Skip to content

feat(ai-monitoring): Return gen_ai memory attributes from the conversation endpoint - #126691

Merged
ArthurKnaus merged 1 commit into
masterfrom
arthurknaus/tet-3034-conversation-memory-attributes
Oct 7, 2026
Merged

ArthurKnaus merged 1 commit into
masterfrom
arthurknaus/tet-3034-conversation-memory-attributes

Conversation

@ArthurKnaus

Copy link
Copy Markdown
Member

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.id and gen_ai.memory.record.count. gen_ai.memory.record.count is 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

…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
@linear-code

linear-code Bot commented Oct 7, 2026

Copy link
Copy Markdown

TET-3034

@github-actions github-actions Bot added the Scope: Backend Automatically applied to PRs that change backend components label Oct 7, 2026
@ArthurKnaus
ArthurKnaus marked this pull request as ready for review October 7, 2026 10:28
@ArthurKnaus
ArthurKnaus requested review from a team as code owners October 7, 2026 10:28
Comment on lines +304 to +308
ResolvedAttribute(
public_alias="gen_ai.memory.record.count",
internal_name="gen_ai.memory.record.count",
search_type="integer",
),

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why do we not need to add the other attributes?

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

agree, this shouldn't be needed

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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?

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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.

@ArthurKnaus
ArthurKnaus merged commit 562448e into master Oct 7, 2026
74 checks passed
@ArthurKnaus
ArthurKnaus deleted the arthurknaus/tet-3034-conversation-memory-attributes branch October 7, 2026 13:27
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Scope: Backend Automatically applied to PRs that change backend components

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants