Repository navigation
bench(dax): declare scoring spec so run summaries carry provider rows - #558
Merged
Merged
Conversation
dax.bench.ts had no scoring config, so each worker's submitted summary contained zero result rows and every merged sandbox-dax-daily run has an empty summary.results[] — the platform leaderboard and the composite benchmark read nothing from it. Score on totalMs with a 5-min ceiling (builds run ~20-150s) and the same median/p95/p99 weights as tti.bench. Co-Authored-By: Noah Kiser <noah@computesdk.com>
Contributor
|
I'll fix CI failures and address comments from users with write access. I'll skip comments containing "(aside)".
|
kisernl
marked this pull request as ready for review
October 27, 2026 13:49
Contributor License AgreementAll contributors are covered by a CLA. |
Contributor
Sandbox Benchmark ResultsBurst
View full run · SVGs available as build artifacts |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Every
sandbox-dax-dailyrun for 2+ weeks merges to an emptysummary.results[]— workers complete (e2b builds 7/7 phases in ~83s, records land intask_results) but each worker's submitted summary carries zero provider rows becausedax.bench.tsnever declared ascoringspec. The platform leaderboard and theprovider-weekly-compositebench both readrun.summary.results, so dax contributes nothing.Adds
scoring.metricsontotalMs(the build's measured duration):ceiling: 300_000ms — dax builds run ~20–150s, so typical providers score ~50–93 rather than clamping at 0 — with the samemedian .60 / p95 .25 / p99 .15weightstti.bench.tsuses.Verified with
bench check:scoringOk: true. From the next daily run onward the run summary will carry per-providercompositeScorerows; earlier windows stay empty (the composite skips missing data rather than zeroing it).Link to Devin session: https://app.devin.ai/sessions/6c1d53718cda4d8d87e45f292b431d89
Open in Devin Desktop: https://app.devin.ai/desktop/session/6c1d53718cda4d8d87e45f292b431d89?variant=devin
Requested by: @kisernl