{"id":351163,"date":"2026-10-10T21:00:49","date_gmt":"2026-10-10T21:00:49","guid":{"rendered":"https:\/\/wordpress.org\/plugins\/sparxio-ai-chatbot-live-chat-lead-generation\/"},"modified":"2026-10-10T21:00:13","modified_gmt":"2026-10-10T21:00:13","slug":"sparxio-ai-chatbot","status":"publish","type":"plugin","link":"https:\/\/wordpress.org\/plugins\/sparxio-ai-chatbot\/","author":20228976,"comment_status":"closed","ping_status":"closed","template":"","meta":{"version":"3.7.5","stable_tag":"3.7.5","tested":"7.1.3","requires":"5.8","requires_php":"7.4","requires_plugins":null,"header_name":"Sparxio \u2013 AI Chatbot, Live Chat & Lead Generation","header_author":"Ameer Hamza","header_description":"AI chatbot for WordPress with a knowledge base, 30 languages, custom branding and chat logs. Works with your own Anthropic, OpenAI, Gemini, DeepSeek, OpenRouter or Ollama key.","assets_banners_color":"49855b","last_updated":"2026-10-10 21:00:13","external_support_url":"","external_repository_url":"","donate_link":"","header_plugin_uri":"https:\/\/skillssparx.com\/sparxio\/","header_author_uri":"https:\/\/skillssparx.com\/","rating":0,"author_block_rating":0,"active_installs":0,"downloads":34,"num_ratings":0,"support_threads":0,"support_threads_resolved":0,"author_block_count":0,"sections":["description","installation","faq","changelog"],"tags":{"3.7.5":{"tag":"3.7.5","author":"haamzaa","date":"2026-10-10 21:00:13","revision":3738706}},"upgrade_notice":{"3.7.5":"<p>More reliable message delivery when a connection or proxy returns an incomplete response. Recommended for all users.<\/p>","3.7.4":"<p>Faster, more reliable replies; current AI models for every provider; new providers (Grok, Mistral, Groq, any OpenAI-compatible API); backup AI provider; answers that don&#039;t invent facts. Recommended for all users.<\/p>","3.7.3":"<p>Fixes message retries, returning-visitor conversations, case-sensitive knowledge-base URLs and Pro order analytics. Recommended for all users.<\/p>","3.7.2":"<p>Reliability update for live chat, leads and the knowledge base, server-side conversation timeout, and safer proxy settings. Recommended for all users.<\/p>","3.7.1":"<p>Fixes the free-trial button, live-agent message handling and lead form reliability, and removes third-party geolocation. Recommended for all users.<\/p>","3.7.0":"<p>Privacy and reliability update: geolocation is now opt-in, no external fonts, language settings for everyone, and more reliable lead capture. Recommended for all users.<\/p>"},"ratings":[],"assets_icons":{"icon-128x128.png":{"filename":"icon-128x128.png","revision":3738706,"resolution":"128x128","location":"assets","locale":"","width":128,"height":128},"icon-256x256.png":{"filename":"icon-256x256.png","revision":3738706,"resolution":"256x256","location":"assets","locale":"","width":256,"height":256}},"assets_banners":{"banner-1544x500.png":{"filename":"banner-1544x500.png","revision":3738706,"resolution":"1544x500","location":"assets","locale":"","width":1544,"height":500},"banner-772x250.png":{"filename":"banner-772x250.png","revision":3738706,"resolution":"772x250","location":"assets","locale":"","width":772,"height":250}},"assets_blueprints":{},"all_blocks":[],"tagged_versions":["3.7.5"],"block_files":[],"assets_screenshots":{"screenshot-1.png":{"filename":"screenshot-1.png","revision":3738706,"resolution":"1","location":"assets","locale":"","width":1440,"height":900},"screenshot-10.png":{"filename":"screenshot-10.png","revision":3738706,"resolution":"10","location":"assets","locale":"","width":1440,"height":1000},"screenshot-2.png":{"filename":"screenshot-2.png","revision":3738706,"resolution":"2","location":"assets","locale":"","width":780,"height":1328},"screenshot-3.png":{"filename":"screenshot-3.png","revision":3738706,"resolution":"3","location":"assets","locale":"","width":1440,"height":1040},"screenshot-4.png":{"filename":"screenshot-4.png","revision":3738706,"resolution":"4","location":"assets","locale":"","width":1440,"height":900},"screenshot-5.png":{"filename":"screenshot-5.png","revision":3738706,"resolution":"5","location":"assets","locale":"","width":1440,"height":900},"screenshot-6.png":{"filename":"screenshot-6.png","revision":3738706,"resolution":"6","location":"assets","locale":"","width":1440,"height":1375},"screenshot-7.png":{"filename":"screenshot-7.png","revision":3738706,"resolution":"7","location":"assets","locale":"","width":1440,"height":1000},"screenshot-8.png":{"filename":"screenshot-8.png","revision":3738706,"resolution":"8","location":"assets","locale":"","width":1440,"height":980},"screenshot-9.png":{"filename":"screenshot-9.png","revision":3738706,"resolution":"9","location":"assets","locale":"","width":1440,"height":1600}},"screenshots":{"1":"Dashboard with session overview and activity","2":"AI chat widget with live typing indicator","3":"Appearance settings with colour presets and live preview","4":"AI Settings with sample prompt templates and provider selection","5":"Chat logs with search and filtering","6":"Setup Guide with a live progress checklist"}},"plugin_section":[],"plugin_tags":[191735,2364,337,2379,286],"plugin_category":[45],"plugin_contributors":[78154,285614],"plugin_business_model":[],"class_list":["post-351163","plugin","type-plugin","status-publish","hentry","plugin_tags-ai-chatbot","plugin_tags-chatbot","plugin_tags-lead-generation","plugin_tags-live-chat","plugin_tags-woocommerce","plugin_category-ecommerce","plugin_contributors-freemius","plugin_contributors-haamzaa","plugin_committers-haamzaa"],"banners":{"banner":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/banner-772x250.png?rev=3738706","banner_2x":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/banner-1544x500.png?rev=3738706","banner_rtl":false,"banner_2x_rtl":false},"icons":{"svg":false,"icon":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/icon-128x128.png?rev=3738706","icon_2x":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/icon-256x256.png?rev=3738706","generated":false},"screenshots":[{"src":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/screenshot-1.png?rev=3738706","caption":"Dashboard with session overview and activity"},{"src":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/screenshot-2.png?rev=3738706","caption":"AI chat widget with live typing indicator"},{"src":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/screenshot-3.png?rev=3738706","caption":"Appearance settings with colour presets and live preview"},{"src":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/screenshot-4.png?rev=3738706","caption":"AI Settings with sample prompt templates and provider selection"},{"src":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/screenshot-5.png?rev=3738706","caption":"Chat logs with search and filtering"},{"src":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/screenshot-6.png?rev=3738706","caption":"Setup Guide with a live progress checklist"},{"src":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/screenshot-7.png?rev=3738706","caption":""},{"src":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/screenshot-8.png?rev=3738706","caption":""},{"src":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/screenshot-9.png?rev=3738706","caption":""},{"src":"https:\/\/ps.w.org\/sparxio-ai-chatbot\/assets\/screenshot-10.png?rev=3738706","caption":""}],"raw_content":"<!--section=description-->\n<p>Sparxio adds a fully customizable AI-powered chat widget to your WordPress site. Visitors chat with an AI assistant that replies in their own language, answers from your knowledge base, and guides them toward your goals \u2014 making a purchase, booking a demo, or submitting an enquiry.<\/p>\n\n<p>You connect your own AI provider with your own API key, so you stay in full control of usage and cost. Nothing is routed through a third-party middleman.<\/p>\n\n<p><strong>Why Sparxio<\/strong><\/p>\n\n<ul>\n<li>Bring your own AI key \u2014 no per-message markup, no forced subscription to use the chat<\/li>\n<li>Answers grounded in your own content, not generic replies<\/li>\n<li>Genuinely multilingual \u2014 the interface ships in 30 languages<\/li>\n<li>Built for WordPress: Shadow DOM isolation, mobile-optimised, no theme conflicts<\/li>\n<\/ul>\n\n<p><strong>Free Features<\/strong><\/p>\n\n<ul>\n<li><strong>10 AI providers<\/strong> \u2014 Anthropic (Claude), OpenAI (GPT), Google Gemini, xAI (Grok), DeepSeek, Mistral, Groq, OpenRouter (hundreds of models), a local Ollama model, or any OpenAI-compatible API (Together, Fireworks, Cerebras, Perplexity, LM Studio\u2026) \u2014 with your own key. Use any model ID, including ones released after this version<\/li>\n<li><strong>Never goes silent<\/strong> \u2014 pick a backup AI provider that answers automatically if the main one fails. Requests adapt to each model's options, and a retired model is replaced by a current one (you are told in AI Settings)<\/li>\n<li><strong>Accurate answers<\/strong> \u2014 the bot only states addresses, numbers, prices and policies it was actually given; otherwise it says so instead of guessing<\/li>\n<li><strong>OpenRouter model browser<\/strong> \u2014 search hundreds of live models, free ones first, with prices, plus up to three backup models<\/li>\n<li><strong>Full branding control<\/strong> \u2014 colour presets or custom colours, header icon, brand name, and CTA button. No attribution is shown unless you add your own footer text.<\/li>\n<li><strong>30-language widget UI<\/strong> \u2014 including German, Spanish, French, Italian, Portuguese, Dutch, Polish, Swedish, Danish, Finnish, Norwegian, Greek, Czech, Hungarian, Romanian, Ukrainian, Russian, Arabic, Turkish, Hindi, Chinese, Japanese, Korean, and more<\/li>\n<li><strong>Unlimited knowledge base<\/strong> \u2014 teach the AI from FAQ entries, documents, web pages, and sitemaps so answers reflect your business<\/li>\n<li><strong>Lead capture &amp; CSV export<\/strong> \u2014 collect name, email, and phone inside the chat, then view, manage, and export leads to CSV<\/li>\n<li><strong>Chat logs<\/strong> \u2014 full transcript of every conversation with the visitor's device and page (and country, when your site is behind Cloudflare)<\/li>\n<li><strong>Basic dashboard<\/strong> \u2014 sessions, messages, and activity at a glance<\/li>\n<li><strong>Live typing indicator<\/strong> \u2014 shown the moment a visitor sends a message, until the answer arrives<\/li>\n<li><strong>Cost controls<\/strong> \u2014 history limits, rolling summarisation, and session timeouts keep API usage low<\/li>\n<li><strong>Built-in setup guide<\/strong> \u2014 a live checklist walks you through configuration<\/li>\n<\/ul>\n\n<p><strong>Sparxio Pro (separate plugin)<\/strong><\/p>\n\n<p>Everything above is free and fully functional. For stores and teams that want more, Sparxio Pro is a separate plugin, sold on our website, that adds:<\/p>\n\n<ul>\n<li><strong>WooCommerce chat<\/strong> \u2014 product search, add-to-cart, and verified order-status lookups inside the chat<\/li>\n<li><strong>Live agent takeover<\/strong> \u2014 jump into any conversation in real time, then hand back to the AI<\/li>\n<li><strong>Advanced analytics<\/strong> \u2014 conversations, leads and top questions for a chosen period, plus WooCommerce orders placed after a chat (paid orders only, minus refunds, per currency)<\/li>\n<li><strong>Proactive engagement<\/strong> \u2014 greet visitors based on time on page, exit intent, or the page they are viewing<\/li>\n<\/ul>\n\n<p><a href=\"https:\/\/skillssparx.com\/sparxio\/\">Learn more about Sparxio Pro<\/a><\/p>\n\n<p><strong>External Services<\/strong><\/p>\n\n<p>This plugin contacts the third-party services below only when you configure or choose them. Nothing is sent to any third party unless you add an AI provider key, or opt in to Freemius when activating the plugin.<\/p>\n\n<p><strong>AI providers.<\/strong> When a visitor sends a chat message, the plugin sends that message, the recent conversation history, your system prompt, and any matching knowledge-base excerpts to the AI provider you selected in AI Settings, using your own API key. Nothing is sent until you add a key and select a provider. Only the selected provider is contacted \u2014 plus the backup provider you may choose in AI Settings, and only when the selected one fails.<\/p>\n\n<ul>\n<li><strong>Anthropic API<\/strong> (api.anthropic.com) \u2014 used when Anthropic is the selected or backup provider. <a href=\"https:\/\/www.anthropic.com\/legal\/commercial-terms\">Terms<\/a> \/ <a href=\"https:\/\/www.anthropic.com\/legal\/privacy\">Privacy<\/a><\/li>\n<li><strong>OpenAI API<\/strong> (api.openai.com) \u2014 used when OpenAI is the selected or backup provider. <a href=\"https:\/\/openai.com\/policies\/terms-of-use\/\">Terms<\/a> \/ <a href=\"https:\/\/openai.com\/policies\/privacy-policy\/\">Privacy<\/a><\/li>\n<li><strong>Google Gemini API<\/strong> (generativelanguage.googleapis.com) \u2014 used when Gemini is the selected or backup provider. <a href=\"https:\/\/ai.google.dev\/gemini-api\/terms\">Terms<\/a> \/ <a href=\"https:\/\/policies.google.com\/privacy\">Privacy<\/a><\/li>\n<li><strong>DeepSeek API<\/strong> (api.deepseek.com) \u2014 used when DeepSeek is the selected or backup provider. <a href=\"https:\/\/cdn.deepseek.com\/policies\/en-US\/deepseek-open-platform-terms-of-service.html\">Terms<\/a> \/ <a href=\"https:\/\/cdn.deepseek.com\/policies\/en-US\/deepseek-privacy-policy.html\">Privacy<\/a><\/li>\n<li><strong>OpenRouter API<\/strong> (openrouter.ai) \u2014 used when OpenRouter is the selected or backup provider. OpenRouter forwards the request to the model you choose (and to your backup models, if set). Your site URL and site name are also sent as attribution headers. When OpenRouter is selected or has a key and an administrator opens AI Settings, the public model list (openrouter.ai\/api\/v1\/models) is fetched, without a key or any site data, and cached for six hours. <a href=\"https:\/\/openrouter.ai\/terms\">Terms<\/a> \/ <a href=\"https:\/\/openrouter.ai\/privacy\">Privacy<\/a><\/li>\n<li><strong>xAI API<\/strong> (api.x.ai) \u2014 used when xAI (Grok) is the selected or backup provider. <a href=\"https:\/\/x.ai\/legal\/terms-of-service-enterprise\">Terms<\/a> \/ <a href=\"https:\/\/x.ai\/legal\/privacy-policy\">Privacy<\/a><\/li>\n<li><strong>Mistral AI API<\/strong> (api.mistral.ai) \u2014 used when Mistral is the selected or backup provider. <a href=\"https:\/\/legal.mistral.ai\/terms\/commercial-terms-of-service\">Terms<\/a> \/ <a href=\"https:\/\/legal.mistral.ai\/terms\/privacy-policy\">Privacy<\/a><\/li>\n<li><strong>Groq API<\/strong> (api.groq.com) \u2014 used when Groq is the selected or backup provider. <a href=\"https:\/\/console.groq.com\/docs\/legal\/services-agreement\">Terms<\/a> \/ <a href=\"https:\/\/groq.com\/privacy-policy\">Privacy<\/a><\/li>\n<li><strong>Custom OpenAI-compatible endpoint<\/strong> \u2014 used when \"Custom\" is the selected or backup provider. Requests go only to the address you enter (for example Together, Fireworks, Cerebras, Perplexity, or your own LM Studio \/ vLLM server); that service's own terms and privacy policy apply.<\/li>\n<li><strong>Ollama<\/strong> (your own server, default http:\/\/localhost:11434) \u2014 used when Ollama is the selected or backup provider. Requests go only to the Ollama server address you enter; no third party is contacted.<\/li>\n<\/ul>\n\n<p><strong>Other services.<\/strong><\/p>\n\n<ul>\n<li><strong>Freemius<\/strong> (api.freemius.com) \u2014 only if you choose to opt in when activating the plugin (you can skip it). Sends your site URL, WordPress and plugin versions, and your admin name and email, so you can receive optional security and feature notices and manage a Pro license. <a href=\"https:\/\/freemius.com\/terms\/\">Terms<\/a> \/ <a href=\"https:\/\/freemius.com\/privacy\/\">Privacy<\/a><\/li>\n<\/ul>\n\n<p><strong>Knowledge base imports.<\/strong> When you import a web page or sitemap, your site fetches that address (and the pages a sitemap lists) directly. Only the address you enter is requested; downloads are size-limited and private\/internal addresses are refused.<\/p>\n\n<p><strong>Cookies and browser storage.<\/strong> The widget keeps the conversation in this browser according to your Chat Persistence setting (memory only, this tab, or this browser). A <code>sparxio_seen<\/code> cookie remembers returning visitors. On WooCommerce stores with Sparxio Pro, a <code>sparxio_attr<\/code> cookie (a signed conversation number, not the conversation itself), set once the visitor has sent a message, lets an order placed later be counted as chat-assisted.<\/p>\n\n<p>No data is sent to any AI service until you enter an API key and a visitor starts a chat. The plugin does not look up visitor locations with any outside service. API keys are stored in your own WordPress database.<\/p>\n\n<p>Payments, licensing, and Pro updates are handled by our partner Freemius (checkout, invoicing, and license management). See the <a href=\"https:\/\/freemius.com\/privacy\/\">Freemius Privacy Policy<\/a>.<\/p>\n\n<h3>Source Code and Build<\/h3>\n\n<p>This plugin ships its complete, human-readable source. No build step, bundler, or minifier is used.<\/p>\n\n<ul>\n<li>assets\/js\/widget.js \u2014 the chat widget script. This is the original hand-written source (short variable names are hand-authored, not the output of a minifier).<\/li>\n<li>All admin scripts in assets\/js\/ are likewise plain, hand-written source.<\/li>\n<\/ul>\n\n<p>Bundled third-party code: the Freemius SDK (vendor\/freemius, GPL), used for opt-in usage analytics and to offer the optional Pro version. Source: https:\/\/github.com\/Freemius\/wordpress-sdk. The free plugin bundles no other third-party JavaScript libraries; Sparxio Pro additionally bundles Chart.js (MIT, https:\/\/www.chartjs.org\/) for its analytics charts. The widget uses your visitors' system fonts, so no web fonts are downloaded.<\/p>\n\n<!--section=installation-->\n<ol>\n<li>In your WordPress admin, go to Plugins \u2192 Add New and search for \"Sparxio\", or upload the <code>sparxio<\/code> folder to <code>\/wp-content\/plugins\/<\/code>.<\/li>\n<li>Activate the plugin through the Plugins menu.<\/li>\n<li>Open Sparxio \u2192 Setup Guide and follow the live checklist.<\/li>\n<li>Enter your AI provider API key in Sparxio \u2192 AI Settings.<\/li>\n<li>Customise the look in Sparxio \u2192 Appearance.<\/li>\n<li>The chat widget appears on your site automatically.<\/li>\n<\/ol>\n\n<!--section=faq-->\n<dl>\n<dt id=\"do%20i%20need%20an%20api%20key%3F\"><h3>Do I need an API key?<\/h3><\/dt>\n<dd><p>Yes. Sparxio uses your own key from one of the supported providers (Anthropic, OpenAI, Google Gemini, DeepSeek, OpenRouter, or a local Ollama model). This keeps you in control of usage and cost. Free keys or trials are available from most providers.<\/p><\/dd>\n<dt id=\"is%20the%20plugin%20free%3F\"><h3>Is the plugin free?<\/h3><\/dt>\n<dd><p>Yes. This plugin is free and fully functional, with no limits, time restrictions, or license checks. A separate plugin, Sparxio Pro, adds WooCommerce chat, live agent takeover, advanced analytics, and proactive engagement for those who need them.<\/p><\/dd>\n<dt id=\"how%20much%20does%20the%20ai%20cost%20to%20run%3F\"><h3>How much does the AI cost to run?<\/h3><\/dt>\n<dd><p>You pay your provider directly for API usage. On the most affordable models this is typically a fraction of a cent per conversation. Built-in history limits, summarisation, and timeouts keep usage low.<\/p><\/dd>\n<dt id=\"will%20it%20slow%20down%20my%20site%3F\"><h3>Will it slow down my site?<\/h3><\/dt>\n<dd><p>No. The widget loads asynchronously after your page content and uses Shadow DOM, so it never conflicts with your theme's CSS or JavaScript.<\/p><\/dd>\n<dt id=\"does%20it%20work%20with%20woocommerce%3F\"><h3>Does it work with WooCommerce?<\/h3><\/dt>\n<dd><p>Yes, with Sparxio Pro. The AI can search products, add items to the cart, and look up order status (with identity verification) directly in the chat.<\/p><\/dd>\n<dt id=\"what%20languages%20are%20supported%3F\"><h3>What languages are supported?<\/h3><\/dt>\n<dd><p>The widget interface ships in 30 languages and the AI replies in whatever language the visitor writes in. Turn on multi-language, choose a default language, and enable browser auto-detection in Sparxio \u2192 Behavior.<\/p><\/dd>\n<dt id=\"can%20i%20customise%20the%20ai%27s%20personality%3F\"><h3>Can I customise the AI's personality?<\/h3><\/dt>\n<dd><p>Completely. Write a system prompt that defines the assistant's identity, tone, knowledge, and rules. Sample templates for e-commerce, SaaS, travel, healthcare, education, and real estate are included.<\/p><\/dd>\n<dt id=\"how%20do%20i%20remove%20all%20data%20when%20uninstalling%3F\"><h3>How do I remove all data when uninstalling?<\/h3><\/dt>\n<dd><p>By default your data is preserved across reinstalls. To wipe everything on uninstall, enable \"Delete all data on uninstall\" in Sparxio \u2192 AI Settings \u2192 Security before removing the plugin.<\/p><\/dd>\n<dt id=\"is%20my%20visitors%27%20data%20safe%3F\"><h3>Is my visitors' data safe?<\/h3><\/dt>\n<dd><p>API keys are stored in your database and messages are sent only to the AI provider you choose. No visitor location lookup service is used. See the External Services section above for the full list of connections.<\/p><\/dd>\n\n<\/dl>\n\n<!--section=changelog-->\n<h4>3.7.5<\/h4>\n\n<ul>\n<li>An empty or damaged server response is no longer treated as an answer: the widget fetches the real answer for the same message instead, so it is never sent twice<\/li>\n<li>A message the server received but could not answer is now labelled \"Answer unavailable\" instead of \"Not sent\"<\/li>\n<\/ul>\n\n<h4>3.7.4<\/h4>\n\n<ul>\n<li>Faster replies: a message is sent the moment the visitor presses Send and the typing indicator appears at once; the artificial pauses before sending and after the answer are gone (the Pre-Typing Delay and Typing Speed settings were removed)<\/li>\n<li>Every chat and session request now has a time limit. If a reply is slow or the connection drops, the widget keeps asking for the same message's answer for up to about 2\u00bd minutes, without the message being stored or answered twice<\/li>\n<li>A message the server is still answering is picked up automatically when ready, instead of showing a \"still being answered\" error<\/li>\n<li>Sending a message again updates its existing bubble instead of adding a duplicate; each visitor message shows Sending\u2026 \/ Waiting for reply \/ Not sent until it is answered<\/li>\n<li>A message sent just before a page reload gets its answer after the reload (Tab and Browser persistence modes)<\/li>\n<li>AI providers updated for current models: Claude 5.5 family, GPT-6 \/ GPT-5.x, Gemini 3.x and 2.5, DeepSeek V4 (deepseek-flash, deepseek-v4-pro), current OpenRouter models. Reasoning models get the right options (low effort, room for thinking), so replies are fast and never empty; thinking text is never shown to visitors<\/li>\n<li>Retired models are switched to a current one on upgrade and, if a model disappears later, at runtime (with a notice in AI Settings)<\/li>\n<li>New providers: xAI (Grok), Mistral AI, Groq, and Custom (any OpenAI-compatible API)<\/li>\n<li>New: backup AI provider, custom model ID for every provider, OpenRouter live model list and backup models, \"Only answer from what you know\" accuracy setting (on by default)<\/li>\n<li>Gemini API key is sent in a header instead of the URL; OpenRouter errors returned inside a successful response and Ollama HTTP errors are now reported in AI Settings<\/li>\n<li>Test Connection shows the model used and how long it took<\/li>\n<li>Every widget request (live-agent updates, lead form, add to cart, summaries) now has a time limit, so a stalled connection can't freeze the chat<\/li>\n<\/ul>\n\n<h4>3.7.3<\/h4>\n\n<ul>\n<li>Retrying a message whose answer is still being written keeps the same identity (also across a page reload in Tab\/Browser mode), so it is never saved or answered twice; a retry gets the original answer back, including product cards<\/li>\n<li>A saved conversation is tied to its key: if the key had to be replaced, earlier messages stay visible and a new conversation starts instead of a broken one<\/li>\n<li>Knowledge base: page addresses keep their exact path and query (for example \/Guide and \/guide are separate pages); only the scheme and host are case-insensitive<\/li>\n<li>Pro: opening an empty chat no longer replaces the order attribution of an earlier conversation \u2014 it is set only after a visitor message is accepted<\/li>\n<li>Pro: the conversion rate now compares the same conversations (started in the period) instead of mixing two groups<\/li>\n<li>Packaging: removed a stray runtime file<\/li>\n<\/ul>\n\n<h4>3.7.2<\/h4>\n\n<ul>\n<li>Live agent: agent replies are now saved as one message in the conversation transcript, so the admin screen and the visitor see the same messages with the same IDs; your own reply is no longer shown twice when the screen refreshes at the same moment<\/li>\n<li>Saving problems are reported: if an AI answer could not be stored it is still shown, with a note; hand-off and \"release to bot\" report failures instead of claiming success<\/li>\n<li>Retrying after a lost connection no longer saves a lead or message twice, and does not pay for a second AI answer<\/li>\n<li>Product cards now also appear when a chat returns from a human agent to the AI; the visitor's language is kept<\/li>\n<li>Trusted proxy list: malformed entries (such as a wrong \/prefix) are rejected and reported<\/li>\n<li>Rate limiting is now exact under simultaneous requests, also on sites without an object cache<\/li>\n<li>Conversations end on the server after the Session Timeout; \"None\" and \"Tab\" persistence now behave as described; old session cookies are migrated or removed<\/li>\n<li>Knowledge base: each web page is identified by its address (two pages with the same title stay separate), a failed re-import keeps the previous version, imports are size-limited, and sitemap imports can continue where they stopped<\/li>\n<li>Pro: office hours support overnight ranges and fall back to the site timezone; analytics use the selected period, site timezone, paid orders minus refunds and each order's currency<\/li>\n<li>Pro: order lookup understands short order numbers and an email sent in a following message (both are still required)<\/li>\n<\/ul>\n\n<h4>3.7.1<\/h4>\n\n<ul>\n<li>Fixed: the \"Start free trial\" button opened a blank page<\/li>\n<li>Chats switched back from a human agent to the AI now show the AI's reply instead of losing it<\/li>\n<li>Live agent screen: fewer duplicated or skipped messages<\/li>\n<li>Lead form: double-clicking while the chat is starting can no longer send the lead twice<\/li>\n<li>Visitor messages and agent replies report an error if they could not be saved<\/li>\n<li>Proxy setting: choose None, Cloudflare (verified against Cloudflare's published IP ranges) or your own trusted proxy IPs<\/li>\n<li>Removed the optional ip-api.com geolocation. With Cloudflare, the visitor's country comes from Cloudflare's own header; no visitor data is sent to a third party<\/li>\n<\/ul>\n\n<h4>3.7.0<\/h4>\n\n<ul>\n<li>Privacy: visitor geolocation is now off by default and must be switched on by the site owner; the widget no longer loads Google Fonts<\/li>\n<li>Language settings (multi-language, default language, auto-detect) are now available to everyone under Sparxio \u2192 Behavior<\/li>\n<li>Lead form only confirms success after your details are actually saved, and keeps what you typed if saving fails<\/li>\n<li>Rate limiting now uses the real visitor IP by default, with an option for sites behind Cloudflare or a proxy<\/li>\n<li>Knowledge base search now understands Urdu, Arabic, Chinese and accented languages<\/li>\n<li>CSV exports are protected against spreadsheet formula injection<\/li>\n<li>Deleting a chat now also removes its related live-agent messages<\/li>\n<li>Safer session keys and clearer messages when the chat cannot connect<\/li>\n<\/ul>\n\n<h4>3.6.5<\/h4>\n\n<ul>\n<li>First public release on WordPress.org.<\/li>\n<\/ul>","raw_excerpt":"AI chatbot for WordPress. Use your own Claude, GPT, Gemini, DeepSeek or OpenRouter key. Unlimited knowledge base, lead capture, 30 languages.","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin\/351163","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin"}],"about":[{"href":"https:\/\/wordpress.org\/plugins\/wp-json\/wp\/v2\/types\/plugin"}],"replies":[{"embeddable":true,"href":"https:\/\/wordpress.org\/plugins\/wp-json\/wp\/v2\/comments?post=351163"}],"author":[{"embeddable":true,"href":"https:\/\/wordpress.org\/plugins\/wp-json\/wporg\/v1\/users\/haamzaa"}],"wp:attachment":[{"href":"https:\/\/wordpress.org\/plugins\/wp-json\/wp\/v2\/media?parent=351163"}],"wp:term":[{"taxonomy":"plugin_section","embeddable":true,"href":"https:\/\/wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_section?post=351163"},{"taxonomy":"plugin_tags","embeddable":true,"href":"https:\/\/wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_tags?post=351163"},{"taxonomy":"plugin_category","embeddable":true,"href":"https:\/\/wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_category?post=351163"},{"taxonomy":"plugin_contributors","embeddable":true,"href":"https:\/\/wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_contributors?post=351163"},{"taxonomy":"plugin_business_model","embeddable":true,"href":"https:\/\/wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_business_model?post=351163"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}