yyqdbngt opened a new pull request, #1931: URL: https://github.com/apache/rocketmq-dashboard/pull/1931
## What is the purpose of the change Extend the AI tool catalog with message diagnostics and stop losing LLM generation settings across restarts: - LLM `maxTokens`/`temperature` configured in the settings page were only held in memory; after a restart the defaults were used again. - Operators could not query messages or inspect a message trace through the AI/MCP/CLI tool surface. ## Brief changelog - Persist `maxTokens` and `temperature` in general settings so the LLM config survives restarts. - Add `rmq.message.query`: query messages by topic, message id, key, tag or time range, projecting a safe read-only subset for AI callers. - Add `rmq.message.trace`: return the message trace timeline and consumer status for one message id. - Register both tools in the catalog YAML and cover the handlers, catalog discovery and gateway validation with tests. ## Verifying this change - `mvn -q -Dtest=LlmConfigServiceTest,MessageQueryToolHandlerTest,MessageTraceToolHandlerTest,ToolCatalogTest,ToolGatewayServiceTest test` - `mvn -q test` (1057/1057) - `git diff --check` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
