OceanBase
English日本語简体中文
Docs Home
Products
Integrations
Release Notes

Databases

OceanBase DatabaseOceanBase AI DatabaseOceanBase Cloud OceanBase Best Practices

Tools

OceanBase Cloud PlatformOceanBase Migration ServiceOceanBase Developer CenterOceanBase Migration AssessmentOceanBase Admin ToolOceanBase Loader and DumperOceanBase DeployerKubernetes operator for OceanBaseOceanBase Diagnostic Tool OceanBase Binlog ServiceOceanBase DataPilotOceanBase OAgent

Connectors and Middleware

OceanBase Database Proxy OceanBase Connector/C OceanBase Connector/J OceanBase Connector/ODBC OceanBase Connector/NETOceanBase Command-Line Client

Databases

OceanBase DatabaseOceanBase AI DatabaseOceanBase Cloud OceanBase Best Practices

Connectors and Middleware

OceanBase Database Proxy OceanBase Connector/C OceanBase Connector/J OceanBase Connector/ODBC OceanBase Connector/NETOceanBase Command-Line Client

Tools

OceanBase Cloud PlatformOceanBase Migration ServiceOceanBase Developer CenterOceanBase Migration AssessmentOceanBase Admin ToolOceanBase Loader and DumperOceanBase DeployerKubernetes operator for OceanBaseOceanBase Diagnostic Tool OceanBase Binlog ServiceOceanBase DataPilotOceanBase OAgent
OceanBase DatabaseOceanBase Cloud ToolsConnectors and MiddlewareLifecycle Support Policy

OceanBase OAgent

V2.2.0
  • Product overview
    • What is OAgent?
    • Key features
    • System architecture
    • Use cases
  • Quick start
  • Deployment
  • Overview
  • Sessions and diagnosis
    • Manage sessions
    • Switch dialogue models
    • Use @ to mention the analysis target
    • View the tool invocation process
    • Upload an attachment
    • Data visualization
    • FAQ
    • Export a report
  • Tools
  • Skill Management
  • Channel management
  • Knowledge base
    • Built-in knowledge base
    • Custom knowledge base
  • Scheduled tasks
    • Overview of scheduled tasks
    • Create a scheduled task
  • View usage
  • Model configuration
    • Manage model services
    • Model scoring
  • Settings and security
    • Product management
    • Experimental features
  • Best practices
    • Perform a cluster health inspection
    • Query cluster and topology information
    • Query resource metrics and task status
    • Read-only queries
    • Alert query and troubleshooting guide
    • Root cause analysis of exceptions
    • ASH diagnostic report
    • Analyze slow SQL, TopSQL, and abnormal SQL
    • SQL pre-analysis and tuning recommendations
    • Interpret execution plans
    • Diagnostic information statistics
    • Parameter check and change governance
    • Database change ticket
  • Appendix
    • Feature list
    • Built-in Skills
  • Release notes
    • OAgent V2.2.0 Release note
    • OAgent V2.1.0 Release note
    • OAgent V2.0.0 Release note
    • OAgent V1.8.0 Release note

Download PDF

Document Feedback
  1. Documentation Center
  2. OceanBase OAgent
  3. V2.2.0

OAgent V2.2.0 Release note

Last Updated:2026-11-20 07:25:11

Overview
New features
Member token usage rankings
Native task continuity
OCP log analysis
Inspection plan closed loop and real-time progress
Experience optimization
Inspection, diagnosis, and reporting
Stress test reports and SQL results
Tool discovery and context
SQL tuning and OceanBase knowledge
Knowledge base status
Dialogue and service availability
Bug fixes
Release date: October 26, 2026

Overview

OAgent V2.2.0 is designed for complex database O&M scenarios, with a focus on enhancing inspection, log analysis, and long-running task collaboration capabilities. This version introduces member token usage rankings, native task continuity, OCP log analysis, and a closed-loop inspection plan feature; it also optimizes tool discovery, context usage, multi-cluster inventory, SQL tuning knowledge loading, and the report evidence, streaming response, and standalone knowledge base experience when OCP/OAS is not available.

New features

Member token usage rankings

  • Added a member token consumption ranking on the dashboard, which calculates the total token consumption for members within the selected time range.
  • Supports viewing details such as input, output, cache read, and cache write, and can expand to view all members.
  • When session details are not fully attributed to a member or statistics are incomplete, the page clearly indicates confirmed subtotals, avoiding mistaking incomplete data for a complete cycle's statistics.

Native task continuity

  • Adds structured records for task context, work objectives, constraints, success criteria, current progress, and next steps for complex tasks.
  • Supports resuming unfinished work within the same task, reducing the need to repeatedly describe backgrounds and re-collect information in lengthy conversations.
  • Task context records are bound to tool evidence, preserving verified facts and their sources, facilitating task recovery and subsequent report delivery.
  • Supports checking task status, saving checkpoints, viewing task metrics, and assessing task context quality.

OCP log analysis

  • Introduces OCP log analysis capability, supporting log retrieval by specified log type, host, and query conditions.
  • Supports log sample location, paginated re-reading, and evidence citation. Analysis conclusions are based solely on evidence from the same source returned by the current query.
  • Limits the number of queries, response size, display quota, and evidence save scope to prevent large logs from overwhelming the context.
  • Log evidence is retained during compression, restoration, and follow-up inquiries. When evidence is inaccessible, the budget is exhausted, or the query fails, clear limitations and next-step suggestions are returned.

Inspection plan closed loop and real-time progress

  • Automatically checks OCP self-healing plans associated with alerts during inspections, and includes the plan status in the inspection summary and report.
  • Supports executing eligible self-healing plans after user confirmation. The real-time status is automatically checked after execution.
  • Execution is reported as successful only when the plan status is COMPLETED and the execution result is successful. The true status is retained if it is In Progress, Failed, or Unknown.
  • Inspection metrics support batch collection, and the tool execution progress is displayed in real-time on the page, reducing wait time during long operations.

Experience optimization

Inspection, diagnosis, and reporting

  • Optimized the single-cluster inspection process, reducing duplicate rewriting and repeated querying to improve inspection speed.
  • Reports include a health conclusion, evidence association, and handling suggestions based on observed facts. Content that cannot be verified is clearly marked as unknown.
  • Retains metric accuracy, SQL values, execution plans, and alert facts. The conclusions in the report are consistent with the actual returned evidence.
  • Supports batch inventory across clusters and tenants, simplifying the payload returned by OCP/OAS tools and reducing context truncation and thought loops in multi-cluster scenarios.
  • Verifies facts and evidence scope before report delivery. If report generation fails, retains the collected facts and provides hints for further troubleshooting.

Stress test reports and SQL results

  • Optimized the generation and delivery of performance testing reports. Metrics such as CPU, load, and throughput are collected for clusters, tenants, and complete time windows specified by users. Inspection data is no longer used to replace performance testing data.
  • Distinguished the boundary between "observed load" and evidence of whether the performance test was actually initiated. When data is missing or execution is incomplete, it is clearly marked as unassessed, rather than treating partial results as a complete success.
  • Streamlined fields before inspection results of slow SQL and top SQL enter the model while retaining the top 5; by default, monitoring curves retain window statistics and curve data is passed only when users explicitly request charts.

Tool discovery and context

  • The tool catalog supports on-demand discovery. The model no longer loads all tool definitions in each new session, reducing the context footprint in the initial round.
  • Tool search supports Chinese and English queries and returns matching results based on tool name, description, and capability information.
  • Tool definitions, parameters, and return results are loaded on demand. When a tool call fails, clearer parameter and retry prompts are provided.
  • Streamlined the context for monitoring, logging, and reporting, retaining only the facts, evidence, and delivery information truly needed for the current task.
  • Purged irrelevant skills and tools, reducing unrelated capabilities from entering the context of new sessions and lowering the likelihood of accidental tool selection and waiting times.

SQL tuning and OceanBase knowledge

  • Stably integrated SQL tuning knowledge into OceanBase Agent, which is automatically enabled after an upgrade.
  • SQL tuning suggestions are generated based on collected SQL, DDL, execution plans, and index dependencies, with applicable scope and validation basis retained.
  • Optimized the transmission of SQL analysis pagination, risk classification, numerical metrics, and chart data to avoid losing key facts when simplifying the returned content.
  • Enhanced the analysis and optimization capabilities for slow SQL, top SQL, and execution plans, retaining key SQL numbers, risk classification, and applicable scope.

Knowledge base status

  • Displays the vectorization status of the knowledge base, including statuses such as No Vector Model Configured, Processing, Vector Search Available, and Failed.
  • Supports re-embedding after vectorization fails, facilitating the recovery of the knowledge base's retrieval capability.

Dialogue and service availability

  • When OCP/OAS is not connected, OAgent automatically downgrades to pure knowledge base and general analysis mode: you can still use the built-in knowledge base and analyze SQL, DDL, execution plans, logs, or ASH provided by users. In this mode, OCP/OAS tools are not called, nor is installation or connection to these products required.
  • If the connected OCP/OAS service is temporarily unavailable, steps that depend on this service are skipped. The system continues to use currently available capabilities to answer questions and resumes streaming responses.
  • The model configuration process automatically handles interface compatibility parameters for models such as DeepSeek. No manual modification is needed in the background after configuration is complete.
  • Retains successfully saved configurations on the frontend after a restart or failure recovery. Provides clear feedback on persistent results if saving fails.
  • Optimized the process for task interruption, service restart, and dialogue resumption. After recovery, the correct running state and task ownership are retained.
  • Model selection takes effect per session. After switching or saving the default model, new dialogues use the correct model, and existing sessions are not accidentally switched.
  • Optimized the dialogue input area, tool execution status, and report delivery feedback. After a task is aborted, the tool bar ends correctly and no longer continuously displays a loading status.
  • Unified the layout, font size, spacing, color scheme, and component styles across main pages, and improved the display states for loading, empty data, error prompts, and long content.
  • Optimized the presentation of thought processes, tool calls, and intermediate states to reduce interference from complex process information when reading final results.
  • Hidden navigation entries for pages without accessible content to reduce instances of entering pages with no content or no permission.

Bug fixes

Domain
Fixed issues
Inspection and Reporting
  • Fixed the issue where reports were repeatedly rewritten, queries were duplicated, and health conclusions were missing during single-cluster inspections.
  • Fixed the issues of unverified content referenced in reports, loss of SQL/alarm facts, and inability to continue troubleshooting after a report failed.
  • Fixed the inconsistency between inspection scope, time window, and cross-cluster tenant inventory.
  • Fixed the issues of load test report generation failure, chapter loss, result truncation, and some results being misreported as fully successful.
OCP Log Analysis
  • Fixed incomplete validation of log query conditions, evidence references, and pagination status.
  • Fixed issues where log evidence is lost after compression or restoration, different query evidences are used interchangeably, and empty results are misinterpreted as no exceptions.
  • Fixed the issue where original logs continue to be read when the log response is too large or the quota is exhausted.
Plan Execution
  • Fixed the issue where a plan query failure was incorrectly reported as no plan generated.
  • Fixed the issues of executing a plan without explicit user confirmation, performing duplicate confirmations, and misreporting EXECUTED as successful execution.
  • Fixed the issue where the asynchronous status after plan execution was not promptly rechecked.
Dialogue and Tasks
  • Fixed the issue where the running status, task ownership, or final response is lost during task interruption, service restart, or session recovery.
  • Fixed the issue where model switching affects existing sessions, and new conversations still use the old model after the default model is saved.
  • Fixed the issue where conversations are blocked and streaming responses cannot be resumed when OCP/OAS is unavailable.
  • Fixed the issue where previously saved frontend configurations are lost after OAgent restarts or recovers from a fault.
Tools and Context
  • Fixed the issue where Chinese queries could not be matched during on-demand discovery, and hidden tools could not be correctly invoked.
  • Fixed the issue where key facts or response fields were lost due to tool streamlining, monitoring summary compression, and long-context compression.
  • Fixed the issue where retry prompts were unclear and thought processes became trapped in loops after a tool invocation failed.
User Interface and Deployment
  • Fixed the display misleading issue when member usage statistics were incomplete.
  • Fixed issues where the tool status continued to spin in circles after a task was aborted, historical messages were repeatedly displayed, and report delivery feedback was missing.
  • Fixed the issue where the build version incorrectly displayed the upstream package version and page version information was inconsistent.
  • Fixed the issue where batch user addition failed via HTTP access and the error message was inaccurate.
  • Fixed the issue where parameters such as DeepSeek still required manual modification for API compatibility after configuration.

Previous topic

Built-in Skills
Last

Next topic

OAgent V2.1.0 Release note
Next
on this page
Overview
New features
Member token usage rankings
Native task continuity
OCP log analysis
Inspection plan closed loop and real-time progress
Experience optimization
Inspection, diagnosis, and reporting
Stress test reports and SQL results
Tool discovery and context
SQL tuning and OceanBase knowledge
Knowledge base status
Dialogue and service availability
Bug fixes