Skip to content

Conversation

@andrej1991
Copy link
Collaborator

@andrej1991 andrej1991 commented Nov 4, 2025

By examining the last 100 runs of assisted-chat eval tests in the CI the issue appeared 4 times. The description of the issue:
The LLM asks for cluster ID even if the cluster was created with the previous message in the same conversation.
Example:
Query: Using the ID of the cluster you just created, get the Discovery ISO download URL for cluster 'eval-test-singlenode-d0xsqi07'
Response: I cannot use the cluster name to get the Discovery ISO download URL. I need the cluster ID. The cluster ID is 12e392cb-82e3-43e1-9923-d627b6476f43. Would you like me to get the Discovery ISO download URL for you?

Possible root cause:
a) the resolution logic in lines 125-129 and the instruction in line 124 never said that the model should not verify the cluster ID or any information which can be learned from tool calls with the user after getting it from the tool calls.
b) line 124 instructed the model to acquire the needed information via tool calls without saying where the logic was located. It might caused uncertainity in the model
c) the query includes both cluster ID and cluster name. Having both is clearly redundant, which might cause some confusion.

@openshift-ci
Copy link

openshift-ci bot commented Nov 4, 2025

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: andrej1991
Once this PR has been reviewed and has the lgtm label, please assign omertuc for approval. For more information see the Code Review Process.

The full list of commands accepted by this bot can be found here.

Details Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@coderabbitai
Copy link

coderabbitai bot commented Nov 4, 2025

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

✨ Finishing touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@openshift-ci
Copy link

openshift-ci bot commented Nov 4, 2025

Skipping CI for Draft Pull Request.
If you want CI signal for your change, please convert it to an actual PR.
You can still manually trigger a test run with /test all

By examining the last 100 runs of assisted-chat eval tests in the CI the issue appeared 4 times.
The description of the issue:
  The LLM asks for cluster ID even if the cluster was created with the previous message in the same conversation.
Example:
  Query: Using the ID of the cluster you just created, get the Discovery ISO download URL for cluster 'eval-test-singlenode-d0xsqi07'
  Response: I cannot use the cluster name to get the Discovery ISO download URL. I need the cluster ID. The cluster ID is 12e392cb-82e3-43e1-9923-d627b6476f43. Would you like me to get the Discovery ISO download URL for you?

Possible root cause:
  a) the resolution logic in lines 125-129 and the instruction in line 124 never said that the model should not verify the cluster ID or any information which can be learned from tool calls with the user after getting it from the tool calls.
  b) line 124 instructed the model to acquire the needed information via tool calls without saying where the logic was located. It might caused uncertainity in the model
  c) the query includes both cluster ID and cluster name. Having both
is clearly redundant, which might cause some confusion.
@carbonin
Copy link
Collaborator

carbonin commented Dec 4, 2025

@andrej1991 do you want to continue work on this? Is it still needed?

@openshift-merge-robot
Copy link

PR needs rebase.

Details

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants