feat: wire evaluations tracking chain in ManagedModel.run()#1333
Draft
jsonbailey wants to merge 1 commit intojb/aic-2388/js-managed-resultfrom
Draft
feat: wire evaluations tracking chain in ManagedModel.run()#1333jsonbailey wants to merge 1 commit intojb/aic-2388/js-managed-resultfrom
jsonbailey wants to merge 1 commit intojb/aic-2388/js-managed-resultfrom
Conversation
jsonbailey
force-pushed
the
jb/aic-2388/js-managed-result
branch
from
fe6948b to
192315f
Compare
ManagedModel.run() now delegates to aiConfig.evaluator.evaluate() and wraps evaluation + tracker.trackJudgeResult() into a single Promise set on ManagedResult.evaluations. run() returns before evaluations resolves; awaiting evaluations guarantees both evaluation and tracking are complete. Removes evaluations from ChatResponse (moved to ManagedResult). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
jsonbailey
force-pushed
the
jb/aic-1657/js-evaluations-chain
branch
from
4494a66 to
2cad276
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
ManagedModel.run()delegates toaiConfig.evaluator.evaluate()after getting the runner responsetracker.trackJudgeResult()into a singlePromiseset onManagedResult.evaluationsrun()returns beforeManagedResult.evaluationsresolvesevaluationsguarantees both evaluation and tracking are completeevaluationsfromChatResponse(moved toManagedResult)TrackedChatRun.test.tswith tests covering the evaluation chain contractTest plan
run()returns ManagedResult before evaluations resolve🤖 Generated with Claude Code