Repository navigation
feat: meter eval gate context by encoded request bytes, drop dead Eval modules - #12
Merged
Merged
Conversation
…l modules contextChars counted the final transcript, missing retries and tool payloads. meteredTlsManagerSettings sums encoded HTTP request-body bytes across every retry instead. GateResult now tags each row with a ContextMetric (LegacyTranscriptChars | EncodedRequestBodyBytes); gateKeysForMetric only resumes runs measured under the current metric, and legacy rows are disclosed rather than silently averaged in. Also drops ~13 Eval.* modules no longer exposed by any component. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
contextCharspriced context growth by a char count of the final transcript, missing retries and tool payloads. Replaced withmeteredTlsManagerSettings, which sums encoded HTTP request-body bytes across every retry.GateResultnow tags each row with aContextMetric(LegacyTranscriptChars|EncodedRequestBodyBytes).gateKeysForMetriconly resumes runs measured under the current metric; legacy rows are excluded from resume and disclosed as "legacy" inrenderCtx/renderGateResultsrather than silently averaged in with the new numbers.Eval.*modules fromsiza-eval.cabalthat were no longer exposed anywhere (Eval.Provider,Eval.Discover,Eval.HoleFit,Eval.Owned,Eval.Repair,Eval.Salvage,Eval.Scaffold, …) — unrelated dead-code cleanup bundled here since it's the same file.Split out of a larger staged diff into an independent PR.
Test plan
cabal buildoneval/neuro-symbolicsucceeds