cc @limited-student-10747 Re: display LLM profile in the comments from automations Fix: show LLM provenance in automation output Please see below how this looks like, in live tests. I'd love to know if you have concerns about this PR. (Your agent

requested changes

asking for fresh evidence, calling October 5th evidence “historical”. 😅 My agent re-ran them just now, on the 9th, updated the PR description, and the last comment also describes in detail what it did.)

thanks approved!

Just to note, a different question in my mind is that we seem to need to send stuff around in the code quite a bit in order to do something so simple… It feels like it should be simpler, I admit. It might be because automation being so completely separate service… the agent had to send info around quite a lot. 🤔 Maybe we can reconsider the automation design sometime

cc @quick-window-91705, we were just talking about this

I'm thinking it would be ideal if 1. automations service only accepts a plugin + scheduling details (event vs cron) 2. plugin defines the agent profile, llm profile, arbitrary automation code, skills, etc Benefits • all agent specs / automation logic is packaged in one place • updating the automation involves opening a PR to the plugin repo and updating the plugin; changes take effect immediately for future automation runs • no need to maintain our git sync feature to back automations to a separate repo, leverage github natively • easy sharing capability; fork our extensions/marketplace and customize as you feel • one click installs (just post request automation server with the relevant plugin path) Haven't confirmed whether plugins are flexible enough to support all of this yet, just noodling

also very interested in improving the automation quality in openhands