Weave: Group workflow traces under the parent evaluation call #663
Conversation
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
AnuradhaKaruppiah
added
the
DO NOT MERGE
Signed-off-by: Anuradha Karuppiah <[email protected]>
AnuradhaKaruppiah
force-pushed
the
ak-weave-eval-fixes
branch
from
56458f1 to
fb3512e
Compare
Signed-off-by: Anuradha Karuppiah <[email protected]>
AnuradhaKaruppiah
force-pushed
the
ak-weave-eval-fixes
branch
from
513b1c0 to
04ae339
Compare
AnuradhaKaruppiah
added
improvement
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR implements grouping of workflow traces under parent evaluation calls in Weave by introducing a trace context management system. The changes enable better debugging by organizing predictions, scores, and traces hierarchically under each evaluation run.
Key changes:
- Adds evaluation trace context system with Weave-specific implementation
- Integrates trace context into evaluation workflow to group traces under parent evaluation
- Adds task waiting mechanism to ensure trace exports complete before evaluation finishes
Reviewed Changes
Copilot reviewed 6 out of 6 changed files in this pull request and generated 4 comments.
Show a summary per file
| File | Description |
|---|---|
| src/nat/eval/utils/eval_trace_ctx.py | New evaluation trace context classes for framework-agnostic trace coordination |
| src/nat/eval/utils/weave_eval.py | Updated to accept and use trace context for evaluation call propagation |
| src/nat/eval/evaluate.py | Integrated trace context and added export task waiting for local workflows |
| src/nat/builder/workflow.py | Added method to expose all exporters for task waiting |
| src/nat/observability/exporter/base_exporter.py | Made task waiting method public for external access |
| packages/nvidia_nat_weave/src/nat/plugins/weave/weave_exporter.py | Updated comments to reflect new export coordination approach |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
You can also share your feedback on Copilot code review for a chance to win a $100 gift card. Take the survey.
Signed-off-by: Anuradha Karuppiah <[email protected]>
Signed-off-by: Anuradha Karuppiah <[email protected]>
Signed-off-by: Anuradha Karuppiah <[email protected]>
Signed-off-by: Anuradha Karuppiah <[email protected]>
mpenn
approved these changes
Aug 21, 2025
Contributor
mpenn
left a comment
mpenn
left a comment
There was a problem hiding this comment.
Overall, this looks good. Just some minor nitpick comments.
Signed-off-by: Anuradha Karuppiah <[email protected]>
Signed-off-by: Anuradha Karuppiah <[email protected]>
Signed-off-by: Anuradha Karuppiah <[email protected]>
Signed-off-by: Anuradha Karuppiah <[email protected]>
Contributor
Author
|
/merge |
saglave
pushed a commit
to snps-scm13/SNPS-NeMo-Agent-Toolkit
that referenced
this pull request
Sep 2, 2025
…#663) When an Evaluation run is started the eval_call id is pushed to the call stack so subsequent traces can be grouped underneath it. This allows the user to debug the predictions, scores and traces for each run easily. - This PR is a workaround as the eval (score) exporting will be migrated to the observability exporter_manager in the future - This workaround only works for local eval. Remote eval is yet to be solved. - This PR also adds a change to wait on the trace export to finish before finishing the evaluation run <img width="2044" height="907" alt="image" src="https://github.com/user-attachments/assets/4f169a63-7152-4b17-a9ea-bdf6ffda9218" /> ## By Submitting this PR I confirm: - I am familiar with the [Contributing Guidelines](https://github.com/NVIDIA/NeMo-Agent-Toolkit/blob/develop/docs/source/resources/contributing.md). - We require that all contributors "sign-off" on their commits. This certifies that the contribution is your original work, or you have rights to submit it under the same license, or a compatible license. - Any contribution which contains commits that are not Signed-Off will not be accepted. - When the PR is ready for review, new or existing tests cover these changes. - When the PR is ready for review, the documentation is up to date with these changes. Authors: - Anuradha Karuppiah (https://github.com/AnuradhaKaruppiah) Approvers: - Matthew Penn (https://github.com/mpenn) URL: NVIDIA#663 Signed-off-by: Sangharsh Aglave <[email protected]>
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.
Description
When an Evaluation run is started the eval_call id is pushed to the call stack so subsequent traces can be grouped underneath it. This allows the user to debug the predictions, scores and traces for each run easily.
By Submitting this PR I confirm: