Higress v2.1.5: 41 engine updates + 8 console updates

Higress Community

Jul 23, 2025

Share on X

Higress Engine Update

📋 Overview of This Release

This release includes 41 updates, covering various aspects such as feature enhancements, bug fixes, and performance optimizations.

Distribution of Updates

New Features: 19 items
Bug Fixes: 14 items
Refactoring Optimizations: 2 items
Documentation Updates: 6 items

⭐ Key Highlights

This release includes 2 important updates, which are recommended for special attention:

feat: add DB MCP Server execute, list tables, describe table tools (#2506): By adding these tools, users can more conveniently manage and operate databases, improving system flexibility and usability, making database operations more intuitive and efficient.
feat: advanced load balance policies for LLM service through wasm plugin (#2531): By introducing advanced load balancing strategies, the performance and resource utilization of the LLM service have been enhanced, allowing users to select the most suitable strategy to optimize their services based on their needs.

For detailed information, please check the important feature description section below.

🌟 Important Feature Descriptions

The following are the detailed explanations of important features and improvements in this release:

1. feat: add DB MCP Server execute, list tables, describe table tools

Related PR: #2506 | Contributor: hongzhouzi

Background

In many application development scenarios, developers need to frequently interact with databases, such as executing SQL statements and viewing table structures. The existing MCP server supports basic database query functions but lacks more advanced operation tools. This update adds three tools: execute (execute SQL), list tables (list tables), and describe table (describe table), aiming to meet users' higher demands for database management. Target user groups include but are not limited to database administrators, backend developers, and application developers who frequently interact with databases.

Feature Description

In terms of specific implementation, new database type constants have been introduced by modifying the db.go file, and new tools have been registered in server.go. The new tools implement functionalities for executing any SQL statements, listing all table names, and obtaining detailed information for specific tables. The core technical point lies in using the GORM framework to handle different types of database connections while providing customized SQL querying logic for each database type. Additionally, code changes also involve optimizing the error handling mechanisms, such as unifying the error handling function handleSQLError, improving code maintainability. These improvements not only enrich the feature set of the MCP server but also enhance its applicability across various database environments.

Usage

Enabling these new features is very simple; just ensure that your MCP server configuration includes the correct database DSN and type. For the execute tool, users can execute INSERT, UPDATE, or DELETE operations by sending a request containing the sql parameter; the list tables tool does not require additional parameters and can be called directly to return all table names in the current database; while the describe table tool requires providing a table parameter to specify the table name to view its structure. Typical usage scenarios include but are not limited to: regularly checking database table structure consistency, automating script generation, and validation before and after data migration. It is important to note that when using the execute tool, caution must be exercised to avoid executing commands that may compromise data integrity.

Feature Value

This feature greatly expands the MCP server's application scope in database management, allowing users to complete daily tasks more efficiently. It not only simplifies complex manual operations, reducing the probability of errors, but also provides a solid foundation for building automated operational processes. Especially for projects that need to work across multiple database platforms, this unified and flexible interface design is undoubtedly a boon. Furthermore, by improving the error handling logic and enhancing security measures (such as preventing SQL injection), this PR further ensures the system's stability and security.

2. feat: advanced load balance policies for LLM service through wasm plugin

Related PR: #2531 | Contributor: rinfx

Background

With the widespread application of large-scale language models (LLM), the demand for high performance and high availability has been steadily increasing. Traditional load balancing strategies may not meet these needs, especially when handling a large number of concurrent requests. The new load balancing strategies aim to solve these issues and offer smarter request allocation methods. Target users include enterprises and developers that require high performance and high availability LLM services.

Feature Description

This PR implements three new load balancing strategies: 1. Minimum load strategy, implemented using WASM, suitable for gateway-api-inference-extension; 2. Redis-based global minimum request count strategy, which uses Redis to track and manage the request count of each host, ensuring requests are allocated to the currently least loaded host; 3. Prompt prefix matching strategy, selecting backend nodes based on the prompt prefix, and falls back to the global minimum request count strategy if no match is found. These strategies are implemented through a WASM plugin, providing high scalability and flexibility.

Usage

To enable these load balancing strategies, you need to specify the corresponding strategy type and configuration parameters in the Higress gateway configuration. For example, to enable the Redis-based global minimum request count strategy, you need to set lb_policy in the configuration file to global_least_request and provide the FQDN, port, username, and password of the Redis service. Similarly, for the prompt prefix matching strategy, you need to set lb_policy to prefix_cache and perform corresponding configuration. Best practices involve choosing the appropriate strategy based on the actual application scenario and regularly monitoring and adjusting the configuration to optimize performance.

Feature Value

These new load balancing strategies bring significant performance improvements to LLM services. The minimum load strategy ensures that requests are allocated to the currently least loaded host, thereby improving response speed and resource utilization. The Redis-based global minimum request count strategy further optimizes resource allocation by tracking the request count of each host in real-time. The prompt prefix matching strategy improves processing efficiency through caching and reusing KV cache. These features enhance not only the performance and stability of the system but also the user experience, especially in high-concurrency scenarios.

📝 Complete Change Log

🚀 New Features

Related PR: #2533 Contributor: johnlanni Change Log: Added support for the subPath field, allowing users to configure request path prefix removal rules, and updated both Chinese and English documentation to include instructions for the new features. Feature Value: By introducing the subPath configuration option, the flexibility and customization of the AI proxy plugin have been enhanced, allowing developers to more precisely control the request path handling logic and improve user experience.
Related PR: #2514 Contributor: daixijun Change Log: This PR commented out the default configuration of tracing.skywalking in values.yaml to resolve the problem where configuring other tracing types automatically adds skywalking configuration. Feature Value: By removing unnecessary skywalking configurations, collisions with user-defined tracing settings are avoided by default, enhancing system flexibility and user experience.
Related PR: #2509 Contributor: daixijun Change Log: This PR implements the processing of OpenAI responses interface bodies and adds support for the Volcano Ark large model responses interface by extending the logic in provider/doubao.go. Feature Value: The new functionality enables the system to support more types of AI response processing, particularly for users utilizing the Volcano Ark large model, significantly improving system compatibility and flexibility.
Related PR: #2488 Contributor: rinfx Change Log: Added trace_span_key and as_separate_log_field configuration items, allowing log records and span attribute record keys to differ and permitting log contents to exist as independent fields. Feature Value: By providing more flexible logging and tracking data recording methods, monitoring capabilities of the system are improved, helping developers better understand and optimize application performance.
Related PR: #2485 Contributor: johnlanni Change Log: This PR introduces the errorResponseTemplate feature, allowing the mcp server plugin to customize response content when the backend HTTP status code exceeds 300. Feature Value: This feature enables users to customize error response templates according to actual conditions, enhancing system flexibility and user experience, especially providing a friendlier feedback during exception handling.
Related PR: #2460 Contributor: erasernoob Change Log: This PR modifies the message endpoint sending logic of the SSE server in the mcp-session plugin, making it capable of passing query parameters to the REST API server and URL-encoding the sessionID. Feature Value: By allowing the SSE server to pass query parameters to the REST API server, the flexibility and function integration capabilities of the system are enhanced, enabling users to more conveniently customize service requests.
Related PR: #2450 Contributor: kenneth-bro Change Log: Added stock market MCP Server, integrating the latest real-time market data and constituent stock information in the industry and concept sectors. Feature Value: Provides users with detailed market data analysis tools, helping investors track the performance of industry and concept sectors in real-time, enabling them to make more informed investment decisions.
Related PR: #2440 Contributor: johnlanni Change Log: This PR fixes two issues in Istio and Envoy and adds a new wasm API to support the injection of encoding filter chains during the encodeHeader phase. Feature Value: By resolving issues related to consistent hashing and providing a new API, this update improves system stability and flexibility, allowing users to more finely control the request processing workflow.
Related PR: #2431 Contributor: mirror58229 Change Log: This PR adds default route support for wanx image and video synthesis and updates the related README files to reflect these changes. Feature Value: By introducing default route support, users can more flexibly handle wanx image and video synthesis requests, enhancing system usability and user experience.
Related PR: #2424 Contributor: wydream Change Log: This PR adds support for the OpenAI Fine-Tuning API in the ai-proxy plugin, including path routing, capability configuration, and related constant definitions. Feature Value: By introducing support for the Fine-Tuning API, users can now leverage the service to conduct more advanced model tuning tasks, enhancing system flexibility and functionality.
Related PR: #2409 Contributor: johnlanni Change Log: Introduced a Wasm-Go plugin named mcp-router, supporting dynamic routing for MCP tool requests, including the creation of Dockerfile, Makefile, and related documentation. Feature Value: This plugin allows aggregation of different tools from multiple backend MCP servers through a single gateway endpoint, simplifying multi-service integration and management, enhancing system flexibility and scalability.
Related PR: #2404 Contributor: 007gzs Change Log: This PR adds reasoning_content support to the AI data masking feature and supports returning multiple index groups in requests, enhancing the flexibility and diversity of AI responses. Feature Value: By adding support for reasoning_content and allowing multiple index groups to be returned, users can handle AI response data more flexibly, enhancing application adaptability and user experience in complex scenarios.
Related PR: #2391 Contributor: daixijun Change Log: Adjusted the streaming response structure of the AI proxy, ensuring null output for usage, logprobs, and finish_reason fields to maintain consistency with the OpenAI interface. Feature Value: By ensuring consistency with the OpenAI interface, system compatibility and user experience are improved, making it easier for developers to integrate and use the API.
Related PR: #2389 Contributor: NorthernBob Change Log: This PR enables one-click deployment of the plugin server on Kubernetes and configures the default download URL for the plugin. Changes include the addition and modification of multiple Helm template files to support the plugin server. Feature Value: By supporting one-click deployment on Kubernetes and pre-setting plugin download URLs, the process of deploying and using plugins in K8s environments is simplified, improving usability and efficiency.
Related PR: #2378 Contributor: mirror58229 Change Log: This PR adds support paths for WANXIANG image/video generation in ai-proxy and adds a configuration item in ai-statistics to avoid errors related to OpenAI. Feature Value: Provides users with new image and video generation capabilities while ensuring stability and compatibility through new configuration items, enhancing user experience.
Related PR: #2343 Contributor: hourmoneys Change Log: This PR introduces an AI-based bidding information tool MCP service, including detailed Chinese and English README files and configuration descriptions. Feature Value: The new feature allows users to query bidding information lists through keywords, enhancing the ability of enterprises to acquire projects and clients, providing more comprehensive and precise information support.
Related PR: #1925 Contributor: kai2321 Change Log: This PR implements the AI-image-reader plugin, which connects to OCR services (such as Alibaba Cloud Lingji) to parse image content. New related Go code and documentation in both Chinese and English have been added. Feature Value: This feature enables users to utilize AI technology to automatically read and process the text information in images, enhancing the intelligence level and user experience of the system.

🐛 Bug Fixes

Related PR: #2524 Contributor: daixijun Change Log: This PR fixes the misuse of the stream_options parameter on non-openai/v1/chatcompletions interfaces by limiting its effectiveness only to the specified interfaces to avoid errors. Feature Value: Ensured the correctness of API calls, preventing errors caused by misleading parameters and enhancing system stability and user experience.
Related PR: #2516 Contributor: HecarimV Change Log: This PR enhances the AI Proxy component’s support for system prompts by adding system message handling capabilities to Bedrock API requests, specifically by including a System field in the request body structure and updating the request construction logic to conditionally include the system message. Feature Value: Enhanced AI proxy support for Bedrock services, allowing users to attach system-level directives or information when sending requests, helping to more precisely control the style and direction of generated content, thereby improving user experience and application flexibility.
Related PR: #2497 Contributor: johnlanni Change Log: This PR fixes the decoding behavior when the configured URL path contains URL-encoded parts through modifying the lib-side code. Feature Value: This fix ensures proper decoding when handling request paths that include URL-encoded components, improving system stability and user experience.
Related PR: #2480 Contributor: HecarimV Change Log: This PR fixes a problem with additional request fields for AWS Bedrock support, ensuring that the AdditionalModelRequestFields field is properly initialized to avoid potential null pointer exceptions. Feature Value: By increasing support for additional model request fields, users can more flexibly configure AWS Bedrock services, enhancing the customization capabilities and stability of API calls.
Related PR: #2475 Contributor: daixijun Change Log: Fixed a 404 error problem caused by the incorrect passing of customPath when the openaiCustomUrl configuration points to a single interface with a non-/v1 path. Adjusted request processing logic to ensure compatibility. Feature Value: This fix resolves a 404 error encountered by users under specific conditions, enhancing stability and user experience when using custom OpenAI service paths.
Related PR: #2469 Contributor: luoxiner Change Log: Corrected a problem where excessive logging occurred during the MCP server discovery process when Nacos is unavailable by fixing erroneous log record calls to reduce unnecessary log output. Feature Value: Reduced the amount of logs generated by the system when the Nacos service is unreachable, preventing storage pressure and performance issues caused by rapid log file growth, and enhancing system stability and user experience.
Related PR: #2445 Contributor: johnlanni Change Log: Fixed an issue in which the mcp server did not return the body when returning a status, changing it to respond through SSE; simultaneously refactored makeHttpResponse. Feature Value: This resolves potential errors caused by the absence of a response body, enhancing system stability and user experience by ensuring proper communication between the backend and the frontend.
Related PR: #2443 Contributor: Colstuwjx Change Log: This PR fixes a problem by adding the missing annotations in the controller service account, allowing users to set annotations for the controller service account. Feature Value: This change allows users to configure service accounts more flexibly, for example, by binding AWS IAM roles to service accounts via annotations, allowing authentication for AWS resources.
Related PR: #2441 Contributor: wydream Change Log: This PR unifies the naming conventions for API name constants and corrects mapping errors in the getApiName function, ensuring API requests can properly match. Feature Value: By addressing inconsistencies in API name spelling and formatting, the system's stability and reliability are enhanced, avoiding feature failures or 404 errors due to path inaccuracies.
Related PR: #2423 Contributor: johnlanni Change Log: This PR resolves a potential crash issue in the controller when configuring an SSE forwarding MCP server by modifying related logic in ingress_config.go to prevent exceptions. Feature Value: Fixed potential crash problems in the controller, enhancing system stability and reliability, ensuring users do not encounter service interruptions when using the SSE forwarding feature.
Related PR: #2408 Contributor: daixijun Change Log: Adjusted Gemini API's returned finishReason to lowercase and fixed missing finishReason content in streaming responses to ensure consistency and integrity with the OpenAI API. Feature Value: This fix enhances the compatibility and stability of the API, ensuring that users receive consistent and complete response results when utilizing the Gemini provider, improving user experience.
Related PR: #2405 Contributor: Erica177 Change Log: Corrected the spelling mistake for McpStreambleProtocol to ensure correct protocol support logic, type mapping, and routing rewrite rules. Feature Value: Fixed protocol recognition and mapping issues caused by the spelling error in constant names, enhancing system stability and reliability.
Related PR: #2402 Contributor: HecarimV Change Log: Fixed the Bedrock Sigv4 signature mismatch issue in the AI proxy, improving the modelId decoding logic to avoid potential data contamination risks. Feature Value: This fix enhances system stability, preventing service call failures due to incorrect model ID, thus improving user experience and reliability of the system.
Related PR: #2398 Contributor: Erica177 Change Log: Corrected the spelling error in the McpStreambleProtocol constant from 'mcp-streamble' to 'mcp-streamable' and adjusted related references to ensure consistency and correctness of the protocol name. Feature Value: Fixed potential protocol matching failure or configuration parsing issues due to spelling errors, enhancing system stability and reliability, avoiding service anomalies caused by such simple errors.

♻️ Refactoring Optimizations

Related PR: #2458 Contributor: johnlanni Change Log: This PR updates the wasm-go repository that the mcp server depends on to the latest version and adjusts the dependency paths in the go.mod file to ensure the project uses the latest codebase. Feature Value: Relying on the latest wasm-go repository ensures the project benefits from the latest features and performance optimizations, enhancing system stability and compatibility.
Related PR: #2403 Contributor: johnlanni Change Log: This PR unifies the line break markers in the MCP session filters by modifying two pieces of code in sse.go for consistency. Feature Value: Unifying line break markers can reduce confusion caused by formatting inconsistencies, enhancing code readability and maintainability, making it easier for developers to understand and utilize related functionalities.

📚 Documentation Updates

Related PR: #2536 Contributor: johnlanni Change Log: This PR mainly updates the version number and relevant version information in configuration files in preparation for releasing version 2.1.5. Feature Value: By updating the version number to reflect the latest software status, users can clearly understand the current software version and its stability.
Related PR: #2503 Contributor: CH3CHO Change Log: Fixed a spelling error in the configuration item names in the ai-proxy plugin README, correcting vertexGeminiSafetySetting to geminiSafetySetting. Feature Value: Ensuring documentation accuracy avoids users being unable to set configurations correctly due to configuration item name errors, enhancing user experience and document readability.
Related PR: #2446 Contributor: johnlanni Change Log: Updated the version number to 2.1.5-rc.1 and synchronized the version information in related files, including Makefile, VERSION files, and Helm charts. Feature Value: This PR primarily updates the project's version information, ensuring all relevant configuration files and documentation reflect the latest version number, providing accurate version tracking information for users.
Related PR: #2433 Contributor: johnlanni Change Log: This PR adds both Chinese and English release notes for version 2.1.4 and updates the license configuration file to exclude the release-notes directory. Feature Value: By providing detailed release notes, users can better understand the improvements and issues fixed in the new version, making it easier to adopt and utilize the software's new features.
Related PR: #2418 Contributor: xuruidong Change Log: Fixed a broken link issue in the mcp-servers README_zh.md file, ensuring document link correctness and availability. Feature Value: By fixing erroneous links in the documentation, user experiences while reading and utilizing the documents are enhanced, avoiding information access barriers caused by invalid links.
Related PR: #2327 Contributor: hourmoneys Change Log: This PR mainly updates documents related to mcp-server, including adjustments to README_ZH.md content and the mcp-server.yaml configuration file. Feature Value: By updating the documentation, users can more clearly understand and utilize the mcp-shebao-tools, providing detailed explanations and configuration examples, enhancing user experience.

📊 Release Statistics

🚀 New Features: 19 items
🐛 Bug Fixes: 14 items
♻️ Refactoring Optimizations: 2 items
📚 Documentation Updates: 6 items

Total: 41 changes (including 2 important updates)

Thanks to all contributors for their hard work!🎉

Higress Console Update

📋 Overview of This Release

This release includes 8 updates, covering various aspects such as feature enhancements, bug fixes, and performance optimizations.

Distribution of Updates

New Features: 5 items
Bug Fixes: 2 items
Testing Improvements: 1 item

⭐ Key Highlights

This release includes 1 important update, which is recommended for special attention:

Feature/issue 514 mcp server manage (#530): The newly added mcp server console management feature allows users to more conveniently manage and configure the mcp server through the interface, enhancing user experience and operational efficiency.

For detailed information, please check the important feature description section below.

🌟 Important Feature Descriptions

The following are the detailed explanations of important features and improvements in this release:

1. Feature/issue 514 mcp server manage

Related PR: #530 | Contributor: Thomas-Eliot

Background

In modern microservice architectures, the mcp server, as one of the key components, is responsible for managing communication between services. However, the existing management system lacks centralized management and visual operations for the mcp server, leading to operational personnel needing to manually configure and manage these services, which is inefficient and error-prone. To address this issue, a console management feature for the mcp server has been added, allowing users to easily create, update, delete, and query mcp server instances through a graphical interface. This feature is primarily aimed at system administrators and operational personnel, intending to improve their work efficiency and reduce errors.

Feature Description

The changes mainly implement the following functionalities:

Create mcp server: Users can fill in the necessary parameters through the console interface to create new mcp server instances.
Update mcp server: Users can modify the configuration information of existing mcp servers and save it through the console interface.
Delete mcp server: Users can select the mcp server instances to delete through the console interface and execute the deletion operation.
Query mcp server: Users can query all mcp server instances and their detailed information.

From a technical implementation perspective, RESTful API interfaces have been built primarily using the Spring Boot framework, and Swagger has been used to generate API documentation. The added McpServerController class handles HTTP requests related to the mcp server. Furthermore, modifications have been made to the Dockerfile to include copying and setting permissions for mcp-related tools. Adjustments have also been made to the SDK configuration files to support the new functionalities.

Usage

The methods for enabling and configuring this feature are as follows:

Start the Application: Ensure that the Higress Console application is correctly deployed and running.
Access the Console: Access the Higress Console URL through a browser to enter the console interface.
Create mcp server: In the console, select the "mcp server" tab, click the "Create" button, fill in the necessary parameters (such as name, type, etc.), and then click the "Save" button.
Update mcp server: Find the instance that needs to be updated in the mcp server list, click the "Edit" button, modify the relevant information, and then click the "Save" button.
Delete mcp server: Find the instance to delete in the mcp server list, click the "Delete" button, and confirm the deletion operation.
Query mcp server: View all instances and their detailed information in the mcp server list. Note: Before performing any operations, please ensure data backup to prevent data loss due to erroneous operations.

Feature Value

By adding console management features for the mcp server, users can more conveniently manage and configure mcp server instances, significantly improving system usability and maintainability. Specifically, this feature brings the following benefits:

Improved Efficiency: Users no longer need to manually write configuration files or execute complex command-line operations; management of mcp servers can be completed through a simple graphical interface.
Reduction of Error Rate: The visual operation interface reduces issues caused by manual configuration errors.
Enhanced User Experience: An intuitive operation interface enables users to quickly get started, lowering the learning curve.
Improved System Stability: Unified console management ensures consistency and standardization of configurations, reducing system instability issues due to configuration inconsistencies.

📝 Complete Change Log

🚀 New Features (Features)

Related PR: #540 Contributor: CH3CHO Change Log: This PR adds a new type of LLM provider to the system: vertex, by extending the LlmProviderType enum and adding the VertexLlmProviderHandler class to support the new provider. Feature Value: New support for vertex as an LLM provider will allow users to utilize the services offered by vertex, enriching the system's feature set to meet a wider variety of scenarios.
Related PR: #538 Contributor: zhangjingcn Change Log: This PR introduces errorResponseTemplate support in the mcp-server plugin, allowing users to customize error response templates and correcting documentation regarding error response trigger conditions and GJSON path escaping descriptions. Feature Value: By providing the ability to customize error responses, user experience and flexibility are enhanced, allowing developers to adjust how error information is displayed according to actual needs, thus better controlling application behavior.
Related PR: #529 Contributor: CH3CHO Change Log: New functionality allowing for multiple model mapping rules to be configured for AI routing upstream through popup dialog boxes for advanced configuration editing. Feature Value: Users can manage model mappings for AI services more flexibly, enhancing configuration efficiency and flexibility to meet diverse scenario needs.
Related PR: #528 Contributor: cr7258 Change Log: Changed the default PVC access mode from ReadWriteMany to ReadWriteOnce, which is more suitable for most default settings. Feature Value: This change reduces unnecessary complexity and improves resource utilization efficiency while providing flexibility for users requiring multiple replicas.

🐛 Bug Fixes (Bug Fixes)

Related PR: #537 Contributor: CH3CHO Change Log: Replaced URL.parse with new URL() to resolve compatibility issues in older browser versions. Feature Value: Improved application compatibility across different browser versions, ensuring that a broader user base can effectively use the related functionality.
Related PR: #525 Contributor: NorthernBob Change Log: This PR corrects the spelling errors in the configuration file, changing 'UrlPattern' to 'urlPattern', ensuring consistency in variable naming. Feature Value: By correcting spelling errors, the correctness and consistency of the configuration file are guaranteed, avoiding service configuration problems due to case sensitivity, thereby enhancing system stability and user experience.

🧪 Testing Improvements (Testing)

Related PR: #526 Contributor: CH3CHO Change Log: This PR adds a unit test case to check whether the Wasm plugin image is up to date, implemented by comparing the current image tag with the latest image tag's manifest. Feature Value: This functionality ensures that the image used by the Wasm plugin is always the latest version, thereby improving system stability and security, avoiding security vulnerabilities or other issues caused by outdated images.