Repository navigation
feat(studio): scores grouped by eval - #747
Merged
Merged
Conversation
#/evals/scores is its own screen now: one row per eval from ?aggregate=eval (pass rate, scores, mean, last seen); expanding a row (open=) loads that eval's rows and shows the pass-rate trend from the eval-level scores (one mean point per bucket), per-check pass rates and the newest failures, each linking to #/traces/<id>?obs=<obs>. Filters eval/agent/source/range live in the query string, defaults unwritten. The daemon-down verdict + retry-while-down is a shared useDaemonDown hook, now used by the Trace, Monitoring and Scores screens. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ned eval The aggregate=eval columns span every check score of an eval, so they read "Score pass rate" / "Mean score" with a tooltip saying so; the expanded panel's per-run figure is labelled "Run pass rate". Switching the expanded eval shows Loading until its own rows land instead of the previous eval's. Co-Authored-By: Claude Opus 5.5 <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Scores get their own screen (#/evals/scores?eval=&agent=&source=&range=): one row per eval with expandable per-check results, a run pass-rate trend and links to each trace.
Ticket: F19 (Forge Observe vs LangSmith evaluation follow-up)
Changes
Verification: focused vitest,
tsc --noEmit, eslint on changed files (details in the review package); full suite and fallow run in CI.🤖 Generated with Claude Code