🔥 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!

[V6.9.6 Major Update] (Released on 2026.09.20): Refactored the large-model dialogue architecture with full support for both the OpenAI Chat Completions and Responses endpoints; added multi-type document understanding for official models (based on model capabilities, via the Responses endpoint), a large-model global configuration center, and a login device & remote-login detection system; refactored the points system (detailed records for all model usage: consumption / refunds / no deduction on API model errors); added in-dialogue file preview (PDF/Word/PPT/Excel/Text/Markdown/HTML...); upgraded super/admin remote-session security; frontend UI updates and optimizations...

🚀 Feat (Refactor / New / Adjustment)

• Refactored the large-model dialogue invocation architecture to automatically route between the Chat Completions / Responses endpoints based on model capabilities, with a built-in multi-level automatic fallback retry chain on failure
• Added support for the official OpenAI Responses endpoint: official series that match the rules (GPT / o-series / Codex) use the official file input channel
• Adjusted non-whitelisted models (Claude / Gemini / DeepSeek, etc.) to consistently use Chat Completions, avoiding failures caused by being mistakenly routed to Responses
• Added multi-type document understanding for large models: official models support uploading and recognizing officially supported types such as PDF / Word / PPT / Excel / Text / Markdown / HTML (based on model capabilities; for non-PDF file extraction please choose a GPT model, routed via the Responses endpoint)
• Added multiple document parsing submission forms: URL concatenation / Base64 inline / file link, automatically choosing the best option and falling back based on file size and token limits
• Added a large-model API streaming parameter setting: controls the stream parameter submitted upstream, enabled by default
• Added the "Large Model Global Configuration" center: consolidates global policies such as endpoint routing rules and whether to charge on failure; supports built-in defaults, regex syntax, and real-time testing against model names; changes take effect immediately on save without a restart
• Refactored the user-end points details system: unified presentation of consumption, failure refunds, and failure exemptions for all model usage
• Added a points details system to the admin backend, consistent with user-end account records, supporting filtering and display by recharge type, change category, points category, time range, etc.
• Added a zero-charge mechanism for failed model calls: 4xx / 5xx errors, timeouts, and empty replies do not deduct points (controlled by a switch), with anti-abuse and infinite-retry protection
• Adjusted points settlement and transaction records for dialogue exceptions: failures / interruptions / empty replies are all settled through a single settlement exit, eliminating incorrect and duplicate charges
• Adjusted account change record times to a full date-time format accurate to the second (YYYY-MM-DD HH:mm:ss) for precise reconciliation
• Added a login device & remote-login detection system: records login IP (resolved to carrier and city/district), browser, operating system, and device type; added "Login Devices" to the personal center to view the device, IP (region), login and expiry times, and online status of the last 5 logins
• Added precise online status determination: based on dual verification of server-side session validity and token expiry; only the most recent valid login is shown as "Online", all others are shown as "Offline / Session expired", consistent across the user end and admin backend
• Refactored the super / admin account session security model: super frontend and admin backend sessions are slotted by login IP — the same IP can keep frontend and backend sessions at the same time, while logins from different locations force each other offline and record the IP (so a stolen login is noticed immediately); the user end allows only one device online at a time; the admin demo account supports concurrent multi-device sessions, and admin backend logins are not overridden by frontend logins, making it easy for multiple people to demo the backend together
• Added sensitive information masking: IPs and regions are masked when viewed by demo / non-super-admin accounts (IP keeps the first two segments, region keeps the province with city/district replaced by **), effective on both the user end and admin backend
• Added secure cloud storage uploads: when cloud storage is enabled, uploads go to the cloud, anonymous writes to the local disk are prohibited, and guest uploads are limited by short-term and daily counts and by capacity
• Added file upload type control: officially supported types are shown first, and the server directly rejects script / code files to avoid invalid uploads
• Added in-dialogue file preview (PDF / Word / PPT / Excel / Text / Markdown / HTML): supports online viewing, printing, and downloading, and shows details such as type and size; file tags use unified hover tooltips, with a hover-state corner radius matching the message bubbles; Coze Agent dialogues use the same implementation
• Added a pre-selected model system to the admin backend: updated new-generation models by vendor, including OpenAI / Claude / Gemini (only used for binding key pools, does not affect the model name actually called upstream)
• Added a points consumption column to the admin backend dialogue list: shows the points consumed by each AI reply for easy reconciliation
• Added a "Login IP Records" column to the user data list: shows IP (region) and device identifier with adaptive column width; when there are multiple logins, a "More" button opens a popup with the last 5 full records (device / IP region / login and expiry times / online status), with dark theme support
• Added adaptive flow layout for multiple images in user messages: fixed, constant spacing between images (PC 8px / mobile 4px) and even spacing for any number of images (including odd counts such as 3 or 5); up to 4 per row on PC and 2 per row on mobile, wrapping automatically with the last row centered
• Added multi-image adaptation for different browser zoom levels: when zooming to 110% / 125% / 150% narrows the bubble, the number of images per row is automatically reduced and kept centered, so images no longer overflow or get cropped
• Adjusted the global announcement popup: on mobile the height is dynamically limited by the visual viewport with a smaller vertical footprint, so the close and action buttons are no longer hidden by the browser toolbar (PC layout unchanged); the page background gets a frosted-glass blur when the popup opens; the fade at the bottom of the body text shows/hides dynamically with the scroll position (disappears automatically at the top / bottom); the title is pure black / pure white depending on the theme; unified card corner radius
• Adjusted the top membership card color scheme: changed the purple gradient to a champagne-gold gradient, with the title, subtitle, and action button colors adapted to ensure readability
• Adjusted the unified corner radius standard for popup cards: model marketplace (outer card and inner model cards), package purchase, top points card (including the inner balance card), check-in reward (including the tip card), and global announcement
• Adjusted the system action button color standard: the check-in button, the announcement "Don't show again for a week" button, etc. now use a unified high-contrast black-and-white monochrome style (dark background with light text in light mode, light background with dark text in dark mode), consistent with the model marketplace "Switch / In use" buttons
• Adjusted popup close buttons: check-in, package purchase, login devices, and other popups now use the global rounded "×" close button, with dark theme support
• Added horizontal scroll navigation for package purchase: the package list supports horizontal scrolling with the mouse wheel, plus new left/right "‹ ›" arrow buttons (smooth paging on click, continuous scrolling on hover on PC, automatically grayed out at the edges, automatically hidden when the packages don't overflow), consistent with the model marketplace vendor switcher
• Adjusted the personal center "Login Devices" card: unified card corner radius and close button, device types now use standard monochrome icons, and non-current sessions are uniformly shown as "Offline"
• Adjusted the AI face-swap painting module: images can no longer be uploaded or submitted, as there is currently no relevant API available on the market (globally), and current policies do not allow it
• Other new features, security optimizations, UI improvements, etc.....

🔨 Fix

• Fixed an issue where, in special cases, repeatedly triggered Midjourney / Niji failure callbacks refunded points multiple times; painting task refunds are now idempotent
• Fixed an issue where the global announcement popup's height constraint failed on mobile, with the content nearly filling the whole screen and making the buttons hard to tap
• Fixed an issue where some built-in models had leftover default upstream configurations; the admin backend model configuration is now uniformly authoritative
• Fixed several stability, security policy, and UI detail issues

[V6.9.5] (Released on 2026.08.22): Added a dialogue navigation bar for the chat large-model module, a dialogue demo data feature, and "Gallery Picks / My Paintings" switch tabs with separate loading logic; refactored the personal center page UI; implemented Chinese font subsetting; performance optimizations: optimized for the iOS single-page memory limit, etc.....

🚀 Feat

• Added a dialogue navigation bar to the chat large-model module: automatically enabled when the current dialogue group contains ≥ 3 "user questions"
• Dialogue navigation bar features: collapsed state, expand on hover, text truncation, adaptive + scroll loading, click-to-locate, etc.
• Added a dialogue demo data feature: not restricted by the "System Function Test Demo Site" switch, and can be freely assigned and removed
• Added a "Dialogue Group List" page to the admin backend, allowing any user's dialogue groups to be designated for site-wide demo display (up to 5)
• Demo dialogue groups are visible to all users and read-only, with an orange "Dialogue Demo Data" label in the title; the owner is not restricted, and deleting the group automatically removes the demo designation
• Added "Gallery Picks / My Paintings" switch tabs at the top of the painting list page, with separate loading logic
• Added a switch configuration for the system voice playback feature
• Refactored the personal center page UI with a brand-new card style and animations
• Refactored the painting module operation tips UI
• App plaza cards on mobile changed from three per row to two per row, with the logo and text moderately enlarged (PC unchanged)
• Adjusted professional painting models on mobile: the input box is not focused and the keyboard does not pop up by default when entering the page; after the user taps the input box, it focuses and accepts input normally
• Optimized painting module list positioning: chat-style following — on completion, the list follows the latest result only if the user is "still at the bottom"; if the user has scrolled up to browse, it won't interrupt
• Performance optimization: Chinese font subsetting — a single font weight reduced from 4.2MB → 0.9MB, covering all commonly used Chinese characters; rare characters automatically fall back to system fonts; the original font source is kept as a backup; SEO structure optimization
• Performance optimization: single-page resource download size reduced by about 50%
• Performance optimization: App plaza resources on mobile are loaded in batches, significantly reducing the risk of crashes on low-memory devices
• Other new features, security optimizations, UI improvements, etc.....

🔨 Fix

• Fixed repeated reloading/refreshing when iOS devices (Safari / WeChat / Chrome) accessed the "App Plaza" and hit the iOS single-page memory limit
• Fixed the issue where "Send verification code" was not clickable when reopening the phone number binding popup

[V6.9.4] (Released on 2026.07.27): Added the standalone Nano Banana 2 painting module; refactored the system painting module architecture with an extracted reusable foundation and asynchronous task orchestration; added support for forcing specified users offline; 200% performance optimization for painting submission configuration queries on the submission path; added support for the "System Function Test" feature, etc.....

🚀 Feat

• Refactored the system painting module architecture, extracting a reusable foundation and adding asynchronous task orchestration
• Developed the standalone Nano Banana 2 painting module (gemini-3.1-flash-image, gemini-3-pro-image)
• Admin backend supports custom Nano Banana 2 API integration and custom extended model versions (e.g., adding a custom gemini-3.1-flash-lite-image Banana model)
• Supports text-to-image, reference image painting, custom resolution and aspect ratio, and other parameters
• Supports "Paint the Same" reuse (syncs the prompt, resolution, aspect ratio, and other parameters)
• Nano Banana 2 image editing API supports multiple smart reference images
• Supports base multiplier billing configuration for image editing, and private storage (original images, thumbnails)
• Supports dynamic display of points prices for frontend users, points refund logic for failed paintings, and a scheduled compensation task for Nano Banana 2 paintings
• Optimized the painting VO aggregation API, and added synchronized frontend display of private storage progress status
• Added support for forcing specified users offline
• Added email whitelist configuration (only allow registration from specified email domains; "+" alias emails can also be blocked)
• Sensitive configuration value masking (unified entry point for queries by non-super-admins)
• API address values keep only the protocol + top-level domain suffix; improved masking for keys / tokens
• Added character limit logic for large-model dialogue input submission, with an admin backend configuration switch
• Added composite indexes for painting data to improve query performance
• 200% performance optimization for painting submission configuration queries on the submission path
• Added support for the "System Function Test" feature: when enabled, all users' AI generation requests (dialogue, painting, video, etc.) are blocked at the system level, no upstream large-model APIs are called, and only a demo-site notice is returned. Suitable for scenarios where generative AI filing has not yet been completed, effectively avoiding compliance risks
• Optimized the issue on mobile where prompts could not be entered and submitted again after submitting a painting, preventing post-generation polling scroll from collapsing the input bar
• Other new features, security optimizations, UI improvements, etc.....

🔨 Fix

• Optimized the issue on mobile where prompts could not be entered and submitted again after submitting a painting, preventing post-generation polling scroll from collapsing the input bar

[V6.9.3 Major Update] (Released on 2026.06.23): Major refactor of the GPT-Image-2 painting module, upgraded system risk-control sensitive-word detection, AI large-model dialogue core refactored into decoupled upstream/downstream connections + an asynchronous execution model, end-to-end reliability hardening of the streaming (SSE) pipeline, full persistence of dialogue data, multi-session concurrency isolation, visualization of stopped / abnormal states, system UI refactors and optimizations.....

🚀 Feat

• Refactored the AI dialogue core into an asynchronous execution model, fully decoupling the "backend ↔ large model" upstream connection from the "frontend ↔ backend" downstream connection
• Upstream requests now run independently of the client lifecycle: switching sessions / navigating to other modules / closing the page / exiting the client does not interrupt generation or persistence
• Extended system risk-control sensitive-word detection to the painting module: GPT-Image image generation / image editing is intercepted at the system level before submission
• Extended system risk-control sensitive-word detection to Midjourney / NIJI / DALL-E text-to-image: prompts in the input box are intercepted when they hit sensitive words
• Large-model dialogue now supports native camera photo upload (native camera on mobile + webcam devices on PC)
• Mailer email service now supports configuring whether SMTP uses SSL; if not set, it is determined automatically by port: 465 is true, other ports (e.g., 25/80/587) are false (configured in .env, see the latest .env.example file)
• Adapted to official Claude / GPT-5 / o3 series models, which do not need the temperature parameter, with the frontend disabling it accordingly
• Added custom resolution support to the GPT-Image-2 painting module
• Optimized the GPT-Image-2 painting module to submit the size parameter strictly within the range required by the official API
• Optimized how the GPT-Image-2 painting module displays aspect ratio, resolution, and quality definitions to frontend users, to avoid misunderstandings
• Added GPT-Image-2-Dev painting model integration with separate billing configuration in the admin backend (this model does not support the quality parameter)
• Refactored and optimized GPT-Image-2 painting concurrency limits: supports per-user concurrency and system-wide concurrency
• Added frontend display switch configuration for each painting model (MJ / Niji, Dalle3, GPT-Image-2 related painting models)
• Optimized the GPT-Image-2 painting module: when "Edit Image" is not enabled in the admin backend, painting editing is unavailable on the frontend
• Added handling for GPT-Image-2 reference image painting where oversized images may be blocked by the server or gateway
• Optimized permissions for the system Admin demo-site account viewing backend user data (including AI large-model dialogues, AI painting results, and system resource image URLs): not viewable
• Refactored the model marketplace UI, adding display of model capability descriptions and a latest-model badge
• Implemented a high-fidelity Apple liquid-glass button effect (painting module action buttons, top buttons)
• Painting models now support a painting progress bar and a blurred background image UI at the bottom
• Optimized the user-end UI: action buttons at the bottom of AI large-model reply bubbles changed to icon-only + hover tooltips
• Added sensitive-word detection to the mind map module, reusing the same risk-control pipeline as the dialogue core, validated on submission
• Painting / mind map sensitive-word hits are now handled the same way as in the dialogue module: intercepted upfront, not submitted to the upstream API, no balance check, no charge, instant response
• Added full logging of violation records triggered by sensitive words in painting / mind map; violations by both users and guests are synced to the admin backend "Violation Detection Records"
• Added the OpenAI file protocol parsing method for document files in large-model dialogues (i.e., supports the Chat Completions OpenAI file protocol and URL concatenation for documents)
• Adjusted large-model dialogues to prefer the real usage returned by the upstream SSE; falls back to the original local system estimate when missing
• Adjusted all large-model dialogues to a unified 10-minute timeout (to accommodate Base64 conversion + large request bodies + potentially slow upstream docx/pdf parsing)
• Added a security policy for user file uploads in large-model dialogues (enforced interception): server-executable script extensions are directly rejected by the upload API with a 400 response, preventing webshells from being triggered via reverse access
• Added automatic fallback when uploaded PDF files exceed the size limit (under the OpenAI file protocol)
• Added large-model configuration for extra billing on PDF Base64, and support for setting the maximum document size
• Added upfront interception when AI video (Pika) upstream integration parameters are not configured: uniformly returns "The system has not configured the related large-model feature", without sending a request or charging
• Upgraded streaming responses to incremental persistence, changing from "save once at the end" to "save while generating" during SSE according to a throttling strategy
• Added session resume display: content already received is retained after the client disconnects, and switching back to an in-progress session directly loads that round's snapshot without resending the request
• Added a closed-loop active stop pipeline: clicking "Stop answering" sends an interrupt signal that explicitly cancels the upstream request, stopping losses and saving quota in time
• Added support for saving the partially received content when actively stopped, marked with the "User actively stopped the question" status
• Added a fallback for first-token timeout / empty responses: when the upstream doesn't respond for a long time or the final response is empty, it uniformly falls back to "No data returned / API response timed out" and is persisted
• Added synchronized frontend display of fallback states, preventing dialogue bubbles from being stuck on "Thinking" or blank
• Added full request logging, based on "whether a request was actually sent to the large model": success / timeout / exception / active stop are all guaranteed to have corresponding records in the persistence layer
• Added support for reconciling full logs against upstream API billing (upfront interceptions where "the request was never sent", such as insufficient balance or sensitive words, are excluded)
• Added the dialogue status labels "User actively stopped the question" and "No data returned / API response timed out", shown on both the frontend and admin backend
• Added multi-session concurrency isolation: UI writes from streaming callbacks are validated against the owning session group scope, so asynchronously completed answers do not update a session that is not currently active
• Optimized the recovery logic after leaving a page to idempotent loading (based on persistence-layer snapshots), eliminating duplicate requests
• Other new features, stability enhancements, security optimizations, UI improvements, etc.....

🔨 Fix

• Optimized boundary handling when switching session groups / pages during streaming generation, preventing asynchronously completed answers from being written into other sessions in special cases
• Optimized the recovery mechanism when leaving and returning to a page, preventing duplicate requests or duplicate charges in special cases
• Optimized persistence logic for client interruption scenarios (switching / closing the page / active stop), preventing missing or incomplete dialogue data in extreme cases
• Optimized the fallback display on empty responses / exceptions, preventing dialogue bubbles from being stuck on "Thinking" or blank
• Optimized AI video (Pika) upstream error handling: HTML error pages / API exceptions returned by the channel are no longer passed through to the frontend as-is; they are only logged on the backend and replaced with a friendly message

[V6.9.2] (Released on 2026.05.25): Added the standalone GPT-Image-2 painting module (text-to-image, reference image painting, image editing, custom quality / quantity / aspect ratio and other parameters), custom GPT-Image-2 API integration, custom extended model versions, brand-new reference image upload and UI animations, a website live-stream entry, refactored painting module UI, security optimizations, other new features, various UI improvements...

🚀 Feat

• Developed the standalone GPT-Image-2 painting module
• Supports text-to-image, reference image painting, image editing, custom quality / quantity / aspect ratio and other parameters
• Supports "Paint the Same" reuse (syncs the prompt, aspect ratio, quality, quantity, and other parameters)
• GPT-Image-2 supports online editing of generated painting results, including brush / box-selection editing
• GPT-Image-2 image editing API supports multiple smart reference images (up to 8)
• Admin backend supports custom GPT-Image-2 API integration and custom extended model versions
• Supports billing configuration for quality multipliers (low, medium, high, auto), the base generation multiplier, and the base image editing multiplier
• Billing rule: ceil(base × quality multiplier × quantity)
• Supports private storage (original images, thumbnails)
• Supports dynamic display of points prices for frontend users, and points refund logic for failed paintings
• Supports a scheduled compensation task for GPT-Image-2 paintings
• Refactored the painting module UI
• Brand-new reference image upload UI and animations
• Unified painting VO aggregation API
• Optimized the custom application workbench UI
• Added "One-click cleanup of user-deleted paintings" (soft delete -> physical delete)
• Refactored MJ/Niji instruction integration logic for different reference images (if a reference image is not uploaded, its corresponding -- instruction is not included)
• Added a website live-stream entry, with automatic PC + H5 detection
• Mobile supports URL Scheme invocation code, and an intermediate operation prompt page inside WeChat
• Added support for split-table aggregated queries across painting categories (frontend aggregated API / admin backend split-table and aggregated queries)
• Optimization: when using the official WeChat Pay API, the JSAPI payment flow is only used in "WeChat environment" + "mobile", avoiding the issue where payment was impossible inside the PC WeChat browser
• Optimized admin backend data query performance with millions of dialogue and painting records: concurrent count execution, using RedisCacheService
• Added user snapshot logic triggered by prohibited words in the risk-control module
• Under the PC Notion style, added automatic collapsing of multiple menu bars and an external-open UI indicator
• Fully masked usernames, email addresses, etc. for the admin backend admin demo-permission account
• Added question/reply labels to large-model AI dialogue records
• Other new features, security optimizations, UI improvements, etc.....

🔨 Fix

• Fixed permission issues in some scenarios for preset applications, and the issue where they could not be copied

[V6.9.1] (Released on 2026.04.08): Redis distributed lock optimization for Coze batch Agent import, new system multi-language internationalization (full i18n) + admin one-click AI internationalization, added support for Midjourney latest V8 flagship model painting, login/registration page refactor, security optimizations, other new features, various UI improvements.....

🚀 Feat

• Added Redis distributed lock: when batch importing large amounts of metadata from Coze configuration, prevents duplicate data and optimizes batch import speed and database write performance
• Added system multi-language internationalization (full i18n: not conventional frontend framework fixed-content i18n — supports backend configuration info + backend response info internationalization)
• Supports automatic website language internationalization based on user client access IP + browser default language setting auto-internationalization
• Added one-click AI internationalization for all configuration content in the admin backend
• Added support for Midjourney latest V8 flagship model version painting (development complete; V8 is currently in Alpha stage officially — once officially released and supported by the API, it will be directly available)
• Added support for MJ V8 high-consumption multiplier billing and admin backend settings
• Professional painting module now supports dynamic display of points prices for each painting model and each painting operation
• Refactored login/registration page: brand-new creative animated login interface (built from scratch using native CSS + Vue 3 + Composition API, enhanced creative version)
• Refactored AI large model dialogue attachment upload UI, with upload progress status indicator support
• Optimized app-store Agent backend logic and user-end UI
• Under Notion style, sidebar added "View More Menu" feature
• Added "Ctrl+K / Command (⌘)+K" shortcut for creating new AI conversations
• Model marketplace modal UI optimization, added support for model provider sliding buttons (PC and mobile H5)
• Removed active input outer border display from all system input fields, replaced with tactile shadow effect
• Optimized default first-time light/dark theme logic: prioritizes user PC/mobile device theme color, then falls back to system time (day/night)
• Optimized user registration bonus model points logic with security improvements to prevent attackers from exploiting special methods or scripts to modify bonus amounts
• Admin backend cleanup of failed painting data, long-unfinished painting tasks, and other batch import operations now includes real-time logs, progress logs, and popup UI display
• Added API key pool: delete all key configurations, and batch select and delete API keys features
• Added API key pool: when adding a KEY, select unconfigured key model feature, and added support for displaying the number of keys under that model
• Optimized backend response messages to use friendly user-facing prompts
• Other new features and various UI improvements.....

🔨 Fix

• Fixed the issue where GPTs agents found via full-web API search could not be added if the agent name or description contained emoji characters
• Optimized mobile experience: fixed the issue on iOS + third-party in-app browsers where the bottom input box would be pushed behind the menu bar

[V6.9.0] (Released on 2026.03.01) - Major system refactor version: 2026 full UI overhaul with brand-new card / Notion-style themes, immersion mode, video creation module UI refactor, multiple custom components, MJ painting submission logic optimizations, and many new features, etc.....

🚀 Feat

• 2026 user-end UI major refactor: brand-new card style / Notion-style themes, allowing users to freely switch the UI
• Optimized MJ painting submission logic: when the API submission result is "queued", the backend will no longer treat it as a submission failure exception (it will be treated as successfully submitted)
• Added AI dialogue immersion mode (on PC only the large-model conversation content is shown for a more focused dialogue experience)
• Under the Notion-style UI, unified management of AI dialogue history and application dialogue lists in the sidebar
• Developed a floating side menu bar (effective in AI dialogue immersion mode, automatically displayed when the mouse hovers over the left area)
• Added "Add Menu" feature (left-side menu items can be quickly collapsed/collected via right-click), allowing users to freely remove/collect function modules into "Add Menu"
• Added support in the admin backend for Agent application management to preview Coze Agent persona and reply logic information when editing
• Added support in the painting plaza and video creation module for hovering over video works to auto-preview playback, including video duration and progress bar display
• Brand-new painting input box UI (replicating the Jidmeng AI painting input UI), which automatically expands or collapses based on input status and painting list state (scroll up, scroll down, bottom)
• Adjusted painting scroll positioning logic so that submitting a painting no longer auto-scrolls to the bottom; it only scrolls when the painting status changes
• Refactored the top bar UI with a brand-new, clean layout and design
• Added top-bar model balance cards (related data is loaded on click/hover)
• Added top-bar personal center card (shown on click/hover)
• Personal center card supports displaying points details, membership status, membership expiry time, and membership activation button
• Refactored the video creation module UI and adapted it for mobile H5
• Added a droplet-style switching animation for the bottom menu on mobile
• Brand-new video player component (colors, buttons, layout)
• Refactored the promotion plan page layout (fixed PC-side promotion statistics panel, with the records list on the right scrollable in a table)
• Brand-new model icons (basic model balance, advanced model balance, professional painting balance, Agent points balance)
• Top bar now automatically adapts to different module pages and shows the corresponding model balances
• Brand-new greeting messages and App plaza top-tip typewriter animations
• Optimized AI dialogue module operation button UI
• Refactored AI dialogue module new-conversation page UI, supporting display of the small explanatory text from previous versions
• Added brand-new hover/click animations for the menu bar modules
• Added an "About Us" info button (showing custom official website, user agreement, privacy policy, site information, ICP number, public security record number, etc.)
• Optimized AI Agent module page UI
• Adjusted AI large-model dialogue information (no longer displays the personal avatar)
• Optimized admin backend operation UI
• Other feature additions and optimizations.....

🔨 Fix

• Fixed the issue where MJ painting submissions without a scale value from the frontend would fail to be written to the database and directly report "submit Action task failed..."
• Fixed the issue of Coze Agent dialogues where, in special cases (continuous same-type characters), content overflowed the dialogue background

[V6.8.6] (Updated on 2026.01.08): Major Midjourney HD video feature development, multiple new features, multiple UI refactors, etc.....

🚀 Feat

• Added support for Midjourney HD video with brand-new MJ HD video creation capabilities
• Supports "Animated (High Motion)" and "Animated (Low Motion)" options for already generated images
• Mid`J HD video supports custom creative description prompts (to describe video motions/scenes)
• Mid`J HD video supports user-selectable generation count per request on the frontend (1/2/4)
• Admin backend now supports configuration of Midjourney HD video high-motion and low-motion billing
• Added support for MJ image-to-image tasks with reference images, including uploaded image UI display and preview
• Added support for displaying uploaded image types and reference indices for image-to-image tasks
• Adjusted AI painting module so that DALL·E painting models are integrated into Text-to-Image → Model Selection
• Adjusted and beautified AI painting module UI components
• Adjusted and beautified painting gallery interface: changed work-style classification from looping Buttons to Tabs (dynamically adapting to category count)
• Adjusted and beautified Agent application plaza interface: changed app-style classification from looping Buttons to Tabs (dynamically adapting to category count)
• Adjusted login/registration page so the privacy policy is no longer checked by default; users must actively check it (meets app store review requirements)
• Optimized alignment between file upload preview and dialogue input box
• Refactored PC + mobile H5 login/registration page UI logic and display
• Added support for recommending Mid`J HD video works to the painting gallery plaza for display and playback
• Developed an independent Mid`J HD video player component with a brand-new video player UI
• Supports video task thumbnail originals and private video storage (intelligently choosing storage between local server, Tencent Cloud COS, Alibaba Cloud OSS based on global storage configuration)
• Refactored painting data polling logic (dual-polling design, supports MJ video task polling)
• Refactored private storage behavior for painting data so that, after switching to private thumbnails and originals, the page seamlessly switches without needing a refresh
• Added user painting task status display (in progress, completed, failed) and painting failure reasons (from API responses)
• Added painting module tooltips (Popovers) for the collapse button, model selection, prompt input box, and submit button
• Adapted AI painting module to support Mid`J HD video task status labels and failure reason descriptions
• Optimized compatibility for some animated icons on iOS mobile devices
• Adjusted auto-scroll behavior for painting task lists so that the page only auto-returns to bottom when in-progress tasks change to completed/failed
• Adapted violation word detection records to correctly display guest users and handle operation buttons accordingly
• Other feature additions and optimizations.....

🔨 Fix

• Fixed the Midjourney painting issue where the ordinary reference image --iw parameter value was ignored and added twice
• Fixed the issue where uploading character-consistent reference images for Midjourney painting resulted in invalid API submissions
• Fixed the issue where distribution account bank-card withdrawal channels could not be submitted

[V6.8.5] (Updated on 2025.12.15): Added multiple new features, new user-side and admin-side functions, UI refactoring and UI optimizations.....

🚀 Feat

• Added support for one-click synchronization and batch update of Agent configuration information from Coze platform in admin backend
• Added support for automatic positioning based on model provider classification when switching large models
• AI dialogue module added support for user-side clearing empty content dialogue groups and batch deletion of selected dialogue groups (backend implementation)
• Added support for AI dialogue code file download functionality
• Added support for model marketplace provider Total model quantity statistics display
• Added model provider logo image display and backend configuration (supports quick preset selection, custom upload)
• Added support for AI model logo configuration quick preset selection and custom upload
• Added support for AI dialogue module immersive dialogue mode
• Added support for website information user-side settings (login window image, robot avatar, user default avatar user-side LOGO, gallery carousel settings) custom upload image resource functionality (admin backend)
• Added Agent module dialogue with image data reply click preview functionality
• Added Agent intelligent streaming response intelligent activity timeout mechanism, resets timeout when active, only triggers timeout when completely no data response
• Added delay protection when batch querying coze api workspace contains large batches of Coze Agents, avoiding requests being rate limited due to too fast requests
• Optimized Agent intelligent dialogue SSE format: delta content direct forwarding; removed unnecessary content processing, improved streaming response performance
• Optimized Agent intelligent dialogue real-time streaming return data link loss and confusion issues
• Optimized Agent intelligent streaming response strategy: no restriction on workflow execution time
• Agent intelligent dialogue interface display optimization
• Added website logo and website name bright polish effect
• Refactored and optimized chat dialogue module layout, UI interface, added numerous Popover explanations
• AI dialogue operation configuration bar added quick new dialogue functionality
• Optimized mobile H5 end, when opening model marketplace, keyboard automatically inputs into model search input box issue
• v6.8.5 version: Large model dialogue module route will change from /chat route to /chatai route (original chat route will not fail)
• Other function optimizations.....

🔨 Fix

• Fixed batch import coze agents unable to query imported agents beyond 50 when exceeding 50+
• Fixed Agent intelligent store search functionality, search results cannot display correctly issue

[V6.8.4] (Updated on 2025.11.06): Added support for reasoning chain content (reasoningContent) streaming return and output, refactored AI large model MaxTokens parameter logic, Agent function module optimization, UI adjustments, etc.....

🚀 Feat

• Added support for reasoning chain content (reasoningContent) complete streaming return and output
• Refactored AI large model MaxTokens parameter logic
• MaxTokens parameter logic: when model default value is 0, do not pass MaxTokens parameter to large model; if dialogue group configuration has value, use dialogue group MaxTokens value; other cases use model default value
• Added Agent module dialogue file upload MIME type checking
• Adjusted chat dialogue mobile UI display: large model new dialogue page file upload UI adjustment
• Adjusted chat dialogue mobile UI display: large model new dialogue page input text exceeding one line automatically hides greeting + Hi icon
• Adjusted and optimized mobile operation configuration bar UI display
• Removed frontend right-click menu disable logic
• Optimized Agent list page tag display UI
• Other function optimizations.....

🔨 Fix

• Optimized Agent intelligent dialogue file content scanning and complex security check logic, resolved project restart issues in specific situations

[V6.8.3] (Updated on 2025.09.28): Added numerous new features, function optimizations, UI refactoring, UI optimizations, etc.....

🚀 Feat

• Added SSE streaming response local content deduplication logic (Agent dialogue module updates and optimizations)
• Added SSE streaming response content history tracking mechanism logic (Agent dialogue module updates and optimizations)
• Adjusted and increased timeout Delta streaming response time: supports longer reasoning and thinking time, complex workflows or large data processing situations (Agent dialogue module updates and optimizations)
• Increased cache size to handle longer dialogues and complex content (Agent dialogue module updates and optimizations)
• Added global configuration for large model dialogue user uploaded file storage, supports local storage, Tencent Cloud COS, Alibaba Cloud OSS; supports intelligent degradation
• Added support for setting large model dialogue image parsing methods, original URL format, reverse format Base64Url
• Added support for user model search functionality
• Added support for deep thinking model reasoning chain acquisition (ReasoningContent field data), field storage, frontend adaptation display of ReasoningContent field data, Think tag data adaptation
• Added support for large model single image upload, multiple image upload, deep thinking model settings
• Multiple image upload support: when selected, users can upload multiple images simultaneously, up to 9 images; mainly used to adapt users using GPT-4o-image drawing model multiple image upload, Nano Banana (gemini-2.5-flash-image) and other image generation models.
• Added support for AI dialogue re-editing dialogue functionality
• Added support for user avatar upload functionality, supports JPG, PNG, GIF, WEBP formats
• Supports user avatar real-time preview, image cropping functionality
• Added support for user personal center large model usage total Token query and display
• Adjusted user personal center model total usage times to points usage count
• User-end plugin display supports automatic show/hide based on large model visibility status settings
• Refactored and optimized chat dialogue module UI: new dialogue input box UI, operation configuration bar, file upload, dialogue configuration, voice dialogue function buttons
• User-end AI dialogue history supports more detailed grouping: today, within 7 days, within 15 days, within a month, more than a month ago, earlier, etc.
• Adjusted system UI theme colors, buttons, modal boxes and other styles
• Optimized and adjusted AI dialogue list layout, dialogue bubble UI styles
• Optimized new dialogue page greeting typewriter effect animation
• Refactored mobile H5 menu bar UI: rounded capsule menu bar and animation UI, supports dynamic adaptation of multiple menu bars
• Adjusted and optimized user personal center UI
• Agent list page APP name, description information display optimization, UI layout adjustment
• Added support for AI dialogue module return to dialogue bottom functionality, AI painting module return to dialogue bottom functionality (frosted glass transparent rendering effect)
• Other function optimizations.....

🔨 Fix

• Fixed management backend model usage statistics mouse hover data being blocked by upper part issue
• Fixed mobile H5 menu bar "selected ICON encoding" not taking effect issue

[V6.8.2] (Updated on 2025.08.25): Agent major module development (supports Coze plugins, workflows, functions, knowledge base Agent integration and operation), numerous function refactoring and new updates.....

🚀 Feat

1. Agent Independent Major Module Development

• Supports Coze plugins, workflows, functions, knowledge base Agent integration and operation (dialogue system)
• Supports Agent application real-time streaming response, supports Agent AI thinking process real-time response (dialogue system)
• Supports single Agent application multi-conversation, based on Coze platform's Agent dialogue engine (dialogue system)
• Supports Agent automatic scoring, activity level, popularity (self-developed algorithm)
• Supports Agent real-time response calling models, plugins, workflows (LLM, tools, model inference, Token usage, execution time) response display (dialogue system)
• Supports frontend user adding dialogue, deleting dialogue, clearing dialogue, batch deletion, editing dialogue and other functions (dialogue record management)
• Complete recording: user messages, AI replies, file information, plugin usage, etc. (dialogue record management)
• Supports soft deletion: supports soft deletion and cleanup of dialogue records (dialogue record management)
• Statistical analysis: detailed usage statistics and cost analysis (dialogue record management)
• Agent file flexible storage support selection: local storage, Tencent Cloud COS, Alibaba Cloud OSS (file processing system)
• Agent file storage supports intelligent degradation: automatically degrades to local storage when cloud storage is unavailable
• Multimodal interaction: supports text, images, files, audio, video and other message type processing (file processing system)
• Session persistence: complete dialogue record storage and management (file processing system)
• Supports frontend user text, images, files, audio, video and other file type uploads and dialogue (file processing system)
• Supports frontend user upload files of different Type types with adaptive display of different icon types and file information (file processing system)
• Progress management: real-time upload progress push and query (file processing system)
• Configuration management support: Coze API configuration creation, update, testing and diagnosis (Agent management system)
• Agent batch import support: supports adding single Coze Agent, supports one-click batch import of Agents from Coze platform (Agent management system)
• When importing Coze Agents, automatically privatize download and upload icons (automatically selected according to Agent global configuration Agent file storage), solving official icon failure issues
• Supports frontend user application list page, supports keyword search for Agents (other support)
• Agent recommended question editing support, frontend user quick follow-up question support (other support)
• Supports Agent application link sharing function, WeChat QR code sharing function, dialogue record preview mode, content poster sharing function
• Other Agent module content.....

2. Refactored management backend statistical data, beautified UI

• Added order data statistics, supports data statistics: today's order amount, total order quantity, total order amount
• Added support for 7-day data line chart statistics (new user data, new dialogue data statistics, new painting data statistics, order data statistics)
• Added model usage statistics and display (daily total model usage times, statistics of usage times for each model)
• Added model token usage statistical data (pie chart statistical display)
• Beautified management backend UI interface

3. Added Agent points logic

• Supports Agent dialogue consumption logic, personal center Agent points data display
• Registration, invitation recommendation points logic, check-in function Agent points
• Membership package Agent points, card key system Agent points and other logic

4. Added AI video module announcement configuration and display
5. Added optimized prompt messages, hover tips with frosted glass effect
6. Adapted MJ latest Animate (High motion) animation (high motion), Animate (Low motion) animation (low motion), Remove Background operation display
7. Beautified frontend UI

• Beautified system fonts, buttons, prompt information, announcement components, modal boxes and other styles

8. Other function optimizations...

🔨 Fix

• Fixed personal center background color confusion issue under dark theme

[V6.8.1] (Updated on 2025.08.09)

🚀 Feat

• This update content will be released together with Agent module [v6.8.2]....

[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