Artemy Belousov

> Hey @whimo! Any thoughts on @joaomdmoura's suggestion to also update agente attributes? Nothing against it. In fact, we can just update #632 with this and close the 2 PRs...

Hi @gvieira @thehapyone , I've updated this PR with changes from #632. Looking forward to a review.

Hi @gvieira, thanks for the approval, can we merge this now?

Hi @joaomdmoura! Really looking forward to merging this. If you have any questions or concerns, please let us know :) P.S. This change should never break, because AgentExecutor is a...

Here is the code where we think we can insert a track_event call: https://github.com/ShoggothAI/motleycrew/blob/main/motleycrew/caching/http_cache.py#L161 Entry point in case you need to run it: https://github.com/ShoggothAI/motleycrew/blob/main/examples/single_llama_index.py

This looks great, thank you! The only limitation I can think of is that we also support Langchain agents and use Lunary natively with them (no track_event calls). How shall...

Thank you! We'll try it and get back to you

Hi @hughcrt, we ran into a problem with this approach which we didn't realize earlier. When an LLM call is made, we don't know beforehand if the cache will be...

> You only need to send the metadata in the track_event corresponding to the `llm end` event. You would know at that time if it was cached, right? Technically we...

🔥 Looks like what we needed, thank you!