Repository navigation
Conversation
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Hi @nicolargo this is a draft PR with my proposal for implementing the LLM reporter feature (#3448).
I would appreciate a quick architecture feedback before proceeding with the full implementation.
Architectural decision
The original feature requests extending the
alertplugin with an LLM reporter. However, this appears to refer to the v4 architecture. In v5, alerting is a standaloneGlancesAlertsengine (glances/alerts.py), separate from the plugin system.Given this separation in v5, I've implemented the LLM reporter as an independent, opt-in plugin (
llm_reporter). It reads system metrics from the stats store and incorporates active alerts from the alerts engine into its reports. This keeps LLM reporting separate from alert detection and management, while allowing the generated reports to be exposed through the existing plugin infrastructure.**I would like your thoughts on whether a standalone plugin is the preferred abstraction for this feature or whether you prefer a closer integration with the alerts engine in v5.
Any other feedback on the implementation/dependency management is also welcome before I proceed.
Resume