Add per-request AI usage event export proposal - #2424
Open
shiv4289 wants to merge 5 commits into
Open
Conversation
Define an acknowledged, stateless export path for normalized per-request usage events. Co-authored-by: Cursor <cursoragent@cursor.com>
dosubot
Bot
added
the
size:L
shiv4289
changed the title
This was referenced Jul 25, 2026
Explain how other gateways handle spend tracking and keep retries and buffering as future options. Co-authored-by: Cursor <cursoragent@cursor.com>
Group design details under a clear hierarchy and simplify configuration documentation. Co-authored-by: Cursor <cursoragent@cursor.com>
Keep the proposal focused on the Envoy AI Gateway design and its alternatives. Co-authored-by: Cursor <cursoragent@cursor.com>
Signed-off-by: Shivji Kumar Jha <shiv.jha@nutanix.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This PR proposes normalized per-request AI usage event export through an acknowledged HTTP sink. It defines the event schema, configuration, observability, deployment topology, and implementation plan while keeping the gateway stateless and the feature disabled by default.
Related Issues/PRs (if applicable)
Special notes for reviewers (if applicable)
This PR contains the proposal only. Feedback on the sink abstraction, event schema, and synchronous publication trade-off is especially welcome. Given this is my first work in this repo, let me know if there are parts that need more work.