feat: export inference and routing observability - #9
Merged
Merged
Conversation
Implements the section 15 metric surface: latency, time-to-first-token, time-per-output-token, token counters, queue and in-flight gauges, routing attribution, fallback frequency, queue-delay prediction error, cache outcomes, and model load duration.
Records routing attribution, queue and in-flight depth, completion latency and tokens, and rejection counts, and serves them from an unauthenticated /metrics endpoint intended for in-cluster scraping.
Confirms a live server publishes routed request counters, latency histograms, token totals, and predicted quality after a real completion.
github-actions
Bot
added
documentation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Implements section 15 of the design specification.
/metricsendpoint served unauthenticated for in-cluster scraping; restrict by network policy.Tests: 7 new unit tests, 3 new integration tests, 1 new Playwright end-to-end test. Local suite 27 passed, 96% branch coverage.