perf(cloud): Smart Placement on production (#15513 prod leg) - #15551
Merged
Merged
Conversation
Staging soak: mode=smart applied cleanly (verified via the Workers settings API) but staging traffic is too thin for Cloudflare's placement analyzer to qualify it — prod volume is what it learns from. Fail-safe by design: CF only moves execution when its analysis concludes it improves performance for the back-end-heavy inference requests; otherwise requests keep default placement. Rollback = delete the line + redeploy.
Contributor
|
Claude encountered an error —— View job I'll analyze this and get back to you. |
This was referenced Jul 9, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Prod leg of #15513 (nubs green-lit full-send; staging leg #15521 merged earlier tonight).
Soak findings (staging, ~1.5h)
placement: {"mode":"smart"}confirmed applied oneliza-cloud-api-stagingvia the Workers settings APIWhy shipping to prod is safe anyway
Smart Placement is fail-safe by design: Cloudflare runs its analysis and only moves execution when it concludes performance improves for the observed request shape (ours is back-end-heavy: api.cerebras.ai / api.openai.com / Hyperdrive subrequests per turn); requests keep default placement otherwise. Worst case = no change. Expected best case = the residual ~0.5s Worker→origin hop collapses on inference calls.
Verification plan (post-deploy)
Warm ttfb trend on
elizacloud.ai/api/v1/chat/completionsover the next hours (baseline tonight: 0.76–1.1s) + the placement status via the settings API. Rollback = delete the line + redeploy (instant).bunx wrangler deploy --env production --dry-runclean.🤖 Generated with Claude Code