Add rate-limiter package - #7
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
adds a packages/rate-limiter with three primitives for throttling calls to a model provider: a token bucket for smoothing bursts with continuous refill, a sliding-window log that stays exact at the window edge instead of letting 2x through across a boundary, and a FIFO concurrency semaphore for capping in-flight work. all three take an injectable clock so the refill, burst, and concurrency behavior is deterministic in tests rather than leaning on real timers. covers the edge cases too, backward clocks, over-release, multi-unit costs. next step is wiring the bucket into the llm provider so a runaway agent can't blow a per-minute quota.