fix(examples): show LLM-as-judge results for Nova (InspectAI-routed) evaluations#6052
Closed
Hannah14295 wants to merge 1 commit into
Closed
fix(examples): show LLM-as-judge results for Nova (InspectAI-routed) evaluations#6052Hannah14295 wants to merge 1 commit into
Hannah14295 wants to merge 1 commit into
Conversation
LLMAsJudgeEvaluator.show_results() raised '[PySDK Error] Could not extract training job name from pipeline steps' for Nova models even when the eval pipeline succeeded. Nova auto-routes to an InspectAI+Bedrock pipeline whose step is named 'EvaluateWithJudge', not EvaluateCustomModelMetrics / EvaluateBaseModelMetrics, so no job name was found. Fall back to that step; its training job holds the judge results in S3.
Hannah14295
requested a deployment
to
manual-approval
July 17, 2026 23:58 — with 
GitHub Actions
Waiting
GitHub Actions
Waiting
Hannah14295
requested a deployment
to
manual-approval
July 17, 2026 23:59 — with
GitHub Actions
Waiting
GitHub Actions
Waiting
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
LLMAsJudgeEvaluator.show_results() raised '[PySDK Error] Could not extract training job name from pipeline steps' for Nova models even when the evaluation pipeline succeeded. Nova models auto-route to an InspectAI + Bedrock evaluation whose pipeline emits an 'EvaluateWithJudge' step rather than EvaluateCustomModelMetrics / EvaluateBaseModelMetrics, so _show_llmaj_results extracted neither a custom nor base job name and raised.
Fall back to the 'EvaluateWithJudge' step when neither standard step is present; that step's training job holds the judge results (.../EvaluateWithJudge-*/output/output/.../bedrock_llm_judge_results.json).
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.