
855	= 1.6.4 =
856	- Added chat notifications for improved user experience when chat persistence is enabled.
857	- Made the entire plugin fully translatable, allowing compatibility with translation services like Loco Translate.
858	- 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.
859
860	= 1.6.4 =
861	- Added chat notifications for improved user experience when chat persistence is enabled.
862	- Made the entire plugin fully translatable, allowing compatibility with translation services like Loco Translate.
863	- 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.
864
865	= 1.6.3 =
866	- Added the new "Rate Limit by User Role" feature, replacing the previous rate limit for logged-in users.
867	- Introduced DeepSeek as a new AI service provider, with full support for their models.
868	- Integrated DeepSeek V3, enhancing chatbot natural language understanding and performance.
869
870	= 1.6.2 =
871	- Fixed a bug preventing the ability to save edits in the knowledge database.
872
873	= 1.6.0 =
874	- Redesigned knowledgebase UI for a cleaner, more user-friendly interface.
875	- Introduced auto-sync functionality for posts and pages, enabling automatic addition of new or updated content to the knowledgebase.
876	- Enhanced XML sitemap submission to prevent duplicate entries by checking and updating existing pages or adding new ones as needed.
877	- Reworked chatbot settings to enable individual autosave after updates, removing the need for manual saving.
878	- Fixed paragraph formatting in the chatbot UI to display line breaks and improve readability.
879
880	= 1.5.9 =
881	- Enhanced transcripts page with new analytics dashboard and improved UI
882	- Added support for X.AI's Grok model
883	- Improved message formatting to preserve paragraphs in intro messages
884	- Updated admin panel interface with better organization and styling
885	- Added better mobile responsiveness across admin screens
886
887	= 1.5.8 =
888	- 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.
889
890	= 1.5.7 =
891	- Enhanced Complianz plugin integration to support the premium version and improve reliability.
892	- Fixed an issue where names were not appearing in chat transcripts for logged-in users.
893	- Added the ability to customize the title bar icon in the theme settings.
894	- Grouped intents by category in dropdown menus for better organization and usability.
895
896	= 1.5.6 =
897	- Improved "Add to Cart" and product recommendation intents for WooCommerce.
898	- Enhanced Brave Search intent for more accurate and structured results.
899	- Added an Edit button to the intent management section for easier adjustments.
900	- Fixed the Word document upload toolbar button for seamless functionality.
901
902	= 1.5.5 =
903	- Chat transcripts now display in newest-to-oldest order and are mobile responsive.
904	- Updated various setting texts with clearer descriptions for better usability.
905	- Fixed issue with rate limit not working properly.
906	- Added Word document upload to the frontend toolbar for direct chatbot interface use.
907	- Improved chatbot's contextual response accuracy.
908	- Major enhancements to "Add to Cart," "Checkout," and "Chat with PDF via URL" intents.
909
910	= 1.5.4 =
911	- Enhanced chat transcripts layout for improved readability, better formatting support (e.g., bold, italics), and inclusion of test agent names from MxChat AI Agents.
912	- Introduced MxChat AI Agents, now available free for Pro users for a limited time, providing a revolutionary way to test and deploy your chatbot.
913
914	= 1.5.3 =
915	- Major bug fix to the similarity threshold comparison which prevented the chatbot from finding relevant content.
916
917	= 1.5.2 =
918	- Enhanced checkout intent functionality to work more robustly, no longer requiring add-to-cart intent trigger.
919	- Fixed issue with send button not displaying properly on iPhone/iOS devices.
920	- Added admin control for similarity threshold matching to fine-tune relevant content results.
921
922	= 1.5.1 =
923	- Vastly improved the ability for the chatbot to give contextually relevant responses from the knowledge database.
924	- Fixed the issue with loops in the lead capture intent.
925	- Updated the PDF upload icon in the frontend chatbot UI to a clearer design, now showing a PDF file icon.
926	- Enhanced the order history intent, recommendation intent, and product card intent for more robust and contextually relevant responses.
927
928	= 1.5 =
929	- Live Agent Transfer: Seamless integration for live agent handoffs and AI chatbot switching.
930	- PDF Toolbar: Added PDF upload to the chatbot interface and knowledge base processing with cron jobs.
931
932	= 1.4.6 =
933	- Product Recommendation Intent: Added personalized product recommendations based on order history, cart contents, and trending items.
934	- Custom Chatbot Icon: Users can upload custom PNG icons for a more personalized chatbot appearance.
935	- Codeblock Copy Button: Introduced a copy button for codeblocks to simplify copying code snippets.
936	- Expanded Popular Questions: Increased flexibility by allowing more than the default three popular questions.
937	- CSS Compatibility Fixes: Improved chatbot CSS for better theme compatibility.
938
939	= 1.4.5 =
940	- 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.
941
942	= 1.4.4 =
943	- Custom Rate Limits: Set different rate limits for logged-in and logged-out users.
944	- PDF Intent Enhancements: Added customizable trigger, success, and error messages, plus a max PDF page limit setting.
945	- Improved Flexibility: Greater control over chatbot behavior and user interactions.
946
947	= 1.4.3 =
948	- PDF Intent: Added support for processing and analyzing PDF content via provided URLs using vector embeddings.
949	- Compatibility Fix: Fixed a rendering issue that prevented the chatbot from displaying in certain environments.
950
951	= 1.4.2 =
952	- Fixed Knowledge Search: Fixed a bug impacting the ability to search knowledge database information.
953
954	= 1.4.1 =
955	- Fixed Intent Loading Issue: Fixed a bug which prevented new intents from being shown on certain installs.
956
957	= 1.4 =
958	- Customizable Sensitivity Threshold: Added support for individual sensitivity thresholds on each intent, offering more precise control over intent recognition.
959	- 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.
960
961	= 1.3 =
962	- Advanced Intent Recognition: Introduced vector embedding for enhanced intent detection, improving chatbot responsiveness.
963	- New Integrations: Added Brave Web Search, Brave Image Search, and DALL-E Image Generation intents.
964	- Security Update: Minor update to unserialization handling for enhanced security.
965
966	= 1.2.1 =
967	- 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.
968	- Enhanced Popular Questions and Pre-Chat Message functionalities for improved user engagement and streamlined chat initiation.
969
970	= 1.2 =
971	- Added Popular Questions Buttons with one free question and two available in the Pro version.
972	- Added Inline Edit Button to the Knowledge Database for easy content management.
973
974	= 1.1.9 =
975	- Added integration with Claude (Anthropic) API (Pro feature) for advanced conversational models like `Claude 3.5 Sonnet` and `Claude 3 Haiku`.
976
977	= 1.1.8 =
978	- Added integration with X.AI API (Pro feature) for advanced chat completions using models like `grok-beta`.
979	- Introduced new model selection dropdown that separates OpenAI and X.AI models, with X.AI models disabled for free users.
980	- Enhanced API key management, allowing users to input and manage both OpenAI and X.AI API keys in settings.
981
982	= 1.1.7 =
983	* Added chat session persistence option for users to maintain conversations across visits for up to 24 hours.
984	* Updated navigation tabs CSS and scripts to prevent conflicts with other plugins.
985	* Rate limit settings are now available to all users, offering better control over chat usage.
986
987	= 1.1.6 =
988	* Minor CSS update.
989
990	= 1.1.5 =
991	* Fixed error when users didn't have WooCommerce it would return "Error communicating with server".
992
993	== Upgrade Notice ==
994
995	= 3.2.5 =
996	Major release: REST API with bearer-token auth (transcripts read/delete, knowledge push, health), new API Access admin page, redesigned chat header with 3-dot menu and Download Transcript, SEO improvements to Content Generator (rank_math_title and image alt sync), and custom transcript retention (1–3650 days).
997
998	== License & Warranty ==
999
1000	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.
1001
1002	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.
1003
1004	== Credits ==
1005
1006	This plugin incorporates the following third-party library:
1007
1008	- Smalot PDF Parser: Used for parsing and extracting text from PDF files. This library is developed by Smalot and distributed under the MIT License. For more details, visit the [Smalot PDF Parser GitHub repository](https://github.com/smalot/pdfparser).
1009
1010	This plugin was developed by [MxChat](https://mxchat.ai/).
1011