MxChat – AI Chatbot & Content Generation for WordPress

बदलांची यादी

3.2.20 – August 28, 2026

• New: The knowledge base can now populate and maintain your OpenAI Vector Store — every addition, edit and deletion is mirrored automatically, and an Import Existing Knowledge Base button (or the wp mxchat vectorstore-import command) uploads what you already have in resumable batches; role-restricted entries are never uploaded.
• New: Chat answers can no longer link to pages that do not exist — every finished answer, streaming included, is checked and links to your own site that would 404 are removed while the sentence stays intact.
• New: A Strip Unapproved Links setting separates link enforcement from Citation Links, so invented links are removed even with citations off; on for new installs, opt-in for existing sites.
• New: A third live-agent handoff destination, Webhook — send handoffs to your helpdesk, CRM or automation flow as a signed JSON POST, with its own availability schedule and delivery errors shown on the settings screen.
• New: The pre-chat email form can show a consent checkbox with your own label and Privacy Policy link, optionally required, enforced on the server — and each capture records whether it was ticked, when, and the exact label shown, visible in Leads, the CSV export and privacy exports.
• New: The chatbot can be placed with a Gutenberg block, or an Elementor widget on Elementor 3.5+ — inline or floating, with a bot picker when Multi-Bot is active, and a neutral placeholder in the editor instead of a live chat.
• New: A Document Upload import method takes .docx, .txt and .md files straight into the knowledge base; the file itself is never stored and re-uploading the same name replaces rather than duplicates.
• New: A Custom Retention (Days) field on Transcripts lets you delete transcripts after any number of days instead of only the weekly and monthly presets.
• New: Pinecone knowledge entries can now be edited in the admin — saving re-chunks and re-embeds in place, so fixing a typo no longer means delete and re-import.
• New: Each ACF field group gains a group-level toggle that includes or excludes every field in it at once, with a distinct half-way state when only some are included.
• New: Add-on AI tools now receive the model’s full tool-call arguments, so a tool declaring typed parameters gets them delivered instead of everything but the query being discarded.
• New: Three developer hooks for custom retrieval — mxchat_retrieval_query rewrites the lookup text without touching the transcript, mxchat_pinecone_query_body tunes Pinecone queries, and mxchat_session_ended fires on both deletion and retention expiry.
• New: The mxchat_final_response_text filter runs on the complete answer on every response path, streaming included, before it is shown and saved.
• Security: With Contextual Awareness on, page text captured from the visitor’s browser is now fenced as untrusted reference material, capped at 8,000 characters and required to belong to your own site, so instructions hidden in comments or reviews are far less likely to be followed.
• Fixed: ACF field toggles now identify each field precisely, so same-named fields in different groups no longer share one toggle or switch each other back off; existing exclusions are migrated on the safe side with a one-time notice.
• Fixed: All remaining Pinecone reads use the correct call shape and respect a configured namespace, so listings, chunked answers and already-indexed detection work on serverless indexes instead of silently returning nothing.
• Fixed: Long manually pasted entries each keep their own identity — previously a second long pasted document silently deleted the first one’s content, in Pinecone and the local database alike.
• Fixed: Shortening an entry below the chunking threshold now removes its old chunk records, so answers can no longer draw on stale text alongside the new version.
• Fixed: Knowledge entries whose address contains percent-encoded characters, such as non-English permalinks, no longer go missing or save a duplicate under a different identity.
• Fixed: Importing Persian, Hindi and other Indic-script content no longer splits words at invisible joiner characters; re-import content added earlier to repair it.
• Fixed: The pre-chat email form now scrolls when taller than the chat window, so the submit button stays reachable — especially on phones with the keyboard open.
• Fixed: Product cards from filtered WooCommerce searches display correctly after a refresh instead of showing raw markup, and history replay now recognizes every MxChat card type automatically.
• Fixed: Cards from an AI tool answer keep their position below the answer text when the chat is refreshed or reopened, matching the order the visitor originally saw.
• Fixed: A floating chatbot placed by shortcode or block on a page that also auto-displays one no longer renders two overlapping bubbles with duplicate element ids.
• Fixed: With citation links on, real published pages on your own site and web-search source links are no longer stripped from answers as unknown.
• Fixed: The Sources tab in Message Context now lists the documents behind tool-answered replies, and tells apart a search that found nothing from a reply with no recorded retrieval.
• Fixed: The “Translation loading for the mxchat domain was triggered too early” notice on WordPress 6.7 and newer is resolved.
• Fixed: A custom retention value set by hand or by code is no longer reset to zero when other transcript settings are saved.
• Fixed: Status pills on admin screens outside API Access now render with their intended styling instead of as plain text.
• Fixed: The chat message input has a real accessible name for screen readers, rather than relying on placeholder text that disappears on typing.
• Fixed: Sites that saved the AI Tools screen on earlier versions now receive the recommended usage guidance for the handoff tools; hints you wrote yourself are never changed.
• Improved: Screen reader support for the conversation is complete — a streamed answer is announced once when it finishes rather than continuously as it types, the waiting state and error notices are read out, and restored history stays silent.
• Improved: On phones and tablets the chat input no longer takes focus after each reply, so the keyboard stays closed while the visitor reads; desktop is unchanged and the mxchat_autofocus_after_reply filter forces either behavior.
• Improved: Saving a WooCommerce product no longer generates two knowledge-base embeddings for the same product, halving embedding API usage on product saves.
• Improved: The daily model health check now watches every model in use, including per-bot models from Multi-Bot, via the new mxchat_models_in_use filter.
• Improved: Replacements for retired AI models live in one shared mapping used across the plugin and its add-ons, and content generation is now rescued from any retired model.
• Improved: The Content Generation model picker derives from the central model catalog, so new models appear automatically and a saved model that is no longer offered stays selected and labeled.
• Improved: The Video Card Match Threshold is now a slider with a live value readout, matching the other threshold controls; its range and limits are unchanged.
• Improved: The admin Testing panel reports how many links the guard checked and which it removed, which was previously silent.
• Improved: On non-English sites, the chat widget’s default texts are saved in the site language on a fresh install.
• Improved: A Pinecone listing call that genuinely fails now logs that the fallback fired instead of masking it.

3.2.19 – August 15, 2026

• Fixed: Hebrew, Arabic and other right-to-left PDFs no longer import with reversed text, and a new WP-CLI repair command fixes entries imported before this update in place.
• Fixed: Sites still set to the retired Claude Opus 4.1, or to older retired Claude models, are automatically moved to the current Claude generation of the same tier and shown a notice.
• New: MxChat checks once a day that your selected AI model still exists and warns you on the AI Models screen and dashboard before a retired model can silence your chatbot.
• Improved: Claude API costs drop on most sites — Anthropic prompt caching now runs automatically, ahead of Anthropic’s September 1 Claude Sonnet 5 price change.
• Fixed: Content generation no longer fails with an Unsupported value error on GPT-5.4 Mini and GPT-5.4 Nano, and any model that rejects a reasoning setting is retried once without it.
• Improved: The xAI Grok lineup is current again — Grok 4.6 and the rest of the new generation are offered first, and existing selections keep working.
• New: Settings edits are protected — changed fields show an Unsaved marker, leaving mid-edit asks for confirmation, and edits are handed to the browser for saving if you leave anyway.
• Fixed: Imported content keeps its currency symbols, and Arabic, Hebrew, Hindi and Thai text keeps the marks its script requires; re-import content added through the bulk website, URL or PDF import tools to repair entries indexed earlier.
• Improved: Leftover HTML character codes are converted to readable text before indexing; re-import affected entries to clean up existing ones.
• Fixed: Draft posts published by import tools or scripts are no longer indexed under your homepage address.
• Fixed: WooCommerce prices are indexed in your store’s base currency with the currency code, and on multi-currency stores the chatbot no longer mixes two currencies in one reply; re-import products to update older entries.
• New: The Notification Email field accepts up to five comma-separated addresses, and an invalid address is refused with a message naming it instead of silently breaking notifications.
• Improved: Visitor names and emails from the pre-chat form move into MxChat’s sessions storage automatically — the Leads tab and live-agent greetings work exactly as before.
• Improved: Link-click records are covered by WordPress’s privacy export and erasure tools, and old records anonymize and delete themselves over time.
• Fixed: A YouTube video card now appears only when the video actually matches the question, with a new match threshold setting — and video cards can be switched off entirely.
• New: Transcripts show which AI Tools ran on each message, with timings and errors; tools handling money, customer records or handoffs log only that they ran.
• Improved: The Slack and Telegram handoff tools arrive with their usage note prefilled, so automatic handoff works without extra setup; you can reword or clear it.
• Fixed: Inspecting a Pinecone knowledge entry works, and deletes on Pinecone setups using a namespace remove the right copy.
• Improved: Conversations are stored once instead of duplicated into the options table, and leftover duplicates clean themselves up in the background.
• Fixed: Shared admin features work again on the Transcripts and License pages, and two pieces of admin text no longer point at settings that do not exist.

3.2.18 – August 8, 2026

• Fixed: OpenAI Vector Store knowledge base search works again — an outdated request parameter caused every search to fail silently, so the chatbot answered without your knowledge base content.
• Fixed: The knowledge base status readout now correctly shows how many vector stores are configured instead of always reporting none.
• Fixed: Content updates made outside the editor are no longer skipped. When a post was published by an import tool, a scheduled post going live, or a script, the first edit after it was silently left out of the knowledge base, so the chatbot kept answering from the original version.
• Fixed: PDFs shared in chat no longer store unreadable pages when an embedding request fails part-way through. Failed pages are skipped and recorded in the Debug Mode log, and if no page can be read the chatbot now gives the real reason instead of calling the file empty or unsupported.
• Fixed: Clearing a conversation, deleting a transcript, or erasing a visitor’s data through WordPress’s privacy tools now removes every trace of that session’s stored state. Some of it was previously left behind forever.
• Fixed: Job listings imported from the content selector now include their location, job type and company name, matching listings saved in the editor. Listings imported earlier keep their old text until you import them again.
• Fixed: Post titles are now added to the knowledge base exactly as written. Curly quotes, apostrophes and long dashes were stored as raw character codes, and protected or private posts gained a Protected prefix — all of which could surface in answers. Entries indexed earlier keep their old titles until you import them again.
• Fixed: A short description made up only of page-builder shortcodes or spaces no longer adds an empty Short Description heading to the indexed text.
• Improved: Custom field names containing hyphens now read as words in the indexed text on both import routes, instead of only one of them.
• Improved: Chat sessions no longer bloat your site’s options table. Per-session details were saved as settings rows that were never cleaned up, so busy sites accumulated thousands, some loading on every page view. Sessions now live in their own table, and existing rows are moved across automatically in the background after you update.
• New: Old chat sessions are tidied up on their own. Sessions untouched for 30 days are removed automatically — the window is adjustable with a developer filter — and the cleanup runs even on sites with WordPress scheduled tasks disabled.
• Fixed: Sitemap imports now tell you why they failed instead of pointing at an empty status area — for example, an API key missing the required permission is now named as the reason.
• Improved: Knowledge base import errors from OpenAI, Gemini and Voyage now pass along the provider’s own explanation instead of a generic invalid key message.
• Improved: Chat-side embedding failures are now recorded in the Debug Mode log with the provider’s real reason, matching knowledge base imports.
• Fixed: In the content selector, a selected item’s tick mark was white on a white box and effectively invisible. Selected items now show a clearly filled checkbox.

3.2.17 – August 5, 2026

• Fixed: Japanese, Chinese and Thai content is no longer erased, split into oversized chunks, or stripped of rare characters during knowledge base imports.
• Fixed: Custom embedding providers such as Ollama, LM Studio and Azure now work end to end — the permanent mismatch banner is gone, and no cloud API key is needed for imports or automatic post syncing.
• Fixed: Scheduled posts now enter the knowledge base the moment they go live, and the developer hook for customizing indexed content also runs during automatic post syncing.
• Fixed: The WordPress content import window now fits phone screens, so its buttons are always reachable.
• Fixed: The hybrid keyword boost and smart asset loading toggles now show the saved confirmation like every other setting.
• New: Every settings tab has its own shareable link that opens directly on that tab, including nested and add-on tabs.
• Improved: Knowledge settings are centralized under Knowledge — ACF PDF extraction is now a persistent setting on the ACF Fields tab, and the hybrid keyword boost lives on the new Chunking and Retrieval tab. Saved choices carry over.
• Improved: The Editor Assistant toggle moved to the Content page’s Settings tab, next to the other content tools.
• Improved: The FAQ now documents custom and local embedding providers such as Ollama and LM Studio.
• Improved: Settings holding a Pinecone API key are no longer loaded into memory on every page view.

3.2.16 – August 2, 2026

• New: Chat conversations are now covered by WordPress’s built-in privacy tools — export requests return readable transcripts, and erasure requests delete conversations, captured emails, saved history and document traces, for both logged-in and anonymous visitors.
• New: Optional hybrid keyword boost for the WordPress-database knowledge base, off by default. It combines keyword matching with the existing similarity search so exact tokens such as product codes, SKUs and error codes find the right document, and Transcripts labels each match Vector, Keyword or Both.
• New: If your AI provider starts rejecting the configured model, MxChat now shows a persistent admin notice naming the model and linking to Settings. Previously only visitors saw the error.
• Fixed: Security — hardened validation of chat session identifiers throughout the plugin. Sites using automatic transcript emails should update.
• Fixed: Security — tightened the permission checks around MxChat’s admin scripts and admin-only actions, so they load and run only for users who can manage plugin options.
• Fixed: Security — removed an unused block of stored settings data that was no longer needed.
• Fixed: OpenAI retires the GPT-5.1 Chat Latest and GPT-5.3 Chat models on August 10, 2026. Both are removed from the picker and affected sites switch to GPT-5.6 Sol automatically, with an admin notice explaining the change.
• Fixed: Unpublishing, trashing or making a post private now always removes it from the knowledge base, including status changes made by scheduled-expiry plugins that bypass the save screen. A new command, wp mxchat prune-unpublished, clears entries left by earlier unpublishes.
• Fixed: Streaming replies arrive word by word again on hosts behind a proxy such as nginx, instead of all at once after a pause. Four PHP warnings per affected chat are gone with it.
• Fixed: Quick Question buttons render at their normal size again. In 3.2.15 the new theme-protection styles let the list compress its buttons to fit the box, so the scrollbar never appeared.
• Fixed: The Loops email-capture messages no longer send you looking for a field that is not on that screen. Both now name the API Keys tab and link straight to it.
• Fixed: Removed a duplicate save-action registration on the knowledge-bot selector that pointed at code which does not exist. It would have crashed the admin screen if load ordering ever changed.
• Improved: Knowledge base import errors now carry the embedding provider’s real reason, such as an invalid API key or exhausted credit, name the model, and say whether embedding or storage failed.
• Improved: Models with an announced retirement date now show that date in the picker and disappear once it passes. A model you already have selected stays visible in Settings.
• Improved: When the knowledge base has nothing relevant, the chatbot is now told so directly instead of receiving a no-information note dressed up as knowledge base content, so it simply says it does not know.

3.2.15 – July 28, 2026

• Fixed: DeepSeek chat works again. DeepSeek retired its older API model names on July 24, 2026, which broke every DeepSeek-powered chat; the model picker now offers DeepSeek V4 Flash and V4 Pro, and sites still set to an older DeepSeek model switch to V4 Flash automatically on update.
• New: Claude Opus 5 is available in the model picker — Anthropic’s newest Opus model, the same price as Claude Opus 4.8, working across chat, streaming and the AI content tools.
• New: Optional performance setting to load chatbot files only on pages where the chatbot actually appears. Off by default, and helpful for reduce-unused-CSS-and-JS findings in performance audits.
• New: Slack live agent handoff can route every conversation into one shared channel your team already monitors, one thread per visitor, instead of creating a channel per visitor. Leave the new field blank and nothing changes.
• New: Optional setting to archive a conversation’s Slack channel when an agent ends the chat, so channels stop piling up. Off by default.
• New: Place your knowledge base content anywhere in your AI instructions using the context placeholder. Leave it out and MxChat works exactly as before.
• New: The SEO content table now shows an average search position column from the last 28 days, available with the Advanced Content add-on connected to Search Console.
• Improved: When Search Console is not connected yet, the SEO content table now explains that connecting it fills the clicks, impressions and position columns, with a link to the Settings tab, instead of showing unexplained dashes.
• Improved: SEO content table sorting now keeps every post in the list on every filter, with posts that have no data grouped at the end.
• Improved: X.AI errors now include the provider’s specific reason, such as the exact model name it could not find, alongside the general explanation.
• Improved: Sites using a delayed or on-interaction script loading strategy no longer perform an unnecessary database write on every page view.
• Fixed: The chat widget now defends itself against website themes whose styles bleed into it, including the header menu. Your own custom widget CSS keeps working unchanged.
• Fixed: When an AI provider returns a successful but empty reply, the chatbot now shows a clear message asking the visitor to try again instead of an empty chat bubble. Streaming chats close out the same way.
• Fixed: Provider errors now pass along the provider’s actual explanation instead of a generic Unknown error, across image providers, embeddings, knowledge base search, web search, streamed replies and OpenRouter.
• Fixed: Conversations handled by a human now show as Live Agent in the Transcripts viewer and in emailed transcripts, instead of everything being labeled AI Assistant.
• Fixed: The streaming test button on the settings page now works with the newest Claude models, which previously returned an error even though chat itself worked.
• Fixed: Turning on developer mode no longer re-runs the plugin’s activation and database migration routine on every page load.
• Fixed: The hourly rate-limit reset now re-creates itself if the scheduled task ever goes missing, so visitors are never left rate-limited longer than intended.
• Fixed: On sites where WordPress scheduled tasks are disabled, the hourly fallback check no longer loads a duplicate copy of the plugin’s internals mid-request.

3.2.14 – July 18, 2026

• New: Editor Assistant — optional AI writing actions right inside the WordPress block editor. Select a paragraph, heading, list, or quote block and rewrite it (concise, expanded, formal, or casual), summarize it, translate it to another language, continue writing, or fix grammar and spelling, then Accept or Discard. It is off by default and uses the AI model you already configured.
• New: You can now add YouTube videos to your knowledge base. A new YouTube option on the Import screen takes a video link and, per video, either auto-fetches its title, channel, and captions or lets you write your own description. When a visitor’s question matches a video, the answer includes it as a playable embed right inside the chat that loads no YouTube player or Google cookies until the visitor taps play.
• New: Live agent handoff can now follow an availability schedule, so visitors are only offered a human during the days and hours your team is actually reachable, and the chatbot simply keeps answering outside them. Slack and Telegram each get their own independent schedule on their own settings tab, so a channel staffed at different hours keeps its own calendar. It is off by default and uses your site timezone.
• New: Added the latest OpenAI GPT-5.6 models — Sol, Terra, and Luna — for both your chatbot and content generation.
• New: MxChat AI Search now appears on the Pro and Extensions page alongside the other add-ons, so you can discover it from inside your dashboard.
• New: Developers can now add their own trusted links to the chatbot’s allowed-links list with the new mxchat_valid_urls filter, so links returned by custom function-calling tools stay clickable in replies.
• Fixed: Editing a Knowledge Base entry no longer throws away your work. Clicking outside the edit box, or selecting text and releasing the mouse just past its edge, used to close it and discard everything you had typed. The box now closes only when you ask it to — the close or cancel button, the Escape key, or a successful save — and confirms first if you have unsaved changes. The same fix applies to the Add Tool and Edit Tool dialog on the Actions screen.
• Fixed: Product and image search now correctly refine your search terms when a GPT-5 model is selected. Previously the refinement step silently stopped working and fell back to the raw text, weakening results.
• Fixed: The Telegram live-agent webhook is no longer accepted without verification when a secret token has not been set; requests are now validated by origin and a reminder is shown to configure a secret.
• Fixed: The Testing page’s chatbot replica now uses the exact same knowledge base as your live chatbot. On sites running Pinecone with the Multi-Bot add-on active, the testing chat was quietly searching the WordPress database instead.
• Fixed: Automatic transcript deletion now repairs its own schedule if the scheduled cleanup task is ever lost, so old transcripts no longer stop being deleted while your settings still say retention is on. The Transcripts settings also now show when the next cleanup will run.

3.2.13 – July 10, 2026

• New: Claude Sonnet 5 is now selectable as both a chat model and a content generation model.
• New: The Knowledge Base Custom Post Meta section can scan your content and suggest custom meta keys as clickable options, so you can add non-ACF meta to the embedding whitelist without knowing the exact key names.
• Fixed: Knowledge Base imports of PDFs and web pages no longer fail with a 403 error on firewall-protected hosts (SiteGround, Wordfence, Cloudflare) — MXChat now identifies itself with an honest, versioned MXChatBot user agent you can allowlist if needed.
• Fixed: PDFs a visitor links in a live chat now use the same MXChatBot identity, so a firewall that allowlists MXChatBot lets them through too.
• Fixed: The close button on the pre-chat greeting bubble now works on chatbots with a custom bot ID, including Multi-Bot setups, not just the default chatbot.
• Improved: The Custom Post Meta help text now points to the built-in key scanner and notes that array and repeater values are flattened during embedding.

3.2.12 – June 30, 2026

• Fixed: Resolved a WordPress.org packaging issue from the previous release that could cause the update to fail to download or appear to hang in the WordPress dashboard on some sites. This maintenance release republishes the plugin so every site can update normally and receive the recent improvements from 3.2.11 — including the per-provider Test API key buttons, built-in WPML and Polylang translation for the chat widget, Google Gemini web search, the optional Max Input Length character counter, cleaner Slack live-agent links, the Knowledge View indexed content panel, and the security and Pinecone matching fixes. No functional changes from 3.2.11; no settings or data are affected.

3.2.11 – June 29, 2026

• New: Each AI provider API key field (OpenAI, X.AI, Claude, DeepSeek, Google Gemini, OpenRouter) now has a Test key button that checks whether the key actually works in one click, so you can confirm a key is valid right after pasting it instead of finding out only when a chat fails. It runs a quick, free validation check and never spends credits.
• Fixed: When restricting knowledge by tag under Knowledge then Role Restrictions, you can now enter a tag by its display name or its slug. Previously only the exact slug worked, so typing a real tag’s name returned a confusing error; the field is now labeled Tag (name or slug) and gives an actionable message when no matching tag exists.
• Fixed: On sites using Pinecone for knowledge, answers added directly through Knowledge then Import Options then Direct Content (manual entries with no source link) are now used by the chatbot when they are the best match. Previously the bot could reply that it did not have the information even though the manual entry clearly matched, and the testing panel showed zero sources used; both are now correct.
• New: Built-in WPML and Polylang compatibility for the chat widget text. The widget’s visible strings (top bar title, greeting, AI agent label, input placeholder, the email and name capture form copy, and the satisfaction prompts) now show up automatically in WPML String Translation, so you can translate the widget into each language without registering every field by hand.
• New: Optional Max Input Length setting caps how many characters a visitor can type or paste into a single message, so you can stop overly long pastes from being sent to the AI. It sits just below the Input Placeholder option in the chatbot settings. Leave it at 0 for unlimited, which is the default and keeps existing behavior unchanged.
• Fixed: Security hardening for the chat intro message setting, following a Wordfence advisory. The intro message is now escaped when shown on the settings page and sanitized when saved, so a crafted value can no longer run script in the admin area on multisite sites or sites where unfiltered HTML is disabled.
• Fixed: When a live agent replies from Slack with a link, the website visitor now sees a clean, clickable link instead of Slack’s raw formatting with a stray closing bracket. Slack user and channel mentions and escaped characters are also tidied up before the message reaches the visitor.
• New: The Slack live-agent channel now shows the visitor’s name and email at the top of the conversation when they were captured at the start of the chat, so your agent can see who they are talking to instead of just a session ID and a user ID of zero for guests.
• Improved: When a maximum message length is set, the chat box now shows a small live character counter as the visitor nears the limit, ramping from a neutral color to amber to red, with a gentle nudge if they reach the cap. This replaces the old behavior where typing past the limit silently did nothing and looked broken. The counter uses only numbers, so it reads correctly on sites in any language.
• New: When the …