Repository navigation
Conversation
🦋 Changeset detectedLatest commit: 842fb73 The changes in this PR will be included in the next version bump. This PR includes changesets to release 2 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
SimulationRun.JobMetricssays which progression checks the judge flagged (unnecessary_tool_calls,information_loss,redundant_statements,poor_question_quality), but not what the agent actually did wrong. The judge already produces that for every flagged check: a 1–3 rating and 1–2 sentences of evidence citing transcript items. Today it only goes to the simulator's logs.This adds
JobMetrics.progression_findings(field 25). There's oneProgressionFindingper flagged check:check: which of the four it is.severity:MINOR(judge rating 2) orCLEAR(rating 1).evidence: the judge's sentence, citing items as[item_id].citations: the cited items in first-cited order, each with itsitem_id,kind(agent, caller, tool call or tool output) andtext. The dashboard can show what was said without loading the transcript, and link each item into it byitem_id.Additive only; no reader of the existing fields changes.
Consumers: