Skip to content

Conversation

@jinghuan-Chen
Copy link
Contributor

Nice project! It helped me a lot.
The elements of assign_to should contain (child.id, child.end_time).

@ultmaster
Copy link
Contributor

Nice catch! I think FIRST_SIBLING is not covered in regular tests. Would you be willing be add some unit-tests for this?

@jinghuan-Chen
Copy link
Contributor Author

@jinghuan-Chen please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.

@microsoft-github-policy-service agree [company="{your company}"]

Options:

  • (default - no company specified) I have sole ownership of intellectual property rights to my Submissions and I am not making Submissions in the course of work for my employer.
@microsoft-github-policy-service agree
  • (when company given) I am making Submissions in the course of work for my employer (or my employer has intellectual property rights in my Submissions by contract or applicable law). I have permission from my employer to make Submissions and enter into this Agreement on behalf of my employer. By signing below, the defined term “You” includes me and my employer.
@microsoft-github-policy-service agree company="Microsoft"

Contributor License Agreement

@microsoft-github-policy-service agree

@ultmaster
Copy link
Contributor

/ci

@github-actions
Copy link

github-actions bot commented Dec 12, 2025

🚀 CI Watcher for correlation id-3644827761-mj2co7je triggered by comment 3644827761
🏃‍♀️ Tracking 1 workflow run(s):

✅ All runs completed.

response_ids=[2],
response_id="resp-1",
)
reward = make_span(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this reward will always assign to llm-1 regardless of what reward matching policy you have selected.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, you are right. Within the same agent loop, I think FIRST_SIBLING and FIRST_OCCURRENCE should produce the same matching results.If you have any guidance, you can direct me.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think you can move the llm-2 to a time between llm-1 and reward, but llm-2 doesn't live in the same tree as reward.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Good idea! Unit tests have been modified.

@ultmaster
Copy link
Contributor

/ci

@github-actions
Copy link

github-actions bot commented Dec 12, 2025

🚀 CI Watcher for correlation id-3647066662-mj31abe8 triggered by comment 3647066662
🏃‍♀️ Tracking 1 workflow run(s):

✅ All runs completed.

@ultmaster ultmaster merged commit a6078ca into microsoft:main Dec 12, 2025
26 checks passed
@jinghuan-Chen jinghuan-Chen deleted the fix/triplet-assign-to branch December 13, 2025 11:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants