Repository navigation
feat(ai-monitoring): Return gen_ai memory attributes from the conversation endpoint - #126691
Merged
ArthurKnaus merged 1 commit intoOct 7, 2026
Merged
Conversation
…ation endpoint Add the memory summary attributes (store id, query text, record id and record count) to the spans returned by the AI conversation details endpoint, so the conversation timeline can show memory operations without a per-span attribute fetch. Register gen_ai.memory.record.count as an integer EAP attribute so it comes back as a number; the string fields resolve dynamically. Part of TET-3034
ArthurKnaus
marked this pull request as ready for review
October 7, 2026 10:28
shellmayr
reviewed
Oct 7, 2026
Comment on lines
+304
to
+308
| ResolvedAttribute( | ||
| public_alias="gen_ai.memory.record.count", | ||
| internal_name="gen_ai.memory.record.count", | ||
| search_type="integer", | ||
| ), |
Member
There was a problem hiding this comment.
Why do we not need to add the other attributes?
Member
There was a problem hiding this comment.
agree, this shouldn't be needed
Member
Author
There was a problem hiding this comment.
we needed it in the past for charts to return the right data type via the timeseries endpoint.
Is that not a thing anymore / utilizing conventions?
Member
Author
There was a problem hiding this comment.
Maybe I am wrong, but from what I saw non-string attributes still need this, and in fact it fails atm without it.
The related conventions are not released yet. Once they are I will follow-up on this.
shellmayr
approved these changes
Oct 7, 2026
vgrozdanic
approved these changes
Oct 7, 2026
ArthurKnaus
deleted the
arthurknaus/tet-3034-conversation-memory-attributes
branch
October 7, 2026 13:27
This was referenced Oct 15, 2026
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.
Adds the memory summary attributes to the spans returned by the AI conversation details endpoint, so the conversation timeline can render memory operations without a per-span attribute fetch.
Each span now carries
gen_ai.memory.store.id,gen_ai.memory.query.text,gen_ai.memory.record.idandgen_ai.memory.record.count.gen_ai.memory.record.countis registered as an integer EAP attribute so it comes back as a number; the string fields resolve dynamically like the other gen_ai span attributes.Backend only, lands before the timeline frontend. The records payload is not added here, the span detail pane reads it from the per-span trace-item-details fetch.
Part of TET-3034