feat(evaluator): add GymRunnerTarget plugin wiring and Studio rendering - #1257
Merged
Conversation
Signed-off-by: Jash Gulabrai <jgulabrai@nvidia.com>
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Enterprise Run ID: 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughThe PR adds ChangesGym evaluation support
Sequence Diagram(s)sequenceDiagram
participant AgentEvalSpec
participant agent_evaluate
participant GymAgentTaskRunner
AgentEvalSpec->>agent_evaluate: Provide GymRunnerTarget
agent_evaluate->>GymAgentTaskRunner: Create GymRuntimeConfig
GymAgentTaskRunner-->>agent_evaluate: Return configured runner
Possibly related PRs
Suggested labels: Suggested reviewers: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
web/packages/studio/src/routes/agents/AgentEvaluationsRoute/AgentEvaluationDetailRoute.test.tsx (1)
87-127: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winAdd a runner-only result test.
Current fixtures always include a native score when runner scores exist. Add a runner-only fixture. Assert the native empty message and the gray runner badge. This verifies both changed branches.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@web/packages/studio/src/routes/agents/AgentEvaluationsRoute/AgentEvaluationDetailRoute.test.tsx` around lines 87 - 127, The existing evaluation tests only cover runner scores alongside a native score; add a runner-only fixture in the test around renderDetail and the agent-evaluation result request. Assert that the native section displays its empty-state message and that the runner section shows the gray runner badge, while preserving the existing runner metric assertions.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Nitpick comments:
In
`@web/packages/studio/src/routes/agents/AgentEvaluationsRoute/AgentEvaluationDetailRoute.test.tsx`:
- Around line 87-127: The existing evaluation tests only cover runner scores
alongside a native score; add a runner-only fixture in the test around
renderDetail and the agent-evaluation result request. Assert that the native
section displays its empty-state message and that the runner section shows the
gray runner badge, while preserving the existing runner metric assertions.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: bc93b92e-ba78-4327-9db7-229b437ae68d
📒 Files selected for processing (10)
plugins/nemo-evaluator/openapi/openapi.yamlplugins/nemo-evaluator/src/nemo_evaluator/jobs/agent_evaluate.pyplugins/nemo-evaluator/src/nemo_evaluator/jobs/agent_spec.pyplugins/nemo-evaluator/src/nemo_evaluator/jobs/result_persistence.pyplugins/nemo-evaluator/tests/jobs/test_publication.pyplugins/nemo-evaluator/tests/test_agent_evaluate.pyplugins/nemo-evaluator/tests/test_result_persistence.pyweb/packages/studio/src/components/evaluation/EvalAggregateScoresTable.tsxweb/packages/studio/src/routes/agents/AgentEvaluationsRoute/AgentEvaluationDetailRoute.test.tsxweb/packages/studio/src/routes/agents/AgentEvaluationsRoute/AgentEvaluationDetailRoute.tsx
Contributor
|
Signed-off-by: Jash Gulabrai <jgulabrai@nvidia.com>
Signed-off-by: Jash Gulabrai <jgulabrai@nvidia.com>
SandyChapman
approved these changes
Aug 12, 2026
SandyChapman
left a comment
SandyChapman
left a comment
Contributor
There was a problem hiding this comment.
This looks good to me!
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
Aug 12, 2026
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
Aug 12, 2026
15 tasks
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
2 participants
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
GymRunnerTargetto the evaluator plugin so Gym evals can run as governed platform jobs with result persistence and Intake publication.runner.gym.*scores in a separate "Runner Scores" section on the Evaluation Details page.Related Issue
GymRunnerTargetviatarget_agent_identity. Before this PR, submitting a Gym job withpublication.intakewould fail at spec validation because the agent name could not be derived from the target.Changes
Backend:
GymRunnerTargetDTO following the same pattern asHarborRunnerTarget; its fields mirrorGymRuntimeConfig1:1 and_resolve_targetmaps them ontoGymAgentTaskRunner._to_runtime_taskto round-trip Gym-specific task data through the plugin's string-only metadata serialization.Frontend: Add
disableScoreColoringprop toEvalAggregateScoresTableand use it to renderrunner.*scores in a separate "Runner Scores" section with gray badges.Type of Change
Quality Gates
Verification
Signed-off-by:traileruv run pre-commit run -apasses, or any blocked checks are identified belowTargeted validation:
End-to-end (AALGO-436 + AALGO-488):
nemo evaluator agent-evaluate submitwith GymRunnerTarget dataset (5 questions, simple_agent, llama-3.1-8b-instruct via NVIDIA Build).End-to-end (AALGO-486):
publication.intakeset to a pre-existing Evaluation (gym-mcqa-eval).gym-mcqa-evalviaSummary by CodeRabbit
New Features
Bug Fixes
Tests