🔥 Must-Read Before Updating

Since version 6.0, local storage has been added, and some files will be stored in the project directory. During the upgrade process, please keep the public/files and public/core directories. core retains the project's core files, and some default upload paths in the system point to this address. The files directory is for daily files, such as files uploaded in chat conversations. You can manually clean up unimportant files. Other upgrades are the same as for older versions! Please be sure to read the reminder below and confirm that you have read it before updating.

⛺️ About Earlier Versions

Version V6 has been extensively refactored into a brand new version. The update content for each version will be recorded in this section. If you encounter any problems with version upgrades, please check here first to see if it is related to a version update!

[V6.8.0] (Updated on 2025.06.11): Added and refactored multiple functional modules....

🚀 Feat

• Refactored user dialogue history query logic, greatly optimizing query speed for hundreds of thousands or even millions of dialogue records.
• Added support for dynamically obtaining and automatically setting the MySQL connection pool size (not exceeding 80% of the MySQL maximum connections).
• Added agent application sharing function, allowing direct access to the corresponding agent application for use via a link (backend implementation).
• Added a unique identifier for agent application sharing links (backend implementation; original APP applications without a sharing link unique identifier will automatically create one).
• Added a counter for agent application sharing (can be custom edited in the background).
• Added support for line breaks in agent application descriptions.
• Added a status prompt for switching dialogue groups.
• Increased the maximum character count for announcement information to 6000 (originally 3000).
• Rewritten the details page for works in the painting plaza and AI painting modules: full-screen display of image details and new loading animations.
• Adjusted and optimized so that non-super administrators using GPTs through search default to non-shared.
• Added support for setting whether agent applications are shared to the plaza and a query function in the background.
• Adjusted so that non-shared agent applications are not displayed in the agent store and cannot be used by unauthorized users.
• Added display of the invitee's avatar and nickname to the agent recommendation order records.
• Changed the referral income percentage to display the real percentage of the distributor.
• Optimized the logic for individual users to edit and share custom applications.
• Added display of creator user information, category, and type to the agent application details (synchronizes with the new dialogue random AI application content on the mobile H5 end).
• Added adaptation for displaying the deep thinking process of inference and thinking large models.
• Changed the AI large model reply content to the original Markdown (not the processed HTML), making it convenient to copy the original content.
• Rewritten the rendering of mathematical formulas to separately render KaTeX formulas (supports KaTeX's inline math mode and independent math mode).
• Added support for the new dialogue homepage greeting to change with the time and a typewriter effect.
• Added a Popover preview function for detailed descriptions of agent applications.
• Added a Popover description for attachment upload requirements.
• Added a function to export mind maps as PDFs (vector PDF, bitmap PDF).
• Added full-screen, zoom in/out, reset view functions for mind maps, and a one-click copy function for the mind map outline.
• Added automatic creation of relevant indexes for the dialogue record table.
• Added display of the user's last login IP in the background.
• System CLS optimization.
• Optimized so that clicking to use from the APP store will automatically create or open and locate the dialogue history of an existing application.
• Changed the title of the dialogue group to the first question asked (in some cases, the AI's reply is used as the title).
• Added top function setting ②: custom system official website name, custom system official website link.
• Optimized and adapted to prevent elements like buttons from overlapping on some Android phones with smaller screen widths.
• Added a real-time loading indicator for AI painting tasks: newly completed paintings → automatically and seamlessly switch to the result image.
• Optimized system interface UI, operation UI, and added system interface UI animations.
• Added a send button synchronized with the AI large model reply status, which can be clicked to stop generation.
• Authorized server v4.0: Added support for license update time verification and release version database management.

🔨 Fix

• Fixed the issue of the $ symbol being lost in code within AI large model replies.

[V6.7.4] (Updated on 2025.05.06): Added adaptation for GPT-4o drawing large model, added support for uploading multiple images in dialogue, deeply adapted to support dialogue image preview function, added heartbeat mechanism, etc.

🚀 Feat

• Added adaptation for OpenAI's latest GPT-4o drawing large model function.
• Unified support for OpenAI's official image_url submission format ("image_url", "url" format).
• Added support for uploading multiple images for editing and drawing in large model dialogues.
• Deeply adapted to automatically support image preview function when the API return contains an image format.
• Added support for previewing uploaded images.
• Added support for standard display of mathematical formulas.
• Increased the response timeout for API connections.
• Added a heartbeat mechanism to prevent some API servers from disconnecting prematurely (requires configuration with Nginx).
• Added a function for users with bound model agents to freely switch models.
• Restored the system theme to maintain user preferences even after refreshing the page.
• Added a differential display for the user's currently used model in the lower-left corner.

🔨 Fix

• Fixed the issue of the latest version not supporting streaming replies from large models.
• Fixed the issue where users could not select a large model for new dialogues after activating a custom model agent.

[V6.7.3] (Updated on 2025.04.10): Added latest MJ V7 version painting function, refactored the parameter logic for image-to-image with a reference image, and added Chinese display for MJ painting button operations, etc.

🚀 Feat

• Added the latest MJ V7 version painting function.
• Refactored the parameter logic for image-to-image with a reference image in the painting module.
• Added support for using a character reference image (cref) and a style reference image (sref) simultaneously.
• Added support for displaying MJ painting button operations in Chinese.
• Added a function for users to custom translate painting button operations (defaults to Chinese).
• Added emoji icons for Upscale (Subtle) and Upscale (Creative).
• Optimized global Popover messages with rounded corners, shadows, animations, etc.
• Changed the model selection list icons to be square.

🔨 Fix

• Fixed the issue of inconsistent display styles for the announcement component on different pages (fixed the issue of lost styles for built-in code styles and Markdown content when opened on non-chat pages).

[V6.7.2] (Updated on 2025.03.28): Added multiple backend functions, refactored and optimized the AI voice dialogue interface, added model information display in dialogues; beautified the UI for painting, chat dialogues, and agents, etc.

🚀 Feat

• Added a backend function to one-click clear all failed painting data and long-unfinished painting tasks.
• Added a one-click select/deselect all function for model selection when adding a KEY.
• Masked and hid the API address for non-super administrator logins in the background.
• Masked and hid user order data, distribution data, painting data lists, AI video data user emails, and other information for non-super administrator logins in the background.
• Added a "Go to Painting" button to the parameter control panel on the AI painting mobile H5 end.
• Refactored and optimized the AI voice dialogue function interface.
• Added voice icons and style descriptions to the AI voice selection list, optimized the voice input and text switching experience, and added a voice selection function button on the mobile end.
• Optimized the page style and loading animations for the chat module.
• Added model logos and related model name information to AI model dialogues.
• Optimized the AI model selection pop-up window for oversized or undersized screen ratios that exceed the model selection component, and optimized the model logo size, style, and layout.
• Adjusted the UI style of the AI painting model.
• Added a Popover description for the AI painting module's painting models.
• Added a typewriter output effect for AI agents (including H5 mobile end).
• Optimized the user login interface with icons for different login methods.
• Other miscellaneous optimizations.

🔨 Fix

• None for now.

[V6.7.1] (Updated on 2025.02.09): Added and optimized multiple functions, UI beautification, etc.

🚀 Feat

• Added support for classifying and sorting user dialogue records by time.
• Added support for exporting order data information (Excel file).
• Added support for exporting user data information (Excel file).
• Increased the limit for users to create custom AI agents to 30+.
• Resolved the issue of Alibaba Cloud COS uploaded images not having an https protocol (to avoid front-end cross-domain issues preventing image resources from being displayed).
• Added support for displaying whether an AI agent application is a regular or advanced model type.
• Optimized the user agreement to be checked by default.
• Beautified the AI agent page UI (layout, background color, animations, etc.).
• Optimized the AI painting page.
• Added Popover messages to the top function bar.
• Changed the AI output text to not be bold (to avoid confusion between titles and text).

🔨 Fix

• None for now.

[V6.7.0] (Updated on 2024.11.04): Refactored and added multiple functions, user UI beautification, management end operation UI optimization, etc.

🚀 Feat

• Refactored the painting plaza and its UI.
• Added painting work style classification and backend configuration.
• Added a gallery carousel and backend configuration (can be used for ad space, tutorial documents, events, etc.).
• Added creator function (more features to be added and improved later).
• Added "User Agreement" and "Privacy Policy", which users must read and agree to before registering and logging in.
• Added a function for users to independently bind and change their mobile phone numbers.
• Added a function for users to independently bind and change their WeChat accounts.
• Beautified the user's personal center UI.
• Added animation effects and layout modifications to the Chat homepage interface.
• Modified and beautified various user-end interfaces and optimized the painting interface UI.
• Modified and optimized the user-end theme colors and changed the default theme to "Light Theme".
• Optimized the operation UI of the backend management end.

🔨 Fix

• Fixed the issue of model images in the model selection modal box on the PC end being stretched at different ratios.
• Fixed issues such as misaligned copyright information icons at the bottom of the chat page.

[V6.6.5] (Updated on 2024.08.13): Added a "forgot password" function on the user end, and support for MJ/NIJI V6.1 painting versions.

🚀 Feat

• Added a "forgot password" function on the user end.
• Added support for users to reset their password via SMS verification.
• Added support for users to reset their password via email verification.
• Added support for MJ/NIJI V6.1 painting versions.
• Optimized the max_tokens parameter configuration.

🔨 Fix

• None for now.

[V6.6.4] (Updated on 2024.07.27): Added custom model manufacturer grouping categories, model logo cover configuration, and rewrote the user PC and H5 mobile end model display UI, etc.

🚀 Feat

• Refactored the model query logic and front-end return mechanism.
• Rewritten the user PC and H5 mobile end model display UI (supports displaying model manufacturer grouping categories).
• Added custom model manufacturer grouping category configuration and custom model logo cover upload configuration.
• Added a card page switching animation to the painting module.
• Added red, yellow, and green effect light styles for AI output code.

🔨 Fix

• Fixed the issue of WeChat login accounts not having a "change password" option (requires binding a mobile number to change the password).
• Fixed the error caused by simultaneously uploading a character reference image and a style reference image in MJ painting (currently limited to uploading one type of reference image at a time).

[V6.6.3] (Updated on 2024.07.09): Added support for the AI video generation function module.

🚀 Feat

• Added an independent AI video generation function, supporting text-to-video/image-to-video.
• Added a function to force users registered with WeChat to bind a mobile number (can be freely enabled or disabled in the background).
• Changed the user painting module to automatically pop up the membership package purchase page when there are no painting points.
• Added category icons to the AI agent APP application page.
• Added display of email and mobile numbers in the user's personal center.
• Modified and beautified various page buttons, input boxes, prompts, etc.
• Optimized the file upload component.
• Modified and optimized the viewing permissions for various configurations of the system demo account (admin).

🔨 Fix

• None for now.

[V6.6.2] Update (Updated on 2024.05.21)

🚀 Feat

• Added support for banning and blacklisting users in the background, forcing them to log out.
• Added optimization for uploaded documents to remove spaces from filenames (to solve issues such as the gpt4-all model not being able to recognize files with spaces in their names).
• Proactively optimized the issue of the MJ program callback queue being too low and the MJ API progress notification being inaccurate (to reduce the possibility of slow painting progress notifications and errors caused by setting the notify_pool_size value too low on the MJ side).
• Added an unread marker number reminder for announcements.

🔨 Fix

• Fixed the issue of banned and blacklisted users still being able to check in and use painting, etc., without being actively logged out.
• Fixed the issue of the result image not being displayed in the painting record after Dall-E painting was completed in the background.

[V6.6.1] Update (Updated on 2024.05.14)

🚀 Feat

• Added support for users to custom modify, edit, and delete applications on the user end.
• Added a storage method for original MJ painting images.
• Optimized MJ painting to store both the original thumbnail and the original image simultaneously, using asynchronous storage to reduce the storage time of the original image.
• Added automatic creation of folders by date and time for classified storage when storing painting images in COS object storage (convenient for future selective cleanup).
• Added an env configuration ("URL_TYP" configuration item) for custom configuration of the API file upload Type.
• Optimized the gallery and backend painting records to uniformly load thumbnails, optimizing loading speed. Clicking to enlarge loads the stored original image.
• Used image emoticons for the AI model dialogue and plugin dialogue lists (can be replaced in the public directory).
• Added the ability to directly edit the dialogue list.
• Added a button to display the submission status when submitting a painting.
• Adjusted and optimized the ratio of the menu bar and top bar on the PC end.
• Adjusted the AI question input box on the mobile end to two lines.
• Other optimizations for buttons, icons, etc., and optimized the website loading animation.

🔨 Fix

• Fixed the issue of users being unable to unfavorite applications on the user end.
• Fixed the issue of Chinese appearing when translation was enabled in the English state.

[V6.5.0] Update (Updated on 2024.05.02)

🚀 Feat

• Added MJ painting with a reference image for Character Reference (cref character consistency function) and parameter usage.
• Added MJ painting with a reference image for Style References (sref style consistency function) and parameter usage.
• Added top function information configuration on the PC user end (user communication group entry function). Configuration path: User End Settings -> Top Function Settings -> Top Function Information Configuration. If not configured, it will not be enabled or displayed.
• Added a setting to enable or hide the "Open Membership" entry at the top (synchronized with the mobile end).
• Added optimization so that the check-in entry is not displayed when check-in is closed (synchronized with the mobile end).
• Optimized the display of images in the painting plaza and user-end painting records. Clicking to enlarge an image now loads the image stored in the system's data storage, instead of the original Discord image (if the Discord channel or MJ account is banned by the official, the original image on Discord will be deleted and inaccessible); optimized the loading speed of viewing painting images.
• Optimized and upgraded the "Open Membership" button at the top to a gradient color button; optimized and upgraded the icons for check-in, theme color control, login button, etc.
• Optimized so that when a user inputs Chinese prompts for painting and closes the automatic translation, it will still be translated into English (provided that the MJ painting API has a built-in translation interface).
• Optimized the AI painting page on the mobile end.
• Optimized so that the user's mobile phone number is hidden when a non-super administrator logs in to the management backend.

🔨 Fix

• Fixed the issue of painting prompts and reference image submissions having double quotes at the end, causing the painted images to have text watermarks.
• Fixed the issue of setting a specified homepage not taking effect (for example, specifying painting as the homepage used a lower version of the painting page).

[V6.4.0] Update (Updated on 2024.04.08)

🚀 Feat

• Unlocked the maximum context Token configuration for the model.
• Added a limit on the number of Tokens for a single reply from the question model and a backend configuration (setting it to 0 means adaptive and unlimited).
• Added a feature to not display the password change option on the user end for WeChat logins (the unique credential for WeChat login is the WeChat account, which has no password, so it is not displayed).
• Supported the use of ultra-long context models (for example, for writing novels and modifying ultra-long copy materials).
• Removed the display of the reply completion token for every reply from the model (to avoid ambiguity for users).
• Added a bank card withdrawal channel to the user-end distribution and backend acquisition, and optimized the prompt content (WeChat, Alipay, bank card).
• Modified the AI statement display prompt.
• Changed the backend visual website visitor statistics to a line chart.
• Optimized the license authorization logic.

🔨 Fix

• Fixed the issue of the backend application icon modification being invalid.
• Fixed the issue of point deduction for painting operations. Painting only deducted 2 points, and the value set in the background was invalid.
• Fixed the issue of getting stuck when inputting a large amount of text (for example, the issue of getting stuck when testing with more than 20,000 words in the Claude3 model).

[V6.3.1] Update (Updated on 2024.03.28)

🚀 Feat

• Refactored the voice dialogue logic to fix the issue of being unable to use voice input most of the time.
• Optimized the gallery page, increasing the image size ratio from scaleWidth * 2 to scaleWidth * 3.
• Optimized the painting prompt to prevent other content from being submitted when translating Chinese into English.

🔨 Fix

• Fixed the issue of being unable to use voice input on mobile.

[V6.3.0] Update (Updated on 2024.03.26)

🚀 Feat

• Added display of public security record number and backend configuration item (displays after backend configuration).
• Added display of ICP record number and public security network record standard icons.
• Removed queries for unnecessary tables from databases of older, no-longer-used versions.
• Fixed the issue of MJ local editing and redrawing not displaying the image.

🔨 Fix

• Compatible with SparkAi v5 system upgrade to V6. Code has been optimized for maximum compatibility to retain data from the old system version as much as possible.
• Other page optimizations.

[V6.2.0] Update (Updated on 2024.03.22)

🚀 Feat

• Added the ability to set the default channel for MJ painting in the backend (Fast channel, Relax channel, default channel rules).
• Added support for connecting to a relay system's WeChat public account (requires modifying the WeChat API callback address and configuring the WX_API_BASE= and WX_OPEN_API_BASE= parameters in the .env file).
• Modified the menu bar style (adjusted menu proportions, selection style).
• Modified the system UI theme color.

🔨 Fix

• Fixed the issue of invalid questions caused by the document upload format or request method.
• Other bug fixes.

[V6.1.0] Update (Updated on 2024.03.18)

🚀 Feat

• Fixed WeChat payment amount issue.
• Fixed the issue of custom applications not being able to be unfavorited or edited.
• Added the ability for administrators logged into the user end to select and add GPTs to the system as system applications after a site-wide search.
• Added display of point consumption for using applications.
• Changed the painting window translation to be a persistent modification.
• Changed the painting window optimization to be a persistent modification.
• Added dual channels for MJ painting (supports Fast mode and Relax mode).
• Supports setting separate deduction quotas for dual channels.
• Supports setting separate concurrency for dual channels, which are independent of each other.
• HupiJiao Pay supports calling WeChat Pay in the WeChat environment.

🔨 Fix

• Fixed the issue of gpt dialogue file upload failure due to incorrect file parameter format, which resulted in documents not being recognized.
• Fixed top positioning of application center categories and search misalignment.
• Fixed occasional jumping issue when loading the painting dropdown and optimized some painting logic.
• Fixed the issue of repeated example content in applications.
• Compatible with the issue of inconsistent WeChat payment dependency package versions causing changes in return values.
• Handled the issue of extra points being given when purchasing membership packages.
• Resolved the issue of reference images not working in some scenarios.
• Added h5 parameter to HupiJiao Pay.

[V6.0] SparkAi v6 Major Version

• V6 is a major refactoring, a brand new version merged with other systems, a major system version update.

• 🚀 Feat

• • Added model classification, support for custom model names, custom sorting, model configuration, setting context Token limits and turn limits for individual models, allowing file uploads for the current model, and enabling networking for the current model!
• • 🔥 Added TTS voice, support for voice mode dialogue, automatic playback of voice replies, six different voice options, real-time reading, without taking up storage space!
• • 🔥 Added a plugin system with multiple built-in plugins that can be enabled through configuration. Supports image recognition, PDF document analysis, dialogue-based Midjourney, SD painting, and custom plugin integration with knowledge bases!
• • Added local storage. Files can be directly uploaded to the server instead of COS. For performance reasons, we only open local storage for non-core files. For example, documents, PDFs, images, voice, and other materials generated in chat conversations will be stored locally. Some lower-priority logos, icons, and system presets are also placed locally. For some important data, we still choose to store it in the cloud.
• • Added list layout, with two layout methods that can be switched between.
• • 🔥 Added GPTS applications, support for site-wide search, can get all official existing GPTS and add them directly to the system for use!
• • Applications now support model binding. Applications with bound models cannot switch models, while unbound ones can. GPTs only support the gpt-4-gizmo model!
• • UI update: The overall style has been changed to a card style. The announcement board has been updated, a top bar has been added, dialogue|Gpts groups are isolated, the application center has been changed, GPTS has been merged, and site-wide search has been added.
• • The sidebar has been updated, supporting dual SVG icon configuration for selected and unselected states, dual image configuration, and the use of image links.
• • Layout changes, remaining point balance is independent, chat group clearing, and workbench position migration.
• • The initial welcome page has been changed. The nine-square grid has been changed to random applications and GPTs, and supports random replacement.
• • The toolbar has been merged, with multiple scenarios and multiple linkage settings.
• • The input box supports pasting and uploading files!
• • The login window background image has been changed, a pop-up background image configuration has been added, and custom background images are now supported!
• • Added sending of images and documents, which can be downloaded in the sending section.
• • Added voice sending, which can be paused and continued to organize speech, and supports direct sending during recording.

• 🔨 Fix

• • Fixed the issue of administrator rejections of user-created applications being approved.
• • Fixed the issue of missing characters if the client's network is unstable.
• • Solved the problem of the last two messages in a newly generated dialogue not being able to be deleted.
• • The license has been fully upgraded. The new license will be bound to a domain, and a single license key will only support one domain or IP at a time.
• • Fixed the issue of freezing or unresponsiveness caused by incorrect context settings.
• • Fixed the display error of the inviter, which only showed oneself.
• • Fixed the issue of promotion links not being recognized in WeChat.

  🔨 Improvement