Skip to main content

Update Log

[1.13.0] - 2025/05/16​

✨ Core Feature Upgrade​

Enhanced Voice Capability for Agent UI Across All Platforms

  • Support switching among 4 scenario-based voice tones (Chat/Reading/Advisory/General)
  • Added support for mute mode playback
  • Mini Program & low-code components now support voice playback speed adjustment
  • Optimized dual-title display logic (hide redundant titles in the content area)
  • Fixed jitter issues in mixed text and image layouts

Agent UI Web Components Capability Expansion

  • Added voice playback feature
  • Support for three types of tool cards including map/weather
  • Fixed several interaction issues

🌐 Expanding Open Capabilities​

MCP Server Template Expansion

  • Tencent Hunyuan 3D MCP: Supports generating 3D models from text/images (MAX/FBX/GLB formats)
  • MarkItDown Service MCP: Enables conversion of any file → Markdown format
  • CRIC Property AI MCP: Integrates dedicated intelligent assistant capabilities for the property management industry

Function-Based Agent Expansion

  • LKE Function-Based Agent Template: Supports integration with large model knowledge engines

🚧 Preview of New Capabilities

  • The Agent interface supports users in independently switching models
  • Optimization of knowledge base search performance and compatibility with multiple file formats
  • Official Accounts/Service Accounts/WeChat Customer Service integration with Function-Based Agent capabilities
  • Agent supports integration with more third-party Agent development platforms
  • Supports one-click conversion of OpenAPI to MCP
  • Provides MCP to connect to third-party knowledge base search and Agent platforms

Features will be released in batches. Please stay tuned for the specific schedule in the version update notifications.

[1.12.0] - 2025/04/29​

✨ Core Feature Upgrade​

Agent supports voice input/output capabilities

With natively integrated voice input/output capabilities for Agents, developers can rapidly build multimodal interaction scenarios:

Agent supports multi-session capabilities

Supports the same Agent instance concurrently handling multiple independent sessions, with each maintaining separate histories

Agent UI Mini Program Component Supports Tool Cards

Agent UI Mini Program source code supports ToolCard tool cards, enabling flexible customization of MCP display effects Can enable custom business logic such as product recommendations or map navigation

⚙️ Developer Experience Improvements​

File Upload Component Security Enhancement

Due to the security policy upgrade in the WeChat Mini Program core library, the file upload feature parsing process may be affected. Developers are advised to upgrade the Agent UI components.

  • Mini Program Source Code Component, please update to the latest version
  • For WeDa Low-Code components, create a new page, then drag and update the agent-ui block, and publish the application upon completion.

🚧 Preview of New Capabilities

  • The Agent interface supports users in independently switching models
  • Optimization of knowledge base search performance and compatibility with multiple file formats
  • Official Accounts/Service Accounts/WeChat Customer Service integration with Function-Based Agent capabilities
  • Agent supports integration with more third-party Agent development platforms
  • Supports one-click conversion of OpenAPI to MCP
  • Provides MCP to connect to third-party knowledge base search and Agent platforms

Features will be released in batches. Please stay tuned for the specific schedule in the version update notifications.

[1.11.0] - 2025/04/17​

✨ Core Feature Upgrade​

  • Supports zero-threshold cloud hosting for MCP Server

    Full support for MCP Servers written in mainstream languages such as Java/Python/GoLang/PHP, with no invasive framework modifications required

    Local MCP Servers can be seamlessly migrated to CloudBase hosting, automatically gaining access to secure and reliable remote MCP services.

  • The CloudBase MCP Marketplace provides a Standardized Listing Process

🌐 Expanding Open Capabilities​

  • The CloudBase MCP Marketplace is now officially available

    CloudBase provides a one-stop MCP Server development and hosting platform, supporting rapid publishing and deployment of MCP Servers.

    Added 30+ standardized service modules, covering mainstream development scenarios:

    DomainRepresentative Service Modules
    AI EnhancementCloudBase AI Capabilities / Memory Module / Meta Component Plugin / Puppeteer Automation
    Data ServicesMongoDB/MySQL/Postgres/Redis Database Access / COS File and Data Processing
    Developer ToolsGithub/Gitee/Gitlab Code Management / Figma Design Collaboration / Apifox API Debugging
    Location & Life ServicesTencent Location Service / Amap / Colorful Cloud Weather / ALAPI Short URL & Hot Data Lists
    Productivity ToolsNotion Knowledge Base / QuickChart Visualization / Mermaid Chart Rendering / Zapier Universal Workflow
    Cloud Native InfrastructureCloudBase Environment Management / Lighthouse Cloud Server / CNB Cloud Native Build / Trends Hub Hotspot Analysis

🚧 Preview of New Capabilities

  • Agent supports session feature
  • Agent voice input and output feature is now available
  • The Agent interface supports users in independently switching models
  • Optimization of knowledge base search performance and compatibility with multiple file formats
  • Official Accounts/Service Accounts/WeChat Customer Service integration with Function-Based Agent capabilities
  • Agent supports integration with more third-party Agent development platforms
  • Supports one-click conversion of OpenAPI to MCP
  • Provides MCP to connect to third-party knowledge base search and Agent platforms

Features will be released in batches. Please stay tuned for the specific schedule in the version update notifications.

[1.10.0] - 2025/03/28​

✨ Core Feature Upgrade: Full Support for MCP​

  • Agent supports the MCP protocol
    MCP Servers can be added to the Agent. The AI can automatically select tools based on task requirements and complete complex operations by invoking tools multiple times.

  • CloudBase supports developing and hosting MCP services
    CloudBase provides a one-stop service from development to deployment, enabling you to host and build your own MCP services on the platform. Provides 6 built-in MCP Server templates

    • CloudBase AI capabilities: Provides CloudBase AI atomic capabilities via the MCP protocol, such as knowledge base search, database query, large model invocation, web search, and image parsing.
    • Yuanqi Plugins: Provides built-in calls to 19 official Tencent Yuanqi plugins, supporting capabilities such as generating images, creating audio, and Sogou search.

  • Yuanqi Agent: Converts Tencent Yuanqi Agent into MCP plugins for use, enabling integration with personal Official Account articles (Yuanqi Agent comes with 100 million tokens built-in).

    • Memory Module: A memory module based on CloudBase database + Knowledge Graph, providing memory capabilities for large models and supporting the storage of user-level information
    • Puppeteer: Can control the Chrome browser to perform operations
    • Blank template: Developers can quickly implement their own MCP Servers, allowing Agents to connect to their own data and features

  • Agent UI Components Upgrade

    • Mini Program Agent supports invoking shared CloudBase environments
    • Added status display for the MCP tool invocation process

🚧 Preview of New Capabilities​

  • Quick import of open-source MCP Servers
  • Agent supports session feature
  • Agent voice input and output feature is now available
  • The Agent interface supports users in independently switching models
  • Optimization of knowledge base search performance and compatibility with multiple file formats
  • Official Accounts/Service Accounts/WeChat Customer Service integration with Function-Based Agent capabilities

Please stay tuned for further announcements regarding the specific launch schedule

[1.9.0] - 2025/03/21​

✨ Core Feature Upgrade​

  • Agent supports image upload, parsing, and Q&A
    Added support for uploading images during conversations, parsing them, and generating AI responses to enhance multimedia interaction capabilities.
  • Agent supports multi-knowledge base selection
    Supports selecting 3 knowledge bases during conversations for comprehensive search, enhancing answer accuracy and information coverage.

⚙️ System Improvements​

  • Knowledge Base Upload and Management Feature Upgrade
    Supports drag-and-drop file upload for more convenient operations. Supports batch upload of up to 200 files Added a batch file deletion feature to enhance management efficiency.

  • Error Handling and Prompt Optimization
    Enhanced error message prompts are provided, offering clear guidance for situations such as Token expiration and service limits being exceeded. Detects the WeCom environment and displays compatibility prompts.

  • Dialogue Processing Logic Enhancement
    Optimized the dialogue logic for the WeChat Official Accounts Platform and fixed the exception of potentially repeating responses to the same query. Refactored the file content parsing interface to resolve timeout issues in complex file parsing.

🌐 Expanding Open Capabilities​

🚧 Preview of New Capabilities​

  • Agents autonomously invoke external tools to implement complex business logic.
  • Agent supports session feature
  • Agent voice input and output feature is now available
  • The Agent interface supports users in independently switching models
  • Optimization of knowledge base search performance and compatibility with multiple file formats
  • Official Accounts/Service Accounts/WeChat Customer Service integration with Function-Based Agent capabilities

Features will be released in batches. Please stay tuned for the specific schedule in the version update notifications.

[1.8.0] - 2025/03/14​

✨ Core Feature Upgrade​

  • Agent supports integration with Cloud Development data models
    Added support for integration with cloud development data models, enabling natural language queries on structured data and generation of AI responses.

  • Agent UI feature optimization, officially open source

⚙️ System Improvements​

  • Integrated Cloud Development extension capabilities for the WeChat Developer Tools IDE Developers can view AI+ usage statistics and develop Agents via Cloud Development - extension feature in the WeChat IDE.

  • Large model usage statistics feature launched
    You can view specific token usage via Development Platform - Package Usage - Resource Dashboard.

  • Agent file upload supports control switch
    Due to the additional large model token consumption caused by file uploads during conversations, a file upload control switch has been added to the Agent. This feature can only be enabled in Entry Edition and above. After the large model resource package is launched, this feature will be made available to Personal Edition.

  • Dialogue Processing Logic Optimization

    • Automatically trims leading and trailing whitespace characters in WeChat dialogue content
    • Cloud-based chat history query scope optimized to the last 1 day, enhancing contextual relevance in conversations

🌐 Expanding Open Capabilities​

🚧 Preview of New Capabilities​

  • Agents autonomously invoke external tools to implement complex business logic.
  • Agent supports image upload on the conversation interface
  • Agent supports session feature
  • Agent voice input and output feature is now available
  • The Agent interface supports users in independently switching models
  • Agent supports integration with multiple knowledge bases
  • Optimization of knowledge base search performance and compatibility with multiple file formats
  • Official Accounts/Service Accounts/WeChat Customer Service integration with Function-Based Agent capabilities

Features will be released in batches. Please stay tuned for the specific schedule in the version update notifications.

[1.7.0] - 2025/03/07​

✨ Core Feature Upgrade​

  • Agent UI document context supports file upload
    Added support for users to upload documents as conversation context during dialogues (This release covers: Mini Program source code components and visually built Web applications; adaptation for visually built mini programs is in development), expanding multimodal interaction scenarios.

  • Cloud Development Environment Resource Sharing
    Supports invoking AI and related resources through shared CloudBase environments within the same account.

  • Mini Program Agent UI Component Experience Optimization Supports text selection and copying, enables dynamic adjustment of input box height based on text content, and exposes more component property configurations.

🌐 Expanding Open Capabilities​

  • Function-Based Agent Provides Standard Interface Documentation The Function-based Agent Framework provides the IBot interface. Developers can deploy corresponding Agents simply by implementing a class that conforms to IBot. For details, refer to the documentation .

  • Agent API Open for Invocation
    Developers can use API Keys to invoke Agent interfaces, enabling automated integration and third-party service connectivity.

  • Custom UI Output Solution
    Adds the capability for Agent to return custom UI structures. Developers can quickly implement personalized interaction designs by following the Documentation Guide.

⚙️ System Improvements​

  • Agent Dialogue Effectiveness Optimization
    Improved the accuracy of online search results, optimized the weight allocation policy for setting information, and enhanced contextual understanding and response relevance.

  • Error Prompts and Process Optimization
    Optimize the experience during Agent setup

🚧 Preview of New Capabilities​

  • Integrate with cloud development databases as a source of structured data, supporting direct referencing in conversations.
  • Agent supports image upload on the conversation interface
  • Agent supports session feature
  • Agent voice input and output feature is now available
  • The Agent interface supports users in independently switching models
  • Agent supports integration with multiple knowledge bases
  • Optimization of knowledge base search performance and compatibility with multiple file formats
  • Official Accounts/Service Accounts/WeChat Customer Service integration with Function-Based Agent capabilities
  • Support viewing large model invocation usage statistics
  • Provides out-of-the-box function-based Agent templates and solutions

Features will be released in batches. Please stay tuned for the specific schedule in the version update notifications.

[1.6.0] - 2025/02/27​

✨ Core Feature Upgrade​

  • Function-Based Agent Launch
    Function-Based Agent is now supported for complex logic development, compatible with open-source Agent frameworks, and capable of integrating with external APIs and diverse data sources, enhancing scalability across multiple scenarios.
  • Hunyuan Turbo S Fast-Thinking Model Launch
    The newly introduced "Hunyuan Turbo S" fast-thinking model achieves near real-time responses (100% faster word generation speed and 44% reduced first-token latency), complementing existing slow-thinking models like DeepSeek-R1.

🎨 Interactive Experience Enhancement​

  • Agent UI Conversation Interface Refresh
    • Refactor Agent UI, optimizing the animation feedback for the "thinking" state and network interactions
    • Historical Conversations: Agent UI adds a historical conversation display feature, supporting retrospective querying.
    • Network Toggle: End users can independently disable the network search feature.
    • Issue Fixes: Resolved the abnormal rendering issue with line breaks in Markdown bold text.

🌐 Expanding Open Capabilities​

  • Knowledge Base Management API
    Developers can use APIs to automate the management of knowledge base documents, supporting features such as creation, deletion, and batch operations. View Documentation.

⚙️ System Improvements​

  • Response Logic Optimization
    Fixed the abnormal behavior of the Agent repeating user questions and the exception of misusing Markdown formatting, enhancing output accuracy.

🚧 Preview of New Capabilities​

  • Supports uploading documents and images on the conversation interface for conversations
  • Supports voice input and output feature
  • The Agent interface supports users in switching models
  • Integrate with cloud development databases as a data source, enabling direct referencing of structured data in conversations.
  • The knowledge base supports automatic synchronization with WeChat Official Accounts
  • Optimize knowledge base search performance
  • Knowledge base supports more file formats
  • Supports invoking the Agent's API via an API key
  • Supports integration of Official Accounts / Service Accounts / WeChat Customer Service, etc. with function-based Agent

Features will be released in batches. Please stay tuned for the specific schedule in the version update notifications.

[1.5.0] - 2025/02/21​

✨ Core Feature Upgrade​

  • Web Search Capability
    Agent now supports integration with large language models (LLMs) like DeepSeek for real-time internet data search
  • Dynamic Model Management
    Added model version control feature, supporting specification of different versions of large models such as DeepSeek-V3.

⚡ Performance Improvement​

  • Document Processing Capability Enhancement
    Knowledge base file capacity has been expanded to 100MB (Markdown files are limited to 10MB)

🌐 Open API​

  • Full API Support
    Added support for HTTP REST API and OpenAI SDK-compatible interface calls.

[1.4.0] - 2025/02/21​

🧠 Model Ecosystem​

  • Added Model Integration
    Added official support for DeepSeek R1 and DeepSeek-V3 large models

🚀 Application Building​

  • Fast Deployment Tool
    Provides an end-to-end AI application publishing feature from dialog flow construction to deployment
  • Interactive Experience Enhancement
    Added a large model conversation real-time preview module to the console.

📱 Cross-Platform Support​

  • Mini Program Integration Solution
    Launch Agent UI component library and industry template suite

[Previous Versions]​

1.3.0​

  • Architecture Upgrade
    WeChat Mini Program basic library integrates native AI SDK

1.2.0​

  • Mini Program Release Compliance Support
    Provides full-process guidance on Mini Program algorithm filing compliance

1.1.0​

  • Development Capabilities Expansion
    • SDK added toolchain invocation support
    • Seamless integration of AI capabilities with Cloud Functions

1.0.0 - Initial Release Version​

  • Basic Capability Building
    • Hunyuan Large Model API Integration
    • Visual Agent Construction Framework
    • WeChat ecosystem multi-platform publishing capability (Mini Programs/Official Accounts/WeCom/Customer Service Systems)
    • RAG Knowledge Base Engine (supports document-based Q&A scenarios)