AI Engine Pro - All Versions & Changelog | Zeebrar
AI Engine Pro Version History
20 versions available
2 Credits
per install
Subscribe to connect and install
v3.5.5
LatestVerified Safe
Released 1.9 MB
Fixed
Path traversal vulnerability in create_image and prevented chatbot discussions from being taken over by another logged-in user.
Add-ons were reported as disabled whenever options were fetched outside the admin context.
Max Tokens entered with a thousands separator (e.g. the Danish "64.000") was read as 64 and capped responses.
Content Aware placeholders now resolve automatically in chatbot instructions without requiring a toggle.
Setup Assistant no longer shows "Connect an AI Provider" as incomplete when only the Fast model is deprecated.
Realtime instructions now resolve placeholders like {FIRST_NAME} into their values.
MCP tools generated from WordPress REST endpoints could break Google Gemini due to enum on non-string types.
Changing the type of an AI environment now drops fields from the previous type (endpoint, region, deployments), preventing engines from calling the wrong provider's endpoint.
The "Default AI Environment not configured" warning no longer appears when a Chroma embeddings environment generates its own vectors.
The Usage widget on the Dashboard no longer overflows its panel when numbers are wide.
Anthropic's streaming ping keepalive events are now ignored instead of being logged as an unknown stream data type.
Improved
Reworked embeddings sync — pages are no longer marked stale without real changes, the background task (now called Maintenance) runs for all environments, processes batches within a time budget, no longer gets blocked by a failing vector, and can be disabled in Settings > Knowledge > Sync Settings.
API key and token fields are now masked with an eye toggle to reveal them.
Marked the original GPT-5 models (gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro) as deprecated per OpenAI's December 10, 2026 shutdown.
The fullscreen resize button now uses thin corner-bracket icons that match the close button.
OpenAI Vector Store document uploads now accept multiple files at once.
Added
User Memory added to the add-ons list.
Optional capability filter for get_chatbots() to fetch only chatbots whose model supports function calling.
Other
🎵 Discuss with others about Ai Engine on [the Discord](https://discord.gg/bHDGh38).
🌴 Keep us motivated with [a little review here](https://wordpress.org/support/plugin/ai-engine/reviews/). Thank you!
🥰 If you want to help us, check our [Patreon](https://www.patreon.com/meowapps). Thank you!
🚀 [Click here](https://trello.com/b/8U9SdiMy/ai-engine-feature-requests) to vote for the features you want the most.
Hold to Talk button on mobile Realtime chatbot no longer triggers the context menu (copy, select) when held.
Sending is now blocked while a file is still uploading, with a spinner on the send button and a progress bar on the file preview until upload completes.
Eliminated the gap between the chatbot and the keyboard on iOS by locking body scroll while the mobile chatbot is open.
Anthropic safety refusals now show a readable message instead of an empty reply.
OpenClaw link in the readme now points to our own article.
PHP 8.2+ deprecation warning caused by an undeclared `$extraData` property on `Meow_MWAI_Reply`.
v3.5.3
Verified Safe
Released 1.8 MB
Fixed
Filenames with underscores (e.g. `Some_File_2026.pdf`) were getting partially italicized by the chatbot's markdown renderer.
ReferenceError (`data is not defined`) in the chatbot response handler that masked the real error message when a host returned a non-JSON body.
The Push All button showed "(null)" when a post type had zero matching posts.
The `wp_update_option` MCP tool schema no longer logs a "problematic union type" warning on every `list_tools` call.
The Meow Apps menu icon now shows correctly in both the expanded and collapsed sidebar states.
Hotfix for the MCP endpoint URL being hidden until a bearer token was generated, even though OAuth doesn't need one. It now appears as soon as the MCP Server is enabled.
Added
v3.5.2
File unavailableVerified Safe
Released 1.8 MB
Added
Setup Assistant on the Dashboard that walks through essential configuration with a progress bar and per-step actions.
Direct file upload to OpenAI Vector Store via a new Documents tab, with async status polling, Sync from OpenAI action, and clearer PHP upload-limit errors.
`setField` and `prefill` methods to the AI Forms JS API for setting values programmatically without manual `dispatchEvent` workarounds.
Improved
Redesigned the Dashboard Usage panel into an analytics card with headline, week-over-week delta, daily bar chart, and provider/peak/average/per-query tiles.
Reorganized the Modules tab into clearer sections with short intros, concise descriptions, renamed Utilities to AI Copilot, and surfaced MCP and Public API as proper modules.
v3.5.1
File unavailableVerified Safe
Released 1.8 MB
Added
Popup Icon Size option in chatbot settings to resize the popup trigger without custom CSS.
Fixed
Chatbots admin preview now keeps long discussions, fullscreen toggles, and resize actions contained within the preview pane instead of clipping or overflowing the viewport.
Chatbot rendering bug where a `$` inside an inline code span caused other message text to leak into the code display.
OAuth 2.1 with Dynamic Client Registration for the MCP server, allowing Claude Desktop and other browser-driven clients to connect without a shared bearer token.
Per-quality image generation (auto/low/medium/high) for GPT Image models, available in the Image Generator UI and as a global default in Settings → Images.
Fixed
Pulling a remote OpenAI vector store no longer creates entries containing raw JSON error bodies for files uploaded with purpose=assistants.
The `mwai_allow_setup` filter now properly grants menu and REST API access to non-admin roles, instead of being overridden by a hardcoded `manage_options` check.
Tiktoken vocab cache is now scoped per WordPress install, preventing permission conflicts on multi-tenant hosts.
v3.4.8
Verified Safe
Released 1.8 MB
Fixed
Resolved OpenAI Responses API "No tool output found" errors during chained recursive tool calls and static-only turns. Static-skip is now disabled for Responses API because every `function_call` must be answered.
Managed-mode WP AI Client and AI Engine integrations now satisfy WordPress 7 AI plugin credential requirements, preventing false rejections for Ollama, OpenRouter, Mistral, Perplexity, and Replicate.
Removed redundant vector-DB addon initialization to prevent idle "OpenAI Vector Store ID is not configured" logs.
Resolved PHP 8.4 nullable-parameter deprecations in query and MCP helpers.
ChatML base now supports string-shaped `error` fields in API responses.
Added
v3.4.7
File unavailableVerified Safe
Released 1.8 MB
Added
GPT-5.5, GPT Image 2, and Claude Opus 4.7 to the model lists.
New Environments panel on the Dashboard with brand-colored rows, smart setup messages, and warnings for missing or deprecated default models.
Live timer on the Image Generator "Generating..." row so progress is visible.
Split print-to-PDF into its own toggle, moved behind a new "More options..." modal in Appearance settings.
System-prompt hint for Anthropic's code_execution tool so Claude uses the sandbox instead of refusing.
Improved
v3.4.6
File unavailableVerified Safe
Released 1.7 MB
Added
Print-to-PDF button next to the copy icon on the last AI message, allowing export of the full conversation via the browser's Save as PDF dialog.
Retention setting for discussions cleanup under Settings > Chatbot > Discussions, with a `mwai_discussions_retention_days` filter for overrides.
Fixed
Chatbot auto-scroll no longer fights users who scroll up during streaming.
AI Form and Chatbot blocks no longer save as "Unsupported" placeholders when used in patterns created via Appearance > Editor.
Hardened chatbot parameter processing so non-string values no longer crash the frontend with "trim is not a function".
v3.4.5
File unavailableVerified Safe
Released 1.7 MB
Fixed
Ensure additional CSS classes set in the block inspector.
Stop mapping tool categories to annotation titles so MCP tools display their correct names.
Resolve an MCP dispatch type mismatch that caused some MCP tools to fail.
Added
Support for GPT-5.4 Pro, Mini, Nano, and GPT-5.3 Chat models.
Improved
Add new getStatus(), hasAI(), and hasMCP() API helpers (deprecated the older checkStatus() method).
v3.4.4
File unavailableVerified Safe
Released 1.6 MB
Fixed
Hotfix resolves MCP server connection failures with clients using protocol version 2024-11-05 by adding automatic version negotiation.
Resolve a broken access control issue in the AI Forms shortcode to ensure only authorized users can access protected content (Private Page/Post).
Prevent crashes when working with multi‑modal messages.
Prevent the Embeddings screen from crashing when closing a modal.
Improve the discussions shortcode by falling back to customId to avoid invalid class names.
Styles for the AI Chatbot Block are back.
Added
v3.4.2
Released 1.6 MB
Added
Display shortcut prompts and names in the Discussions tab.
Introduce image embeddings support (Gemini Embedding 2) with multimodal embedding: bulk media push, and an AI-powered Library Search that replaces the native Media Library Search.
Fixed
Resolve a broken access control issue in the AI Forms shortcode to ensure only authorized users can access protected content (Private Page/Post).
Prevent crashes when working with multi‑modal messages.
Prevent the Embeddings screen from crashing when closing a modal.
Improve the discussions shortcode by falling back to customId to avoid invalid class names.
Styles for the AI Chatbot Block are back.
Improved
v3.4.1
File unavailableVerified Safe
Released 1.6 MB
Improved
Hide the Editor Assistant functions from the chatbot settings to simplify the interface.
Added
Support for the new GPT-5.4 model for improved AI responses.
Introduce a fully featured Editor Assistant sidebar (with a client-side feedback loop for chained AI actions). It's called Assistant in the Admin Modules.
Introduce new dev filters (`mwai_mcp_server` and `mwai_function_call_params`) for customizing MCP servers and function call parameters.
Allow ignoring posts during embeddings sync, with a “hide” icon for linked posts, a “Show Ignored” modal, and a `mwai_embeddings_sync_post` filter for developers.
Fixed
Hotfix chat sessions so the chat ID resets correctly when needed.
Restore the missing scope for AI Search.
Improved
v3.3.9
File unavailableVerified Safe
Released 1.7 MB
Added
Cross Site now support shorcuts (Quick Actions), blocks (GDPR-friendly), etc.
Improved
Modernized all Gutenberg Blocks.
Fixed
Avoid crashes caused by Claude when using MCP tools together with function calling.
`wp_alter_post` regex mode now handles patterns containing "/" (e.g. Gutenberg block markers) and returns the actual PCRE error instead of a generic one.
Improved
Images and files can now be sent without a text message; engines skip the empty text part for providers that reject it.
AI provider connectors now mentioned in the readme description.
PDF import now remembers the Density, Overlap, and filename-as-title settings between imports.
Marked GPT Image 1.5 and GPT Image 1 Mini as deprecated; default image model moved to GPT Image 2.
Added
Claude Fable 5 model. Marked Claude Sonnet 4, Opus 4, and Opus 4.1 as deprecated.
Web search support for OpenRouter via the Tools & Capabilities section.
Full Screen view for Discussions, a Discussions count on the Dashboard, and fixed filenames with underscores being rendered as italics in the admin discussion view.
Embeddings sync can now be restricted to specific Polylang languages via a comma-separated languages field.
Renamed the user-facing "Units" metric to "Tokens" across the dashboard, queries explorer, insights, and `[mwai_stats]` shortcode, with full back-compat on REST output and legacy settings.
Aligned the Discussions, Insights, and Knowledge layouts by standardizing column ratios and removing custom margin and header overrides.
Added a Refresh button to the Usage panel header, widened the Tokens column in Queries Explorer, and showed "N/A" for queries with no scope.
MCP tool-registration warnings are now always written to the PHP error log instead of requiring the debug logging flag.
Fixed
Stripped inline citation markers from OpenAI's file_search Responses API text that were surfacing as gibberish in chatbot replies.
Stopped embedding the sessionId in chatbot and forms HTML for logged-out visitors, so page caches no longer share one sessionId across all visitors.
Guarded REST AI endpoints so they no longer overwrite the cookie-derived session with an empty client-sent sessionId.
Gemini embedding queries no longer report bogus token counts by correctly reading promptTokenCount from the response.
Dynamic MCP REST tool schemas no longer serialize the meta arg on media/posts/pages as an array, which Claude's MCP validator was rejecting.
Translate Post now translates list items inside modern Gutenberg lists, which were silently skipped since WP 6.1+.
Migrated OpenAI Realtime integration from the deprecated Beta endpoint to the GA API, enabling support for gpt-realtime-2 and new voice models.
Reorganized MCP settings panel with a dedicated section for Bearer Token and Access Level, and a new Connected Apps section to review and revoke OAuth grants.
Generalized the `manage_options` gate in shared code so each Meow Apps plugin gets its own `{prefix}_allow_setup` filter instead of hardcoding `mwai_allow_setup`.
Removed gpt-4o-realtime-preview, gpt-4o-mini-realtime-preview, and gpt-realtime-translate from the model list.
SSE transport for MCP is scheduled for removal in July 2026 and is now hidden from the UI for new users.
Custom OpenAI-compatible provider for Ollama, LM Studio, vLLM, llama.cpp, LocalAI, and similar servers.
Built-in xAI/Grok provider with dynamic model fetching and fallback support.
Insights retention setting with daily cleanup for old log rows. Defaults to Never.
Embedding chunk metadata: source, partIndex, and partTotal, exposed through `mwai_embeddings_vector_metadata` for Pinecone, Qdrant, Chroma, and OpenAI Vector Store. PDF imports can now use the filename as the chunk title, and Modify Embedding can edit the new fields.
Code Engine static/dynamic Behavior now applies to Callable function snippets, skipping AI feedback when all calls are static.
Improved
Reworked onboarding with a default OpenAI environment, Knowledge provider chooser, one-click OpenAI vector store creation, no-key welcome message, and AI Assistant enabled by default.
Reworked Pro license management with a Modify License flow for Re-Validate, Modify, and Remove actions.
Hardened MCP handling by releasing PHP session locks, using proper trash hooks, deduplicating cache busts, enforcing `confirm_write` for non-read SQL, and purging LiteSpeed/WP Rocket caches after post writes.
Usage widget preferences for Price/Units/Queries and Daily/Monthly now persist across reloads.
Query and Reply tabs now point users to Settings > Others > Insights when data is unavailable.
Removed the legacy snippet-vault fallback and unused per-environment usage field.
Refreshed default fallback models to GPT-5.4 and GPT-5-mini, and marked several upcoming OpenAI shutdowns as deprecated (gpt-5-chat-latest, gpt-4.1-nano, o3-mini, gpt-realtime-mini, gpt-image-1, sora-2, sora-2-pro).
Major UI/UX updates! I hope you'll enjoy them, otherwise... let me know! 😊
Redesigned the Usage and Activity widgets with compact CSS-only stacked bars grouped by provider.
Switched chatbot and form shortcode displays to the NekoShortcode component.
Functions section now appears as soon as the model supports it.
Fixed
MCP write helpers (wp_alter_post, wp_update_post) were silently stripping backslashes from Unicode escapes.
Auto-open is now skipped on mobile so a fullscreen chatbot no longer hijacks the screen on page load.
AI Forms not rendering with their theme CSS when embedded via a synced Pattern.
Oversized embedding inputs are now caught before they hit OpenAI's 8192-token limit.
(Hotfix) Two mobile chatbot issues — keyboard pushing header and messages off-screen, and ChatGPT theme's submit button stretching into an oval below the input pill.
Blocks with line breaks breaking after save in the Forms editor.
Display shortcut prompts and names in the Discussions tab.
Introduce image embeddings support (Gemini Embedding 2) with multimodal embedding: bulk media push, and an AI-powered Library Search that replaces the native Media Library Search.
Improved
Preserve links and inline HTML formatting in both the Editor Assistant and Magic Wand tools.
Refactor Magic Wand actions to use system messages.
Clean up old, deprecated options and legacy migration code.
Fixed Quick Test for Anthropic to use the models endpoint.
Chatbot Max Height moved to the Appearance section.
Rename Assistant Mode to Chatbot Mode in AI Forms, you can now use any chatbot to handle your AI Forms.
Prevent unsafe file renaming during metadata updates.
Hotfix SSRF vulnerabilities by using wp_safe_remote_get for external URLs and secure URL fetching in audio transcription and file handling.
Via MCP, ensure scheduled posts created via wp_update_post respect the schedule_for parameter and edit_date flag so they publish at the correct time.
Improve Gemini 3 support, restoring vision capabilities, function calling, and enforcing a single candidate response, and fixed image generation pricing.
Resolve undefined array key warnings in Remote URL sync and only update timestamps when content actually changes.
Improved
Redesign and refine the ChatGPT Theme and Foundation Theme with improved layouts, bubble styling, and more flexible avatar/name display and header titles.
Other
🎵 Discuss with others about Ai Engine on [the Discord](https://discord.gg/bHDGh38).
🌴 Keep us motivated with [a little review here](https://wordpress.org/support/plugin/ai-engine/reviews/). Thank you!
🥰 If you want to help us, check our [Patreon](https://www.patreon.com/meowapps). Thank you!
🚀 [Click here](https://trello.com/b/8U9SdiMy/ai-engine-feature-requests) to vote for the features you want the most.