feat: improve routing latency and provider readiness#111
Open
hankbobtheresearchoor wants to merge 1 commit into
Open
Conversation
- Add routing replay simulator for strategy comparison - Add provider network quality heartbeats and routing penalties - Add Swift provider lifecycle telemetry and capacity fidelity - Tighten first-response deadlines for faster invisible retries - Prewarm standby Swift providers for redundant ready nodes
|
@hankbobtheresearchoor is attempting to deploy a commit to the EigenLabs Team on Vercel. A member of the Team first needs to authorize it. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
rtt_ms,jitter_ms, reconnects, write failures, write latency) and route away from degraded links.active_tokens, pending/active counts, TTFT/total timings).load_modelprewarm hints to cold standby Swift providers so redundant nodes are ready if the primary is not.Why
Goal is OpenRouter-facing sub-5s TTFT even when a selected provider is cold/unhealthy. Swift gets ~3s cold and ~300ms warm, so the coordinator should be the timing authority: quickly retry before writing the HTTP response, penalize bad paths, and keep standby providers warming.
Tests
cd coordinator && go test ./...cd provider-swift && swift test --filter 'NetworkQuality|BatchSchedulerTelemetry|ProtocolTests|CoordinatorClient'cd provider-swift && swift build -c releaseNote: full
swift testhits an existing live MLX/metallib environment failure (Failed to load the default metallib) in live integration tests; focused non-live suites and release build pass.