perf(cloud): Smart Placement soak on staging (#15513) - #15521
Merged
Merged
Conversation
Run the API Worker near the origins it fetches (api.cerebras.ai / api.openai.com) instead of near the caller. With pass-through live the preforward gates cost ~91ms warm, but client ttfb is still ~740ms vs 130ms direct — the residual is the Worker->origin network hop Smart Placement exists to remove. Staging-only until the before/after ttfb comparison on api-staging holds; production follows in its own change.
Contributor
|
Claude encountered an error —— View job I'll analyze this and get back to you. |
NubsCarson
moved this from In progress
to Done
in Launch QA — Eliza app + Cloud (#13406)
NubsCarson
moved this from Done
to Needs-agent-verify
in Launch QA — Eliza app + Cloud (#13406)
This was referenced Jul 8, 2026
lalalune
moved this from Needs-agent-verify
to needs-human-verify
in Launch QA — Eliza app + Cloud (#13406)
Member
|
Project 12 agent verification: this staging Smart Placement PR is merged; its source change is present on develop, the subsequent production leg merged in #15551, and the linked issue now records both rollout commits. Moving from Needs-agent-verify to needs-human-verify; only maintainers/board owners should mark Done. [codex-agent] |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Part of #15513 (Fix B from the #15502 decomposition) — staging soak leg.
Summary
placement = { mode = "smart" }on[env.staging]onlyRollout
api-staging.elizacloud.aibefore/after (baseline captured today: warm ~0.75–1.0s ttfb, passthrough engaged). Also sanity-check an app/auth route for regression — placement moves the WHOLE Worker, so client-near routes could see +RTT; the inference-dominant traffic mix should still win.[env.production]in its own one-line change.Rollback = remove the line + redeploy (or
mode = "off").Verification
bunx wrangler deploy --env staging --dry-runparses + bundles clean (16052.92 KiB, same as develop).🤖 Generated with Claude Code